ce75cd14ee
Model: fpadovani/dan-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed3407 Source: Original Platform
96211 lines
2.6 MiB
96211 lines
2.6 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 4.009355162044771,
|
|
"eval_steps": 3000,
|
|
"global_step": 48000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 6.974994325637818,
|
|
"epoch": 0.000417641162712997,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.6015,
|
|
"mean_token_accuracy": 0.10177180394530297,
|
|
"num_tokens": 9371.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.047821569442749,
|
|
"epoch": 0.000835282325425994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.6893,
|
|
"mean_token_accuracy": 0.10747795924544334,
|
|
"num_tokens": 18155.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.001016473770141,
|
|
"epoch": 0.001252923488138991,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.6687,
|
|
"mean_token_accuracy": 0.0982088290154934,
|
|
"num_tokens": 27776.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.041731929779052,
|
|
"epoch": 0.001670564650851988,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.6699,
|
|
"mean_token_accuracy": 0.10469619780778885,
|
|
"num_tokens": 37166.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.000826597213745,
|
|
"epoch": 0.002088205813564985,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.618,
|
|
"mean_token_accuracy": 0.10739438831806183,
|
|
"num_tokens": 46667.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.009681844711304,
|
|
"epoch": 0.002505846976277982,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.6186,
|
|
"mean_token_accuracy": 0.10922864452004433,
|
|
"num_tokens": 55738.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.123480558395386,
|
|
"epoch": 0.002923488138990979,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.7494,
|
|
"mean_token_accuracy": 0.1005694568157196,
|
|
"num_tokens": 65303.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.074628782272339,
|
|
"epoch": 0.003341129301703976,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.5241,
|
|
"mean_token_accuracy": 0.11036743149161339,
|
|
"num_tokens": 74876.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.085372972488403,
|
|
"epoch": 0.003758770464416973,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.6515,
|
|
"mean_token_accuracy": 0.11546419188380241,
|
|
"num_tokens": 84683.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.120099067687988,
|
|
"epoch": 0.00417641162712997,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.6524,
|
|
"mean_token_accuracy": 0.10372202694416047,
|
|
"num_tokens": 94511.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.116729831695556,
|
|
"epoch": 0.004594052789842967,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.6418,
|
|
"mean_token_accuracy": 0.11203298419713974,
|
|
"num_tokens": 103820.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.081749200820923,
|
|
"epoch": 0.005011693952555964,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.6178,
|
|
"mean_token_accuracy": 0.10972007438540458,
|
|
"num_tokens": 112398.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.064388227462769,
|
|
"epoch": 0.005429335115268961,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.5782,
|
|
"mean_token_accuracy": 0.11708607077598572,
|
|
"num_tokens": 121167.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.080944776535034,
|
|
"epoch": 0.005846976277981958,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.596,
|
|
"mean_token_accuracy": 0.11205784305930137,
|
|
"num_tokens": 129399.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.128628587722778,
|
|
"epoch": 0.006264617440694955,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.5887,
|
|
"mean_token_accuracy": 0.10802783071994781,
|
|
"num_tokens": 138512.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.073452806472778,
|
|
"epoch": 0.006682258603407952,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.6437,
|
|
"mean_token_accuracy": 0.10293481424450875,
|
|
"num_tokens": 147712.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.0505595207214355,
|
|
"epoch": 0.007099899766120949,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.6094,
|
|
"mean_token_accuracy": 0.11598187386989593,
|
|
"num_tokens": 156759.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.033814144134522,
|
|
"epoch": 0.007517540928833946,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.6423,
|
|
"mean_token_accuracy": 0.10784239917993546,
|
|
"num_tokens": 166395.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.128949785232544,
|
|
"epoch": 0.007935182091546943,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.5776,
|
|
"mean_token_accuracy": 0.11605502218008042,
|
|
"num_tokens": 174739.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.042219877243042,
|
|
"epoch": 0.00835282325425994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.4709,
|
|
"mean_token_accuracy": 0.11599281206727027,
|
|
"num_tokens": 183010.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 6.9831122875213625,
|
|
"epoch": 0.008770464416972937,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.6344,
|
|
"mean_token_accuracy": 0.1058510735630989,
|
|
"num_tokens": 192589.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.014032506942749,
|
|
"epoch": 0.009188105579685933,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.5731,
|
|
"mean_token_accuracy": 0.11620197221636772,
|
|
"num_tokens": 201638.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.060356569290161,
|
|
"epoch": 0.00960574674239893,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.4989,
|
|
"mean_token_accuracy": 0.11458343639969826,
|
|
"num_tokens": 209862.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.0534099578857425,
|
|
"epoch": 0.010023387905111928,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.6346,
|
|
"mean_token_accuracy": 0.10284667909145355,
|
|
"num_tokens": 218897.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.093526840209961,
|
|
"epoch": 0.010441029067824925,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.6924,
|
|
"mean_token_accuracy": 0.1075212113559246,
|
|
"num_tokens": 227682.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.1558643817901615,
|
|
"epoch": 0.010858670230537921,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.5783,
|
|
"mean_token_accuracy": 0.11288131624460221,
|
|
"num_tokens": 236170.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.093167066574097,
|
|
"epoch": 0.011276311393250919,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.6689,
|
|
"mean_token_accuracy": 0.10450198128819466,
|
|
"num_tokens": 245710.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 6.978710603713989,
|
|
"epoch": 0.011693952555963916,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.6178,
|
|
"mean_token_accuracy": 0.10575460121035576,
|
|
"num_tokens": 254751.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.034113359451294,
|
|
"epoch": 0.012111593718676913,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.5614,
|
|
"mean_token_accuracy": 0.11512050479650497,
|
|
"num_tokens": 264210.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.06213526725769,
|
|
"epoch": 0.01252923488138991,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.5988,
|
|
"mean_token_accuracy": 0.11738329231739045,
|
|
"num_tokens": 272944.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.066068315505982,
|
|
"epoch": 0.012946876044102907,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.5057,
|
|
"mean_token_accuracy": 0.11759286895394325,
|
|
"num_tokens": 281311.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 6.99861330986023,
|
|
"epoch": 0.013364517206815904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.4934,
|
|
"mean_token_accuracy": 0.11470050439238548,
|
|
"num_tokens": 289701.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 6.999594020843506,
|
|
"epoch": 0.013782158369528901,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.6443,
|
|
"mean_token_accuracy": 0.1106612429022789,
|
|
"num_tokens": 299459.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.093910980224609,
|
|
"epoch": 0.014199799532241897,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.6559,
|
|
"mean_token_accuracy": 0.10836043506860733,
|
|
"num_tokens": 309343.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.137103700637818,
|
|
"epoch": 0.014617440694954895,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.6505,
|
|
"mean_token_accuracy": 0.10711321234703064,
|
|
"num_tokens": 318840.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 6.972873401641846,
|
|
"epoch": 0.015035081857667892,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.4931,
|
|
"mean_token_accuracy": 0.11117812916636467,
|
|
"num_tokens": 328689.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 6.988192701339722,
|
|
"epoch": 0.01545272302038089,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.6021,
|
|
"mean_token_accuracy": 0.10945339202880859,
|
|
"num_tokens": 338209.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.049764633178711,
|
|
"epoch": 0.015870364183093885,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.5287,
|
|
"mean_token_accuracy": 0.11342571824789047,
|
|
"num_tokens": 347270.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.03518533706665,
|
|
"epoch": 0.016288005345806884,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.5849,
|
|
"mean_token_accuracy": 0.11009221971035003,
|
|
"num_tokens": 356366.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.03167085647583,
|
|
"epoch": 0.01670564650851988,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.5328,
|
|
"mean_token_accuracy": 0.11283481717109681,
|
|
"num_tokens": 365980.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 6.968191242218017,
|
|
"epoch": 0.017123287671232876,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.5148,
|
|
"mean_token_accuracy": 0.11944594606757164,
|
|
"num_tokens": 374591.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.072711515426636,
|
|
"epoch": 0.017540928833945875,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.5385,
|
|
"mean_token_accuracy": 0.1136755608022213,
|
|
"num_tokens": 383250.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 6.995183229446411,
|
|
"epoch": 0.01795856999665887,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.4583,
|
|
"mean_token_accuracy": 0.11463667005300522,
|
|
"num_tokens": 391502.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.895081424713135,
|
|
"epoch": 0.018376211159371866,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.3988,
|
|
"mean_token_accuracy": 0.11630335673689843,
|
|
"num_tokens": 400225.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.06805739402771,
|
|
"epoch": 0.018793852322084866,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.6072,
|
|
"mean_token_accuracy": 0.10876822546124458,
|
|
"num_tokens": 410008.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.0077355861663815,
|
|
"epoch": 0.01921149348479786,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.5571,
|
|
"mean_token_accuracy": 0.11483839824795723,
|
|
"num_tokens": 418979.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 6.974493551254272,
|
|
"epoch": 0.01962913464751086,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.5401,
|
|
"mean_token_accuracy": 0.11396894752979278,
|
|
"num_tokens": 428139.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.025577116012573,
|
|
"epoch": 0.020046775810223856,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.4599,
|
|
"mean_token_accuracy": 0.1212654784321785,
|
|
"num_tokens": 437113.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.048428630828857,
|
|
"epoch": 0.020464416972936852,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.7074,
|
|
"mean_token_accuracy": 0.10927195772528649,
|
|
"num_tokens": 446879.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.040731477737427,
|
|
"epoch": 0.02088205813564985,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.6006,
|
|
"mean_token_accuracy": 0.11155584380030632,
|
|
"num_tokens": 456362.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 6.9144243717193605,
|
|
"epoch": 0.021299699298362847,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.4035,
|
|
"mean_token_accuracy": 0.12014602795243264,
|
|
"num_tokens": 464930.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.058174657821655,
|
|
"epoch": 0.021717340461075842,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.5859,
|
|
"mean_token_accuracy": 0.10830959379673004,
|
|
"num_tokens": 474303.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.00397891998291,
|
|
"epoch": 0.02213498162378884,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.6132,
|
|
"mean_token_accuracy": 0.10992222279310226,
|
|
"num_tokens": 483750.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 6.9822266578674315,
|
|
"epoch": 0.022552622786501837,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.5084,
|
|
"mean_token_accuracy": 0.11087508201599121,
|
|
"num_tokens": 493325.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.009824895858765,
|
|
"epoch": 0.022970263949214833,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.5137,
|
|
"mean_token_accuracy": 0.10929684713482857,
|
|
"num_tokens": 501907.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.979407691955567,
|
|
"epoch": 0.023387905111927832,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.5808,
|
|
"mean_token_accuracy": 0.11485241651535034,
|
|
"num_tokens": 511522.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.028356742858887,
|
|
"epoch": 0.023805546274640828,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.5271,
|
|
"mean_token_accuracy": 0.11359211280941964,
|
|
"num_tokens": 521287.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.061210489273071,
|
|
"epoch": 0.024223187437353827,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.6216,
|
|
"mean_token_accuracy": 0.105019910633564,
|
|
"num_tokens": 530631.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.979819393157959,
|
|
"epoch": 0.024640828600066823,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.5007,
|
|
"mean_token_accuracy": 0.12092425003647804,
|
|
"num_tokens": 540386.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.993960380554199,
|
|
"epoch": 0.02505846976277982,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.5707,
|
|
"mean_token_accuracy": 0.10561831966042519,
|
|
"num_tokens": 550121.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.893993711471557,
|
|
"epoch": 0.025476110925492818,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.4518,
|
|
"mean_token_accuracy": 0.11266563385725022,
|
|
"num_tokens": 559460.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.0018908977508545,
|
|
"epoch": 0.025893752088205813,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.4121,
|
|
"mean_token_accuracy": 0.12040314078330994,
|
|
"num_tokens": 568392.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.900617361068726,
|
|
"epoch": 0.02631139325091881,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.11066874042153359,
|
|
"num_tokens": 578248.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.024792003631592,
|
|
"epoch": 0.026729034413631808,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.602,
|
|
"mean_token_accuracy": 0.10860413312911987,
|
|
"num_tokens": 588164.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.956603240966797,
|
|
"epoch": 0.027146675576344804,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.5426,
|
|
"mean_token_accuracy": 0.11270351558923722,
|
|
"num_tokens": 598715.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.0015754222869875,
|
|
"epoch": 0.027564316739057803,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.4531,
|
|
"mean_token_accuracy": 0.11661125272512436,
|
|
"num_tokens": 606939.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.93249478340149,
|
|
"epoch": 0.0279819579017708,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.5601,
|
|
"mean_token_accuracy": 0.1157400868833065,
|
|
"num_tokens": 615803.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.946778154373169,
|
|
"epoch": 0.028399599064483794,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.4094,
|
|
"mean_token_accuracy": 0.11591838151216508,
|
|
"num_tokens": 624730.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.9720173358917235,
|
|
"epoch": 0.028817240227196794,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.5152,
|
|
"mean_token_accuracy": 0.11504784747958183,
|
|
"num_tokens": 634082.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.009779977798462,
|
|
"epoch": 0.02923488138990979,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.5062,
|
|
"mean_token_accuracy": 0.11588201373815536,
|
|
"num_tokens": 643367.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.747243738174438,
|
|
"epoch": 0.029652522552622785,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.11819797530770301,
|
|
"num_tokens": 651861.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.997044849395752,
|
|
"epoch": 0.030070163715335784,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.4763,
|
|
"mean_token_accuracy": 0.11358832642436027,
|
|
"num_tokens": 661064.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.892722797393799,
|
|
"epoch": 0.03048780487804878,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.4584,
|
|
"mean_token_accuracy": 0.12111971825361252,
|
|
"num_tokens": 669299.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.900249767303467,
|
|
"epoch": 0.03090544604076178,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.5432,
|
|
"mean_token_accuracy": 0.11214440464973449,
|
|
"num_tokens": 678631.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.960112619400024,
|
|
"epoch": 0.03132308720347477,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.5439,
|
|
"mean_token_accuracy": 0.11418872177600861,
|
|
"num_tokens": 688511.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.962337827682495,
|
|
"epoch": 0.03174072836618777,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.4884,
|
|
"mean_token_accuracy": 0.11288235932588578,
|
|
"num_tokens": 697956.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.944037771224975,
|
|
"epoch": 0.03215836952890077,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.3916,
|
|
"mean_token_accuracy": 0.12509041503071786,
|
|
"num_tokens": 706779.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.810015869140625,
|
|
"epoch": 0.03257601069161377,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.4229,
|
|
"mean_token_accuracy": 0.11323002874851226,
|
|
"num_tokens": 715749.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.847266960144043,
|
|
"epoch": 0.03299365185432676,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.3759,
|
|
"mean_token_accuracy": 0.11320273652672767,
|
|
"num_tokens": 724756.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.870378017425537,
|
|
"epoch": 0.03341129301703976,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.4005,
|
|
"mean_token_accuracy": 0.11667888462543488,
|
|
"num_tokens": 733288.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.97679648399353,
|
|
"epoch": 0.03382893417975276,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.5154,
|
|
"mean_token_accuracy": 0.11304147318005561,
|
|
"num_tokens": 741629.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.885066270828247,
|
|
"epoch": 0.03424657534246575,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.4607,
|
|
"mean_token_accuracy": 0.11880626678466796,
|
|
"num_tokens": 751336.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.025588083267212,
|
|
"epoch": 0.03466421650517875,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.5438,
|
|
"mean_token_accuracy": 0.10914942175149918,
|
|
"num_tokens": 759725.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.9342803955078125,
|
|
"epoch": 0.03508185766789175,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.5553,
|
|
"mean_token_accuracy": 0.1125187747180462,
|
|
"num_tokens": 769752.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.87856764793396,
|
|
"epoch": 0.03549949883060474,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.4352,
|
|
"mean_token_accuracy": 0.11564558148384094,
|
|
"num_tokens": 779124.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.843322324752807,
|
|
"epoch": 0.03591713999331774,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.4045,
|
|
"mean_token_accuracy": 0.11882894486188889,
|
|
"num_tokens": 788892.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.755243921279908,
|
|
"epoch": 0.03633478115603074,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.3802,
|
|
"mean_token_accuracy": 0.12028775066137314,
|
|
"num_tokens": 798265.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.811845159530639,
|
|
"epoch": 0.03675242231874373,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.3309,
|
|
"mean_token_accuracy": 0.12370585277676582,
|
|
"num_tokens": 806896.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.91562705039978,
|
|
"epoch": 0.03717006348145673,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.4074,
|
|
"mean_token_accuracy": 0.12382019609212876,
|
|
"num_tokens": 815540.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.7790063381195065,
|
|
"epoch": 0.03758770464416973,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.4711,
|
|
"mean_token_accuracy": 0.11695906072854996,
|
|
"num_tokens": 824555.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.968459796905518,
|
|
"epoch": 0.03800534580688272,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.5115,
|
|
"mean_token_accuracy": 0.11615965217351913,
|
|
"num_tokens": 833414.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.775349855422974,
|
|
"epoch": 0.03842298696959572,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.3606,
|
|
"mean_token_accuracy": 0.12755532786250115,
|
|
"num_tokens": 842644.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.829344940185547,
|
|
"epoch": 0.03884062813230872,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.11902292668819428,
|
|
"num_tokens": 851786.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.812217950820923,
|
|
"epoch": 0.03925826929502172,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.4623,
|
|
"mean_token_accuracy": 0.11948096305131913,
|
|
"num_tokens": 861508.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.814907360076904,
|
|
"epoch": 0.03967591045773471,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.12454579472541809,
|
|
"num_tokens": 870433.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.905804967880249,
|
|
"epoch": 0.04009355162044771,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.4355,
|
|
"mean_token_accuracy": 0.11918441057205201,
|
|
"num_tokens": 879059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.840558004379273,
|
|
"epoch": 0.04051119278316071,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.4766,
|
|
"mean_token_accuracy": 0.1148101843893528,
|
|
"num_tokens": 888009.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.811307907104492,
|
|
"epoch": 0.040928833945873704,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.3523,
|
|
"mean_token_accuracy": 0.11887899562716484,
|
|
"num_tokens": 897335.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.947777843475341,
|
|
"epoch": 0.0413464751085867,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.3711,
|
|
"mean_token_accuracy": 0.12019851058721542,
|
|
"num_tokens": 905802.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.698061895370484,
|
|
"epoch": 0.0417641162712997,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.3767,
|
|
"mean_token_accuracy": 0.12129626050591469,
|
|
"num_tokens": 914836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.701544523239136,
|
|
"epoch": 0.042181757434012694,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.3367,
|
|
"mean_token_accuracy": 0.12701809629797936,
|
|
"num_tokens": 924254.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.849635410308838,
|
|
"epoch": 0.04259939859672569,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.4222,
|
|
"mean_token_accuracy": 0.1207270435988903,
|
|
"num_tokens": 933841.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.831308794021607,
|
|
"epoch": 0.04301703975943869,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.4824,
|
|
"mean_token_accuracy": 0.11359498947858811,
|
|
"num_tokens": 943304.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.787075567245483,
|
|
"epoch": 0.043434680922151685,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.3107,
|
|
"mean_token_accuracy": 0.12178815752267838,
|
|
"num_tokens": 952915.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.7996033191680905,
|
|
"epoch": 0.043852322084864684,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.376,
|
|
"mean_token_accuracy": 0.11833536252379417,
|
|
"num_tokens": 962752.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.803986644744873,
|
|
"epoch": 0.04426996324757768,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.11484252288937569,
|
|
"num_tokens": 971240.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.836751461029053,
|
|
"epoch": 0.044687604410290675,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.4379,
|
|
"mean_token_accuracy": 0.11609105840325355,
|
|
"num_tokens": 981391.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.825729942321777,
|
|
"epoch": 0.045105245573003674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.4411,
|
|
"mean_token_accuracy": 0.12200247570872307,
|
|
"num_tokens": 990551.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.753824377059937,
|
|
"epoch": 0.045522886735716674,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.3708,
|
|
"mean_token_accuracy": 0.12560774609446526,
|
|
"num_tokens": 999593.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.751221561431885,
|
|
"epoch": 0.045940527898429666,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.435,
|
|
"mean_token_accuracy": 0.1148043192923069,
|
|
"num_tokens": 1008785.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.792971754074097,
|
|
"epoch": 0.046358169061142665,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.4275,
|
|
"mean_token_accuracy": 0.11967866346240044,
|
|
"num_tokens": 1016815.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.81648211479187,
|
|
"epoch": 0.046775810223855664,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.12556978464126586,
|
|
"num_tokens": 1026182.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.699583864212036,
|
|
"epoch": 0.04719345138656866,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.1253122940659523,
|
|
"num_tokens": 1034032.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.784116649627686,
|
|
"epoch": 0.047611092549281656,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.4463,
|
|
"mean_token_accuracy": 0.1194463238120079,
|
|
"num_tokens": 1043493.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.798874998092652,
|
|
"epoch": 0.048028733711994655,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.3696,
|
|
"mean_token_accuracy": 0.12368837371468544,
|
|
"num_tokens": 1052989.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.72132363319397,
|
|
"epoch": 0.048446374874707654,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.3139,
|
|
"mean_token_accuracy": 0.1262795701622963,
|
|
"num_tokens": 1061803.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.786125230789184,
|
|
"epoch": 0.048864016037420646,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.4369,
|
|
"mean_token_accuracy": 0.11582259833812714,
|
|
"num_tokens": 1071227.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.798495769500732,
|
|
"epoch": 0.049281657200133645,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.4515,
|
|
"mean_token_accuracy": 0.11928854063153267,
|
|
"num_tokens": 1080082.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.744865560531617,
|
|
"epoch": 0.049699298362846644,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.2751,
|
|
"mean_token_accuracy": 0.129691481590271,
|
|
"num_tokens": 1089750.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.612829875946045,
|
|
"epoch": 0.05011693952555964,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.12416435405611992,
|
|
"num_tokens": 1098691.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.762234783172607,
|
|
"epoch": 0.050534580688272636,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.304,
|
|
"mean_token_accuracy": 0.12247414365410805,
|
|
"num_tokens": 1107602.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.6523035049438475,
|
|
"epoch": 0.050952221850985635,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.1269650489091873,
|
|
"num_tokens": 1116426.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.778998899459839,
|
|
"epoch": 0.05136986301369863,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.4285,
|
|
"mean_token_accuracy": 0.11890402808785439,
|
|
"num_tokens": 1126221.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.653987455368042,
|
|
"epoch": 0.051787504176411626,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.2885,
|
|
"mean_token_accuracy": 0.1295793242752552,
|
|
"num_tokens": 1135662.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.7479198455810545,
|
|
"epoch": 0.052205145339124626,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.3947,
|
|
"mean_token_accuracy": 0.11984972506761551,
|
|
"num_tokens": 1143963.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.682434034347534,
|
|
"epoch": 0.05262278650183762,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.2794,
|
|
"mean_token_accuracy": 0.1316371254622936,
|
|
"num_tokens": 1152470.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.658819675445557,
|
|
"epoch": 0.05304042766455062,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.2405,
|
|
"mean_token_accuracy": 0.12752789109945298,
|
|
"num_tokens": 1161257.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.748351955413819,
|
|
"epoch": 0.053458068827263616,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.3653,
|
|
"mean_token_accuracy": 0.12206655815243721,
|
|
"num_tokens": 1170969.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.841134929656983,
|
|
"epoch": 0.053875709989976615,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5096,
|
|
"mean_token_accuracy": 0.12022155672311782,
|
|
"num_tokens": 1181127.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.656730985641479,
|
|
"epoch": 0.05429335115268961,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.1269573986530304,
|
|
"num_tokens": 1190260.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.648819923400879,
|
|
"epoch": 0.05471099231540261,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.3811,
|
|
"mean_token_accuracy": 0.12258001565933227,
|
|
"num_tokens": 1200013.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.800306510925293,
|
|
"epoch": 0.055128633478115606,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.2984,
|
|
"mean_token_accuracy": 0.12799592241644858,
|
|
"num_tokens": 1209239.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.62961049079895,
|
|
"epoch": 0.0555462746408286,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.12337995842099189,
|
|
"num_tokens": 1218552.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.628785181045532,
|
|
"epoch": 0.0559639158035416,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.12454259842634201,
|
|
"num_tokens": 1227632.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.668724393844604,
|
|
"epoch": 0.056381556966254597,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.3478,
|
|
"mean_token_accuracy": 0.12489912509918213,
|
|
"num_tokens": 1236433.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.6647257804870605,
|
|
"epoch": 0.05679919812896759,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.3787,
|
|
"mean_token_accuracy": 0.11425701901316643,
|
|
"num_tokens": 1245700.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.721970319747925,
|
|
"epoch": 0.05721683929168059,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.2294,
|
|
"mean_token_accuracy": 0.12574136778712272,
|
|
"num_tokens": 1254206.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.5612939357757565,
|
|
"epoch": 0.05763448045439359,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.1284436322748661,
|
|
"num_tokens": 1263302.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.64943904876709,
|
|
"epoch": 0.05805212161710658,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.1250022418797016,
|
|
"num_tokens": 1272998.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.659237289428711,
|
|
"epoch": 0.05846976277981958,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.2938,
|
|
"mean_token_accuracy": 0.12968498468399048,
|
|
"num_tokens": 1281955.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.673580741882324,
|
|
"epoch": 0.05888740394253258,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.3191,
|
|
"mean_token_accuracy": 0.12429769113659858,
|
|
"num_tokens": 1291219.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.618105745315551,
|
|
"epoch": 0.05930504510524557,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.3399,
|
|
"mean_token_accuracy": 0.1173406608402729,
|
|
"num_tokens": 1300963.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.732410621643067,
|
|
"epoch": 0.05972268626795857,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.358,
|
|
"mean_token_accuracy": 0.12274901047348977,
|
|
"num_tokens": 1310112.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.636858129501343,
|
|
"epoch": 0.06014032743067157,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.2925,
|
|
"mean_token_accuracy": 0.13005554676055908,
|
|
"num_tokens": 1319309.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.491259765625,
|
|
"epoch": 0.06055796859338457,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.2686,
|
|
"mean_token_accuracy": 0.12515867426991462,
|
|
"num_tokens": 1329049.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.600369119644165,
|
|
"epoch": 0.06097560975609756,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.109,
|
|
"mean_token_accuracy": 0.129255248606205,
|
|
"num_tokens": 1337770.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.448912858963013,
|
|
"epoch": 0.06139325091881056,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.1278871200978756,
|
|
"num_tokens": 1346705.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.637778997421265,
|
|
"epoch": 0.06181089208152356,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.2804,
|
|
"mean_token_accuracy": 0.12408471331000329,
|
|
"num_tokens": 1354860.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.631476402282715,
|
|
"epoch": 0.06222853324423655,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.1262032598257065,
|
|
"num_tokens": 1364140.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.6420732021331785,
|
|
"epoch": 0.06264617440694954,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.383,
|
|
"mean_token_accuracy": 0.11741869822144509,
|
|
"num_tokens": 1373645.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.614962768554688,
|
|
"epoch": 0.06306381556966255,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2628,
|
|
"mean_token_accuracy": 0.12924929931759835,
|
|
"num_tokens": 1383291.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.541449499130249,
|
|
"epoch": 0.06348145673237554,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.12891636416316032,
|
|
"num_tokens": 1391172.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.567931509017944,
|
|
"epoch": 0.06389909789508853,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.1962,
|
|
"mean_token_accuracy": 0.12836265712976455,
|
|
"num_tokens": 1400864.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.577566814422608,
|
|
"epoch": 0.06431673905780154,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.2475,
|
|
"mean_token_accuracy": 0.13195167928934098,
|
|
"num_tokens": 1410570.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.4961103916168215,
|
|
"epoch": 0.06473438022051453,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.2196,
|
|
"mean_token_accuracy": 0.12905707359313964,
|
|
"num_tokens": 1419536.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.544592094421387,
|
|
"epoch": 0.06515202138322754,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.1324485160410404,
|
|
"num_tokens": 1428000.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.524274158477783,
|
|
"epoch": 0.06556966254594053,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.12751191332936287,
|
|
"num_tokens": 1437789.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.527570533752441,
|
|
"epoch": 0.06598730370865352,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.13085014671087264,
|
|
"num_tokens": 1446848.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.503874588012695,
|
|
"epoch": 0.06640494487136653,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.2138,
|
|
"mean_token_accuracy": 0.1266377955675125,
|
|
"num_tokens": 1455749.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.490093851089478,
|
|
"epoch": 0.06682258603407952,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.1232,
|
|
"mean_token_accuracy": 0.1335439622402191,
|
|
"num_tokens": 1464556.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.529352855682373,
|
|
"epoch": 0.06724022719679251,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.2528,
|
|
"mean_token_accuracy": 0.12460074424743653,
|
|
"num_tokens": 1473617.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.553039026260376,
|
|
"epoch": 0.06765786835950552,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.271,
|
|
"mean_token_accuracy": 0.127645106613636,
|
|
"num_tokens": 1483006.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.596258735656738,
|
|
"epoch": 0.06807550952221851,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2902,
|
|
"mean_token_accuracy": 0.1250758670270443,
|
|
"num_tokens": 1493009.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.5069859504699705,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.1761,
|
|
"mean_token_accuracy": 0.13094822615385054,
|
|
"num_tokens": 1501261.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.490626192092895,
|
|
"epoch": 0.06891079184764451,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.2834,
|
|
"mean_token_accuracy": 0.1269587032496929,
|
|
"num_tokens": 1511623.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.578334522247315,
|
|
"epoch": 0.0693284330103575,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2791,
|
|
"mean_token_accuracy": 0.12188976258039474,
|
|
"num_tokens": 1521741.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.502293491363526,
|
|
"epoch": 0.0697460741730705,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.2152,
|
|
"mean_token_accuracy": 0.12901918739080429,
|
|
"num_tokens": 1530988.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.41391224861145,
|
|
"epoch": 0.0701637153357835,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.0477,
|
|
"mean_token_accuracy": 0.13469421193003656,
|
|
"num_tokens": 1539415.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.599431276321411,
|
|
"epoch": 0.07058135649849649,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.2591,
|
|
"mean_token_accuracy": 0.13088077455759048,
|
|
"num_tokens": 1547969.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.374254846572876,
|
|
"epoch": 0.07099899766120948,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.1072,
|
|
"mean_token_accuracy": 0.13475026711821556,
|
|
"num_tokens": 1557526.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.417814064025879,
|
|
"epoch": 0.07141663882392249,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.0887,
|
|
"mean_token_accuracy": 0.13038780987262727,
|
|
"num_tokens": 1565982.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.40412015914917,
|
|
"epoch": 0.07183427998663548,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.1433,
|
|
"mean_token_accuracy": 0.13692082837224007,
|
|
"num_tokens": 1574492.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.388799810409546,
|
|
"epoch": 0.07225192114934847,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.13500951156020163,
|
|
"num_tokens": 1583726.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.44487509727478,
|
|
"epoch": 0.07266956231206148,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1361,
|
|
"mean_token_accuracy": 0.12648910656571388,
|
|
"num_tokens": 1593780.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.468150472640991,
|
|
"epoch": 0.07308720347477447,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.1348,
|
|
"mean_token_accuracy": 0.13127309009432792,
|
|
"num_tokens": 1602746.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.515667915344238,
|
|
"epoch": 0.07350484463748747,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.13110396489501,
|
|
"num_tokens": 1611767.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.435206174850464,
|
|
"epoch": 0.07392248580020047,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.13171651512384414,
|
|
"num_tokens": 1621568.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.482450342178344,
|
|
"epoch": 0.07434012696291346,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.1917,
|
|
"mean_token_accuracy": 0.13484023958444596,
|
|
"num_tokens": 1630650.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.516539001464844,
|
|
"epoch": 0.07475776812562646,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.12935673892498017,
|
|
"num_tokens": 1640482.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.491699361801148,
|
|
"epoch": 0.07517540928833946,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.12839881628751754,
|
|
"num_tokens": 1649344.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.393206262588501,
|
|
"epoch": 0.07559305045105245,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.1696,
|
|
"mean_token_accuracy": 0.12845856323838234,
|
|
"num_tokens": 1658962.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.4265542984008786,
|
|
"epoch": 0.07601069161376545,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.1747,
|
|
"mean_token_accuracy": 0.13029418736696244,
|
|
"num_tokens": 1668615.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.521175193786621,
|
|
"epoch": 0.07642833277647845,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.1143,
|
|
"mean_token_accuracy": 0.13495683968067168,
|
|
"num_tokens": 1679282.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.303538370132446,
|
|
"epoch": 0.07684597393919144,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2102,
|
|
"mean_token_accuracy": 0.13202547430992126,
|
|
"num_tokens": 1688362.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.46322808265686,
|
|
"epoch": 0.07726361510190444,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.12747513502836227,
|
|
"num_tokens": 1697593.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.421608257293701,
|
|
"epoch": 0.07768125626461744,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.12738403007388116,
|
|
"num_tokens": 1706961.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.462583541870117,
|
|
"epoch": 0.07809889742733044,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2079,
|
|
"mean_token_accuracy": 0.13471694365143777,
|
|
"num_tokens": 1716222.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.365508604049682,
|
|
"epoch": 0.07851653859004344,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.0777,
|
|
"mean_token_accuracy": 0.12822124660015105,
|
|
"num_tokens": 1726750.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.432874298095703,
|
|
"epoch": 0.07893417975275643,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1788,
|
|
"mean_token_accuracy": 0.12462074533104897,
|
|
"num_tokens": 1736262.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.418917083740235,
|
|
"epoch": 0.07935182091546943,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.208,
|
|
"mean_token_accuracy": 0.13261273950338365,
|
|
"num_tokens": 1745555.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.264679765701294,
|
|
"epoch": 0.07976946207818243,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.12742999866604804,
|
|
"num_tokens": 1754107.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.569329309463501,
|
|
"epoch": 0.08018710324089542,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2585,
|
|
"mean_token_accuracy": 0.12915159463882447,
|
|
"num_tokens": 1762982.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.333677053451538,
|
|
"epoch": 0.08060474440360842,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.1485,
|
|
"mean_token_accuracy": 0.1329043798148632,
|
|
"num_tokens": 1772545.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.501676940917969,
|
|
"epoch": 0.08102238556632142,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.12669501081109047,
|
|
"num_tokens": 1782052.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.379133939743042,
|
|
"epoch": 0.08144002672903441,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.13307300806045533,
|
|
"num_tokens": 1791682.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.325070905685425,
|
|
"epoch": 0.08185766789174741,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.0852,
|
|
"mean_token_accuracy": 0.136198490858078,
|
|
"num_tokens": 1800526.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.438921642303467,
|
|
"epoch": 0.08227530905446041,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2128,
|
|
"mean_token_accuracy": 0.1367432154715061,
|
|
"num_tokens": 1810062.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.437668371200561,
|
|
"epoch": 0.0826929502171734,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.193,
|
|
"mean_token_accuracy": 0.13399267047643662,
|
|
"num_tokens": 1818909.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.417872190475464,
|
|
"epoch": 0.0831105913798864,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1495,
|
|
"mean_token_accuracy": 0.13555187806487085,
|
|
"num_tokens": 1827978.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.295065593719483,
|
|
"epoch": 0.0835282325425994,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.115,
|
|
"mean_token_accuracy": 0.13612975925207138,
|
|
"num_tokens": 1837955.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.429361057281494,
|
|
"epoch": 0.0839458737053124,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999999987395534,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.13162293881177903,
|
|
"num_tokens": 1847699.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.420073318481445,
|
|
"epoch": 0.08436351486802539,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999936189888,
|
|
"loss": 6.1517,
|
|
"mean_token_accuracy": 0.13114715069532396,
|
|
"num_tokens": 1856490.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.38634729385376,
|
|
"epoch": 0.0847811560307384,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999845595285,
|
|
"loss": 6.1503,
|
|
"mean_token_accuracy": 0.13426092267036438,
|
|
"num_tokens": 1865644.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.398542594909668,
|
|
"epoch": 0.08519879719345139,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999999715611727,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.1395128108561039,
|
|
"num_tokens": 1874450.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.275608062744141,
|
|
"epoch": 0.08561643835616438,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999546239215,
|
|
"loss": 6.104,
|
|
"mean_token_accuracy": 0.13559797704219817,
|
|
"num_tokens": 1883259.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.392034816741943,
|
|
"epoch": 0.08603407951887738,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999999337477753,
|
|
"loss": 6.1933,
|
|
"mean_token_accuracy": 0.12675563469529152,
|
|
"num_tokens": 1891897.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.44005560874939,
|
|
"epoch": 0.08645172068159038,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999999089327344,
|
|
"loss": 6.1532,
|
|
"mean_token_accuracy": 0.13319713696837426,
|
|
"num_tokens": 1901011.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.2367016792297365,
|
|
"epoch": 0.08686936184430337,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999998801787993,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.13727857545018196,
|
|
"num_tokens": 1910132.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.4353138446807865,
|
|
"epoch": 0.08728700300701638,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999998474859704,
|
|
"loss": 6.1844,
|
|
"mean_token_accuracy": 0.13210511356592178,
|
|
"num_tokens": 1919938.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.260934543609619,
|
|
"epoch": 0.08770464416972937,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999998108542483,
|
|
"loss": 6.0466,
|
|
"mean_token_accuracy": 0.13039984107017516,
|
|
"num_tokens": 1928199.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.3116625308990475,
|
|
"epoch": 0.08812228533244236,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004999997702836339,
|
|
"loss": 6.0458,
|
|
"mean_token_accuracy": 0.13747427314519883,
|
|
"num_tokens": 1937133.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.441593408584595,
|
|
"epoch": 0.08853992649515537,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999997257741274,
|
|
"loss": 6.2143,
|
|
"mean_token_accuracy": 0.1290765218436718,
|
|
"num_tokens": 1946580.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.280451679229737,
|
|
"epoch": 0.08895756765786836,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00049999967732573,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.13576303273439408,
|
|
"num_tokens": 1955413.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.547540473937988,
|
|
"epoch": 0.08937520882058135,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999996249384425,
|
|
"loss": 6.2026,
|
|
"mean_token_accuracy": 0.12969096824526788,
|
|
"num_tokens": 1964716.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.2454064846038815,
|
|
"epoch": 0.08979284998329436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999995686122657,
|
|
"loss": 6.0586,
|
|
"mean_token_accuracy": 0.13843119516968727,
|
|
"num_tokens": 1974081.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.207799673080444,
|
|
"epoch": 0.09021049114600735,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999995083472006,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.13496628925204276,
|
|
"num_tokens": 1983035.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.349649572372437,
|
|
"epoch": 0.09062813230872034,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999994441432481,
|
|
"loss": 6.0406,
|
|
"mean_token_accuracy": 0.1435403674840927,
|
|
"num_tokens": 1992475.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.300027513504029,
|
|
"epoch": 0.09104577347143335,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999993760004097,
|
|
"loss": 6.1209,
|
|
"mean_token_accuracy": 0.13500647395849227,
|
|
"num_tokens": 2002729.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.230009746551514,
|
|
"epoch": 0.09146341463414634,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999993039186864,
|
|
"loss": 5.9614,
|
|
"mean_token_accuracy": 0.13840871751308442,
|
|
"num_tokens": 2011319.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.26380090713501,
|
|
"epoch": 0.09188105579685933,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999992278980794,
|
|
"loss": 6.0199,
|
|
"mean_token_accuracy": 0.13688360154628754,
|
|
"num_tokens": 2020456.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.208072185516357,
|
|
"epoch": 0.09229869695957234,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999991479385901,
|
|
"loss": 6.0945,
|
|
"mean_token_accuracy": 0.13740770444273948,
|
|
"num_tokens": 2029417.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.422892808914185,
|
|
"epoch": 0.09271633812228533,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999990640402198,
|
|
"loss": 6.1701,
|
|
"mean_token_accuracy": 0.1360443763434887,
|
|
"num_tokens": 2039290.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.3189490795135494,
|
|
"epoch": 0.09313397928499834,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999989762029701,
|
|
"loss": 5.9962,
|
|
"mean_token_accuracy": 0.13912804424762726,
|
|
"num_tokens": 2048485.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.146860980987549,
|
|
"epoch": 0.09355162044771133,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999988844268425,
|
|
"loss": 5.992,
|
|
"mean_token_accuracy": 0.14194743409752847,
|
|
"num_tokens": 2057131.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.23108491897583,
|
|
"epoch": 0.09396926161042432,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999987887118387,
|
|
"loss": 5.9713,
|
|
"mean_token_accuracy": 0.1364756427705288,
|
|
"num_tokens": 2066295.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.220802450180054,
|
|
"epoch": 0.09438690277313733,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999986890579602,
|
|
"loss": 5.9838,
|
|
"mean_token_accuracy": 0.14211056828498841,
|
|
"num_tokens": 2075656.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.2367716312408445,
|
|
"epoch": 0.09480454393585032,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999985854652087,
|
|
"loss": 6.1204,
|
|
"mean_token_accuracy": 0.1285279080271721,
|
|
"num_tokens": 2086046.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.345442581176758,
|
|
"epoch": 0.09522218509856331,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999984779335862,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.1319953002035618,
|
|
"num_tokens": 2094808.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.1862023830413815,
|
|
"epoch": 0.09563982626127632,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999983664630945,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.13912759348750114,
|
|
"num_tokens": 2104155.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.319784164428711,
|
|
"epoch": 0.09605746742398931,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999982510537357,
|
|
"loss": 5.9529,
|
|
"mean_token_accuracy": 0.13932174518704415,
|
|
"num_tokens": 2112517.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.080702924728394,
|
|
"epoch": 0.0964751085867023,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999981317055116,
|
|
"loss": 5.9205,
|
|
"mean_token_accuracy": 0.13805301561951638,
|
|
"num_tokens": 2121355.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.28314437866211,
|
|
"epoch": 0.09689274974941531,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999980084184244,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.14036146476864814,
|
|
"num_tokens": 2129278.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.273211431503296,
|
|
"epoch": 0.0973103909121283,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999978811924762,
|
|
"loss": 6.1979,
|
|
"mean_token_accuracy": 0.13250343650579452,
|
|
"num_tokens": 2139548.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.278427934646606,
|
|
"epoch": 0.09772803207484129,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999977500276693,
|
|
"loss": 6.0961,
|
|
"mean_token_accuracy": 0.13529025316238402,
|
|
"num_tokens": 2148765.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.313056421279907,
|
|
"epoch": 0.0981456732375543,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999976149240058,
|
|
"loss": 6.0145,
|
|
"mean_token_accuracy": 0.14838937819004058,
|
|
"num_tokens": 2157482.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.236321830749512,
|
|
"epoch": 0.09856331440026729,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999974758814884,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.13229444101452828,
|
|
"num_tokens": 2167320.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.276017045974731,
|
|
"epoch": 0.09898095556298028,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999973329001193,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.13247895389795303,
|
|
"num_tokens": 2175454.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.221844720840454,
|
|
"epoch": 0.09939859672569329,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999971859799009,
|
|
"loss": 5.9926,
|
|
"mean_token_accuracy": 0.1372641235589981,
|
|
"num_tokens": 2184391.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.083957529067993,
|
|
"epoch": 0.09981623788840628,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999970351208361,
|
|
"loss": 5.8895,
|
|
"mean_token_accuracy": 0.1443878285586834,
|
|
"num_tokens": 2193309.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.318909502029419,
|
|
"epoch": 0.10023387905111927,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999968803229275,
|
|
"loss": 6.0251,
|
|
"mean_token_accuracy": 0.13645748943090438,
|
|
"num_tokens": 2202057.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.210393238067627,
|
|
"epoch": 0.10065152021383228,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999967215861775,
|
|
"loss": 6.1176,
|
|
"mean_token_accuracy": 0.1318912997841835,
|
|
"num_tokens": 2212384.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.331364917755127,
|
|
"epoch": 0.10106916137654527,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499996558910589,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.13522329032421113,
|
|
"num_tokens": 2221451.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.12385663986206,
|
|
"epoch": 0.10148680253925826,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000499996392296165,
|
|
"loss": 5.9336,
|
|
"mean_token_accuracy": 0.13527244850993156,
|
|
"num_tokens": 2230440.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.182936525344848,
|
|
"epoch": 0.10190444370197127,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999962217429083,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.1339232660830021,
|
|
"num_tokens": 2239985.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.22488694190979,
|
|
"epoch": 0.10232208486468426,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 5.9821,
|
|
"mean_token_accuracy": 0.14048198014497756,
|
|
"num_tokens": 2250391.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.340797090530396,
|
|
"epoch": 0.10273972602739725,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499995868819909,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.13700031563639642,
|
|
"num_tokens": 2260620.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.190806722640991,
|
|
"epoch": 0.10315736719011026,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999956864501725,
|
|
"loss": 6.0585,
|
|
"mean_token_accuracy": 0.13748134523630143,
|
|
"num_tokens": 2271176.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.3144207954406735,
|
|
"epoch": 0.10357500835282325,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999955001416156,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.14711003750562668,
|
|
"num_tokens": 2280371.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.0102637767791744,
|
|
"epoch": 0.10399264951553625,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999953098942417,
|
|
"loss": 5.9442,
|
|
"mean_token_accuracy": 0.13787835761904715,
|
|
"num_tokens": 2289015.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.191421127319336,
|
|
"epoch": 0.10441029067824925,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999951157080541,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.14192727878689765,
|
|
"num_tokens": 2297409.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.158661842346191,
|
|
"epoch": 0.10482793184096224,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999949175830561,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.13258421197533607,
|
|
"num_tokens": 2307017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.216726875305175,
|
|
"epoch": 0.10524557300367524,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999947155192514,
|
|
"loss": 5.8686,
|
|
"mean_token_accuracy": 0.14748067185282707,
|
|
"num_tokens": 2316014.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.156877565383911,
|
|
"epoch": 0.10566321416638824,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999945095166433,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.1419251538813114,
|
|
"num_tokens": 2326326.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.325374746322632,
|
|
"epoch": 0.10608085532910123,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999942995752354,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.13753873556852342,
|
|
"num_tokens": 2335108.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.153518962860107,
|
|
"epoch": 0.10649849649181423,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999940856950315,
|
|
"loss": 5.9915,
|
|
"mean_token_accuracy": 0.15058054327964782,
|
|
"num_tokens": 2343971.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.263919925689697,
|
|
"epoch": 0.10691613765452723,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999938678760354,
|
|
"loss": 6.0506,
|
|
"mean_token_accuracy": 0.13512684255838395,
|
|
"num_tokens": 2353742.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.151162433624267,
|
|
"epoch": 0.10733377881724022,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999936461182507,
|
|
"loss": 5.9985,
|
|
"mean_token_accuracy": 0.14433275312185287,
|
|
"num_tokens": 2363629.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.037757158279419,
|
|
"epoch": 0.10775141997995323,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999934204216814,
|
|
"loss": 5.8621,
|
|
"mean_token_accuracy": 0.14499263167381288,
|
|
"num_tokens": 2372705.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.187420225143432,
|
|
"epoch": 0.10816906114266622,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999931907863315,
|
|
"loss": 5.9654,
|
|
"mean_token_accuracy": 0.1408788852393627,
|
|
"num_tokens": 2382136.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.083423089981079,
|
|
"epoch": 0.10858670230537922,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499992957212205,
|
|
"loss": 5.9401,
|
|
"mean_token_accuracy": 0.1388118125498295,
|
|
"num_tokens": 2391060.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.293563318252564,
|
|
"epoch": 0.10900434346809222,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999927196993059,
|
|
"loss": 6.0751,
|
|
"mean_token_accuracy": 0.13740024641156195,
|
|
"num_tokens": 2399885.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.209824800491333,
|
|
"epoch": 0.10942198463080521,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999924782476384,
|
|
"loss": 5.9442,
|
|
"mean_token_accuracy": 0.14959385469555855,
|
|
"num_tokens": 2409654.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.124826669692993,
|
|
"epoch": 0.1098396257935182,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999922328572068,
|
|
"loss": 6.0068,
|
|
"mean_token_accuracy": 0.14170742481946946,
|
|
"num_tokens": 2419342.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.088650369644165,
|
|
"epoch": 0.11025726695623121,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999919835280154,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.1480419561266899,
|
|
"num_tokens": 2428845.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.196817445755005,
|
|
"epoch": 0.1106749081189442,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999917302600684,
|
|
"loss": 5.8964,
|
|
"mean_token_accuracy": 0.14959906339645385,
|
|
"num_tokens": 2437134.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 5.955138206481934,
|
|
"epoch": 0.1110925492816572,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999914730533704,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.15773703902959824,
|
|
"num_tokens": 2445438.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.206940174102783,
|
|
"epoch": 0.1115101904443702,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999912119079258,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.1382726550102234,
|
|
"num_tokens": 2455039.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.197380590438843,
|
|
"epoch": 0.1119278316070832,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999909468237393,
|
|
"loss": 6.0001,
|
|
"mean_token_accuracy": 0.14009671807289123,
|
|
"num_tokens": 2465170.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.0352026462554935,
|
|
"epoch": 0.11234547276979619,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999906778008153,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.15088334530591965,
|
|
"num_tokens": 2473688.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.086208772659302,
|
|
"epoch": 0.11276311393250919,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999904048391588,
|
|
"loss": 5.9998,
|
|
"mean_token_accuracy": 0.13953111916780472,
|
|
"num_tokens": 2482335.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.136913299560547,
|
|
"epoch": 0.11318075509522219,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999901279387743,
|
|
"loss": 5.9396,
|
|
"mean_token_accuracy": 0.14635005444288254,
|
|
"num_tokens": 2491808.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.263986206054687,
|
|
"epoch": 0.11359839625793518,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999898470996669,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.1350573979318142,
|
|
"num_tokens": 2501422.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.080953550338745,
|
|
"epoch": 0.11401603742064818,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999895623218415,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.149327090382576,
|
|
"num_tokens": 2511201.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.1295037269592285,
|
|
"epoch": 0.11443367858336118,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999892736053027,
|
|
"loss": 5.9104,
|
|
"mean_token_accuracy": 0.14041806608438492,
|
|
"num_tokens": 2519798.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.107069873809815,
|
|
"epoch": 0.11485131974607417,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999889809500561,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.14723242446780205,
|
|
"num_tokens": 2529177.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.182288074493409,
|
|
"epoch": 0.11526896090878717,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999886843561065,
|
|
"loss": 5.872,
|
|
"mean_token_accuracy": 0.1503610208630562,
|
|
"num_tokens": 2537571.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.0060066223144535,
|
|
"epoch": 0.11568660207150017,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999883838234592,
|
|
"loss": 5.8006,
|
|
"mean_token_accuracy": 0.15079671740531922,
|
|
"num_tokens": 2546258.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.066942644119263,
|
|
"epoch": 0.11610424323421316,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999880793521194,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.14280073940753937,
|
|
"num_tokens": 2555862.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.880656099319458,
|
|
"epoch": 0.11652188439692616,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999877709420924,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.14871919453144072,
|
|
"num_tokens": 2564583.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.192148923873901,
|
|
"epoch": 0.11693952555963916,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999874585933837,
|
|
"loss": 5.9361,
|
|
"mean_token_accuracy": 0.14413623362779618,
|
|
"num_tokens": 2574217.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.042350625991821,
|
|
"epoch": 0.11735716672235215,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999871423059987,
|
|
"loss": 5.8261,
|
|
"mean_token_accuracy": 0.15127213895320893,
|
|
"num_tokens": 2582821.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.120534801483155,
|
|
"epoch": 0.11777480788506516,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499986822079943,
|
|
"loss": 5.9869,
|
|
"mean_token_accuracy": 0.13811271116137505,
|
|
"num_tokens": 2592748.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.115459203720093,
|
|
"epoch": 0.11819244904777815,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999864979152221,
|
|
"loss": 5.8812,
|
|
"mean_token_accuracy": 0.1500445157289505,
|
|
"num_tokens": 2602053.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.0357581615448,
|
|
"epoch": 0.11861009021049114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999861698118417,
|
|
"loss": 5.9734,
|
|
"mean_token_accuracy": 0.1448266699910164,
|
|
"num_tokens": 2610557.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.063483715057373,
|
|
"epoch": 0.11902773137320415,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999858377698076,
|
|
"loss": 5.8583,
|
|
"mean_token_accuracy": 0.1476134791970253,
|
|
"num_tokens": 2619628.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.24661111831665,
|
|
"epoch": 0.11944537253591714,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999855017891256,
|
|
"loss": 6.0248,
|
|
"mean_token_accuracy": 0.14348386973142624,
|
|
"num_tokens": 2629284.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.072677373886108,
|
|
"epoch": 0.11986301369863013,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999851618698017,
|
|
"loss": 5.9275,
|
|
"mean_token_accuracy": 0.1488335132598877,
|
|
"num_tokens": 2638001.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.050741863250733,
|
|
"epoch": 0.12028065486134314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999848180118416,
|
|
"loss": 5.9276,
|
|
"mean_token_accuracy": 0.15267922058701516,
|
|
"num_tokens": 2647071.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.169870662689209,
|
|
"epoch": 0.12069829602405613,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999844702152516,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.15194404125213623,
|
|
"num_tokens": 2655826.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.010311937332153,
|
|
"epoch": 0.12111593718676913,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999841184800374,
|
|
"loss": 5.7654,
|
|
"mean_token_accuracy": 0.15490481853485108,
|
|
"num_tokens": 2664431.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.939828205108642,
|
|
"epoch": 0.12153357834948213,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999837628062055,
|
|
"loss": 5.7018,
|
|
"mean_token_accuracy": 0.15625880509614945,
|
|
"num_tokens": 2673631.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.022509479522705,
|
|
"epoch": 0.12195121951219512,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999834031937621,
|
|
"loss": 5.9699,
|
|
"mean_token_accuracy": 0.14635280668735504,
|
|
"num_tokens": 2683363.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.089596748352051,
|
|
"epoch": 0.12236886067490813,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999830396427133,
|
|
"loss": 5.9188,
|
|
"mean_token_accuracy": 0.14480822607874871,
|
|
"num_tokens": 2692533.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.08122296333313,
|
|
"epoch": 0.12278650183762112,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999826721530657,
|
|
"loss": 5.9124,
|
|
"mean_token_accuracy": 0.15013255774974824,
|
|
"num_tokens": 2701211.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.1377417087554935,
|
|
"epoch": 0.12320414300033411,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999823007248255,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.1476438969373703,
|
|
"num_tokens": 2709543.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.091922330856323,
|
|
"epoch": 0.12362178416304712,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999819253579992,
|
|
"loss": 5.9091,
|
|
"mean_token_accuracy": 0.1487370640039444,
|
|
"num_tokens": 2718336.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.109616804122925,
|
|
"epoch": 0.12403942532576011,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999815460525938,
|
|
"loss": 5.8609,
|
|
"mean_token_accuracy": 0.15401075929403304,
|
|
"num_tokens": 2726504.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.007654333114624,
|
|
"epoch": 0.1244570664884731,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999811628086155,
|
|
"loss": 5.8721,
|
|
"mean_token_accuracy": 0.15031274408102036,
|
|
"num_tokens": 2736076.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.982239532470703,
|
|
"epoch": 0.1248747076511861,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499980775626071,
|
|
"loss": 5.8002,
|
|
"mean_token_accuracy": 0.15212904959917067,
|
|
"num_tokens": 2745497.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.028728914260864,
|
|
"epoch": 0.12529234881389908,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999803845049674,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.14615222066640854,
|
|
"num_tokens": 2754455.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.188329696655273,
|
|
"epoch": 0.1257099899766121,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999799894453112,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.14670175090432166,
|
|
"num_tokens": 2763603.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.046121978759766,
|
|
"epoch": 0.1261276311393251,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999795904471095,
|
|
"loss": 5.823,
|
|
"mean_token_accuracy": 0.14852236732840537,
|
|
"num_tokens": 2772152.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.0766355991363525,
|
|
"epoch": 0.12654527230203808,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999791875103694,
|
|
"loss": 5.9296,
|
|
"mean_token_accuracy": 0.14995151311159133,
|
|
"num_tokens": 2781459.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.126511430740356,
|
|
"epoch": 0.12696291346475108,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999787806350977,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.14601188898086548,
|
|
"num_tokens": 2791177.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.947288370132446,
|
|
"epoch": 0.1273805546274641,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999783698213016,
|
|
"loss": 5.873,
|
|
"mean_token_accuracy": 0.15467000156641006,
|
|
"num_tokens": 2800543.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.972626209259033,
|
|
"epoch": 0.12779819579017707,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999779550689885,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.15765649527311326,
|
|
"num_tokens": 2809301.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.0915940284729,
|
|
"epoch": 0.12821583695289007,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999775363781654,
|
|
"loss": 5.9221,
|
|
"mean_token_accuracy": 0.14328951239585877,
|
|
"num_tokens": 2818269.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.007693910598755,
|
|
"epoch": 0.12863347811560308,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999771137488395,
|
|
"loss": 5.776,
|
|
"mean_token_accuracy": 0.15171888172626496,
|
|
"num_tokens": 2827170.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.956274175643921,
|
|
"epoch": 0.12905111927831608,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999766871810188,
|
|
"loss": 5.7801,
|
|
"mean_token_accuracy": 0.15684526711702346,
|
|
"num_tokens": 2835320.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.969413709640503,
|
|
"epoch": 0.12946876044102906,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999762566747101,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.15092990100383757,
|
|
"num_tokens": 2843755.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.063136291503906,
|
|
"epoch": 0.12988640160374207,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999758222299214,
|
|
"loss": 5.8867,
|
|
"mean_token_accuracy": 0.14139319956302643,
|
|
"num_tokens": 2853462.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.024035835266114,
|
|
"epoch": 0.13030404276645507,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999753838466601,
|
|
"loss": 5.7984,
|
|
"mean_token_accuracy": 0.1518419101834297,
|
|
"num_tokens": 2863041.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.192575836181641,
|
|
"epoch": 0.13072168392916805,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999749415249338,
|
|
"loss": 6.0118,
|
|
"mean_token_accuracy": 0.14672885984182357,
|
|
"num_tokens": 2873019.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.968512344360351,
|
|
"epoch": 0.13113932509188106,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999744952647505,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.14861792474985122,
|
|
"num_tokens": 2881467.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.945395612716675,
|
|
"epoch": 0.13155696625459407,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999740450661176,
|
|
"loss": 5.8507,
|
|
"mean_token_accuracy": 0.14255610182881356,
|
|
"num_tokens": 2890914.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.9906907081604,
|
|
"epoch": 0.13197460741730704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999735909290436,
|
|
"loss": 5.7662,
|
|
"mean_token_accuracy": 0.15616359561681747,
|
|
"num_tokens": 2901164.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.008242225646972,
|
|
"epoch": 0.13239224858002005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999731328535358,
|
|
"loss": 5.9214,
|
|
"mean_token_accuracy": 0.14676916003227233,
|
|
"num_tokens": 2910560.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.969047927856446,
|
|
"epoch": 0.13280988974273306,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999726708396026,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.1559065029025078,
|
|
"num_tokens": 2918980.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.996972751617432,
|
|
"epoch": 0.13322753090544603,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499972204887252,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.14731249064207078,
|
|
"num_tokens": 2929516.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.111129522323608,
|
|
"epoch": 0.13364517206815904,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999717349964922,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.140457571297884,
|
|
"num_tokens": 2940603.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.054074048995972,
|
|
"epoch": 0.13406281323087205,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999712611673313,
|
|
"loss": 5.851,
|
|
"mean_token_accuracy": 0.14854641109704972,
|
|
"num_tokens": 2950082.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.9107592582702635,
|
|
"epoch": 0.13448045439358502,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999707833997777,
|
|
"loss": 5.7105,
|
|
"mean_token_accuracy": 0.15870693773031236,
|
|
"num_tokens": 2959098.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.108852100372315,
|
|
"epoch": 0.13489809555629803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999703016938398,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.15099167972803115,
|
|
"num_tokens": 2968585.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.004882907867431,
|
|
"epoch": 0.13531573671901104,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499969816049526,
|
|
"loss": 5.8873,
|
|
"mean_token_accuracy": 0.1482114464044571,
|
|
"num_tokens": 2978430.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.122372436523437,
|
|
"epoch": 0.13573337788172402,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999693264668446,
|
|
"loss": 5.9446,
|
|
"mean_token_accuracy": 0.14382612630724906,
|
|
"num_tokens": 2988398.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.039432668685913,
|
|
"epoch": 0.13615101904443702,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999688329458045,
|
|
"loss": 5.9617,
|
|
"mean_token_accuracy": 0.14274221137166024,
|
|
"num_tokens": 2999255.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.129848527908325,
|
|
"epoch": 0.13656866020715003,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999683354864141,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.15093710422515869,
|
|
"num_tokens": 3008638.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.9884625434875485,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999678340886823,
|
|
"loss": 5.8524,
|
|
"mean_token_accuracy": 0.14955973774194717,
|
|
"num_tokens": 3018070.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.922165441513061,
|
|
"epoch": 0.137403942532576,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999673287526176,
|
|
"loss": 5.8151,
|
|
"mean_token_accuracy": 0.15436604022979736,
|
|
"num_tokens": 3027878.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.128602933883667,
|
|
"epoch": 0.13782158369528902,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999668194782291,
|
|
"loss": 5.9886,
|
|
"mean_token_accuracy": 0.14296915978193284,
|
|
"num_tokens": 3037031.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.110314464569091,
|
|
"epoch": 0.138239224858002,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999663062655257,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.13569552153348924,
|
|
"num_tokens": 3046311.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.003753995895385,
|
|
"epoch": 0.138656866020715,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999657891145162,
|
|
"loss": 5.7534,
|
|
"mean_token_accuracy": 0.15544594079256058,
|
|
"num_tokens": 3055108.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.924490451812744,
|
|
"epoch": 0.139074507183428,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999652680252099,
|
|
"loss": 5.7931,
|
|
"mean_token_accuracy": 0.1543886348605156,
|
|
"num_tokens": 3063492.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.126929235458374,
|
|
"epoch": 0.139492148346141,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999647429976157,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.1553393468260765,
|
|
"num_tokens": 3072572.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.044676351547241,
|
|
"epoch": 0.139909789508854,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999642140317429,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.14429560154676438,
|
|
"num_tokens": 3082942.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.997855949401855,
|
|
"epoch": 0.140327430671567,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999636811276007,
|
|
"loss": 5.8469,
|
|
"mean_token_accuracy": 0.1536177761852741,
|
|
"num_tokens": 3091410.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.0224682807922365,
|
|
"epoch": 0.14074507183427998,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999631442851986,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.15009904503822327,
|
|
"num_tokens": 3100626.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.0320216655731205,
|
|
"epoch": 0.14116271299699298,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999626035045458,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.1567755565047264,
|
|
"num_tokens": 3109339.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.0257481098175045,
|
|
"epoch": 0.141580354159706,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999620587856519,
|
|
"loss": 5.8463,
|
|
"mean_token_accuracy": 0.1439797654747963,
|
|
"num_tokens": 3118636.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.952003431320191,
|
|
"epoch": 0.14199799532241897,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999615101285262,
|
|
"loss": 5.8113,
|
|
"mean_token_accuracy": 0.14703552275896073,
|
|
"num_tokens": 3128162.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.0136284828186035,
|
|
"epoch": 0.14241563648513197,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999609575331786,
|
|
"loss": 5.8267,
|
|
"mean_token_accuracy": 0.15116721987724305,
|
|
"num_tokens": 3136451.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.987718105316162,
|
|
"epoch": 0.14283327764784498,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999604009996186,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.1483292445540428,
|
|
"num_tokens": 3146599.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.0418936252594,
|
|
"epoch": 0.14325091881055796,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499959840527856,
|
|
"loss": 5.865,
|
|
"mean_token_accuracy": 0.14836757779121398,
|
|
"num_tokens": 3155941.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.981376600265503,
|
|
"epoch": 0.14366855997327097,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999592761179007,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.15541139990091324,
|
|
"num_tokens": 3164641.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.985382604598999,
|
|
"epoch": 0.14408620113598397,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999587077697624,
|
|
"loss": 5.836,
|
|
"mean_token_accuracy": 0.15462168231606482,
|
|
"num_tokens": 3173701.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.883602571487427,
|
|
"epoch": 0.14450384229869695,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999581354834512,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.15326338410377502,
|
|
"num_tokens": 3182268.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.8569074153900145,
|
|
"epoch": 0.14492148346140996,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499957559258977,
|
|
"loss": 5.7703,
|
|
"mean_token_accuracy": 0.15202518552541733,
|
|
"num_tokens": 3191513.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.987961149215698,
|
|
"epoch": 0.14533912462412296,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049995697909635,
|
|
"loss": 5.7246,
|
|
"mean_token_accuracy": 0.15589588582515718,
|
|
"num_tokens": 3200580.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.856524658203125,
|
|
"epoch": 0.14575676578683594,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999563949955803,
|
|
"loss": 5.8087,
|
|
"mean_token_accuracy": 0.1553361989557743,
|
|
"num_tokens": 3209053.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.0035093307495115,
|
|
"epoch": 0.14617440694954895,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499955806956678,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.15282343551516533,
|
|
"num_tokens": 3218241.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.058890104293823,
|
|
"epoch": 0.14659204811226195,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999552149796536,
|
|
"loss": 5.8465,
|
|
"mean_token_accuracy": 0.14872528836131096,
|
|
"num_tokens": 3227887.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.856602144241333,
|
|
"epoch": 0.14700968927497493,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999546190645175,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.16461554318666458,
|
|
"num_tokens": 3237281.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.890706157684326,
|
|
"epoch": 0.14742733043768794,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999540192112799,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.15412323474884032,
|
|
"num_tokens": 3246907.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.820692110061645,
|
|
"epoch": 0.14784497160040094,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999534154199514,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.15027530640363693,
|
|
"num_tokens": 3256312.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.074083471298218,
|
|
"epoch": 0.14826261276311392,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999528076905426,
|
|
"loss": 5.8001,
|
|
"mean_token_accuracy": 0.1542187049984932,
|
|
"num_tokens": 3265554.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.754930448532105,
|
|
"epoch": 0.14868025392582693,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999521960230641,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.1565927043557167,
|
|
"num_tokens": 3274731.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.933595037460327,
|
|
"epoch": 0.14909789508853993,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 5.7895,
|
|
"mean_token_accuracy": 0.14958274662494658,
|
|
"num_tokens": 3283518.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.951525926589966,
|
|
"epoch": 0.1495155362512529,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499950960873941,
|
|
"loss": 5.7859,
|
|
"mean_token_accuracy": 0.15745193660259246,
|
|
"num_tokens": 3292244.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.963454151153565,
|
|
"epoch": 0.14993317741396592,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999503373923182,
|
|
"loss": 5.765,
|
|
"mean_token_accuracy": 0.16077590733766556,
|
|
"num_tokens": 3301198.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.918994140625,
|
|
"epoch": 0.15035081857667892,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999497099726687,
|
|
"loss": 5.7452,
|
|
"mean_token_accuracy": 0.1589679017663002,
|
|
"num_tokens": 3309983.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.970966100692749,
|
|
"epoch": 0.1507684597393919,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999490786150039,
|
|
"loss": 5.837,
|
|
"mean_token_accuracy": 0.15418724715709686,
|
|
"num_tokens": 3319313.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.909102869033814,
|
|
"epoch": 0.1511861009021049,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999484433193348,
|
|
"loss": 5.6928,
|
|
"mean_token_accuracy": 0.1517741158604622,
|
|
"num_tokens": 3327497.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.8330848693847654,
|
|
"epoch": 0.15160374206481791,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999478040856722,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.15902745127677917,
|
|
"num_tokens": 3337029.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.866577863693237,
|
|
"epoch": 0.1520213832275309,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999471609140276,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.15399467051029206,
|
|
"num_tokens": 3346243.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.9908100128173825,
|
|
"epoch": 0.1524390243902439,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999465138044122,
|
|
"loss": 5.8181,
|
|
"mean_token_accuracy": 0.15329389721155168,
|
|
"num_tokens": 3354846.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.896318197250366,
|
|
"epoch": 0.1528566655529569,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999458627568373,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.14822318404912949,
|
|
"num_tokens": 3364683.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.946144962310791,
|
|
"epoch": 0.15327430671566988,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999452077713144,
|
|
"loss": 5.7304,
|
|
"mean_token_accuracy": 0.1531567633152008,
|
|
"num_tokens": 3374652.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.936914443969727,
|
|
"epoch": 0.1536919478783829,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999445488478547,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.1530358150601387,
|
|
"num_tokens": 3384040.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.872563695907592,
|
|
"epoch": 0.1541095890410959,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00049994388598647,
|
|
"loss": 5.809,
|
|
"mean_token_accuracy": 0.15368022173643112,
|
|
"num_tokens": 3393185.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.916036987304688,
|
|
"epoch": 0.15452723020380887,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999432191871719,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.1590338796377182,
|
|
"num_tokens": 3403077.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.922382068634033,
|
|
"epoch": 0.15494487136652188,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999425484499718,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.16295739710330964,
|
|
"num_tokens": 3412165.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.917156219482422,
|
|
"epoch": 0.1553625125292349,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999418737748817,
|
|
"loss": 5.7864,
|
|
"mean_token_accuracy": 0.15014993846416474,
|
|
"num_tokens": 3421162.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.0512267589569095,
|
|
"epoch": 0.15578015369194786,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999411951619134,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.14904813170433046,
|
|
"num_tokens": 3430363.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.9039225578308105,
|
|
"epoch": 0.15619779485466087,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999405126110786,
|
|
"loss": 5.7589,
|
|
"mean_token_accuracy": 0.15248761922121049,
|
|
"num_tokens": 3439199.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.058674573898315,
|
|
"epoch": 0.15661543601737388,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999398261223895,
|
|
"loss": 5.8786,
|
|
"mean_token_accuracy": 0.14814874157309532,
|
|
"num_tokens": 3448720.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.953385496139527,
|
|
"epoch": 0.15703307718008688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999391356958579,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.15151757299900054,
|
|
"num_tokens": 3458472.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.901563405990601,
|
|
"epoch": 0.15745071834279986,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499938441331496,
|
|
"loss": 5.7974,
|
|
"mean_token_accuracy": 0.15049149096012115,
|
|
"num_tokens": 3467140.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.021198081970215,
|
|
"epoch": 0.15786835950551287,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999377430293159,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.15717735141515732,
|
|
"num_tokens": 3476431.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.848060035705567,
|
|
"epoch": 0.15828600066822587,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999370407893299,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.16121015697717667,
|
|
"num_tokens": 3485768.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.948093843460083,
|
|
"epoch": 0.15870364183093885,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999363346115501,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.14542020708322526,
|
|
"num_tokens": 3495678.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.946852588653565,
|
|
"epoch": 0.15912128299365186,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999356244959893,
|
|
"loss": 5.8267,
|
|
"mean_token_accuracy": 0.1487009271979332,
|
|
"num_tokens": 3505168.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.898217058181762,
|
|
"epoch": 0.15953892415636486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999349104426594,
|
|
"loss": 5.7751,
|
|
"mean_token_accuracy": 0.1467003971338272,
|
|
"num_tokens": 3514498.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.959862756729126,
|
|
"epoch": 0.15995656531907784,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999341924515732,
|
|
"loss": 5.6972,
|
|
"mean_token_accuracy": 0.15165367797017099,
|
|
"num_tokens": 3524617.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.876605606079101,
|
|
"epoch": 0.16037420648179085,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999334705227431,
|
|
"loss": 5.6697,
|
|
"mean_token_accuracy": 0.16165476739406587,
|
|
"num_tokens": 3533523.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.918030166625977,
|
|
"epoch": 0.16079184764450385,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499932744656182,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.15332375168800355,
|
|
"num_tokens": 3542922.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.910229635238648,
|
|
"epoch": 0.16120948880721683,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999320148519024,
|
|
"loss": 5.7379,
|
|
"mean_token_accuracy": 0.15843380093574524,
|
|
"num_tokens": 3551827.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.871778774261474,
|
|
"epoch": 0.16162712996992984,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999312811099171,
|
|
"loss": 5.7178,
|
|
"mean_token_accuracy": 0.1555511921644211,
|
|
"num_tokens": 3560911.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.904352331161499,
|
|
"epoch": 0.16204477113264285,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999305434302391,
|
|
"loss": 5.7368,
|
|
"mean_token_accuracy": 0.15174949616193772,
|
|
"num_tokens": 3569473.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.919321489334107,
|
|
"epoch": 0.16246241229535582,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499929801812881,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.15868740230798722,
|
|
"num_tokens": 3578843.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.860245084762573,
|
|
"epoch": 0.16288005345806883,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999290562578561,
|
|
"loss": 5.7353,
|
|
"mean_token_accuracy": 0.15620914250612258,
|
|
"num_tokens": 3588304.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.888051176071167,
|
|
"epoch": 0.16329769462078184,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999283067651773,
|
|
"loss": 5.8009,
|
|
"mean_token_accuracy": 0.1543695256114006,
|
|
"num_tokens": 3598354.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.011698055267334,
|
|
"epoch": 0.16371533578349481,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999275533348577,
|
|
"loss": 5.8477,
|
|
"mean_token_accuracy": 0.1474734641611576,
|
|
"num_tokens": 3607503.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.79921932220459,
|
|
"epoch": 0.16413297694620782,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999267959669106,
|
|
"loss": 5.6562,
|
|
"mean_token_accuracy": 0.16296175867319107,
|
|
"num_tokens": 3617467.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.922436189651489,
|
|
"epoch": 0.16455061810892083,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999260346613491,
|
|
"loss": 5.6689,
|
|
"mean_token_accuracy": 0.1523266538977623,
|
|
"num_tokens": 3627048.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.803083086013794,
|
|
"epoch": 0.1649682592716338,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999252694181867,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.15438316911458969,
|
|
"num_tokens": 3636683.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.812573051452636,
|
|
"epoch": 0.1653859004343468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999245002374367,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.16638619005680083,
|
|
"num_tokens": 3645231.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.846198654174804,
|
|
"epoch": 0.16580354159705982,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999237271191125,
|
|
"loss": 5.6846,
|
|
"mean_token_accuracy": 0.1619308263063431,
|
|
"num_tokens": 3653851.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.832628393173218,
|
|
"epoch": 0.1662211827597728,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999229500632279,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.16223268061876298,
|
|
"num_tokens": 3662720.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.705533599853515,
|
|
"epoch": 0.1666388239224858,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999221690697961,
|
|
"loss": 5.6132,
|
|
"mean_token_accuracy": 0.16336482465267183,
|
|
"num_tokens": 3671777.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.847080707550049,
|
|
"epoch": 0.1670564650851988,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999213841388312,
|
|
"loss": 5.6881,
|
|
"mean_token_accuracy": 0.16348690390586854,
|
|
"num_tokens": 3681390.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.917251682281494,
|
|
"epoch": 0.16747410624791179,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999205952703466,
|
|
"loss": 5.7464,
|
|
"mean_token_accuracy": 0.1585702434182167,
|
|
"num_tokens": 3690899.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.978084659576416,
|
|
"epoch": 0.1678917474106248,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999198024643563,
|
|
"loss": 5.8358,
|
|
"mean_token_accuracy": 0.1485416978597641,
|
|
"num_tokens": 3699891.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.7726466178894045,
|
|
"epoch": 0.1683093885733378,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999190057208741,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.16494597047567366,
|
|
"num_tokens": 3709860.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.8699462890625,
|
|
"epoch": 0.16872702973605078,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499918205039914,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.15509038269519806,
|
|
"num_tokens": 3718896.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.803660774230957,
|
|
"epoch": 0.16914467089876378,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999174004214899,
|
|
"loss": 5.5717,
|
|
"mean_token_accuracy": 0.1623939424753189,
|
|
"num_tokens": 3727355.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.7896076202392575,
|
|
"epoch": 0.1695623120614768,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999165918656161,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.15922652035951615,
|
|
"num_tokens": 3736191.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.883917236328125,
|
|
"epoch": 0.16997995322418977,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999157793723065,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.15698790550231934,
|
|
"num_tokens": 3744832.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.81550817489624,
|
|
"epoch": 0.17039759438690277,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999149629415755,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.15519305020570756,
|
|
"num_tokens": 3753835.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.9895366668701175,
|
|
"epoch": 0.17081523554961578,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999141425734374,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.1554757535457611,
|
|
"num_tokens": 3762816.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.809294700622559,
|
|
"epoch": 0.17123287671232876,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999133182679064,
|
|
"loss": 5.7946,
|
|
"mean_token_accuracy": 0.15067907720804213,
|
|
"num_tokens": 3773244.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.8846066951751705,
|
|
"epoch": 0.17165051787504176,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999124900249971,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.16037556380033494,
|
|
"num_tokens": 3782122.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.842645502090454,
|
|
"epoch": 0.17206815903775477,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999116578447239,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.16681777983903884,
|
|
"num_tokens": 3791303.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.874477386474609,
|
|
"epoch": 0.17248580020046775,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999108217271015,
|
|
"loss": 5.7206,
|
|
"mean_token_accuracy": 0.1557923972606659,
|
|
"num_tokens": 3800991.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.81466908454895,
|
|
"epoch": 0.17290344136318075,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999099816721444,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.15679699778556824,
|
|
"num_tokens": 3811293.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.934940910339355,
|
|
"epoch": 0.17332108252589376,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999091376798673,
|
|
"loss": 5.7245,
|
|
"mean_token_accuracy": 0.1563497804105282,
|
|
"num_tokens": 3820013.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.82628173828125,
|
|
"epoch": 0.17373872368860674,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999082897502849,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.16271923631429672,
|
|
"num_tokens": 3829099.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.759806680679321,
|
|
"epoch": 0.17415636485131974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999074378834123,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.1553027555346489,
|
|
"num_tokens": 3838308.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.896584510803223,
|
|
"epoch": 0.17457400601403275,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999065820792644,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.16025962680578232,
|
|
"num_tokens": 3847650.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.934039211273193,
|
|
"epoch": 0.17499164717674573,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999057223378559,
|
|
"loss": 5.844,
|
|
"mean_token_accuracy": 0.14192623198032378,
|
|
"num_tokens": 3857252.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.864416837692261,
|
|
"epoch": 0.17540928833945874,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499904858659202,
|
|
"loss": 5.7049,
|
|
"mean_token_accuracy": 0.15697439014911652,
|
|
"num_tokens": 3865747.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.810830020904541,
|
|
"epoch": 0.17582692950217174,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999039910433179,
|
|
"loss": 5.659,
|
|
"mean_token_accuracy": 0.1645386263728142,
|
|
"num_tokens": 3874958.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.744087553024292,
|
|
"epoch": 0.17624457066488472,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999031194902187,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.16506801843643187,
|
|
"num_tokens": 3885216.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.754455709457398,
|
|
"epoch": 0.17666221182759773,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999022439999198,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.1671660214662552,
|
|
"num_tokens": 3893973.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.944645500183105,
|
|
"epoch": 0.17707985299031073,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999013645724362,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.15572567880153657,
|
|
"num_tokens": 3903532.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.836982297897339,
|
|
"epoch": 0.1774974941530237,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999004812077836,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.15952192693948747,
|
|
"num_tokens": 3913427.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.893245220184326,
|
|
"epoch": 0.17791513531573672,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998995939059773,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.14690941274166108,
|
|
"num_tokens": 3923870.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.807616281509399,
|
|
"epoch": 0.17833277647844972,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499898702667033,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.16058423221111298,
|
|
"num_tokens": 3933469.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.830925941467285,
|
|
"epoch": 0.1787504176411627,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998978074909661,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.17098447531461716,
|
|
"num_tokens": 3942427.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.76401195526123,
|
|
"epoch": 0.1791680588038757,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998969083777925,
|
|
"loss": 5.6649,
|
|
"mean_token_accuracy": 0.1665211722254753,
|
|
"num_tokens": 3951250.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.841114616394043,
|
|
"epoch": 0.1795856999665887,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998960053275277,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.16053525656461715,
|
|
"num_tokens": 3959969.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.82116289138794,
|
|
"epoch": 0.1800033411293017,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998950983401875,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.1598428264260292,
|
|
"num_tokens": 3968171.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.894432878494262,
|
|
"epoch": 0.1804209822920147,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998941874157882,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.1645335629582405,
|
|
"num_tokens": 3976686.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.7327415466308596,
|
|
"epoch": 0.1808386234547277,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998932725543453,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.1576009765267372,
|
|
"num_tokens": 3986552.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.8359321594238285,
|
|
"epoch": 0.18125626461744068,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998923537558749,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.15782566368579865,
|
|
"num_tokens": 3995501.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.710008239746093,
|
|
"epoch": 0.1816739057801537,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998914310203932,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.1638147160410881,
|
|
"num_tokens": 4004423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.84242000579834,
|
|
"epoch": 0.1820915469428667,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998905043479163,
|
|
"loss": 5.7582,
|
|
"mean_token_accuracy": 0.15638344138860702,
|
|
"num_tokens": 4013324.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.852623367309571,
|
|
"epoch": 0.18250918810557967,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998895737384605,
|
|
"loss": 5.6477,
|
|
"mean_token_accuracy": 0.15933823138475417,
|
|
"num_tokens": 4021896.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.727082061767578,
|
|
"epoch": 0.18292682926829268,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998886391920418,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.15712598264217376,
|
|
"num_tokens": 4030590.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.802021408081055,
|
|
"epoch": 0.18334447043100568,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998877007086769,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.16887603253126143,
|
|
"num_tokens": 4040041.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.7888710498809814,
|
|
"epoch": 0.18376211159371866,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998867582883821,
|
|
"loss": 5.6962,
|
|
"mean_token_accuracy": 0.1554000347852707,
|
|
"num_tokens": 4049119.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.80960488319397,
|
|
"epoch": 0.18417975275643167,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998858119311739,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.15796089097857474,
|
|
"num_tokens": 4059265.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.779888057708741,
|
|
"epoch": 0.18459739391914468,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998848616370689,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.159270016849041,
|
|
"num_tokens": 4068363.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.799966812133789,
|
|
"epoch": 0.18501503508185768,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998839074060837,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.16761811226606368,
|
|
"num_tokens": 4077390.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.7324597358703615,
|
|
"epoch": 0.18543267624457066,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499882949238235,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.15475580096244812,
|
|
"num_tokens": 4087331.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.980052328109741,
|
|
"epoch": 0.18585031740728367,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998819871335396,
|
|
"loss": 5.8267,
|
|
"mean_token_accuracy": 0.15336512476205827,
|
|
"num_tokens": 4096425.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.77472767829895,
|
|
"epoch": 0.18626795856999667,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998810210920142,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.16035911142826081,
|
|
"num_tokens": 4106056.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.701298999786377,
|
|
"epoch": 0.18668559973270965,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998800511136759,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.15928506404161452,
|
|
"num_tokens": 4115133.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.816712808609009,
|
|
"epoch": 0.18710324089542266,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998790771985417,
|
|
"loss": 5.5912,
|
|
"mean_token_accuracy": 0.160226671397686,
|
|
"num_tokens": 4123630.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.731363201141358,
|
|
"epoch": 0.18752088205813566,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998780993466284,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.16045138984918594,
|
|
"num_tokens": 4133337.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.8761168956756595,
|
|
"epoch": 0.18793852322084864,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998771175579534,
|
|
"loss": 5.6467,
|
|
"mean_token_accuracy": 0.16236401796340943,
|
|
"num_tokens": 4142240.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.759765577316284,
|
|
"epoch": 0.18835616438356165,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998761318325337,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.15987929254770278,
|
|
"num_tokens": 4151297.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.761353254318237,
|
|
"epoch": 0.18877380554627465,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998751421703868,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.1627461642026901,
|
|
"num_tokens": 4160193.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.856572532653809,
|
|
"epoch": 0.18919144670898763,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998741485715297,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.15776600688695908,
|
|
"num_tokens": 4169948.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.932883214950562,
|
|
"epoch": 0.18960908787170064,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049987315103598,
|
|
"loss": 5.7576,
|
|
"mean_token_accuracy": 0.15294902846217157,
|
|
"num_tokens": 4179981.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.834502363204956,
|
|
"epoch": 0.19002672903441364,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998721495637551,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.15345177948474883,
|
|
"num_tokens": 4189172.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.774939393997192,
|
|
"epoch": 0.19044437019712662,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998711441548726,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.15776675045490265,
|
|
"num_tokens": 4197312.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.827042913436889,
|
|
"epoch": 0.19086201135983963,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998701348093499,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.1647990196943283,
|
|
"num_tokens": 4206828.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.904668378829956,
|
|
"epoch": 0.19127965252255263,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499869121527205,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.16681263595819473,
|
|
"num_tokens": 4214835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.8230327606201175,
|
|
"epoch": 0.1916972936852656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998681043084553,
|
|
"loss": 5.7899,
|
|
"mean_token_accuracy": 0.14819930419325827,
|
|
"num_tokens": 4225119.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.684073781967163,
|
|
"epoch": 0.19211493484797862,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998670831531188,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.16301271319389343,
|
|
"num_tokens": 4235257.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.862882328033447,
|
|
"epoch": 0.19253257601069163,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998660580612135,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.16653790175914765,
|
|
"num_tokens": 4244211.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.840312385559082,
|
|
"epoch": 0.1929502171734046,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998650290327569,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.15949375480413436,
|
|
"num_tokens": 4253149.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.719400072097779,
|
|
"epoch": 0.1933678583361176,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998639960677675,
|
|
"loss": 5.6045,
|
|
"mean_token_accuracy": 0.16629393100738527,
|
|
"num_tokens": 4262557.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.765211296081543,
|
|
"epoch": 0.19378549949883062,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998629591662631,
|
|
"loss": 5.6186,
|
|
"mean_token_accuracy": 0.1608939915895462,
|
|
"num_tokens": 4272881.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.732853174209595,
|
|
"epoch": 0.1942031406615436,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499861918328262,
|
|
"loss": 5.6153,
|
|
"mean_token_accuracy": 0.16830391734838485,
|
|
"num_tokens": 4281158.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.767421293258667,
|
|
"epoch": 0.1946207818242566,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998608735537822,
|
|
"loss": 5.613,
|
|
"mean_token_accuracy": 0.15854829102754592,
|
|
"num_tokens": 4290319.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.8061658382415775,
|
|
"epoch": 0.1950384229869696,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998598248428423,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.1628992959856987,
|
|
"num_tokens": 4299276.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.820240068435669,
|
|
"epoch": 0.19545606414968258,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998587721954604,
|
|
"loss": 5.6563,
|
|
"mean_token_accuracy": 0.16527265459299087,
|
|
"num_tokens": 4308291.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.764502143859863,
|
|
"epoch": 0.1958737053123956,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.1616749197244644,
|
|
"num_tokens": 4316654.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.757666826248169,
|
|
"epoch": 0.1962913464751086,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998566550914448,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.16192719340324402,
|
|
"num_tokens": 4325911.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.76278510093689,
|
|
"epoch": 0.19670898763782158,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998555906348481,
|
|
"loss": 5.7319,
|
|
"mean_token_accuracy": 0.15768774896860122,
|
|
"num_tokens": 4334846.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.823022794723511,
|
|
"epoch": 0.19712662880053458,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998545222418836,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.1655540272593498,
|
|
"num_tokens": 4343728.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.810211420059204,
|
|
"epoch": 0.1975442699632476,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998534499125701,
|
|
"loss": 5.6015,
|
|
"mean_token_accuracy": 0.1647025465965271,
|
|
"num_tokens": 4352774.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.798485040664673,
|
|
"epoch": 0.19796191112596057,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998523736469263,
|
|
"loss": 5.7515,
|
|
"mean_token_accuracy": 0.15903669595718384,
|
|
"num_tokens": 4361663.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.767217540740967,
|
|
"epoch": 0.19837955228867357,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499851293444971,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.17194907814264299,
|
|
"num_tokens": 4370278.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.825853443145752,
|
|
"epoch": 0.19879719345138658,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998502093067231,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.16817053258419037,
|
|
"num_tokens": 4379010.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.835199785232544,
|
|
"epoch": 0.19921483461409956,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998491212322017,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.161689792573452,
|
|
"num_tokens": 4388145.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.710544586181641,
|
|
"epoch": 0.19963247577681256,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998480292214258,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.16246786564588547,
|
|
"num_tokens": 4396321.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.789666175842285,
|
|
"epoch": 0.20005011693952557,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998469332744144,
|
|
"loss": 5.5277,
|
|
"mean_token_accuracy": 0.1656605526804924,
|
|
"num_tokens": 4404854.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.63559889793396,
|
|
"epoch": 0.20046775810223855,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998458333911869,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.169854998588562,
|
|
"num_tokens": 4413890.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.735365390777588,
|
|
"epoch": 0.20088539926495155,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998447295717624,
|
|
"loss": 5.6776,
|
|
"mean_token_accuracy": 0.15991291105747224,
|
|
"num_tokens": 4423019.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.759283638000488,
|
|
"epoch": 0.20130304042766456,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998436218161602,
|
|
"loss": 5.6051,
|
|
"mean_token_accuracy": 0.16260855495929719,
|
|
"num_tokens": 4432340.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.737146377563477,
|
|
"epoch": 0.20172068159037754,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998425101243999,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.16569507718086243,
|
|
"num_tokens": 4441834.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.740446710586548,
|
|
"epoch": 0.20213832275309054,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998413944965007,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.16548486649990082,
|
|
"num_tokens": 4450864.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.706497478485107,
|
|
"epoch": 0.20255596391580355,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998402749324823,
|
|
"loss": 5.6982,
|
|
"mean_token_accuracy": 0.1565281093120575,
|
|
"num_tokens": 4460697.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.930861711502075,
|
|
"epoch": 0.20297360507851653,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998391514323642,
|
|
"loss": 5.7108,
|
|
"mean_token_accuracy": 0.1600305914878845,
|
|
"num_tokens": 4469926.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.704679727554321,
|
|
"epoch": 0.20339124624122953,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998380239961661,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.16277854442596434,
|
|
"num_tokens": 4478818.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.797401666641235,
|
|
"epoch": 0.20380888740394254,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998368926239078,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.16615838557481766,
|
|
"num_tokens": 4487451.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.729301643371582,
|
|
"epoch": 0.20422652856665552,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499835757315609,
|
|
"loss": 5.6466,
|
|
"mean_token_accuracy": 0.15662010610103608,
|
|
"num_tokens": 4497674.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.70154185295105,
|
|
"epoch": 0.20464416972936852,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998346180712898,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.17245133817195893,
|
|
"num_tokens": 4507666.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.775140380859375,
|
|
"epoch": 0.20506181089208153,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998334748909698,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.15649858564138414,
|
|
"num_tokens": 4517409.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.744282531738281,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998323277746694,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.167903570830822,
|
|
"num_tokens": 4526495.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.750102710723877,
|
|
"epoch": 0.20589709321750752,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998311767224081,
|
|
"loss": 5.5807,
|
|
"mean_token_accuracy": 0.17419597804546355,
|
|
"num_tokens": 4535240.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.732834100723267,
|
|
"epoch": 0.20631473438022052,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998300217342067,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.15876903831958772,
|
|
"num_tokens": 4544716.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.706253528594971,
|
|
"epoch": 0.2067323755429335,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998288628100851,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.1646232396364212,
|
|
"num_tokens": 4553867.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.765943002700806,
|
|
"epoch": 0.2071500167056465,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998276999500636,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.15891273021698,
|
|
"num_tokens": 4562529.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.631934547424317,
|
|
"epoch": 0.2075676578683595,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.17996778339147568,
|
|
"num_tokens": 4571041.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.640371704101563,
|
|
"epoch": 0.2079852990310725,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998253624224026,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.16657757610082627,
|
|
"num_tokens": 4579914.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.763918113708496,
|
|
"epoch": 0.2084029401937855,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499824187754804,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.16418944895267487,
|
|
"num_tokens": 4590277.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.712745714187622,
|
|
"epoch": 0.2088205813564985,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998230091513872,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.1670702204108238,
|
|
"num_tokens": 4598719.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.713497543334961,
|
|
"epoch": 0.20923822251921148,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998218266121731,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.16411634981632234,
|
|
"num_tokens": 4607804.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.684199476242066,
|
|
"epoch": 0.2096558636819245,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998206401371823,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.16946808695793153,
|
|
"num_tokens": 4616529.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.745693397521973,
|
|
"epoch": 0.2100735048446375,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998194497264357,
|
|
"loss": 5.5853,
|
|
"mean_token_accuracy": 0.16157063841819763,
|
|
"num_tokens": 4624545.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.682206106185913,
|
|
"epoch": 0.21049114600735047,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998182553799538,
|
|
"loss": 5.5612,
|
|
"mean_token_accuracy": 0.16494014412164687,
|
|
"num_tokens": 4633316.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.716932487487793,
|
|
"epoch": 0.21090878717006348,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998170570977579,
|
|
"loss": 5.5239,
|
|
"mean_token_accuracy": 0.17361541986465454,
|
|
"num_tokens": 4643353.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.672225570678711,
|
|
"epoch": 0.21132642833277648,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998158548798687,
|
|
"loss": 5.6111,
|
|
"mean_token_accuracy": 0.15904673039913178,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.804123878479004,
|
|
"epoch": 0.21174406949548946,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998146487263074,
|
|
"loss": 5.5887,
|
|
"mean_token_accuracy": 0.16919029206037522,
|
|
"num_tokens": 4659937.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.694881916046143,
|
|
"epoch": 0.21216171065820247,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998134386370951,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.16248628944158555,
|
|
"num_tokens": 4669396.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.780102729797363,
|
|
"epoch": 0.21257935182091547,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998122246122529,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.16667612195014953,
|
|
"num_tokens": 4679320.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.78121657371521,
|
|
"epoch": 0.21299699298362845,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998110066518021,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.16336911022663117,
|
|
"num_tokens": 4688807.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.7891148090362545,
|
|
"epoch": 0.21341463414634146,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499809784755764,
|
|
"loss": 5.586,
|
|
"mean_token_accuracy": 0.1745486855506897,
|
|
"num_tokens": 4697819.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.657274389266968,
|
|
"epoch": 0.21383227530905446,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049980855892416,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.16846721321344377,
|
|
"num_tokens": 4706931.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.702887630462646,
|
|
"epoch": 0.21424991647176747,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998073291570116,
|
|
"loss": 5.5458,
|
|
"mean_token_accuracy": 0.16121839135885238,
|
|
"num_tokens": 4716262.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.719077396392822,
|
|
"epoch": 0.21466755763448045,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998060954543404,
|
|
"loss": 5.5625,
|
|
"mean_token_accuracy": 0.16510672271251678,
|
|
"num_tokens": 4725415.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.698775100708008,
|
|
"epoch": 0.21508519879719346,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998048578161678,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.1652575522661209,
|
|
"num_tokens": 4734580.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.629653978347778,
|
|
"epoch": 0.21550283995990646,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998036162425155,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.1736736297607422,
|
|
"num_tokens": 4742966.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.673403930664063,
|
|
"epoch": 0.21592048112261944,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998023707334055,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.16784193962812424,
|
|
"num_tokens": 4751696.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.810158061981201,
|
|
"epoch": 0.21633812228533245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998011212888592,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.1684272915124893,
|
|
"num_tokens": 4760460.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.736129999160767,
|
|
"epoch": 0.21675576344804545,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997998679088988,
|
|
"loss": 5.5736,
|
|
"mean_token_accuracy": 0.16521882116794587,
|
|
"num_tokens": 4769004.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.699703645706177,
|
|
"epoch": 0.21717340461075843,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997986105935461,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.17166536301374435,
|
|
"num_tokens": 4777204.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.832093715667725,
|
|
"epoch": 0.21759104577347144,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997973493428231,
|
|
"loss": 5.68,
|
|
"mean_token_accuracy": 0.16324937492609023,
|
|
"num_tokens": 4786766.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.5970458984375,
|
|
"epoch": 0.21800868693618444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997960841567519,
|
|
"loss": 5.5624,
|
|
"mean_token_accuracy": 0.16770660877227783,
|
|
"num_tokens": 4796676.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.866506433486938,
|
|
"epoch": 0.21842632809889742,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997948150353548,
|
|
"loss": 5.5635,
|
|
"mean_token_accuracy": 0.16808499097824098,
|
|
"num_tokens": 4805514.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.711924076080322,
|
|
"epoch": 0.21884396926161043,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997935419786537,
|
|
"loss": 5.6443,
|
|
"mean_token_accuracy": 0.1581789255142212,
|
|
"num_tokens": 4815487.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.754567623138428,
|
|
"epoch": 0.21926161042432343,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997922649866712,
|
|
"loss": 5.6067,
|
|
"mean_token_accuracy": 0.1666237533092499,
|
|
"num_tokens": 4825044.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.642407846450806,
|
|
"epoch": 0.2196792515870364,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997909840594294,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.1773268923163414,
|
|
"num_tokens": 4833875.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.627975368499756,
|
|
"epoch": 0.22009689274974942,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997896991969509,
|
|
"loss": 5.625,
|
|
"mean_token_accuracy": 0.15834506303071977,
|
|
"num_tokens": 4843317.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.7512366771698,
|
|
"epoch": 0.22051453391246242,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997884103992581,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.16193510740995407,
|
|
"num_tokens": 4852514.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.652145338058472,
|
|
"epoch": 0.2209321750751754,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997871176663736,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.17478466778993607,
|
|
"num_tokens": 4861260.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.647412824630737,
|
|
"epoch": 0.2213498162378884,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997858209983201,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.1661353215575218,
|
|
"num_tokens": 4869654.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.697892093658448,
|
|
"epoch": 0.22176745740060141,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997845203951202,
|
|
"loss": 5.5662,
|
|
"mean_token_accuracy": 0.15931454449892044,
|
|
"num_tokens": 4878311.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.775735664367676,
|
|
"epoch": 0.2221850985633144,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997832158567967,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.16189286559820176,
|
|
"num_tokens": 4887251.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.661660861968994,
|
|
"epoch": 0.2226027397260274,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997819073833724,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.16523526906967162,
|
|
"num_tokens": 4896528.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.6543995380401615,
|
|
"epoch": 0.2230203808887404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997805949748702,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.16553283780813216,
|
|
"num_tokens": 4904962.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.735087060928345,
|
|
"epoch": 0.22343802205145338,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997792786313132,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.16544881463050842,
|
|
"num_tokens": 4914735.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.543456125259399,
|
|
"epoch": 0.2238556632141664,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997779583527243,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.1624772235751152,
|
|
"num_tokens": 4924271.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.808428812026977,
|
|
"epoch": 0.2242733043768794,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997766341391268,
|
|
"loss": 5.671,
|
|
"mean_token_accuracy": 0.16082177311182022,
|
|
"num_tokens": 4933928.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.692340898513794,
|
|
"epoch": 0.22469094553959237,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997753059905437,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.17430844008922577,
|
|
"num_tokens": 4942714.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.564800643920899,
|
|
"epoch": 0.22510858670230538,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997739739069981,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.17042783945798873,
|
|
"num_tokens": 4952297.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.639291620254516,
|
|
"epoch": 0.22552622786501839,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997726378885138,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.17526621520519256,
|
|
"num_tokens": 4960947.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.712133836746216,
|
|
"epoch": 0.22594386902773136,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004997712979351137,
|
|
"loss": 5.615,
|
|
"mean_token_accuracy": 0.16013166829943656,
|
|
"num_tokens": 4969705.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.725390529632568,
|
|
"epoch": 0.22636151019044437,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997699540468216,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.16332891583442688,
|
|
"num_tokens": 4979112.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.675234031677246,
|
|
"epoch": 0.22677915135315738,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997686062236609,
|
|
"loss": 5.506,
|
|
"mean_token_accuracy": 0.1692604660987854,
|
|
"num_tokens": 4987894.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.71347975730896,
|
|
"epoch": 0.22719679251587035,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997672544656553,
|
|
"loss": 5.6388,
|
|
"mean_token_accuracy": 0.16482105404138564,
|
|
"num_tokens": 4997774.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.727224731445313,
|
|
"epoch": 0.22761443367858336,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997658987728283,
|
|
"loss": 5.5714,
|
|
"mean_token_accuracy": 0.17016370892524718,
|
|
"num_tokens": 5006183.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.6868468761444095,
|
|
"epoch": 0.22803207484129637,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997645391452035,
|
|
"loss": 5.5612,
|
|
"mean_token_accuracy": 0.16689683645963668,
|
|
"num_tokens": 5016909.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.735447740554809,
|
|
"epoch": 0.22844971600400935,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499763175582805,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.16711424440145492,
|
|
"num_tokens": 5027326.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.719646978378296,
|
|
"epoch": 0.22886735716672235,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997618080856566,
|
|
"loss": 5.5495,
|
|
"mean_token_accuracy": 0.16903014183044435,
|
|
"num_tokens": 5037043.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.604584503173828,
|
|
"epoch": 0.22928499832943536,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997604366537823,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.1673525631427765,
|
|
"num_tokens": 5045992.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.626076936721802,
|
|
"epoch": 0.22970263949214834,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997590612872058,
|
|
"loss": 5.5183,
|
|
"mean_token_accuracy": 0.1726035326719284,
|
|
"num_tokens": 5055568.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.741823148727417,
|
|
"epoch": 0.23012028065486134,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997576819859515,
|
|
"loss": 5.5923,
|
|
"mean_token_accuracy": 0.16661985069513321,
|
|
"num_tokens": 5065512.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.562215900421142,
|
|
"epoch": 0.23053792181757435,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997562987500434,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.17851751446723937,
|
|
"num_tokens": 5074776.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.584406423568725,
|
|
"epoch": 0.23095556298028733,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997549115795058,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.17101089656352997,
|
|
"num_tokens": 5084743.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.762922859191894,
|
|
"epoch": 0.23137320414300033,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499753520474363,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.16293612420558928,
|
|
"num_tokens": 5095387.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.643383598327636,
|
|
"epoch": 0.23179084530571334,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997521254346391,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.17110240757465361,
|
|
"num_tokens": 5104628.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.731733131408691,
|
|
"epoch": 0.23220848646842632,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997507264603589,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.17133565843105317,
|
|
"num_tokens": 5113169.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.664657878875732,
|
|
"epoch": 0.23262612763113932,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997493235515466,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.16721148937940597,
|
|
"num_tokens": 5122294.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.568096113204956,
|
|
"epoch": 0.23304376879385233,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997479167082269,
|
|
"loss": 5.4109,
|
|
"mean_token_accuracy": 0.17732056379318237,
|
|
"num_tokens": 5131191.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.633753061294556,
|
|
"epoch": 0.2334614099565653,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997465059304243,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.16502068489789962,
|
|
"num_tokens": 5141974.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.777873897552491,
|
|
"epoch": 0.23387905111927831,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997450912181637,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.16790447533130645,
|
|
"num_tokens": 5151412.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.601756000518799,
|
|
"epoch": 0.23429669228199132,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997436725714696,
|
|
"loss": 5.4844,
|
|
"mean_token_accuracy": 0.17448533326387405,
|
|
"num_tokens": 5160989.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.64455623626709,
|
|
"epoch": 0.2347143334447043,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997422499903671,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.16700967252254487,
|
|
"num_tokens": 5170241.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.763780546188355,
|
|
"epoch": 0.2351319746074173,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499740823474881,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.16039506942033768,
|
|
"num_tokens": 5180247.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.686127328872681,
|
|
"epoch": 0.2355496157701303,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997393930250363,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.1688424378633499,
|
|
"num_tokens": 5189144.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.624299049377441,
|
|
"epoch": 0.2359672569328433,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499737958640858,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.1643349289894104,
|
|
"num_tokens": 5199410.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.713594150543213,
|
|
"epoch": 0.2363848980955563,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997365203223711,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.1714593917131424,
|
|
"num_tokens": 5209032.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.528335237503052,
|
|
"epoch": 0.2368025392582693,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499735078069601,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.17411164492368697,
|
|
"num_tokens": 5217787.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.589128541946411,
|
|
"epoch": 0.23722018042098228,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997336318825728,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.17099891901016234,
|
|
"num_tokens": 5226962.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.6476799011230465,
|
|
"epoch": 0.23763782158369529,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997321817613119,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.17186253815889357,
|
|
"num_tokens": 5236111.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.721078395843506,
|
|
"epoch": 0.2380554627464083,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997307277058436,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.1622317001223564,
|
|
"num_tokens": 5246628.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.663838911056518,
|
|
"epoch": 0.23847310390912127,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997292697161935,
|
|
"loss": 5.5422,
|
|
"mean_token_accuracy": 0.16941989213228226,
|
|
"num_tokens": 5255543.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.553099489212036,
|
|
"epoch": 0.23889074507183428,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499727807792387,
|
|
"loss": 5.3969,
|
|
"mean_token_accuracy": 0.17895766198635102,
|
|
"num_tokens": 5264559.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.56001091003418,
|
|
"epoch": 0.23930838623454728,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997263419344495,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.1690398707985878,
|
|
"num_tokens": 5274599.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.5944366455078125,
|
|
"epoch": 0.23972602739726026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997248721424071,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.17228546887636184,
|
|
"num_tokens": 5283495.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.7175524711608885,
|
|
"epoch": 0.24014366855997327,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997233984162853,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.1762276753783226,
|
|
"num_tokens": 5292064.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.618496513366699,
|
|
"epoch": 0.24056130972268627,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997219207561099,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.16717917770147322,
|
|
"num_tokens": 5301696.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.672824716567993,
|
|
"epoch": 0.24097895088539925,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997204391619068,
|
|
"loss": 5.6309,
|
|
"mean_token_accuracy": 0.16025216281414031,
|
|
"num_tokens": 5311427.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.8007079601287845,
|
|
"epoch": 0.24139659204811226,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997189536337018,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.1670021340250969,
|
|
"num_tokens": 5321406.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.68375244140625,
|
|
"epoch": 0.24181423321082526,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997174641715211,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.16562104225158691,
|
|
"num_tokens": 5332257.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.524214267730713,
|
|
"epoch": 0.24223187437353827,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997159707753906,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.1770200565457344,
|
|
"num_tokens": 5341857.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.61238694190979,
|
|
"epoch": 0.24264951553625125,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.17293385416269302,
|
|
"num_tokens": 5351367.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.561303424835205,
|
|
"epoch": 0.24306715669896425,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997129721813853,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.17672393321990967,
|
|
"num_tokens": 5360627.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.612178468704224,
|
|
"epoch": 0.24348479786167726,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997114669835629,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.18178218305110933,
|
|
"num_tokens": 5369703.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.626357889175415,
|
|
"epoch": 0.24390243902439024,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997099578518959,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.16822381019592286,
|
|
"num_tokens": 5378432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.549802303314209,
|
|
"epoch": 0.24432008018710324,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004997084447864105,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.1717028349637985,
|
|
"num_tokens": 5386489.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.731553316116333,
|
|
"epoch": 0.24473772134981625,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997069277871333,
|
|
"loss": 5.5927,
|
|
"mean_token_accuracy": 0.16572516411542892,
|
|
"num_tokens": 5395908.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.730947780609131,
|
|
"epoch": 0.24515536251252923,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997054068540908,
|
|
"loss": 5.5232,
|
|
"mean_token_accuracy": 0.17338006645441056,
|
|
"num_tokens": 5404822.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.546732187271118,
|
|
"epoch": 0.24557300367524224,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997038819873098,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.1758014366030693,
|
|
"num_tokens": 5413980.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.5830179214477536,
|
|
"epoch": 0.24599064483795524,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997023531868167,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.1676984280347824,
|
|
"num_tokens": 5423538.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.577688503265381,
|
|
"epoch": 0.24640828600066822,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997008204526386,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.17327087819576265,
|
|
"num_tokens": 5431930.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.603110074996948,
|
|
"epoch": 0.24682592716338123,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996992837848021,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.1806345522403717,
|
|
"num_tokens": 5440721.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.566134643554688,
|
|
"epoch": 0.24724356832609423,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996977431833342,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.1686984345316887,
|
|
"num_tokens": 5449617.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.592004728317261,
|
|
"epoch": 0.2476612094888072,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996961986482618,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.16898861825466155,
|
|
"num_tokens": 5458827.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.65282416343689,
|
|
"epoch": 0.24807885065152022,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996946501796119,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.1748599410057068,
|
|
"num_tokens": 5467348.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.639726400375366,
|
|
"epoch": 0.24849649181423322,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996930977774118,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.16322759091854094,
|
|
"num_tokens": 5476645.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.68959789276123,
|
|
"epoch": 0.2489141329769462,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996915414416885,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.16389098167419433,
|
|
"num_tokens": 5486120.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.6930344581604,
|
|
"epoch": 0.2493317741396592,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996899811724693,
|
|
"loss": 5.5118,
|
|
"mean_token_accuracy": 0.1725097730755806,
|
|
"num_tokens": 5495313.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.617242097854614,
|
|
"epoch": 0.2497494153023722,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996884169697816,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.16844751238822936,
|
|
"num_tokens": 5504587.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.582669925689697,
|
|
"epoch": 0.2501670564650852,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996868488336526,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.17021068334579467,
|
|
"num_tokens": 5514188.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.647515344619751,
|
|
"epoch": 0.25058469762779817,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996852767641099,
|
|
"loss": 5.5618,
|
|
"mean_token_accuracy": 0.16375300735235215,
|
|
"num_tokens": 5524075.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.25058469762779817,
|
|
"eval_entropy": 5.439305083677441,
|
|
"eval_loss": 5.4750590324401855,
|
|
"eval_mean_token_accuracy": 0.1805651797318239,
|
|
"eval_num_tokens": 5524075.0,
|
|
"eval_runtime": 20.8359,
|
|
"eval_samples_per_second": 1812.405,
|
|
"eval_steps_per_second": 226.581,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.5746406555175785,
|
|
"epoch": 0.2510023387905112,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996837007611811,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.1788409635424614,
|
|
"num_tokens": 5533323.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.555060625076294,
|
|
"epoch": 0.2514199799532242,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996821208248935,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.18060948252677916,
|
|
"num_tokens": 5542288.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.6625090599060055,
|
|
"epoch": 0.25183762111593716,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996805369552749,
|
|
"loss": 5.5262,
|
|
"mean_token_accuracy": 0.16582419127225875,
|
|
"num_tokens": 5550869.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.61263689994812,
|
|
"epoch": 0.2522552622786502,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996789491523532,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.18086858242750167,
|
|
"num_tokens": 5560147.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.584115076065063,
|
|
"epoch": 0.2526729034413632,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996773574161559,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.1779685065150261,
|
|
"num_tokens": 5568358.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.581736087799072,
|
|
"epoch": 0.25309054460407615,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996757617467112,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.16878845989704133,
|
|
"num_tokens": 5577755.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.627927446365357,
|
|
"epoch": 0.2535081857667892,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996741621440466,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.1548949271440506,
|
|
"num_tokens": 5587515.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.689059638977051,
|
|
"epoch": 0.25392582692950216,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996725586081906,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.1566411778330803,
|
|
"num_tokens": 5597860.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.716712379455567,
|
|
"epoch": 0.25434346809221514,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996709511391709,
|
|
"loss": 5.5153,
|
|
"mean_token_accuracy": 0.17109416723251342,
|
|
"num_tokens": 5607302.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.583583164215088,
|
|
"epoch": 0.2547611092549282,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996693397370158,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.16726490557193757,
|
|
"num_tokens": 5616345.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.592926645278931,
|
|
"epoch": 0.25517875041764115,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996677244017534,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.16961175054311753,
|
|
"num_tokens": 5624745.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.644578170776367,
|
|
"epoch": 0.25559639158035413,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996661051334121,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.16580781042575837,
|
|
"num_tokens": 5634022.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.59101185798645,
|
|
"epoch": 0.25601403274306717,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996644819320201,
|
|
"loss": 5.4405,
|
|
"mean_token_accuracy": 0.17269326746463776,
|
|
"num_tokens": 5643631.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.626284551620484,
|
|
"epoch": 0.25643167390578014,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996628547976061,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.16607993543148042,
|
|
"num_tokens": 5653155.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.624527502059936,
|
|
"epoch": 0.2568493150684932,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996612237301983,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.16944321095943451,
|
|
"num_tokens": 5663091.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.513746976852417,
|
|
"epoch": 0.25726695623120616,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996595887298254,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.18227278143167497,
|
|
"num_tokens": 5671885.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.633248281478882,
|
|
"epoch": 0.25768459739391913,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499657949796516,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.1742770180106163,
|
|
"num_tokens": 5680225.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.480945110321045,
|
|
"epoch": 0.25810223855663217,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996563069302986,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.18399772942066192,
|
|
"num_tokens": 5689456.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.548539304733277,
|
|
"epoch": 0.25851987971934515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996546601312023,
|
|
"loss": 5.4269,
|
|
"mean_token_accuracy": 0.1769353613257408,
|
|
"num_tokens": 5698127.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.601634740829468,
|
|
"epoch": 0.2589375208820581,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996530093992558,
|
|
"loss": 5.4655,
|
|
"mean_token_accuracy": 0.17368797361850738,
|
|
"num_tokens": 5706825.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.586195087432861,
|
|
"epoch": 0.25935516204477116,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996513547344877,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.17347013354301452,
|
|
"num_tokens": 5715677.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.5339923858642575,
|
|
"epoch": 0.25977280320748414,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996496961369274,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.17383432239294053,
|
|
"num_tokens": 5725371.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.590665435791015,
|
|
"epoch": 0.2601904443701971,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996480336066037,
|
|
"loss": 5.443,
|
|
"mean_token_accuracy": 0.17748117595911025,
|
|
"num_tokens": 5734664.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.585344505310059,
|
|
"epoch": 0.26060808553291015,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996463671435458,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.17878079265356064,
|
|
"num_tokens": 5743870.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.502107095718384,
|
|
"epoch": 0.26102572669562313,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996446967477829,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.17417071759700775,
|
|
"num_tokens": 5752855.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.676599073410034,
|
|
"epoch": 0.2614433678583361,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996430224193441,
|
|
"loss": 5.5115,
|
|
"mean_token_accuracy": 0.17244183123111725,
|
|
"num_tokens": 5762435.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.631258726119995,
|
|
"epoch": 0.26186100902104914,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996413441582589,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.17057334929704665,
|
|
"num_tokens": 5771463.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.591678667068481,
|
|
"epoch": 0.2622786501837621,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996396619645564,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.16607145965099335,
|
|
"num_tokens": 5780530.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.587051868438721,
|
|
"epoch": 0.2626962913464751,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996379758382662,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.1801774248480797,
|
|
"num_tokens": 5789199.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.696636009216308,
|
|
"epoch": 0.26311393250918813,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499636285779418,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.16596160233020782,
|
|
"num_tokens": 5799170.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.598244905471802,
|
|
"epoch": 0.2635315736719011,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996345917880412,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.16822701841592788,
|
|
"num_tokens": 5807662.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.503729772567749,
|
|
"epoch": 0.2639492148346141,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996328938641654,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.17659097015857697,
|
|
"num_tokens": 5815790.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.628265619277954,
|
|
"epoch": 0.2643668559973271,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996311920078204,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.17756222933530807,
|
|
"num_tokens": 5824746.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.531688022613525,
|
|
"epoch": 0.2647844971600401,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996294862190361,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.17825444787740707,
|
|
"num_tokens": 5833678.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.592626237869263,
|
|
"epoch": 0.2652021383227531,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499627776497842,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.1763753041625023,
|
|
"num_tokens": 5842218.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.779583406448364,
|
|
"epoch": 0.2656197794854661,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996260628442686,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.16098430752754211,
|
|
"num_tokens": 5853250.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.561507797241211,
|
|
"epoch": 0.2660374206481791,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996243452583454,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.18044775128364562,
|
|
"num_tokens": 5862661.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.606974411010742,
|
|
"epoch": 0.26645506181089207,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996226237401028,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.17085277885198594,
|
|
"num_tokens": 5872327.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.487444353103638,
|
|
"epoch": 0.2668727029736051,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996208982895706,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.17556480765342714,
|
|
"num_tokens": 5881539.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.640183639526367,
|
|
"epoch": 0.2672903441363181,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996191689067794,
|
|
"loss": 5.4883,
|
|
"mean_token_accuracy": 0.17237293645739554,
|
|
"num_tokens": 5891602.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.556846761703492,
|
|
"epoch": 0.26770798529903106,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996174355917591,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.1711392104625702,
|
|
"num_tokens": 5899831.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.657775163650513,
|
|
"epoch": 0.2681256264617441,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996156983445404,
|
|
"loss": 5.579,
|
|
"mean_token_accuracy": 0.16365482211112975,
|
|
"num_tokens": 5909193.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.6107306480407715,
|
|
"epoch": 0.26854326762445707,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996139571651534,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.17259648889303209,
|
|
"num_tokens": 5919353.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.559420347213745,
|
|
"epoch": 0.26896090878717005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996122120536288,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.1734701871871948,
|
|
"num_tokens": 5927853.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.527252721786499,
|
|
"epoch": 0.2693785499498831,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996104630099969,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.17499730437994004,
|
|
"num_tokens": 5937943.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.589746618270874,
|
|
"epoch": 0.26979619111259606,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996087100342885,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.17634052485227586,
|
|
"num_tokens": 5946213.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.5539998531341555,
|
|
"epoch": 0.27021383227530904,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996069531265345,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.17404123842716218,
|
|
"num_tokens": 5954997.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.502858591079712,
|
|
"epoch": 0.2706314734380221,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996051922867653,
|
|
"loss": 5.3805,
|
|
"mean_token_accuracy": 0.18266110569238664,
|
|
"num_tokens": 5963947.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.517758321762085,
|
|
"epoch": 0.27104911460073505,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996034275150118,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.1729441612958908,
|
|
"num_tokens": 5972077.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.499938154220581,
|
|
"epoch": 0.27146675576344803,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499601658811305,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.17419400662183762,
|
|
"num_tokens": 5982649.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.6074347496032715,
|
|
"epoch": 0.27188439692616106,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995998861756758,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.1733310416340828,
|
|
"num_tokens": 5991349.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.480852460861206,
|
|
"epoch": 0.27230203808887404,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995981096081552,
|
|
"loss": 5.4216,
|
|
"mean_token_accuracy": 0.17784159779548644,
|
|
"num_tokens": 6000555.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.7927711486816404,
|
|
"epoch": 0.272719679251587,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995963291087744,
|
|
"loss": 5.5414,
|
|
"mean_token_accuracy": 0.16226843744516373,
|
|
"num_tokens": 6009554.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.654748201370239,
|
|
"epoch": 0.27313732041430006,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995945446775645,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.16894907951354982,
|
|
"num_tokens": 6019330.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.639603614807129,
|
|
"epoch": 0.27355496157701303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995927563145566,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.1725250318646431,
|
|
"num_tokens": 6028527.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.590549421310425,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995909640197825,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.17592502534389495,
|
|
"num_tokens": 6038223.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.521470594406128,
|
|
"epoch": 0.27439024390243905,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995891677932729,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.17709806561470032,
|
|
"num_tokens": 6047459.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.653777599334717,
|
|
"epoch": 0.274807885065152,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995873676350597,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.16930995285511016,
|
|
"num_tokens": 6057322.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.677785110473633,
|
|
"epoch": 0.275225526227865,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995855635451743,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.16371311098337174,
|
|
"num_tokens": 6067520.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.610356712341309,
|
|
"epoch": 0.27564316739057804,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995837555236484,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.16796472072601318,
|
|
"num_tokens": 6076729.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.653829765319824,
|
|
"epoch": 0.276060808553291,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995819435705133,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.16715407967567444,
|
|
"num_tokens": 6086529.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.634232521057129,
|
|
"epoch": 0.276478449716004,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995801276858011,
|
|
"loss": 5.4995,
|
|
"mean_token_accuracy": 0.17505144476890563,
|
|
"num_tokens": 6095784.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.659713315963745,
|
|
"epoch": 0.276896090878717,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995783078695434,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.17024864703416825,
|
|
"num_tokens": 6104626.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.576074314117432,
|
|
"epoch": 0.27731373204143,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499576484121772,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.17644223123788833,
|
|
"num_tokens": 6113758.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.676805877685547,
|
|
"epoch": 0.277731373204143,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995746564425191,
|
|
"loss": 5.4574,
|
|
"mean_token_accuracy": 0.1774701103568077,
|
|
"num_tokens": 6123265.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.6020440578460695,
|
|
"epoch": 0.278149014366856,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995728248318163,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.17074089795351027,
|
|
"num_tokens": 6132855.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.493814182281494,
|
|
"epoch": 0.278566655529569,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995709892896961,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.17272404879331588,
|
|
"num_tokens": 6142739.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.489976930618286,
|
|
"epoch": 0.278984296692282,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995691498161903,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.17681270390748977,
|
|
"num_tokens": 6152169.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.460879278182984,
|
|
"epoch": 0.279401937854995,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995673064113313,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.17841996848583222,
|
|
"num_tokens": 6160235.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.560737037658692,
|
|
"epoch": 0.279819579017708,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995654590751513,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.17495323121547698,
|
|
"num_tokens": 6169440.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.512513160705566,
|
|
"epoch": 0.28023722018042097,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995636078076825,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.17717572897672654,
|
|
"num_tokens": 6178456.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.483798456192017,
|
|
"epoch": 0.280654861343134,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995617526089575,
|
|
"loss": 5.4666,
|
|
"mean_token_accuracy": 0.17098009288311006,
|
|
"num_tokens": 6186844.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.5602109909057615,
|
|
"epoch": 0.281072502505847,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995598934790087,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.1738967329263687,
|
|
"num_tokens": 6196117.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.567266845703125,
|
|
"epoch": 0.28149014366855996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995580304178687,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.17981449663639068,
|
|
"num_tokens": 6204636.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.478482961654663,
|
|
"epoch": 0.281907784831273,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995561634255701,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.1768627479672432,
|
|
"num_tokens": 6214537.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.561605930328369,
|
|
"epoch": 0.28232542599398597,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995542925021455,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.17716920822858812,
|
|
"num_tokens": 6224753.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.776811122894287,
|
|
"epoch": 0.28274306715669895,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995524176476277,
|
|
"loss": 5.6359,
|
|
"mean_token_accuracy": 0.16989700496196747,
|
|
"num_tokens": 6233842.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.689156103134155,
|
|
"epoch": 0.283160708319412,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995505388620497,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.1734553098678589,
|
|
"num_tokens": 6243467.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.455839538574219,
|
|
"epoch": 0.28357834948212496,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499548656145444,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.16760174334049224,
|
|
"num_tokens": 6253263.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.609464502334594,
|
|
"epoch": 0.28399599064483794,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995467694978439,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.18367697149515153,
|
|
"num_tokens": 6262249.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.505943679809571,
|
|
"epoch": 0.28441363180755097,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995448789192823,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.17404457926750183,
|
|
"num_tokens": 6271154.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.483510875701905,
|
|
"epoch": 0.28483127297026395,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995429844097922,
|
|
"loss": 5.4619,
|
|
"mean_token_accuracy": 0.17957177758216858,
|
|
"num_tokens": 6280377.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.62252106666565,
|
|
"epoch": 0.2852489141329769,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995410859694071,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.17485124468803406,
|
|
"num_tokens": 6289941.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.594379425048828,
|
|
"epoch": 0.28566655529568996,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995391835981599,
|
|
"loss": 5.508,
|
|
"mean_token_accuracy": 0.17386738806962967,
|
|
"num_tokens": 6299281.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.561397552490234,
|
|
"epoch": 0.28608419645840294,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499537277296084,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.1735068678855896,
|
|
"num_tokens": 6309408.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.591901636123657,
|
|
"epoch": 0.2865018376211159,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995353670632127,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.17716914564371108,
|
|
"num_tokens": 6318979.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.5408731460571286,
|
|
"epoch": 0.28691947878382895,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995334528995797,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.1836568832397461,
|
|
"num_tokens": 6327616.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.4383015632629395,
|
|
"epoch": 0.28733711994654193,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995315348052182,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.18269999772310258,
|
|
"num_tokens": 6336486.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.528027677536011,
|
|
"epoch": 0.2877547611092549,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499529612780162,
|
|
"loss": 5.3928,
|
|
"mean_token_accuracy": 0.17357015162706374,
|
|
"num_tokens": 6345671.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.600039863586426,
|
|
"epoch": 0.28817240227196794,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995276868244446,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.1713360771536827,
|
|
"num_tokens": 6354534.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.544518899917603,
|
|
"epoch": 0.2885900434346809,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995257569380998,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.17810316979885102,
|
|
"num_tokens": 6364052.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.596878623962402,
|
|
"epoch": 0.2890076845973939,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995238231211614,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.1739054024219513,
|
|
"num_tokens": 6373305.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.502811527252197,
|
|
"epoch": 0.28942532576010693,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995218853736631,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.17193110883235932,
|
|
"num_tokens": 6382673.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.576852607727051,
|
|
"epoch": 0.2898429669228199,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995199436956391,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.16693659275770187,
|
|
"num_tokens": 6392122.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.61850323677063,
|
|
"epoch": 0.2902606080855329,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995179980871231,
|
|
"loss": 5.5081,
|
|
"mean_token_accuracy": 0.1674024909734726,
|
|
"num_tokens": 6401130.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.555272769927979,
|
|
"epoch": 0.2906782492482459,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995160485481493,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.1730802908539772,
|
|
"num_tokens": 6409471.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.50113615989685,
|
|
"epoch": 0.2910958904109589,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499514095078752,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.17283471226692199,
|
|
"num_tokens": 6418902.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.592144966125488,
|
|
"epoch": 0.2915135315736719,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499512137678965,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.17761690467596053,
|
|
"num_tokens": 6428529.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.549305438995361,
|
|
"epoch": 0.2919311727363849,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995101763488229,
|
|
"loss": 5.3338,
|
|
"mean_token_accuracy": 0.17831255495548248,
|
|
"num_tokens": 6437460.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.5336507797241214,
|
|
"epoch": 0.2923488138990979,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995082110883599,
|
|
"loss": 5.3786,
|
|
"mean_token_accuracy": 0.17854560911655426,
|
|
"num_tokens": 6446005.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.49955677986145,
|
|
"epoch": 0.29276645506181087,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995062418976104,
|
|
"loss": 5.4383,
|
|
"mean_token_accuracy": 0.17510765939950942,
|
|
"num_tokens": 6455241.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.5724241733551025,
|
|
"epoch": 0.2931840962245239,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995042687766089,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.18050031810998918,
|
|
"num_tokens": 6464748.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.5032836437225345,
|
|
"epoch": 0.2936017373872369,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995022917253899,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.18206857442855834,
|
|
"num_tokens": 6473834.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.523321914672851,
|
|
"epoch": 0.29401937854994986,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995003107439882,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.17559723556041718,
|
|
"num_tokens": 6482169.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.491705989837646,
|
|
"epoch": 0.2944370197126629,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994983258324383,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.18005243092775344,
|
|
"num_tokens": 6491798.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.429749870300293,
|
|
"epoch": 0.2948546608753759,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994963369907748,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.18179493099451066,
|
|
"num_tokens": 6500143.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.4342066764831545,
|
|
"epoch": 0.29527230203808885,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994943442190328,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.17470866143703462,
|
|
"num_tokens": 6509745.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.607319450378418,
|
|
"epoch": 0.2956899432008019,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994923475172471,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.17269728034734727,
|
|
"num_tokens": 6520931.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.5933128833770756,
|
|
"epoch": 0.29610758436351486,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994903468854527,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.17606248557567597,
|
|
"num_tokens": 6529774.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.451561403274536,
|
|
"epoch": 0.29652522552622784,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994883423236843,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.1742999017238617,
|
|
"num_tokens": 6538922.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.462928581237793,
|
|
"epoch": 0.2969428666889409,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994863338319775,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.1813220962882042,
|
|
"num_tokens": 6548891.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.441606712341309,
|
|
"epoch": 0.29736050785165385,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994843214103672,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.18053237050771714,
|
|
"num_tokens": 6557025.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.58992075920105,
|
|
"epoch": 0.29777814901436683,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994823050588886,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.17266968488693238,
|
|
"num_tokens": 6567037.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.550380373001099,
|
|
"epoch": 0.29819579017707987,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499480284777577,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.17562949657440186,
|
|
"num_tokens": 6576766.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.541287851333618,
|
|
"epoch": 0.29861343133979285,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994782605664677,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.17942708879709243,
|
|
"num_tokens": 6585576.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.567754125595092,
|
|
"epoch": 0.2990310725025058,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994762324255965,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.17856290936470032,
|
|
"num_tokens": 6594463.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.482272386550903,
|
|
"epoch": 0.29944871366521886,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994742003549986,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.17593453377485274,
|
|
"num_tokens": 6603651.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.563546991348266,
|
|
"epoch": 0.29986635482793184,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994721643547095,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.1821247473359108,
|
|
"num_tokens": 6612950.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.556297636032104,
|
|
"epoch": 0.3002839959906448,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499470124424765,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.18147182017564772,
|
|
"num_tokens": 6622013.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.512169313430786,
|
|
"epoch": 0.30070163715335785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994680805652008,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.1777033269405365,
|
|
"num_tokens": 6632046.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.534895753860473,
|
|
"epoch": 0.3011192783160708,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994660327760527,
|
|
"loss": 5.4681,
|
|
"mean_token_accuracy": 0.18036231845617295,
|
|
"num_tokens": 6641169.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.496008777618409,
|
|
"epoch": 0.3015369194787838,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994639810573565,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.1871926799416542,
|
|
"num_tokens": 6649663.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.598363018035888,
|
|
"epoch": 0.30195456064149684,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499461925409148,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.17643528431653976,
|
|
"num_tokens": 6659448.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.580114126205444,
|
|
"epoch": 0.3023722018042098,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994598658314634,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.17718038260936736,
|
|
"num_tokens": 6670314.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.506917190551758,
|
|
"epoch": 0.3027898429669228,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994578023243386,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.181967531144619,
|
|
"num_tokens": 6679413.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.530770635604858,
|
|
"epoch": 0.30320748412963583,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994557348878098,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.18353726267814635,
|
|
"num_tokens": 6688439.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.507672929763794,
|
|
"epoch": 0.3036251252923488,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994536635219133,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.18460191935300826,
|
|
"num_tokens": 6697471.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.588464164733887,
|
|
"epoch": 0.3040427664550618,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994515882266852,
|
|
"loss": 5.399,
|
|
"mean_token_accuracy": 0.1802619442343712,
|
|
"num_tokens": 6706698.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.463037109375,
|
|
"epoch": 0.3044604076177748,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994495090021618,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.1899622604250908,
|
|
"num_tokens": 6715676.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.421985530853272,
|
|
"epoch": 0.3048780487804878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994474258483796,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.18088990300893784,
|
|
"num_tokens": 6723818.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.5057212829589846,
|
|
"epoch": 0.3052956899432008,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994453387653751,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.17914116978645325,
|
|
"num_tokens": 6733450.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.549224996566773,
|
|
"epoch": 0.3057133311059138,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994432477531847,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.18117241859436034,
|
|
"num_tokens": 6743142.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.444807386398315,
|
|
"epoch": 0.3061309722686268,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994411528118452,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.18373701125383377,
|
|
"num_tokens": 6752185.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.432768440246582,
|
|
"epoch": 0.30654861343133977,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994390539413931,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.1874572068452835,
|
|
"num_tokens": 6761549.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.503639650344849,
|
|
"epoch": 0.3069662545940528,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994369511418652,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.17693545073270797,
|
|
"num_tokens": 6770395.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.603547716140747,
|
|
"epoch": 0.3073838957567658,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994348444132983,
|
|
"loss": 5.4779,
|
|
"mean_token_accuracy": 0.17427192777395248,
|
|
"num_tokens": 6779154.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.436843156814575,
|
|
"epoch": 0.30780153691947876,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994327337557293,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.18041885197162627,
|
|
"num_tokens": 6789263.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.519675064086914,
|
|
"epoch": 0.3082191780821918,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994306191691952,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.17405094504356383,
|
|
"num_tokens": 6797985.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.486072731018067,
|
|
"epoch": 0.30863681924490477,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994285006537329,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.1826901137828827,
|
|
"num_tokens": 6807566.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.443434047698974,
|
|
"epoch": 0.30905446040761775,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994263782093796,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.1786921888589859,
|
|
"num_tokens": 6815637.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.477226972579956,
|
|
"epoch": 0.3094721015703308,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994242518361723,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.18317863792181016,
|
|
"num_tokens": 6823721.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.563334131240845,
|
|
"epoch": 0.30988974273304376,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994221215341484,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.1805688202381134,
|
|
"num_tokens": 6833437.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.528415250778198,
|
|
"epoch": 0.31030738389575674,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994199873033452,
|
|
"loss": 5.4853,
|
|
"mean_token_accuracy": 0.17529656738042831,
|
|
"num_tokens": 6842287.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.574981307983398,
|
|
"epoch": 0.3107250250584698,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994178491437999,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.17678289562463761,
|
|
"num_tokens": 6851520.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.478482484817505,
|
|
"epoch": 0.31114266622118275,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994157070555501,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.18189572989940644,
|
|
"num_tokens": 6861219.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.559235620498657,
|
|
"epoch": 0.31156030738389573,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994135610386331,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.1737344443798065,
|
|
"num_tokens": 6870525.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.579884576797485,
|
|
"epoch": 0.31197794854660876,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994114110930867,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.17428294867277144,
|
|
"num_tokens": 6880183.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.503607940673828,
|
|
"epoch": 0.31239558970932174,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994092572189483,
|
|
"loss": 5.4816,
|
|
"mean_token_accuracy": 0.17305418252944946,
|
|
"num_tokens": 6890442.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.5101171970367435,
|
|
"epoch": 0.3128132308720348,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994070994162558,
|
|
"loss": 5.3875,
|
|
"mean_token_accuracy": 0.17789959907531738,
|
|
"num_tokens": 6900091.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.510205888748169,
|
|
"epoch": 0.31323087203474775,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994049376850471,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.1794740691781044,
|
|
"num_tokens": 6910489.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.528826951980591,
|
|
"epoch": 0.31364851319746073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994027720253596,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.17456467300653458,
|
|
"num_tokens": 6919895.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.655718803405762,
|
|
"epoch": 0.31406615436017377,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994006024372315,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.17024042308330536,
|
|
"num_tokens": 6929511.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.47804627418518,
|
|
"epoch": 0.31448379552288674,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993984289207007,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.18062639385461807,
|
|
"num_tokens": 6938059.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.48602876663208,
|
|
"epoch": 0.3149014366855997,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993962514758054,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.1788356751203537,
|
|
"num_tokens": 6946894.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.54166693687439,
|
|
"epoch": 0.31531907784831276,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993940701025836,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.172277994453907,
|
|
"num_tokens": 6955494.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.458626556396484,
|
|
"epoch": 0.31573671901102573,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993918848010734,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.17690639197826385,
|
|
"num_tokens": 6964347.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.578127527236939,
|
|
"epoch": 0.3161543601737387,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993896955713133,
|
|
"loss": 5.404,
|
|
"mean_token_accuracy": 0.17243928760290145,
|
|
"num_tokens": 6974750.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.5424340724945065,
|
|
"epoch": 0.31657200133645175,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993875024133414,
|
|
"loss": 5.3923,
|
|
"mean_token_accuracy": 0.1762187063694,
|
|
"num_tokens": 6984228.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.4567211151123045,
|
|
"epoch": 0.3169896424991647,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993853053271962,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.17981710135936738,
|
|
"num_tokens": 6993173.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.679009103775025,
|
|
"epoch": 0.3174072836618777,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993831043129161,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.1643933981657028,
|
|
"num_tokens": 7003486.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.4468996047973635,
|
|
"epoch": 0.31782492482459074,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993808993705397,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.17920849919319154,
|
|
"num_tokens": 7011985.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.458551502227783,
|
|
"epoch": 0.3182425659873037,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993786905001055,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.1822291061282158,
|
|
"num_tokens": 7021148.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.47202353477478,
|
|
"epoch": 0.3186602071500167,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993764777016524,
|
|
"loss": 5.3455,
|
|
"mean_token_accuracy": 0.1797745183110237,
|
|
"num_tokens": 7030110.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.541410303115844,
|
|
"epoch": 0.31907784831272973,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993742609752188,
|
|
"loss": 5.4247,
|
|
"mean_token_accuracy": 0.18440490812063218,
|
|
"num_tokens": 7039428.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.6262492656707765,
|
|
"epoch": 0.3194954894754427,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993720403208438,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.17609096318483353,
|
|
"num_tokens": 7048703.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.4990678310394285,
|
|
"epoch": 0.3199131306381557,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499369815738566,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.1763720229268074,
|
|
"num_tokens": 7057612.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.476385498046875,
|
|
"epoch": 0.3203307718008687,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993675872284248,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.17945525646209717,
|
|
"num_tokens": 7066660.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.431416654586792,
|
|
"epoch": 0.3207484129635817,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993653547904586,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.1728386864066124,
|
|
"num_tokens": 7075368.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.506367111206055,
|
|
"epoch": 0.3211660541262947,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499363118424707,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.18204201459884645,
|
|
"num_tokens": 7085276.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.4822998046875,
|
|
"epoch": 0.3215836952890077,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993608781312088,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.1749197781085968,
|
|
"num_tokens": 7094292.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.6277257919311525,
|
|
"epoch": 0.3220013364517207,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993586339100035,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.16883062720298767,
|
|
"num_tokens": 7104712.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.5858546733856205,
|
|
"epoch": 0.32241897761443367,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993563857611301,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.18445784449577332,
|
|
"num_tokens": 7113297.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.414010143280029,
|
|
"epoch": 0.3228366187771467,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993541336846283,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.17146380245685577,
|
|
"num_tokens": 7122706.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.531915330886841,
|
|
"epoch": 0.3232542599398597,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993518776805372,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.18176922351121902,
|
|
"num_tokens": 7131939.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.420168447494507,
|
|
"epoch": 0.32367190110257266,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993496177488965,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.18499719649553298,
|
|
"num_tokens": 7141016.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.359659099578858,
|
|
"epoch": 0.3240895422652857,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993473538897457,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.18912801891565323,
|
|
"num_tokens": 7149177.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.484179496765137,
|
|
"epoch": 0.32450718342799867,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993450861031243,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.1831592485308647,
|
|
"num_tokens": 7157839.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.571604919433594,
|
|
"epoch": 0.32492482459071165,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993428143890722,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.1706176444888115,
|
|
"num_tokens": 7167759.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.558566522598267,
|
|
"epoch": 0.3253424657534247,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993405387476291,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.17039104998111726,
|
|
"num_tokens": 7177141.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.437656307220459,
|
|
"epoch": 0.32576010691613766,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993382591788349,
|
|
"loss": 5.3222,
|
|
"mean_token_accuracy": 0.1868903785943985,
|
|
"num_tokens": 7185350.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.417111158370972,
|
|
"epoch": 0.32617774807885064,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993359756827293,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.18155012130737305,
|
|
"num_tokens": 7194073.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.510383987426758,
|
|
"epoch": 0.32659538924156367,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993336882593524,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.17435751110315323,
|
|
"num_tokens": 7203421.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.461305284500122,
|
|
"epoch": 0.32701303040427665,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993313969087444,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.18621868640184402,
|
|
"num_tokens": 7212548.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.498770236968994,
|
|
"epoch": 0.32743067156698963,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993291016309452,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.17446689158678055,
|
|
"num_tokens": 7221668.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.47779221534729,
|
|
"epoch": 0.32784831272970266,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499326802425995,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.17811784148216248,
|
|
"num_tokens": 7231775.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.554512977600098,
|
|
"epoch": 0.32826595389241564,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993244992939342,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.17753950208425523,
|
|
"num_tokens": 7241264.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.516229963302612,
|
|
"epoch": 0.3286835950551286,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499322192234803,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.17567516565322877,
|
|
"num_tokens": 7250519.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.6126152038574215,
|
|
"epoch": 0.32910123621784165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993198812486418,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.17280989438295363,
|
|
"num_tokens": 7259533.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.464484548568725,
|
|
"epoch": 0.32951887738055463,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499317566335491,
|
|
"loss": 5.2726,
|
|
"mean_token_accuracy": 0.1795586496591568,
|
|
"num_tokens": 7268980.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.462821054458618,
|
|
"epoch": 0.3299365185432676,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993152474953913,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.17920627146959306,
|
|
"num_tokens": 7277126.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.541590356826783,
|
|
"epoch": 0.33035415970598064,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993129247283831,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.18637250661849974,
|
|
"num_tokens": 7286223.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.484134912490845,
|
|
"epoch": 0.3307718008686936,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993105980345071,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.18047412782907485,
|
|
"num_tokens": 7295054.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.471391773223877,
|
|
"epoch": 0.3311894420314066,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993082674138042,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.18078695386648178,
|
|
"num_tokens": 7304502.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.492424154281617,
|
|
"epoch": 0.33160708319411963,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499305932866315,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.17749465256929398,
|
|
"num_tokens": 7314093.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.520782423019409,
|
|
"epoch": 0.3320247243568326,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993035943920805,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.17957361191511154,
|
|
"num_tokens": 7323059.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.570900297164917,
|
|
"epoch": 0.3324423655195456,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993012519911416,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.17249713987112045,
|
|
"num_tokens": 7332596.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.4793473243713375,
|
|
"epoch": 0.3328600066822586,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992989056635392,
|
|
"loss": 5.298,
|
|
"mean_token_accuracy": 0.18367077261209488,
|
|
"num_tokens": 7341671.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.456484317779541,
|
|
"epoch": 0.3332776478449716,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992965554093146,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.17515567541122437,
|
|
"num_tokens": 7350344.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.561565256118774,
|
|
"epoch": 0.3336952890076846,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992942012285086,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.18539106994867324,
|
|
"num_tokens": 7359844.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.4745471477508545,
|
|
"epoch": 0.3341129301703976,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992918431211629,
|
|
"loss": 5.3688,
|
|
"mean_token_accuracy": 0.17929453253746033,
|
|
"num_tokens": 7369377.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.470567226409912,
|
|
"epoch": 0.3345305713331106,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992894810873183,
|
|
"loss": 5.3307,
|
|
"mean_token_accuracy": 0.1800221860408783,
|
|
"num_tokens": 7378814.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.48086895942688,
|
|
"epoch": 0.33494821249582357,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992871151270165,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.18241927474737168,
|
|
"num_tokens": 7387333.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.401240062713623,
|
|
"epoch": 0.3353658536585366,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004992847452402986,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.18221889287233353,
|
|
"num_tokens": 7396895.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.481763124465942,
|
|
"epoch": 0.3357834948212496,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992823714272064,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.18173366487026216,
|
|
"num_tokens": 7406430.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.494069623947143,
|
|
"epoch": 0.33620113598396256,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992799936877813,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.19242478907108307,
|
|
"num_tokens": 7415224.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.511053419113159,
|
|
"epoch": 0.3366187771466756,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992776120220649,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.16617913842201232,
|
|
"num_tokens": 7424250.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.540709114074707,
|
|
"epoch": 0.3370364183093886,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992752264300989,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.1892720192670822,
|
|
"num_tokens": 7433579.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.441310787200928,
|
|
"epoch": 0.33745405947210155,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992728369119252,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.18562408685684204,
|
|
"num_tokens": 7442621.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.508677577972412,
|
|
"epoch": 0.3378717006348146,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992704434675855,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.17891159504652024,
|
|
"num_tokens": 7452077.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.448977851867676,
|
|
"epoch": 0.33828934179752757,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992680460971218,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.1813043788075447,
|
|
"num_tokens": 7461146.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.373752307891846,
|
|
"epoch": 0.33870698296024054,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992656448005758,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.17925926595926284,
|
|
"num_tokens": 7470335.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.502498149871826,
|
|
"epoch": 0.3391246241229536,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992632395779899,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.18008628487586975,
|
|
"num_tokens": 7479458.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.367786502838134,
|
|
"epoch": 0.33954226528566656,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992608304294061,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.1907706767320633,
|
|
"num_tokens": 7488005.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.38989953994751,
|
|
"epoch": 0.33995990644837953,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992584173548664,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.18200177252292632,
|
|
"num_tokens": 7496807.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.495892333984375,
|
|
"epoch": 0.34037754761109257,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992560003544131,
|
|
"loss": 5.3211,
|
|
"mean_token_accuracy": 0.1855458453297615,
|
|
"num_tokens": 7505383.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.5039510250091555,
|
|
"epoch": 0.34079518877380555,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992535794280887,
|
|
"loss": 5.3868,
|
|
"mean_token_accuracy": 0.17639458030462266,
|
|
"num_tokens": 7515093.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.513694953918457,
|
|
"epoch": 0.3412128299365185,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992511545759354,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.17677693963050842,
|
|
"num_tokens": 7524067.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.405082702636719,
|
|
"epoch": 0.34163047109923156,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992487257979958,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.176565483212471,
|
|
"num_tokens": 7533197.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.486233472824097,
|
|
"epoch": 0.34204811226194454,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992462930943123,
|
|
"loss": 5.3106,
|
|
"mean_token_accuracy": 0.17456244677305222,
|
|
"num_tokens": 7543030.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.484900045394897,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992438564649275,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.176419173181057,
|
|
"num_tokens": 7551556.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.462079763412476,
|
|
"epoch": 0.34288339458737055,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992414159098841,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.18483974188566207,
|
|
"num_tokens": 7559284.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.560677242279053,
|
|
"epoch": 0.3433010357500835,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992389714292247,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.17652314454317092,
|
|
"num_tokens": 7568750.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.403720951080322,
|
|
"epoch": 0.3437186769127965,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992365230229922,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.18145160526037216,
|
|
"num_tokens": 7578309.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.373352813720703,
|
|
"epoch": 0.34413631807550954,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992340706912295,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.18348611146211624,
|
|
"num_tokens": 7586760.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.412221050262451,
|
|
"epoch": 0.3445539592382225,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992316144339794,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.1827987939119339,
|
|
"num_tokens": 7595472.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.478467702865601,
|
|
"epoch": 0.3449716004009355,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992291542512852,
|
|
"loss": 5.4436,
|
|
"mean_token_accuracy": 0.16591697186231613,
|
|
"num_tokens": 7605663.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.569995403289795,
|
|
"epoch": 0.34538924156364853,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004992266901431895,
|
|
"loss": 5.3492,
|
|
"mean_token_accuracy": 0.17636355459690095,
|
|
"num_tokens": 7616110.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.431912803649903,
|
|
"epoch": 0.3458068827263615,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992242221097358,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.17962000519037247,
|
|
"num_tokens": 7625311.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.466735982894898,
|
|
"epoch": 0.3462245238890745,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992217501509672,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.18079007863998414,
|
|
"num_tokens": 7634562.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.413268947601319,
|
|
"epoch": 0.3466421650517875,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499219274266927,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.18195686340332032,
|
|
"num_tokens": 7643231.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.477395963668823,
|
|
"epoch": 0.3470598062145005,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004992167944576584,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.18180298209190368,
|
|
"num_tokens": 7653556.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.4794454097747805,
|
|
"epoch": 0.3474774473772135,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499214310723205,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.1838551789522171,
|
|
"num_tokens": 7662295.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.414899301528931,
|
|
"epoch": 0.3478950885399265,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992118230636102,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.18160173147916794,
|
|
"num_tokens": 7671429.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.428017425537109,
|
|
"epoch": 0.3483127297026395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992093314789176,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.17811413258314132,
|
|
"num_tokens": 7680589.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.417633533477783,
|
|
"epoch": 0.34873037086535247,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992068359691707,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.18602515012025833,
|
|
"num_tokens": 7689005.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.32882604598999,
|
|
"epoch": 0.3491480120280655,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992043365344132,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.18629551231861113,
|
|
"num_tokens": 7698231.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.513964557647705,
|
|
"epoch": 0.3495656531907785,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992018331746891,
|
|
"loss": 5.337,
|
|
"mean_token_accuracy": 0.18228928446769715,
|
|
"num_tokens": 7706678.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.52466516494751,
|
|
"epoch": 0.34998329435349146,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991993258900418,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.17994895726442336,
|
|
"num_tokens": 7715506.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.522128391265869,
|
|
"epoch": 0.3504009355162045,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991968146805156,
|
|
"loss": 5.3495,
|
|
"mean_token_accuracy": 0.1793279230594635,
|
|
"num_tokens": 7726549.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.501314687728882,
|
|
"epoch": 0.35081857667891747,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991942995461542,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.17973428666591645,
|
|
"num_tokens": 7735563.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.519511270523071,
|
|
"epoch": 0.35123621784163045,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004991917804870018,
|
|
"loss": 5.3681,
|
|
"mean_token_accuracy": 0.17985545247793197,
|
|
"num_tokens": 7746144.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.473354625701904,
|
|
"epoch": 0.3516538590043435,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991892575031024,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.17899980396032333,
|
|
"num_tokens": 7755394.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.431820058822632,
|
|
"epoch": 0.35207150016705646,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991867305945001,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.18442139774560928,
|
|
"num_tokens": 7764855.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.3907936096191404,
|
|
"epoch": 0.35248914132976944,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991841997612394,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.1767048254609108,
|
|
"num_tokens": 7773394.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.4907787322998045,
|
|
"epoch": 0.3529067824924825,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991816650033643,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.18165876269340514,
|
|
"num_tokens": 7783111.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.544708347320556,
|
|
"epoch": 0.35332442365519545,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991791263209194,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.1770080104470253,
|
|
"num_tokens": 7792569.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.491802167892456,
|
|
"epoch": 0.35374206481790843,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991765837139491,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.18510207533836365,
|
|
"num_tokens": 7801483.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.514691591262817,
|
|
"epoch": 0.35415970598062146,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004991740371824977,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.17008600383996964,
|
|
"num_tokens": 7812274.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.438403081893921,
|
|
"epoch": 0.35457734714333444,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049917148672661,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.17945397794246673,
|
|
"num_tokens": 7821101.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.52276291847229,
|
|
"epoch": 0.3549949883060474,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991689323463306,
|
|
"loss": 5.2589,
|
|
"mean_token_accuracy": 0.18459457606077195,
|
|
"num_tokens": 7829805.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.499110412597656,
|
|
"epoch": 0.35541262946876045,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991663740417042,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.17341142147779465,
|
|
"num_tokens": 7839772.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.403382635116577,
|
|
"epoch": 0.35583027063147343,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991638118127757,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.17146531045436858,
|
|
"num_tokens": 7850290.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.535537481307983,
|
|
"epoch": 0.3562479117941864,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991612456595896,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.17515116631984712,
|
|
"num_tokens": 7860180.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.3561484813690186,
|
|
"epoch": 0.35666555295689945,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991586755821913,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.1924109935760498,
|
|
"num_tokens": 7869625.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.36612458229065,
|
|
"epoch": 0.3570831941196124,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991561015806254,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.18171904385089874,
|
|
"num_tokens": 7878671.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.441513586044311,
|
|
"epoch": 0.3575008352823254,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991535236549372,
|
|
"loss": 5.3518,
|
|
"mean_token_accuracy": 0.18813330829143524,
|
|
"num_tokens": 7887225.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.3925230503082275,
|
|
"epoch": 0.35791847644503844,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991509418051718,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.19238315224647523,
|
|
"num_tokens": 7895504.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.517259693145752,
|
|
"epoch": 0.3583361176077514,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991483560313743,
|
|
"loss": 5.296,
|
|
"mean_token_accuracy": 0.1823975533246994,
|
|
"num_tokens": 7904875.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.476126194000244,
|
|
"epoch": 0.3587537587704644,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00049914576633359,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.18191782087087632,
|
|
"num_tokens": 7914747.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.440190839767456,
|
|
"epoch": 0.3591713999331774,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991431727118643,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.1787615954875946,
|
|
"num_tokens": 7923858.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.401712942123413,
|
|
"epoch": 0.3595890410958904,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991405751662426,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.1769140377640724,
|
|
"num_tokens": 7932396.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.484080982208252,
|
|
"epoch": 0.3600066822586034,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004991379736967703,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.18441410958766938,
|
|
"num_tokens": 7940763.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.374558019638061,
|
|
"epoch": 0.3604243234213164,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991353683034929,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.17722967714071275,
|
|
"num_tokens": 7949424.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.443452215194702,
|
|
"epoch": 0.3608419645840294,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991327589864563,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.1885138511657715,
|
|
"num_tokens": 7958805.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.558720874786377,
|
|
"epoch": 0.3612596057467424,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991301457457057,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.18473998159170152,
|
|
"num_tokens": 7967859.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.579258871078491,
|
|
"epoch": 0.3616772469094554,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991275285812873,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.17163486927747726,
|
|
"num_tokens": 7978357.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.54759955406189,
|
|
"epoch": 0.3620948880721684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991249074932466,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.18578984588384628,
|
|
"num_tokens": 7986637.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.399906015396118,
|
|
"epoch": 0.36251252923488136,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991222824816296,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.18341715335845948,
|
|
"num_tokens": 7995954.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.453273773193359,
|
|
"epoch": 0.3629301703975944,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991196535464824,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.17291699200868607,
|
|
"num_tokens": 8005193.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.581499433517456,
|
|
"epoch": 0.3633478115603074,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991170206878508,
|
|
"loss": 5.371,
|
|
"mean_token_accuracy": 0.1862796038389206,
|
|
"num_tokens": 8014419.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.473800468444824,
|
|
"epoch": 0.36376545272302035,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499114383905781,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.17989490330219268,
|
|
"num_tokens": 8024133.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.410901927947998,
|
|
"epoch": 0.3641830938857334,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991117432003192,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.18804570734500886,
|
|
"num_tokens": 8033059.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.4767594814300535,
|
|
"epoch": 0.36460073504844637,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991090985715116,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.1849939852952957,
|
|
"num_tokens": 8041866.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.439702463150025,
|
|
"epoch": 0.36501837621115935,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991064500194043,
|
|
"loss": 5.3674,
|
|
"mean_token_accuracy": 0.1755709558725357,
|
|
"num_tokens": 8051541.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.52640552520752,
|
|
"epoch": 0.3654360173738724,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991037975440439,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.17630892544984816,
|
|
"num_tokens": 8061964.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.4062323570251465,
|
|
"epoch": 0.36585365853658536,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991011411454769,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.1819170743227005,
|
|
"num_tokens": 8071006.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.418624353408814,
|
|
"epoch": 0.36627129969929834,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990984808237495,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.18490436524152756,
|
|
"num_tokens": 8080104.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.477575635910034,
|
|
"epoch": 0.36668894086201137,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990958165789086,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.18513503223657607,
|
|
"num_tokens": 8089397.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.4587804794311525,
|
|
"epoch": 0.36710658202472435,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990931484110005,
|
|
"loss": 5.3608,
|
|
"mean_token_accuracy": 0.1821795478463173,
|
|
"num_tokens": 8099055.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.420783519744873,
|
|
"epoch": 0.3675242231874373,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990904763200722,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.18283597379922867,
|
|
"num_tokens": 8107609.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.526882123947144,
|
|
"epoch": 0.36794186435015036,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990878003061705,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.1872669517993927,
|
|
"num_tokens": 8116905.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.406569910049439,
|
|
"epoch": 0.36835950551286334,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990851203693419,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.18111734390258788,
|
|
"num_tokens": 8125580.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.405193901062011,
|
|
"epoch": 0.3687771466755763,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990824365096336,
|
|
"loss": 5.2117,
|
|
"mean_token_accuracy": 0.1829536721110344,
|
|
"num_tokens": 8134568.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.377598524093628,
|
|
"epoch": 0.36919478783828935,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990797487270926,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.1847143605351448,
|
|
"num_tokens": 8143044.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.410204696655273,
|
|
"epoch": 0.36961242900100233,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990770570217659,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.1766589418053627,
|
|
"num_tokens": 8153701.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.387406826019287,
|
|
"epoch": 0.37003007016371536,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004990743613937005,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.18566205501556396,
|
|
"num_tokens": 8163264.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.385189628601074,
|
|
"epoch": 0.37044771132642834,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990716618429436,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.17380984127521515,
|
|
"num_tokens": 8173332.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.493477392196655,
|
|
"epoch": 0.3708653524891413,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990689583695428,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.18039319664239883,
|
|
"num_tokens": 8181881.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.529300594329834,
|
|
"epoch": 0.37128299365185435,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499066250973545,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.17962669879198073,
|
|
"num_tokens": 8190771.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.427795267105102,
|
|
"epoch": 0.37170063481456733,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990635396549978,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.17741245180368423,
|
|
"num_tokens": 8200740.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.3374334335327145,
|
|
"epoch": 0.3721182759772803,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990608244139486,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.17950542271137238,
|
|
"num_tokens": 8209935.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.419774103164673,
|
|
"epoch": 0.37253591713999334,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499058105250445,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.17584601193666458,
|
|
"num_tokens": 8219137.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.520624589920044,
|
|
"epoch": 0.3729535583027063,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004990553821645346,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.18713461607694626,
|
|
"num_tokens": 8228076.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.430020046234131,
|
|
"epoch": 0.3733711994654193,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499052655156265,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.18921683132648467,
|
|
"num_tokens": 8237581.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.469464349746704,
|
|
"epoch": 0.37378884062813234,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990499242256839,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.17375379651784897,
|
|
"num_tokens": 8247384.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.518513488769531,
|
|
"epoch": 0.3742064817908453,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990471893728394,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.17811532318592072,
|
|
"num_tokens": 8256383.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.42158579826355,
|
|
"epoch": 0.3746241229535583,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499044450597779,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.18826888948678971,
|
|
"num_tokens": 8264848.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.407288694381714,
|
|
"epoch": 0.3750417641162713,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990417079005508,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.17884940207004546,
|
|
"num_tokens": 8274403.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.417221403121948,
|
|
"epoch": 0.3754594052789843,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499038961281203,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.1896192878484726,
|
|
"num_tokens": 8282700.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.370702457427979,
|
|
"epoch": 0.3758770464416973,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990362107397834,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.1917378708720207,
|
|
"num_tokens": 8291718.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.396169281005859,
|
|
"epoch": 0.3762946876044103,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990334562763401,
|
|
"loss": 5.2991,
|
|
"mean_token_accuracy": 0.1826751172542572,
|
|
"num_tokens": 8301113.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.516213417053223,
|
|
"epoch": 0.3767123287671233,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990306978909216,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.18016503304243087,
|
|
"num_tokens": 8310357.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.472635126113891,
|
|
"epoch": 0.3771299699298363,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990279355835761,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.1848587304353714,
|
|
"num_tokens": 8319680.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.460148000717163,
|
|
"epoch": 0.3775476110925493,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990251693543519,
|
|
"loss": 5.3482,
|
|
"mean_token_accuracy": 0.17708287090063096,
|
|
"num_tokens": 8329127.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.376772785186768,
|
|
"epoch": 0.3779652522552623,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990223992032975,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.18650275617837905,
|
|
"num_tokens": 8338308.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.427081775665283,
|
|
"epoch": 0.37838289341797526,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990196251304612,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.18599178791046142,
|
|
"num_tokens": 8347491.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.3125927448272705,
|
|
"epoch": 0.3788005345806883,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499016847135892,
|
|
"loss": 5.2356,
|
|
"mean_token_accuracy": 0.18336963802576065,
|
|
"num_tokens": 8357112.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.374479627609253,
|
|
"epoch": 0.3792181757434013,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499014065219638,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.1855645716190338,
|
|
"num_tokens": 8366285.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.370549964904785,
|
|
"epoch": 0.37963581690611425,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990112793817481,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.19749765396118163,
|
|
"num_tokens": 8374362.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.457964134216309,
|
|
"epoch": 0.3800534580688273,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990084896222713,
|
|
"loss": 5.373,
|
|
"mean_token_accuracy": 0.18038429617881774,
|
|
"num_tokens": 8383297.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.430696821212768,
|
|
"epoch": 0.38047109923154027,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990056959412562,
|
|
"loss": 5.2628,
|
|
"mean_token_accuracy": 0.1892472431063652,
|
|
"num_tokens": 8391926.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.446486377716065,
|
|
"epoch": 0.38088874039425324,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990028983387517,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.18545185774564743,
|
|
"num_tokens": 8401226.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.451544904708863,
|
|
"epoch": 0.3813063815569663,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990000968148068,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.18938764780759812,
|
|
"num_tokens": 8409966.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.303572940826416,
|
|
"epoch": 0.38172402271967926,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989972913694707,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.20117300301790236,
|
|
"num_tokens": 8418281.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.274835681915283,
|
|
"epoch": 0.38214166388239224,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989944820027923,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.1878328278660774,
|
|
"num_tokens": 8427436.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.419345569610596,
|
|
"epoch": 0.38255930504510527,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989916687148209,
|
|
"loss": 5.2788,
|
|
"mean_token_accuracy": 0.18807316869497298,
|
|
"num_tokens": 8436066.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.425437164306641,
|
|
"epoch": 0.38297694620781825,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989888515056057,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18518477976322173,
|
|
"num_tokens": 8445572.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.4465185642242435,
|
|
"epoch": 0.3833945873705312,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498986030375196,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.18124320209026337,
|
|
"num_tokens": 8454781.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.398690462112427,
|
|
"epoch": 0.38381222853324426,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989832053236413,
|
|
"loss": 5.4056,
|
|
"mean_token_accuracy": 0.18197121024131774,
|
|
"num_tokens": 8463239.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.471783447265625,
|
|
"epoch": 0.38422986969595724,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498980376350991,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.18408905565738679,
|
|
"num_tokens": 8472664.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.451982927322388,
|
|
"epoch": 0.3846475108586702,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004989775434572945,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.1786923885345459,
|
|
"num_tokens": 8483149.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.516049861907959,
|
|
"epoch": 0.38506515202138325,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989747066426015,
|
|
"loss": 5.3099,
|
|
"mean_token_accuracy": 0.1834728553891182,
|
|
"num_tokens": 8492297.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.4100135326385494,
|
|
"epoch": 0.38548279318409623,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989718659069618,
|
|
"loss": 5.3725,
|
|
"mean_token_accuracy": 0.1779784470796585,
|
|
"num_tokens": 8502092.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.456999015808106,
|
|
"epoch": 0.3859004343468092,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498969021250425,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.18879384994506837,
|
|
"num_tokens": 8510816.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.477408838272095,
|
|
"epoch": 0.38631807550952224,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989661726730407,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.18392803966999055,
|
|
"num_tokens": 8520055.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.466255474090576,
|
|
"epoch": 0.3867357166722352,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989633201748591,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.18248372673988342,
|
|
"num_tokens": 8528271.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.369926929473877,
|
|
"epoch": 0.3871533578349482,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989604637559299,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.19368561655282973,
|
|
"num_tokens": 8537360.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.309154796600342,
|
|
"epoch": 0.38757099899766123,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989576034163033,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.19796622395515442,
|
|
"num_tokens": 8546574.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.3989345073699955,
|
|
"epoch": 0.3879886401603742,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989547391560293,
|
|
"loss": 5.2798,
|
|
"mean_token_accuracy": 0.18358010351657866,
|
|
"num_tokens": 8555581.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.393827152252197,
|
|
"epoch": 0.3884062813230872,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000498951870975158,
|
|
"loss": 5.2921,
|
|
"mean_token_accuracy": 0.19488899111747743,
|
|
"num_tokens": 8564539.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.423291778564453,
|
|
"epoch": 0.3888239224858002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989489988737395,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.1843041330575943,
|
|
"num_tokens": 8573804.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.426351499557495,
|
|
"epoch": 0.3892415636485132,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989461228518243,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.18572501242160797,
|
|
"num_tokens": 8583262.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.3900086879730225,
|
|
"epoch": 0.3896592048112262,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989432429094627,
|
|
"loss": 5.3345,
|
|
"mean_token_accuracy": 0.18001127392053604,
|
|
"num_tokens": 8592763.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.511094856262207,
|
|
"epoch": 0.3900768459739392,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989403590467049,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.19080917537212372,
|
|
"num_tokens": 8601884.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.369794034957886,
|
|
"epoch": 0.3904944871366522,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989374712636017,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.18227493464946748,
|
|
"num_tokens": 8611207.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.267108011245727,
|
|
"epoch": 0.39091212829936517,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989345795602036,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.2014046385884285,
|
|
"num_tokens": 8620104.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.394426250457764,
|
|
"epoch": 0.3913297694620782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989316839365609,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.18162577748298644,
|
|
"num_tokens": 8629552.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.404517269134521,
|
|
"epoch": 0.3917474106247912,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989287843927246,
|
|
"loss": 5.2259,
|
|
"mean_token_accuracy": 0.1871084377169609,
|
|
"num_tokens": 8638961.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.44123010635376,
|
|
"epoch": 0.39216505178750416,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989258809287455,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.1845007449388504,
|
|
"num_tokens": 8648051.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.433137226104736,
|
|
"epoch": 0.3925826929502172,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004989229735446743,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.18420229405164718,
|
|
"num_tokens": 8656863.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.24554853439331,
|
|
"epoch": 0.39300033411293017,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989200622405619,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.1956641286611557,
|
|
"num_tokens": 8665455.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.294233274459839,
|
|
"epoch": 0.39341797527564315,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989171470164592,
|
|
"loss": 5.1907,
|
|
"mean_token_accuracy": 0.19241441637277604,
|
|
"num_tokens": 8674119.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.436267757415772,
|
|
"epoch": 0.3938356164383562,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989142278724173,
|
|
"loss": 5.3051,
|
|
"mean_token_accuracy": 0.1827457368373871,
|
|
"num_tokens": 8682979.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.409713268280029,
|
|
"epoch": 0.39425325760106916,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989113048084874,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.18503501117229462,
|
|
"num_tokens": 8692392.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.346532917022705,
|
|
"epoch": 0.39467089876378214,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989083778247206,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.1888894557952881,
|
|
"num_tokens": 8700932.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.528902149200439,
|
|
"epoch": 0.3950885399264952,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498905446921168,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.1768330678343773,
|
|
"num_tokens": 8710683.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.354623413085937,
|
|
"epoch": 0.39550618108920815,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989025120978812,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.18597883284091948,
|
|
"num_tokens": 8719939.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.432675361633301,
|
|
"epoch": 0.39592382225192113,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988995733549113,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.18257280737161635,
|
|
"num_tokens": 8729275.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.369746303558349,
|
|
"epoch": 0.39634146341463417,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988966306923099,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.1936023235321045,
|
|
"num_tokens": 8738048.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.366156435012817,
|
|
"epoch": 0.39675910457734714,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988936841101284,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.18162603229284285,
|
|
"num_tokens": 8746967.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.33245325088501,
|
|
"epoch": 0.3971767457400601,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988907336084186,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.1940227285027504,
|
|
"num_tokens": 8754908.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.359864854812622,
|
|
"epoch": 0.39759438690277316,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988877791872319,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.1967082843184471,
|
|
"num_tokens": 8764489.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.490834379196167,
|
|
"epoch": 0.39801202806548613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988848208466202,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.1675260528922081,
|
|
"num_tokens": 8774365.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.358370637893676,
|
|
"epoch": 0.3984296692281991,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988818585866351,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.18375155776739122,
|
|
"num_tokens": 8783538.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.345037603378296,
|
|
"epoch": 0.39884731039091215,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988788924073288,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.18548517674207687,
|
|
"num_tokens": 8792171.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.465332555770874,
|
|
"epoch": 0.3992649515536251,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988759223087528,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.18156448900699615,
|
|
"num_tokens": 8801325.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.442465782165527,
|
|
"epoch": 0.3996825927163381,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004988729482909595,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.18715113699436187,
|
|
"num_tokens": 8810566.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.313873910903931,
|
|
"epoch": 0.40010023387905114,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004988699703540006,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.19315367490053176,
|
|
"num_tokens": 8819735.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.364927625656128,
|
|
"epoch": 0.4005178750417641,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988669884979284,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.1797439396381378,
|
|
"num_tokens": 8828820.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.402219915390015,
|
|
"epoch": 0.4009355162044771,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988640027227951,
|
|
"loss": 5.1973,
|
|
"mean_token_accuracy": 0.18148496747016907,
|
|
"num_tokens": 8837858.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.383600044250488,
|
|
"epoch": 0.4013531573671901,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000498861013028653,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.1918726831674576,
|
|
"num_tokens": 8847172.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.339367866516113,
|
|
"epoch": 0.4017707985299031,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004988580194155544,
|
|
"loss": 5.1993,
|
|
"mean_token_accuracy": 0.1855437323451042,
|
|
"num_tokens": 8856700.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.259844493865967,
|
|
"epoch": 0.4021884396926161,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988550218835517,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.19720280021429062,
|
|
"num_tokens": 8866108.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.368190765380859,
|
|
"epoch": 0.4026060808553291,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988520204326975,
|
|
"loss": 5.2,
|
|
"mean_token_accuracy": 0.1931179940700531,
|
|
"num_tokens": 8874833.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.440584754943847,
|
|
"epoch": 0.4030237220180421,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988490150630441,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.19055643379688264,
|
|
"num_tokens": 8884211.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.477317667007446,
|
|
"epoch": 0.4034413631807551,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988460057746443,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.18232444822788238,
|
|
"num_tokens": 8893443.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.363722658157348,
|
|
"epoch": 0.4038590043434681,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988429925675507,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.19029450416564941,
|
|
"num_tokens": 8903544.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.393617820739746,
|
|
"epoch": 0.4042766455061811,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988399754418161,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.18659300208091736,
|
|
"num_tokens": 8912270.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.479620504379272,
|
|
"epoch": 0.40469428666889407,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004988369543974932,
|
|
"loss": 5.3615,
|
|
"mean_token_accuracy": 0.17487489730119704,
|
|
"num_tokens": 8922155.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.475509738922119,
|
|
"epoch": 0.4051119278316071,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004988339294346351,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.18078164756298065,
|
|
"num_tokens": 8931844.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.424736261367798,
|
|
"epoch": 0.4055295689943201,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004988309005532946,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.188868248462677,
|
|
"num_tokens": 8940874.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.383653688430786,
|
|
"epoch": 0.40594721015703306,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988278677535247,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.1868128404021263,
|
|
"num_tokens": 8950108.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.417459535598755,
|
|
"epoch": 0.4063648513197461,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988248310353788,
|
|
"loss": 5.3071,
|
|
"mean_token_accuracy": 0.17722485065460206,
|
|
"num_tokens": 8960610.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.328103685379029,
|
|
"epoch": 0.40678249248245907,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988217903989095,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.18296899795532226,
|
|
"num_tokens": 8969853.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.432433557510376,
|
|
"epoch": 0.40720013364517205,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988187458441704,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.1880389094352722,
|
|
"num_tokens": 8979800.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.413327312469482,
|
|
"epoch": 0.4076177748078851,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988156973712149,
|
|
"loss": 5.2561,
|
|
"mean_token_accuracy": 0.18577214777469636,
|
|
"num_tokens": 8988667.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.292411470413208,
|
|
"epoch": 0.40803541597059806,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988126449800961,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.1949210599064827,
|
|
"num_tokens": 8997385.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.291972017288208,
|
|
"epoch": 0.40845305713331104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988095886708676,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.19438403099775314,
|
|
"num_tokens": 9005999.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.415342092514038,
|
|
"epoch": 0.40887069829602407,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988065284435828,
|
|
"loss": 5.3108,
|
|
"mean_token_accuracy": 0.19038266986608504,
|
|
"num_tokens": 9014837.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.4015308856964115,
|
|
"epoch": 0.40928833945873705,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988034642982954,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.18948441743850708,
|
|
"num_tokens": 9023956.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.429320335388184,
|
|
"epoch": 0.40970598062145,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988003962350589,
|
|
"loss": 5.3091,
|
|
"mean_token_accuracy": 0.1788921609520912,
|
|
"num_tokens": 9032945.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.398872375488281,
|
|
"epoch": 0.41012362178416306,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498797324253927,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.19394539296627045,
|
|
"num_tokens": 9042109.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.348408222198486,
|
|
"epoch": 0.41054126294687604,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987942483549537,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.18845173865556716,
|
|
"num_tokens": 9052210.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.368225765228272,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987911685381926,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.19780864268541337,
|
|
"num_tokens": 9060089.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.4792078018188475,
|
|
"epoch": 0.41137654527230205,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987880848036977,
|
|
"loss": 5.2864,
|
|
"mean_token_accuracy": 0.18507588654756546,
|
|
"num_tokens": 9069235.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.3411558151245115,
|
|
"epoch": 0.41179418643501503,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987849971515232,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.19006325900554658,
|
|
"num_tokens": 9077509.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.377354001998901,
|
|
"epoch": 0.412211827597728,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987819055817227,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.201543128490448,
|
|
"num_tokens": 9085493.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.2620697021484375,
|
|
"epoch": 0.41262946876044104,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987788100943507,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.19052086770534515,
|
|
"num_tokens": 9094748.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.375295400619507,
|
|
"epoch": 0.413047109923154,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987757106894613,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.19285566508769988,
|
|
"num_tokens": 9103678.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.401708030700684,
|
|
"epoch": 0.413464751085867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987726073671086,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.19074908047914504,
|
|
"num_tokens": 9112851.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.477257871627808,
|
|
"epoch": 0.41388239224858003,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987695001273471,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.1664121478796005,
|
|
"num_tokens": 9122106.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.40750937461853,
|
|
"epoch": 0.414300033411293,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004987663889702313,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.19598094522953033,
|
|
"num_tokens": 9131580.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.400323009490966,
|
|
"epoch": 0.414717674574006,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987632738958155,
|
|
"loss": 5.3255,
|
|
"mean_token_accuracy": 0.18313443511724473,
|
|
"num_tokens": 9141642.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.477530670166016,
|
|
"epoch": 0.415135315736719,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987601549041541,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.18152194768190383,
|
|
"num_tokens": 9151192.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.430545139312744,
|
|
"epoch": 0.415552956899432,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987570319953018,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.18437962532043456,
|
|
"num_tokens": 9161316.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.464178133010864,
|
|
"epoch": 0.415970598062145,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987539051693134,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.1832400307059288,
|
|
"num_tokens": 9169535.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.379512214660645,
|
|
"epoch": 0.416388239224858,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987507744262436,
|
|
"loss": 5.3,
|
|
"mean_token_accuracy": 0.18225391954183578,
|
|
"num_tokens": 9178187.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.317387676239013,
|
|
"epoch": 0.416805880387571,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987476397661472,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.1872805178165436,
|
|
"num_tokens": 9186342.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.407452154159546,
|
|
"epoch": 0.41722352155028397,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987445011890789,
|
|
"loss": 5.3091,
|
|
"mean_token_accuracy": 0.1835791602730751,
|
|
"num_tokens": 9196470.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.371914911270141,
|
|
"epoch": 0.417641162712997,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498741358695094,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.19258766174316405,
|
|
"num_tokens": 9206587.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.395420503616333,
|
|
"epoch": 0.41805880387571,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000498738212284247,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.18418889343738556,
|
|
"num_tokens": 9216459.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.5213212966918945,
|
|
"epoch": 0.41847644503842296,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987350619565934,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.187247833609581,
|
|
"num_tokens": 9227301.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.453257465362549,
|
|
"epoch": 0.418894086201136,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987319077121884,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.18132562935352325,
|
|
"num_tokens": 9236577.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.308163356781006,
|
|
"epoch": 0.419311727363849,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987287495510869,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.18752797842025756,
|
|
"num_tokens": 9246451.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.355569458007812,
|
|
"epoch": 0.41972936852656195,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987255874733444,
|
|
"loss": 5.1432,
|
|
"mean_token_accuracy": 0.18961535692214965,
|
|
"num_tokens": 9256108.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.32446517944336,
|
|
"epoch": 0.420147009689275,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987224214790161,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.19091393947601318,
|
|
"num_tokens": 9265173.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.348441457748413,
|
|
"epoch": 0.42056465085198796,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987192515681575,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.18611770123243332,
|
|
"num_tokens": 9273979.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.315766763687134,
|
|
"epoch": 0.42098229201470094,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987160777408243,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.18787530064582825,
|
|
"num_tokens": 9281893.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.472248077392578,
|
|
"epoch": 0.421399933177414,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987128999970717,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.18296749889850616,
|
|
"num_tokens": 9290799.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.4789495944976805,
|
|
"epoch": 0.42181757434012696,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987097183369555,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.17676152437925338,
|
|
"num_tokens": 9300562.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.31746916770935,
|
|
"epoch": 0.42223521550283993,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004987065327605315,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.1990979179739952,
|
|
"num_tokens": 9308889.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.2725362300872805,
|
|
"epoch": 0.42265285666555297,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987033432678553,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.189493590593338,
|
|
"num_tokens": 9317957.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.472368431091309,
|
|
"epoch": 0.42307049782826595,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004987001498589828,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.17723825573921204,
|
|
"num_tokens": 9327849.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.440432453155518,
|
|
"epoch": 0.4234881389909789,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049869695253397,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.18077140152454377,
|
|
"num_tokens": 9337165.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.313253164291382,
|
|
"epoch": 0.42390578015369196,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986937512928727,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.18746636509895326,
|
|
"num_tokens": 9346817.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.455717754364014,
|
|
"epoch": 0.42432342131640494,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498690546135747,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.18911795169115067,
|
|
"num_tokens": 9356420.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.386098766326905,
|
|
"epoch": 0.4247410624791179,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986873370626491,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.189178729057312,
|
|
"num_tokens": 9365580.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.350814390182495,
|
|
"epoch": 0.42515870364183095,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498684124073635,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.18439095914363862,
|
|
"num_tokens": 9375116.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.436033010482788,
|
|
"epoch": 0.4255763448045439,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986809071687612,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.1926806852221489,
|
|
"num_tokens": 9384129.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.3734883785247805,
|
|
"epoch": 0.4259939859672569,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986776863480838,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.1906578704714775,
|
|
"num_tokens": 9392757.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.2859800338745115,
|
|
"epoch": 0.42641162712996994,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986744616116593,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.18857923597097398,
|
|
"num_tokens": 9401753.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.378779363632202,
|
|
"epoch": 0.4268292682926829,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498671232959544,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.1763235256075859,
|
|
"num_tokens": 9411400.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.43658299446106,
|
|
"epoch": 0.42724690945539595,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986680003917947,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.18982613682746888,
|
|
"num_tokens": 9420206.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.401480293273925,
|
|
"epoch": 0.42766455061810893,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986647639084677,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.19036026149988175,
|
|
"num_tokens": 9428418.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.409142255783081,
|
|
"epoch": 0.4280821917808219,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049866152350962,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.18732437193393708,
|
|
"num_tokens": 9437624.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.315325927734375,
|
|
"epoch": 0.42849983294353494,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986582791953078,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.19597716480493546,
|
|
"num_tokens": 9446857.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.343311595916748,
|
|
"epoch": 0.4289174741062479,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986550309655884,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.18682250380516052,
|
|
"num_tokens": 9456024.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.340610456466675,
|
|
"epoch": 0.4293351152689609,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986517788205184,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.1896860346198082,
|
|
"num_tokens": 9464018.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.362600564956665,
|
|
"epoch": 0.42975275643167393,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986485227601548,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.18536152690649033,
|
|
"num_tokens": 9472430.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.369005727767944,
|
|
"epoch": 0.4301703975943869,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986452627845547,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.1967921644449234,
|
|
"num_tokens": 9480592.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.33554310798645,
|
|
"epoch": 0.4305880387570999,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498641998893775,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.19341528415679932,
|
|
"num_tokens": 9489162.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.318466138839722,
|
|
"epoch": 0.4310056799198129,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986387310878728,
|
|
"loss": 5.2151,
|
|
"mean_token_accuracy": 0.19112633168697357,
|
|
"num_tokens": 9499210.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.377790069580078,
|
|
"epoch": 0.4314233210825259,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986354593669056,
|
|
"loss": 5.2663,
|
|
"mean_token_accuracy": 0.18936024606227875,
|
|
"num_tokens": 9508062.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.407652807235718,
|
|
"epoch": 0.4318409622452389,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004986321837309304,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.19714585691690445,
|
|
"num_tokens": 9516756.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.316244173049927,
|
|
"epoch": 0.4322586034079519,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986289041800046,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.1943398654460907,
|
|
"num_tokens": 9525305.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.3937585830688475,
|
|
"epoch": 0.4326762445706649,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986256207141857,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.19480980634689332,
|
|
"num_tokens": 9534310.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.436962366104126,
|
|
"epoch": 0.43309388573337787,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004986223333335311,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.18273770362138747,
|
|
"num_tokens": 9543648.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.295369672775268,
|
|
"epoch": 0.4335115268960909,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004986190420380985,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.19407663643360137,
|
|
"num_tokens": 9553081.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.418140506744384,
|
|
"epoch": 0.4339291680588039,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004986157468279453,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.18970040380954742,
|
|
"num_tokens": 9563184.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.360654497146607,
|
|
"epoch": 0.43434680922151686,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986124477031293,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.18823157697916032,
|
|
"num_tokens": 9572550.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.323933410644531,
|
|
"epoch": 0.4347644503842299,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986091446637083,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.18797653615474702,
|
|
"num_tokens": 9580900.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.410753631591797,
|
|
"epoch": 0.4351820915469429,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049860583770974,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.19158488065004348,
|
|
"num_tokens": 9589340.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.4190937042236325,
|
|
"epoch": 0.43559973270965585,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986025268412823,
|
|
"loss": 5.3459,
|
|
"mean_token_accuracy": 0.18684408366680144,
|
|
"num_tokens": 9599316.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.426744747161865,
|
|
"epoch": 0.4360173738723689,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004985992120583933,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.1843533769249916,
|
|
"num_tokens": 9609350.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.425740528106689,
|
|
"epoch": 0.43643501503508186,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498595893361131,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.18969244211912156,
|
|
"num_tokens": 9618491.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.4246128559112545,
|
|
"epoch": 0.43685265619779484,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004985925707495533,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.1807746022939682,
|
|
"num_tokens": 9629613.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.364225912094116,
|
|
"epoch": 0.4372702973605079,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985892442237186,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.19382885545492173,
|
|
"num_tokens": 9638035.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.4434620380401615,
|
|
"epoch": 0.43768793852322085,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004985859137836851,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.18356846868991852,
|
|
"num_tokens": 9647378.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.447882747650146,
|
|
"epoch": 0.43810557968593383,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985825794295109,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19364110082387925,
|
|
"num_tokens": 9655728.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.3699218273162845,
|
|
"epoch": 0.43852322084864687,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985792411612546,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.1897771030664444,
|
|
"num_tokens": 9665063.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.397814607620239,
|
|
"epoch": 0.43894086201135984,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985758989789746,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.18403451442718505,
|
|
"num_tokens": 9674406.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.380377006530762,
|
|
"epoch": 0.4393585031740728,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985725528827293,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.18937455415725707,
|
|
"num_tokens": 9683303.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.35370659828186,
|
|
"epoch": 0.43977614433678586,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985692028725774,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.18712253719568253,
|
|
"num_tokens": 9692938.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.3999334335327145,
|
|
"epoch": 0.44019378549949884,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985658489485774,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.18869786560535431,
|
|
"num_tokens": 9702192.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.406451416015625,
|
|
"epoch": 0.4406114266622118,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985624911107882,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.1780784010887146,
|
|
"num_tokens": 9711301.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.386457204818726,
|
|
"epoch": 0.44102906782492485,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985591293592685,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.1831320807337761,
|
|
"num_tokens": 9720768.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.37437219619751,
|
|
"epoch": 0.4414467089876378,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985557636940771,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.18987678736448288,
|
|
"num_tokens": 9730007.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.458893823623657,
|
|
"epoch": 0.4418643501503508,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498552394115273,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.18142006546258926,
|
|
"num_tokens": 9739546.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.348581266403198,
|
|
"epoch": 0.44228199131306384,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985490206229151,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.1912358820438385,
|
|
"num_tokens": 9749615.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.432922267913819,
|
|
"epoch": 0.4426996324757768,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985456432170626,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.18086133599281312,
|
|
"num_tokens": 9759285.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.318398141860962,
|
|
"epoch": 0.4431172736384898,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004985422618977744,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.18311391472816468,
|
|
"num_tokens": 9769396.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.392572450637817,
|
|
"epoch": 0.44353491480120283,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049853887666511,
|
|
"loss": 5.2861,
|
|
"mean_token_accuracy": 0.18341459333896637,
|
|
"num_tokens": 9779632.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.4518075466156,
|
|
"epoch": 0.4439525559639158,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985354875191283,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.1879651963710785,
|
|
"num_tokens": 9788090.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.241060638427735,
|
|
"epoch": 0.4443701971266288,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985320944598889,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.2016327351331711,
|
|
"num_tokens": 9795844.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.2943628311157225,
|
|
"epoch": 0.4447878382893418,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985286974874512,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.20228331387043,
|
|
"num_tokens": 9805119.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.386738395690918,
|
|
"epoch": 0.4452054794520548,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985252966018745,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.19004951119422914,
|
|
"num_tokens": 9813842.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.406052017211914,
|
|
"epoch": 0.4456231206147678,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985218918032184,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.17869383841753006,
|
|
"num_tokens": 9822872.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.441792345046997,
|
|
"epoch": 0.4460407617774808,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004985184830915426,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.1822514697909355,
|
|
"num_tokens": 9832710.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.438762617111206,
|
|
"epoch": 0.4464584029401938,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985150704669067,
|
|
"loss": 5.2431,
|
|
"mean_token_accuracy": 0.1892638772726059,
|
|
"num_tokens": 9841047.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.4218213081359865,
|
|
"epoch": 0.44687604410290677,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985116539293704,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.19137232452630998,
|
|
"num_tokens": 9850168.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.315924024581909,
|
|
"epoch": 0.4472936852656198,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985082334789936,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.18233537375926973,
|
|
"num_tokens": 9859550.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.454907941818237,
|
|
"epoch": 0.4477113264283328,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004985048091158361,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.18741666227579118,
|
|
"num_tokens": 9868317.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.514013719558716,
|
|
"epoch": 0.44812896759104576,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985013808399578,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.1722334012389183,
|
|
"num_tokens": 9878421.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.412441158294678,
|
|
"epoch": 0.4485466087537588,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004984979486514189,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.19599671363830568,
|
|
"num_tokens": 9887213.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.3495858669281,
|
|
"epoch": 0.44896424991647177,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984945125502795,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.18053569197654723,
|
|
"num_tokens": 9897274.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.295299482345581,
|
|
"epoch": 0.44938189107918475,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984910725365994,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.19133128225803375,
|
|
"num_tokens": 9906765.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.466361427307129,
|
|
"epoch": 0.4497995322418978,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984876286104392,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.1816006988286972,
|
|
"num_tokens": 9916149.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.355660104751587,
|
|
"epoch": 0.45021717340461076,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004984841807718591,
|
|
"loss": 5.2264,
|
|
"mean_token_accuracy": 0.18760104328393937,
|
|
"num_tokens": 9925657.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.349101877212524,
|
|
"epoch": 0.45063481456732374,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984807290209193,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.18206236511468887,
|
|
"num_tokens": 9934740.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.493886566162109,
|
|
"epoch": 0.45105245573003677,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984772733576803,
|
|
"loss": 5.3559,
|
|
"mean_token_accuracy": 0.18267310559749603,
|
|
"num_tokens": 9943516.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.413296508789062,
|
|
"epoch": 0.45147009689274975,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984738137822028,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.1804915949702263,
|
|
"num_tokens": 9952998.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.389512252807617,
|
|
"epoch": 0.45188773805546273,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498470350294547,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.19502537548542023,
|
|
"num_tokens": 9961698.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.3808997631072994,
|
|
"epoch": 0.45230537921817576,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984668828947739,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.1822548598051071,
|
|
"num_tokens": 9972015.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.457005596160888,
|
|
"epoch": 0.45272302038088874,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004984634115829439,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.18134659230709077,
|
|
"num_tokens": 9981834.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.376378774642944,
|
|
"epoch": 0.4531406615436017,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498459936359118,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.18979233056306838,
|
|
"num_tokens": 9991113.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.345542335510254,
|
|
"epoch": 0.45355830270631475,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984564572233568,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.19134598821401597,
|
|
"num_tokens": 10000048.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.394504261016846,
|
|
"epoch": 0.45397594386902773,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004984529741757216,
|
|
"loss": 5.2096,
|
|
"mean_token_accuracy": 0.19118922650814058,
|
|
"num_tokens": 10009389.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.343679285049438,
|
|
"epoch": 0.4543935850317407,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984494872162728,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.1975254774093628,
|
|
"num_tokens": 10018342.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.370709705352783,
|
|
"epoch": 0.45481122619445374,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498445996345072,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.19156473726034165,
|
|
"num_tokens": 10027219.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.3162154197692875,
|
|
"epoch": 0.4552288673571667,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984425015621799,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.18539076298475266,
|
|
"num_tokens": 10036635.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.341330337524414,
|
|
"epoch": 0.4556465085198797,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498439002867658,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.18753532469272613,
|
|
"num_tokens": 10045655.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.47757921218872,
|
|
"epoch": 0.45606414968259273,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984355002615673,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.1800361230969429,
|
|
"num_tokens": 10054366.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.371311235427856,
|
|
"epoch": 0.4564817908453057,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984319937439693,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.19732216447591783,
|
|
"num_tokens": 10062548.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.317391633987427,
|
|
"epoch": 0.4568994320080187,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004984284833149252,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.1900743067264557,
|
|
"num_tokens": 10071333.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.275013732910156,
|
|
"epoch": 0.4573170731707317,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004984249689744966,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.2027517795562744,
|
|
"num_tokens": 10079502.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.317129468917846,
|
|
"epoch": 0.4577347143334447,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498421450722745,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.19829394668340683,
|
|
"num_tokens": 10088648.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.303921461105347,
|
|
"epoch": 0.4581523554961577,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498417928559732,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.1948361501097679,
|
|
"num_tokens": 10097742.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.390201759338379,
|
|
"epoch": 0.4585699966588707,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004984144024855191,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.18410812467336654,
|
|
"num_tokens": 10107228.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.381973600387573,
|
|
"epoch": 0.4589876378215837,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984108725001683,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.19159997403621673,
|
|
"num_tokens": 10115488.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.295147180557251,
|
|
"epoch": 0.45940527898429667,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004984073386037413,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.203596593439579,
|
|
"num_tokens": 10124235.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.248975610733032,
|
|
"epoch": 0.4598229201470097,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004984038007962997,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.1957690253853798,
|
|
"num_tokens": 10133208.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.298121595382691,
|
|
"epoch": 0.4602405613097227,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004984002590779059,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.19542327374219895,
|
|
"num_tokens": 10142754.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.3809497356414795,
|
|
"epoch": 0.46065820247243566,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983967134486215,
|
|
"loss": 5.2314,
|
|
"mean_token_accuracy": 0.18743112087249755,
|
|
"num_tokens": 10152114.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.307916259765625,
|
|
"epoch": 0.4610758436351487,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004983931639085088,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.19539449959993363,
|
|
"num_tokens": 10161562.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.418841218948364,
|
|
"epoch": 0.4614934847978617,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983896104576298,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.18959795981645583,
|
|
"num_tokens": 10170461.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.31503381729126,
|
|
"epoch": 0.46191112596057465,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498386053096047,
|
|
"loss": 5.2426,
|
|
"mean_token_accuracy": 0.1898938775062561,
|
|
"num_tokens": 10179243.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.35144624710083,
|
|
"epoch": 0.4623287671232877,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983824918238221,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.1926346242427826,
|
|
"num_tokens": 10187935.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.3695355415344235,
|
|
"epoch": 0.46274640828600067,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498378926641018,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.18204442411661148,
|
|
"num_tokens": 10196185.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.3888304233551025,
|
|
"epoch": 0.46316404944871364,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983753575476969,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.1844029977917671,
|
|
"num_tokens": 10205373.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.396563768386841,
|
|
"epoch": 0.4635816906114267,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983717845439212,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.19701038748025895,
|
|
"num_tokens": 10214464.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.376925754547119,
|
|
"epoch": 0.46399933177413966,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983682076297536,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.187737900018692,
|
|
"num_tokens": 10224462.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.389674329757691,
|
|
"epoch": 0.46441697293685263,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983646268052567,
|
|
"loss": 5.2054,
|
|
"mean_token_accuracy": 0.19277113527059556,
|
|
"num_tokens": 10233123.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.291779088973999,
|
|
"epoch": 0.46483461409956567,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983610420704931,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.19439888894557952,
|
|
"num_tokens": 10241613.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.424734973907471,
|
|
"epoch": 0.46525225526227865,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983574534255256,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.17613304555416107,
|
|
"num_tokens": 10251809.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.3163489818573,
|
|
"epoch": 0.4656698964249916,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498353860870417,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.19350660890340804,
|
|
"num_tokens": 10260198.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.349600791931152,
|
|
"epoch": 0.46608753758770466,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004983502644052303,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.19048164933919906,
|
|
"num_tokens": 10268906.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.3378270149230955,
|
|
"epoch": 0.46650517875041764,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983466640300282,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.18908486217260362,
|
|
"num_tokens": 10278526.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.34457745552063,
|
|
"epoch": 0.4669228199131306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983430597448741,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.1906500831246376,
|
|
"num_tokens": 10287428.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.454566383361817,
|
|
"epoch": 0.46734046107584365,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983394515498308,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.1834123745560646,
|
|
"num_tokens": 10297136.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.384262609481811,
|
|
"epoch": 0.46775810223855663,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004983358394449616,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.18722758144140245,
|
|
"num_tokens": 10305678.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.251025152206421,
|
|
"epoch": 0.4681757434012696,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983322234303297,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.1910208821296692,
|
|
"num_tokens": 10314690.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.319563531875611,
|
|
"epoch": 0.46859338456398264,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983286035059984,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.19533875435590745,
|
|
"num_tokens": 10323521.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.380634450912476,
|
|
"epoch": 0.4690110257266956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983249796720311,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.19393938928842544,
|
|
"num_tokens": 10333077.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.3757720470428465,
|
|
"epoch": 0.4694286668894086,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983213519284912,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.18983528167009353,
|
|
"num_tokens": 10342194.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.260043954849243,
|
|
"epoch": 0.46984630805212163,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983177202754421,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.2030367597937584,
|
|
"num_tokens": 10351009.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.376303195953369,
|
|
"epoch": 0.4702639492148346,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004983140847129476,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.18697713911533356,
|
|
"num_tokens": 10360872.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.40290060043335,
|
|
"epoch": 0.4706815903775476,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004983104452410713,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.19480491876602174,
|
|
"num_tokens": 10370159.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.324526309967041,
|
|
"epoch": 0.4710992315402606,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983068018598768,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.1943564236164093,
|
|
"num_tokens": 10379219.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.348826360702515,
|
|
"epoch": 0.4715168727029736,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498303154569428,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.1874924674630165,
|
|
"num_tokens": 10389425.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.41987681388855,
|
|
"epoch": 0.4719345138656866,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982995033697887,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.19177254438400268,
|
|
"num_tokens": 10398023.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.375391054153442,
|
|
"epoch": 0.4723521550283996,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982958482610226,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.19643176794052125,
|
|
"num_tokens": 10406578.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.2869110107421875,
|
|
"epoch": 0.4727697961911126,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498292189243194,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.19533443599939346,
|
|
"num_tokens": 10416448.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.3916514873504635,
|
|
"epoch": 0.47318743735382557,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000498288526316367,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.19050733000040054,
|
|
"num_tokens": 10425414.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.32529845237732,
|
|
"epoch": 0.4736050785165386,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982848594806054,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.19978216737508775,
|
|
"num_tokens": 10433900.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.386235618591309,
|
|
"epoch": 0.4740227196792516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982811887359736,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.18401811867952347,
|
|
"num_tokens": 10443077.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.3513110160827635,
|
|
"epoch": 0.47444036084196456,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004982775140825359,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.19070570021867753,
|
|
"num_tokens": 10452791.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.452741479873657,
|
|
"epoch": 0.4748580020046776,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004982738355203565,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18342108875513077,
|
|
"num_tokens": 10462087.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.504034519195557,
|
|
"epoch": 0.47527564316739057,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982701530494998,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.17478589415550233,
|
|
"num_tokens": 10472576.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.34589409828186,
|
|
"epoch": 0.47569328433010355,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982664666700304,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.19960732609033585,
|
|
"num_tokens": 10481176.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.341583633422852,
|
|
"epoch": 0.4761109254928166,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982627763820128,
|
|
"loss": 5.1829,
|
|
"mean_token_accuracy": 0.18901185393333436,
|
|
"num_tokens": 10490558.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.384727573394775,
|
|
"epoch": 0.47652856665552956,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004982590821855115,
|
|
"loss": 5.2513,
|
|
"mean_token_accuracy": 0.18868363350629808,
|
|
"num_tokens": 10499543.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.299352836608887,
|
|
"epoch": 0.47694620781824254,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004982553840805912,
|
|
"loss": 5.1354,
|
|
"mean_token_accuracy": 0.1942030221223831,
|
|
"num_tokens": 10508162.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.332329607009887,
|
|
"epoch": 0.4773638489809556,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982516820673167,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.19356240928173066,
|
|
"num_tokens": 10516837.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.273949670791626,
|
|
"epoch": 0.47778149014366855,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982479761457528,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.1921186253428459,
|
|
"num_tokens": 10526208.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.390781116485596,
|
|
"epoch": 0.47819913130638153,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004982442663159643,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.18640661835670472,
|
|
"num_tokens": 10536002.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.427158784866333,
|
|
"epoch": 0.47861677246909456,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982405525780162,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.19370876550674437,
|
|
"num_tokens": 10545861.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.300282430648804,
|
|
"epoch": 0.47903441363180754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982368349319736,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.1909020721912384,
|
|
"num_tokens": 10555357.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.320709848403931,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982331133779014,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.1870773509144783,
|
|
"num_tokens": 10564744.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.308973360061645,
|
|
"epoch": 0.47986969595723356,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982293879158649,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.1974307656288147,
|
|
"num_tokens": 10573736.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.330884265899658,
|
|
"epoch": 0.48028733711994653,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982256585459293,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.18826668560504914,
|
|
"num_tokens": 10583238.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.409971714019775,
|
|
"epoch": 0.4807049782826595,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982219252681597,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.18804027289152145,
|
|
"num_tokens": 10592316.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.385182619094849,
|
|
"epoch": 0.48112261944537255,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004982181880826218,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.19537543058395385,
|
|
"num_tokens": 10601418.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.325291872024536,
|
|
"epoch": 0.4815402606080855,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982144469893807,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.19584563970565796,
|
|
"num_tokens": 10610513.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.37113094329834,
|
|
"epoch": 0.4819579017707985,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498210701988502,
|
|
"loss": 5.1228,
|
|
"mean_token_accuracy": 0.19749906957149505,
|
|
"num_tokens": 10619529.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.43244514465332,
|
|
"epoch": 0.48237554293351154,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982069530800514,
|
|
"loss": 5.209,
|
|
"mean_token_accuracy": 0.1954508662223816,
|
|
"num_tokens": 10628263.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.354029369354248,
|
|
"epoch": 0.4827931840962245,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982032002640943,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19558541029691695,
|
|
"num_tokens": 10637605.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.36125111579895,
|
|
"epoch": 0.48321082525893755,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981994435406965,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.1866827830672264,
|
|
"num_tokens": 10647113.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.312998199462891,
|
|
"epoch": 0.4836284664216505,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981956829099239,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.20114692598581313,
|
|
"num_tokens": 10655464.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.374098062515259,
|
|
"epoch": 0.4840461075843635,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981919183718422,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.19232010394334792,
|
|
"num_tokens": 10664689.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.234326982498169,
|
|
"epoch": 0.48446374874707654,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981881499265173,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.19535593539476395,
|
|
"num_tokens": 10673440.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.307293033599853,
|
|
"epoch": 0.4848813899097895,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981843775740151,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.19040369093418122,
|
|
"num_tokens": 10683075.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.375690889358521,
|
|
"epoch": 0.4852990310725025,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981806013144017,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.1962505415081978,
|
|
"num_tokens": 10692663.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.327901124954224,
|
|
"epoch": 0.48571667223521553,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981768211477434,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.19828961789608002,
|
|
"num_tokens": 10702068.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.332657814025879,
|
|
"epoch": 0.4861343133979285,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000498173037074106,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.18400243371725084,
|
|
"num_tokens": 10711230.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.278089427947998,
|
|
"epoch": 0.4865519545606415,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004981692490935561,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.19734678864479066,
|
|
"num_tokens": 10719651.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.325994205474854,
|
|
"epoch": 0.4869695957233545,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004981654572061597,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.19402495622634888,
|
|
"num_tokens": 10729342.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.37397608757019,
|
|
"epoch": 0.4873872368860675,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004981616614119836,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.19246188551187515,
|
|
"num_tokens": 10738617.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.408673477172852,
|
|
"epoch": 0.4878048780487805,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981578617110938,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.19588533341884612,
|
|
"num_tokens": 10746881.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.3041821956634525,
|
|
"epoch": 0.4882225192114935,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981540581035571,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.1984473794698715,
|
|
"num_tokens": 10755848.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.253594017028808,
|
|
"epoch": 0.4886401603742065,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049815025058944,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.19371838867664337,
|
|
"num_tokens": 10765519.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.268149375915527,
|
|
"epoch": 0.48905780153691947,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981464391688092,
|
|
"loss": 5.206,
|
|
"mean_token_accuracy": 0.19048965275287627,
|
|
"num_tokens": 10776408.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.354688262939453,
|
|
"epoch": 0.4894754426996325,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981426238417312,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.1960027977824211,
|
|
"num_tokens": 10785499.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.340050077438354,
|
|
"epoch": 0.4898930838623455,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981388046082731,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.19211888015270234,
|
|
"num_tokens": 10794736.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.344694471359253,
|
|
"epoch": 0.49031072502505846,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981349814685016,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.1892123520374298,
|
|
"num_tokens": 10804125.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.415939283370972,
|
|
"epoch": 0.4907283661877715,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004981311544224838,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.18712200224399567,
|
|
"num_tokens": 10813465.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.321809864044189,
|
|
"epoch": 0.49114600735048447,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004981273234702864,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.2013658717274666,
|
|
"num_tokens": 10821550.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.297535037994384,
|
|
"epoch": 0.49156364851319745,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004981234886119767,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.19541339278221131,
|
|
"num_tokens": 10830683.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.335745573043823,
|
|
"epoch": 0.4919812896759105,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981196498476217,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.1970521867275238,
|
|
"num_tokens": 10839492.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.273152780532837,
|
|
"epoch": 0.49239893083862346,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981158071772887,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.2064237639307976,
|
|
"num_tokens": 10847998.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.222529649734497,
|
|
"epoch": 0.49281657200133644,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981119606010449,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.20315144956111908,
|
|
"num_tokens": 10856438.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.228286170959473,
|
|
"epoch": 0.4932342131640495,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981081101189577,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.19506627172231675,
|
|
"num_tokens": 10865936.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.309895753860474,
|
|
"epoch": 0.49365185432676245,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004981042557310945,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.19949063807725906,
|
|
"num_tokens": 10874621.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.278696966171265,
|
|
"epoch": 0.49406949548947543,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981003974375227,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.19836925566196442,
|
|
"num_tokens": 10883516.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.313035345077514,
|
|
"epoch": 0.49448713665218846,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004980965352383099,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.18487957268953323,
|
|
"num_tokens": 10892580.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.378054094314575,
|
|
"epoch": 0.49490477781490144,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980926691335238,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.20027163475751877,
|
|
"num_tokens": 10901227.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.363157463073731,
|
|
"epoch": 0.4953224189776144,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980887991232318,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.18527625054121016,
|
|
"num_tokens": 10909454.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.4356568336486815,
|
|
"epoch": 0.49574006014032745,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498084925207502,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.18741102665662765,
|
|
"num_tokens": 10919792.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.316114044189453,
|
|
"epoch": 0.49615770130304043,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000498081047386402,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.18623075932264327,
|
|
"num_tokens": 10930523.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.262543535232544,
|
|
"epoch": 0.4965753424657534,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980771656599998,
|
|
"loss": 5.1516,
|
|
"mean_token_accuracy": 0.19434967637062073,
|
|
"num_tokens": 10940075.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.344896221160889,
|
|
"epoch": 0.49699298362846644,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980732800283633,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.1927078127861023,
|
|
"num_tokens": 10949059.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.3015882015228275,
|
|
"epoch": 0.4974106247911794,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980693904915604,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.20048502832651138,
|
|
"num_tokens": 10958313.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.296784687042236,
|
|
"epoch": 0.4978282659538924,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004980654970496595,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.18923251777887345,
|
|
"num_tokens": 10967666.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.3919782638549805,
|
|
"epoch": 0.49824590711660544,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980615997027284,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.1863034501671791,
|
|
"num_tokens": 10976519.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.4367328643798825,
|
|
"epoch": 0.4986635482793184,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980576984508356,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.18201553225517272,
|
|
"num_tokens": 10987138.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.35586109161377,
|
|
"epoch": 0.4990811894420314,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980537932940492,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.19468488544225693,
|
|
"num_tokens": 10996517.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.32632417678833,
|
|
"epoch": 0.4994988306047444,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980498842324377,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.1932087779045105,
|
|
"num_tokens": 11006312.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.308896780014038,
|
|
"epoch": 0.4999164717674574,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980459712660694,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.19807814210653304,
|
|
"num_tokens": 11015535.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.336176252365112,
|
|
"epoch": 0.5003341129301704,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980420543950131,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.1983096867799759,
|
|
"num_tokens": 11024887.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.209236431121826,
|
|
"epoch": 0.5007517540928834,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004980381336193371,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.1991642013192177,
|
|
"num_tokens": 11033147.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.311929416656494,
|
|
"epoch": 0.5011693952555963,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980342089391099,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.1955171287059784,
|
|
"num_tokens": 11042726.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5011693952555963,
|
|
"eval_entropy": 5.081735794384129,
|
|
"eval_loss": 5.141722679138184,
|
|
"eval_mean_token_accuracy": 0.2040335075616887,
|
|
"eval_num_tokens": 11042726.0,
|
|
"eval_runtime": 20.9105,
|
|
"eval_samples_per_second": 1805.931,
|
|
"eval_steps_per_second": 225.771,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.360365772247315,
|
|
"epoch": 0.5015870364183094,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004980302803544006,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.1939845934510231,
|
|
"num_tokens": 11052181.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.3511741161346436,
|
|
"epoch": 0.5020046775810224,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980263478652778,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.19110709428787231,
|
|
"num_tokens": 11061586.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.4524132251739506,
|
|
"epoch": 0.5024223187437353,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004980224114718102,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.1969229742884636,
|
|
"num_tokens": 11070914.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.271578216552735,
|
|
"epoch": 0.5028399599064484,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980184711740669,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.20396809577941893,
|
|
"num_tokens": 11079836.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.236273670196534,
|
|
"epoch": 0.5032576010691614,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004980145269721168,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.1967662677168846,
|
|
"num_tokens": 11088320.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.365673637390136,
|
|
"epoch": 0.5036752422318743,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498010578866029,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.188813653588295,
|
|
"num_tokens": 11097803.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.427157783508301,
|
|
"epoch": 0.5040928833945874,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004980066268558726,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.18771855682134628,
|
|
"num_tokens": 11107218.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.37835807800293,
|
|
"epoch": 0.5045105245573004,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980026709417167,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.18941182047128677,
|
|
"num_tokens": 11115599.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.248134517669678,
|
|
"epoch": 0.5049281657200133,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979987111236306,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20160748362541198,
|
|
"num_tokens": 11124312.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.226345014572144,
|
|
"epoch": 0.5053458068827263,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004979947474016837,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.1943332776427269,
|
|
"num_tokens": 11133117.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.434397459030151,
|
|
"epoch": 0.5057634480454394,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979907797759453,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.19548466205596923,
|
|
"num_tokens": 11141972.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.465583467483521,
|
|
"epoch": 0.5061810892081523,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979868082464849,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.19221996515989304,
|
|
"num_tokens": 11151416.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.306528520584107,
|
|
"epoch": 0.5065987303708653,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979828328133719,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.19172205179929733,
|
|
"num_tokens": 11160727.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.280411195755005,
|
|
"epoch": 0.5070163715335784,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004979788534766762,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.18678625226020812,
|
|
"num_tokens": 11171350.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.363430213928223,
|
|
"epoch": 0.5074340126962913,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004979748702364672,
|
|
"loss": 5.124,
|
|
"mean_token_accuracy": 0.19078159481287002,
|
|
"num_tokens": 11180233.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.319603109359742,
|
|
"epoch": 0.5078516538590043,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004979708830928147,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.1907967209815979,
|
|
"num_tokens": 11189269.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.328796815872193,
|
|
"epoch": 0.5082692950217174,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004979668920457884,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.1928774580359459,
|
|
"num_tokens": 11199072.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.29304986000061,
|
|
"epoch": 0.5086869361844303,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004979628970954584,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.20194179713726043,
|
|
"num_tokens": 11207164.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.3017181873321535,
|
|
"epoch": 0.5091045773471433,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004979588982418944,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.18876982778310775,
|
|
"num_tokens": 11216557.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.441608667373657,
|
|
"epoch": 0.5095222185098564,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979548954851666,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.19242940545082093,
|
|
"num_tokens": 11227277.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.2942492961883545,
|
|
"epoch": 0.5099398596725693,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000497950888825345,
|
|
"loss": 5.0952,
|
|
"mean_token_accuracy": 0.19799752682447433,
|
|
"num_tokens": 11236226.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.334103298187256,
|
|
"epoch": 0.5103575008352823,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004979468782624996,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.19401877075433732,
|
|
"num_tokens": 11245246.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.353033399581909,
|
|
"epoch": 0.5107751419979953,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979428637967009,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.1874435395002365,
|
|
"num_tokens": 11254437.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.355159568786621,
|
|
"epoch": 0.5111927831607083,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979388454280189,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.19815486371517183,
|
|
"num_tokens": 11262413.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.332062864303589,
|
|
"epoch": 0.5116104243234213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497934823156524,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.1853897526860237,
|
|
"num_tokens": 11272061.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.298949956893921,
|
|
"epoch": 0.5120280654861343,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979307969822869,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.20036447942256927,
|
|
"num_tokens": 11281623.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.277247905731201,
|
|
"epoch": 0.5124457066488474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979267669053776,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.2129800647497177,
|
|
"num_tokens": 11290202.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.328994989395142,
|
|
"epoch": 0.5128633478115603,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004979227329258671,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.19619348347187043,
|
|
"num_tokens": 11299040.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.369257879257202,
|
|
"epoch": 0.5132809889742733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004979186950438256,
|
|
"loss": 5.1705,
|
|
"mean_token_accuracy": 0.1910765990614891,
|
|
"num_tokens": 11307938.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.337589979171753,
|
|
"epoch": 0.5136986301369864,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004979146532593243,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.1924214020371437,
|
|
"num_tokens": 11316915.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.341695308685303,
|
|
"epoch": 0.5141162712996993,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004979106075724334,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.19055252224206926,
|
|
"num_tokens": 11326634.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.424534702301026,
|
|
"epoch": 0.5145339124624123,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979065579832242,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.18226447850465774,
|
|
"num_tokens": 11336502.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.347924280166626,
|
|
"epoch": 0.5149515536251253,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004979025044917673,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.1873267561197281,
|
|
"num_tokens": 11346125.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.425796222686768,
|
|
"epoch": 0.5153691947878383,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978984470981339,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.18079230785369874,
|
|
"num_tokens": 11355713.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.306069564819336,
|
|
"epoch": 0.5157868359505513,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004978943858023946,
|
|
"loss": 5.1206,
|
|
"mean_token_accuracy": 0.19629030227661132,
|
|
"num_tokens": 11364726.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.305667066574097,
|
|
"epoch": 0.5162044771132643,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497890320604621,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.19300412088632585,
|
|
"num_tokens": 11373779.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.268637418746948,
|
|
"epoch": 0.5166221182759773,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000497886251504884,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.19585707783699036,
|
|
"num_tokens": 11382641.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.302853298187256,
|
|
"epoch": 0.5170397594386903,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978821785032549,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.19570249319076538,
|
|
"num_tokens": 11392200.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.355218982696533,
|
|
"epoch": 0.5174574006014033,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.2121,
|
|
"mean_token_accuracy": 0.18448595255613326,
|
|
"num_tokens": 11401884.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.363968133926392,
|
|
"epoch": 0.5178750417641163,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004978740207946056,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.2057302013039589,
|
|
"num_tokens": 11410710.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.28050856590271,
|
|
"epoch": 0.5182926829268293,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004978699360877281,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.20113258808851242,
|
|
"num_tokens": 11419622.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.2555395603179935,
|
|
"epoch": 0.5187103240895423,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978658474792442,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.20424578189849854,
|
|
"num_tokens": 11427631.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.295728254318237,
|
|
"epoch": 0.5191279652522552,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978617549692253,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.19481036812067032,
|
|
"num_tokens": 11437630.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.402774667739868,
|
|
"epoch": 0.5195456064149683,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004978576585577432,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.1782876655459404,
|
|
"num_tokens": 11447962.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.4383378505706785,
|
|
"epoch": 0.5199632475776813,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004978535582448695,
|
|
"loss": 5.2032,
|
|
"mean_token_accuracy": 0.18970052450895308,
|
|
"num_tokens": 11458154.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.254659509658813,
|
|
"epoch": 0.5203808887403942,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004978494540306761,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.19914498180150986,
|
|
"num_tokens": 11467449.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.32906928062439,
|
|
"epoch": 0.5207985299031073,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004978453459152346,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.1862478032708168,
|
|
"num_tokens": 11477775.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.356950902938843,
|
|
"epoch": 0.5212161710658203,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004978412338986172,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.2001352459192276,
|
|
"num_tokens": 11486921.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.264500999450684,
|
|
"epoch": 0.5216338122285332,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004978371179808958,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.1985421136021614,
|
|
"num_tokens": 11496562.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.2977049350738525,
|
|
"epoch": 0.5220514533912463,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978329981621424,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.19366098940372467,
|
|
"num_tokens": 11504906.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.237130403518677,
|
|
"epoch": 0.5224690945539593,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000497828874442429,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.19339817762374878,
|
|
"num_tokens": 11513757.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.2508077144622805,
|
|
"epoch": 0.5228867357166722,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000497824746821828,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.18978381752967835,
|
|
"num_tokens": 11523195.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.3768940448760985,
|
|
"epoch": 0.5233043768793852,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978206153004117,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.1967854768037796,
|
|
"num_tokens": 11532348.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.3399145126342775,
|
|
"epoch": 0.5237220180420983,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004978164798782523,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.19802623987197876,
|
|
"num_tokens": 11542356.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.285486698150635,
|
|
"epoch": 0.5241396592048112,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004978123405554221,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.19770974218845366,
|
|
"num_tokens": 11550914.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.306386184692383,
|
|
"epoch": 0.5245573003675242,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978081973319938,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.20215959548950196,
|
|
"num_tokens": 11559314.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.270102834701538,
|
|
"epoch": 0.5249749415302373,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004978040502080398,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.1954461842775345,
|
|
"num_tokens": 11567990.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.302718448638916,
|
|
"epoch": 0.5253925826929502,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004977998991836327,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.1959675595164299,
|
|
"num_tokens": 11577133.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.341172122955323,
|
|
"epoch": 0.5258102238556632,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977957442588451,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.19485693871974946,
|
|
"num_tokens": 11585330.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.400000429153442,
|
|
"epoch": 0.5262278650183763,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004977915854337498,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.19147393405437468,
|
|
"num_tokens": 11595005.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.234791231155396,
|
|
"epoch": 0.5266455061810892,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004977874227084197,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.19957670271396638,
|
|
"num_tokens": 11603969.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.2541234493255615,
|
|
"epoch": 0.5270631473438022,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004977832560829277,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.19244313091039658,
|
|
"num_tokens": 11613118.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.293309211730957,
|
|
"epoch": 0.5274807885065153,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004977790855573464,
|
|
"loss": 5.0407,
|
|
"mean_token_accuracy": 0.20061798840761186,
|
|
"num_tokens": 11621799.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.243203067779541,
|
|
"epoch": 0.5278984296692282,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004977749111317492,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.201016865670681,
|
|
"num_tokens": 11630557.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.31305456161499,
|
|
"epoch": 0.5283160708319412,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000497770732806209,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.20196808725595475,
|
|
"num_tokens": 11639179.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.3803223133087155,
|
|
"epoch": 0.5287337119946542,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497766550580799,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.186115300655365,
|
|
"num_tokens": 11648273.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.317419004440308,
|
|
"epoch": 0.5291513531573672,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977623644555923,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.18851786702871323,
|
|
"num_tokens": 11656372.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.3123400688171385,
|
|
"epoch": 0.5295689943200802,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004977581744306624,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.19599805027246475,
|
|
"num_tokens": 11665007.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.3401329040527346,
|
|
"epoch": 0.5299866354827932,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004977539805060824,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.1913927599787712,
|
|
"num_tokens": 11674519.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.351407861709594,
|
|
"epoch": 0.5304042766455062,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004977497826819259,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.19579148292541504,
|
|
"num_tokens": 11683705.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.273947668075562,
|
|
"epoch": 0.5308219178082192,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977455809582664,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.1974862262606621,
|
|
"num_tokens": 11693152.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.295919036865234,
|
|
"epoch": 0.5312395589709322,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004977413753351772,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.18985859006643296,
|
|
"num_tokens": 11702584.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.272398662567139,
|
|
"epoch": 0.5316572001336451,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977371658127323,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.19131954461336137,
|
|
"num_tokens": 11711633.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.3008965969085695,
|
|
"epoch": 0.5320748412963582,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004977329523910051,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.19723836332559586,
|
|
"num_tokens": 11720116.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.368786573410034,
|
|
"epoch": 0.5324924824590712,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977287350700695,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.19029541909694672,
|
|
"num_tokens": 11729564.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.295741081237793,
|
|
"epoch": 0.5329101236217841,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977245138499993,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.20430125892162324,
|
|
"num_tokens": 11737935.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.2621618747711185,
|
|
"epoch": 0.5333277647844972,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977202887308684,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.20029551684856414,
|
|
"num_tokens": 11745989.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.295744705200195,
|
|
"epoch": 0.5337454059472102,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004977160597127507,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.19474478363990783,
|
|
"num_tokens": 11755530.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.326966190338135,
|
|
"epoch": 0.5341630471099231,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004977118267957204,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.19233764261007308,
|
|
"num_tokens": 11764546.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.406210994720459,
|
|
"epoch": 0.5345806882726362,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977075899798513,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.18585114032030106,
|
|
"num_tokens": 11774117.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.361804819107055,
|
|
"epoch": 0.5349983294353492,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000497703349265218,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.1979572132229805,
|
|
"num_tokens": 11782952.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.357758331298828,
|
|
"epoch": 0.5354159705980621,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976991046518943,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.1897083640098572,
|
|
"num_tokens": 11792369.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.299869680404663,
|
|
"epoch": 0.5358336117607752,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004976948561399549,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.2049008384346962,
|
|
"num_tokens": 11801365.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.368355369567871,
|
|
"epoch": 0.5362512529234882,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976906037294738,
|
|
"loss": 5.1546,
|
|
"mean_token_accuracy": 0.19871300011873244,
|
|
"num_tokens": 11809785.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.274523591995239,
|
|
"epoch": 0.5366688940862011,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004976863474205257,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.20144133567810057,
|
|
"num_tokens": 11817978.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.30309648513794,
|
|
"epoch": 0.5370865352489141,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976820872131851,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.19588867872953414,
|
|
"num_tokens": 11827796.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.219935417175293,
|
|
"epoch": 0.5375041764116272,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004976778231075266,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.19789498448371887,
|
|
"num_tokens": 11836439.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.303558874130249,
|
|
"epoch": 0.5379218175743401,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976735551036245,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.18276141434907914,
|
|
"num_tokens": 11845268.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.389260864257812,
|
|
"epoch": 0.5383394587370531,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000497669283201554,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.19253468215465547,
|
|
"num_tokens": 11855185.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.27318000793457,
|
|
"epoch": 0.5387570998997662,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976650074013895,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.18944740444421768,
|
|
"num_tokens": 11865073.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.311315536499023,
|
|
"epoch": 0.5391747410624791,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004976607277032061,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.19220987409353257,
|
|
"num_tokens": 11875004.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.373875284194947,
|
|
"epoch": 0.5395923822251921,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004976564441070788,
|
|
"loss": 5.1694,
|
|
"mean_token_accuracy": 0.19231561869382857,
|
|
"num_tokens": 11884905.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.352836656570434,
|
|
"epoch": 0.5400100233879052,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004976521566130823,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.18691412806510926,
|
|
"num_tokens": 11894669.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.437765312194824,
|
|
"epoch": 0.5404276645506181,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976478652212918,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.18312625139951705,
|
|
"num_tokens": 11904127.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.344949960708618,
|
|
"epoch": 0.5408453057133311,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976435699317824,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.19357477575540544,
|
|
"num_tokens": 11912031.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.244085741043091,
|
|
"epoch": 0.5412629468760441,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976392707446293,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.20516027957201005,
|
|
"num_tokens": 11920961.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.4183173179626465,
|
|
"epoch": 0.5416805880387571,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976349676599078,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.19104507565498352,
|
|
"num_tokens": 11930454.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.233908414840698,
|
|
"epoch": 0.5420982292014701,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976306606776932,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.19654074162244797,
|
|
"num_tokens": 11938610.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.265337657928467,
|
|
"epoch": 0.5425158703641831,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976263497980609,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.19067789912223815,
|
|
"num_tokens": 11947882.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.331164741516114,
|
|
"epoch": 0.5429335115268961,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004976220350210864,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.18939108550548553,
|
|
"num_tokens": 11957552.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.313904571533203,
|
|
"epoch": 0.5433511526896091,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004976177163468451,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.20095171332359313,
|
|
"num_tokens": 11967350.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.291358709335327,
|
|
"epoch": 0.5437687938523221,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004976133937754128,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.19372995048761368,
|
|
"num_tokens": 11976107.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.315399646759033,
|
|
"epoch": 0.544186435015035,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004976090673068651,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.2024029955267906,
|
|
"num_tokens": 11985059.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.284027767181397,
|
|
"epoch": 0.5446040761777481,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004976047369412778,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.19809736907482148,
|
|
"num_tokens": 11993453.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.2076856136322025,
|
|
"epoch": 0.5450217173404611,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976004026787266,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.20305539816617965,
|
|
"num_tokens": 12002524.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.215392827987671,
|
|
"epoch": 0.545439358503174,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975960645192873,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.1970770165324211,
|
|
"num_tokens": 12011516.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.346496200561523,
|
|
"epoch": 0.5458569996658871,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975917224630359,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.18892473578453065,
|
|
"num_tokens": 12020058.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.343629169464111,
|
|
"epoch": 0.5462746408286001,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004975873765100487,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.19308668076992036,
|
|
"num_tokens": 12029167.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.358614253997803,
|
|
"epoch": 0.546692281991313,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975830266604013,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.1965801313519478,
|
|
"num_tokens": 12038298.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.335472583770752,
|
|
"epoch": 0.5471099231540261,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004975786729141702,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.19307419359683992,
|
|
"num_tokens": 12047437.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.345617341995239,
|
|
"epoch": 0.5475275643167391,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004975743152714314,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.19558456689119338,
|
|
"num_tokens": 12055821.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.3069781303405765,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004975699537322616,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.20470962524414063,
|
|
"num_tokens": 12064378.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.238099813461304,
|
|
"epoch": 0.5483628466421651,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004975655882967366,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.19546643048524856,
|
|
"num_tokens": 12073110.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.305172967910766,
|
|
"epoch": 0.5487804878048781,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004975612189649331,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.19604372084140778,
|
|
"num_tokens": 12081224.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.29809684753418,
|
|
"epoch": 0.549198128967591,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975568457369276,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.19554249048233033,
|
|
"num_tokens": 12090279.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.338534355163574,
|
|
"epoch": 0.549615770130304,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004975524686127966,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.20001107156276704,
|
|
"num_tokens": 12098818.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.333001232147216,
|
|
"epoch": 0.5500334112930171,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004975480875926168,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.1991492137312889,
|
|
"num_tokens": 12107358.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.299057292938232,
|
|
"epoch": 0.55045105245573,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004975437026764648,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.18686739057302476,
|
|
"num_tokens": 12116802.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.325213432312012,
|
|
"epoch": 0.550868693618443,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975393138644175,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.1964704141020775,
|
|
"num_tokens": 12126347.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.212339162826538,
|
|
"epoch": 0.5512863347811561,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004975349211565515,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.19702374339103698,
|
|
"num_tokens": 12136138.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.216978406906128,
|
|
"epoch": 0.551703975943869,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000497530524552944,
|
|
"loss": 5.1422,
|
|
"mean_token_accuracy": 0.19698679745197295,
|
|
"num_tokens": 12146436.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.338571453094483,
|
|
"epoch": 0.552121617106582,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004975261240536716,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.19080499261617662,
|
|
"num_tokens": 12157003.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.301218748092651,
|
|
"epoch": 0.5525392582692951,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004975217196588117,
|
|
"loss": 5.0774,
|
|
"mean_token_accuracy": 0.20672063678503036,
|
|
"num_tokens": 12166671.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.255537843704223,
|
|
"epoch": 0.552956899432008,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004975173113684413,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.19832688570022583,
|
|
"num_tokens": 12176474.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.314903306961059,
|
|
"epoch": 0.553374540594721,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004975128991826374,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.19805006831884384,
|
|
"num_tokens": 12185307.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.330648374557495,
|
|
"epoch": 0.553792181757434,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004975084831014774,
|
|
"loss": 5.1002,
|
|
"mean_token_accuracy": 0.1972905933856964,
|
|
"num_tokens": 12195179.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.268302726745605,
|
|
"epoch": 0.554209822920147,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975040631250386,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.20092782527208328,
|
|
"num_tokens": 12204083.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.2424415111541744,
|
|
"epoch": 0.55462746408286,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004974996392533983,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.20482616126537323,
|
|
"num_tokens": 12213322.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.284097909927368,
|
|
"epoch": 0.555045105245573,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497495211486634,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.1973011776804924,
|
|
"num_tokens": 12222305.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.335782194137574,
|
|
"epoch": 0.555462746408286,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974907798248232,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.19180105328559877,
|
|
"num_tokens": 12232196.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.345500421524048,
|
|
"epoch": 0.555880387570999,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974863442680434,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.19878633469343185,
|
|
"num_tokens": 12241914.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.169161415100097,
|
|
"epoch": 0.556298028733712,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004974819048163725,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.2084399312734604,
|
|
"num_tokens": 12250185.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.307212924957275,
|
|
"epoch": 0.556715669896425,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000497477461469888,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.1905367374420166,
|
|
"num_tokens": 12258954.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.396745300292968,
|
|
"epoch": 0.557133311059138,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974730142286677,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.19282874017953872,
|
|
"num_tokens": 12268320.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.266105890274048,
|
|
"epoch": 0.557550952221851,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004974685630927895,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.19353167563676835,
|
|
"num_tokens": 12276804.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.3798384189605715,
|
|
"epoch": 0.557968593384564,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004974641080623314,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.1893237993121147,
|
|
"num_tokens": 12286024.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.362668132781982,
|
|
"epoch": 0.558386234547277,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004974596491373711,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.19659725427627564,
|
|
"num_tokens": 12295154.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.341537141799927,
|
|
"epoch": 0.55880387570999,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004974551863179871,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.18393664211034774,
|
|
"num_tokens": 12306349.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.32152910232544,
|
|
"epoch": 0.5592215168727029,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004974507196042572,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.19363887310028077,
|
|
"num_tokens": 12315496.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.205521726608277,
|
|
"epoch": 0.559639158035416,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004974462489962597,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.1931314080953598,
|
|
"num_tokens": 12325070.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.318253517150879,
|
|
"epoch": 0.560056799198129,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974417744940729,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.19227463454008104,
|
|
"num_tokens": 12333509.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.3194911003112795,
|
|
"epoch": 0.5604744403608419,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497437296097775,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.19293676763772966,
|
|
"num_tokens": 12342495.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.270238447189331,
|
|
"epoch": 0.560892081523555,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004974328138074445,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.19657109379768373,
|
|
"num_tokens": 12351560.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.280338478088379,
|
|
"epoch": 0.561309722686268,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974283276231599,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.19223884791135787,
|
|
"num_tokens": 12360773.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.3519281387329105,
|
|
"epoch": 0.5617273638489809,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004974238375449996,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.1871039927005768,
|
|
"num_tokens": 12370519.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.359848594665527,
|
|
"epoch": 0.562145005011694,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004974193435730424,
|
|
"loss": 5.1803,
|
|
"mean_token_accuracy": 0.1928796261548996,
|
|
"num_tokens": 12380563.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.3633232593536375,
|
|
"epoch": 0.562562646174407,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004974148457073668,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.19602532535791398,
|
|
"num_tokens": 12389291.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.303618907928467,
|
|
"epoch": 0.5629802873371199,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974103439480517,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.19577138721942902,
|
|
"num_tokens": 12399037.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.260379076004028,
|
|
"epoch": 0.563397928499833,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004974058382951757,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.20362965613603592,
|
|
"num_tokens": 12407553.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.200782632827758,
|
|
"epoch": 0.563815569662546,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004974013287488177,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.1990644082427025,
|
|
"num_tokens": 12416298.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.315585708618164,
|
|
"epoch": 0.5642332108252589,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973968153090569,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.1855603501200676,
|
|
"num_tokens": 12425918.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.326476383209228,
|
|
"epoch": 0.5646508519879719,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973922979759722,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.1968759000301361,
|
|
"num_tokens": 12434693.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.22205662727356,
|
|
"epoch": 0.565068493150685,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004973877767496424,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.20309523791074752,
|
|
"num_tokens": 12444055.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.231982183456421,
|
|
"epoch": 0.5654861343133979,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004973832516301472,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.20229601711034775,
|
|
"num_tokens": 12453012.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.24539589881897,
|
|
"epoch": 0.5659037754761109,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004973787226175652,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.1979959174990654,
|
|
"num_tokens": 12462292.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.223973751068115,
|
|
"epoch": 0.566321416638824,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973741897119761,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.21107324808835984,
|
|
"num_tokens": 12471178.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.2185029029846195,
|
|
"epoch": 0.5667390578015369,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004973696529134592,
|
|
"loss": 5.0902,
|
|
"mean_token_accuracy": 0.20570143163204194,
|
|
"num_tokens": 12479977.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.282926464080811,
|
|
"epoch": 0.5671566989642499,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973651122220938,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.1929614707827568,
|
|
"num_tokens": 12489004.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.388546133041382,
|
|
"epoch": 0.567574340126963,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004973605676379595,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.19547222852706908,
|
|
"num_tokens": 12498979.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.3541638374328615,
|
|
"epoch": 0.5679919812896759,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004973560191611357,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.1881989285349846,
|
|
"num_tokens": 12508293.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.4007574081420895,
|
|
"epoch": 0.5684096224523889,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004973514667917021,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.1894750252366066,
|
|
"num_tokens": 12517828.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.326935911178589,
|
|
"epoch": 0.5688272636151019,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004973469105297386,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.19313381761312484,
|
|
"num_tokens": 12526569.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.302963447570801,
|
|
"epoch": 0.5692449047778149,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973423503753247,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.19802432060241698,
|
|
"num_tokens": 12535706.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.369307661056519,
|
|
"epoch": 0.5696625459405279,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004973377863285403,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.1947503864765167,
|
|
"num_tokens": 12544689.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.264971208572388,
|
|
"epoch": 0.5700801871032409,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004973332183894653,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.20027651339769365,
|
|
"num_tokens": 12553318.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.2390038013458256,
|
|
"epoch": 0.5704978282659539,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973286465581798,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.20361087918281556,
|
|
"num_tokens": 12562009.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.36572151184082,
|
|
"epoch": 0.5709154694286669,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004973240708347637,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.19767710715532302,
|
|
"num_tokens": 12571043.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.388772296905517,
|
|
"epoch": 0.5713331105913799,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004973194912192971,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.19718704074621202,
|
|
"num_tokens": 12581151.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.326244831085205,
|
|
"epoch": 0.5717507517540928,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004973149077118602,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.19785343408584594,
|
|
"num_tokens": 12590671.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.251832962036133,
|
|
"epoch": 0.5721683929168059,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004973103203125333,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.1969648167490959,
|
|
"num_tokens": 12599693.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.2909646987915036,
|
|
"epoch": 0.5725860340795189,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004973057290213965,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.19987472593784333,
|
|
"num_tokens": 12609238.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.318179893493652,
|
|
"epoch": 0.5730036752422318,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973011338385304,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.19612429141998292,
|
|
"num_tokens": 12618273.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.328787899017334,
|
|
"epoch": 0.5734213164049449,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004972965347640154,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.19214983582496642,
|
|
"num_tokens": 12628229.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.312824058532715,
|
|
"epoch": 0.5738389575676579,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497291931797932,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.20360389351844788,
|
|
"num_tokens": 12636533.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.2589497566223145,
|
|
"epoch": 0.5742565987303708,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004972873249403608,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.20134925842285156,
|
|
"num_tokens": 12645503.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.325412130355835,
|
|
"epoch": 0.5746742398930839,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972827141913822,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.19533587992191315,
|
|
"num_tokens": 12654355.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.324506092071533,
|
|
"epoch": 0.5750918810557969,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972780995510773,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.19854477196931838,
|
|
"num_tokens": 12663774.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.214340925216675,
|
|
"epoch": 0.5755095222185098,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004972734810195266,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.19537777602672576,
|
|
"num_tokens": 12674436.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.315042924880982,
|
|
"epoch": 0.5759271633812229,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004972688585968112,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.19828243255615235,
|
|
"num_tokens": 12682891.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.231833457946777,
|
|
"epoch": 0.5763448045439359,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004972642322830118,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.2060108244419098,
|
|
"num_tokens": 12691170.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.233250761032105,
|
|
"epoch": 0.5767624457066488,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004972596020782096,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.20176639258861542,
|
|
"num_tokens": 12700314.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.284579515457153,
|
|
"epoch": 0.5771800868693618,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004972549679824853,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.20291773676872255,
|
|
"num_tokens": 12709418.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.259470224380493,
|
|
"epoch": 0.5775977280320749,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004972503299959204,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.1915157586336136,
|
|
"num_tokens": 12719287.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.291198825836181,
|
|
"epoch": 0.5780153691947878,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497245688118596,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.20262208580970764,
|
|
"num_tokens": 12728836.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.346963834762573,
|
|
"epoch": 0.5784330103575008,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972410423505932,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.1931448131799698,
|
|
"num_tokens": 12738173.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.274334383010864,
|
|
"epoch": 0.5788506515202139,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004972363926919935,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.20028227120637893,
|
|
"num_tokens": 12747428.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.297267436981201,
|
|
"epoch": 0.5792682926829268,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972317391428782,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.18428369760513305,
|
|
"num_tokens": 12757148.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.395060920715332,
|
|
"epoch": 0.5796859338456398,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004972270817033288,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.18490305095911025,
|
|
"num_tokens": 12766820.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.369648075103759,
|
|
"epoch": 0.5801035750083529,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004972224203734269,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.19279582649469376,
|
|
"num_tokens": 12776082.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.307328128814698,
|
|
"epoch": 0.5805212161710658,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497217755153254,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.1991540089249611,
|
|
"num_tokens": 12785057.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.332828140258789,
|
|
"epoch": 0.5809388573337788,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972130860428918,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.20429168194532393,
|
|
"num_tokens": 12793599.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.323731184005737,
|
|
"epoch": 0.5813564984964918,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972084130424222,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.19042249619960785,
|
|
"num_tokens": 12803775.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.3047911643981935,
|
|
"epoch": 0.5817741396592048,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004972037361519267,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.19613023847341537,
|
|
"num_tokens": 12812327.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.294750785827636,
|
|
"epoch": 0.5821917808219178,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004971990553714874,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.2047479510307312,
|
|
"num_tokens": 12821218.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.2968666553497314,
|
|
"epoch": 0.5826094219846308,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004971943707011861,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.19258713722229004,
|
|
"num_tokens": 12831579.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.356349325180053,
|
|
"epoch": 0.5830270631473438,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497189682141105,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.19508877247571946,
|
|
"num_tokens": 12841026.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.247263956069946,
|
|
"epoch": 0.5834447043100568,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971849896913259,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.19512754082679748,
|
|
"num_tokens": 12850136.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.3282195091247555,
|
|
"epoch": 0.5838623454727698,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004971802933519312,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.1934357389807701,
|
|
"num_tokens": 12860345.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.260236740112305,
|
|
"epoch": 0.5842799866354828,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971755931230031,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.1916600614786148,
|
|
"num_tokens": 12868995.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.417574739456176,
|
|
"epoch": 0.5846976277981958,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971708890046236,
|
|
"loss": 5.2874,
|
|
"mean_token_accuracy": 0.18892727494239808,
|
|
"num_tokens": 12878043.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.3191173553466795,
|
|
"epoch": 0.5851152689609088,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004971661809968755,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.20073588639497758,
|
|
"num_tokens": 12887090.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.246047067642212,
|
|
"epoch": 0.5855329101236217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971614690998409,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.20798927396535874,
|
|
"num_tokens": 12896349.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.289060401916504,
|
|
"epoch": 0.5859505512863348,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971567533136024,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.19288735389709472,
|
|
"num_tokens": 12905698.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.223328256607056,
|
|
"epoch": 0.5863681924490478,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971520336382424,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.20283860415220262,
|
|
"num_tokens": 12915146.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.150896120071411,
|
|
"epoch": 0.5867858336117607,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971473100738437,
|
|
"loss": 4.9543,
|
|
"mean_token_accuracy": 0.21041145026683808,
|
|
"num_tokens": 12924933.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.328949213027954,
|
|
"epoch": 0.5872034747744738,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497142582620489,
|
|
"loss": 5.1947,
|
|
"mean_token_accuracy": 0.19117712676525117,
|
|
"num_tokens": 12934959.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.307005977630615,
|
|
"epoch": 0.5876211159371868,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971378512782609,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.20460983514785766,
|
|
"num_tokens": 12943470.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.1801504611969,
|
|
"epoch": 0.5880387570998997,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004971331160472424,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.2065888449549675,
|
|
"num_tokens": 12953592.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.346447372436524,
|
|
"epoch": 0.5884563982626128,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004971283769275163,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.1901643842458725,
|
|
"num_tokens": 12962893.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.237546586990357,
|
|
"epoch": 0.5888740394253258,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004971236339191656,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.20495195537805558,
|
|
"num_tokens": 12971635.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.210694265365601,
|
|
"epoch": 0.5892916805880387,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971188870222734,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.2032220706343651,
|
|
"num_tokens": 12981040.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.273572158813477,
|
|
"epoch": 0.5897093217507517,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971141362369226,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.19886477887630463,
|
|
"num_tokens": 12989898.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.253807735443115,
|
|
"epoch": 0.5901269629134648,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971093815631965,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.1980026111006737,
|
|
"num_tokens": 12998584.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.234729051589966,
|
|
"epoch": 0.5905446040761777,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971046230011783,
|
|
"loss": 5.0897,
|
|
"mean_token_accuracy": 0.19813366383314132,
|
|
"num_tokens": 13008007.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.310987949371338,
|
|
"epoch": 0.5909622452388907,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004970998605509514,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.19112719148397445,
|
|
"num_tokens": 13017034.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.4063859462738035,
|
|
"epoch": 0.5913798864016038,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497095094212599,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.18501462042331696,
|
|
"num_tokens": 13025916.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.393344974517822,
|
|
"epoch": 0.5917975275643167,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004970903239862047,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.19150344729423524,
|
|
"num_tokens": 13035242.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.28661699295044,
|
|
"epoch": 0.5922151687270297,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004970855498718519,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.1944814145565033,
|
|
"num_tokens": 13044123.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.27246880531311,
|
|
"epoch": 0.5926328098897428,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004970807718696243,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.19152534008026123,
|
|
"num_tokens": 13053503.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.3138662815094,
|
|
"epoch": 0.5930504510524557,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004970759899796055,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.1943088263273239,
|
|
"num_tokens": 13062106.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.319834566116333,
|
|
"epoch": 0.5934680922151687,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004970712042018791,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.19662788063287734,
|
|
"num_tokens": 13071509.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.2435088634490965,
|
|
"epoch": 0.5938857333778818,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004970664145365289,
|
|
"loss": 5.0407,
|
|
"mean_token_accuracy": 0.20235697627067567,
|
|
"num_tokens": 13080469.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.24275050163269,
|
|
"epoch": 0.5943033745405947,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497061620983639,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.20667399615049362,
|
|
"num_tokens": 13089826.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.330239915847779,
|
|
"epoch": 0.5947210157033077,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004970568235432931,
|
|
"loss": 5.2066,
|
|
"mean_token_accuracy": 0.1961497887969017,
|
|
"num_tokens": 13098630.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.310578012466431,
|
|
"epoch": 0.5951386568660207,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004970520222155751,
|
|
"loss": 5.0865,
|
|
"mean_token_accuracy": 0.20251888930797576,
|
|
"num_tokens": 13106819.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.335030221939087,
|
|
"epoch": 0.5955562980287337,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004970472170005692,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.19765260368585585,
|
|
"num_tokens": 13115471.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.257332706451416,
|
|
"epoch": 0.5959739391914467,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970424078983596,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.20673562586307526,
|
|
"num_tokens": 13124537.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.222427558898926,
|
|
"epoch": 0.5963915803541597,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004970375949090302,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.1995763063430786,
|
|
"num_tokens": 13135326.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.382026672363281,
|
|
"epoch": 0.5968092215168727,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004970327780326655,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.19228799939155578,
|
|
"num_tokens": 13145502.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.360210371017456,
|
|
"epoch": 0.5972268626795857,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004970279572693498,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.20425592809915544,
|
|
"num_tokens": 13154808.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.242071342468262,
|
|
"epoch": 0.5976445038422987,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970231326191674,
|
|
"loss": 5.2339,
|
|
"mean_token_accuracy": 0.1881676897406578,
|
|
"num_tokens": 13163982.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.298562622070312,
|
|
"epoch": 0.5980621450050116,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004970183040822029,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.19804944694042206,
|
|
"num_tokens": 13172446.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.326335763931274,
|
|
"epoch": 0.5984797861677247,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970134716585407,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.19709307551383973,
|
|
"num_tokens": 13181671.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.28006501197815,
|
|
"epoch": 0.5988974273304377,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004970086353482654,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.19996021091938018,
|
|
"num_tokens": 13190207.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.257366037368774,
|
|
"epoch": 0.5993150684931506,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004970037951514617,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.20581307262182236,
|
|
"num_tokens": 13198866.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.286292552947998,
|
|
"epoch": 0.5997327096558637,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969989510682143,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.20628595799207688,
|
|
"num_tokens": 13207921.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.374574756622314,
|
|
"epoch": 0.6001503508185767,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004969941030986082,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.19341373294591904,
|
|
"num_tokens": 13217759.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.21600604057312,
|
|
"epoch": 0.6005679919812896,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000496989251242728,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.20396703183650972,
|
|
"num_tokens": 13226592.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.2362250804901125,
|
|
"epoch": 0.6009856331440027,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969843955006588,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.19819783568382263,
|
|
"num_tokens": 13236123.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.2788323879241945,
|
|
"epoch": 0.6014032743067157,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969795358724855,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.19469741433858873,
|
|
"num_tokens": 13246169.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.259560823440552,
|
|
"epoch": 0.6018209154694286,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004969746723582932,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.20535566806793212,
|
|
"num_tokens": 13256141.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.302822637557983,
|
|
"epoch": 0.6022385566321417,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004969698049581672,
|
|
"loss": 5.2068,
|
|
"mean_token_accuracy": 0.19715954661369323,
|
|
"num_tokens": 13265491.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.366161823272705,
|
|
"epoch": 0.6026561977948547,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004969649336721924,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.19652217775583267,
|
|
"num_tokens": 13274805.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.385281944274903,
|
|
"epoch": 0.6030738389575676,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969600585004544,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.19282495528459548,
|
|
"num_tokens": 13284589.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.218282079696655,
|
|
"epoch": 0.6034914801202806,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969551794430383,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.2075082093477249,
|
|
"num_tokens": 13293370.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.394102096557617,
|
|
"epoch": 0.6039091212829937,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969502965000297,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.20173947960138322,
|
|
"num_tokens": 13302555.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.23027925491333,
|
|
"epoch": 0.6043267624457066,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000496945409671514,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.1969628483057022,
|
|
"num_tokens": 13311632.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.2610822200775145,
|
|
"epoch": 0.6047444036084196,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004969405189575768,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.20429269671440126,
|
|
"num_tokens": 13320593.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.275874948501587,
|
|
"epoch": 0.6051620447711327,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969356243583036,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.20849602669477463,
|
|
"num_tokens": 13329095.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.2053272247314455,
|
|
"epoch": 0.6055796859338456,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004969307258737802,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.20320384502410888,
|
|
"num_tokens": 13338404.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.244780397415161,
|
|
"epoch": 0.6059973270965586,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004969258235040921,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.20462302565574647,
|
|
"num_tokens": 13347095.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.2744855880737305,
|
|
"epoch": 0.6064149682592717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004969209172493255,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.19743907004594802,
|
|
"num_tokens": 13356606.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.265245962142944,
|
|
"epoch": 0.6068326094219846,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004969160071095661,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.1987444594502449,
|
|
"num_tokens": 13366889.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.3010406494140625,
|
|
"epoch": 0.6072502505846976,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969110930848999,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.19477009475231172,
|
|
"num_tokens": 13376761.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.28683032989502,
|
|
"epoch": 0.6076678917474106,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004969061751754129,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.2073565900325775,
|
|
"num_tokens": 13386226.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.229002475738525,
|
|
"epoch": 0.6080855329101236,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004969012533811911,
|
|
"loss": 4.9782,
|
|
"mean_token_accuracy": 0.2045301005244255,
|
|
"num_tokens": 13394243.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.280516815185547,
|
|
"epoch": 0.6085031740728366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004968963277023208,
|
|
"loss": 5.2601,
|
|
"mean_token_accuracy": 0.18198539614677428,
|
|
"num_tokens": 13403708.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.2522890090942385,
|
|
"epoch": 0.6089208152355496,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968913981388882,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.20691966265439987,
|
|
"num_tokens": 13412911.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.333075761795044,
|
|
"epoch": 0.6093384563982626,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004968864646909797,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.18911741226911544,
|
|
"num_tokens": 13422423.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.286247873306275,
|
|
"epoch": 0.6097560975609756,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004968815273586814,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.19744611233472825,
|
|
"num_tokens": 13430984.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.296880674362183,
|
|
"epoch": 0.6101737387236886,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004968765861420799,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.19726217687129974,
|
|
"num_tokens": 13440492.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.327346563339233,
|
|
"epoch": 0.6105913798864016,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004968716410412617,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.1950830653309822,
|
|
"num_tokens": 13449222.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.295615386962891,
|
|
"epoch": 0.6110090210491146,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004968666920563134,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.20350987762212752,
|
|
"num_tokens": 13459126.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.4395183563232425,
|
|
"epoch": 0.6114266622118276,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004968617391873216,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.18673343807458878,
|
|
"num_tokens": 13468811.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.315000343322754,
|
|
"epoch": 0.6118443033745405,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004968567824343729,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.19488857537508011,
|
|
"num_tokens": 13477765.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.292313957214356,
|
|
"epoch": 0.6122619445372536,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004968518217975542,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.18590581566095352,
|
|
"num_tokens": 13487184.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.306622505187988,
|
|
"epoch": 0.6126795856999666,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004968468572769524,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.198933407664299,
|
|
"num_tokens": 13496784.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.298367023468018,
|
|
"epoch": 0.6130972268626795,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004968418888726543,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.20009292364120485,
|
|
"num_tokens": 13505824.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.220296335220337,
|
|
"epoch": 0.6135148680253926,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004968369165847469,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.20139865428209305,
|
|
"num_tokens": 13515111.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.241522312164307,
|
|
"epoch": 0.6139325091881056,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968319404133173,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.20197376161813735,
|
|
"num_tokens": 13524163.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.243652439117431,
|
|
"epoch": 0.6143501503508185,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004968269603584525,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.21017141044139862,
|
|
"num_tokens": 13533368.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.286370277404785,
|
|
"epoch": 0.6147677915135316,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968219764202397,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.19288029968738557,
|
|
"num_tokens": 13543708.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.270022058486939,
|
|
"epoch": 0.6151854326762446,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004968169885987663,
|
|
"loss": 5.1357,
|
|
"mean_token_accuracy": 0.19452259242534636,
|
|
"num_tokens": 13552561.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.385063219070434,
|
|
"epoch": 0.6156030738389575,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004968119968941193,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.18661929219961165,
|
|
"num_tokens": 13562050.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.265257024765015,
|
|
"epoch": 0.6160207150016705,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004968070013063866,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.1947042465209961,
|
|
"num_tokens": 13571356.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.249632549285889,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004968020018356552,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.19511717110872268,
|
|
"num_tokens": 13581357.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.246051979064942,
|
|
"epoch": 0.6168559973270965,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967969984820128,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.2002262517809868,
|
|
"num_tokens": 13589392.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.280205965042114,
|
|
"epoch": 0.6172736384898095,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004967919912455469,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.2097433477640152,
|
|
"num_tokens": 13598376.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.131550550460815,
|
|
"epoch": 0.6176912796525226,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967869801263454,
|
|
"loss": 4.9224,
|
|
"mean_token_accuracy": 0.21441829651594163,
|
|
"num_tokens": 13607014.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.242445039749145,
|
|
"epoch": 0.6181089208152355,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004967819651244957,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.19649894684553146,
|
|
"num_tokens": 13615700.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.331611442565918,
|
|
"epoch": 0.6185265619779485,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967769462400857,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.20140802562236787,
|
|
"num_tokens": 13625230.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.392923259735108,
|
|
"epoch": 0.6189442031406616,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004967719234732033,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.19482791125774385,
|
|
"num_tokens": 13635258.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.2099607467651365,
|
|
"epoch": 0.6193618443033745,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004967668968239365,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.20576905757188796,
|
|
"num_tokens": 13643688.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.257021903991699,
|
|
"epoch": 0.6197794854660875,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004967618662923732,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.19347460120916365,
|
|
"num_tokens": 13652894.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.255383586883545,
|
|
"epoch": 0.6201971266288006,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004967568318786016,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.19903222024440764,
|
|
"num_tokens": 13662852.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.325408697128296,
|
|
"epoch": 0.6206147677915135,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967517935827097,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.1971137970685959,
|
|
"num_tokens": 13671457.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.28644642829895,
|
|
"epoch": 0.6210324089542265,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004967467514047856,
|
|
"loss": 5.134,
|
|
"mean_token_accuracy": 0.19861085265874862,
|
|
"num_tokens": 13681002.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.232876014709473,
|
|
"epoch": 0.6214500501169395,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004967417053449178,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.20014744102954865,
|
|
"num_tokens": 13690677.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.2322088241577145,
|
|
"epoch": 0.6218676912796525,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004967366554031945,
|
|
"loss": 4.917,
|
|
"mean_token_accuracy": 0.21409218460321428,
|
|
"num_tokens": 13699151.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.277127599716186,
|
|
"epoch": 0.6222853324423655,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967316015797042,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.2019924610853195,
|
|
"num_tokens": 13708105.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.281523942947388,
|
|
"epoch": 0.6227029736050785,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004967265438745352,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.1887054458260536,
|
|
"num_tokens": 13717094.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.285523176193237,
|
|
"epoch": 0.6231206147677915,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967214822877763,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.2033928155899048,
|
|
"num_tokens": 13726639.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.303518772125244,
|
|
"epoch": 0.6235382559305045,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004967164168195159,
|
|
"loss": 5.0431,
|
|
"mean_token_accuracy": 0.1991380587220192,
|
|
"num_tokens": 13735220.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.162773323059082,
|
|
"epoch": 0.6239558970932175,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967113474698428,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.20923568904399872,
|
|
"num_tokens": 13743277.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.2870705127716064,
|
|
"epoch": 0.6243735382559304,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967062742388456,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.1997038260102272,
|
|
"num_tokens": 13752946.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.3088672161102295,
|
|
"epoch": 0.6247911794186435,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004967011971266132,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.19633412659168242,
|
|
"num_tokens": 13761297.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.280236721038818,
|
|
"epoch": 0.6252088205813565,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004966961161332346,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.19141292870044707,
|
|
"num_tokens": 13771238.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.291513442993164,
|
|
"epoch": 0.6256264617440696,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004966910312587985,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.19851056039333342,
|
|
"num_tokens": 13781420.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.219727849960327,
|
|
"epoch": 0.6260441029067825,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004966859425033941,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.20145111829042434,
|
|
"num_tokens": 13789833.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.323534679412842,
|
|
"epoch": 0.6264617440694955,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004966808498671104,
|
|
"loss": 5.1806,
|
|
"mean_token_accuracy": 0.1901519700884819,
|
|
"num_tokens": 13799202.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.355959701538086,
|
|
"epoch": 0.6268793852322085,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004966757533500367,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.19450042098760606,
|
|
"num_tokens": 13809097.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.281562471389771,
|
|
"epoch": 0.6272970263949215,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000496670652952262,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.20122548341751098,
|
|
"num_tokens": 13818437.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.190532493591308,
|
|
"epoch": 0.6277146675576345,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004966655486738757,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.1990937203168869,
|
|
"num_tokens": 13827083.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.214270877838135,
|
|
"epoch": 0.6281323087203475,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004966604405149672,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.2016884207725525,
|
|
"num_tokens": 13835905.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.248412179946899,
|
|
"epoch": 0.6285499498830605,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004966553284756257,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.2088845804333687,
|
|
"num_tokens": 13845136.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.267665863037109,
|
|
"epoch": 0.6289675910457735,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004966502125559411,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.1976991981267929,
|
|
"num_tokens": 13855087.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.280507516860962,
|
|
"epoch": 0.6293852322084865,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966450927560026,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.19763447791337968,
|
|
"num_tokens": 13864077.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.291547536849976,
|
|
"epoch": 0.6298028733711994,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004966399690759,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.19496095925569534,
|
|
"num_tokens": 13873404.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.325375938415528,
|
|
"epoch": 0.6302205145339125,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000496634841515723,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.1921955093741417,
|
|
"num_tokens": 13883231.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.187126159667969,
|
|
"epoch": 0.6306381556966255,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004966297100755613,
|
|
"loss": 4.9257,
|
|
"mean_token_accuracy": 0.2123725801706314,
|
|
"num_tokens": 13892314.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.214571285247803,
|
|
"epoch": 0.6310557968593384,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966245747555047,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.20491755604743958,
|
|
"num_tokens": 13900771.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.225977802276612,
|
|
"epoch": 0.6314734380220515,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004966194355556432,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.20504699945449828,
|
|
"num_tokens": 13909615.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.269973564147949,
|
|
"epoch": 0.6318910791847645,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004966142924760666,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.19951668679714202,
|
|
"num_tokens": 13918491.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.256102132797241,
|
|
"epoch": 0.6323087203474774,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004966091455168652,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.19039285331964492,
|
|
"num_tokens": 13927935.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.2345452308654785,
|
|
"epoch": 0.6327263615101905,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004966039946781289,
|
|
"loss": 4.9508,
|
|
"mean_token_accuracy": 0.20827628374099733,
|
|
"num_tokens": 13936524.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.223987483978272,
|
|
"epoch": 0.6331440026729035,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000496598839959948,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.2000010296702385,
|
|
"num_tokens": 13945544.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.259314775466919,
|
|
"epoch": 0.6335616438356164,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004965936813624126,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.21094494611024855,
|
|
"num_tokens": 13955016.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.194518089294434,
|
|
"epoch": 0.6339792849983295,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000496588518885613,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.19977759569883347,
|
|
"num_tokens": 13964045.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.262182712554932,
|
|
"epoch": 0.6343969261610425,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965833525296397,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.19878716468811036,
|
|
"num_tokens": 13973554.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.2696366786956785,
|
|
"epoch": 0.6348145673237554,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004965781822945831,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.19465476423501968,
|
|
"num_tokens": 13982669.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.359630537033081,
|
|
"epoch": 0.6352322084864684,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004965730081805338,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.1928557872772217,
|
|
"num_tokens": 13993392.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.359306144714355,
|
|
"epoch": 0.6356498496491815,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004965678301875821,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.19565411359071733,
|
|
"num_tokens": 14002659.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.242954397201538,
|
|
"epoch": 0.6360674908118944,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000496562648315819,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.1931462585926056,
|
|
"num_tokens": 14011561.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.27168231010437,
|
|
"epoch": 0.6364851319746074,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496557462565335,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.2037852704524994,
|
|
"num_tokens": 14021286.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.253484439849854,
|
|
"epoch": 0.6369027731373205,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965522729362209,
|
|
"loss": 5.0855,
|
|
"mean_token_accuracy": 0.20241313576698303,
|
|
"num_tokens": 14031901.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.268364381790161,
|
|
"epoch": 0.6373204143000334,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004965470794285676,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.20597634017467498,
|
|
"num_tokens": 14041000.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.351800203323364,
|
|
"epoch": 0.6377380554627464,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496541882042466,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.1904378667473793,
|
|
"num_tokens": 14050567.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.250691890716553,
|
|
"epoch": 0.6381556966254595,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004965366807780071,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.20330618917942048,
|
|
"num_tokens": 14059990.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.299921607971191,
|
|
"epoch": 0.6385733377881724,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965314756352818,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.20028862357139587,
|
|
"num_tokens": 14069317.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.268960762023926,
|
|
"epoch": 0.6389909789508854,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004965262666143816,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20145545154809952,
|
|
"num_tokens": 14078809.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.295058298110962,
|
|
"epoch": 0.6394086201135984,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004965210537153973,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.19449316412210466,
|
|
"num_tokens": 14087660.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.3194272994995115,
|
|
"epoch": 0.6398262612763114,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004965158369384204,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.19463611245155335,
|
|
"num_tokens": 14096585.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.2938367366790775,
|
|
"epoch": 0.6402439024390244,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496510616283542,
|
|
"loss": 5.0323,
|
|
"mean_token_accuracy": 0.20457970798015596,
|
|
"num_tokens": 14106079.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.25977578163147,
|
|
"epoch": 0.6406615436017374,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004965053917508537,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.19478278756141662,
|
|
"num_tokens": 14115988.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.26710991859436,
|
|
"epoch": 0.6410791847644504,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004965001633404469,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.18913919776678084,
|
|
"num_tokens": 14126980.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.310529279708862,
|
|
"epoch": 0.6414968259271634,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004964949310524131,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.2001107305288315,
|
|
"num_tokens": 14135780.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.350729179382324,
|
|
"epoch": 0.6419144670898764,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964896948868439,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.18921735137701035,
|
|
"num_tokens": 14145655.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.291706132888794,
|
|
"epoch": 0.6423321082525894,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004964844548438311,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.20752628594636918,
|
|
"num_tokens": 14154157.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.329635095596314,
|
|
"epoch": 0.6427497494153024,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004964792109234662,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.19566696733236313,
|
|
"num_tokens": 14163749.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.277985048294068,
|
|
"epoch": 0.6431673905780154,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964739631258411,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.1988380119204521,
|
|
"num_tokens": 14174170.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.251490783691406,
|
|
"epoch": 0.6435850317407283,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964687114510478,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.19689277708530425,
|
|
"num_tokens": 14182625.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.315349102020264,
|
|
"epoch": 0.6440026729034414,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000496463455899178,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.19784579426050186,
|
|
"num_tokens": 14192351.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.238921689987182,
|
|
"epoch": 0.6444203140661544,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004964581964703239,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.20523313134908677,
|
|
"num_tokens": 14201107.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.29321141242981,
|
|
"epoch": 0.6448379552288673,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004964529331645776,
|
|
"loss": 5.03,
|
|
"mean_token_accuracy": 0.2010428711771965,
|
|
"num_tokens": 14209540.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.220217084884643,
|
|
"epoch": 0.6452555963915804,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496447665982031,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.20668008476495742,
|
|
"num_tokens": 14217944.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.226902294158935,
|
|
"epoch": 0.6456732375542934,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004964423949227765,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.20413003563880922,
|
|
"num_tokens": 14226044.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.281259202957154,
|
|
"epoch": 0.6460908787170063,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004964371199869062,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.19337351769208908,
|
|
"num_tokens": 14235566.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.2492311000823975,
|
|
"epoch": 0.6465085198797194,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004964318411745127,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.21127513200044631,
|
|
"num_tokens": 14244511.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.246586894989013,
|
|
"epoch": 0.6469261610424324,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004964265584856883,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.19707143157720566,
|
|
"num_tokens": 14254299.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.18250675201416,
|
|
"epoch": 0.6473438022051453,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964212719205254,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.19456934332847595,
|
|
"num_tokens": 14262915.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.302042531967163,
|
|
"epoch": 0.6477614433678583,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004964159814791167,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.19750718623399735,
|
|
"num_tokens": 14272606.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.284196662902832,
|
|
"epoch": 0.6481790845305714,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964106871615547,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.19279372990131377,
|
|
"num_tokens": 14282117.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.228738451004029,
|
|
"epoch": 0.6485967256932843,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496405388967932,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.20145741552114488,
|
|
"num_tokens": 14290421.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.340937232971191,
|
|
"epoch": 0.6490143668559973,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004964000868983416,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.19089989513158798,
|
|
"num_tokens": 14299870.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.35228419303894,
|
|
"epoch": 0.6494320080187104,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004963947809528761,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.19675163477659224,
|
|
"num_tokens": 14309916.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.247927188873291,
|
|
"epoch": 0.6498496491814233,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004963894711316285,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.2006386026740074,
|
|
"num_tokens": 14319061.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.280343818664551,
|
|
"epoch": 0.6502672903441363,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004963841574346917,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.20942596197128296,
|
|
"num_tokens": 14327241.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.3175538063049315,
|
|
"epoch": 0.6506849315068494,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004963788398621587,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.19320109039545058,
|
|
"num_tokens": 14336586.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.279233503341675,
|
|
"epoch": 0.6511025726695623,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963735184141227,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.19558528065681458,
|
|
"num_tokens": 14346484.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.324158954620361,
|
|
"epoch": 0.6515202138322753,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963681930906768,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.1899666890501976,
|
|
"num_tokens": 14356255.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.270466566085815,
|
|
"epoch": 0.6519378549949884,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963628638919141,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.2003247022628784,
|
|
"num_tokens": 14365680.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.300762796401978,
|
|
"epoch": 0.6523554961577013,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963575308179281,
|
|
"loss": 5.1116,
|
|
"mean_token_accuracy": 0.19403816908597946,
|
|
"num_tokens": 14374546.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.310976028442383,
|
|
"epoch": 0.6527731373204143,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963521938688122,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.20134818702936172,
|
|
"num_tokens": 14383624.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.310570526123047,
|
|
"epoch": 0.6531907784831273,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004963468530446596,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.1927497386932373,
|
|
"num_tokens": 14392482.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.294511556625366,
|
|
"epoch": 0.6536084196458403,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004963415083455639,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.20018113106489183,
|
|
"num_tokens": 14401940.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.308073902130127,
|
|
"epoch": 0.6540260608085533,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004963361597716186,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.19864506125450135,
|
|
"num_tokens": 14411127.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.2413536548614506,
|
|
"epoch": 0.6544437019712663,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004963308073229175,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.19848764389753343,
|
|
"num_tokens": 14421358.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.271971845626831,
|
|
"epoch": 0.6548613431339793,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963254509995542,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.1917330265045166,
|
|
"num_tokens": 14430507.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.237987804412842,
|
|
"epoch": 0.6552789842966923,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004963200908016224,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.20113077759742737,
|
|
"num_tokens": 14439723.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.237930107116699,
|
|
"epoch": 0.6556966254594053,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000496314726729216,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.20351206809282302,
|
|
"num_tokens": 14449011.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.216968822479248,
|
|
"epoch": 0.6561142666221182,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004963093587824289,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.20348867624998093,
|
|
"num_tokens": 14457676.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.32591757774353,
|
|
"epoch": 0.6565319077848313,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004963039869613551,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.19848504066467285,
|
|
"num_tokens": 14466956.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.276518297195435,
|
|
"epoch": 0.6569495489475443,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004962986112660887,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.2069736897945404,
|
|
"num_tokens": 14476083.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.310458612442017,
|
|
"epoch": 0.6573671901102572,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004962932316967237,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.19386200606822968,
|
|
"num_tokens": 14484980.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.285442781448364,
|
|
"epoch": 0.6577848312729703,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004962878482533544,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.19880761057138444,
|
|
"num_tokens": 14493965.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.3383582592010494,
|
|
"epoch": 0.6582024724356833,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004962824609360748,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.19012716561555862,
|
|
"num_tokens": 14501914.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.257783126831055,
|
|
"epoch": 0.6586201135983962,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004962770697449794,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.2009807735681534,
|
|
"num_tokens": 14511447.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.226074314117431,
|
|
"epoch": 0.6590377547611093,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004962716746801625,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.19946035444736482,
|
|
"num_tokens": 14520558.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.251298904418945,
|
|
"epoch": 0.6594553959238223,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004962662757417187,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.20043639540672303,
|
|
"num_tokens": 14529995.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.269401884078979,
|
|
"epoch": 0.6598730370865352,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004962608729297424,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.19268594980239867,
|
|
"num_tokens": 14538972.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.319367504119873,
|
|
"epoch": 0.6602906782492483,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004962554662443281,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.19816566556692122,
|
|
"num_tokens": 14548255.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.305744695663452,
|
|
"epoch": 0.6607083194119613,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004962500556855706,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.19913562536239623,
|
|
"num_tokens": 14557265.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.35813946723938,
|
|
"epoch": 0.6611259605746742,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004962446412535645,
|
|
"loss": 5.1192,
|
|
"mean_token_accuracy": 0.19741419851779937,
|
|
"num_tokens": 14566650.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.263308477401734,
|
|
"epoch": 0.6615436017373872,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004962392229484046,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.20689138770103455,
|
|
"num_tokens": 14575550.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.247211599349976,
|
|
"epoch": 0.6619612429001003,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000496233800770186,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.20259950309991837,
|
|
"num_tokens": 14584459.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.346441173553467,
|
|
"epoch": 0.6623788840628132,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004962283747190033,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.19215742945671083,
|
|
"num_tokens": 14593709.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.232115364074707,
|
|
"epoch": 0.6627965252255262,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004962229447949515,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.20079489797353745,
|
|
"num_tokens": 14602071.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.309496688842773,
|
|
"epoch": 0.6632141663882393,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004962175109981259,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.18943134993314742,
|
|
"num_tokens": 14612842.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.393085289001465,
|
|
"epoch": 0.6636318075509522,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004962120733286215,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.1939552068710327,
|
|
"num_tokens": 14621645.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.2452645778656,
|
|
"epoch": 0.6640494487136652,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004962066317865334,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.20014073997735976,
|
|
"num_tokens": 14630447.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.191257333755493,
|
|
"epoch": 0.6644670898763783,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000496201186371957,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.2021063581109047,
|
|
"num_tokens": 14639371.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.256074714660644,
|
|
"epoch": 0.6648847310390912,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004961957370849875,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.19830821305513383,
|
|
"num_tokens": 14648540.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.326945781707764,
|
|
"epoch": 0.6653023722018042,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004961902839257205,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.19664984941482544,
|
|
"num_tokens": 14658130.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.329861640930176,
|
|
"epoch": 0.6657200133645172,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004961848268942513,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.1910384029150009,
|
|
"num_tokens": 14667538.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.325843858718872,
|
|
"epoch": 0.6661376545272302,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004961793659906754,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.19738476276397704,
|
|
"num_tokens": 14677115.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.317537784576416,
|
|
"epoch": 0.6665552956899432,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004961739012150885,
|
|
"loss": 5.0628,
|
|
"mean_token_accuracy": 0.20533277541399003,
|
|
"num_tokens": 14686444.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.26391568183899,
|
|
"epoch": 0.6669729368526562,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004961684325675862,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.2067578598856926,
|
|
"num_tokens": 14695951.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.26440167427063,
|
|
"epoch": 0.6673905780153692,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004961629600482643,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.1963884249329567,
|
|
"num_tokens": 14705415.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.3255226612091064,
|
|
"epoch": 0.6678082191780822,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004961574836572186,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.19435861855745315,
|
|
"num_tokens": 14714793.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.206659412384033,
|
|
"epoch": 0.6682258603407952,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004961520033945448,
|
|
"loss": 4.9033,
|
|
"mean_token_accuracy": 0.21076162457466124,
|
|
"num_tokens": 14723820.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.1991291522979735,
|
|
"epoch": 0.6686435015035082,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004961465192603391,
|
|
"loss": 5.0239,
|
|
"mean_token_accuracy": 0.20842347294092178,
|
|
"num_tokens": 14733055.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.244641876220703,
|
|
"epoch": 0.6690611426662212,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004961410312546974,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.19755880832672118,
|
|
"num_tokens": 14742416.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.237119388580322,
|
|
"epoch": 0.6694787838289342,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004961355393777158,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.19402147382497786,
|
|
"num_tokens": 14751384.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.206970071792602,
|
|
"epoch": 0.6698964249916471,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004961300436294902,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.20273444801568985,
|
|
"num_tokens": 14760525.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.271725130081177,
|
|
"epoch": 0.6703140661543602,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004961245440101171,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.19418921917676926,
|
|
"num_tokens": 14769405.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.181735610961914,
|
|
"epoch": 0.6707317073170732,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004961190405196928,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.1997751161456108,
|
|
"num_tokens": 14778945.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.267147207260132,
|
|
"epoch": 0.6711493484797861,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004961135331583135,
|
|
"loss": 5.1484,
|
|
"mean_token_accuracy": 0.1927126944065094,
|
|
"num_tokens": 14788289.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.253804063796997,
|
|
"epoch": 0.6715669896424992,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004961080219260755,
|
|
"loss": 5.0802,
|
|
"mean_token_accuracy": 0.19208644032478334,
|
|
"num_tokens": 14797761.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.342914199829101,
|
|
"epoch": 0.6719846308052122,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004961025068230757,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.20384342968463898,
|
|
"num_tokens": 14806424.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.232385683059692,
|
|
"epoch": 0.6724022719679251,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004960969878494103,
|
|
"loss": 5.0564,
|
|
"mean_token_accuracy": 0.19770175516605376,
|
|
"num_tokens": 14815816.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.190597867965698,
|
|
"epoch": 0.6728199131306382,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004960914650051758,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.19733770042657853,
|
|
"num_tokens": 14824877.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.160306739807129,
|
|
"epoch": 0.6732375542933512,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004960859382904691,
|
|
"loss": 4.9638,
|
|
"mean_token_accuracy": 0.21198989152908326,
|
|
"num_tokens": 14833095.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.28259162902832,
|
|
"epoch": 0.6736551954560641,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000496080407705387,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.19757722914218903,
|
|
"num_tokens": 14842963.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.365403079986573,
|
|
"epoch": 0.6740728366187771,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004960748732500263,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.1914261609315872,
|
|
"num_tokens": 14851552.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.299939870834351,
|
|
"epoch": 0.6744904777814902,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004960693349244838,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.20068265050649642,
|
|
"num_tokens": 14859997.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.256127214431762,
|
|
"epoch": 0.6749081189442031,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004960637927288566,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.2066433921456337,
|
|
"num_tokens": 14868050.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.294862508773804,
|
|
"epoch": 0.6753257601069161,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004960582466632414,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.1935010939836502,
|
|
"num_tokens": 14877774.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.257643461227417,
|
|
"epoch": 0.6757434012696292,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004960526967277356,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.20574513226747512,
|
|
"num_tokens": 14886971.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.20984992980957,
|
|
"epoch": 0.6761610424323421,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004960471429224363,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.19896087646484376,
|
|
"num_tokens": 14895815.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.211242628097534,
|
|
"epoch": 0.6765786835950551,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004960415852474406,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.20744565576314927,
|
|
"num_tokens": 14904082.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.2219987392425535,
|
|
"epoch": 0.6769963247577682,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496036023702846,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.20610882043838502,
|
|
"num_tokens": 14913533.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.2054485321044925,
|
|
"epoch": 0.6774139659204811,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004960304582887497,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.2043306604027748,
|
|
"num_tokens": 14922063.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.273014783859253,
|
|
"epoch": 0.6778316070831941,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004960248890052493,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.20246654152870178,
|
|
"num_tokens": 14930219.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.321018171310425,
|
|
"epoch": 0.6782492482459072,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000496019315852442,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.19694280326366426,
|
|
"num_tokens": 14939463.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.354000043869019,
|
|
"epoch": 0.6786668894086201,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960137388304255,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.20048824846744537,
|
|
"num_tokens": 14948289.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.2940751075744625,
|
|
"epoch": 0.6790845305713331,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004960081579392975,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.2025760218501091,
|
|
"num_tokens": 14958172.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.244129753112793,
|
|
"epoch": 0.6795021717340461,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004960025731791558,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.20291187316179277,
|
|
"num_tokens": 14967362.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.217186117172242,
|
|
"epoch": 0.6799198128967591,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004959969845500979,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.198426353931427,
|
|
"num_tokens": 14975942.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.258469343185425,
|
|
"epoch": 0.6803374540594721,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004959913920522218,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.20564988851547242,
|
|
"num_tokens": 14985428.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.271545886993408,
|
|
"epoch": 0.6807550952221851,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004959857956856254,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.200580133497715,
|
|
"num_tokens": 14994558.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.245328950881958,
|
|
"epoch": 0.6811727363848981,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004959801954504067,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.20047099590301515,
|
|
"num_tokens": 15003674.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.286739110946655,
|
|
"epoch": 0.6815903775476111,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004959745913466635,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.19756890833377838,
|
|
"num_tokens": 15012569.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.274727296829224,
|
|
"epoch": 0.6820080187103241,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004959689833744942,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.20128057450056075,
|
|
"num_tokens": 15021863.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.285109615325927,
|
|
"epoch": 0.682425659873037,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004959633715339969,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.19124172627925873,
|
|
"num_tokens": 15032272.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.272710466384888,
|
|
"epoch": 0.6828433010357501,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004959577558252698,
|
|
"loss": 5.0775,
|
|
"mean_token_accuracy": 0.19612036794424056,
|
|
"num_tokens": 15041066.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.390922689437867,
|
|
"epoch": 0.6832609421984631,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004959521362484112,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.19278655350208282,
|
|
"num_tokens": 15050855.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.259741544723511,
|
|
"epoch": 0.683678583361176,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004959465128035195,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.20553713738918306,
|
|
"num_tokens": 15060810.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.256798362731933,
|
|
"epoch": 0.6840962245238891,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959408854906932,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.2029556378722191,
|
|
"num_tokens": 15069761.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.224723958969117,
|
|
"epoch": 0.6845138656866021,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004959352543100306,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.20431439727544784,
|
|
"num_tokens": 15078691.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.193182706832886,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004959296192616305,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.20527298450469972,
|
|
"num_tokens": 15087068.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.208588600158691,
|
|
"epoch": 0.6853491480120281,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004959239803455916,
|
|
"loss": 4.9114,
|
|
"mean_token_accuracy": 0.20903899073600768,
|
|
"num_tokens": 15095962.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.255855703353882,
|
|
"epoch": 0.6857667891747411,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959183375620123,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.19978296309709548,
|
|
"num_tokens": 15105835.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.261897182464599,
|
|
"epoch": 0.686184430337454,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004959126909109918,
|
|
"loss": 5.0068,
|
|
"mean_token_accuracy": 0.21271485537290574,
|
|
"num_tokens": 15114140.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.254195642471314,
|
|
"epoch": 0.686602071500167,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004959070403926286,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.1995564505457878,
|
|
"num_tokens": 15123253.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.322494745254517,
|
|
"epoch": 0.6870197126628801,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004959013860070217,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.18709080815315246,
|
|
"num_tokens": 15133699.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.263164091110229,
|
|
"epoch": 0.687437353825593,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004958957277542701,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.20392623990774156,
|
|
"num_tokens": 15142133.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.251707220077515,
|
|
"epoch": 0.687854994988306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004958900656344731,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.20342947393655778,
|
|
"num_tokens": 15151367.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.288553190231323,
|
|
"epoch": 0.6882726361510191,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004958843996477296,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.1969807490706444,
|
|
"num_tokens": 15160938.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.340473461151123,
|
|
"epoch": 0.688690277313732,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004958787297941386,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.19682133793830872,
|
|
"num_tokens": 15170507.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.307331562042236,
|
|
"epoch": 0.689107918476445,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004958730560737998,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.19860267490148545,
|
|
"num_tokens": 15179822.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.215660953521729,
|
|
"epoch": 0.6895255596391581,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004958673784868121,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.19516651779413224,
|
|
"num_tokens": 15189353.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.320306587219238,
|
|
"epoch": 0.689943200801871,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004958616970332752,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.20226444005966188,
|
|
"num_tokens": 15197772.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.259267711639405,
|
|
"epoch": 0.690360841964584,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004958560117132884,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.2034023955464363,
|
|
"num_tokens": 15207453.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.231773376464844,
|
|
"epoch": 0.6907784831272971,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004958503225269513,
|
|
"loss": 4.9702,
|
|
"mean_token_accuracy": 0.20691758692264556,
|
|
"num_tokens": 15215787.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.310279798507691,
|
|
"epoch": 0.69119612429001,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004958446294743633,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.2009010374546051,
|
|
"num_tokens": 15225148.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.310588359832764,
|
|
"epoch": 0.691613765452723,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004958389325556245,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.1997177168726921,
|
|
"num_tokens": 15234533.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.285093355178833,
|
|
"epoch": 0.692031406615436,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004958332317708341,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.18973229229450225,
|
|
"num_tokens": 15243805.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.300602912902832,
|
|
"epoch": 0.692449047778149,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004958275271200924,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.19764800518751144,
|
|
"num_tokens": 15253298.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.243519067764282,
|
|
"epoch": 0.692866688940862,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004958218186034988,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.20032398253679276,
|
|
"num_tokens": 15261860.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.270795440673828,
|
|
"epoch": 0.693284330103575,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004958161062211537,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.20298123806715013,
|
|
"num_tokens": 15271021.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.199359512329101,
|
|
"epoch": 0.693701971266288,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004958103899731566,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.19973012506961824,
|
|
"num_tokens": 15280489.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.285273027420044,
|
|
"epoch": 0.694119612429001,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004958046698596081,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.20405687391757965,
|
|
"num_tokens": 15289387.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.2996439933776855,
|
|
"epoch": 0.694537253591714,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004957989458806079,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.19696756154298783,
|
|
"num_tokens": 15299334.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.273708724975586,
|
|
"epoch": 0.694954894754427,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957932180362564,
|
|
"loss": 5.0894,
|
|
"mean_token_accuracy": 0.19985067695379258,
|
|
"num_tokens": 15309174.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.322696495056152,
|
|
"epoch": 0.69537253591714,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004957874863266538,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.1984089195728302,
|
|
"num_tokens": 15318722.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.33597731590271,
|
|
"epoch": 0.695790177079853,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004957817507519006,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.20511474609375,
|
|
"num_tokens": 15327606.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.240427160263062,
|
|
"epoch": 0.696207818242566,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004957760113120971,
|
|
"loss": 5.0453,
|
|
"mean_token_accuracy": 0.20776250213384628,
|
|
"num_tokens": 15336520.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.311306524276733,
|
|
"epoch": 0.696625459405279,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004957702680073437,
|
|
"loss": 5.0971,
|
|
"mean_token_accuracy": 0.19944253861904143,
|
|
"num_tokens": 15345437.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.339717721939087,
|
|
"epoch": 0.697043100567992,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004957645208377411,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.2050753116607666,
|
|
"num_tokens": 15354660.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.276466417312622,
|
|
"epoch": 0.6974607417307049,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004957587698033898,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.20376146882772445,
|
|
"num_tokens": 15363958.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.2119224071502686,
|
|
"epoch": 0.697878382893418,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004957530149043905,
|
|
"loss": 5.0435,
|
|
"mean_token_accuracy": 0.21254927963018416,
|
|
"num_tokens": 15373351.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.297517776489258,
|
|
"epoch": 0.698296024056131,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004957472561408438,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.20222960263490677,
|
|
"num_tokens": 15383069.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.268164539337159,
|
|
"epoch": 0.6987136652188439,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004957414935128509,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.20236707478761673,
|
|
"num_tokens": 15391394.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.273834562301635,
|
|
"epoch": 0.699131306381557,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004957357270205123,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.20052915662527085,
|
|
"num_tokens": 15399993.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.2266136646270756,
|
|
"epoch": 0.69954894754427,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004957299566639292,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.20349505692720413,
|
|
"num_tokens": 15409886.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.32217698097229,
|
|
"epoch": 0.6999665887069829,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004957241824432025,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.2070102497935295,
|
|
"num_tokens": 15419772.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.282202291488647,
|
|
"epoch": 0.700384229869696,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004957184043584333,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.19971132576465606,
|
|
"num_tokens": 15429631.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.191723775863648,
|
|
"epoch": 0.700801871032409,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004957126224097227,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.21051173508167267,
|
|
"num_tokens": 15438411.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.175636339187622,
|
|
"epoch": 0.7012195121951219,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000495706836597172,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.20456888079643248,
|
|
"num_tokens": 15448943.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.274762678146362,
|
|
"epoch": 0.7016371533578349,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004957010469208825,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.2067001536488533,
|
|
"num_tokens": 15457908.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.298433113098144,
|
|
"epoch": 0.702054794520548,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956952533809554,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.2018888607621193,
|
|
"num_tokens": 15467390.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.257892417907715,
|
|
"epoch": 0.7024724356832609,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004956894559774923,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.2005039319396019,
|
|
"num_tokens": 15476419.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.1845649719238285,
|
|
"epoch": 0.7028900768459739,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004956836547105947,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.2094436079263687,
|
|
"num_tokens": 15485147.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.327765703201294,
|
|
"epoch": 0.703307718008687,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004956778495803641,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.20788611024618148,
|
|
"num_tokens": 15493816.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.314032030105591,
|
|
"epoch": 0.7037253591713999,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000495672040586902,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.19806592613458635,
|
|
"num_tokens": 15503051.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.246690034866333,
|
|
"epoch": 0.7041430003341129,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004956662277303103,
|
|
"loss": 4.9545,
|
|
"mean_token_accuracy": 0.20806530117988586,
|
|
"num_tokens": 15511854.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.211560535430908,
|
|
"epoch": 0.704560641496826,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004956604110106905,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.20776846259832382,
|
|
"num_tokens": 15521492.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.337711048126221,
|
|
"epoch": 0.7049782826595389,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004956545904281447,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.19189982116222382,
|
|
"num_tokens": 15530983.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.2513548851013185,
|
|
"epoch": 0.7053959238222519,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004956487659827748,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.21151032000780107,
|
|
"num_tokens": 15539722.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.212906980514527,
|
|
"epoch": 0.705813564984965,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004956429376746825,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.20425132364034654,
|
|
"num_tokens": 15548738.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.199920034408569,
|
|
"epoch": 0.7062312061476779,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004956371055039701,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.20703549385070802,
|
|
"num_tokens": 15557520.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.361644887924195,
|
|
"epoch": 0.7066488473103909,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004956312694707395,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.19470117837190629,
|
|
"num_tokens": 15567860.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.275394058227539,
|
|
"epoch": 0.7070664884731039,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000495625429575093,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.192530956864357,
|
|
"num_tokens": 15577174.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.161514568328857,
|
|
"epoch": 0.7074841296358169,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004956195858171327,
|
|
"loss": 4.9073,
|
|
"mean_token_accuracy": 0.2106803759932518,
|
|
"num_tokens": 15585476.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.183865547180176,
|
|
"epoch": 0.7079017707985299,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004956137381969611,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.2044389247894287,
|
|
"num_tokens": 15595422.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.305235052108765,
|
|
"epoch": 0.7083194119612429,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004956078867146805,
|
|
"loss": 5.1673,
|
|
"mean_token_accuracy": 0.19780557453632355,
|
|
"num_tokens": 15604223.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.3606634616851805,
|
|
"epoch": 0.7087370531239559,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004956020313703933,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.2004591390490532,
|
|
"num_tokens": 15613715.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.243637561798096,
|
|
"epoch": 0.7091546942866689,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004955961721642018,
|
|
"loss": 4.9434,
|
|
"mean_token_accuracy": 0.2148403376340866,
|
|
"num_tokens": 15623826.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.248225212097168,
|
|
"epoch": 0.7095723354493819,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495590309096209,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.19210588932037354,
|
|
"num_tokens": 15633311.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.277963781356812,
|
|
"epoch": 0.7099899766120948,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004955844421665171,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.2018355742096901,
|
|
"num_tokens": 15642785.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.423093318939209,
|
|
"epoch": 0.7104076177748079,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004955785713752292,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.19276996552944184,
|
|
"num_tokens": 15653009.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.273379230499268,
|
|
"epoch": 0.7108252589375209,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004955726967224479,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.20702264010906218,
|
|
"num_tokens": 15661672.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.231540060043335,
|
|
"epoch": 0.7112429001002338,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000495566818208276,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.1988774225115776,
|
|
"num_tokens": 15672186.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.201446294784546,
|
|
"epoch": 0.7116605412629469,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004955609358328163,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.20787085741758346,
|
|
"num_tokens": 15680351.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.30036244392395,
|
|
"epoch": 0.7120781824256599,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004955550495961722,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.20204918533563615,
|
|
"num_tokens": 15690140.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.316356039047241,
|
|
"epoch": 0.7124958235883728,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004955491594984462,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.19640470892190934,
|
|
"num_tokens": 15699968.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.231197261810303,
|
|
"epoch": 0.7129134647510859,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004955432655397419,
|
|
"loss": 4.9754,
|
|
"mean_token_accuracy": 0.2068644419312477,
|
|
"num_tokens": 15709061.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.2801690101623535,
|
|
"epoch": 0.7133311059137989,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004955373677201621,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.197358538210392,
|
|
"num_tokens": 15718350.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.273557424545288,
|
|
"epoch": 0.7137487470765118,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004955314660398105,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.2013487324118614,
|
|
"num_tokens": 15727120.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.270314645767212,
|
|
"epoch": 0.7141663882392248,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004955255604987899,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.2005222484469414,
|
|
"num_tokens": 15735865.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.237473011016846,
|
|
"epoch": 0.7145840294019379,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000495519651097204,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.19991200864315034,
|
|
"num_tokens": 15745239.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.2389201641082765,
|
|
"epoch": 0.7150016705646508,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004955137378351561,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.20553722977638245,
|
|
"num_tokens": 15754418.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.257720136642456,
|
|
"epoch": 0.7154193117273638,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004955078207127498,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.2104574754834175,
|
|
"num_tokens": 15764175.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.2815117835998535,
|
|
"epoch": 0.7158369528900769,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004955018997300886,
|
|
"loss": 5.0169,
|
|
"mean_token_accuracy": 0.20599781423807145,
|
|
"num_tokens": 15772766.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.206281900405884,
|
|
"epoch": 0.7162545940527898,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004954959748872764,
|
|
"loss": 5.0349,
|
|
"mean_token_accuracy": 0.20548219829797745,
|
|
"num_tokens": 15781768.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.28205304145813,
|
|
"epoch": 0.7166722352155028,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004954900461844167,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.20031414926052094,
|
|
"num_tokens": 15791706.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.345217370986939,
|
|
"epoch": 0.7170898763782159,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004954841136216132,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.20170393139123916,
|
|
"num_tokens": 15802015.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.309958505630493,
|
|
"epoch": 0.7175075175409288,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004954781771989701,
|
|
"loss": 5.0456,
|
|
"mean_token_accuracy": 0.20367103368043898,
|
|
"num_tokens": 15811116.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.314964151382446,
|
|
"epoch": 0.7179251587036418,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000495472236916591,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.20001891255378723,
|
|
"num_tokens": 15819240.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.2686151504516605,
|
|
"epoch": 0.7183427998663549,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004954662927745799,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.1942302703857422,
|
|
"num_tokens": 15827740.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.210627937316895,
|
|
"epoch": 0.7187604410290678,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004954603447730411,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.19641515016555786,
|
|
"num_tokens": 15836763.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.375260496139527,
|
|
"epoch": 0.7191780821917808,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004954543929120786,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.19764616191387177,
|
|
"num_tokens": 15846624.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.298106527328491,
|
|
"epoch": 0.7195957233544938,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004954484371917967,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.19640001952648162,
|
|
"num_tokens": 15855713.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.16616473197937,
|
|
"epoch": 0.7200133645172068,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004954424776122993,
|
|
"loss": 4.8918,
|
|
"mean_token_accuracy": 0.21470627933740616,
|
|
"num_tokens": 15863577.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.279843521118164,
|
|
"epoch": 0.7204310056799198,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004954365141736913,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.2035283163189888,
|
|
"num_tokens": 15872479.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.324910879135132,
|
|
"epoch": 0.7208486468426328,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004954305468760765,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.19687013626098632,
|
|
"num_tokens": 15882170.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.309424781799317,
|
|
"epoch": 0.7212662880053458,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004954245757195598,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.2052209496498108,
|
|
"num_tokens": 15891694.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.274164819717408,
|
|
"epoch": 0.7216839291680588,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004954186007042454,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.18969081789255143,
|
|
"num_tokens": 15902232.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.278906059265137,
|
|
"epoch": 0.7221015703307718,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004954126218302382,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.20347175896167755,
|
|
"num_tokens": 15912218.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.219909191131592,
|
|
"epoch": 0.7225192114934847,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004954066390976427,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.21221179217100145,
|
|
"num_tokens": 15922011.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.1396472454071045,
|
|
"epoch": 0.7229368526561978,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004954006525065639,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.20297198444604875,
|
|
"num_tokens": 15930394.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.274592733383178,
|
|
"epoch": 0.7233544938189108,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953946620571061,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.19526482373476028,
|
|
"num_tokens": 15939880.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.290974426269531,
|
|
"epoch": 0.7237721349816237,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004953886677493746,
|
|
"loss": 4.9489,
|
|
"mean_token_accuracy": 0.21133266687393187,
|
|
"num_tokens": 15948521.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.274592638015747,
|
|
"epoch": 0.7241897761443368,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004953826695834741,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.1997961863875389,
|
|
"num_tokens": 15956811.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.2429595470428465,
|
|
"epoch": 0.7246074173070498,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004953766675595098,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.2035137638449669,
|
|
"num_tokens": 15967019.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.354040670394897,
|
|
"epoch": 0.7250250584697627,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004953706616775866,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.1990467756986618,
|
|
"num_tokens": 15976149.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.254963731765747,
|
|
"epoch": 0.7254426996324758,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953646519378097,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.2116715356707573,
|
|
"num_tokens": 15986711.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.24354920387268,
|
|
"epoch": 0.7258603407951888,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004953586383402844,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.20086046904325486,
|
|
"num_tokens": 15996482.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.149643039703369,
|
|
"epoch": 0.7262779819579017,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004953526208851157,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.20385881513357162,
|
|
"num_tokens": 16005801.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.177530908584595,
|
|
"epoch": 0.7266956231206148,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004953465995724092,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.1998415321111679,
|
|
"num_tokens": 16014807.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.2974365234375,
|
|
"epoch": 0.7271132642833278,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004953405744022705,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.19839449375867843,
|
|
"num_tokens": 16023326.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.315508270263672,
|
|
"epoch": 0.7275309054460407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953345453748045,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.19503802806138992,
|
|
"num_tokens": 16031648.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.237546396255493,
|
|
"epoch": 0.7279485466087537,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004953285124901171,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.20778812617063522,
|
|
"num_tokens": 16040179.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.300989723205566,
|
|
"epoch": 0.7283661877714668,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000495322475748314,
|
|
"loss": 5.1709,
|
|
"mean_token_accuracy": 0.18818193376064302,
|
|
"num_tokens": 16050770.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.342928552627564,
|
|
"epoch": 0.7287838289341797,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004953164351495007,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.2061034619808197,
|
|
"num_tokens": 16060504.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.196336698532105,
|
|
"epoch": 0.7292014700968927,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004953103906937831,
|
|
"loss": 4.8675,
|
|
"mean_token_accuracy": 0.2219960495829582,
|
|
"num_tokens": 16069240.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.171235275268555,
|
|
"epoch": 0.7296191112596058,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004953043423812669,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.2030269593000412,
|
|
"num_tokens": 16079098.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.1972565174102785,
|
|
"epoch": 0.7300367524223187,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004952982902120579,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.2079069882631302,
|
|
"num_tokens": 16088454.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.318050289154053,
|
|
"epoch": 0.7304543935850317,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004952922341862622,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.19803341329097748,
|
|
"num_tokens": 16096985.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.3538170337677,
|
|
"epoch": 0.7308720347477448,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004952861743039858,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.1922142758965492,
|
|
"num_tokens": 16105434.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.1745552062988285,
|
|
"epoch": 0.7312896759104577,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004952801105653347,
|
|
"loss": 4.9221,
|
|
"mean_token_accuracy": 0.21185823231935502,
|
|
"num_tokens": 16114933.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.322063159942627,
|
|
"epoch": 0.7317073170731707,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004952740429704152,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.19681729823350907,
|
|
"num_tokens": 16124954.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.270959997177124,
|
|
"epoch": 0.7321249582358837,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004952679715193334,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.208741395175457,
|
|
"num_tokens": 16134442.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.288479423522949,
|
|
"epoch": 0.7325425993985967,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004952618962121956,
|
|
"loss": 5.0851,
|
|
"mean_token_accuracy": 0.19861603677272796,
|
|
"num_tokens": 16143994.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.243255472183227,
|
|
"epoch": 0.7329602405613097,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004952558170491082,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.20211314409971237,
|
|
"num_tokens": 16152931.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.245799493789673,
|
|
"epoch": 0.7333778817240227,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004952497340301776,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.1979086145758629,
|
|
"num_tokens": 16162716.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.296688508987427,
|
|
"epoch": 0.7337955228867357,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952436471555103,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.19739053249359131,
|
|
"num_tokens": 16172371.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.2739451885223385,
|
|
"epoch": 0.7342131640494487,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004952375564252128,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.19860313832759857,
|
|
"num_tokens": 16181823.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.25150237083435,
|
|
"epoch": 0.7346308052121617,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004952314618393919,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.2048737421631813,
|
|
"num_tokens": 16190720.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.257874298095703,
|
|
"epoch": 0.7350484463748747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495225363398154,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.20101274698972701,
|
|
"num_tokens": 16199589.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.328910684585571,
|
|
"epoch": 0.7354660875375877,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004952192611016061,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.1968383178114891,
|
|
"num_tokens": 16208800.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.29531717300415,
|
|
"epoch": 0.7358837287003007,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000495213154949855,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.19798899292945862,
|
|
"num_tokens": 16218835.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.340003442764282,
|
|
"epoch": 0.7363013698630136,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004952070449430075,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.19999463707208634,
|
|
"num_tokens": 16228441.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.331887245178223,
|
|
"epoch": 0.7367190110257267,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004952009310811706,
|
|
"loss": 5.0701,
|
|
"mean_token_accuracy": 0.21234453469514847,
|
|
"num_tokens": 16237877.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.240772485733032,
|
|
"epoch": 0.7371366521884397,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004951948133644514,
|
|
"loss": 4.9805,
|
|
"mean_token_accuracy": 0.20158906430006027,
|
|
"num_tokens": 16246809.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.290755653381348,
|
|
"epoch": 0.7375542933511526,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495188691792957,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.20858348906040192,
|
|
"num_tokens": 16255754.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.28316445350647,
|
|
"epoch": 0.7379719345138657,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004951825663667943,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.20280176401138306,
|
|
"num_tokens": 16264861.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.243086957931519,
|
|
"epoch": 0.7383895756765787,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000495176437086071,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.20233129411935807,
|
|
"num_tokens": 16273628.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.249120569229126,
|
|
"epoch": 0.7388072168392917,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000495170303950894,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.2020691901445389,
|
|
"num_tokens": 16282958.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.308465099334716,
|
|
"epoch": 0.7392248580020047,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004951641669613708,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.199604432284832,
|
|
"num_tokens": 16292763.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.268598318099976,
|
|
"epoch": 0.7396424991647177,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004951580261176088,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.20101107507944108,
|
|
"num_tokens": 16302216.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.183607196807861,
|
|
"epoch": 0.7400601403274307,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004951518814197156,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.20984770506620407,
|
|
"num_tokens": 16311672.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.24825758934021,
|
|
"epoch": 0.7404777814901436,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004951457328677989,
|
|
"loss": 4.977,
|
|
"mean_token_accuracy": 0.2042390450835228,
|
|
"num_tokens": 16321027.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.31235294342041,
|
|
"epoch": 0.7408954226528567,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004951395804619659,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.19446713775396346,
|
|
"num_tokens": 16329471.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.218226528167724,
|
|
"epoch": 0.7413130638155697,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004951334242023247,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.20271010547876359,
|
|
"num_tokens": 16339085.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.325715017318726,
|
|
"epoch": 0.7417307049782826,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004951272640889828,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.20869650989770888,
|
|
"num_tokens": 16347950.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.233249616622925,
|
|
"epoch": 0.7421483461409957,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004951211001220484,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.21582262516021727,
|
|
"num_tokens": 16357129.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.223073482513428,
|
|
"epoch": 0.7425659873037087,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495114932301629,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.20700258016586304,
|
|
"num_tokens": 16365768.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.237380933761597,
|
|
"epoch": 0.7429836284664216,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004951087606278328,
|
|
"loss": 4.9705,
|
|
"mean_token_accuracy": 0.208609639108181,
|
|
"num_tokens": 16375548.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.266794967651367,
|
|
"epoch": 0.7434012696291347,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004951025851007678,
|
|
"loss": 5.0544,
|
|
"mean_token_accuracy": 0.2037885829806328,
|
|
"num_tokens": 16385472.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.237098455429077,
|
|
"epoch": 0.7438189107918477,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004950964057205421,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.20577559471130372,
|
|
"num_tokens": 16395048.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.313109016418457,
|
|
"epoch": 0.7442365519545606,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000495090222487264,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.192625992000103,
|
|
"num_tokens": 16405378.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.210748910903931,
|
|
"epoch": 0.7446541931172737,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004950840354010415,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.20468075424432755,
|
|
"num_tokens": 16415206.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.287775468826294,
|
|
"epoch": 0.7450718342799867,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004950778444619831,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.21236399561166763,
|
|
"num_tokens": 16424185.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.25602502822876,
|
|
"epoch": 0.7454894754426996,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000495071649670197,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.2037174880504608,
|
|
"num_tokens": 16433330.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.228633642196655,
|
|
"epoch": 0.7459071166054126,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000495065451025792,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.2042685016989708,
|
|
"num_tokens": 16442777.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.263068723678589,
|
|
"epoch": 0.7463247577681257,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004950592485288761,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.20811281353235245,
|
|
"num_tokens": 16451838.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.219137287139892,
|
|
"epoch": 0.7467423989308386,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004950530421795584,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.20272775441408158,
|
|
"num_tokens": 16460022.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.167187166213989,
|
|
"epoch": 0.7471600400935516,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004950468319779472,
|
|
"loss": 4.8758,
|
|
"mean_token_accuracy": 0.21294345259666442,
|
|
"num_tokens": 16468891.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.13449501991272,
|
|
"epoch": 0.7475776812562647,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004950406179241515,
|
|
"loss": 4.9634,
|
|
"mean_token_accuracy": 0.21613859981298447,
|
|
"num_tokens": 16478020.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.23965220451355,
|
|
"epoch": 0.7479953224189776,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004950344000182798,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.20133345276117326,
|
|
"num_tokens": 16487536.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.304015159606934,
|
|
"epoch": 0.7484129635816906,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004950281782604411,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.1971128597855568,
|
|
"num_tokens": 16495786.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.3689838409423825,
|
|
"epoch": 0.7488306047444037,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004950219526507442,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.20024119615554808,
|
|
"num_tokens": 16505535.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.324792814254761,
|
|
"epoch": 0.7492482459071166,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004950157231892983,
|
|
"loss": 5.1203,
|
|
"mean_token_accuracy": 0.20252104997634887,
|
|
"num_tokens": 16515387.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.255785942077637,
|
|
"epoch": 0.7496658870698296,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004950094898762123,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.20343419462442397,
|
|
"num_tokens": 16524421.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.304853010177612,
|
|
"epoch": 0.7500835282325427,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004950032527115954,
|
|
"loss": 5.056,
|
|
"mean_token_accuracy": 0.20461238771677018,
|
|
"num_tokens": 16534533.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.283917474746704,
|
|
"epoch": 0.7505011693952556,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004949970116955566,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.19695334881544113,
|
|
"num_tokens": 16543712.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.258808565139771,
|
|
"epoch": 0.7509188105579686,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004949907668282054,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.20198098570108414,
|
|
"num_tokens": 16552475.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.280427408218384,
|
|
"epoch": 0.7513364517206816,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000494984518109651,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.20394277125597,
|
|
"num_tokens": 16562237.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.304880857467651,
|
|
"epoch": 0.7517540928833946,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004949782655400028,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.20637119859457015,
|
|
"num_tokens": 16570508.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7517540928833946,
|
|
"eval_entropy": 4.971683328925894,
|
|
"eval_loss": 4.990440845489502,
|
|
"eval_mean_token_accuracy": 0.21553165673912897,
|
|
"eval_num_tokens": 16570508.0,
|
|
"eval_runtime": 20.8669,
|
|
"eval_samples_per_second": 1809.711,
|
|
"eval_steps_per_second": 226.244,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.144710350036621,
|
|
"epoch": 0.7521717340461076,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004949720091193704,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.21272427439689637,
|
|
"num_tokens": 16578561.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.18804292678833,
|
|
"epoch": 0.7525893752088206,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000494965748847863,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.21331399232149123,
|
|
"num_tokens": 16587168.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.28304238319397,
|
|
"epoch": 0.7530070163715336,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004949594847255905,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.19797411561012268,
|
|
"num_tokens": 16597252.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.189943599700928,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004949532167526625,
|
|
"loss": 4.9097,
|
|
"mean_token_accuracy": 0.21874556690454483,
|
|
"num_tokens": 16607558.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.275495147705078,
|
|
"epoch": 0.7538422986969596,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004949469449291886,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.19630672335624694,
|
|
"num_tokens": 16617019.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.251516199111938,
|
|
"epoch": 0.7542599398596725,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004949406692552787,
|
|
"loss": 4.9558,
|
|
"mean_token_accuracy": 0.20503464490175247,
|
|
"num_tokens": 16625815.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.316648817062378,
|
|
"epoch": 0.7546775810223856,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004949343897310426,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.19475164860486985,
|
|
"num_tokens": 16634876.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.263617897033692,
|
|
"epoch": 0.7550952221850986,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004949281063565904,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.19559246748685838,
|
|
"num_tokens": 16643770.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.304959774017334,
|
|
"epoch": 0.7555128633478115,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004949218191320319,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.2030907079577446,
|
|
"num_tokens": 16652845.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.221572589874268,
|
|
"epoch": 0.7559305045105246,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004949155280574772,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.20531387627124786,
|
|
"num_tokens": 16662224.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.2179888725280765,
|
|
"epoch": 0.7563481456732376,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004949092331330365,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.2033061534166336,
|
|
"num_tokens": 16671114.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.280143690109253,
|
|
"epoch": 0.7567657868359505,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00049490293435882,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.1989634022116661,
|
|
"num_tokens": 16680395.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.2822998046875,
|
|
"epoch": 0.7571834279986636,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948966317349379,
|
|
"loss": 5.021,
|
|
"mean_token_accuracy": 0.2037866398692131,
|
|
"num_tokens": 16690251.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.179423666000366,
|
|
"epoch": 0.7576010691613766,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948903252615006,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.21268972456455232,
|
|
"num_tokens": 16698945.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.320975351333618,
|
|
"epoch": 0.7580187103240895,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004948840149386184,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.19887876212596894,
|
|
"num_tokens": 16708325.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.255396699905395,
|
|
"epoch": 0.7584363514868026,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000494877700766402,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.20498788207769394,
|
|
"num_tokens": 16716392.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.233533430099487,
|
|
"epoch": 0.7588539926495156,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004948713827449616,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.20308665335178375,
|
|
"num_tokens": 16725284.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.2349292755126955,
|
|
"epoch": 0.7592716338122285,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004948650608744081,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.20699726045131683,
|
|
"num_tokens": 16734658.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.3296911239624025,
|
|
"epoch": 0.7596892749749415,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000494858735154852,
|
|
"loss": 5.1348,
|
|
"mean_token_accuracy": 0.1941468149423599,
|
|
"num_tokens": 16744403.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.344699382781982,
|
|
"epoch": 0.7601069161376546,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004948524055864041,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.20310524702072144,
|
|
"num_tokens": 16754254.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.3007111072540285,
|
|
"epoch": 0.7605245573003675,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004948460721691752,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.19811128377914428,
|
|
"num_tokens": 16763941.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.248220920562744,
|
|
"epoch": 0.7609421984630805,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948397349032762,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.20318600833415984,
|
|
"num_tokens": 16773181.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.165061044692993,
|
|
"epoch": 0.7613598396257936,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494833393788818,
|
|
"loss": 4.8566,
|
|
"mean_token_accuracy": 0.217023828625679,
|
|
"num_tokens": 16782622.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.278229284286499,
|
|
"epoch": 0.7617774807885065,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004948270488259117,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.20295659750699996,
|
|
"num_tokens": 16792805.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.283652067184448,
|
|
"epoch": 0.7621951219512195,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004948207000146682,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.20985897034406661,
|
|
"num_tokens": 16802641.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.310847425460816,
|
|
"epoch": 0.7626127631139326,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948143473551989,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.20163532048463823,
|
|
"num_tokens": 16812037.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.2317976474761965,
|
|
"epoch": 0.7630304042766455,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004948079908476147,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.21333686113357545,
|
|
"num_tokens": 16820279.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.247088146209717,
|
|
"epoch": 0.7634480454393585,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004948016304920271,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.20384583175182341,
|
|
"num_tokens": 16829396.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.275693798065186,
|
|
"epoch": 0.7638656866020715,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004947952662885473,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.20674884915351868,
|
|
"num_tokens": 16838389.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.249728488922119,
|
|
"epoch": 0.7642833277647845,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000494788898237287,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.1978883594274521,
|
|
"num_tokens": 16848012.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.2860208511352536,
|
|
"epoch": 0.7647009689274975,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004947825263383573,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.20621383488178252,
|
|
"num_tokens": 16857591.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.330141067504883,
|
|
"epoch": 0.7651186100902105,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049477615059187,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.19161659330129624,
|
|
"num_tokens": 16866792.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.233716058731079,
|
|
"epoch": 0.7655362512529235,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004947697709979367,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.20814401060342788,
|
|
"num_tokens": 16876602.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.2778706550598145,
|
|
"epoch": 0.7659538924156365,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004947633875566688,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.19809906482696532,
|
|
"num_tokens": 16886992.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.252055597305298,
|
|
"epoch": 0.7663715335783495,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004947570002681785,
|
|
"loss": 4.9806,
|
|
"mean_token_accuracy": 0.20402293503284455,
|
|
"num_tokens": 16895716.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.20696382522583,
|
|
"epoch": 0.7667891747410625,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004947506091325772,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.21368362456560136,
|
|
"num_tokens": 16904568.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.294762516021729,
|
|
"epoch": 0.7672068159037755,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004947442141499771,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.20015564411878586,
|
|
"num_tokens": 16913667.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.2819679260253904,
|
|
"epoch": 0.7676244570664885,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004947378153204899,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.19964004904031754,
|
|
"num_tokens": 16922897.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.312068891525269,
|
|
"epoch": 0.7680420982292014,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004947314126442279,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.19939082413911818,
|
|
"num_tokens": 16931559.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.249738121032715,
|
|
"epoch": 0.7684597393919145,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000494725006121303,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.19830271899700164,
|
|
"num_tokens": 16940191.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.273727178573608,
|
|
"epoch": 0.7688773805546275,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004947185957518273,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.20251138657331466,
|
|
"num_tokens": 16948971.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.278915452957153,
|
|
"epoch": 0.7692950217173404,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004947121815359133,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.20440083593130112,
|
|
"num_tokens": 16957944.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.216281127929688,
|
|
"epoch": 0.7697126628800535,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004947057634736729,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.20289336740970612,
|
|
"num_tokens": 16967418.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.209739112854004,
|
|
"epoch": 0.7701303040427665,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004946993415652186,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.2110656678676605,
|
|
"num_tokens": 16977233.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.228751564025879,
|
|
"epoch": 0.7705479452054794,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000494692915810663,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.20815958976745605,
|
|
"num_tokens": 16986023.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.249615001678467,
|
|
"epoch": 0.7709655863681925,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004946864862101185,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.19978789240121841,
|
|
"num_tokens": 16994987.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.247474956512451,
|
|
"epoch": 0.7713832275309055,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004946800527636975,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.2031473085284233,
|
|
"num_tokens": 17003902.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.274008560180664,
|
|
"epoch": 0.7718008686936184,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004946736154715129,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.1966204673051834,
|
|
"num_tokens": 17013258.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.316514253616333,
|
|
"epoch": 0.7722185098563314,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004946671743336771,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.20075574815273284,
|
|
"num_tokens": 17022258.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.308055591583252,
|
|
"epoch": 0.7726361510190445,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004946607293503031,
|
|
"loss": 5.0017,
|
|
"mean_token_accuracy": 0.2058529183268547,
|
|
"num_tokens": 17031485.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.14595251083374,
|
|
"epoch": 0.7730537921817574,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004946542805215036,
|
|
"loss": 4.9583,
|
|
"mean_token_accuracy": 0.21243593394756316,
|
|
"num_tokens": 17039916.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.169200134277344,
|
|
"epoch": 0.7734714333444704,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004946478278473914,
|
|
"loss": 5.0017,
|
|
"mean_token_accuracy": 0.2055194139480591,
|
|
"num_tokens": 17048153.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.260590076446533,
|
|
"epoch": 0.7738890745071835,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004946413713280797,
|
|
"loss": 5.0219,
|
|
"mean_token_accuracy": 0.2032251998782158,
|
|
"num_tokens": 17057473.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.293311071395874,
|
|
"epoch": 0.7743067156698964,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004946349109636814,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.20725265592336656,
|
|
"num_tokens": 17066431.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.295569515228271,
|
|
"epoch": 0.7747243568326094,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004946284467543096,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.195576910674572,
|
|
"num_tokens": 17076519.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.286792802810669,
|
|
"epoch": 0.7751419979953225,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004946219787000776,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.20168675035238265,
|
|
"num_tokens": 17084651.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.322910165786743,
|
|
"epoch": 0.7755596391580354,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004946155068010984,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.20444207787513732,
|
|
"num_tokens": 17094943.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.24666953086853,
|
|
"epoch": 0.7759772803207484,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004946090310574854,
|
|
"loss": 4.9665,
|
|
"mean_token_accuracy": 0.21084154546260833,
|
|
"num_tokens": 17103548.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.247779417037964,
|
|
"epoch": 0.7763949214834615,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004946025514693519,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.2076132670044899,
|
|
"num_tokens": 17112472.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.368599224090576,
|
|
"epoch": 0.7768125626461744,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004945960680368115,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.20087247341871262,
|
|
"num_tokens": 17121536.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.382666158676147,
|
|
"epoch": 0.7772302038088874,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004945895807599775,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.19446681439876556,
|
|
"num_tokens": 17130708.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.201947450637817,
|
|
"epoch": 0.7776478449716004,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004945830896389636,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.21008164882659913,
|
|
"num_tokens": 17139437.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.217733240127563,
|
|
"epoch": 0.7780654861343134,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945765946738835,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.19784676730632783,
|
|
"num_tokens": 17149107.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.300842905044556,
|
|
"epoch": 0.7784831272970264,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004945700958648507,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.19664413332939149,
|
|
"num_tokens": 17158866.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.264042329788208,
|
|
"epoch": 0.7789007684597394,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000494563593211979,
|
|
"loss": 4.9389,
|
|
"mean_token_accuracy": 0.2061143398284912,
|
|
"num_tokens": 17167909.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.196863794326783,
|
|
"epoch": 0.7793184096224524,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945570867153826,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.19810560196638108,
|
|
"num_tokens": 17176746.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.274602890014648,
|
|
"epoch": 0.7797360507851654,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004945505763751749,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.19951799511909485,
|
|
"num_tokens": 17186219.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.292765760421753,
|
|
"epoch": 0.7801536919478784,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945440621914702,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.21013571619987487,
|
|
"num_tokens": 17195811.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.1434410572052,
|
|
"epoch": 0.7805713331105913,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945375441643823,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.2075558379292488,
|
|
"num_tokens": 17205333.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.247045278549194,
|
|
"epoch": 0.7809889742733044,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004945310222940254,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.20057919770479202,
|
|
"num_tokens": 17214493.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.35245270729065,
|
|
"epoch": 0.7814066154360174,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004945244965805138,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.20075549334287643,
|
|
"num_tokens": 17223602.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.296604013442993,
|
|
"epoch": 0.7818242565987303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945179670239616,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.20265195965766908,
|
|
"num_tokens": 17232915.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.297085237503052,
|
|
"epoch": 0.7822418977614434,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004945114336244832,
|
|
"loss": 5.0452,
|
|
"mean_token_accuracy": 0.19677061289548875,
|
|
"num_tokens": 17242489.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.184795999526978,
|
|
"epoch": 0.7826595389241564,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000494504896382193,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.21818662881851197,
|
|
"num_tokens": 17251496.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.212567138671875,
|
|
"epoch": 0.7830771800868693,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004944983552972053,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.2103630617260933,
|
|
"num_tokens": 17260550.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.229867839813233,
|
|
"epoch": 0.7834948212495824,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004944918103696347,
|
|
"loss": 4.9552,
|
|
"mean_token_accuracy": 0.20542027205228805,
|
|
"num_tokens": 17269085.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.32703332901001,
|
|
"epoch": 0.7839124624122954,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004944852615995956,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.20348155349493027,
|
|
"num_tokens": 17278766.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.3745780944824215,
|
|
"epoch": 0.7843301035750083,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000494478708987203,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.19566073417663574,
|
|
"num_tokens": 17288316.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.20438175201416,
|
|
"epoch": 0.7847477447377214,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004944721525325713,
|
|
"loss": 4.908,
|
|
"mean_token_accuracy": 0.209099118411541,
|
|
"num_tokens": 17297829.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.261895179748535,
|
|
"epoch": 0.7851653859004344,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004944655922358154,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.20480266511440276,
|
|
"num_tokens": 17306631.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.222080183029175,
|
|
"epoch": 0.7855830270631473,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004944590280970503,
|
|
"loss": 4.989,
|
|
"mean_token_accuracy": 0.20846811830997466,
|
|
"num_tokens": 17316829.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.256192016601562,
|
|
"epoch": 0.7860006682258603,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004944524601163905,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.201057530939579,
|
|
"num_tokens": 17326568.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.2691083431243895,
|
|
"epoch": 0.7864183093885734,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004944458882939513,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.20296941846609115,
|
|
"num_tokens": 17335524.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.340509080886841,
|
|
"epoch": 0.7868359505512863,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004944393126298478,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.1955065533518791,
|
|
"num_tokens": 17346198.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.2453478336334225,
|
|
"epoch": 0.7872535917139993,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000494432733124195,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.20681069791316986,
|
|
"num_tokens": 17354696.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.204918050765992,
|
|
"epoch": 0.7876712328767124,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000494426149777108,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.2065887674689293,
|
|
"num_tokens": 17363314.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.189809083938599,
|
|
"epoch": 0.7880888740394253,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494419562588702,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.2123241752386093,
|
|
"num_tokens": 17372662.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.191453742980957,
|
|
"epoch": 0.7885065152021383,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004944129715590927,
|
|
"loss": 4.9492,
|
|
"mean_token_accuracy": 0.20553091168403625,
|
|
"num_tokens": 17381931.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.3013721942901615,
|
|
"epoch": 0.7889241563648514,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000494406376688395,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.19830621927976608,
|
|
"num_tokens": 17391210.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.187519788742065,
|
|
"epoch": 0.7893417975275643,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004943997779767248,
|
|
"loss": 4.9235,
|
|
"mean_token_accuracy": 0.21679074913263321,
|
|
"num_tokens": 17401102.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.203726530075073,
|
|
"epoch": 0.7897594386902773,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004943931754241972,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.2029724195599556,
|
|
"num_tokens": 17410036.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.239491033554077,
|
|
"epoch": 0.7901770798529903,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000494386569030928,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.20094247162342072,
|
|
"num_tokens": 17419348.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.265246057510376,
|
|
"epoch": 0.7905947210157033,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004943799587970328,
|
|
"loss": 5.0164,
|
|
"mean_token_accuracy": 0.20252895057201387,
|
|
"num_tokens": 17427937.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.184537696838379,
|
|
"epoch": 0.7910123621784163,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004943733447226275,
|
|
"loss": 4.8873,
|
|
"mean_token_accuracy": 0.21136914193630219,
|
|
"num_tokens": 17436259.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.300499439239502,
|
|
"epoch": 0.7914300033411293,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004943667268078277,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.19979051351547242,
|
|
"num_tokens": 17445202.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.233816242218017,
|
|
"epoch": 0.7918476445038423,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004943601050527493,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.20705427080392838,
|
|
"num_tokens": 17453928.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.252202081680298,
|
|
"epoch": 0.7922652856665553,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004943534794575081,
|
|
"loss": 4.9965,
|
|
"mean_token_accuracy": 0.20691302716732024,
|
|
"num_tokens": 17462609.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.317341661453247,
|
|
"epoch": 0.7926829268292683,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004943468500222203,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.20451964288949967,
|
|
"num_tokens": 17471326.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.222711610794067,
|
|
"epoch": 0.7931005679919813,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004943402167470019,
|
|
"loss": 4.9679,
|
|
"mean_token_accuracy": 0.2102462112903595,
|
|
"num_tokens": 17480296.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.184522390365601,
|
|
"epoch": 0.7935182091546943,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494333579631969,
|
|
"loss": 4.9088,
|
|
"mean_token_accuracy": 0.2054891526699066,
|
|
"num_tokens": 17489779.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.277272033691406,
|
|
"epoch": 0.7939358503174073,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004943269386772376,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.1985737845301628,
|
|
"num_tokens": 17499796.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.304689884185791,
|
|
"epoch": 0.7943534914801202,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004943202938829243,
|
|
"loss": 5.1333,
|
|
"mean_token_accuracy": 0.19701941907405854,
|
|
"num_tokens": 17509223.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.270747947692871,
|
|
"epoch": 0.7947711326428333,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004943136452491452,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.20057281106710434,
|
|
"num_tokens": 17518712.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.191637945175171,
|
|
"epoch": 0.7951887738055463,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004943069927760168,
|
|
"loss": 4.9626,
|
|
"mean_token_accuracy": 0.203747196495533,
|
|
"num_tokens": 17528648.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.137279605865478,
|
|
"epoch": 0.7956064149682592,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004943003364636554,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.2042611077427864,
|
|
"num_tokens": 17537859.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.312052059173584,
|
|
"epoch": 0.7960240561309723,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004942936763121777,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.19656646996736526,
|
|
"num_tokens": 17546438.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.2376564025878904,
|
|
"epoch": 0.7964416972936853,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004942870123217002,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.2112952396273613,
|
|
"num_tokens": 17554537.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.380575275421142,
|
|
"epoch": 0.7968593384563982,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004942803444923398,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.1969597101211548,
|
|
"num_tokens": 17564239.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.252948236465454,
|
|
"epoch": 0.7972769796191113,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004942736728242127,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.20550868511199952,
|
|
"num_tokens": 17574437.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.186539793014527,
|
|
"epoch": 0.7976946207818243,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004942669973174363,
|
|
"loss": 4.9622,
|
|
"mean_token_accuracy": 0.2088138207793236,
|
|
"num_tokens": 17583173.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.250811910629272,
|
|
"epoch": 0.7981122619445372,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000494260317972127,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.20072976499795914,
|
|
"num_tokens": 17591731.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.297665643692016,
|
|
"epoch": 0.7985299031072502,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004942536347884019,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.20334923267364502,
|
|
"num_tokens": 17600778.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.2076068878173825,
|
|
"epoch": 0.7989475442699633,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942469477663782,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.21386162638664247,
|
|
"num_tokens": 17609470.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.205557775497437,
|
|
"epoch": 0.7993651854326762,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004942402569061726,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.21139156073331833,
|
|
"num_tokens": 17618434.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.185389471054077,
|
|
"epoch": 0.7997828265953892,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942335622079025,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.20148361325263978,
|
|
"num_tokens": 17628170.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.2103941440582275,
|
|
"epoch": 0.8002004677581023,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942268636716848,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.2081296220421791,
|
|
"num_tokens": 17637391.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.267648792266845,
|
|
"epoch": 0.8006181089208152,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942201612976372,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.20556529015302658,
|
|
"num_tokens": 17647466.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.265105676651001,
|
|
"epoch": 0.8010357500835282,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004942134550858767,
|
|
"loss": 4.9583,
|
|
"mean_token_accuracy": 0.21140941977500916,
|
|
"num_tokens": 17656155.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.356911611557007,
|
|
"epoch": 0.8014533912462413,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942067450365208,
|
|
"loss": 5.0549,
|
|
"mean_token_accuracy": 0.2033181369304657,
|
|
"num_tokens": 17665242.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.255355453491211,
|
|
"epoch": 0.8018710324089542,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004942000311496871,
|
|
"loss": 5.0751,
|
|
"mean_token_accuracy": 0.20186760425567626,
|
|
"num_tokens": 17674964.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.314096927642822,
|
|
"epoch": 0.8022886735716672,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004941933134254928,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.20182795077562332,
|
|
"num_tokens": 17683275.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.285370635986328,
|
|
"epoch": 0.8027063147343803,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004941865918640559,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.19964318126440048,
|
|
"num_tokens": 17691841.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.274875020980835,
|
|
"epoch": 0.8031239558970932,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004941798664654937,
|
|
"loss": 4.9791,
|
|
"mean_token_accuracy": 0.2069456920027733,
|
|
"num_tokens": 17701258.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.266730213165284,
|
|
"epoch": 0.8035415970598062,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004941731372299241,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.2015609160065651,
|
|
"num_tokens": 17711028.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.292852544784546,
|
|
"epoch": 0.8039592382225192,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004941664041574651,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.21195669919252397,
|
|
"num_tokens": 17720175.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.2639209747314455,
|
|
"epoch": 0.8043768793852322,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004941596672482343,
|
|
"loss": 4.9768,
|
|
"mean_token_accuracy": 0.2064968004822731,
|
|
"num_tokens": 17730420.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.314378452301026,
|
|
"epoch": 0.8047945205479452,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004941529265023498,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.19087517410516738,
|
|
"num_tokens": 17739802.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.292182397842407,
|
|
"epoch": 0.8052121617106582,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004941461819199293,
|
|
"loss": 4.9583,
|
|
"mean_token_accuracy": 0.2136206090450287,
|
|
"num_tokens": 17749450.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.382546997070312,
|
|
"epoch": 0.8056298028733712,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004941394335010912,
|
|
"loss": 5.1735,
|
|
"mean_token_accuracy": 0.19719568341970445,
|
|
"num_tokens": 17758733.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.218323659896851,
|
|
"epoch": 0.8060474440360842,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004941326812459535,
|
|
"loss": 5.0691,
|
|
"mean_token_accuracy": 0.19888763427734374,
|
|
"num_tokens": 17769037.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.229291296005249,
|
|
"epoch": 0.8064650851987972,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004941259251546346,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.19772055000066757,
|
|
"num_tokens": 17777603.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.263878726959229,
|
|
"epoch": 0.8068827263615101,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004941191652272526,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.1985536277294159,
|
|
"num_tokens": 17787513.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.259982395172119,
|
|
"epoch": 0.8073003675242232,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004941124014639258,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.20427324175834655,
|
|
"num_tokens": 17796720.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.245716905593872,
|
|
"epoch": 0.8077180086869362,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004941056338647726,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.20633052289485931,
|
|
"num_tokens": 17806024.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.179434108734131,
|
|
"epoch": 0.8081356498496491,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004940988624299116,
|
|
"loss": 4.9501,
|
|
"mean_token_accuracy": 0.20712766647338868,
|
|
"num_tokens": 17815247.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.3371247291564945,
|
|
"epoch": 0.8085532910123622,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004940920871594613,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.20772816836833954,
|
|
"num_tokens": 17824024.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.244819259643554,
|
|
"epoch": 0.8089709321750752,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004940853080535403,
|
|
"loss": 4.9842,
|
|
"mean_token_accuracy": 0.2007152572274208,
|
|
"num_tokens": 17832782.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.257729005813599,
|
|
"epoch": 0.8093885733377881,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004940785251122673,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.2104298397898674,
|
|
"num_tokens": 17841961.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.259595680236816,
|
|
"epoch": 0.8098062145005012,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004940717383357608,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.215986667573452,
|
|
"num_tokens": 17851364.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.375884962081909,
|
|
"epoch": 0.8102238556632142,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940649477241401,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.189899742603302,
|
|
"num_tokens": 17860871.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.259339380264282,
|
|
"epoch": 0.8106414968259271,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940581532775237,
|
|
"loss": 5.039,
|
|
"mean_token_accuracy": 0.2024725005030632,
|
|
"num_tokens": 17869687.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.234317636489868,
|
|
"epoch": 0.8110591379886402,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004940513549960306,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.20565674751996993,
|
|
"num_tokens": 17878815.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.2361349105834964,
|
|
"epoch": 0.8114767791513532,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004940445528797798,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.21066177040338516,
|
|
"num_tokens": 17888302.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.21515474319458,
|
|
"epoch": 0.8118944203140661,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004940377469288906,
|
|
"loss": 4.8795,
|
|
"mean_token_accuracy": 0.2131497159600258,
|
|
"num_tokens": 17896807.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.254328346252441,
|
|
"epoch": 0.8123120614767791,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004940309371434819,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.20791725665330887,
|
|
"num_tokens": 17905988.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.299395370483398,
|
|
"epoch": 0.8127297026394922,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004940241235236731,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.1999855011701584,
|
|
"num_tokens": 17915917.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.31751708984375,
|
|
"epoch": 0.8131473438022051,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004940173060695833,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.2012006938457489,
|
|
"num_tokens": 17926158.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.239197778701782,
|
|
"epoch": 0.8135649849649181,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004940104847813319,
|
|
"loss": 5.0243,
|
|
"mean_token_accuracy": 0.20381434559822081,
|
|
"num_tokens": 17935488.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.2489635944366455,
|
|
"epoch": 0.8139826261276312,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004940036596590384,
|
|
"loss": 4.9471,
|
|
"mean_token_accuracy": 0.20430123060941696,
|
|
"num_tokens": 17944850.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.218004846572876,
|
|
"epoch": 0.8144002672903441,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004939968307028221,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.20269592404365538,
|
|
"num_tokens": 17954796.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.200586891174316,
|
|
"epoch": 0.8148179084530571,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004939899979128028,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.21451111286878585,
|
|
"num_tokens": 17963875.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.236223316192627,
|
|
"epoch": 0.8152355496157702,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004939831612890999,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.20401419401168824,
|
|
"num_tokens": 17972789.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.2286656379699705,
|
|
"epoch": 0.8156531907784831,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004939763208318332,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.2086518257856369,
|
|
"num_tokens": 17982355.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.310059642791748,
|
|
"epoch": 0.8160708319411961,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004939694765411225,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.20342446118593216,
|
|
"num_tokens": 17992046.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.225096130371094,
|
|
"epoch": 0.8164884731039092,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004939626284170874,
|
|
"loss": 4.9456,
|
|
"mean_token_accuracy": 0.2147072121500969,
|
|
"num_tokens": 18001440.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.349632263183594,
|
|
"epoch": 0.8169061142666221,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000493955776459848,
|
|
"loss": 5.0819,
|
|
"mean_token_accuracy": 0.19849843829870223,
|
|
"num_tokens": 18010817.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.260217952728271,
|
|
"epoch": 0.8173237554293351,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004939489206695241,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.2012816607952118,
|
|
"num_tokens": 18019547.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.201365327835083,
|
|
"epoch": 0.8177413965920481,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004939420610462359,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.2021454930305481,
|
|
"num_tokens": 18029191.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.297500085830689,
|
|
"epoch": 0.8181590377547611,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004939351975901034,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.19817759841680527,
|
|
"num_tokens": 18038831.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.290134620666504,
|
|
"epoch": 0.8185766789174741,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004939283303012467,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.20580538362264633,
|
|
"num_tokens": 18049243.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.179692077636719,
|
|
"epoch": 0.8189943200801871,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000493921459179786,
|
|
"loss": 4.9339,
|
|
"mean_token_accuracy": 0.21075773239135742,
|
|
"num_tokens": 18057960.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.254844760894775,
|
|
"epoch": 0.8194119612429,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004939145842258418,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.20131519436836243,
|
|
"num_tokens": 18066677.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.270044183731079,
|
|
"epoch": 0.8198296024056131,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004939077054395341,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.20133571326732635,
|
|
"num_tokens": 18075830.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.260774183273315,
|
|
"epoch": 0.8202472435683261,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004939008228209836,
|
|
"loss": 4.9231,
|
|
"mean_token_accuracy": 0.20229074805974961,
|
|
"num_tokens": 18085335.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.25436749458313,
|
|
"epoch": 0.820664884731039,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004938939363703106,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.1998175337910652,
|
|
"num_tokens": 18094531.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.233586263656616,
|
|
"epoch": 0.8210825258937521,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004938870460876359,
|
|
"loss": 4.9473,
|
|
"mean_token_accuracy": 0.20644865930080414,
|
|
"num_tokens": 18103593.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.25080304145813,
|
|
"epoch": 0.8215001670564651,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049388015197308,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.20640114843845367,
|
|
"num_tokens": 18112826.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.280575084686279,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004938732540267635,
|
|
"loss": 5.0734,
|
|
"mean_token_accuracy": 0.2011779710650444,
|
|
"num_tokens": 18121687.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.286564016342163,
|
|
"epoch": 0.8223354493818911,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004938663522488072,
|
|
"loss": 4.9466,
|
|
"mean_token_accuracy": 0.21447840332984924,
|
|
"num_tokens": 18130071.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.303811550140381,
|
|
"epoch": 0.8227530905446041,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004938594466393321,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.19955944567918776,
|
|
"num_tokens": 18139077.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.271750211715698,
|
|
"epoch": 0.823170731707317,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004938525371984588,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.20915289372205734,
|
|
"num_tokens": 18147173.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.261496305465698,
|
|
"epoch": 0.8235883728700301,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004938456239263085,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.20853268653154372,
|
|
"num_tokens": 18157061.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.266523456573486,
|
|
"epoch": 0.8240060140327431,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004938387068230021,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.20922657698392869,
|
|
"num_tokens": 18166115.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.205725622177124,
|
|
"epoch": 0.824423655195456,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004938317858886606,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.20832649022340774,
|
|
"num_tokens": 18174978.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.2515706539154055,
|
|
"epoch": 0.824841296358169,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004938248611234055,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.20427511185407637,
|
|
"num_tokens": 18184948.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.276036500930786,
|
|
"epoch": 0.8252589375208821,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004938179325273577,
|
|
"loss": 4.9748,
|
|
"mean_token_accuracy": 0.20765022188425064,
|
|
"num_tokens": 18193443.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.308985567092895,
|
|
"epoch": 0.825676578683595,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004938110001006385,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.2085065871477127,
|
|
"num_tokens": 18202512.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.323337841033935,
|
|
"epoch": 0.826094219846308,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004938040638433694,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.20810281336307526,
|
|
"num_tokens": 18212328.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.272327280044555,
|
|
"epoch": 0.8265118610090211,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004937971237556719,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.20873690843582154,
|
|
"num_tokens": 18221155.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.2430308818817135,
|
|
"epoch": 0.826929502171734,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004937901798376672,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.20983963906764985,
|
|
"num_tokens": 18230604.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.2834024906158445,
|
|
"epoch": 0.827347143334447,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004937832320894772,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.2117239713668823,
|
|
"num_tokens": 18239126.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.253672409057617,
|
|
"epoch": 0.8277647844971601,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004937762805112233,
|
|
"loss": 4.9871,
|
|
"mean_token_accuracy": 0.2026601955294609,
|
|
"num_tokens": 18248634.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.2304778575897215,
|
|
"epoch": 0.828182425659873,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004937693251030273,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.19533180296421052,
|
|
"num_tokens": 18258500.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.301457118988037,
|
|
"epoch": 0.828600066822586,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000493762365865011,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.210722716152668,
|
|
"num_tokens": 18268374.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.2965020656585695,
|
|
"epoch": 0.8290177079852991,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004937554027972961,
|
|
"loss": 5.0534,
|
|
"mean_token_accuracy": 0.19986099153757095,
|
|
"num_tokens": 18277667.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.278017997741699,
|
|
"epoch": 0.829435349148012,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004937484359000046,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.20482454001903533,
|
|
"num_tokens": 18287516.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.2147575378417965,
|
|
"epoch": 0.829852990310725,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004937414651732584,
|
|
"loss": 4.923,
|
|
"mean_token_accuracy": 0.2071461170911789,
|
|
"num_tokens": 18296534.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.298532772064209,
|
|
"epoch": 0.830270631473438,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004937344906171795,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.2091649979352951,
|
|
"num_tokens": 18305743.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.3474061489105225,
|
|
"epoch": 0.830688272636151,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004937275122318902,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.20396639704704284,
|
|
"num_tokens": 18315524.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.254120349884033,
|
|
"epoch": 0.831105913798864,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004937205300175123,
|
|
"loss": 4.9332,
|
|
"mean_token_accuracy": 0.21345308423042297,
|
|
"num_tokens": 18324280.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.292413282394409,
|
|
"epoch": 0.831523554961577,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004937135439741682,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.20525659173727034,
|
|
"num_tokens": 18332661.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.277207899093628,
|
|
"epoch": 0.83194119612429,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004937065541019806,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.18974896967411042,
|
|
"num_tokens": 18342986.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.334020137786865,
|
|
"epoch": 0.832358837287003,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004936995604010711,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.20301198661327363,
|
|
"num_tokens": 18351873.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.368306255340576,
|
|
"epoch": 0.832776478449716,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004936925628715628,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.20117400139570235,
|
|
"num_tokens": 18362174.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.271776008605957,
|
|
"epoch": 0.833194119612429,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004936855615135779,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.2095385327935219,
|
|
"num_tokens": 18371272.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.306307363510132,
|
|
"epoch": 0.833611760775142,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000493678556327239,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.20720719546079636,
|
|
"num_tokens": 18380526.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.258482122421265,
|
|
"epoch": 0.834029401937855,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004936715473126688,
|
|
"loss": 4.9692,
|
|
"mean_token_accuracy": 0.20239598900079728,
|
|
"num_tokens": 18390027.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.190728092193604,
|
|
"epoch": 0.8344470431005679,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049366453446999,
|
|
"loss": 4.9502,
|
|
"mean_token_accuracy": 0.21156060546636582,
|
|
"num_tokens": 18399012.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.1778669357299805,
|
|
"epoch": 0.834864684263281,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004936575177993251,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.20892443060874938,
|
|
"num_tokens": 18408891.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.248783731460572,
|
|
"epoch": 0.835282325425994,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004936504973007973,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.21122715920209884,
|
|
"num_tokens": 18417909.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.230789995193481,
|
|
"epoch": 0.8356999665887069,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004936434729745294,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.20500878244638443,
|
|
"num_tokens": 18427250.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.291396808624268,
|
|
"epoch": 0.83611760775142,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004936364448206442,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.20601308196783066,
|
|
"num_tokens": 18435851.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.212124919891357,
|
|
"epoch": 0.836535248914133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004936294128392649,
|
|
"loss": 4.9648,
|
|
"mean_token_accuracy": 0.2005218267440796,
|
|
"num_tokens": 18444535.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.262107706069946,
|
|
"epoch": 0.8369528900768459,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004936223770305146,
|
|
"loss": 5.0876,
|
|
"mean_token_accuracy": 0.20311591178178787,
|
|
"num_tokens": 18454453.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.378511095046997,
|
|
"epoch": 0.837370531239559,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004936153373945165,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.19575342088937758,
|
|
"num_tokens": 18465033.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.32452883720398,
|
|
"epoch": 0.837788172402272,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004936082939313936,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.20863575637340545,
|
|
"num_tokens": 18473786.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.228324365615845,
|
|
"epoch": 0.8382058135649849,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004936012466412695,
|
|
"loss": 4.969,
|
|
"mean_token_accuracy": 0.20423714965581893,
|
|
"num_tokens": 18483282.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.373920631408692,
|
|
"epoch": 0.838623454727698,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004935941955242674,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.20020185708999633,
|
|
"num_tokens": 18492612.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.250041770935058,
|
|
"epoch": 0.839041095890411,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004935871405805109,
|
|
"loss": 4.9552,
|
|
"mean_token_accuracy": 0.2173479452729225,
|
|
"num_tokens": 18501120.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.25679931640625,
|
|
"epoch": 0.8394587370531239,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004935800818101232,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.19972871690988542,
|
|
"num_tokens": 18510613.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.2476129055023195,
|
|
"epoch": 0.8398763782158369,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004935730192132282,
|
|
"loss": 4.9394,
|
|
"mean_token_accuracy": 0.20895889401435852,
|
|
"num_tokens": 18518854.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.300178909301758,
|
|
"epoch": 0.84029401937855,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004935659527899493,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.20423698723316192,
|
|
"num_tokens": 18527592.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.219785833358765,
|
|
"epoch": 0.8407116605412629,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004935588825404104,
|
|
"loss": 4.9084,
|
|
"mean_token_accuracy": 0.21537507325410843,
|
|
"num_tokens": 18536396.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.176874780654908,
|
|
"epoch": 0.8411293017039759,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004935518084647351,
|
|
"loss": 4.8775,
|
|
"mean_token_accuracy": 0.21990620195865632,
|
|
"num_tokens": 18545201.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.238845300674439,
|
|
"epoch": 0.841546942866689,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004935447305630474,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.206235833466053,
|
|
"num_tokens": 18554944.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.271214008331299,
|
|
"epoch": 0.8419645840294019,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004935376488354711,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.20508895218372344,
|
|
"num_tokens": 18564642.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.274746036529541,
|
|
"epoch": 0.8423822251921149,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004935305632821303,
|
|
"loss": 4.973,
|
|
"mean_token_accuracy": 0.2051324337720871,
|
|
"num_tokens": 18573897.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.249931192398071,
|
|
"epoch": 0.842799866354828,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004935234739031488,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.20907960832118988,
|
|
"num_tokens": 18583174.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.255146455764771,
|
|
"epoch": 0.8432175075175409,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004935163806986508,
|
|
"loss": 4.9275,
|
|
"mean_token_accuracy": 0.21141382902860642,
|
|
"num_tokens": 18592540.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.2272542953491214,
|
|
"epoch": 0.8436351486802539,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004935092836687607,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.2063366264104843,
|
|
"num_tokens": 18602743.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.154385089874268,
|
|
"epoch": 0.8440527898429669,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004935021828136025,
|
|
"loss": 4.9072,
|
|
"mean_token_accuracy": 0.20498106479644776,
|
|
"num_tokens": 18611544.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.322114944458008,
|
|
"epoch": 0.8444704310056799,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004934950781333005,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.2066030189394951,
|
|
"num_tokens": 18620841.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.267197895050049,
|
|
"epoch": 0.8448880721683929,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004934879696279793,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.20487528294324875,
|
|
"num_tokens": 18630890.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.31003041267395,
|
|
"epoch": 0.8453057133311059,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004934808572977632,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.20005080103874207,
|
|
"num_tokens": 18639768.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.178198623657226,
|
|
"epoch": 0.8457233544938189,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004934737411427765,
|
|
"loss": 4.8729,
|
|
"mean_token_accuracy": 0.21061053425073623,
|
|
"num_tokens": 18649578.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.237571811676025,
|
|
"epoch": 0.8461409956565319,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004934666211631442,
|
|
"loss": 4.969,
|
|
"mean_token_accuracy": 0.20928623974323274,
|
|
"num_tokens": 18658470.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.237877082824707,
|
|
"epoch": 0.8465586368192449,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004934594973589906,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.20185777693986892,
|
|
"num_tokens": 18668037.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.235051822662354,
|
|
"epoch": 0.8469762779819578,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004934523697304406,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.20137634724378586,
|
|
"num_tokens": 18677841.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.335362768173217,
|
|
"epoch": 0.8473939191446709,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004934452382776189,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.2000858500599861,
|
|
"num_tokens": 18686244.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.259623050689697,
|
|
"epoch": 0.8478115603073839,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004934381030006504,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.20433571934700012,
|
|
"num_tokens": 18695129.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.157860279083252,
|
|
"epoch": 0.8482292014700968,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00049343096389966,
|
|
"loss": 4.8696,
|
|
"mean_token_accuracy": 0.2209343433380127,
|
|
"num_tokens": 18703566.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.269841480255127,
|
|
"epoch": 0.8486468426328099,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004934238209747724,
|
|
"loss": 5.061,
|
|
"mean_token_accuracy": 0.1979523330926895,
|
|
"num_tokens": 18713616.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.30966968536377,
|
|
"epoch": 0.8490644837955229,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004934166742261132,
|
|
"loss": 4.985,
|
|
"mean_token_accuracy": 0.2088114485144615,
|
|
"num_tokens": 18722851.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.248343753814697,
|
|
"epoch": 0.8494821249582358,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000493409523653807,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.2050369843840599,
|
|
"num_tokens": 18731961.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.252809667587281,
|
|
"epoch": 0.8498997661209489,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004934023692579793,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.20414309203624725,
|
|
"num_tokens": 18741267.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.295991230010986,
|
|
"epoch": 0.8503174072836619,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004933952110387553,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.2051036164164543,
|
|
"num_tokens": 18750266.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.2430657863616945,
|
|
"epoch": 0.8507350484463748,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004933880489962602,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.20580157339572908,
|
|
"num_tokens": 18759910.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.350414800643921,
|
|
"epoch": 0.8511526896090879,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004933808831306194,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.1928314045071602,
|
|
"num_tokens": 18769510.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.2096569538116455,
|
|
"epoch": 0.8515703307718009,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004933737134419583,
|
|
"loss": 4.9306,
|
|
"mean_token_accuracy": 0.20774139910936357,
|
|
"num_tokens": 18779893.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.27144570350647,
|
|
"epoch": 0.8519879719345138,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004933665399304025,
|
|
"loss": 4.996,
|
|
"mean_token_accuracy": 0.21487488597631454,
|
|
"num_tokens": 18788802.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.217508554458618,
|
|
"epoch": 0.8524056130972268,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004933593625960777,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.21084739565849303,
|
|
"num_tokens": 18797154.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.222530889511108,
|
|
"epoch": 0.8528232542599399,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004933521814391094,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.20759905576705934,
|
|
"num_tokens": 18806151.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.310242795944214,
|
|
"epoch": 0.8532408954226529,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004933449964596232,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.2173854425549507,
|
|
"num_tokens": 18815162.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.185241222381592,
|
|
"epoch": 0.8536585365853658,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004933378076577451,
|
|
"loss": 4.9001,
|
|
"mean_token_accuracy": 0.20504977852106093,
|
|
"num_tokens": 18823676.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.307117700576782,
|
|
"epoch": 0.8540761777480789,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004933306150336009,
|
|
"loss": 5.2121,
|
|
"mean_token_accuracy": 0.19228034615516662,
|
|
"num_tokens": 18832991.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.340936374664307,
|
|
"epoch": 0.8544938189107919,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004933234185873164,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.20017870515584946,
|
|
"num_tokens": 18842614.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.365727663040161,
|
|
"epoch": 0.8549114600735048,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004933162183190177,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.1973433494567871,
|
|
"num_tokens": 18852747.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.216653728485108,
|
|
"epoch": 0.8553291012362179,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004933090142288308,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.20647422671318055,
|
|
"num_tokens": 18862005.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.24114499092102,
|
|
"epoch": 0.8557467423989309,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004933018063168819,
|
|
"loss": 4.9496,
|
|
"mean_token_accuracy": 0.21857316493988038,
|
|
"num_tokens": 18870172.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.270547008514404,
|
|
"epoch": 0.8561643835616438,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000493294594583297,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.2063850998878479,
|
|
"num_tokens": 18879428.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.258616876602173,
|
|
"epoch": 0.8565820247243568,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004932873790282026,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.21842623353004456,
|
|
"num_tokens": 18888694.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.302799701690674,
|
|
"epoch": 0.8569996658870699,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004932801596517248,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.20132369995117189,
|
|
"num_tokens": 18898317.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.203007698059082,
|
|
"epoch": 0.8574173070497828,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932729364539901,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.20466060638427735,
|
|
"num_tokens": 18906749.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.220407867431641,
|
|
"epoch": 0.8578349482124958,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004932657094351248,
|
|
"loss": 4.9059,
|
|
"mean_token_accuracy": 0.2052523359656334,
|
|
"num_tokens": 18915404.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.270706415176392,
|
|
"epoch": 0.8582525893752089,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004932584785952555,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.20949395149946212,
|
|
"num_tokens": 18925512.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.202923536300659,
|
|
"epoch": 0.8586702305379218,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000493251243934509,
|
|
"loss": 4.93,
|
|
"mean_token_accuracy": 0.21665686815977098,
|
|
"num_tokens": 18934278.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.223158597946167,
|
|
"epoch": 0.8590878717006348,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004932440054530116,
|
|
"loss": 5.0202,
|
|
"mean_token_accuracy": 0.20478919744491578,
|
|
"num_tokens": 18943126.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.264473581314087,
|
|
"epoch": 0.8595055128633479,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004932367631508903,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.20530630350112916,
|
|
"num_tokens": 18951716.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.264700651168823,
|
|
"epoch": 0.8599231540260608,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004932295170282717,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.2013673096895218,
|
|
"num_tokens": 18960692.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.245903015136719,
|
|
"epoch": 0.8603407951887738,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004932222670852828,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.20959464013576506,
|
|
"num_tokens": 18969813.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.235074853897094,
|
|
"epoch": 0.8607584363514869,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004932150133220504,
|
|
"loss": 4.8729,
|
|
"mean_token_accuracy": 0.2154097780585289,
|
|
"num_tokens": 18978536.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.238340997695923,
|
|
"epoch": 0.8611760775141998,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932077557387015,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.20798897743225098,
|
|
"num_tokens": 18987637.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.125835037231445,
|
|
"epoch": 0.8615937186769128,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004932004943353633,
|
|
"loss": 4.8114,
|
|
"mean_token_accuracy": 0.21476808041334153,
|
|
"num_tokens": 18997010.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.226070976257324,
|
|
"epoch": 0.8620113598396258,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004931932291121627,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.20777673572301864,
|
|
"num_tokens": 19005685.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.227260971069336,
|
|
"epoch": 0.8624290010023388,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004931859600692269,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.20662796199321748,
|
|
"num_tokens": 19014836.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.292548656463623,
|
|
"epoch": 0.8628466421650518,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004931786872066833,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.20313481986522675,
|
|
"num_tokens": 19024442.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.244026803970337,
|
|
"epoch": 0.8632642833277648,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004931714105246592,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.21448239535093308,
|
|
"num_tokens": 19033730.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.1913618564605715,
|
|
"epoch": 0.8636819244904778,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004931641300232819,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.21826999634504318,
|
|
"num_tokens": 19042765.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.266368007659912,
|
|
"epoch": 0.8640995656531908,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004931568457026789,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.20834215432405473,
|
|
"num_tokens": 19051408.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.2913788795471195,
|
|
"epoch": 0.8645172068159038,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004931495575629778,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.20063044577836991,
|
|
"num_tokens": 19061145.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.240260124206543,
|
|
"epoch": 0.8649348479786167,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000493142265604306,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.20513593405485153,
|
|
"num_tokens": 19070157.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.2030281066894535,
|
|
"epoch": 0.8653524891413298,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004931349698267914,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.22250519692897797,
|
|
"num_tokens": 19078532.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.206335020065308,
|
|
"epoch": 0.8657701303040428,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004931276702305615,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.21466850340366364,
|
|
"num_tokens": 19087283.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.260415983200073,
|
|
"epoch": 0.8661877714667557,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004931203668157441,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.20373378843069076,
|
|
"num_tokens": 19097568.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.326429843902588,
|
|
"epoch": 0.8666054126294688,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004931130595824672,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.1997108355164528,
|
|
"num_tokens": 19107218.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.282728958129883,
|
|
"epoch": 0.8670230537921818,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004931057485308587,
|
|
"loss": 5.0112,
|
|
"mean_token_accuracy": 0.20635404139757157,
|
|
"num_tokens": 19116128.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.168923187255859,
|
|
"epoch": 0.8674406949548947,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004930984336610465,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.2116895005106926,
|
|
"num_tokens": 19124885.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.287353277206421,
|
|
"epoch": 0.8678583361176078,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004930911149731587,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.20740906596183778,
|
|
"num_tokens": 19134125.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.250035190582276,
|
|
"epoch": 0.8682759772803208,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004930837924673233,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.20845960825681686,
|
|
"num_tokens": 19141925.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.272624492645264,
|
|
"epoch": 0.8686936184430337,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004930764661436688,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.2049855411052704,
|
|
"num_tokens": 19151440.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.288385391235352,
|
|
"epoch": 0.8691112596057468,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004930691360023231,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.20376590192317962,
|
|
"num_tokens": 19161447.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.305224323272705,
|
|
"epoch": 0.8695289007684598,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004930618020434147,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.20132783204317092,
|
|
"num_tokens": 19170804.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.366559314727783,
|
|
"epoch": 0.8699465419311727,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004930544642670721,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.20298609435558318,
|
|
"num_tokens": 19179898.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.222680282592774,
|
|
"epoch": 0.8703641830938857,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004930471226734235,
|
|
"loss": 4.9302,
|
|
"mean_token_accuracy": 0.21022806763648988,
|
|
"num_tokens": 19188919.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.239116573333741,
|
|
"epoch": 0.8707818242565988,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004930397772625976,
|
|
"loss": 5.0116,
|
|
"mean_token_accuracy": 0.21419499218463897,
|
|
"num_tokens": 19197745.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.236387491226196,
|
|
"epoch": 0.8711994654193117,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000493032428034723,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.21296040415763856,
|
|
"num_tokens": 19206681.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.319953155517578,
|
|
"epoch": 0.8716171065820247,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004930250749899282,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.20518571734428406,
|
|
"num_tokens": 19215806.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.256429624557495,
|
|
"epoch": 0.8720347477447378,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004930177181283422,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.20314709842205048,
|
|
"num_tokens": 19224681.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.224412441253662,
|
|
"epoch": 0.8724523889074507,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004930103574500934,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.20471603125333787,
|
|
"num_tokens": 19232684.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.27227554321289,
|
|
"epoch": 0.8728700300701637,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004930029929553109,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.20247936397790908,
|
|
"num_tokens": 19242538.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.221435165405273,
|
|
"epoch": 0.8732876712328768,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004929956246441237,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.20176523327827453,
|
|
"num_tokens": 19251146.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.338691234588623,
|
|
"epoch": 0.8737053123955897,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929882525166608,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.20471732467412948,
|
|
"num_tokens": 19259931.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.307700061798096,
|
|
"epoch": 0.8741229535583027,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004929808765730509,
|
|
"loss": 5.0184,
|
|
"mean_token_accuracy": 0.20228454619646072,
|
|
"num_tokens": 19268796.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.268148422241211,
|
|
"epoch": 0.8745405947210158,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004929734968134235,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.20123215168714523,
|
|
"num_tokens": 19278396.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.29532380104065,
|
|
"epoch": 0.8749582358837287,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004929661132379076,
|
|
"loss": 5.0628,
|
|
"mean_token_accuracy": 0.20126961618661882,
|
|
"num_tokens": 19287914.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.282534170150757,
|
|
"epoch": 0.8753758770464417,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004929587258466326,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.2008860394358635,
|
|
"num_tokens": 19297304.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.297150135040283,
|
|
"epoch": 0.8757935182091547,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004929513346397278,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.2093738704919815,
|
|
"num_tokens": 19306245.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.274601888656616,
|
|
"epoch": 0.8762111593718677,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004929439396173223,
|
|
"loss": 5.0031,
|
|
"mean_token_accuracy": 0.20090779960155486,
|
|
"num_tokens": 19316160.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.24749264717102,
|
|
"epoch": 0.8766288005345807,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492936540779546,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.198929101228714,
|
|
"num_tokens": 19325411.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.308377981185913,
|
|
"epoch": 0.8770464416972937,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004929291381265281,
|
|
"loss": 4.9781,
|
|
"mean_token_accuracy": 0.20716729611158372,
|
|
"num_tokens": 19334297.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.3498210430145265,
|
|
"epoch": 0.8774640828600067,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004929217316583985,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.19487884193658828,
|
|
"num_tokens": 19344121.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.28120985031128,
|
|
"epoch": 0.8778817240227197,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929143213752865,
|
|
"loss": 5.026,
|
|
"mean_token_accuracy": 0.20545616298913955,
|
|
"num_tokens": 19353428.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.319450092315674,
|
|
"epoch": 0.8782993651854327,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492906907277322,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.20412155985832214,
|
|
"num_tokens": 19362661.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.161779165267944,
|
|
"epoch": 0.8787170063481456,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000492899489364635,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.2184468537569046,
|
|
"num_tokens": 19371246.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.218709897994995,
|
|
"epoch": 0.8791346475108587,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004928920676373549,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.20777586698532105,
|
|
"num_tokens": 19379777.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.230556392669678,
|
|
"epoch": 0.8795522886735717,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000492884642095612,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.20845843255519866,
|
|
"num_tokens": 19388717.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.390680027008057,
|
|
"epoch": 0.8799699298362846,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004928772127395361,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.1973919078707695,
|
|
"num_tokens": 19397936.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.405518388748169,
|
|
"epoch": 0.8803875709989977,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004928697795692575,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.19810874611139298,
|
|
"num_tokens": 19406830.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.311608791351318,
|
|
"epoch": 0.8808052121617107,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492862342584906,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.20270439386367797,
|
|
"num_tokens": 19415131.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.243639898300171,
|
|
"epoch": 0.8812228533244236,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492854901786612,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.22015682309865953,
|
|
"num_tokens": 19423585.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.197366333007812,
|
|
"epoch": 0.8816404944871367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004928474571745058,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.21833127439022065,
|
|
"num_tokens": 19431890.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.234969615936279,
|
|
"epoch": 0.8820581356498497,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004928400087487175,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.20382655113935472,
|
|
"num_tokens": 19441377.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.292036437988282,
|
|
"epoch": 0.8824757768125626,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004928325565093777,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.2021671026945114,
|
|
"num_tokens": 19451003.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.2545257091522215,
|
|
"epoch": 0.8828934179752757,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004928251004566167,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.21055592596530914,
|
|
"num_tokens": 19460166.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.2335553646087645,
|
|
"epoch": 0.8833110591379887,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004928176405905653,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.20982991009950638,
|
|
"num_tokens": 19469417.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.278882837295532,
|
|
"epoch": 0.8837287003007016,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004928101769113537,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.20859286487102507,
|
|
"num_tokens": 19479275.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.31929235458374,
|
|
"epoch": 0.8841463414634146,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000492802709419113,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.20477900505065919,
|
|
"num_tokens": 19488804.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.309050512313843,
|
|
"epoch": 0.8845639826261277,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004927952381139735,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.2141982525587082,
|
|
"num_tokens": 19497701.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.2885033130645756,
|
|
"epoch": 0.8849816237888406,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004927877629960663,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.2070293605327606,
|
|
"num_tokens": 19508177.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.231440162658691,
|
|
"epoch": 0.8853992649515536,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004927802840655221,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.20901501923799515,
|
|
"num_tokens": 19516866.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.298340225219727,
|
|
"epoch": 0.8858169061142667,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492772801322472,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.20141841024160384,
|
|
"num_tokens": 19525788.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.2866922378540036,
|
|
"epoch": 0.8862345472769796,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004927653147670468,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.20848783552646638,
|
|
"num_tokens": 19534748.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.201768445968628,
|
|
"epoch": 0.8866521884396926,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004927578243993777,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.21083342432975768,
|
|
"num_tokens": 19544083.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.199670124053955,
|
|
"epoch": 0.8870698296024057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004927503302195957,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.20604782849550246,
|
|
"num_tokens": 19553978.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.34895167350769,
|
|
"epoch": 0.8874874707651186,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000492742832227832,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.20453699976205825,
|
|
"num_tokens": 19563265.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.348745203018188,
|
|
"epoch": 0.8879051119278316,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000492735330424218,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.19322868883609773,
|
|
"num_tokens": 19572904.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.3203552722930905,
|
|
"epoch": 0.8883227530905446,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492727824808885,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.20697953253984452,
|
|
"num_tokens": 19581680.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.20696496963501,
|
|
"epoch": 0.8887403942532576,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004927203153819643,
|
|
"loss": 4.9056,
|
|
"mean_token_accuracy": 0.20259732753038406,
|
|
"num_tokens": 19590885.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.199515247344971,
|
|
"epoch": 0.8891580354159706,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004927128021435875,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.21411491185426712,
|
|
"num_tokens": 19599901.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.333843517303467,
|
|
"epoch": 0.8895756765786836,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492705285093886,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.2027731329202652,
|
|
"num_tokens": 19608745.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.159836196899414,
|
|
"epoch": 0.8899933177413966,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004926977642329913,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.21130220741033554,
|
|
"num_tokens": 19618418.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.177483558654785,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004926902395610353,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.2093990445137024,
|
|
"num_tokens": 19627118.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.304584598541259,
|
|
"epoch": 0.8908286000668226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004926827110781496,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.20386219024658203,
|
|
"num_tokens": 19636565.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.231849241256714,
|
|
"epoch": 0.8912462412295356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492675178784466,
|
|
"loss": 4.9091,
|
|
"mean_token_accuracy": 0.20857710093259813,
|
|
"num_tokens": 19645038.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.2259563446044925,
|
|
"epoch": 0.8916638823922486,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004926676426801164,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.20830583870410918,
|
|
"num_tokens": 19654088.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.266425657272339,
|
|
"epoch": 0.8920815235549616,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004926601027652328,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.2043178841471672,
|
|
"num_tokens": 19662551.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.3232197761535645,
|
|
"epoch": 0.8924991647176745,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000492652559039947,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.2048268124461174,
|
|
"num_tokens": 19672405.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.202703142166138,
|
|
"epoch": 0.8929168058803876,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004926450115043912,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.20604293197393417,
|
|
"num_tokens": 19681288.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.216831111907959,
|
|
"epoch": 0.8933344470431006,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004926374601586975,
|
|
"loss": 4.9058,
|
|
"mean_token_accuracy": 0.21093586087226868,
|
|
"num_tokens": 19690723.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.249474906921387,
|
|
"epoch": 0.8937520882058135,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004926299050029981,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.21203804165124893,
|
|
"num_tokens": 19699642.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.215154409408569,
|
|
"epoch": 0.8941697293685266,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004926223460374251,
|
|
"loss": 4.9064,
|
|
"mean_token_accuracy": 0.21234430223703385,
|
|
"num_tokens": 19707563.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.275932121276855,
|
|
"epoch": 0.8945873705312396,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004926147832621111,
|
|
"loss": 5.0529,
|
|
"mean_token_accuracy": 0.20878610759973526,
|
|
"num_tokens": 19717109.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.199494171142578,
|
|
"epoch": 0.8950050116939525,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004926072166771884,
|
|
"loss": 4.8751,
|
|
"mean_token_accuracy": 0.22296062260866165,
|
|
"num_tokens": 19725585.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.142381095886231,
|
|
"epoch": 0.8954226528566656,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004925996462827895,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.22324466407299043,
|
|
"num_tokens": 19733502.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.27479100227356,
|
|
"epoch": 0.8958402940193786,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004925920720790466,
|
|
"loss": 4.9624,
|
|
"mean_token_accuracy": 0.20894502997398376,
|
|
"num_tokens": 19742926.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.207340049743652,
|
|
"epoch": 0.8962579351820915,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004925844940660928,
|
|
"loss": 4.9493,
|
|
"mean_token_accuracy": 0.21365946978330613,
|
|
"num_tokens": 19752488.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.288606929779053,
|
|
"epoch": 0.8966755763448045,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004925769122440606,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.1995077386498451,
|
|
"num_tokens": 19762705.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.16873607635498,
|
|
"epoch": 0.8970932175075176,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004925693266130824,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.21496324688196183,
|
|
"num_tokens": 19771156.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.212031555175781,
|
|
"epoch": 0.8975108586702305,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004925617371732914,
|
|
"loss": 4.917,
|
|
"mean_token_accuracy": 0.21031807214021683,
|
|
"num_tokens": 19780788.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.1424261093139645,
|
|
"epoch": 0.8979284998329435,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004925541439248203,
|
|
"loss": 4.903,
|
|
"mean_token_accuracy": 0.2190555602312088,
|
|
"num_tokens": 19790169.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.348916482925415,
|
|
"epoch": 0.8983461409956566,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000492546546867802,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.19824612885713577,
|
|
"num_tokens": 19800249.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.236260604858399,
|
|
"epoch": 0.8987637821583695,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004925389460023696,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.21087584644556046,
|
|
"num_tokens": 19809797.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.173718690872192,
|
|
"epoch": 0.8991814233210825,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004925313413286559,
|
|
"loss": 4.8706,
|
|
"mean_token_accuracy": 0.21703252345323562,
|
|
"num_tokens": 19818826.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.238109493255616,
|
|
"epoch": 0.8995990644837956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004925237328467945,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.21215492784976958,
|
|
"num_tokens": 19827947.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.334453964233399,
|
|
"epoch": 0.9000167056465085,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004925161205569182,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.20384490191936494,
|
|
"num_tokens": 19835734.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.376838159561157,
|
|
"epoch": 0.9004343468092215,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004925085044591604,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.19279010742902755,
|
|
"num_tokens": 19845175.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.273960542678833,
|
|
"epoch": 0.9008519879719346,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004925008845536544,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.20825846046209334,
|
|
"num_tokens": 19853684.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.249964189529419,
|
|
"epoch": 0.9012696291346475,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004924932608405336,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.20598021298646926,
|
|
"num_tokens": 19862813.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.271593141555786,
|
|
"epoch": 0.9016872702973605,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004924856333199315,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.2069075584411621,
|
|
"num_tokens": 19871545.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.263514518737793,
|
|
"epoch": 0.9021049114600735,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004924780019919816,
|
|
"loss": 4.973,
|
|
"mean_token_accuracy": 0.2045950323343277,
|
|
"num_tokens": 19880060.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.233592128753662,
|
|
"epoch": 0.9025225526227865,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004924703668568174,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.2013958990573883,
|
|
"num_tokens": 19889151.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.28199200630188,
|
|
"epoch": 0.9029401937854995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004924627279145728,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.20838769525289536,
|
|
"num_tokens": 19898087.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.210484600067138,
|
|
"epoch": 0.9033578349482125,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004924550851653814,
|
|
"loss": 4.9496,
|
|
"mean_token_accuracy": 0.2111678034067154,
|
|
"num_tokens": 19906196.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.279273128509521,
|
|
"epoch": 0.9037754761109255,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004924474386093769,
|
|
"loss": 4.9994,
|
|
"mean_token_accuracy": 0.20398373305797576,
|
|
"num_tokens": 19915837.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.232589817047119,
|
|
"epoch": 0.9041931172736385,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004924397882466933,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.2037132650613785,
|
|
"num_tokens": 19926012.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.248990678787232,
|
|
"epoch": 0.9046107584363515,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004924321340774644,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.21445536613464355,
|
|
"num_tokens": 19935987.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.22609577178955,
|
|
"epoch": 0.9050283995990644,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004924244761018243,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.20592359006404876,
|
|
"num_tokens": 19945865.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.285213994979858,
|
|
"epoch": 0.9054460407617775,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492416814319907,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.20610006600618364,
|
|
"num_tokens": 19954824.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.192721366882324,
|
|
"epoch": 0.9058636819244905,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924091487318468,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.20356374680995942,
|
|
"num_tokens": 19964740.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.2060781955719,
|
|
"epoch": 0.9062813230872034,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004924014793377776,
|
|
"loss": 4.9143,
|
|
"mean_token_accuracy": 0.20999296009540558,
|
|
"num_tokens": 19974310.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.193950557708741,
|
|
"epoch": 0.9066989642499165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004923938061378339,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.2156645327806473,
|
|
"num_tokens": 19982943.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.237184953689575,
|
|
"epoch": 0.9071166054126295,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004923861291321499,
|
|
"loss": 4.9385,
|
|
"mean_token_accuracy": 0.21150051206350326,
|
|
"num_tokens": 19991971.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.310812091827392,
|
|
"epoch": 0.9075342465753424,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004923784483208601,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.20122545659542085,
|
|
"num_tokens": 20001491.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.231065845489502,
|
|
"epoch": 0.9079518877380555,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004923707637040989,
|
|
"loss": 4.8794,
|
|
"mean_token_accuracy": 0.21680667251348495,
|
|
"num_tokens": 20010605.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.089680957794189,
|
|
"epoch": 0.9083695289007685,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004923630752820008,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.21169963777065276,
|
|
"num_tokens": 20019291.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.195355701446533,
|
|
"epoch": 0.9087871700634814,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004923553830547004,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.20168370604515076,
|
|
"num_tokens": 20029048.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.2884307384490965,
|
|
"epoch": 0.9092048112261945,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923476870223324,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.20142191797494888,
|
|
"num_tokens": 20037878.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.223582792282104,
|
|
"epoch": 0.9096224523889075,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004923399871850315,
|
|
"loss": 4.9472,
|
|
"mean_token_accuracy": 0.21160757839679717,
|
|
"num_tokens": 20046662.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.181941080093384,
|
|
"epoch": 0.9100400935516204,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004923322835429326,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.21173545271158217,
|
|
"num_tokens": 20055329.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.126730155944824,
|
|
"epoch": 0.9104577347143334,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004923245760961704,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.21947408020496367,
|
|
"num_tokens": 20064024.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.243212652206421,
|
|
"epoch": 0.9108753758770465,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004923168648448799,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.20177298337221145,
|
|
"num_tokens": 20073022.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.2675834655761715,
|
|
"epoch": 0.9112930170397594,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004923091497891961,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.20252961665391922,
|
|
"num_tokens": 20081495.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.236374235153198,
|
|
"epoch": 0.9117106582024724,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004923014309292541,
|
|
"loss": 4.9365,
|
|
"mean_token_accuracy": 0.21498846411705017,
|
|
"num_tokens": 20090545.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.2209217071533205,
|
|
"epoch": 0.9121282993651855,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000492293708265189,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.20339341461658478,
|
|
"num_tokens": 20100236.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.2035435199737545,
|
|
"epoch": 0.9125459405278984,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004922859817971359,
|
|
"loss": 4.95,
|
|
"mean_token_accuracy": 0.21139469146728515,
|
|
"num_tokens": 20109522.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.222307825088501,
|
|
"epoch": 0.9129635816906114,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004922782515252302,
|
|
"loss": 4.8771,
|
|
"mean_token_accuracy": 0.21581975221633912,
|
|
"num_tokens": 20118248.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.149579000473023,
|
|
"epoch": 0.9133812228533245,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004922705174496072,
|
|
"loss": 4.9498,
|
|
"mean_token_accuracy": 0.20979409217834472,
|
|
"num_tokens": 20127096.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.200905513763428,
|
|
"epoch": 0.9137988640160374,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004922627795704022,
|
|
"loss": 4.9332,
|
|
"mean_token_accuracy": 0.20702405124902726,
|
|
"num_tokens": 20136815.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.263401222229004,
|
|
"epoch": 0.9142165051787504,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004922550378877507,
|
|
"loss": 4.923,
|
|
"mean_token_accuracy": 0.219817054271698,
|
|
"num_tokens": 20145455.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.248750114440918,
|
|
"epoch": 0.9146341463414634,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004922472924017882,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.20423217713832856,
|
|
"num_tokens": 20156139.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.292355346679687,
|
|
"epoch": 0.9150517875041764,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004922395431126506,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.20554944574832917,
|
|
"num_tokens": 20166266.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.376341676712036,
|
|
"epoch": 0.9154694286668894,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004922317900204732,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.2030709207057953,
|
|
"num_tokens": 20175005.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.173110485076904,
|
|
"epoch": 0.9158870698296024,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004922240331253916,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.21906585842370987,
|
|
"num_tokens": 20183488.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.213016748428345,
|
|
"epoch": 0.9163047109923154,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004922162724275421,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.2155229151248932,
|
|
"num_tokens": 20193724.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.2084283351898195,
|
|
"epoch": 0.9167223521550284,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004922085079270602,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.20799088180065156,
|
|
"num_tokens": 20203733.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.363068294525147,
|
|
"epoch": 0.9171399933177414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004922007396240819,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.2126768410205841,
|
|
"num_tokens": 20213448.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.289379405975342,
|
|
"epoch": 0.9175576344804544,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004921929675187433,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.21146342009305955,
|
|
"num_tokens": 20222837.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.291475486755371,
|
|
"epoch": 0.9179752756431674,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921851916111802,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.19906468093395233,
|
|
"num_tokens": 20232056.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.362490272521972,
|
|
"epoch": 0.9183929168058804,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921774119015289,
|
|
"loss": 5.032,
|
|
"mean_token_accuracy": 0.20598455667495727,
|
|
"num_tokens": 20241052.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.350063037872315,
|
|
"epoch": 0.9188105579685933,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004921696283899257,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.20262417793273926,
|
|
"num_tokens": 20251015.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.2182862758636475,
|
|
"epoch": 0.9192281991313064,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004921618410765067,
|
|
"loss": 4.9471,
|
|
"mean_token_accuracy": 0.20732340663671495,
|
|
"num_tokens": 20259388.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.2440643310546875,
|
|
"epoch": 0.9196458402940194,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004921540499614083,
|
|
"loss": 4.9241,
|
|
"mean_token_accuracy": 0.2058340311050415,
|
|
"num_tokens": 20268146.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.206805562973022,
|
|
"epoch": 0.9200634814567323,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921462550447669,
|
|
"loss": 4.9013,
|
|
"mean_token_accuracy": 0.210525307059288,
|
|
"num_tokens": 20277559.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.207626581192017,
|
|
"epoch": 0.9204811226194454,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921384563267189,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.21042125523090363,
|
|
"num_tokens": 20285661.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.209737968444824,
|
|
"epoch": 0.9208987637821584,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004921306538074008,
|
|
"loss": 5.0276,
|
|
"mean_token_accuracy": 0.2068430706858635,
|
|
"num_tokens": 20294636.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.288813781738281,
|
|
"epoch": 0.9213164049448713,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004921228474869493,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.21262361258268356,
|
|
"num_tokens": 20302372.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.290921688079834,
|
|
"epoch": 0.9217340461075844,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492115037365501,
|
|
"loss": 4.9477,
|
|
"mean_token_accuracy": 0.20561295002698898,
|
|
"num_tokens": 20311974.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.227998208999634,
|
|
"epoch": 0.9221516872702974,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004921072234431925,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.20474060624837875,
|
|
"num_tokens": 20321720.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.26362829208374,
|
|
"epoch": 0.9225693284330103,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000492099405720161,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.20439235866069794,
|
|
"num_tokens": 20331324.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.344644069671631,
|
|
"epoch": 0.9229869695957233,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004920915841965429,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.2000857338309288,
|
|
"num_tokens": 20340921.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.3625640869140625,
|
|
"epoch": 0.9234046107584364,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004920837588724753,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.20848338305950165,
|
|
"num_tokens": 20349871.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.153538942337036,
|
|
"epoch": 0.9238222519211493,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004920759297480953,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.21771738231182097,
|
|
"num_tokens": 20359171.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.234503555297851,
|
|
"epoch": 0.9242398930838623,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004920680968235397,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.21394995898008345,
|
|
"num_tokens": 20367779.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.203851938247681,
|
|
"epoch": 0.9246575342465754,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004920602600989459,
|
|
"loss": 4.8968,
|
|
"mean_token_accuracy": 0.21597154289484025,
|
|
"num_tokens": 20377568.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.321035957336425,
|
|
"epoch": 0.9250751754092883,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004920524195744509,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.20113638788461685,
|
|
"num_tokens": 20385915.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.186092758178711,
|
|
"epoch": 0.9254928165720013,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004920445752501921,
|
|
"loss": 4.896,
|
|
"mean_token_accuracy": 0.20959176272153854,
|
|
"num_tokens": 20394877.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.242312240600586,
|
|
"epoch": 0.9259104577347144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004920367271263066,
|
|
"loss": 4.908,
|
|
"mean_token_accuracy": 0.21296796351671218,
|
|
"num_tokens": 20403741.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.261515045166016,
|
|
"epoch": 0.9263280988974273,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004920288752029321,
|
|
"loss": 4.9432,
|
|
"mean_token_accuracy": 0.2100354790687561,
|
|
"num_tokens": 20412702.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.225878524780273,
|
|
"epoch": 0.9267457400601403,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004920210194802059,
|
|
"loss": 4.9711,
|
|
"mean_token_accuracy": 0.20904820710420607,
|
|
"num_tokens": 20421776.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.270692920684814,
|
|
"epoch": 0.9271633812228534,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004920131599582654,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.19687581211328506,
|
|
"num_tokens": 20432204.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.297599411010742,
|
|
"epoch": 0.9275810223855663,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004920052966372485,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.20225125551223755,
|
|
"num_tokens": 20441344.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.229573440551758,
|
|
"epoch": 0.9279986635482793,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004919974295172926,
|
|
"loss": 4.8868,
|
|
"mean_token_accuracy": 0.21324522346258162,
|
|
"num_tokens": 20449800.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.179731941223144,
|
|
"epoch": 0.9284163047109923,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004919895585985353,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.22074775844812394,
|
|
"num_tokens": 20458326.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.248476028442383,
|
|
"epoch": 0.9288339458737053,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004919816838811149,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.20186921656131745,
|
|
"num_tokens": 20468050.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.217872953414917,
|
|
"epoch": 0.9292515870364183,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004919738053651687,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.2135712817311287,
|
|
"num_tokens": 20477046.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.257941055297851,
|
|
"epoch": 0.9296692281991313,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000491965923050835,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.20851668566465378,
|
|
"num_tokens": 20486228.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.275617027282715,
|
|
"epoch": 0.9300868693618443,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004919580369382516,
|
|
"loss": 4.9965,
|
|
"mean_token_accuracy": 0.20068540275096894,
|
|
"num_tokens": 20494764.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.259941577911377,
|
|
"epoch": 0.9305045105245573,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004919501470275567,
|
|
"loss": 4.8942,
|
|
"mean_token_accuracy": 0.2105300948023796,
|
|
"num_tokens": 20502805.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.217697858810425,
|
|
"epoch": 0.9309221516872703,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004919422533188882,
|
|
"loss": 4.9557,
|
|
"mean_token_accuracy": 0.20720615535974501,
|
|
"num_tokens": 20512322.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.232539987564087,
|
|
"epoch": 0.9313397928499833,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004919343558123845,
|
|
"loss": 4.9515,
|
|
"mean_token_accuracy": 0.20555578470230101,
|
|
"num_tokens": 20520680.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.197862672805786,
|
|
"epoch": 0.9317574340126963,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004919264545081838,
|
|
"loss": 4.8051,
|
|
"mean_token_accuracy": 0.2218254342675209,
|
|
"num_tokens": 20528864.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.239057731628418,
|
|
"epoch": 0.9321750751754093,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004919185494064244,
|
|
"loss": 4.9385,
|
|
"mean_token_accuracy": 0.2032955601811409,
|
|
"num_tokens": 20538195.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.212842893600464,
|
|
"epoch": 0.9325927163381222,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004919106405072446,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.20588600039482116,
|
|
"num_tokens": 20547312.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.242993402481079,
|
|
"epoch": 0.9330103575008353,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000491902727810783,
|
|
"loss": 5.0059,
|
|
"mean_token_accuracy": 0.20013969987630845,
|
|
"num_tokens": 20557184.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.2526445388793945,
|
|
"epoch": 0.9334279986635483,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004918948113171781,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.20985149592161179,
|
|
"num_tokens": 20565819.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.182739686965943,
|
|
"epoch": 0.9338456398262612,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004918868910265684,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.21389106214046477,
|
|
"num_tokens": 20574761.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.299805450439453,
|
|
"epoch": 0.9342632809889743,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004918789669390927,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.19830050617456435,
|
|
"num_tokens": 20584003.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.279335927963257,
|
|
"epoch": 0.9346809221516873,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004918710390548895,
|
|
"loss": 4.9063,
|
|
"mean_token_accuracy": 0.20839720070362092,
|
|
"num_tokens": 20593123.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.232050466537475,
|
|
"epoch": 0.9350985633144002,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004918631073740977,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.20570932775735856,
|
|
"num_tokens": 20602582.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.207696771621704,
|
|
"epoch": 0.9355162044771133,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004918551718968562,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.2170298680663109,
|
|
"num_tokens": 20611681.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.214097118377685,
|
|
"epoch": 0.9359338456398263,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000491847232623304,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.2133308619260788,
|
|
"num_tokens": 20620671.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.228054666519165,
|
|
"epoch": 0.9363514868025392,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004918392895535798,
|
|
"loss": 4.9343,
|
|
"mean_token_accuracy": 0.20824634432792663,
|
|
"num_tokens": 20629986.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.226334428787231,
|
|
"epoch": 0.9367691279652522,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000491831342687823,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.20142373889684678,
|
|
"num_tokens": 20639274.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.253062629699707,
|
|
"epoch": 0.9371867691279653,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004918233920261723,
|
|
"loss": 4.9429,
|
|
"mean_token_accuracy": 0.21001542806625367,
|
|
"num_tokens": 20647753.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.154575252532959,
|
|
"epoch": 0.9376044102906782,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004918154375687673,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.21612597554922103,
|
|
"num_tokens": 20656226.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.153843927383423,
|
|
"epoch": 0.9380220514533912,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004918074793157472,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.2133975088596344,
|
|
"num_tokens": 20664682.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.266940593719482,
|
|
"epoch": 0.9384396926161043,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004917995172672511,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.21307457089424134,
|
|
"num_tokens": 20672909.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.1379166603088375,
|
|
"epoch": 0.9388573337788172,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004917915514234184,
|
|
"loss": 4.8109,
|
|
"mean_token_accuracy": 0.22096774429082872,
|
|
"num_tokens": 20681316.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.233173513412476,
|
|
"epoch": 0.9392749749415302,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004917835817843887,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.2031506448984146,
|
|
"num_tokens": 20690360.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.271797370910645,
|
|
"epoch": 0.9396926161042433,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004917756083503014,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.20605792254209518,
|
|
"num_tokens": 20700398.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.290175151824951,
|
|
"epoch": 0.9401102572669562,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004917676311212962,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.20291667580604553,
|
|
"num_tokens": 20709705.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.16318416595459,
|
|
"epoch": 0.9405278984296692,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004917596500975127,
|
|
"loss": 4.8818,
|
|
"mean_token_accuracy": 0.20749556869268418,
|
|
"num_tokens": 20717774.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.248675680160522,
|
|
"epoch": 0.9409455395923823,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004917516652790907,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.20820364505052566,
|
|
"num_tokens": 20725966.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.235063314437866,
|
|
"epoch": 0.9413631807550952,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004917436766661697,
|
|
"loss": 4.926,
|
|
"mean_token_accuracy": 0.2085683360695839,
|
|
"num_tokens": 20735254.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.207594919204712,
|
|
"epoch": 0.9417808219178082,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049173568425889,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.21636435389518738,
|
|
"num_tokens": 20743331.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.2406641960144045,
|
|
"epoch": 0.9421984630805212,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004917276880573911,
|
|
"loss": 4.9578,
|
|
"mean_token_accuracy": 0.19679056257009506,
|
|
"num_tokens": 20753966.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.238484048843384,
|
|
"epoch": 0.9426161042432342,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004917196880618132,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.21526833474636078,
|
|
"num_tokens": 20762608.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.150291776657104,
|
|
"epoch": 0.9430337454059472,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004917116842722962,
|
|
"loss": 4.8419,
|
|
"mean_token_accuracy": 0.21369767785072327,
|
|
"num_tokens": 20771194.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.214266300201416,
|
|
"epoch": 0.9434513865686602,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004917036766889804,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.21139425784349442,
|
|
"num_tokens": 20779700.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.307117462158203,
|
|
"epoch": 0.9438690277313732,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004916956653120058,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.19819415360689163,
|
|
"num_tokens": 20788117.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.257313632965088,
|
|
"epoch": 0.9442866688940862,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004916876501415129,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.201534965634346,
|
|
"num_tokens": 20798041.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.247580671310425,
|
|
"epoch": 0.9447043100567992,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004916796311776417,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.19957735538482665,
|
|
"num_tokens": 20807423.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.195126628875732,
|
|
"epoch": 0.9451219512195121,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004916716084205328,
|
|
"loss": 4.8647,
|
|
"mean_token_accuracy": 0.21924707442522048,
|
|
"num_tokens": 20816727.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.219134044647217,
|
|
"epoch": 0.9455395923822252,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004916635818703266,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.20576269775629044,
|
|
"num_tokens": 20824855.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.165248155593872,
|
|
"epoch": 0.9459572335449382,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004916555515271635,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.21847965568304062,
|
|
"num_tokens": 20833096.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.20643196105957,
|
|
"epoch": 0.9463748747076511,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004916475173911844,
|
|
"loss": 4.8607,
|
|
"mean_token_accuracy": 0.21841619163751602,
|
|
"num_tokens": 20842398.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.3712554454803465,
|
|
"epoch": 0.9467925158703642,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004916394794625296,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.19960071742534638,
|
|
"num_tokens": 20851745.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.386512422561646,
|
|
"epoch": 0.9472101570330772,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004916314377413399,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.20947361439466478,
|
|
"num_tokens": 20860935.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.25192174911499,
|
|
"epoch": 0.9476277981957901,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004916233922277562,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.20341380536556244,
|
|
"num_tokens": 20871088.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.235308504104614,
|
|
"epoch": 0.9480454393585032,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004916153429219192,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.2074069321155548,
|
|
"num_tokens": 20879313.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.228966331481933,
|
|
"epoch": 0.9484630805212162,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004916072898239699,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.20672965049743652,
|
|
"num_tokens": 20888392.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.329317188262939,
|
|
"epoch": 0.9488807216839291,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004915992329340493,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.19646379798650743,
|
|
"num_tokens": 20897456.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.275510454177857,
|
|
"epoch": 0.9492983628466422,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004915911722522984,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.2065662369132042,
|
|
"num_tokens": 20906621.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.363337421417237,
|
|
"epoch": 0.9497160040093552,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004915831077788583,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.20354874283075333,
|
|
"num_tokens": 20916929.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.294428920745849,
|
|
"epoch": 0.9501336451720681,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004915750395138702,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.2074909210205078,
|
|
"num_tokens": 20926028.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.304751205444336,
|
|
"epoch": 0.9505512863347811,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004915669674574754,
|
|
"loss": 5.0492,
|
|
"mean_token_accuracy": 0.19772983491420745,
|
|
"num_tokens": 20935516.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.213559579849243,
|
|
"epoch": 0.9509689274974942,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004915588916098151,
|
|
"loss": 4.8551,
|
|
"mean_token_accuracy": 0.21815962493419647,
|
|
"num_tokens": 20944100.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.236780166625977,
|
|
"epoch": 0.9513865686602071,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004915508119710307,
|
|
"loss": 4.9961,
|
|
"mean_token_accuracy": 0.20491190254688263,
|
|
"num_tokens": 20953733.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.310271406173706,
|
|
"epoch": 0.9518042098229201,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004915427285412636,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.19966332167387008,
|
|
"num_tokens": 20962413.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.187750720977784,
|
|
"epoch": 0.9522218509856332,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004915346413206555,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.21946113258600236,
|
|
"num_tokens": 20971172.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.199890232086181,
|
|
"epoch": 0.9526394921483461,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004915265503093478,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.22010363638401031,
|
|
"num_tokens": 20979450.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.193245697021484,
|
|
"epoch": 0.9530571333110591,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004915184555074824,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.20616060942411424,
|
|
"num_tokens": 20988518.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.354827547073365,
|
|
"epoch": 0.9534747744737722,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004915103569152005,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.19906944185495376,
|
|
"num_tokens": 20998721.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.325136947631836,
|
|
"epoch": 0.9538924156364851,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004915022545326444,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.21161193698644637,
|
|
"num_tokens": 21008007.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.269908237457275,
|
|
"epoch": 0.9543100567991981,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004914941483599558,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.2049628645181656,
|
|
"num_tokens": 21017199.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.170241498947144,
|
|
"epoch": 0.9547276979619111,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004914860383972763,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.21301472038030625,
|
|
"num_tokens": 21025571.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.27745041847229,
|
|
"epoch": 0.9551453391246241,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004914779246447483,
|
|
"loss": 4.9631,
|
|
"mean_token_accuracy": 0.20924217253923416,
|
|
"num_tokens": 21035040.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.261585855484009,
|
|
"epoch": 0.9555629802873371,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004914698071025136,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.21184210777282714,
|
|
"num_tokens": 21044018.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.188579988479614,
|
|
"epoch": 0.9559806214500501,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004914616857707143,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.21313706487417222,
|
|
"num_tokens": 21052489.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.250027894973755,
|
|
"epoch": 0.9563982626127631,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004914535606494927,
|
|
"loss": 4.9595,
|
|
"mean_token_accuracy": 0.21554958522319795,
|
|
"num_tokens": 21061153.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.197196674346924,
|
|
"epoch": 0.9568159037754761,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000491445431738991,
|
|
"loss": 4.8586,
|
|
"mean_token_accuracy": 0.2168806940317154,
|
|
"num_tokens": 21069671.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.364026594161987,
|
|
"epoch": 0.9572335449381891,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004914372990393515,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.2001868963241577,
|
|
"num_tokens": 21079339.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.244997596740722,
|
|
"epoch": 0.957651186100902,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004914291625507164,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.21217142343521117,
|
|
"num_tokens": 21087868.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.23007173538208,
|
|
"epoch": 0.9580688272636151,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004914210222732284,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.21253537386655807,
|
|
"num_tokens": 21096258.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.223325109481811,
|
|
"epoch": 0.9584864684263281,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004914128782070299,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.20620037019252777,
|
|
"num_tokens": 21104504.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.237201976776123,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004914047303522636,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.21205006837844848,
|
|
"num_tokens": 21114402.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.241027069091797,
|
|
"epoch": 0.9593217507517541,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004913965787090718,
|
|
"loss": 4.9324,
|
|
"mean_token_accuracy": 0.21317453384399415,
|
|
"num_tokens": 21123572.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.3358031749725345,
|
|
"epoch": 0.9597393919144671,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004913884232775974,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.18839406073093415,
|
|
"num_tokens": 21132385.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.1815544128417965,
|
|
"epoch": 0.96015703307718,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913802640579833,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.21900732368230819,
|
|
"num_tokens": 21140383.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.26951961517334,
|
|
"epoch": 0.9605746742398931,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004913721010503722,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.20764800161123276,
|
|
"num_tokens": 21149793.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.265140676498413,
|
|
"epoch": 0.9609923154026061,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000491363934254907,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.2045946329832077,
|
|
"num_tokens": 21158955.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.307435989379883,
|
|
"epoch": 0.961409956565319,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004913557636717307,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.20109861642122268,
|
|
"num_tokens": 21167900.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.210939741134643,
|
|
"epoch": 0.9618275977280321,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004913475893009864,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.21275007873773574,
|
|
"num_tokens": 21177243.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.25946192741394,
|
|
"epoch": 0.9622452388907451,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000491339411142817,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.20528562366962433,
|
|
"num_tokens": 21186118.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.256955099105835,
|
|
"epoch": 0.962662880053458,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004913312291973659,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.2076512947678566,
|
|
"num_tokens": 21195032.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.246916007995606,
|
|
"epoch": 0.963080521216171,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004913230434647762,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.20421538203954698,
|
|
"num_tokens": 21205388.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.21542501449585,
|
|
"epoch": 0.9634981623788841,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004913148539451912,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.21418605744838715,
|
|
"num_tokens": 21215181.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.144198656082153,
|
|
"epoch": 0.963915803541597,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004913066606387544,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.2182680130004883,
|
|
"num_tokens": 21223668.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.2277195930480955,
|
|
"epoch": 0.96433344470431,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000491298463545609,
|
|
"loss": 4.9138,
|
|
"mean_token_accuracy": 0.20792694985866547,
|
|
"num_tokens": 21232448.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.175724840164184,
|
|
"epoch": 0.9647510858670231,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004912902626658988,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.20924461632966995,
|
|
"num_tokens": 21240777.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.259989404678345,
|
|
"epoch": 0.965168727029736,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004912820579997672,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.2013513833284378,
|
|
"num_tokens": 21248803.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.313172817230225,
|
|
"epoch": 0.965586368192449,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004912738495473577,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.205942040681839,
|
|
"num_tokens": 21257861.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.261660194396972,
|
|
"epoch": 0.9660040093551621,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004912656373088142,
|
|
"loss": 4.8983,
|
|
"mean_token_accuracy": 0.21377579122781754,
|
|
"num_tokens": 21267140.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.259865856170654,
|
|
"epoch": 0.9664216505178751,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004912574212842804,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.2053929090499878,
|
|
"num_tokens": 21276313.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.19338698387146,
|
|
"epoch": 0.966839291680588,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004912492014739001,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.20924219042062758,
|
|
"num_tokens": 21286156.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.296078443527222,
|
|
"epoch": 0.967256932843301,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004912409778778173,
|
|
"loss": 5.0012,
|
|
"mean_token_accuracy": 0.21322192400693893,
|
|
"num_tokens": 21295420.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.3498866081237795,
|
|
"epoch": 0.9676745740060141,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004912327504961758,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.1908525660634041,
|
|
"num_tokens": 21306292.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.283988380432129,
|
|
"epoch": 0.968092215168727,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004912245193291198,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.2055877387523651,
|
|
"num_tokens": 21315165.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.271773815155029,
|
|
"epoch": 0.96850985633144,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004912162843767932,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.20729406774044037,
|
|
"num_tokens": 21324608.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.260155487060547,
|
|
"epoch": 0.9689274974941531,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004912080456393404,
|
|
"loss": 4.9257,
|
|
"mean_token_accuracy": 0.20998802781105042,
|
|
"num_tokens": 21333609.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.328645420074463,
|
|
"epoch": 0.969345138656866,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004911998031169056,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.19846827983856202,
|
|
"num_tokens": 21344397.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.320654630661011,
|
|
"epoch": 0.969762779819579,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004911915568096328,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.1986811563372612,
|
|
"num_tokens": 21354111.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.155001592636109,
|
|
"epoch": 0.9701804209822921,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004911833067176666,
|
|
"loss": 4.8383,
|
|
"mean_token_accuracy": 0.21193551123142243,
|
|
"num_tokens": 21362807.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.311326169967652,
|
|
"epoch": 0.970598062145005,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004911750528411515,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.20339540988206864,
|
|
"num_tokens": 21372609.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.222001552581787,
|
|
"epoch": 0.971015703307718,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004911667951802318,
|
|
"loss": 4.9452,
|
|
"mean_token_accuracy": 0.20612942427396774,
|
|
"num_tokens": 21381182.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.267542600631714,
|
|
"epoch": 0.9714333444704311,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004911585337350524,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.21081383973360063,
|
|
"num_tokens": 21389930.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.292898559570313,
|
|
"epoch": 0.971850985633144,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004911502685057573,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.20550652146339415,
|
|
"num_tokens": 21399315.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.257982683181763,
|
|
"epoch": 0.972268626795857,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004911419994924918,
|
|
"loss": 5.0047,
|
|
"mean_token_accuracy": 0.20879339277744294,
|
|
"num_tokens": 21408857.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.311028099060058,
|
|
"epoch": 0.97268626795857,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004911337266954004,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.20657797902822495,
|
|
"num_tokens": 21417452.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.224212312698365,
|
|
"epoch": 0.973103909121283,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004911254501146279,
|
|
"loss": 4.9614,
|
|
"mean_token_accuracy": 0.20963917821645736,
|
|
"num_tokens": 21427315.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.244308662414551,
|
|
"epoch": 0.973521550283996,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004911171697503193,
|
|
"loss": 5.0195,
|
|
"mean_token_accuracy": 0.20526772886514663,
|
|
"num_tokens": 21437080.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.2551497459411625,
|
|
"epoch": 0.973939191446709,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004911088856026194,
|
|
"loss": 4.875,
|
|
"mean_token_accuracy": 0.22287640422582627,
|
|
"num_tokens": 21445421.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.248556756973267,
|
|
"epoch": 0.974356832609422,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004911005976716734,
|
|
"loss": 4.8857,
|
|
"mean_token_accuracy": 0.21865725368261338,
|
|
"num_tokens": 21454684.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.147059535980224,
|
|
"epoch": 0.974774473772135,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004910923059576264,
|
|
"loss": 4.8599,
|
|
"mean_token_accuracy": 0.2113525852560997,
|
|
"num_tokens": 21464287.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.246096563339234,
|
|
"epoch": 0.975192114934848,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004910840104606234,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.210259510576725,
|
|
"num_tokens": 21472835.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.209566497802735,
|
|
"epoch": 0.975609756097561,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004910757111808097,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.21674559116363526,
|
|
"num_tokens": 21482327.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.254481554031372,
|
|
"epoch": 0.976027397260274,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004910674081183305,
|
|
"loss": 4.986,
|
|
"mean_token_accuracy": 0.20231358855962753,
|
|
"num_tokens": 21492257.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.196622276306153,
|
|
"epoch": 0.976445038422987,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004910591012733313,
|
|
"loss": 4.9825,
|
|
"mean_token_accuracy": 0.21050516813993453,
|
|
"num_tokens": 21501930.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.31681456565857,
|
|
"epoch": 0.9768626795857,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004910507906459575,
|
|
"loss": 4.972,
|
|
"mean_token_accuracy": 0.20518902093172073,
|
|
"num_tokens": 21511924.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.277094411849975,
|
|
"epoch": 0.977280320748413,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004910424762363545,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.2062234029173851,
|
|
"num_tokens": 21522279.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.206339550018311,
|
|
"epoch": 0.977697961911126,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000491034158044668,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.20828241407871245,
|
|
"num_tokens": 21532016.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.282204341888428,
|
|
"epoch": 0.9781156030738389,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004910258360710434,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.20450843423604964,
|
|
"num_tokens": 21541952.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.2347245693206785,
|
|
"epoch": 0.978533244236552,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004910175103156266,
|
|
"loss": 4.8629,
|
|
"mean_token_accuracy": 0.2208071306347847,
|
|
"num_tokens": 21550185.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.2522307395935055,
|
|
"epoch": 0.978950885399265,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004910091807785632,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.20871129631996155,
|
|
"num_tokens": 21558891.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.229831981658935,
|
|
"epoch": 0.9793685265619779,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004910008474599991,
|
|
"loss": 4.967,
|
|
"mean_token_accuracy": 0.20676353573799133,
|
|
"num_tokens": 21568808.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.331714725494384,
|
|
"epoch": 0.979786167724691,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004909925103600801,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.20442893505096435,
|
|
"num_tokens": 21578838.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.181356525421142,
|
|
"epoch": 0.980203808887404,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004909841694789523,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.20721932202577592,
|
|
"num_tokens": 21588008.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.250650835037232,
|
|
"epoch": 0.9806214500501169,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004909758248167616,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.2122446656227112,
|
|
"num_tokens": 21597036.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.298967552185059,
|
|
"epoch": 0.98103909121283,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004909674763736542,
|
|
"loss": 4.9617,
|
|
"mean_token_accuracy": 0.20732021778821946,
|
|
"num_tokens": 21606028.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.322318601608276,
|
|
"epoch": 0.981456732375543,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004909591241497761,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.21251314729452134,
|
|
"num_tokens": 21615377.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.322495603561402,
|
|
"epoch": 0.9818743735382559,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004909507681452736,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.20028105676174163,
|
|
"num_tokens": 21625751.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.379936027526855,
|
|
"epoch": 0.9822920147009689,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004909424083602929,
|
|
"loss": 5.0464,
|
|
"mean_token_accuracy": 0.20821478664875032,
|
|
"num_tokens": 21634825.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.29578971862793,
|
|
"epoch": 0.982709655863682,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004909340447949805,
|
|
"loss": 4.906,
|
|
"mean_token_accuracy": 0.21622461974620819,
|
|
"num_tokens": 21644286.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.256733369827271,
|
|
"epoch": 0.9831272970263949,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004909256774494827,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.20455544590950012,
|
|
"num_tokens": 21653384.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.238363456726074,
|
|
"epoch": 0.9835449381891079,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000490917306323946,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.20643121898174285,
|
|
"num_tokens": 21662126.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.281286764144897,
|
|
"epoch": 0.983962579351821,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004909089314185169,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.20617246329784394,
|
|
"num_tokens": 21671940.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.211923122406006,
|
|
"epoch": 0.9843802205145339,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004909005527333421,
|
|
"loss": 4.858,
|
|
"mean_token_accuracy": 0.21985848098993302,
|
|
"num_tokens": 21680928.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.186456346511841,
|
|
"epoch": 0.9847978616772469,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004908921702685683,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.20638045072555541,
|
|
"num_tokens": 21689712.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.2519118309021,
|
|
"epoch": 0.98521550283996,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004908837840243421,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.21620728969573974,
|
|
"num_tokens": 21698325.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.213983535766602,
|
|
"epoch": 0.9856331440026729,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004908753940008105,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.21821026802062987,
|
|
"num_tokens": 21707607.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.156694746017456,
|
|
"epoch": 0.9860507851653859,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004908670001981201,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.21160940527915956,
|
|
"num_tokens": 21715887.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.244639110565186,
|
|
"epoch": 0.986468426328099,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004908586026164182,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.21405802369117738,
|
|
"num_tokens": 21724992.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.276792192459107,
|
|
"epoch": 0.9868860674908119,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004908502012558516,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.21022170335054396,
|
|
"num_tokens": 21734317.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.307264041900635,
|
|
"epoch": 0.9873037086535249,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004908417961165674,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.19987943023443222,
|
|
"num_tokens": 21743014.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.314628791809082,
|
|
"epoch": 0.9877213498162379,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004908333871987126,
|
|
"loss": 4.9473,
|
|
"mean_token_accuracy": 0.20823633074760436,
|
|
"num_tokens": 21751058.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.314991044998169,
|
|
"epoch": 0.9881389909789509,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004908249745024347,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.20536646693944932,
|
|
"num_tokens": 21760549.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.251653242111206,
|
|
"epoch": 0.9885566321416639,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000490816558027881,
|
|
"loss": 4.9477,
|
|
"mean_token_accuracy": 0.21385378986597062,
|
|
"num_tokens": 21769873.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.283232927322388,
|
|
"epoch": 0.9889742733043769,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004908081377751985,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.20937252640724183,
|
|
"num_tokens": 21779036.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.362845468521118,
|
|
"epoch": 0.9893919144670899,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004907997137445347,
|
|
"loss": 5.0416,
|
|
"mean_token_accuracy": 0.19741031527519226,
|
|
"num_tokens": 21787671.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.304118728637695,
|
|
"epoch": 0.9898095556298029,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004907912859360373,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.20538109987974168,
|
|
"num_tokens": 21797269.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.352012348175049,
|
|
"epoch": 0.9902271967925159,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004907828543498536,
|
|
"loss": 5.0482,
|
|
"mean_token_accuracy": 0.20298876464366913,
|
|
"num_tokens": 21806738.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.2701146602630615,
|
|
"epoch": 0.9906448379552288,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004907744189861313,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.21473019272089006,
|
|
"num_tokens": 21815612.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.256022930145264,
|
|
"epoch": 0.9910624791179419,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000490765979845018,
|
|
"loss": 4.9691,
|
|
"mean_token_accuracy": 0.21128876656293868,
|
|
"num_tokens": 21824222.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.287555313110351,
|
|
"epoch": 0.9914801202806549,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004907575369266617,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.21175474375486375,
|
|
"num_tokens": 21833929.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.279915189743042,
|
|
"epoch": 0.9918977614433678,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004907490902312099,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.20772093534469604,
|
|
"num_tokens": 21843261.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.31715145111084,
|
|
"epoch": 0.9923154026060809,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004907406397588106,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.2012326180934906,
|
|
"num_tokens": 21853004.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.292102956771851,
|
|
"epoch": 0.9927330437687939,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004907321855096117,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.20694056302309036,
|
|
"num_tokens": 21862628.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.201880025863647,
|
|
"epoch": 0.9931506849315068,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004907237274837613,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.21111992746591568,
|
|
"num_tokens": 21872041.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.257568216323852,
|
|
"epoch": 0.9935683260942199,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004907152656814072,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.20352355688810347,
|
|
"num_tokens": 21881834.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.377972173690796,
|
|
"epoch": 0.9939859672569329,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004907068001026978,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.20234731137752532,
|
|
"num_tokens": 21892349.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.330263328552246,
|
|
"epoch": 0.9944036084196458,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004906983307477813,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.21077365279197693,
|
|
"num_tokens": 21901427.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.24789023399353,
|
|
"epoch": 0.9948212495823588,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004906898576168057,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.2096038892865181,
|
|
"num_tokens": 21910654.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.151152563095093,
|
|
"epoch": 0.9952388907450719,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004906813807099197,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.21697333604097366,
|
|
"num_tokens": 21919583.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.144541549682617,
|
|
"epoch": 0.9956565319077848,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004906729000272714,
|
|
"loss": 4.84,
|
|
"mean_token_accuracy": 0.2203632116317749,
|
|
"num_tokens": 21927843.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.249289846420288,
|
|
"epoch": 0.9960741730704978,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004906644155690095,
|
|
"loss": 4.9202,
|
|
"mean_token_accuracy": 0.21024616807699203,
|
|
"num_tokens": 21937269.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.37962532043457,
|
|
"epoch": 0.9964918142332109,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004906559273352823,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.20636256784200668,
|
|
"num_tokens": 21946965.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.296957778930664,
|
|
"epoch": 0.9969094553959238,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004906474353262386,
|
|
"loss": 4.9392,
|
|
"mean_token_accuracy": 0.20794398635625838,
|
|
"num_tokens": 21955957.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.209753799438476,
|
|
"epoch": 0.9973270965586368,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004906389395420269,
|
|
"loss": 4.8824,
|
|
"mean_token_accuracy": 0.21355696767568588,
|
|
"num_tokens": 21965643.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.256015205383301,
|
|
"epoch": 0.9977447377213499,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000490630439982796,
|
|
"loss": 4.9547,
|
|
"mean_token_accuracy": 0.21004107743501663,
|
|
"num_tokens": 21974789.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.209260606765747,
|
|
"epoch": 0.9981623788840628,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004906219366486947,
|
|
"loss": 4.8532,
|
|
"mean_token_accuracy": 0.21987275779247284,
|
|
"num_tokens": 21983411.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.309891605377198,
|
|
"epoch": 0.9985800200467758,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004906134295398719,
|
|
"loss": 4.9548,
|
|
"mean_token_accuracy": 0.20860873758792878,
|
|
"num_tokens": 21992570.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.149970579147339,
|
|
"epoch": 0.9989976612094889,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004906049186564764,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.22459676414728164,
|
|
"num_tokens": 22001411.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.373264646530151,
|
|
"epoch": 0.9994153023722018,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004905964039986574,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.19684274941682817,
|
|
"num_tokens": 22010882.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.329038190841675,
|
|
"epoch": 0.9998329435349148,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004905878855665637,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.20282467752695083,
|
|
"num_tokens": 22020885.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.266513252258301,
|
|
"epoch": 1.0002505846976277,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004905793633603446,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.21747443228960037,
|
|
"num_tokens": 22030278.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.321501159667969,
|
|
"epoch": 1.0006682258603408,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004905708373801492,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.20348309576511384,
|
|
"num_tokens": 22039601.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.230185842514038,
|
|
"epoch": 1.0010858670230538,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004905623076261269,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.2150204911828041,
|
|
"num_tokens": 22049158.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.2984694480896,
|
|
"epoch": 1.0015035081857668,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000490553774098427,
|
|
"loss": 4.9523,
|
|
"mean_token_accuracy": 0.19978320747613906,
|
|
"num_tokens": 22059278.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.3364222049713135,
|
|
"epoch": 1.0019211493484799,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004905452367971986,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.2111041158437729,
|
|
"num_tokens": 22068415.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.301036405563354,
|
|
"epoch": 1.0023387905111927,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004905366957225916,
|
|
"loss": 4.8894,
|
|
"mean_token_accuracy": 0.2096370205283165,
|
|
"num_tokens": 22077815.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0023387905111927,
|
|
"eval_entropy": 4.965815823503885,
|
|
"eval_loss": 4.902433395385742,
|
|
"eval_mean_token_accuracy": 0.22218906617763057,
|
|
"eval_num_tokens": 22077815.0,
|
|
"eval_runtime": 20.7745,
|
|
"eval_samples_per_second": 1817.753,
|
|
"eval_steps_per_second": 227.249,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.303226900100708,
|
|
"epoch": 1.0027564316739057,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004905281508747552,
|
|
"loss": 4.9671,
|
|
"mean_token_accuracy": 0.20342456698417663,
|
|
"num_tokens": 22087606.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.226786375045776,
|
|
"epoch": 1.0031740728366187,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004905196022538391,
|
|
"loss": 4.7974,
|
|
"mean_token_accuracy": 0.2188867673277855,
|
|
"num_tokens": 22096300.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.356914520263672,
|
|
"epoch": 1.0035917139993318,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000490511049859993,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.21059678941965104,
|
|
"num_tokens": 22105750.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.368550205230713,
|
|
"epoch": 1.0040093551620448,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004905024936933664,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.21047618240118027,
|
|
"num_tokens": 22115163.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.338752269744873,
|
|
"epoch": 1.0044269963247578,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004904939337541093,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.2094682902097702,
|
|
"num_tokens": 22125580.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.173619413375855,
|
|
"epoch": 1.0048446374874707,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004904853700423716,
|
|
"loss": 4.8301,
|
|
"mean_token_accuracy": 0.22426499873399736,
|
|
"num_tokens": 22134985.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.284524726867676,
|
|
"epoch": 1.0052622786501837,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004904768025583031,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.21809403896331786,
|
|
"num_tokens": 22142530.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.273666286468506,
|
|
"epoch": 1.0056799198128967,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004904682313020537,
|
|
"loss": 4.9269,
|
|
"mean_token_accuracy": 0.21893782019615174,
|
|
"num_tokens": 22151696.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.23625373840332,
|
|
"epoch": 1.0060975609756098,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004904596562737737,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.2138594776391983,
|
|
"num_tokens": 22161286.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.260410499572754,
|
|
"epoch": 1.0065152021383228,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000490451077473613,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.2189845100045204,
|
|
"num_tokens": 22169678.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.2340696334838865,
|
|
"epoch": 1.0069328433010358,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004904424949017218,
|
|
"loss": 4.8898,
|
|
"mean_token_accuracy": 0.22822704017162324,
|
|
"num_tokens": 22178618.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.198746252059936,
|
|
"epoch": 1.0073504844637486,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004904339085582504,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.21217740327119827,
|
|
"num_tokens": 22187574.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.325077199935913,
|
|
"epoch": 1.0077681256264617,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004904253184433491,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.20161740481853485,
|
|
"num_tokens": 22198840.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.249087381362915,
|
|
"epoch": 1.0081857667891747,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004904167245571684,
|
|
"loss": 4.8222,
|
|
"mean_token_accuracy": 0.22452458888292312,
|
|
"num_tokens": 22207166.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.231739139556884,
|
|
"epoch": 1.0086034079518877,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004904081268998586,
|
|
"loss": 4.8505,
|
|
"mean_token_accuracy": 0.20791447013616562,
|
|
"num_tokens": 22216232.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.279721784591675,
|
|
"epoch": 1.0090210491146008,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004903995254715702,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.21342765390872956,
|
|
"num_tokens": 22224853.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.204632043838501,
|
|
"epoch": 1.0094386902773138,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004903909202724539,
|
|
"loss": 4.8321,
|
|
"mean_token_accuracy": 0.2166557639837265,
|
|
"num_tokens": 22233971.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.180267381668091,
|
|
"epoch": 1.0098563314400266,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004903823113026602,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.22446223646402358,
|
|
"num_tokens": 22242548.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.14296145439148,
|
|
"epoch": 1.0102739726027397,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049037369856234,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.2271137535572052,
|
|
"num_tokens": 22251086.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.268225574493409,
|
|
"epoch": 1.0106916137654527,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004903650820516438,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.20856316536664962,
|
|
"num_tokens": 22260035.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.292072868347168,
|
|
"epoch": 1.0111092549281657,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004903564617707227,
|
|
"loss": 4.8248,
|
|
"mean_token_accuracy": 0.2224615290760994,
|
|
"num_tokens": 22269134.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.256594181060791,
|
|
"epoch": 1.0115268960908788,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004903478377197275,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.21892376244068146,
|
|
"num_tokens": 22278123.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.2195079803466795,
|
|
"epoch": 1.0119445372535918,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004903392098988092,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.21010321676731109,
|
|
"num_tokens": 22287557.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.255034875869751,
|
|
"epoch": 1.0123621784163046,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004903305783081188,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.21760648339986802,
|
|
"num_tokens": 22296705.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.2143120765686035,
|
|
"epoch": 1.0127798195790176,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004903219429478075,
|
|
"loss": 4.8267,
|
|
"mean_token_accuracy": 0.2192690461874008,
|
|
"num_tokens": 22305904.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.228439855575561,
|
|
"epoch": 1.0131974607417307,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004903133038180263,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.2163556545972824,
|
|
"num_tokens": 22315051.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.222309589385986,
|
|
"epoch": 1.0136151019044437,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004903046609189266,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.21598743498325348,
|
|
"num_tokens": 22324469.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.343123245239258,
|
|
"epoch": 1.0140327430671567,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004902960142506597,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.20847066193819047,
|
|
"num_tokens": 22334407.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.375848913192749,
|
|
"epoch": 1.0144503842298698,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004902873638133768,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.2062999814748764,
|
|
"num_tokens": 22342975.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.21583251953125,
|
|
"epoch": 1.0148680253925826,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004902787096072296,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.21695789247751235,
|
|
"num_tokens": 22351649.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.251254653930664,
|
|
"epoch": 1.0152856665552956,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004902700516323693,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.21128410398960112,
|
|
"num_tokens": 22361956.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.2743712902069095,
|
|
"epoch": 1.0157033077180087,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004902613898889477,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.20540902465581895,
|
|
"num_tokens": 22372354.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.215880632400513,
|
|
"epoch": 1.0161209488807217,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004902527243771164,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.21881221383810043,
|
|
"num_tokens": 22381225.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.145952367782593,
|
|
"epoch": 1.0165385900434347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000490244055097027,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.22199922651052476,
|
|
"num_tokens": 22390666.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.226683521270752,
|
|
"epoch": 1.0169562312061478,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004902353820488314,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.22460553795099258,
|
|
"num_tokens": 22399528.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.23760142326355,
|
|
"epoch": 1.0173738723688606,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004902267052326812,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.22610697746276856,
|
|
"num_tokens": 22408827.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.194698858261108,
|
|
"epoch": 1.0177915135315736,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004902180246487285,
|
|
"loss": 4.8275,
|
|
"mean_token_accuracy": 0.21363172978162764,
|
|
"num_tokens": 22418098.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.1333168029785154,
|
|
"epoch": 1.0182091546942866,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004902093402971254,
|
|
"loss": 4.7161,
|
|
"mean_token_accuracy": 0.22548915892839433,
|
|
"num_tokens": 22427417.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.220947170257569,
|
|
"epoch": 1.0186267958569997,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004902006521780236,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.20760053992271424,
|
|
"num_tokens": 22436938.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.244035720825195,
|
|
"epoch": 1.0190444370197127,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004901919602915754,
|
|
"loss": 4.9399,
|
|
"mean_token_accuracy": 0.20598081052303313,
|
|
"num_tokens": 22447361.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.342454624176026,
|
|
"epoch": 1.0194620781824257,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004901832646379328,
|
|
"loss": 4.9687,
|
|
"mean_token_accuracy": 0.2058907076716423,
|
|
"num_tokens": 22457431.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.285581636428833,
|
|
"epoch": 1.0198797193451385,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004901745652172483,
|
|
"loss": 4.9348,
|
|
"mean_token_accuracy": 0.21030229330062866,
|
|
"num_tokens": 22466219.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.27685022354126,
|
|
"epoch": 1.0202973605078516,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000490165862029674,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.20924250185489654,
|
|
"num_tokens": 22476231.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.237607049942016,
|
|
"epoch": 1.0207150016705646,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004901571550753622,
|
|
"loss": 4.7555,
|
|
"mean_token_accuracy": 0.2266775533556938,
|
|
"num_tokens": 22484288.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.250530767440796,
|
|
"epoch": 1.0211326428332776,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004901484443544655,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.2209512010216713,
|
|
"num_tokens": 22493619.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.19850344657898,
|
|
"epoch": 1.0215502839959907,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004901397298671362,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.22263919115066527,
|
|
"num_tokens": 22501606.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.246945571899414,
|
|
"epoch": 1.0219679251587037,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004901310116135271,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.2104639783501625,
|
|
"num_tokens": 22510410.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.253802108764648,
|
|
"epoch": 1.0223855663214167,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004901222895937905,
|
|
"loss": 4.9071,
|
|
"mean_token_accuracy": 0.22030350118875502,
|
|
"num_tokens": 22518796.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.223279905319214,
|
|
"epoch": 1.0228032074841296,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004901135638080796,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.2178732842206955,
|
|
"num_tokens": 22527532.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.216985511779785,
|
|
"epoch": 1.0232208486468426,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004901048342565465,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.21073698550462722,
|
|
"num_tokens": 22536882.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.193503141403198,
|
|
"epoch": 1.0236384898095556,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004900961009393445,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.21342957019805908,
|
|
"num_tokens": 22545549.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.2669741153717045,
|
|
"epoch": 1.0240561309722687,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004900873638566263,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.2066861480474472,
|
|
"num_tokens": 22554941.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.195732545852661,
|
|
"epoch": 1.0244737721349817,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000490078623008545,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.2140896812081337,
|
|
"num_tokens": 22565159.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.200196409225464,
|
|
"epoch": 1.0248914132976945,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004900698783952533,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.22105319947004318,
|
|
"num_tokens": 22574184.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.220670413970947,
|
|
"epoch": 1.0253090544604075,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004900611300169048,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.21008820831775665,
|
|
"num_tokens": 22584062.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.272613859176635,
|
|
"epoch": 1.0257266956231206,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004900523778736521,
|
|
"loss": 4.8491,
|
|
"mean_token_accuracy": 0.21551709324121476,
|
|
"num_tokens": 22592845.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.2538573265075685,
|
|
"epoch": 1.0261443367858336,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004900436219656488,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.20796047300100326,
|
|
"num_tokens": 22602750.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.224932050704956,
|
|
"epoch": 1.0265619779485466,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000490034862293048,
|
|
"loss": 4.8802,
|
|
"mean_token_accuracy": 0.21285858154296874,
|
|
"num_tokens": 22611788.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.234642219543457,
|
|
"epoch": 1.0269796191112597,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004900260988560031,
|
|
"loss": 4.812,
|
|
"mean_token_accuracy": 0.21548476219177246,
|
|
"num_tokens": 22620234.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.144550418853759,
|
|
"epoch": 1.0273972602739727,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004900173316546675,
|
|
"loss": 4.7503,
|
|
"mean_token_accuracy": 0.22607030719518661,
|
|
"num_tokens": 22629155.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.288060426712036,
|
|
"epoch": 1.0278149014366855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004900085606891947,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.20788461714982986,
|
|
"num_tokens": 22638647.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.267986679077149,
|
|
"epoch": 1.0282325425993986,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004899997859597382,
|
|
"loss": 4.8812,
|
|
"mean_token_accuracy": 0.20709498077630997,
|
|
"num_tokens": 22648295.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.212376451492309,
|
|
"epoch": 1.0286501837621116,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004899910074664518,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.2136357009410858,
|
|
"num_tokens": 22657342.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.195553779602051,
|
|
"epoch": 1.0290678249248246,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004899822252094889,
|
|
"loss": 4.8181,
|
|
"mean_token_accuracy": 0.21486542075872422,
|
|
"num_tokens": 22665230.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.187868642807007,
|
|
"epoch": 1.0294854660875377,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004899734391890034,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.21881980448961258,
|
|
"num_tokens": 22674385.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.153425979614258,
|
|
"epoch": 1.0299031072502507,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004899646494051491,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.23175030946731567,
|
|
"num_tokens": 22683493.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.2316196918487545,
|
|
"epoch": 1.0303207484129635,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004899558558580798,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.21134551018476486,
|
|
"num_tokens": 22691878.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.183561134338379,
|
|
"epoch": 1.0307383895756765,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004899470585479495,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.2121802508831024,
|
|
"num_tokens": 22700112.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.230071401596069,
|
|
"epoch": 1.0311560307383896,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004899382574749124,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.2159165248274803,
|
|
"num_tokens": 22709218.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.240807580947876,
|
|
"epoch": 1.0315736719011026,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004899294526391221,
|
|
"loss": 4.8524,
|
|
"mean_token_accuracy": 0.21802583783864976,
|
|
"num_tokens": 22718423.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.2064775943756105,
|
|
"epoch": 1.0319913130638156,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004899206440407332,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.20433194786310196,
|
|
"num_tokens": 22727333.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.248548793792724,
|
|
"epoch": 1.0324089542265287,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004899118316798996,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.2147328346967697,
|
|
"num_tokens": 22737248.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.220589923858642,
|
|
"epoch": 1.0328265953892415,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004899030155567759,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.21049937903881072,
|
|
"num_tokens": 22747515.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.302844285964966,
|
|
"epoch": 1.0332442365519545,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000489894195671516,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.21734669655561448,
|
|
"num_tokens": 22756670.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.275622129440308,
|
|
"epoch": 1.0336618777146676,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004898853720242747,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.20328406989574432,
|
|
"num_tokens": 22766332.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.268140125274658,
|
|
"epoch": 1.0340795188773806,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004898765446152062,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.2166372463107109,
|
|
"num_tokens": 22774999.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.229842472076416,
|
|
"epoch": 1.0344971600400936,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004898677134444652,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.21339935809373856,
|
|
"num_tokens": 22784578.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.236107015609742,
|
|
"epoch": 1.0349148012028067,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004898588785122063,
|
|
"loss": 4.8658,
|
|
"mean_token_accuracy": 0.21692902147769927,
|
|
"num_tokens": 22794508.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.28031325340271,
|
|
"epoch": 1.0353324423655195,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004898500398185841,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.20784918069839478,
|
|
"num_tokens": 22804399.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.284021615982056,
|
|
"epoch": 1.0357500835282325,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004898411973637532,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.2101735606789589,
|
|
"num_tokens": 22814361.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.158568954467773,
|
|
"epoch": 1.0361677246909455,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004898323511478686,
|
|
"loss": 4.7996,
|
|
"mean_token_accuracy": 0.22410439550876618,
|
|
"num_tokens": 22823780.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.16712212562561,
|
|
"epoch": 1.0365853658536586,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004898235011710851,
|
|
"loss": 4.8096,
|
|
"mean_token_accuracy": 0.20864272266626357,
|
|
"num_tokens": 22832575.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.116033029556275,
|
|
"epoch": 1.0370030070163716,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004898146474335577,
|
|
"loss": 4.6768,
|
|
"mean_token_accuracy": 0.22577485591173171,
|
|
"num_tokens": 22841822.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.3240140914917,
|
|
"epoch": 1.0374206481790846,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004898057899354412,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.20677891075611116,
|
|
"num_tokens": 22851835.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.2146642208099365,
|
|
"epoch": 1.0378382893417974,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000489796928676891,
|
|
"loss": 4.8577,
|
|
"mean_token_accuracy": 0.212488853931427,
|
|
"num_tokens": 22861025.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.194211721420288,
|
|
"epoch": 1.0382559305045105,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004897880636580618,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.20952626764774324,
|
|
"num_tokens": 22869721.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.225072956085205,
|
|
"epoch": 1.0386735716672235,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000489779194879109,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.22638733834028243,
|
|
"num_tokens": 22878225.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.294962596893311,
|
|
"epoch": 1.0390912128299366,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000489770322340188,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.20481373518705367,
|
|
"num_tokens": 22888598.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.230847978591919,
|
|
"epoch": 1.0395088539926496,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004897614460414539,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.20875990986824036,
|
|
"num_tokens": 22897326.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.218255710601807,
|
|
"epoch": 1.0399264951553626,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004897525659830623,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.21220337450504304,
|
|
"num_tokens": 22906372.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.139008951187134,
|
|
"epoch": 1.0403441363180754,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004897436821651683,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.22020286768674852,
|
|
"num_tokens": 22915987.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.235173273086548,
|
|
"epoch": 1.0407617774807885,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004897347945879278,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.21541378200054168,
|
|
"num_tokens": 22926118.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.251816701889038,
|
|
"epoch": 1.0411794186435015,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004897259032514963,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.21668784320354462,
|
|
"num_tokens": 22934813.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.292257070541382,
|
|
"epoch": 1.0415970598062145,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004897170081560292,
|
|
"loss": 4.9492,
|
|
"mean_token_accuracy": 0.20914019048213958,
|
|
"num_tokens": 22944579.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.161676645278931,
|
|
"epoch": 1.0420147009689276,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004897081093016827,
|
|
"loss": 4.7778,
|
|
"mean_token_accuracy": 0.22160271555185318,
|
|
"num_tokens": 22953515.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.272727394104004,
|
|
"epoch": 1.0424323421316406,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004896992066886121,
|
|
"loss": 4.9221,
|
|
"mean_token_accuracy": 0.20415965020656585,
|
|
"num_tokens": 22962599.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.2651573657989506,
|
|
"epoch": 1.0428499832943534,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004896903003169735,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.22134290039539337,
|
|
"num_tokens": 22971717.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.129202747344971,
|
|
"epoch": 1.0432676244570664,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004896813901869229,
|
|
"loss": 4.6866,
|
|
"mean_token_accuracy": 0.2221896842122078,
|
|
"num_tokens": 22980587.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.242172527313232,
|
|
"epoch": 1.0436852656197795,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004896724762986159,
|
|
"loss": 4.8641,
|
|
"mean_token_accuracy": 0.22232221066951752,
|
|
"num_tokens": 22990197.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.229210901260376,
|
|
"epoch": 1.0441029067824925,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004896635586522089,
|
|
"loss": 4.9377,
|
|
"mean_token_accuracy": 0.21098632365465164,
|
|
"num_tokens": 22999670.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.282371187210083,
|
|
"epoch": 1.0445205479452055,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004896546372478581,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.21877632439136505,
|
|
"num_tokens": 23008125.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.175100612640381,
|
|
"epoch": 1.0449381891079186,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004896457120857192,
|
|
"loss": 4.7287,
|
|
"mean_token_accuracy": 0.2224934756755829,
|
|
"num_tokens": 23017469.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.148062801361084,
|
|
"epoch": 1.0453558302706314,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000489636783165949,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.21109567284584047,
|
|
"num_tokens": 23026468.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.271733283996582,
|
|
"epoch": 1.0457734714333444,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004896278504887033,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.2173850268125534,
|
|
"num_tokens": 23034944.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.157717323303222,
|
|
"epoch": 1.0461911125960575,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000489618914054139,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.22263168245553971,
|
|
"num_tokens": 23043834.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.189675569534302,
|
|
"epoch": 1.0466087537587705,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000489609973862412,
|
|
"loss": 4.8322,
|
|
"mean_token_accuracy": 0.21560015827417373,
|
|
"num_tokens": 23052542.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.3103477478027346,
|
|
"epoch": 1.0470263949214835,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004896010299136793,
|
|
"loss": 4.88,
|
|
"mean_token_accuracy": 0.22052811980247497,
|
|
"num_tokens": 23061438.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.306296062469483,
|
|
"epoch": 1.0474440360841966,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004895920822080972,
|
|
"loss": 5.006,
|
|
"mean_token_accuracy": 0.20380628407001494,
|
|
"num_tokens": 23071777.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.276973581314087,
|
|
"epoch": 1.0478616772469094,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004895831307458224,
|
|
"loss": 4.8342,
|
|
"mean_token_accuracy": 0.21723357439041138,
|
|
"num_tokens": 23080889.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.198975849151611,
|
|
"epoch": 1.0482793184096224,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004895741755270115,
|
|
"loss": 4.7565,
|
|
"mean_token_accuracy": 0.22187688946723938,
|
|
"num_tokens": 23089737.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.216781520843506,
|
|
"epoch": 1.0486969595723354,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004895652165518215,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.22120230346918107,
|
|
"num_tokens": 23098861.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.229921865463257,
|
|
"epoch": 1.0491146007350485,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004895562538204091,
|
|
"loss": 4.9359,
|
|
"mean_token_accuracy": 0.21338330954313278,
|
|
"num_tokens": 23107798.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.225877571105957,
|
|
"epoch": 1.0495322418977615,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004895472873329311,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.22304095774888993,
|
|
"num_tokens": 23116698.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.302195358276367,
|
|
"epoch": 1.0499498830604745,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004895383170895447,
|
|
"loss": 4.9335,
|
|
"mean_token_accuracy": 0.20603199303150177,
|
|
"num_tokens": 23125880.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.317913007736206,
|
|
"epoch": 1.0503675242231874,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004895293430904067,
|
|
"loss": 4.9576,
|
|
"mean_token_accuracy": 0.2114333152770996,
|
|
"num_tokens": 23135633.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.187646484375,
|
|
"epoch": 1.0507851653859004,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004895203653356745,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.22155859917402268,
|
|
"num_tokens": 23144952.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.173389720916748,
|
|
"epoch": 1.0512028065486134,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004895113838255049,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.2190578743815422,
|
|
"num_tokens": 23154128.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.161665630340576,
|
|
"epoch": 1.0516204477113265,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004895023985600555,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.2294712945818901,
|
|
"num_tokens": 23162579.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.214745712280274,
|
|
"epoch": 1.0520380888740395,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004894934095394832,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.21518432348966599,
|
|
"num_tokens": 23171889.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.12669529914856,
|
|
"epoch": 1.0524557300367525,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004894844167639458,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.2251098409295082,
|
|
"num_tokens": 23180876.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.17280387878418,
|
|
"epoch": 1.0528733711994653,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004894754202336004,
|
|
"loss": 4.7706,
|
|
"mean_token_accuracy": 0.22653575837612153,
|
|
"num_tokens": 23189567.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.313782215118408,
|
|
"epoch": 1.0532910123621784,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004894664199486047,
|
|
"loss": 4.7796,
|
|
"mean_token_accuracy": 0.22133691012859344,
|
|
"num_tokens": 23198142.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.253270292282105,
|
|
"epoch": 1.0537086535248914,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004894574159091161,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.20770644694566726,
|
|
"num_tokens": 23207143.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.280078792572022,
|
|
"epoch": 1.0541262946876044,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004894484081152922,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.21874524056911468,
|
|
"num_tokens": 23215637.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.2663270950317385,
|
|
"epoch": 1.0545439358503175,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004894393965672909,
|
|
"loss": 4.8593,
|
|
"mean_token_accuracy": 0.20948199629783631,
|
|
"num_tokens": 23224402.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.368009424209594,
|
|
"epoch": 1.0549615770130305,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004894303812652698,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.20247316360473633,
|
|
"num_tokens": 23232669.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.137831592559815,
|
|
"epoch": 1.0553792181757433,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004894213622093867,
|
|
"loss": 4.8297,
|
|
"mean_token_accuracy": 0.215559920668602,
|
|
"num_tokens": 23242204.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.25097622871399,
|
|
"epoch": 1.0557968593384564,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004894123393997997,
|
|
"loss": 4.8708,
|
|
"mean_token_accuracy": 0.2124776914715767,
|
|
"num_tokens": 23250765.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.212322664260864,
|
|
"epoch": 1.0562145005011694,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004894033128366665,
|
|
"loss": 4.7845,
|
|
"mean_token_accuracy": 0.21550067663192748,
|
|
"num_tokens": 23259986.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.177496862411499,
|
|
"epoch": 1.0566321416638824,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004893942825201453,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.22544896453619004,
|
|
"num_tokens": 23268599.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.160654878616333,
|
|
"epoch": 1.0570497828265955,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000489385248450394,
|
|
"loss": 4.7802,
|
|
"mean_token_accuracy": 0.2227555751800537,
|
|
"num_tokens": 23277509.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.238864755630493,
|
|
"epoch": 1.0574674239893085,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000489376210627571,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.21802323162555695,
|
|
"num_tokens": 23286673.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.271339178085327,
|
|
"epoch": 1.0578850651520213,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004893671690518343,
|
|
"loss": 4.7868,
|
|
"mean_token_accuracy": 0.22503027468919753,
|
|
"num_tokens": 23295775.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.175595951080322,
|
|
"epoch": 1.0583027063147343,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004893581237233423,
|
|
"loss": 4.8251,
|
|
"mean_token_accuracy": 0.21998846977949144,
|
|
"num_tokens": 23305321.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.220540571212768,
|
|
"epoch": 1.0587203474774474,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004893490746422533,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.21817719787359238,
|
|
"num_tokens": 23313798.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.122827529907227,
|
|
"epoch": 1.0591379886401604,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004893400218087258,
|
|
"loss": 4.6859,
|
|
"mean_token_accuracy": 0.2308323249220848,
|
|
"num_tokens": 23322308.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.218010139465332,
|
|
"epoch": 1.0595556298028734,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004893309652229183,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.20868233293294908,
|
|
"num_tokens": 23331311.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.309686374664307,
|
|
"epoch": 1.0599732709655865,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004893219048849891,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.20849304497241974,
|
|
"num_tokens": 23340655.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.375186967849731,
|
|
"epoch": 1.0603909121282993,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004893128407950971,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.20240500718355178,
|
|
"num_tokens": 23350999.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.225055408477783,
|
|
"epoch": 1.0608085532910123,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004893037729534007,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.21835637986660003,
|
|
"num_tokens": 23359311.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.241750717163086,
|
|
"epoch": 1.0612261944537253,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004892947013600589,
|
|
"loss": 4.8773,
|
|
"mean_token_accuracy": 0.21438717246055602,
|
|
"num_tokens": 23367925.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.274806308746338,
|
|
"epoch": 1.0616438356164384,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004892856260152304,
|
|
"loss": 4.9782,
|
|
"mean_token_accuracy": 0.20920428037643432,
|
|
"num_tokens": 23377159.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.387077760696411,
|
|
"epoch": 1.0620614767791514,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000489276546919074,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.20560240000486374,
|
|
"num_tokens": 23387699.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.303796863555908,
|
|
"epoch": 1.0624791179418644,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004892674640717488,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.2079336538910866,
|
|
"num_tokens": 23397520.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.19766411781311,
|
|
"epoch": 1.0628967591045773,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004892583774734138,
|
|
"loss": 4.8416,
|
|
"mean_token_accuracy": 0.21412750482559204,
|
|
"num_tokens": 23406853.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.177767324447632,
|
|
"epoch": 1.0633144002672903,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004892492871242278,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.21835287511348725,
|
|
"num_tokens": 23416235.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.245934915542603,
|
|
"epoch": 1.0637320414300033,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004892401930243504,
|
|
"loss": 4.8507,
|
|
"mean_token_accuracy": 0.2132192999124527,
|
|
"num_tokens": 23425347.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.319457960128784,
|
|
"epoch": 1.0641496825927164,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004892310951739404,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.20810493379831313,
|
|
"num_tokens": 23434905.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.3060602188110355,
|
|
"epoch": 1.0645673237554294,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004892219935731571,
|
|
"loss": 4.8372,
|
|
"mean_token_accuracy": 0.21815156638622285,
|
|
"num_tokens": 23444495.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.215586233139038,
|
|
"epoch": 1.0649849649181424,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048921288822216,
|
|
"loss": 4.7977,
|
|
"mean_token_accuracy": 0.21846087723970414,
|
|
"num_tokens": 23452224.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.236117935180664,
|
|
"epoch": 1.0654026060808552,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004892037791211086,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.20849195420742034,
|
|
"num_tokens": 23461987.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.112642860412597,
|
|
"epoch": 1.0658202472435683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004891946662701621,
|
|
"loss": 4.7749,
|
|
"mean_token_accuracy": 0.2230517476797104,
|
|
"num_tokens": 23470645.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.273208856582642,
|
|
"epoch": 1.0662378884062813,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004891855496694801,
|
|
"loss": 4.9509,
|
|
"mean_token_accuracy": 0.2094174474477768,
|
|
"num_tokens": 23480169.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.303360271453857,
|
|
"epoch": 1.0666555295689943,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004891764293192222,
|
|
"loss": 4.8901,
|
|
"mean_token_accuracy": 0.21132962852716447,
|
|
"num_tokens": 23488630.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.232302522659301,
|
|
"epoch": 1.0670731707317074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004891673052195482,
|
|
"loss": 4.7637,
|
|
"mean_token_accuracy": 0.21507320553064346,
|
|
"num_tokens": 23497800.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.246088171005249,
|
|
"epoch": 1.0674908118944204,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004891581773706177,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.2063503310084343,
|
|
"num_tokens": 23507400.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.260066318511963,
|
|
"epoch": 1.0679084530571332,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004891490457725906,
|
|
"loss": 4.9625,
|
|
"mean_token_accuracy": 0.19660153687000276,
|
|
"num_tokens": 23516441.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.254949951171875,
|
|
"epoch": 1.0683260942198463,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004891399104256266,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.21528470814228057,
|
|
"num_tokens": 23525066.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.185192537307739,
|
|
"epoch": 1.0687437353825593,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004891307713298857,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.21939579546451568,
|
|
"num_tokens": 23533892.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.193038082122802,
|
|
"epoch": 1.0691613765452723,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000489121628485528,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.20785707384347915,
|
|
"num_tokens": 23542680.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.164651870727539,
|
|
"epoch": 1.0695790177079854,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004891124818927133,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.22928306460380554,
|
|
"num_tokens": 23550573.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.12838044166565,
|
|
"epoch": 1.0699966588706984,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004891033315516019,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.20719024688005447,
|
|
"num_tokens": 23561281.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.151580190658569,
|
|
"epoch": 1.0704143000334112,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004890941774623541,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.22178731560707093,
|
|
"num_tokens": 23569846.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.194808578491211,
|
|
"epoch": 1.0708319411961242,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004890850196251299,
|
|
"loss": 4.7549,
|
|
"mean_token_accuracy": 0.2266395330429077,
|
|
"num_tokens": 23578145.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.230224990844727,
|
|
"epoch": 1.0712495823588373,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004890758580400898,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.21416720002889633,
|
|
"num_tokens": 23587494.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.2825868129730225,
|
|
"epoch": 1.0716672235215503,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004890666927073941,
|
|
"loss": 4.938,
|
|
"mean_token_accuracy": 0.20918689370155336,
|
|
"num_tokens": 23596599.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.240298414230347,
|
|
"epoch": 1.0720848646842633,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004890575236272032,
|
|
"loss": 4.8693,
|
|
"mean_token_accuracy": 0.22016445994377137,
|
|
"num_tokens": 23606170.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.149721622467041,
|
|
"epoch": 1.0725025058469764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890483507996778,
|
|
"loss": 4.7027,
|
|
"mean_token_accuracy": 0.2289431408047676,
|
|
"num_tokens": 23614558.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.2588951587677,
|
|
"epoch": 1.0729201470096892,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004890391742249783,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.2081690937280655,
|
|
"num_tokens": 23624125.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.343946075439453,
|
|
"epoch": 1.0733377881724022,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004890299939032654,
|
|
"loss": 4.856,
|
|
"mean_token_accuracy": 0.21386821269989015,
|
|
"num_tokens": 23633025.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.1685834407806395,
|
|
"epoch": 1.0737554293351153,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004890208098346999,
|
|
"loss": 4.8234,
|
|
"mean_token_accuracy": 0.21432046741247177,
|
|
"num_tokens": 23643387.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.2288847923278805,
|
|
"epoch": 1.0741730704978283,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004890116220194425,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.21494300067424774,
|
|
"num_tokens": 23653486.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.185152149200439,
|
|
"epoch": 1.0745907116605413,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000489002430457654,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.21413567811250686,
|
|
"num_tokens": 23663483.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.139757490158081,
|
|
"epoch": 1.0750083528232544,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004889932351494954,
|
|
"loss": 4.8301,
|
|
"mean_token_accuracy": 0.22664326727390288,
|
|
"num_tokens": 23672453.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.197592067718506,
|
|
"epoch": 1.0754259939859672,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004889840360951277,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.21682154387235641,
|
|
"num_tokens": 23681351.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.248225545883178,
|
|
"epoch": 1.0758436351486802,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004889748332947118,
|
|
"loss": 4.8103,
|
|
"mean_token_accuracy": 0.21747412979602815,
|
|
"num_tokens": 23689581.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.259065628051758,
|
|
"epoch": 1.0762612763113932,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004889656267484089,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.20671027898788452,
|
|
"num_tokens": 23699415.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.225963354110718,
|
|
"epoch": 1.0766789174741063,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048895641645638,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.21646557301282882,
|
|
"num_tokens": 23708933.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.2275087356567385,
|
|
"epoch": 1.0770965586368193,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004889472024187867,
|
|
"loss": 4.8843,
|
|
"mean_token_accuracy": 0.2048141911625862,
|
|
"num_tokens": 23718423.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.266251134872436,
|
|
"epoch": 1.0775141997995323,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048893798463579,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.21379691362380981,
|
|
"num_tokens": 23728131.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.220509719848633,
|
|
"epoch": 1.0779318409622451,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004889287631075513,
|
|
"loss": 4.8598,
|
|
"mean_token_accuracy": 0.21344517469406127,
|
|
"num_tokens": 23737378.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.368014240264893,
|
|
"epoch": 1.0783494821249582,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004889195378342322,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.2046034350991249,
|
|
"num_tokens": 23747156.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.294266891479492,
|
|
"epoch": 1.0787671232876712,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004889103088159941,
|
|
"loss": 4.8887,
|
|
"mean_token_accuracy": 0.2129557266831398,
|
|
"num_tokens": 23757090.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.206354141235352,
|
|
"epoch": 1.0791847644503842,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004889010760529986,
|
|
"loss": 4.8726,
|
|
"mean_token_accuracy": 0.21684232652187346,
|
|
"num_tokens": 23766679.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.1722166538238525,
|
|
"epoch": 1.0796024056130973,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004888918395454071,
|
|
"loss": 4.7785,
|
|
"mean_token_accuracy": 0.22636109143495559,
|
|
"num_tokens": 23775109.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.210043668746948,
|
|
"epoch": 1.0800200467758103,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004888825992933817,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.22390944957733155,
|
|
"num_tokens": 23784698.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.134778594970703,
|
|
"epoch": 1.0804376879385231,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004888733552970839,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.22148578315973283,
|
|
"num_tokens": 23793590.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.221730089187622,
|
|
"epoch": 1.0808553291012362,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004888641075566755,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.21749978065490722,
|
|
"num_tokens": 23802421.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.26275634765625,
|
|
"epoch": 1.0812729702639492,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004888548560723184,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.2105383649468422,
|
|
"num_tokens": 23811610.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.343714380264283,
|
|
"epoch": 1.0816906114266622,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004888456008441748,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.21813207119703293,
|
|
"num_tokens": 23821197.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.302690267562866,
|
|
"epoch": 1.0821082525893753,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004888363418724064,
|
|
"loss": 4.872,
|
|
"mean_token_accuracy": 0.2089340105652809,
|
|
"num_tokens": 23829757.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.237730979919434,
|
|
"epoch": 1.0825258937520883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004888270791571756,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.21033529192209244,
|
|
"num_tokens": 23839242.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.197435998916626,
|
|
"epoch": 1.082943534914801,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004888178126986444,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.2276303693652153,
|
|
"num_tokens": 23848193.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.217899894714355,
|
|
"epoch": 1.0833611760775141,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004888085424969748,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.21680044382810593,
|
|
"num_tokens": 23857623.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.257705736160278,
|
|
"epoch": 1.0837788172402272,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004887992685523295,
|
|
"loss": 4.9291,
|
|
"mean_token_accuracy": 0.20544066429138183,
|
|
"num_tokens": 23866424.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.242016983032227,
|
|
"epoch": 1.0841964584029402,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004887899908648706,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.21376932859420777,
|
|
"num_tokens": 23874855.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.285948610305786,
|
|
"epoch": 1.0846140995656532,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004887807094347606,
|
|
"loss": 4.9058,
|
|
"mean_token_accuracy": 0.21738510727882385,
|
|
"num_tokens": 23884634.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.27073302268982,
|
|
"epoch": 1.0850317407283663,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004887714242621619,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.2107292026281357,
|
|
"num_tokens": 23894307.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.26188554763794,
|
|
"epoch": 1.085449381891079,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004887621353472371,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.21864177733659745,
|
|
"num_tokens": 23903274.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.249912691116333,
|
|
"epoch": 1.0858670230537921,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004887528426901488,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.2171175852417946,
|
|
"num_tokens": 23912787.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.2976480484008786,
|
|
"epoch": 1.0862846642165052,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004887435462910597,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.20445887595415116,
|
|
"num_tokens": 23921558.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.2179313659667965,
|
|
"epoch": 1.0867023053792182,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004887342461501326,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.21802895069122313,
|
|
"num_tokens": 23929868.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.238583707809449,
|
|
"epoch": 1.0871199465419312,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004887249422675301,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.20702324956655502,
|
|
"num_tokens": 23939206.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.267602396011353,
|
|
"epoch": 1.0875375877046443,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004887156346434154,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.21662983894348145,
|
|
"num_tokens": 23948213.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.284174060821533,
|
|
"epoch": 1.087955228867357,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004887063232779513,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.21060694456100465,
|
|
"num_tokens": 23957269.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.298280858993531,
|
|
"epoch": 1.08837287003007,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004886970081713006,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.21369003206491471,
|
|
"num_tokens": 23967300.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.217717170715332,
|
|
"epoch": 1.0887905111927831,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004886876893236266,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.2136838987469673,
|
|
"num_tokens": 23976934.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.233928632736206,
|
|
"epoch": 1.0892081523554962,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004886783667350925,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.21503854990005494,
|
|
"num_tokens": 23986119.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.211476802825928,
|
|
"epoch": 1.0896257935182092,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004886690404058613,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.22073738723993303,
|
|
"num_tokens": 23996093.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.340795993804932,
|
|
"epoch": 1.0900434346809222,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004886597103360963,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.20277346074581146,
|
|
"num_tokens": 24006585.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.3235101222991945,
|
|
"epoch": 1.090461075843635,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004886503765259609,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.21455197185277938,
|
|
"num_tokens": 24016398.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.255006599426269,
|
|
"epoch": 1.090878717006348,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004886410389756186,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.21583203971385956,
|
|
"num_tokens": 24025988.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.262542343139648,
|
|
"epoch": 1.0912963581690611,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004886316976852326,
|
|
"loss": 4.862,
|
|
"mean_token_accuracy": 0.2193292498588562,
|
|
"num_tokens": 24036448.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.282661962509155,
|
|
"epoch": 1.0917139993317742,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004886223526549666,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.20162615925073624,
|
|
"num_tokens": 24047011.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.2397486686706545,
|
|
"epoch": 1.0921316404944872,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004886130038849843,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.220853491127491,
|
|
"num_tokens": 24056332.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.282353448867798,
|
|
"epoch": 1.0925492816572002,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004886036513754491,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.21582366079092025,
|
|
"num_tokens": 24065538.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.247653532028198,
|
|
"epoch": 1.092966922819913,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004885942951265251,
|
|
"loss": 4.8551,
|
|
"mean_token_accuracy": 0.21096169501543044,
|
|
"num_tokens": 24074950.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.326016426086426,
|
|
"epoch": 1.093384563982626,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004885849351383756,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.2145658403635025,
|
|
"num_tokens": 24084571.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.224700832366944,
|
|
"epoch": 1.093802205145339,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004885755714111649,
|
|
"loss": 4.9127,
|
|
"mean_token_accuracy": 0.21595772057771684,
|
|
"num_tokens": 24093693.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.219994735717774,
|
|
"epoch": 1.0942198463080521,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004885662039450565,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.21061645001173018,
|
|
"num_tokens": 24104140.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.286078071594238,
|
|
"epoch": 1.0946374874707652,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004885568327402149,
|
|
"loss": 4.8242,
|
|
"mean_token_accuracy": 0.21445247083902358,
|
|
"num_tokens": 24113107.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.282752990722656,
|
|
"epoch": 1.0950551286334782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004885474577968038,
|
|
"loss": 4.8687,
|
|
"mean_token_accuracy": 0.21503041535615922,
|
|
"num_tokens": 24122271.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.304904508590698,
|
|
"epoch": 1.095472769796191,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004885380791149874,
|
|
"loss": 4.9311,
|
|
"mean_token_accuracy": 0.21116736084222792,
|
|
"num_tokens": 24132068.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.242220306396485,
|
|
"epoch": 1.095890410958904,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004885286966949298,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.21276765614748,
|
|
"num_tokens": 24140429.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.208037805557251,
|
|
"epoch": 1.096308052121617,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004885193105367955,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.20948296636343003,
|
|
"num_tokens": 24150563.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.30492844581604,
|
|
"epoch": 1.0967256932843301,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004885099206407486,
|
|
"loss": 4.8464,
|
|
"mean_token_accuracy": 0.2084736183285713,
|
|
"num_tokens": 24159059.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.354366397857666,
|
|
"epoch": 1.0971433344470432,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004885005270069535,
|
|
"loss": 4.973,
|
|
"mean_token_accuracy": 0.21015786975622178,
|
|
"num_tokens": 24168858.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.228873062133789,
|
|
"epoch": 1.0975609756097562,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004884911296355746,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.21524029225111008,
|
|
"num_tokens": 24177573.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.253412389755249,
|
|
"epoch": 1.097978616772469,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004884817285267766,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.21889718919992446,
|
|
"num_tokens": 24186832.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.254666328430176,
|
|
"epoch": 1.098396257935182,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004884723236807239,
|
|
"loss": 4.8464,
|
|
"mean_token_accuracy": 0.21593521535396576,
|
|
"num_tokens": 24195281.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.252399635314942,
|
|
"epoch": 1.098813899097895,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004884629150975814,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.2140156015753746,
|
|
"num_tokens": 24204499.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.180082321166992,
|
|
"epoch": 1.099231540260608,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004884535027775135,
|
|
"loss": 4.7371,
|
|
"mean_token_accuracy": 0.2248645693063736,
|
|
"num_tokens": 24213418.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.166523218154907,
|
|
"epoch": 1.0996491814233211,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004884440867206851,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.2238975793123245,
|
|
"num_tokens": 24222834.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.199524736404419,
|
|
"epoch": 1.1000668225860342,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000488434666927261,
|
|
"loss": 4.8694,
|
|
"mean_token_accuracy": 0.2112327426671982,
|
|
"num_tokens": 24231821.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.2935247898101805,
|
|
"epoch": 1.100484463748747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004884252433974062,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.21594813466072083,
|
|
"num_tokens": 24240694.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.250130319595337,
|
|
"epoch": 1.10090210491146,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004884158161312856,
|
|
"loss": 4.884,
|
|
"mean_token_accuracy": 0.21344706416130066,
|
|
"num_tokens": 24249927.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.24536452293396,
|
|
"epoch": 1.101319746074173,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004884063851290642,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.21420626491308212,
|
|
"num_tokens": 24259174.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.270415496826172,
|
|
"epoch": 1.101737387236886,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004883969503909073,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.21345755308866501,
|
|
"num_tokens": 24268381.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.326361465454101,
|
|
"epoch": 1.1021550283995991,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004883875119169798,
|
|
"loss": 4.9339,
|
|
"mean_token_accuracy": 0.20831522792577745,
|
|
"num_tokens": 24277916.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.284889650344849,
|
|
"epoch": 1.1025726695623121,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000488378069707447,
|
|
"loss": 4.9407,
|
|
"mean_token_accuracy": 0.20667493343353271,
|
|
"num_tokens": 24287530.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.307422685623169,
|
|
"epoch": 1.102990310725025,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004883686237624744,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.19534914344549179,
|
|
"num_tokens": 24298239.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.353365135192871,
|
|
"epoch": 1.103407951887738,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004883591740822271,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.21096159219741822,
|
|
"num_tokens": 24307001.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.244023656845092,
|
|
"epoch": 1.103825593050451,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004883497206668707,
|
|
"loss": 4.8264,
|
|
"mean_token_accuracy": 0.22099598199129106,
|
|
"num_tokens": 24315995.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.205710554122925,
|
|
"epoch": 1.104243234213164,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004883402635165705,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.22322101294994354,
|
|
"num_tokens": 24324421.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.260620880126953,
|
|
"epoch": 1.104660875375877,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004883308026314923,
|
|
"loss": 4.9128,
|
|
"mean_token_accuracy": 0.2143041118979454,
|
|
"num_tokens": 24333715.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.2339475631713865,
|
|
"epoch": 1.1050785165385901,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883213380118016,
|
|
"loss": 4.8187,
|
|
"mean_token_accuracy": 0.2211301013827324,
|
|
"num_tokens": 24342085.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.29259877204895,
|
|
"epoch": 1.105496157701303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004883118696576642,
|
|
"loss": 4.923,
|
|
"mean_token_accuracy": 0.21399969309568406,
|
|
"num_tokens": 24350906.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.155297327041626,
|
|
"epoch": 1.105913798864016,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004883023975692457,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.21487554013729096,
|
|
"num_tokens": 24359948.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.134910583496094,
|
|
"epoch": 1.106331440026729,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004882929217467118,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.22303156107664107,
|
|
"num_tokens": 24369440.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.251122093200683,
|
|
"epoch": 1.106749081189442,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004882834421902287,
|
|
"loss": 4.8832,
|
|
"mean_token_accuracy": 0.21683633029460908,
|
|
"num_tokens": 24378442.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.210130214691162,
|
|
"epoch": 1.107166722352155,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048827395889996226,
|
|
"loss": 4.8519,
|
|
"mean_token_accuracy": 0.21275528520345688,
|
|
"num_tokens": 24387750.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.2122437953948975,
|
|
"epoch": 1.107584363514868,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004882644718760784,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.22701943814754486,
|
|
"num_tokens": 24396380.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.178321266174317,
|
|
"epoch": 1.108002004677581,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048825498111874325,
|
|
"loss": 4.7617,
|
|
"mean_token_accuracy": 0.22451317608356475,
|
|
"num_tokens": 24405135.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.189883089065551,
|
|
"epoch": 1.108419645840294,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048824548662812294,
|
|
"loss": 4.8708,
|
|
"mean_token_accuracy": 0.21518644541502,
|
|
"num_tokens": 24413517.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.290142488479614,
|
|
"epoch": 1.108837287003007,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048823598840438384,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.21741467714309692,
|
|
"num_tokens": 24422170.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.380312776565551,
|
|
"epoch": 1.10925492816572,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048822648644769194,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.2055615156888962,
|
|
"num_tokens": 24431083.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.263618135452271,
|
|
"epoch": 1.109672569328433,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004882169807582138,
|
|
"loss": 4.8903,
|
|
"mean_token_accuracy": 0.2128120020031929,
|
|
"num_tokens": 24440582.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.229394483566284,
|
|
"epoch": 1.110090210491146,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004882074713361157,
|
|
"loss": 4.8446,
|
|
"mean_token_accuracy": 0.21971453726291656,
|
|
"num_tokens": 24450047.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.151370716094971,
|
|
"epoch": 1.110507851653859,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004881979581815642,
|
|
"loss": 4.7351,
|
|
"mean_token_accuracy": 0.21893464922904968,
|
|
"num_tokens": 24457955.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.1044291973114015,
|
|
"epoch": 1.110925492816572,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004881884412947259,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.22038147300481797,
|
|
"num_tokens": 24467394.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.165178966522217,
|
|
"epoch": 1.111343133979285,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048817892067576726,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.21887305080890657,
|
|
"num_tokens": 24476386.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.164067888259888,
|
|
"epoch": 1.111760775141998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000488169396324855,
|
|
"loss": 4.8275,
|
|
"mean_token_accuracy": 0.2195124849677086,
|
|
"num_tokens": 24484800.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.230305147171021,
|
|
"epoch": 1.112178416304711,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048815986824215585,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.22188521027565003,
|
|
"num_tokens": 24494252.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.268514490127563,
|
|
"epoch": 1.112596057467424,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004881503364278366,
|
|
"loss": 4.8477,
|
|
"mean_token_accuracy": 0.21776132583618163,
|
|
"num_tokens": 24503315.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.2596601963043215,
|
|
"epoch": 1.1130136986301369,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004881408008820642,
|
|
"loss": 4.8249,
|
|
"mean_token_accuracy": 0.2207837864756584,
|
|
"num_tokens": 24512660.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.197649335861206,
|
|
"epoch": 1.11343133979285,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048813126160500555,
|
|
"loss": 4.8445,
|
|
"mean_token_accuracy": 0.213183169066906,
|
|
"num_tokens": 24521712.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.162497711181641,
|
|
"epoch": 1.113848980955563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004881217185968276,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.22562020421028137,
|
|
"num_tokens": 24529851.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.284162473678589,
|
|
"epoch": 1.114266622118276,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004881121718576974,
|
|
"loss": 4.8565,
|
|
"mean_token_accuracy": 0.21240015476942062,
|
|
"num_tokens": 24538425.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.2338639259338375,
|
|
"epoch": 1.114684263280989,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048810262138778213,
|
|
"loss": 4.9277,
|
|
"mean_token_accuracy": 0.21427140831947328,
|
|
"num_tokens": 24547477.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.257066535949707,
|
|
"epoch": 1.115101904443702,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048809306718724886,
|
|
"loss": 4.8831,
|
|
"mean_token_accuracy": 0.20407006591558458,
|
|
"num_tokens": 24556230.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.251175355911255,
|
|
"epoch": 1.115519545606415,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048808350925626514,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.21735915988683702,
|
|
"num_tokens": 24565021.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.272104167938233,
|
|
"epoch": 1.115937186769128,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048807394759499797,
|
|
"loss": 4.8422,
|
|
"mean_token_accuracy": 0.21709293574094773,
|
|
"num_tokens": 24575012.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.32255973815918,
|
|
"epoch": 1.116354827931841,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004880643822036149,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.20188573002815247,
|
|
"num_tokens": 24584267.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.25855073928833,
|
|
"epoch": 1.116772469094554,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048805481308228333,
|
|
"loss": 4.8784,
|
|
"mean_token_accuracy": 0.21697256565093995,
|
|
"num_tokens": 24594299.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.260472297668457,
|
|
"epoch": 1.117190110257267,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004880452402311709,
|
|
"loss": 4.8806,
|
|
"mean_token_accuracy": 0.2148116111755371,
|
|
"num_tokens": 24603717.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.295331573486328,
|
|
"epoch": 1.11760775141998,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048803566365044493,
|
|
"loss": 4.9339,
|
|
"mean_token_accuracy": 0.21398739665746688,
|
|
"num_tokens": 24613141.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.239920043945313,
|
|
"epoch": 1.1180253925826928,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004880260833402734,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.22103586345911025,
|
|
"num_tokens": 24621837.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.314539527893066,
|
|
"epoch": 1.1184430337454059,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048801649930082375,
|
|
"loss": 4.8914,
|
|
"mean_token_accuracy": 0.21081933230161667,
|
|
"num_tokens": 24630657.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.401352643966675,
|
|
"epoch": 1.118860674908119,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000488006911532264,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.20111834704875947,
|
|
"num_tokens": 24639929.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.289968490600586,
|
|
"epoch": 1.119278316070832,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004879973200347617,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.21525239646434785,
|
|
"num_tokens": 24648537.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.226531267166138,
|
|
"epoch": 1.119695957233545,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048798772480848504,
|
|
"loss": 4.8843,
|
|
"mean_token_accuracy": 0.21989901214838029,
|
|
"num_tokens": 24656809.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.2453755855560305,
|
|
"epoch": 1.120113598396258,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048797812585360187,
|
|
"loss": 4.8696,
|
|
"mean_token_accuracy": 0.21047572642564774,
|
|
"num_tokens": 24665523.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.299148225784302,
|
|
"epoch": 1.120531239558971,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048796852317028024,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.21580089032649993,
|
|
"num_tokens": 24675618.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.235862779617309,
|
|
"epoch": 1.1209488807216839,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004879589167586882,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.21585194170475006,
|
|
"num_tokens": 24684922.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.245304012298584,
|
|
"epoch": 1.121366521884397,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048794930661899414,
|
|
"loss": 4.9206,
|
|
"mean_token_accuracy": 0.2157478630542755,
|
|
"num_tokens": 24693791.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.188789892196655,
|
|
"epoch": 1.12178416304711,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048793969275136593,
|
|
"loss": 4.7921,
|
|
"mean_token_accuracy": 0.21483764350414275,
|
|
"num_tokens": 24702661.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.233766174316406,
|
|
"epoch": 1.122201804209823,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004879300751559722,
|
|
"loss": 4.8746,
|
|
"mean_token_accuracy": 0.21093385964632033,
|
|
"num_tokens": 24711019.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.293105268478394,
|
|
"epoch": 1.122619445372536,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004879204538329812,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.20947402268648146,
|
|
"num_tokens": 24720456.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.249146413803101,
|
|
"epoch": 1.1230370865352488,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004879108287825614,
|
|
"loss": 4.8582,
|
|
"mean_token_accuracy": 0.21839351654052735,
|
|
"num_tokens": 24729395.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.208390951156616,
|
|
"epoch": 1.1234547276979618,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048790120000488115,
|
|
"loss": 4.8368,
|
|
"mean_token_accuracy": 0.2201671302318573,
|
|
"num_tokens": 24738543.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.279634618759156,
|
|
"epoch": 1.1238723688606749,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004878915675001092,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.2118135169148445,
|
|
"num_tokens": 24747860.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.172195482254028,
|
|
"epoch": 1.124290010023388,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004878819312684141,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.21404541581869124,
|
|
"num_tokens": 24757457.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.286320972442627,
|
|
"epoch": 1.124707651186101,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004878722913099645,
|
|
"loss": 4.8684,
|
|
"mean_token_accuracy": 0.2124683752655983,
|
|
"num_tokens": 24766844.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.282261943817138,
|
|
"epoch": 1.125125292348814,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004878626476249293,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.20631824880838395,
|
|
"num_tokens": 24776041.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.272881889343262,
|
|
"epoch": 1.125542933511527,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004878530002134772,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.22347832322120667,
|
|
"num_tokens": 24785515.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.317842054367065,
|
|
"epoch": 1.1259605746742398,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004878433490757771,
|
|
"loss": 4.9272,
|
|
"mean_token_accuracy": 0.21852009743452072,
|
|
"num_tokens": 24795251.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.193519926071167,
|
|
"epoch": 1.1263782158369529,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004878336942119979,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.21865068823099137,
|
|
"num_tokens": 24804672.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.289021253585815,
|
|
"epoch": 1.126795856999666,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048782403562230874,
|
|
"loss": 4.8728,
|
|
"mean_token_accuracy": 0.21527854800224305,
|
|
"num_tokens": 24813520.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.214760971069336,
|
|
"epoch": 1.127213498162379,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004878143733068787,
|
|
"loss": 4.7259,
|
|
"mean_token_accuracy": 0.2280208110809326,
|
|
"num_tokens": 24821368.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.210858631134033,
|
|
"epoch": 1.127631139325092,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004878047072658769,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.21307984441518785,
|
|
"num_tokens": 24830071.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.168901348114014,
|
|
"epoch": 1.1280487804878048,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004877950374994725,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.22504222691059111,
|
|
"num_tokens": 24838982.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.270542097091675,
|
|
"epoch": 1.1284664216505178,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004877853640078349,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.20333398580551149,
|
|
"num_tokens": 24848313.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.243781423568725,
|
|
"epoch": 1.1288840628132308,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004877756867911333,
|
|
"loss": 4.8928,
|
|
"mean_token_accuracy": 0.2185330033302307,
|
|
"num_tokens": 24857477.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.227798080444336,
|
|
"epoch": 1.1293017039759439,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004877660058495372,
|
|
"loss": 4.8532,
|
|
"mean_token_accuracy": 0.21268229186534882,
|
|
"num_tokens": 24866561.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.245633697509765,
|
|
"epoch": 1.129719345138657,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004877563211832161,
|
|
"loss": 4.9309,
|
|
"mean_token_accuracy": 0.2064286470413208,
|
|
"num_tokens": 24876113.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.35431547164917,
|
|
"epoch": 1.13013698630137,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048774663279233947,
|
|
"loss": 4.9826,
|
|
"mean_token_accuracy": 0.20603052228689195,
|
|
"num_tokens": 24885974.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.279431343078613,
|
|
"epoch": 1.130554627464083,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048773694067707693,
|
|
"loss": 4.8251,
|
|
"mean_token_accuracy": 0.22038171142339708,
|
|
"num_tokens": 24895046.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.242886734008789,
|
|
"epoch": 1.1309722686267958,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048772724483759825,
|
|
"loss": 4.9775,
|
|
"mean_token_accuracy": 0.20775714218616487,
|
|
"num_tokens": 24903315.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.274171638488769,
|
|
"epoch": 1.1313899097895088,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000487717545274073,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.2105189621448517,
|
|
"num_tokens": 24912556.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.349406385421753,
|
|
"epoch": 1.1318075509522219,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004877078419866711,
|
|
"loss": 4.8878,
|
|
"mean_token_accuracy": 0.21738782823085784,
|
|
"num_tokens": 24921854.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.202975225448609,
|
|
"epoch": 1.1322251921149349,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048769813497556236,
|
|
"loss": 4.8336,
|
|
"mean_token_accuracy": 0.21986557841300963,
|
|
"num_tokens": 24930691.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.213990592956543,
|
|
"epoch": 1.132642833277648,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004876884242409168,
|
|
"loss": 4.9058,
|
|
"mean_token_accuracy": 0.21323849707841874,
|
|
"num_tokens": 24940573.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.242026042938233,
|
|
"epoch": 1.1330604744403607,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048767870978290434,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.21502540111541749,
|
|
"num_tokens": 24950902.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.265374183654785,
|
|
"epoch": 1.1334781156030738,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004876689916016951,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.21692950427532195,
|
|
"num_tokens": 24960055.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.25055947303772,
|
|
"epoch": 1.1338957567657868,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004876592696974591,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.21373529136180877,
|
|
"num_tokens": 24969896.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.267461490631104,
|
|
"epoch": 1.1343133979284998,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004876495440703667,
|
|
"loss": 4.8178,
|
|
"mean_token_accuracy": 0.21601286083459853,
|
|
"num_tokens": 24978467.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.228731727600097,
|
|
"epoch": 1.1347310390912129,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004876398147205879,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.22007479816675185,
|
|
"num_tokens": 24987038.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.32305588722229,
|
|
"epoch": 1.135148680253926,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004876300816482933,
|
|
"loss": 4.9267,
|
|
"mean_token_accuracy": 0.2078369677066803,
|
|
"num_tokens": 24997228.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.256027317047119,
|
|
"epoch": 1.135566321416639,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004876203448536532,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.2127974048256874,
|
|
"num_tokens": 25005784.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.248302173614502,
|
|
"epoch": 1.1359839625793517,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004876106043368381,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.21064002811908722,
|
|
"num_tokens": 25015863.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.13584337234497,
|
|
"epoch": 1.1364016037420648,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004876008600980183,
|
|
"loss": 4.7376,
|
|
"mean_token_accuracy": 0.23130580186843872,
|
|
"num_tokens": 25025391.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.284393405914306,
|
|
"epoch": 1.1368192449047778,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048759111213736455,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.2080138385295868,
|
|
"num_tokens": 25035387.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.181062316894531,
|
|
"epoch": 1.1372368860674908,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004875813604550476,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.22142590284347535,
|
|
"num_tokens": 25044485.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.183429765701294,
|
|
"epoch": 1.1376545272302039,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004875716050512379,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.22024296522140502,
|
|
"num_tokens": 25053079.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.301594924926758,
|
|
"epoch": 1.1380721683929167,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004875618459261065,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.2068393662571907,
|
|
"num_tokens": 25063262.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.272895193099975,
|
|
"epoch": 1.1384898095556297,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048755208307982414,
|
|
"loss": 4.8218,
|
|
"mean_token_accuracy": 0.22080254405736924,
|
|
"num_tokens": 25071720.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.210835552215576,
|
|
"epoch": 1.1389074507183428,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004875423165125616,
|
|
"loss": 4.8551,
|
|
"mean_token_accuracy": 0.21650370210409164,
|
|
"num_tokens": 25080460.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.204386901855469,
|
|
"epoch": 1.1393250918810558,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048753254622449006,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.2172856003046036,
|
|
"num_tokens": 25089162.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.209817028045654,
|
|
"epoch": 1.1397427330437688,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004875227722157804,
|
|
"loss": 4.7467,
|
|
"mean_token_accuracy": 0.21587816178798674,
|
|
"num_tokens": 25098234.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.211898136138916,
|
|
"epoch": 1.1401603742064819,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004875129944866039,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.21857476383447647,
|
|
"num_tokens": 25107832.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.220652532577515,
|
|
"epoch": 1.140578015369195,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004875032130371316,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.22030058801174163,
|
|
"num_tokens": 25116118.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.127211856842041,
|
|
"epoch": 1.1409956565319077,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004874934278675347,
|
|
"loss": 4.6753,
|
|
"mean_token_accuracy": 0.2224624216556549,
|
|
"num_tokens": 25125025.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.269464731216431,
|
|
"epoch": 1.1414132976946207,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004874836389779846,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.21597711890935897,
|
|
"num_tokens": 25135763.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.385318994522095,
|
|
"epoch": 1.1418309388573338,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048747384636865267,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.21099156588315965,
|
|
"num_tokens": 25145510.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.282127141952515,
|
|
"epoch": 1.1422485800200468,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004874640500397103,
|
|
"loss": 4.8146,
|
|
"mean_token_accuracy": 0.21781854778528215,
|
|
"num_tokens": 25153910.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.19629979133606,
|
|
"epoch": 1.1426662211827598,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004874542499913289,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.21522289365530015,
|
|
"num_tokens": 25163357.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.2414525032043455,
|
|
"epoch": 1.1430838623454727,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048744444622368015,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.22141324430704118,
|
|
"num_tokens": 25172423.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.24610481262207,
|
|
"epoch": 1.1435015035081857,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048743463873693576,
|
|
"loss": 4.7905,
|
|
"mean_token_accuracy": 0.21471354365348816,
|
|
"num_tokens": 25181508.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.262304592132568,
|
|
"epoch": 1.1439191446708987,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004874248275312673,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.2110977828502655,
|
|
"num_tokens": 25190741.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.337632417678833,
|
|
"epoch": 1.1443367858336118,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048741501260684644,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.20501408278942107,
|
|
"num_tokens": 25201288.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.254593181610107,
|
|
"epoch": 1.1447544269963248,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048740519396384515,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.22259767204523087,
|
|
"num_tokens": 25210111.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.251527452468872,
|
|
"epoch": 1.1451720681590378,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048739537160243524,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.2129773497581482,
|
|
"num_tokens": 25220061.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.275093984603882,
|
|
"epoch": 1.1455897093217509,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048738554552278874,
|
|
"loss": 4.8579,
|
|
"mean_token_accuracy": 0.2132376804947853,
|
|
"num_tokens": 25229336.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.231576728820801,
|
|
"epoch": 1.1460073504844637,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048737571572507753,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.22256459891796113,
|
|
"num_tokens": 25238539.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.248430681228638,
|
|
"epoch": 1.1464249916471767,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048736588220947384,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.21245583146810532,
|
|
"num_tokens": 25247880.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.251602697372436,
|
|
"epoch": 1.1468426328098897,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048735604497614974,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.21428230851888658,
|
|
"num_tokens": 25257295.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.274798202514648,
|
|
"epoch": 1.1472602739726028,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004873462040252775,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.2127823904156685,
|
|
"num_tokens": 25266784.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.330947637557983,
|
|
"epoch": 1.1476779151353158,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004873363593570293,
|
|
"loss": 4.9258,
|
|
"mean_token_accuracy": 0.20749097019433976,
|
|
"num_tokens": 25276910.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.281500625610351,
|
|
"epoch": 1.1480955562980286,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004873265109715776,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.22124791741371155,
|
|
"num_tokens": 25285776.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.266375255584717,
|
|
"epoch": 1.1485131974607417,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004873166588690947,
|
|
"loss": 4.8186,
|
|
"mean_token_accuracy": 0.21715654134750367,
|
|
"num_tokens": 25294319.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.2414977073669435,
|
|
"epoch": 1.1489308386234547,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004873068030497532,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.21985534727573394,
|
|
"num_tokens": 25304396.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.15681471824646,
|
|
"epoch": 1.1493484797861677,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048729694351372545,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.2255796417593956,
|
|
"num_tokens": 25313095.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.262956619262695,
|
|
"epoch": 1.1497661209488808,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004872870802611842,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.2101575806736946,
|
|
"num_tokens": 25322948.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.251209306716919,
|
|
"epoch": 1.1501837621115938,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004872772132923021,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.21364057809114456,
|
|
"num_tokens": 25332707.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.2221856117248535,
|
|
"epoch": 1.1506014032743068,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048726734260725186,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.22046921402215958,
|
|
"num_tokens": 25342029.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.202862358093261,
|
|
"epoch": 1.1510190444370196,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004872574682062063,
|
|
"loss": 4.7611,
|
|
"mean_token_accuracy": 0.22316405922174454,
|
|
"num_tokens": 25350374.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.249643468856812,
|
|
"epoch": 1.1514366855997327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004872475900893382,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.2148176297545433,
|
|
"num_tokens": 25359370.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.230676078796387,
|
|
"epoch": 1.1518543267624457,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004872377082568206,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.22174135148525237,
|
|
"num_tokens": 25368329.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.302226448059082,
|
|
"epoch": 1.1522719679251587,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048722782270882643,
|
|
"loss": 4.9554,
|
|
"mean_token_accuracy": 0.20625295042991637,
|
|
"num_tokens": 25377795.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.320987129211426,
|
|
"epoch": 1.1526896090878718,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004872179334455288,
|
|
"loss": 4.896,
|
|
"mean_token_accuracy": 0.2148436576128006,
|
|
"num_tokens": 25387134.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.350821399688721,
|
|
"epoch": 1.1531072502505846,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048720804046710074,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.21427614092826844,
|
|
"num_tokens": 25396320.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.280384111404419,
|
|
"epoch": 1.1535248914132976,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048719814377371553,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.21237116903066636,
|
|
"num_tokens": 25404727.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.183207225799561,
|
|
"epoch": 1.1539425325760106,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004871882433655464,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.2148485466837883,
|
|
"num_tokens": 25414137.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.283994150161743,
|
|
"epoch": 1.1543601737387237,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004871783392427666,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.2191103309392929,
|
|
"num_tokens": 25423297.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.34541163444519,
|
|
"epoch": 1.1547778149014367,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004871684314055497,
|
|
"loss": 4.9635,
|
|
"mean_token_accuracy": 0.2100587695837021,
|
|
"num_tokens": 25433185.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.308906745910645,
|
|
"epoch": 1.1551954560641498,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004871585198540689,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.21503650695085524,
|
|
"num_tokens": 25441769.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.227680921554565,
|
|
"epoch": 1.1556130972268628,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048714860458849794,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.2127696692943573,
|
|
"num_tokens": 25450650.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.242100763320923,
|
|
"epoch": 1.1560307383895756,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048713868560901013,
|
|
"loss": 4.8142,
|
|
"mean_token_accuracy": 0.22460245937108994,
|
|
"num_tokens": 25458721.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.293939065933228,
|
|
"epoch": 1.1564483795522886,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004871287629157794,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.21358436793088914,
|
|
"num_tokens": 25468004.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.292747449874878,
|
|
"epoch": 1.1568660207150017,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004871188365089793,
|
|
"loss": 4.9929,
|
|
"mean_token_accuracy": 0.21236582696437836,
|
|
"num_tokens": 25478042.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.315775585174561,
|
|
"epoch": 1.1572836618777147,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004871089063887837,
|
|
"loss": 4.8831,
|
|
"mean_token_accuracy": 0.21270231306552886,
|
|
"num_tokens": 25488439.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.285203123092652,
|
|
"epoch": 1.1577013030404277,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048709897255536626,
|
|
"loss": 4.8801,
|
|
"mean_token_accuracy": 0.21377596110105515,
|
|
"num_tokens": 25497928.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.291836881637574,
|
|
"epoch": 1.1581189442031405,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004870890350089011,
|
|
"loss": 4.9241,
|
|
"mean_token_accuracy": 0.21098549515008927,
|
|
"num_tokens": 25506522.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.277757883071899,
|
|
"epoch": 1.1585365853658536,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004870790937495621,
|
|
"loss": 4.888,
|
|
"mean_token_accuracy": 0.2061069577932358,
|
|
"num_tokens": 25516017.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.285283088684082,
|
|
"epoch": 1.1589542265285666,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048706914877752325,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.21824978590011596,
|
|
"num_tokens": 25525262.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.172430562973022,
|
|
"epoch": 1.1593718676912796,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048705920009295867,
|
|
"loss": 4.8272,
|
|
"mean_token_accuracy": 0.21890588998794555,
|
|
"num_tokens": 25534479.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.247219276428223,
|
|
"epoch": 1.1597895088539927,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004870492476960426,
|
|
"loss": 4.8573,
|
|
"mean_token_accuracy": 0.22094037830829621,
|
|
"num_tokens": 25543338.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.390956401824951,
|
|
"epoch": 1.1602071500167057,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004870392915869491,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.20572028160095215,
|
|
"num_tokens": 25552286.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.316050386428833,
|
|
"epoch": 1.1606247911794187,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004870293317658526,
|
|
"loss": 4.9092,
|
|
"mean_token_accuracy": 0.21064271479845048,
|
|
"num_tokens": 25561978.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.233201789855957,
|
|
"epoch": 1.1610424323421316,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004870193682329275,
|
|
"loss": 4.8171,
|
|
"mean_token_accuracy": 0.2178492873907089,
|
|
"num_tokens": 25570139.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.274347019195557,
|
|
"epoch": 1.1614600735048446,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048700940098834805,
|
|
"loss": 4.844,
|
|
"mean_token_accuracy": 0.21332231611013414,
|
|
"num_tokens": 25579761.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.26838903427124,
|
|
"epoch": 1.1618777146675576,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004869994300322889,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.21357373595237733,
|
|
"num_tokens": 25588740.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.230331754684448,
|
|
"epoch": 1.1622953558302707,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048698945536492454,
|
|
"loss": 4.8824,
|
|
"mean_token_accuracy": 0.21274254471063614,
|
|
"num_tokens": 25597963.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.199088907241821,
|
|
"epoch": 1.1627129969929837,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004869794769864296,
|
|
"loss": 4.8498,
|
|
"mean_token_accuracy": 0.21362008899450302,
|
|
"num_tokens": 25606782.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.357897520065308,
|
|
"epoch": 1.1631306381556965,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004869694948969787,
|
|
"loss": 4.951,
|
|
"mean_token_accuracy": 0.20440163761377333,
|
|
"num_tokens": 25616458.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.314084482192993,
|
|
"epoch": 1.1635482793184095,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048695950909674666,
|
|
"loss": 4.915,
|
|
"mean_token_accuracy": 0.20270895212888718,
|
|
"num_tokens": 25625081.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.278805208206177,
|
|
"epoch": 1.1639659204811226,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048694951958590835,
|
|
"loss": 4.9319,
|
|
"mean_token_accuracy": 0.2117127373814583,
|
|
"num_tokens": 25634000.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.303723764419556,
|
|
"epoch": 1.1643835616438356,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048693952636463854,
|
|
"loss": 4.8352,
|
|
"mean_token_accuracy": 0.21585446149110793,
|
|
"num_tokens": 25642715.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.162616491317749,
|
|
"epoch": 1.1648012028065486,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048692952943311214,
|
|
"loss": 4.6661,
|
|
"mean_token_accuracy": 0.2331972062587738,
|
|
"num_tokens": 25650979.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.250091600418091,
|
|
"epoch": 1.1652188439692617,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004869195287915043,
|
|
"loss": 4.9055,
|
|
"mean_token_accuracy": 0.21361140459775924,
|
|
"num_tokens": 25660860.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.132626104354858,
|
|
"epoch": 1.1656364851319747,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048690952443999,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.22511593997478485,
|
|
"num_tokens": 25670331.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.311589765548706,
|
|
"epoch": 1.1660541262946875,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048689951637874445,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.20973535031080245,
|
|
"num_tokens": 25679276.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.294576740264892,
|
|
"epoch": 1.1664717674574006,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004868895046079428,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.22473430931568145,
|
|
"num_tokens": 25688509.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.207734775543213,
|
|
"epoch": 1.1668894086201136,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004868794891277602,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.22347115129232406,
|
|
"num_tokens": 25697776.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.215428495407105,
|
|
"epoch": 1.1673070497828266,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004868694699383722,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.2061985045671463,
|
|
"num_tokens": 25707528.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.273661518096924,
|
|
"epoch": 1.1677246909455397,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004868594470399541,
|
|
"loss": 4.8458,
|
|
"mean_token_accuracy": 0.21596421152353287,
|
|
"num_tokens": 25716568.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.2904833316802975,
|
|
"epoch": 1.1681423321082525,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048684942043268137,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.21145651787519454,
|
|
"num_tokens": 25726441.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.23344578742981,
|
|
"epoch": 1.1685599732709655,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048683939011672953,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.21856956779956818,
|
|
"num_tokens": 25735386.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.285693359375,
|
|
"epoch": 1.1689776144336785,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048682935609227414,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.21226132959127425,
|
|
"num_tokens": 25744758.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.230813264846802,
|
|
"epoch": 1.1693952555963916,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048681931835949083,
|
|
"loss": 4.8976,
|
|
"mean_token_accuracy": 0.21647658199071884,
|
|
"num_tokens": 25753836.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.281685876846313,
|
|
"epoch": 1.1698128967591046,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004868092769185555,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.20064594298601152,
|
|
"num_tokens": 25763302.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.254870939254761,
|
|
"epoch": 1.1702305379218176,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048679923176964384,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.22437354326248168,
|
|
"num_tokens": 25772204.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.277496242523194,
|
|
"epoch": 1.1706481790845307,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004867891829129316,
|
|
"loss": 4.8595,
|
|
"mean_token_accuracy": 0.21018785387277603,
|
|
"num_tokens": 25781762.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.265302848815918,
|
|
"epoch": 1.1710658202472435,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004867791303485948,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.2073584407567978,
|
|
"num_tokens": 25791573.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.232767343521118,
|
|
"epoch": 1.1714834614099565,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004867690740768094,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.2194257453083992,
|
|
"num_tokens": 25800777.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.238540935516357,
|
|
"epoch": 1.1719011025726696,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048675901409775147,
|
|
"loss": 4.8293,
|
|
"mean_token_accuracy": 0.21526730358600615,
|
|
"num_tokens": 25809145.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.205876111984253,
|
|
"epoch": 1.1723187437353826,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048674895041159714,
|
|
"loss": 4.761,
|
|
"mean_token_accuracy": 0.22335259914398192,
|
|
"num_tokens": 25817884.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.278775882720947,
|
|
"epoch": 1.1727363848980956,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048673888301852247,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.21528892517089843,
|
|
"num_tokens": 25826953.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.336396265029907,
|
|
"epoch": 1.1731540260608084,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004867288119187039,
|
|
"loss": 4.9219,
|
|
"mean_token_accuracy": 0.21320491582155227,
|
|
"num_tokens": 25835597.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.2598833560943605,
|
|
"epoch": 1.1735716672235215,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004867187371123175,
|
|
"loss": 4.8816,
|
|
"mean_token_accuracy": 0.21371833384037017,
|
|
"num_tokens": 25845072.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.245011520385742,
|
|
"epoch": 1.1739893083862345,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048670865859953984,
|
|
"loss": 4.7821,
|
|
"mean_token_accuracy": 0.21745716035366058,
|
|
"num_tokens": 25854902.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.289572525024414,
|
|
"epoch": 1.1744069495489475,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004866985763805472,
|
|
"loss": 4.9214,
|
|
"mean_token_accuracy": 0.20893015414476396,
|
|
"num_tokens": 25863807.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.273925304412842,
|
|
"epoch": 1.1748245907116606,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004866884904555162,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.21114666312932967,
|
|
"num_tokens": 25873709.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.248942136764526,
|
|
"epoch": 1.1752422318743736,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004866784008246233,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.21534528136253356,
|
|
"num_tokens": 25883425.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.2000367641448975,
|
|
"epoch": 1.1756598730370866,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004866683074880453,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.22570968717336654,
|
|
"num_tokens": 25892317.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.261901330947876,
|
|
"epoch": 1.1760775141997994,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048665821044595884,
|
|
"loss": 4.8352,
|
|
"mean_token_accuracy": 0.2215958222746849,
|
|
"num_tokens": 25901733.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.181770324707031,
|
|
"epoch": 1.1764951553625125,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004866481096985405,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.21730040311813353,
|
|
"num_tokens": 25911574.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.236448526382446,
|
|
"epoch": 1.1769127965252255,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004866380052459673,
|
|
"loss": 4.9092,
|
|
"mean_token_accuracy": 0.21119863986968995,
|
|
"num_tokens": 25921152.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.3263258934021,
|
|
"epoch": 1.1773304376879385,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004866278970884161,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.20814426392316818,
|
|
"num_tokens": 25930455.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.208253288269043,
|
|
"epoch": 1.1777480788506516,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048661778522606376,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.21605266779661178,
|
|
"num_tokens": 25939298.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.229600477218628,
|
|
"epoch": 1.1781657200133644,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048660766965908736,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.21330373734235764,
|
|
"num_tokens": 25948426.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.279765510559082,
|
|
"epoch": 1.1785833611760774,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048659755038766406,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.21497643291950225,
|
|
"num_tokens": 25958469.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.226970911026001,
|
|
"epoch": 1.1790010023387905,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048658742741197086,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.22974183559417724,
|
|
"num_tokens": 25967173.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.246548509597778,
|
|
"epoch": 1.1794186435015035,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048657730073218517,
|
|
"loss": 4.8816,
|
|
"mean_token_accuracy": 0.21790513396263123,
|
|
"num_tokens": 25976474.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.263751554489136,
|
|
"epoch": 1.1798362846642165,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004865671703484841,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.21895242035388945,
|
|
"num_tokens": 25984745.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.2349663257598875,
|
|
"epoch": 1.1802539258269296,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048655703626104493,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.22485953867435454,
|
|
"num_tokens": 25993265.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.289504289627075,
|
|
"epoch": 1.1806715669896426,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048654689847004535,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.2165503039956093,
|
|
"num_tokens": 26002390.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.342466592788696,
|
|
"epoch": 1.1810892081523554,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004865367569756626,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.21828051805496215,
|
|
"num_tokens": 26013086.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.325785398483276,
|
|
"epoch": 1.1815068493150684,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048652661177807426,
|
|
"loss": 4.8703,
|
|
"mean_token_accuracy": 0.2175700306892395,
|
|
"num_tokens": 26022119.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.276900863647461,
|
|
"epoch": 1.1819244904777815,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048651646287745803,
|
|
"loss": 4.9063,
|
|
"mean_token_accuracy": 0.21038872748613358,
|
|
"num_tokens": 26031805.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.264519309997558,
|
|
"epoch": 1.1823421316404945,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048650631027399155,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.2102193593978882,
|
|
"num_tokens": 26040965.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.26584906578064,
|
|
"epoch": 1.1827597728032075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048649615396785246,
|
|
"loss": 4.8746,
|
|
"mean_token_accuracy": 0.21252837777137756,
|
|
"num_tokens": 26049618.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.261823892593384,
|
|
"epoch": 1.1831774139659206,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048648599395921863,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.2164057031273842,
|
|
"num_tokens": 26058335.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.134583759307861,
|
|
"epoch": 1.1835950551286334,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048647583024826786,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.22768326103687286,
|
|
"num_tokens": 26067361.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.321046972274781,
|
|
"epoch": 1.1840126962913464,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048646566283517824,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.20828020721673965,
|
|
"num_tokens": 26077401.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.225003480911255,
|
|
"epoch": 1.1844303374540595,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048645549172012756,
|
|
"loss": 4.7629,
|
|
"mean_token_accuracy": 0.21947086602449417,
|
|
"num_tokens": 26086422.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.266509103775024,
|
|
"epoch": 1.1848479786167725,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000486445316903294,
|
|
"loss": 4.9139,
|
|
"mean_token_accuracy": 0.21090536564588547,
|
|
"num_tokens": 26095974.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.216038751602173,
|
|
"epoch": 1.1852656197794855,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004864351383848556,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.22109560668468475,
|
|
"num_tokens": 26104782.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.283239126205444,
|
|
"epoch": 1.1856832609421986,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004864249561649906,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.21540673375129699,
|
|
"num_tokens": 26113769.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.268804216384888,
|
|
"epoch": 1.1861009021049114,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004864147702438773,
|
|
"loss": 4.9154,
|
|
"mean_token_accuracy": 0.21180143505334853,
|
|
"num_tokens": 26123759.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.286877822875977,
|
|
"epoch": 1.1865185432676244,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000486404580621694,
|
|
"loss": 4.7881,
|
|
"mean_token_accuracy": 0.22520847767591476,
|
|
"num_tokens": 26133392.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.326722431182861,
|
|
"epoch": 1.1869361844303374,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000486394387298619,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.21022869199514388,
|
|
"num_tokens": 26142102.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.189328956604004,
|
|
"epoch": 1.1873538255930505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048638419027483075,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.22178433686494828,
|
|
"num_tokens": 26151504.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.27337384223938,
|
|
"epoch": 1.1877714667557635,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004863739895505079,
|
|
"loss": 4.9695,
|
|
"mean_token_accuracy": 0.2069292426109314,
|
|
"num_tokens": 26160717.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.231488037109375,
|
|
"epoch": 1.1881891079184765,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048636378512582884,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.21972067803144454,
|
|
"num_tokens": 26169788.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.221753311157227,
|
|
"epoch": 1.1886067490811894,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048635357700097236,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.21143840700387956,
|
|
"num_tokens": 26178904.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.279734373092651,
|
|
"epoch": 1.1890243902439024,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004863433651761171,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.2129896193742752,
|
|
"num_tokens": 26188832.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.300274085998535,
|
|
"epoch": 1.1894420314066154,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004863331496514418,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.20776755958795548,
|
|
"num_tokens": 26199003.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.337502574920654,
|
|
"epoch": 1.1898596725693285,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048632293042712545,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.2114368349313736,
|
|
"num_tokens": 26209001.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.265765523910522,
|
|
"epoch": 1.1902773137320415,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048631270750334674,
|
|
"loss": 4.8498,
|
|
"mean_token_accuracy": 0.21795356273651123,
|
|
"num_tokens": 26217834.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.312463665008545,
|
|
"epoch": 1.1906949548947545,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048630248088028474,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.21495429873466493,
|
|
"num_tokens": 26226935.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.298838567733765,
|
|
"epoch": 1.1911125960574673,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004862922505581185,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.2122185006737709,
|
|
"num_tokens": 26236874.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.28390679359436,
|
|
"epoch": 1.1915302372201804,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000486282016537027,
|
|
"loss": 4.8489,
|
|
"mean_token_accuracy": 0.2179478794336319,
|
|
"num_tokens": 26246361.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.186296081542968,
|
|
"epoch": 1.1919478783828934,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048627177881718954,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.22431518882513046,
|
|
"num_tokens": 26255316.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.370869112014771,
|
|
"epoch": 1.1923655195456064,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004862615373987853,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.21484034955501558,
|
|
"num_tokens": 26265250.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.230578184127808,
|
|
"epoch": 1.1927831607083195,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004862512922819935,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.22784640938043593,
|
|
"num_tokens": 26273858.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.299671745300293,
|
|
"epoch": 1.1932008018710325,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004862410434669936,
|
|
"loss": 4.9619,
|
|
"mean_token_accuracy": 0.20785875171422957,
|
|
"num_tokens": 26283536.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.243133163452148,
|
|
"epoch": 1.1936184430337453,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048623079095396496,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.2246714562177658,
|
|
"num_tokens": 26291761.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.226649141311645,
|
|
"epoch": 1.1940360841964583,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000486220534743087,
|
|
"loss": 4.8197,
|
|
"mean_token_accuracy": 0.2074689209461212,
|
|
"num_tokens": 26301082.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.2370246887207035,
|
|
"epoch": 1.1944537253591714,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004862102748345394,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.2137410596013069,
|
|
"num_tokens": 26310424.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.291343259811401,
|
|
"epoch": 1.1948713665218844,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048620001122850164,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.212006838619709,
|
|
"num_tokens": 26319442.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.2116326808929445,
|
|
"epoch": 1.1952890076845974,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004861897439251535,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.22284260839223863,
|
|
"num_tokens": 26327757.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.257479095458985,
|
|
"epoch": 1.1957066488473105,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048617947292467473,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.2201303720474243,
|
|
"num_tokens": 26337327.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.292124557495117,
|
|
"epoch": 1.1961242900100233,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048616919822724506,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.21943730860948563,
|
|
"num_tokens": 26345821.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.270337533950806,
|
|
"epoch": 1.1965419311727363,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048615891983304436,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.21361027359962464,
|
|
"num_tokens": 26355423.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.220322561264038,
|
|
"epoch": 1.1969595723354494,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004861486377422526,
|
|
"loss": 4.7482,
|
|
"mean_token_accuracy": 0.22685548663139343,
|
|
"num_tokens": 26363770.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.213330411911011,
|
|
"epoch": 1.1973772134981624,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004861383519550498,
|
|
"loss": 4.7835,
|
|
"mean_token_accuracy": 0.2186871737241745,
|
|
"num_tokens": 26373530.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.34317831993103,
|
|
"epoch": 1.1977948546608754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048612806247161594,
|
|
"loss": 4.9683,
|
|
"mean_token_accuracy": 0.20695498436689377,
|
|
"num_tokens": 26382960.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.216606092453003,
|
|
"epoch": 1.1982124958235885,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004861177692921313,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.22145187854766846,
|
|
"num_tokens": 26392105.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.203483629226684,
|
|
"epoch": 1.1986301369863013,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048610747241677595,
|
|
"loss": 4.8691,
|
|
"mean_token_accuracy": 0.22045579850673674,
|
|
"num_tokens": 26401780.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.264136838912964,
|
|
"epoch": 1.1990477781490143,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004860971718457302,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.215750290453434,
|
|
"num_tokens": 26410290.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.299140119552613,
|
|
"epoch": 1.1994654193117273,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004860868675791743,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.21460972130298614,
|
|
"num_tokens": 26420591.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.322714519500733,
|
|
"epoch": 1.1998830604744404,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048607655961728876,
|
|
"loss": 4.8913,
|
|
"mean_token_accuracy": 0.20529481172561645,
|
|
"num_tokens": 26429453.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.300403881072998,
|
|
"epoch": 1.2003007016371534,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000486066247960254,
|
|
"loss": 4.8903,
|
|
"mean_token_accuracy": 0.21422112882137298,
|
|
"num_tokens": 26439111.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.229467344284058,
|
|
"epoch": 1.2007183427998664,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048605593260825044,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.22626828104257585,
|
|
"num_tokens": 26448071.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.320676183700561,
|
|
"epoch": 1.2011359839625793,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048604561356145875,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.20780376046895982,
|
|
"num_tokens": 26457226.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.269116306304932,
|
|
"epoch": 1.2015536251252923,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048603529082005955,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.21954833567142487,
|
|
"num_tokens": 26466052.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.320966482162476,
|
|
"epoch": 1.2019712662880053,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048602496438423354,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.21352484822273254,
|
|
"num_tokens": 26476102.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.274449110031128,
|
|
"epoch": 1.2023889074507184,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004860146342541616,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.21424734592437744,
|
|
"num_tokens": 26485775.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.247258424758911,
|
|
"epoch": 1.2028065486134314,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004860043004300244,
|
|
"loss": 4.8252,
|
|
"mean_token_accuracy": 0.21424051970243455,
|
|
"num_tokens": 26495268.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.298926973342896,
|
|
"epoch": 1.2032241897761444,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000485993962912003,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.2181801274418831,
|
|
"num_tokens": 26505253.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.279757785797119,
|
|
"epoch": 1.2036418309388572,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004859836217002783,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.21459296494722366,
|
|
"num_tokens": 26513609.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.291082859039307,
|
|
"epoch": 1.2040594721015703,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004859732767950313,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.20860320329666138,
|
|
"num_tokens": 26523565.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.260896921157837,
|
|
"epoch": 1.2044771132642833,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048596292819644315,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.21955199986696244,
|
|
"num_tokens": 26532554.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.268648481369018,
|
|
"epoch": 1.2048947544269963,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000485952575904695,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.20920979231595993,
|
|
"num_tokens": 26541474.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.238227319717407,
|
|
"epoch": 1.2053123955897094,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048594221991996814,
|
|
"loss": 4.8067,
|
|
"mean_token_accuracy": 0.2203333005309105,
|
|
"num_tokens": 26551095.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.219856119155883,
|
|
"epoch": 1.2057300367524224,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048593186024244373,
|
|
"loss": 4.8003,
|
|
"mean_token_accuracy": 0.2217871814966202,
|
|
"num_tokens": 26560144.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.175525283813476,
|
|
"epoch": 1.2061476779151352,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004859214968723033,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.2273492619395256,
|
|
"num_tokens": 26568983.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.225905799865723,
|
|
"epoch": 1.2065653190778483,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048591112980972813,
|
|
"loss": 4.7789,
|
|
"mean_token_accuracy": 0.22034153938293458,
|
|
"num_tokens": 26577229.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.280101013183594,
|
|
"epoch": 1.2069829602405613,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004859007590548997,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.21020960211753845,
|
|
"num_tokens": 26585567.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.262277317047119,
|
|
"epoch": 1.2074006014032743,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048589038460799974,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.21767779141664506,
|
|
"num_tokens": 26594656.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.236123418807983,
|
|
"epoch": 1.2078182425659874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004858800064692097,
|
|
"loss": 4.8534,
|
|
"mean_token_accuracy": 0.20786337107419967,
|
|
"num_tokens": 26604002.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.255459022521973,
|
|
"epoch": 1.2082358837287004,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048586962463871124,
|
|
"loss": 4.8503,
|
|
"mean_token_accuracy": 0.21493040323257445,
|
|
"num_tokens": 26613376.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.369153547286987,
|
|
"epoch": 1.2086535248914134,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048585923911668625,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.21130916029214858,
|
|
"num_tokens": 26623117.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.260523176193237,
|
|
"epoch": 1.2090711660541262,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048584884990331644,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.21103012412786484,
|
|
"num_tokens": 26632855.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.16309871673584,
|
|
"epoch": 1.2094888072168393,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048583845699878375,
|
|
"loss": 4.6683,
|
|
"mean_token_accuracy": 0.23508591651916505,
|
|
"num_tokens": 26641753.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.161226081848144,
|
|
"epoch": 1.2099064483795523,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004858280604032701,
|
|
"loss": 4.7933,
|
|
"mean_token_accuracy": 0.22113201767206192,
|
|
"num_tokens": 26650278.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.260244846343994,
|
|
"epoch": 1.2103240895422653,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048581766011695745,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.22149814218282698,
|
|
"num_tokens": 26658891.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.268285751342773,
|
|
"epoch": 1.2107417307049784,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048580725614002785,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.21526864320039749,
|
|
"num_tokens": 26668197.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.289354610443115,
|
|
"epoch": 1.2111593718676912,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048579684847266353,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.21388903260231018,
|
|
"num_tokens": 26676796.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.187674140930175,
|
|
"epoch": 1.2115770130304042,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004857864371150467,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.22059858292341233,
|
|
"num_tokens": 26686237.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.252602195739746,
|
|
"epoch": 1.2119946541931172,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048577602206735943,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.2172572657465935,
|
|
"num_tokens": 26695931.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.197261810302734,
|
|
"epoch": 1.2124122953558303,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004857656033297843,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.22293526083230972,
|
|
"num_tokens": 26704326.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.201439094543457,
|
|
"epoch": 1.2128299365185433,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048575518090250347,
|
|
"loss": 4.722,
|
|
"mean_token_accuracy": 0.2275531679391861,
|
|
"num_tokens": 26713000.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.289874267578125,
|
|
"epoch": 1.2132475776812564,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004857447547856996,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.20810612738132478,
|
|
"num_tokens": 26722014.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.282582855224609,
|
|
"epoch": 1.2136652188439694,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004857343249795552,
|
|
"loss": 4.8245,
|
|
"mean_token_accuracy": 0.21530905961990357,
|
|
"num_tokens": 26730975.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.181610441207885,
|
|
"epoch": 1.2140828600066822,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004857238914842526,
|
|
"loss": 4.8921,
|
|
"mean_token_accuracy": 0.21229861974716185,
|
|
"num_tokens": 26740087.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.2412412643432615,
|
|
"epoch": 1.2145005011693952,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048571345429997473,
|
|
"loss": 4.8915,
|
|
"mean_token_accuracy": 0.20686740428209305,
|
|
"num_tokens": 26749820.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.305351686477661,
|
|
"epoch": 1.2149181423321083,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048570301342690416,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.2146441236138344,
|
|
"num_tokens": 26759850.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.171995973587036,
|
|
"epoch": 1.2153357834948213,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004856925688652238,
|
|
"loss": 4.7018,
|
|
"mean_token_accuracy": 0.2293485313653946,
|
|
"num_tokens": 26769519.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.271476459503174,
|
|
"epoch": 1.2157534246575343,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048568212061511634,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.20334169417619705,
|
|
"num_tokens": 26779999.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.2734270095825195,
|
|
"epoch": 1.2161710658202471,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048567166867676475,
|
|
"loss": 4.8426,
|
|
"mean_token_accuracy": 0.2126029461622238,
|
|
"num_tokens": 26788903.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.3442364692687985,
|
|
"epoch": 1.2165887069829602,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048566121305035207,
|
|
"loss": 4.9214,
|
|
"mean_token_accuracy": 0.2162555307149887,
|
|
"num_tokens": 26799161.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.242086267471313,
|
|
"epoch": 1.2170063481456732,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048565075373606126,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.21623900085687636,
|
|
"num_tokens": 26807887.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.230453109741211,
|
|
"epoch": 1.2174239893083862,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048564029073407545,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.21752656996250153,
|
|
"num_tokens": 26816466.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.248807764053344,
|
|
"epoch": 1.2178416304710993,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004856298240445778,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.21374992281198502,
|
|
"num_tokens": 26825847.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.3171995162963865,
|
|
"epoch": 1.2182592716338123,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004856193536677515,
|
|
"loss": 4.9016,
|
|
"mean_token_accuracy": 0.20760947614908218,
|
|
"num_tokens": 26835610.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.304117107391358,
|
|
"epoch": 1.2186769127965253,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048560887960377995,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.21577996015548706,
|
|
"num_tokens": 26844319.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.290330934524536,
|
|
"epoch": 1.2190945539592382,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048559840185284647,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.2093891531229019,
|
|
"num_tokens": 26853508.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.235029172897339,
|
|
"epoch": 1.2195121951219512,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048558792041513446,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.2169165328145027,
|
|
"num_tokens": 26863268.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.293287134170532,
|
|
"epoch": 1.2199298362846642,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004855774352908273,
|
|
"loss": 4.8477,
|
|
"mean_token_accuracy": 0.2173473373055458,
|
|
"num_tokens": 26871879.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.261962413787842,
|
|
"epoch": 1.2203474774473773,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004855669464801088,
|
|
"loss": 4.9426,
|
|
"mean_token_accuracy": 0.21410669684410094,
|
|
"num_tokens": 26880920.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.300980424880981,
|
|
"epoch": 1.2207651186100903,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048555645398316237,
|
|
"loss": 4.9219,
|
|
"mean_token_accuracy": 0.21055618673563004,
|
|
"num_tokens": 26890020.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.283225059509277,
|
|
"epoch": 1.221182759772803,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004855459578001718,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.20661787390708924,
|
|
"num_tokens": 26899486.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.222373723983765,
|
|
"epoch": 1.2216004009355161,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004855354579313208,
|
|
"loss": 4.8687,
|
|
"mean_token_accuracy": 0.2197137326002121,
|
|
"num_tokens": 26908298.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.334035062789917,
|
|
"epoch": 1.2220180420982292,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004855249543767932,
|
|
"loss": 4.8789,
|
|
"mean_token_accuracy": 0.21279219835996627,
|
|
"num_tokens": 26917601.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.223217487335205,
|
|
"epoch": 1.2224356832609422,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048551444713677285,
|
|
"loss": 4.7272,
|
|
"mean_token_accuracy": 0.229127000272274,
|
|
"num_tokens": 26926368.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.283053541183472,
|
|
"epoch": 1.2228533244236552,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048550393621144374,
|
|
"loss": 4.867,
|
|
"mean_token_accuracy": 0.20644961148500443,
|
|
"num_tokens": 26935424.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.186474561691284,
|
|
"epoch": 1.2232709655863683,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004854934216009898,
|
|
"loss": 4.7826,
|
|
"mean_token_accuracy": 0.2188817083835602,
|
|
"num_tokens": 26944906.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.199680423736572,
|
|
"epoch": 1.2236886067490813,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004854829033055951,
|
|
"loss": 4.777,
|
|
"mean_token_accuracy": 0.22642798721790314,
|
|
"num_tokens": 26953709.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.195003175735474,
|
|
"epoch": 1.2241062479117941,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004854723813254439,
|
|
"loss": 4.8259,
|
|
"mean_token_accuracy": 0.21447259932756424,
|
|
"num_tokens": 26962726.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.274465608596802,
|
|
"epoch": 1.2245238890745072,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004854618556607203,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.2119511693716049,
|
|
"num_tokens": 26972519.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.265407133102417,
|
|
"epoch": 1.2249415302372202,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048545132631160856,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.21436620950698854,
|
|
"num_tokens": 26981251.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.245042705535889,
|
|
"epoch": 1.2253591713999332,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004854407932782931,
|
|
"loss": 4.8255,
|
|
"mean_token_accuracy": 0.21701659858226777,
|
|
"num_tokens": 26990707.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.244553422927856,
|
|
"epoch": 1.2257768125626463,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004854302565609582,
|
|
"loss": 4.8183,
|
|
"mean_token_accuracy": 0.21727242618799208,
|
|
"num_tokens": 26999364.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.311228179931641,
|
|
"epoch": 1.226194453725359,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048541971615978833,
|
|
"loss": 4.888,
|
|
"mean_token_accuracy": 0.20594630241394044,
|
|
"num_tokens": 27008757.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.243261384963989,
|
|
"epoch": 1.226612094888072,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048540917207496806,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.22302851229906082,
|
|
"num_tokens": 27017244.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.2677891731262205,
|
|
"epoch": 1.2270297360507851,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048539862430668204,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.2148282214999199,
|
|
"num_tokens": 27026527.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.245715045928955,
|
|
"epoch": 1.2274473772134982,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048538807285511474,
|
|
"loss": 4.8121,
|
|
"mean_token_accuracy": 0.21968334764242173,
|
|
"num_tokens": 27034890.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.243682718276977,
|
|
"epoch": 1.2278650183762112,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048537751772045103,
|
|
"loss": 4.8015,
|
|
"mean_token_accuracy": 0.22471472024917602,
|
|
"num_tokens": 27044122.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.263213109970093,
|
|
"epoch": 1.2282826595389242,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004853669589028757,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.21286704689264296,
|
|
"num_tokens": 27053929.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.26832766532898,
|
|
"epoch": 1.2287003007016373,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004853563964025734,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.21538350731134415,
|
|
"num_tokens": 27062914.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.219442224502563,
|
|
"epoch": 1.22911794186435,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048534583021972926,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.20939597636461257,
|
|
"num_tokens": 27072121.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.222753047943115,
|
|
"epoch": 1.2295355830270631,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004853352603545281,
|
|
"loss": 4.8051,
|
|
"mean_token_accuracy": 0.2162916675209999,
|
|
"num_tokens": 27081753.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.2557422637939455,
|
|
"epoch": 1.2299532241897762,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004853246868071551,
|
|
"loss": 4.8631,
|
|
"mean_token_accuracy": 0.2097421780228615,
|
|
"num_tokens": 27090942.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.221450519561768,
|
|
"epoch": 1.2303708653524892,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048531410957779533,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.21504938304424287,
|
|
"num_tokens": 27100620.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.332400941848755,
|
|
"epoch": 1.2307885065152022,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004853035286666338,
|
|
"loss": 4.8956,
|
|
"mean_token_accuracy": 0.2170274704694748,
|
|
"num_tokens": 27110370.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.258469867706299,
|
|
"epoch": 1.231206147677915,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000485292944073856,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.22694297283887863,
|
|
"num_tokens": 27119163.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.194995546340943,
|
|
"epoch": 1.231623788840628,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000485282355799647,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.2224283918738365,
|
|
"num_tokens": 27127855.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.255087375640869,
|
|
"epoch": 1.232041430003341,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048527176384419217,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.2141097828745842,
|
|
"num_tokens": 27136932.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.22685432434082,
|
|
"epoch": 1.2324590711660541,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048526116820767713,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.22041203081607819,
|
|
"num_tokens": 27146371.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.269681787490844,
|
|
"epoch": 1.2328767123287672,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004852505688902872,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.2146592766046524,
|
|
"num_tokens": 27156473.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.383332777023315,
|
|
"epoch": 1.2332943534914802,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004852399658922079,
|
|
"loss": 4.9633,
|
|
"mean_token_accuracy": 0.2109057828783989,
|
|
"num_tokens": 27165915.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.194656229019165,
|
|
"epoch": 1.2337119946541932,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004852293592136251,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.22245650589466096,
|
|
"num_tokens": 27174792.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.268296480178833,
|
|
"epoch": 1.234129635816906,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004852187488547242,
|
|
"loss": 4.8247,
|
|
"mean_token_accuracy": 0.22186411619186402,
|
|
"num_tokens": 27183785.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.353235483169556,
|
|
"epoch": 1.234547276979619,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048520813481569116,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.21075529903173446,
|
|
"num_tokens": 27193599.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.316882991790772,
|
|
"epoch": 1.2349649181423321,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004851975170967116,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.21430208832025527,
|
|
"num_tokens": 27202191.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.263414192199707,
|
|
"epoch": 1.2353825593050451,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004851868956979715,
|
|
"loss": 4.8772,
|
|
"mean_token_accuracy": 0.21270706951618196,
|
|
"num_tokens": 27210833.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.221717071533203,
|
|
"epoch": 1.2358002004677582,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004851762706196568,
|
|
"loss": 4.8186,
|
|
"mean_token_accuracy": 0.20993368625640868,
|
|
"num_tokens": 27220053.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.315036916732788,
|
|
"epoch": 1.236217841630471,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048516564186195353,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.21809660494327546,
|
|
"num_tokens": 27229370.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.153961658477783,
|
|
"epoch": 1.236635482793184,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048515500942504763,
|
|
"loss": 4.7594,
|
|
"mean_token_accuracy": 0.2274767979979515,
|
|
"num_tokens": 27238923.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.289598226547241,
|
|
"epoch": 1.237053123955897,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048514437330912544,
|
|
"loss": 4.8673,
|
|
"mean_token_accuracy": 0.21737243235111237,
|
|
"num_tokens": 27247929.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.269976425170898,
|
|
"epoch": 1.23747076511861,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048513373351437294,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.21926791816949845,
|
|
"num_tokens": 27257455.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.221728420257568,
|
|
"epoch": 1.2378884062813231,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048512309004097653,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.21339675784111023,
|
|
"num_tokens": 27267718.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.2137127876281735,
|
|
"epoch": 1.2383060474440362,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004851124428891226,
|
|
"loss": 4.7828,
|
|
"mean_token_accuracy": 0.22040338069200516,
|
|
"num_tokens": 27276706.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.174860572814941,
|
|
"epoch": 1.2387236886067492,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004851017920589973,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.22143872529268266,
|
|
"num_tokens": 27285389.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.279577922821045,
|
|
"epoch": 1.239141329769462,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004850911375507873,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.2171168550848961,
|
|
"num_tokens": 27295529.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.309674072265625,
|
|
"epoch": 1.239558970932175,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048508047936467907,
|
|
"loss": 4.9408,
|
|
"mean_token_accuracy": 0.21387905031442642,
|
|
"num_tokens": 27305358.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.258985805511474,
|
|
"epoch": 1.239976612094888,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048506981750085914,
|
|
"loss": 4.7588,
|
|
"mean_token_accuracy": 0.22130178064107894,
|
|
"num_tokens": 27314765.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.297021675109863,
|
|
"epoch": 1.240394253257601,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048505915195951423,
|
|
"loss": 4.843,
|
|
"mean_token_accuracy": 0.21377589255571366,
|
|
"num_tokens": 27324227.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.280306100845337,
|
|
"epoch": 1.2408118944203141,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048504848274083095,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.21156216859817506,
|
|
"num_tokens": 27332890.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.2137330055236815,
|
|
"epoch": 1.241229535583027,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048503780984499625,
|
|
"loss": 4.773,
|
|
"mean_token_accuracy": 0.2277920052409172,
|
|
"num_tokens": 27342411.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.218091869354248,
|
|
"epoch": 1.24164717674574,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004850271332721968,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.21713701039552688,
|
|
"num_tokens": 27351649.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.202201461791992,
|
|
"epoch": 1.242064817908453,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004850164530226196,
|
|
"loss": 4.7446,
|
|
"mean_token_accuracy": 0.2170140728354454,
|
|
"num_tokens": 27360093.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.213349342346191,
|
|
"epoch": 1.242482459071166,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004850057690964515,
|
|
"loss": 4.7842,
|
|
"mean_token_accuracy": 0.21863021701574326,
|
|
"num_tokens": 27368593.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.234057331085205,
|
|
"epoch": 1.242900100233879,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048499508149387973,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.21050596237182617,
|
|
"num_tokens": 27378126.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.231464529037476,
|
|
"epoch": 1.2433177413965921,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048498439021509124,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.22138206362724305,
|
|
"num_tokens": 27386225.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.324013996124267,
|
|
"epoch": 1.2437353825593052,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004849736952602732,
|
|
"loss": 4.8598,
|
|
"mean_token_accuracy": 0.21405726820230483,
|
|
"num_tokens": 27395629.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.290941572189331,
|
|
"epoch": 1.244153023722018,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000484962996629613,
|
|
"loss": 4.8676,
|
|
"mean_token_accuracy": 0.22351083606481553,
|
|
"num_tokens": 27404431.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.236309242248535,
|
|
"epoch": 1.244570664884731,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048495229432329775,
|
|
"loss": 4.8683,
|
|
"mean_token_accuracy": 0.2175241470336914,
|
|
"num_tokens": 27412944.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.215290594100952,
|
|
"epoch": 1.244988306047444,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048494158834151485,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.22120076268911362,
|
|
"num_tokens": 27422006.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.31653094291687,
|
|
"epoch": 1.245405947210157,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048493087868445176,
|
|
"loss": 4.856,
|
|
"mean_token_accuracy": 0.21661407351493836,
|
|
"num_tokens": 27431568.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.301338338851929,
|
|
"epoch": 1.24582358837287,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048492016535229594,
|
|
"loss": 4.8128,
|
|
"mean_token_accuracy": 0.21790147572755814,
|
|
"num_tokens": 27440471.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.1754223823547365,
|
|
"epoch": 1.246241229535583,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004849094483452349,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.22413057386875151,
|
|
"num_tokens": 27450209.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.285812473297119,
|
|
"epoch": 1.246658870698296,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004848987276634564,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.2068515956401825,
|
|
"num_tokens": 27458876.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.332606458663941,
|
|
"epoch": 1.247076511861009,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048488800330714795,
|
|
"loss": 4.8903,
|
|
"mean_token_accuracy": 0.21899379640817643,
|
|
"num_tokens": 27467526.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.26704592704773,
|
|
"epoch": 1.247494153023722,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048487727527649733,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.21874541640281678,
|
|
"num_tokens": 27477063.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.272008562088013,
|
|
"epoch": 1.247911794186435,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048486654357169246,
|
|
"loss": 4.8737,
|
|
"mean_token_accuracy": 0.2165556237101555,
|
|
"num_tokens": 27486243.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.2966796875,
|
|
"epoch": 1.248329435349148,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004848558081929211,
|
|
"loss": 4.8689,
|
|
"mean_token_accuracy": 0.21633549630641938,
|
|
"num_tokens": 27495491.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.2518219470977785,
|
|
"epoch": 1.2487470765118611,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004848450691403712,
|
|
"loss": 4.8573,
|
|
"mean_token_accuracy": 0.2147799015045166,
|
|
"num_tokens": 27505105.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.211459302902222,
|
|
"epoch": 1.249164717674574,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004848343264142307,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.2177164927124977,
|
|
"num_tokens": 27514457.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.304086923599243,
|
|
"epoch": 1.249582358837287,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004848235800146879,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.21292440444231034,
|
|
"num_tokens": 27524073.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.242766618728638,
|
|
"epoch": 1.25,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004848128299419306,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.2133875235915184,
|
|
"num_tokens": 27532840.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.293502330780029,
|
|
"epoch": 1.250417641162713,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048480207619614726,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.2111164554953575,
|
|
"num_tokens": 27541775.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.273660278320312,
|
|
"epoch": 1.250835282325426,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000484791318777526,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.22218123972415924,
|
|
"num_tokens": 27550668.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.267524242401123,
|
|
"epoch": 1.2512529234881389,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048478055768625517,
|
|
"loss": 4.8761,
|
|
"mean_token_accuracy": 0.2147900268435478,
|
|
"num_tokens": 27560255.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.196520376205444,
|
|
"epoch": 1.251670564650852,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048476979292252323,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.21789973229169846,
|
|
"num_tokens": 27569028.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.247531175613403,
|
|
"epoch": 1.252088205813565,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004847590244865185,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.22580423206090927,
|
|
"num_tokens": 27577396.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.272535991668701,
|
|
"epoch": 1.252505846976278,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048474825237842964,
|
|
"loss": 4.9002,
|
|
"mean_token_accuracy": 0.21001444905996322,
|
|
"num_tokens": 27586710.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.174076509475708,
|
|
"epoch": 1.252923488138991,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000484737476598445,
|
|
"loss": 4.7453,
|
|
"mean_token_accuracy": 0.2232905238866806,
|
|
"num_tokens": 27594842.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.252923488138991,
|
|
"eval_entropy": 4.947821310177064,
|
|
"eval_loss": 4.862187385559082,
|
|
"eval_mean_token_accuracy": 0.2268059364038866,
|
|
"eval_num_tokens": 27594842.0,
|
|
"eval_runtime": 20.839,
|
|
"eval_samples_per_second": 1812.127,
|
|
"eval_steps_per_second": 226.546,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.1005778312683105,
|
|
"epoch": 1.253341129301704,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048472669714675357,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.22038424015045166,
|
|
"num_tokens": 27604661.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.200062322616577,
|
|
"epoch": 1.253758770464417,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048471591402354374,
|
|
"loss": 4.7021,
|
|
"mean_token_accuracy": 0.22987406551837922,
|
|
"num_tokens": 27614015.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.3480723857879635,
|
|
"epoch": 1.25417641162713,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048470512722900434,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.2089667946100235,
|
|
"num_tokens": 27624164.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.223937559127807,
|
|
"epoch": 1.254594052789843,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048469433676332434,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.2230541154742241,
|
|
"num_tokens": 27633993.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.214732933044433,
|
|
"epoch": 1.255011693952556,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004846835426266926,
|
|
"loss": 4.8695,
|
|
"mean_token_accuracy": 0.21150156557559968,
|
|
"num_tokens": 27643772.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.269437980651856,
|
|
"epoch": 1.255429335115269,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004846727448192981,
|
|
"loss": 4.7622,
|
|
"mean_token_accuracy": 0.2187471568584442,
|
|
"num_tokens": 27652511.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.238465070724487,
|
|
"epoch": 1.255846976277982,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048466194334132964,
|
|
"loss": 4.7559,
|
|
"mean_token_accuracy": 0.21976885348558425,
|
|
"num_tokens": 27661589.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.18982949256897,
|
|
"epoch": 1.2562646174406948,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048465113819297654,
|
|
"loss": 4.8353,
|
|
"mean_token_accuracy": 0.22397416830062866,
|
|
"num_tokens": 27670299.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.2916679859161375,
|
|
"epoch": 1.2566822586034079,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000484640329374428,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.20885302424430846,
|
|
"num_tokens": 27679375.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.206171369552612,
|
|
"epoch": 1.257099899766121,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048462951688587317,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.2303939864039421,
|
|
"num_tokens": 27688754.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.220288848876953,
|
|
"epoch": 1.257517540928834,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048461870072750117,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.21035558879375457,
|
|
"num_tokens": 27697799.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.225629997253418,
|
|
"epoch": 1.257935182091547,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048460788089950164,
|
|
"loss": 4.7589,
|
|
"mean_token_accuracy": 0.22318170517683028,
|
|
"num_tokens": 27707239.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.254047536849976,
|
|
"epoch": 1.25835282325426,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004845970574020637,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.22046903222799302,
|
|
"num_tokens": 27716027.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.22706241607666,
|
|
"epoch": 1.258770464416973,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004845862302353771,
|
|
"loss": 4.7059,
|
|
"mean_token_accuracy": 0.23316124081611633,
|
|
"num_tokens": 27724849.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.224192476272583,
|
|
"epoch": 1.2591881055796859,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048457539939963126,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.2243426725268364,
|
|
"num_tokens": 27733899.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.2015691757202145,
|
|
"epoch": 1.259605746742399,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048456456489501574,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.21627393513917922,
|
|
"num_tokens": 27743967.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.210313606262207,
|
|
"epoch": 1.260023387905112,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004845537267217202,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.21880790144205092,
|
|
"num_tokens": 27753105.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.305580139160156,
|
|
"epoch": 1.260441029067825,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004845428848799346,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.21694325506687165,
|
|
"num_tokens": 27762771.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.222398853302002,
|
|
"epoch": 1.260858670230538,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004845320393698484,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.22849614769220353,
|
|
"num_tokens": 27771653.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.2294182777404785,
|
|
"epoch": 1.2612763113932508,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004845211901916517,
|
|
"loss": 4.8551,
|
|
"mean_token_accuracy": 0.22002785205841063,
|
|
"num_tokens": 27780585.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.2122314453125,
|
|
"epoch": 1.2616939525559638,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048451033734553444,
|
|
"loss": 4.7847,
|
|
"mean_token_accuracy": 0.22075446844100952,
|
|
"num_tokens": 27790625.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.42040638923645,
|
|
"epoch": 1.2621115937186769,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004844994808316864,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.20570729970932006,
|
|
"num_tokens": 27800948.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.353004026412964,
|
|
"epoch": 1.26252923488139,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004844886206502979,
|
|
"loss": 4.9155,
|
|
"mean_token_accuracy": 0.21498710960149764,
|
|
"num_tokens": 27809973.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.297404670715332,
|
|
"epoch": 1.262946876044103,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048447775680155884,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.21065747141838073,
|
|
"num_tokens": 27818738.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.225978040695191,
|
|
"epoch": 1.263364517206816,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048446688928565956,
|
|
"loss": 4.8021,
|
|
"mean_token_accuracy": 0.22742349952459334,
|
|
"num_tokens": 27827537.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.381576919555664,
|
|
"epoch": 1.263782158369529,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004844560181027903,
|
|
"loss": 4.9726,
|
|
"mean_token_accuracy": 0.2019422948360443,
|
|
"num_tokens": 27837498.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.288975095748901,
|
|
"epoch": 1.2641997995322418,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004844451432531412,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.21545517891645433,
|
|
"num_tokens": 27847547.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.263050651550293,
|
|
"epoch": 1.2646174406949549,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004844342647369028,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.2211300551891327,
|
|
"num_tokens": 27856468.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.309576177597046,
|
|
"epoch": 1.2650350818576679,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048442338255426555,
|
|
"loss": 4.962,
|
|
"mean_token_accuracy": 0.2141152173280716,
|
|
"num_tokens": 27865324.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.2453460693359375,
|
|
"epoch": 1.265452723020381,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004844124967054199,
|
|
"loss": 4.8411,
|
|
"mean_token_accuracy": 0.21606793701648713,
|
|
"num_tokens": 27875364.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.284607601165772,
|
|
"epoch": 1.265870364183094,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004844016071905564,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.22387004196643828,
|
|
"num_tokens": 27884739.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.159937572479248,
|
|
"epoch": 1.2662880053458068,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004843907140098656,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.22778168618679046,
|
|
"num_tokens": 27893235.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.201054239273072,
|
|
"epoch": 1.2667056465085198,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004843798171635384,
|
|
"loss": 4.8541,
|
|
"mean_token_accuracy": 0.22084476947784423,
|
|
"num_tokens": 27902090.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.276468706130982,
|
|
"epoch": 1.2671232876712328,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004843689166517655,
|
|
"loss": 4.8196,
|
|
"mean_token_accuracy": 0.2181324452161789,
|
|
"num_tokens": 27910702.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.297541522979737,
|
|
"epoch": 1.2675409288339459,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004843580124747377,
|
|
"loss": 4.8442,
|
|
"mean_token_accuracy": 0.21936260163784027,
|
|
"num_tokens": 27919296.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.246033096313477,
|
|
"epoch": 1.267958569996659,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048434710463264585,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.22765704542398452,
|
|
"num_tokens": 27929074.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.2782666206359865,
|
|
"epoch": 1.268376211159372,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048433619312568095,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.21559595912694932,
|
|
"num_tokens": 27938227.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.324566221237182,
|
|
"epoch": 1.268793852322085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048432527795403405,
|
|
"loss": 4.8824,
|
|
"mean_token_accuracy": 0.21429187208414077,
|
|
"num_tokens": 27948050.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.2870927333831785,
|
|
"epoch": 1.2692114934847978,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004843143591178962,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.2107207179069519,
|
|
"num_tokens": 27957702.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.326660680770874,
|
|
"epoch": 1.2696291346475108,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048430343661745844,
|
|
"loss": 4.9348,
|
|
"mean_token_accuracy": 0.2085317924618721,
|
|
"num_tokens": 27966085.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.336013460159302,
|
|
"epoch": 1.2700467758102238,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004842925104529122,
|
|
"loss": 4.9111,
|
|
"mean_token_accuracy": 0.21338675171136856,
|
|
"num_tokens": 27976228.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.296880388259888,
|
|
"epoch": 1.2704644169729369,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048428158062444857,
|
|
"loss": 4.8329,
|
|
"mean_token_accuracy": 0.21821285486221315,
|
|
"num_tokens": 27984910.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.294002342224121,
|
|
"epoch": 1.27088205813565,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048427064713225894,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.21626504957675935,
|
|
"num_tokens": 27993767.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.292312669754028,
|
|
"epoch": 1.2712996992983627,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048425970997653477,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.21599121987819672,
|
|
"num_tokens": 28002587.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.264909934997559,
|
|
"epoch": 1.2717173404610758,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004842487691574675,
|
|
"loss": 4.8805,
|
|
"mean_token_accuracy": 0.2152280405163765,
|
|
"num_tokens": 28011598.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.311469078063965,
|
|
"epoch": 1.2721349816237888,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048423782467524865,
|
|
"loss": 4.955,
|
|
"mean_token_accuracy": 0.2150879129767418,
|
|
"num_tokens": 28021321.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.269651746749878,
|
|
"epoch": 1.2725526227865018,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004842268765300698,
|
|
"loss": 4.8715,
|
|
"mean_token_accuracy": 0.21869305074214934,
|
|
"num_tokens": 28031009.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.303914308547974,
|
|
"epoch": 1.2729702639492149,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048421592472212263,
|
|
"loss": 4.9188,
|
|
"mean_token_accuracy": 0.20813646912574768,
|
|
"num_tokens": 28040330.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.29559645652771,
|
|
"epoch": 1.273387905111928,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048420496925159886,
|
|
"loss": 4.8561,
|
|
"mean_token_accuracy": 0.21195922791957855,
|
|
"num_tokens": 28048952.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.281173849105835,
|
|
"epoch": 1.273805546274641,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004841940101186903,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.2144905999302864,
|
|
"num_tokens": 28058803.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.30088324546814,
|
|
"epoch": 1.2742231874373537,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004841830473235888,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.2236664205789566,
|
|
"num_tokens": 28067978.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.205398225784302,
|
|
"epoch": 1.2746408286000668,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048417208086648625,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.22074113935232162,
|
|
"num_tokens": 28077229.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.267566156387329,
|
|
"epoch": 1.2750584697627798,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004841611107475746,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.21653033494949342,
|
|
"num_tokens": 28086316.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.424878406524658,
|
|
"epoch": 1.2754761109254928,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000484150136967046,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.2095193773508072,
|
|
"num_tokens": 28096914.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.336724662780762,
|
|
"epoch": 1.2758937520882059,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004841391595250925,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.21245651692152023,
|
|
"num_tokens": 28106532.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.278273391723633,
|
|
"epoch": 1.2763113932509187,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004841281784219063,
|
|
"loss": 4.8481,
|
|
"mean_token_accuracy": 0.2140345185995102,
|
|
"num_tokens": 28115052.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.233472490310669,
|
|
"epoch": 1.2767290344136317,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048411719365767947,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.2208313226699829,
|
|
"num_tokens": 28123571.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.194874048233032,
|
|
"epoch": 1.2771466755763448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048410620523260455,
|
|
"loss": 4.7354,
|
|
"mean_token_accuracy": 0.22771790474653245,
|
|
"num_tokens": 28131973.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.302814149856568,
|
|
"epoch": 1.2775643167390578,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048409521314687383,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.21472862958908082,
|
|
"num_tokens": 28140965.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.25965142250061,
|
|
"epoch": 1.2779819579017708,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004840842174006797,
|
|
"loss": 4.9123,
|
|
"mean_token_accuracy": 0.21593084633350373,
|
|
"num_tokens": 28150652.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.387570762634278,
|
|
"epoch": 1.2783995990644839,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004840732179942146,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.2015869840979576,
|
|
"num_tokens": 28160830.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.348824691772461,
|
|
"epoch": 1.278817240227197,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004840622149276712,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.22054090797901155,
|
|
"num_tokens": 28169423.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.267931032180786,
|
|
"epoch": 1.2792348813899097,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004840512082012421,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.21871915757656096,
|
|
"num_tokens": 28178997.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.272339630126953,
|
|
"epoch": 1.2796525225526227,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048404019781511995,
|
|
"loss": 4.8135,
|
|
"mean_token_accuracy": 0.2188413545489311,
|
|
"num_tokens": 28188014.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.272914409637451,
|
|
"epoch": 1.2800701637153358,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048402918376949753,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.2102026581764221,
|
|
"num_tokens": 28197800.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.264981603622436,
|
|
"epoch": 1.2804878048780488,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004840181660645676,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.22524489015340804,
|
|
"num_tokens": 28207388.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.23778920173645,
|
|
"epoch": 1.2809054460407618,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004840071447005231,
|
|
"loss": 4.8567,
|
|
"mean_token_accuracy": 0.2207813650369644,
|
|
"num_tokens": 28216774.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.253377103805542,
|
|
"epoch": 1.2813230872034747,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000483996119677557,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.2192865714430809,
|
|
"num_tokens": 28226402.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.250535106658935,
|
|
"epoch": 1.281740728366188,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048398509099586225,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.21187101006507875,
|
|
"num_tokens": 28235890.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.254048585891724,
|
|
"epoch": 1.2821583695289007,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048397405865563186,
|
|
"loss": 4.8168,
|
|
"mean_token_accuracy": 0.21759405583143235,
|
|
"num_tokens": 28244121.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.360864448547363,
|
|
"epoch": 1.2825760106916138,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004839630226570591,
|
|
"loss": 4.8944,
|
|
"mean_token_accuracy": 0.2166463702917099,
|
|
"num_tokens": 28252259.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.252173662185669,
|
|
"epoch": 1.2829936518543268,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000483951983000337,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.22253577262163163,
|
|
"num_tokens": 28262199.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.28775577545166,
|
|
"epoch": 1.2834112930170398,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000483940939685659,
|
|
"loss": 4.8602,
|
|
"mean_token_accuracy": 0.21447569727897645,
|
|
"num_tokens": 28271120.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.30679612159729,
|
|
"epoch": 1.2838289341797529,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048392989271321836,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.21961030513048171,
|
|
"num_tokens": 28279766.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.258337116241455,
|
|
"epoch": 1.2842465753424657,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004839188420832084,
|
|
"loss": 4.8347,
|
|
"mean_token_accuracy": 0.226750648021698,
|
|
"num_tokens": 28288872.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.176149034500122,
|
|
"epoch": 1.2846642165051787,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048390778779582266,
|
|
"loss": 4.7968,
|
|
"mean_token_accuracy": 0.2171001136302948,
|
|
"num_tokens": 28297719.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.293716287612915,
|
|
"epoch": 1.2850818576678917,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048389672985125467,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.21746450811624526,
|
|
"num_tokens": 28306547.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.241091585159301,
|
|
"epoch": 1.2854994988306048,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004838856682496979,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.21917952746152877,
|
|
"num_tokens": 28316387.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.3222192287445065,
|
|
"epoch": 1.2859171399933178,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004838746029913461,
|
|
"loss": 4.9021,
|
|
"mean_token_accuracy": 0.20875128507614135,
|
|
"num_tokens": 28326642.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.268610191345215,
|
|
"epoch": 1.2863347811560306,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000483863534076393,
|
|
"loss": 4.7977,
|
|
"mean_token_accuracy": 0.22220593690872192,
|
|
"num_tokens": 28335647.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.2114410400390625,
|
|
"epoch": 1.2867524223187439,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004838524615050323,
|
|
"loss": 4.8345,
|
|
"mean_token_accuracy": 0.2180909350514412,
|
|
"num_tokens": 28344536.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.277103996276855,
|
|
"epoch": 1.2871700634814567,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004838413852774579,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.21599063277244568,
|
|
"num_tokens": 28354121.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.215767478942871,
|
|
"epoch": 1.2875877046441697,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048383030539386355,
|
|
"loss": 4.8121,
|
|
"mean_token_accuracy": 0.22215283811092376,
|
|
"num_tokens": 28362215.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.324783802032471,
|
|
"epoch": 1.2880053458068828,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004838192218544434,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.21697398126125336,
|
|
"num_tokens": 28371323.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.384504175186157,
|
|
"epoch": 1.2884229869695958,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004838081346593915,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.21226252764463424,
|
|
"num_tokens": 28380333.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.2508749008178714,
|
|
"epoch": 1.2888406281323088,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048379704380890177,
|
|
"loss": 4.8507,
|
|
"mean_token_accuracy": 0.20811833143234254,
|
|
"num_tokens": 28389021.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.197482776641846,
|
|
"epoch": 1.2892582692950216,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004837859493031685,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.21593234091997146,
|
|
"num_tokens": 28398309.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.15800108909607,
|
|
"epoch": 1.2896759104577347,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048377485114238576,
|
|
"loss": 4.6887,
|
|
"mean_token_accuracy": 0.22763103544712066,
|
|
"num_tokens": 28406946.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.2332030773162845,
|
|
"epoch": 1.2900935516204477,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004837637493267481,
|
|
"loss": 4.8435,
|
|
"mean_token_accuracy": 0.22063682675361634,
|
|
"num_tokens": 28416561.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.239918518066406,
|
|
"epoch": 1.2905111927831607,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004837526438564496,
|
|
"loss": 4.6741,
|
|
"mean_token_accuracy": 0.2374308079481125,
|
|
"num_tokens": 28425133.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.240010166168213,
|
|
"epoch": 1.2909288339458738,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004837415347316849,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.21092569679021836,
|
|
"num_tokens": 28434282.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.306089687347412,
|
|
"epoch": 1.2913464751085866,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048373042195264836,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.2120417982339859,
|
|
"num_tokens": 28443149.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.368785238265991,
|
|
"epoch": 1.2917641162712998,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004837193055195344,
|
|
"loss": 4.9272,
|
|
"mean_token_accuracy": 0.20348942875862122,
|
|
"num_tokens": 28453294.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.267763900756836,
|
|
"epoch": 1.2921817574340126,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048370818543253793,
|
|
"loss": 4.7783,
|
|
"mean_token_accuracy": 0.2266727238893509,
|
|
"num_tokens": 28462518.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.257400321960449,
|
|
"epoch": 1.2925993985967257,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048369706169185334,
|
|
"loss": 4.8547,
|
|
"mean_token_accuracy": 0.2194067120552063,
|
|
"num_tokens": 28470674.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.266986751556397,
|
|
"epoch": 1.2930170397594387,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048368593429767555,
|
|
"loss": 4.8689,
|
|
"mean_token_accuracy": 0.21773144751787185,
|
|
"num_tokens": 28480088.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.296182155609131,
|
|
"epoch": 1.2934346809221517,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048367480325019923,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.21523147970438003,
|
|
"num_tokens": 28489533.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.315198707580566,
|
|
"epoch": 1.2938523220848648,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048366366854961937,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.21588331907987596,
|
|
"num_tokens": 28498758.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.223083019256592,
|
|
"epoch": 1.2942699632475776,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004836525301961307,
|
|
"loss": 4.8128,
|
|
"mean_token_accuracy": 0.2188344269990921,
|
|
"num_tokens": 28507633.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.207599639892578,
|
|
"epoch": 1.2946876044102906,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004836413881899285,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.21737829893827437,
|
|
"num_tokens": 28516905.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.316872406005859,
|
|
"epoch": 1.2951052455730037,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004836302425312075,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.20810219943523406,
|
|
"num_tokens": 28527419.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.200619506835937,
|
|
"epoch": 1.2955228867357167,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004836190932201631,
|
|
"loss": 4.6769,
|
|
"mean_token_accuracy": 0.22887225449085236,
|
|
"num_tokens": 28535950.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.234211206436157,
|
|
"epoch": 1.2959405278984297,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048360794025699026,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.22344177961349487,
|
|
"num_tokens": 28544341.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.314818286895752,
|
|
"epoch": 1.2963581690611425,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004835967836418844,
|
|
"loss": 4.8856,
|
|
"mean_token_accuracy": 0.2131818041205406,
|
|
"num_tokens": 28553805.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.297514915466309,
|
|
"epoch": 1.2967758102238558,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004835856233750407,
|
|
"loss": 4.775,
|
|
"mean_token_accuracy": 0.21669580936431884,
|
|
"num_tokens": 28562224.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.193550300598145,
|
|
"epoch": 1.2971934513865686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048357445945665465,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.22293675243854522,
|
|
"num_tokens": 28570771.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.277394008636475,
|
|
"epoch": 1.2976110925492816,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004835632918869215,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.21394737362861632,
|
|
"num_tokens": 28580447.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.363695383071899,
|
|
"epoch": 1.2980287337119947,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000483552120666037,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.21820655316114426,
|
|
"num_tokens": 28590472.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.295226955413819,
|
|
"epoch": 1.2984463748747077,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048354094579419656,
|
|
"loss": 4.8181,
|
|
"mean_token_accuracy": 0.21800008714199065,
|
|
"num_tokens": 28599201.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.252237319946289,
|
|
"epoch": 1.2988640160374207,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004835297672715958,
|
|
"loss": 4.8751,
|
|
"mean_token_accuracy": 0.20888104885816575,
|
|
"num_tokens": 28608499.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.253686475753784,
|
|
"epoch": 1.2992816572001336,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048351858509843054,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.2257247045636177,
|
|
"num_tokens": 28618310.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.308226871490478,
|
|
"epoch": 1.2996992983628466,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004835073992748964,
|
|
"loss": 4.8705,
|
|
"mean_token_accuracy": 0.20634905993938446,
|
|
"num_tokens": 28627374.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.247251033782959,
|
|
"epoch": 1.3001169395255596,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048349620980118926,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.21606418937444688,
|
|
"num_tokens": 28636331.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.246735239028931,
|
|
"epoch": 1.3005345806882727,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000483485016677505,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.2184160605072975,
|
|
"num_tokens": 28645006.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.247215032577515,
|
|
"epoch": 1.3009522218509857,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048347381990403957,
|
|
"loss": 4.8368,
|
|
"mean_token_accuracy": 0.21925996541976928,
|
|
"num_tokens": 28653202.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.291823863983154,
|
|
"epoch": 1.3013698630136985,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048346261948098895,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.2193479508161545,
|
|
"num_tokens": 28662701.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.27932071685791,
|
|
"epoch": 1.3017875041764118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048345141540854933,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.21539936810731888,
|
|
"num_tokens": 28670967.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.315127801895142,
|
|
"epoch": 1.3022051453391246,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048344020768691673,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.22603441178798675,
|
|
"num_tokens": 28679458.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.223771953582764,
|
|
"epoch": 1.3026227865018376,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004834289963162874,
|
|
"loss": 4.7836,
|
|
"mean_token_accuracy": 0.22036585956811905,
|
|
"num_tokens": 28688497.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.239935207366943,
|
|
"epoch": 1.3030404276645506,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004834177812968576,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.20909491181373596,
|
|
"num_tokens": 28697729.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.375596380233764,
|
|
"epoch": 1.3034580688272637,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048340656262882366,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.20808393508195877,
|
|
"num_tokens": 28707778.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.28636999130249,
|
|
"epoch": 1.3038757099899767,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048339534031238197,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.2122778207063675,
|
|
"num_tokens": 28718010.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.27435269355774,
|
|
"epoch": 1.3042933511526895,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000483384114347729,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.2230281800031662,
|
|
"num_tokens": 28727279.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.29445447921753,
|
|
"epoch": 1.3047109923154026,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004833728847350613,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.21973117738962172,
|
|
"num_tokens": 28736510.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.318698215484619,
|
|
"epoch": 1.3051286334781156,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048336165147457537,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.21478508561849594,
|
|
"num_tokens": 28745226.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.323725175857544,
|
|
"epoch": 1.3055462746408286,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004833504145664681,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.2212085619568825,
|
|
"num_tokens": 28754052.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.244320631027222,
|
|
"epoch": 1.3059639158035417,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048333917401093587,
|
|
"loss": 4.7839,
|
|
"mean_token_accuracy": 0.22470874935388566,
|
|
"num_tokens": 28763580.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.2558670997619625,
|
|
"epoch": 1.3063815569662545,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048332792980817563,
|
|
"loss": 4.7975,
|
|
"mean_token_accuracy": 0.21908804029226303,
|
|
"num_tokens": 28772540.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.26675968170166,
|
|
"epoch": 1.3067991981289677,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004833166819583843,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.21845584809780122,
|
|
"num_tokens": 28782027.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.312422180175782,
|
|
"epoch": 1.3072168392916805,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004833054304617586,
|
|
"loss": 4.8287,
|
|
"mean_token_accuracy": 0.21592971831560134,
|
|
"num_tokens": 28791724.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.290583515167237,
|
|
"epoch": 1.3076344804543936,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048329417531849567,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.21449677348136903,
|
|
"num_tokens": 28800681.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.300615739822388,
|
|
"epoch": 1.3080521216171066,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048328291652879245,
|
|
"loss": 4.9144,
|
|
"mean_token_accuracy": 0.2169949844479561,
|
|
"num_tokens": 28810121.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.232244205474854,
|
|
"epoch": 1.3084697627798196,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048327165409284614,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.21605213582515717,
|
|
"num_tokens": 28819287.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.36219801902771,
|
|
"epoch": 1.3088874039425327,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004832603880108537,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.20249463319778443,
|
|
"num_tokens": 28828907.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.337918615341186,
|
|
"epoch": 1.3093050451052455,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048324911828301256,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.21442092210054398,
|
|
"num_tokens": 28839087.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.363365507125854,
|
|
"epoch": 1.3097226862679585,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004832378449095199,
|
|
"loss": 4.9317,
|
|
"mean_token_accuracy": 0.21380549520254136,
|
|
"num_tokens": 28848956.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.269158220291137,
|
|
"epoch": 1.3101403274306715,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004832265678905731,
|
|
"loss": 4.8394,
|
|
"mean_token_accuracy": 0.21623616218566893,
|
|
"num_tokens": 28858105.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.284167098999023,
|
|
"epoch": 1.3105579685933846,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004832152872263697,
|
|
"loss": 4.9664,
|
|
"mean_token_accuracy": 0.20575012713670732,
|
|
"num_tokens": 28867539.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.259546947479248,
|
|
"epoch": 1.3109756097560976,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004832040029171069,
|
|
"loss": 4.7914,
|
|
"mean_token_accuracy": 0.21687899827957152,
|
|
"num_tokens": 28876536.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.342623519897461,
|
|
"epoch": 1.3113932509188104,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048319271496298255,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.20733736604452133,
|
|
"num_tokens": 28885354.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.296169710159302,
|
|
"epoch": 1.3118108920815237,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048318142336419413,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.21023851186037062,
|
|
"num_tokens": 28894181.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.260473918914795,
|
|
"epoch": 1.3122285332442365,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048317012812093926,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.22634583711624146,
|
|
"num_tokens": 28903803.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.305691766738891,
|
|
"epoch": 1.3126461744069495,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004831588292334157,
|
|
"loss": 4.8937,
|
|
"mean_token_accuracy": 0.21844163537025452,
|
|
"num_tokens": 28913192.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.2753456115722654,
|
|
"epoch": 1.3130638155696626,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004831475267018213,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.22416060715913771,
|
|
"num_tokens": 28922413.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.300964212417602,
|
|
"epoch": 1.3134814567323756,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004831362205263538,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.215138578414917,
|
|
"num_tokens": 28933589.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.266475582122803,
|
|
"epoch": 1.3138990978950886,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004831249107072114,
|
|
"loss": 4.841,
|
|
"mean_token_accuracy": 0.22268788367509842,
|
|
"num_tokens": 28942458.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.268698358535767,
|
|
"epoch": 1.3143167390578014,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048311359724459175,
|
|
"loss": 4.8192,
|
|
"mean_token_accuracy": 0.22037870436906815,
|
|
"num_tokens": 28951834.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.28041090965271,
|
|
"epoch": 1.3147343802205145,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048310228013869323,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.21924296915531158,
|
|
"num_tokens": 28960885.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.272366857528686,
|
|
"epoch": 1.3151520213832275,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004830909593897137,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.22154124826192856,
|
|
"num_tokens": 28970922.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.309080266952515,
|
|
"epoch": 1.3155696625459405,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004830796349978515,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.2091851457953453,
|
|
"num_tokens": 28980873.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.346289205551147,
|
|
"epoch": 1.3159873037086536,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004830683069633048,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.20601918846368789,
|
|
"num_tokens": 28989876.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.293038463592529,
|
|
"epoch": 1.3164049448713664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004830569752862719,
|
|
"loss": 4.8598,
|
|
"mean_token_accuracy": 0.2191443532705307,
|
|
"num_tokens": 28999480.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.2601845264434814,
|
|
"epoch": 1.3168225860340796,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048304563996695127,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.21099896132946014,
|
|
"num_tokens": 29009855.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.295566558837891,
|
|
"epoch": 1.3172402271967925,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048303430100554126,
|
|
"loss": 4.7549,
|
|
"mean_token_accuracy": 0.2277539402246475,
|
|
"num_tokens": 29018506.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.298423862457275,
|
|
"epoch": 1.3176578683595055,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004830229584022404,
|
|
"loss": 4.8107,
|
|
"mean_token_accuracy": 0.2139461100101471,
|
|
"num_tokens": 29027560.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.166060829162598,
|
|
"epoch": 1.3180755095222185,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004830116121572472,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.2176080033183098,
|
|
"num_tokens": 29036038.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.268411684036255,
|
|
"epoch": 1.3184931506849316,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004830002622707604,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.2201457291841507,
|
|
"num_tokens": 29046074.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.266195249557495,
|
|
"epoch": 1.3189107918476446,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048298890874297866,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.21286092698574066,
|
|
"num_tokens": 29055750.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.210245943069458,
|
|
"epoch": 1.3193284330103574,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004829775515741007,
|
|
"loss": 4.775,
|
|
"mean_token_accuracy": 0.22157898545265198,
|
|
"num_tokens": 29065012.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.286662149429321,
|
|
"epoch": 1.3197460741730704,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004829661907643253,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.20163265615701675,
|
|
"num_tokens": 29074780.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.33975887298584,
|
|
"epoch": 1.3201637153357835,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004829548263138515,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.21001427620649338,
|
|
"num_tokens": 29083321.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.283021783828735,
|
|
"epoch": 1.3205813564984965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004829434582228781,
|
|
"loss": 4.8183,
|
|
"mean_token_accuracy": 0.20996019542217254,
|
|
"num_tokens": 29092110.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.196117305755616,
|
|
"epoch": 1.3209989976612095,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004829320864916042,
|
|
"loss": 4.7738,
|
|
"mean_token_accuracy": 0.2193888932466507,
|
|
"num_tokens": 29100451.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.3185319900512695,
|
|
"epoch": 1.3214166388239224,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048292071112022886,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.20905899107456208,
|
|
"num_tokens": 29110468.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.282467889785766,
|
|
"epoch": 1.3218342799866356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004829093321089511,
|
|
"loss": 4.8855,
|
|
"mean_token_accuracy": 0.21679864078760147,
|
|
"num_tokens": 29119660.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.347619581222534,
|
|
"epoch": 1.3222519211493484,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004828979494579703,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.20556318908929824,
|
|
"num_tokens": 29129145.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.32127423286438,
|
|
"epoch": 1.3226695623120615,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048288656316748554,
|
|
"loss": 4.9159,
|
|
"mean_token_accuracy": 0.21720298677682875,
|
|
"num_tokens": 29137980.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.270041847229004,
|
|
"epoch": 1.3230872034747745,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048287517323769634,
|
|
"loss": 4.7924,
|
|
"mean_token_accuracy": 0.22338598370552062,
|
|
"num_tokens": 29147535.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.190232133865356,
|
|
"epoch": 1.3235048446374875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048286377966880206,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.22335263937711716,
|
|
"num_tokens": 29157162.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.255061292648316,
|
|
"epoch": 1.3239224858002006,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048285238246100203,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.21646544486284255,
|
|
"num_tokens": 29166542.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.303708124160766,
|
|
"epoch": 1.3243401269629134,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004828409816144959,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.22284827530384063,
|
|
"num_tokens": 29176040.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.3364996910095215,
|
|
"epoch": 1.3247577681256264,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004828295771294831,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.2128174662590027,
|
|
"num_tokens": 29184730.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.281658554077149,
|
|
"epoch": 1.3251754092883394,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048281816900616354,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.21920831501483917,
|
|
"num_tokens": 29193671.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.27759051322937,
|
|
"epoch": 1.3255930504510525,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004828067572447367,
|
|
"loss": 4.859,
|
|
"mean_token_accuracy": 0.21476883292198182,
|
|
"num_tokens": 29203094.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.204766368865966,
|
|
"epoch": 1.3260106916137655,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048279534184540246,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.2189892664551735,
|
|
"num_tokens": 29211678.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.356805992126465,
|
|
"epoch": 1.3264283327764783,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004827839228083606,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.20455215722322465,
|
|
"num_tokens": 29220993.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.326261377334594,
|
|
"epoch": 1.3268459739391916,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004827725001338111,
|
|
"loss": 4.8178,
|
|
"mean_token_accuracy": 0.2174289807677269,
|
|
"num_tokens": 29230006.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.264250802993774,
|
|
"epoch": 1.3272636151019044,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048276107382195393,
|
|
"loss": 4.7665,
|
|
"mean_token_accuracy": 0.23004098683595658,
|
|
"num_tokens": 29238906.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.338213586807251,
|
|
"epoch": 1.3276812562646174,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048274964387298903,
|
|
"loss": 4.8913,
|
|
"mean_token_accuracy": 0.21885153353214265,
|
|
"num_tokens": 29248383.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.244008636474609,
|
|
"epoch": 1.3280988974273304,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004827382102871166,
|
|
"loss": 4.8237,
|
|
"mean_token_accuracy": 0.21846426725387574,
|
|
"num_tokens": 29257999.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.240027189254761,
|
|
"epoch": 1.3285165385900435,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048272677306453665,
|
|
"loss": 4.7875,
|
|
"mean_token_accuracy": 0.22008167207241058,
|
|
"num_tokens": 29267143.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.307524728775024,
|
|
"epoch": 1.3289341797527565,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048271533220544955,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.20756545960903167,
|
|
"num_tokens": 29276730.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.3311608791351315,
|
|
"epoch": 1.3293518209154693,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048270388771005555,
|
|
"loss": 4.9089,
|
|
"mean_token_accuracy": 0.21417022496461868,
|
|
"num_tokens": 29285480.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.32054762840271,
|
|
"epoch": 1.3297694620781824,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048269243957855493,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.2078758880496025,
|
|
"num_tokens": 29294927.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.31000862121582,
|
|
"epoch": 1.3301871032408954,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004826809878111481,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.21613177955150603,
|
|
"num_tokens": 29304567.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.227256202697754,
|
|
"epoch": 1.3306047444036084,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048266953240803576,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.2243459165096283,
|
|
"num_tokens": 29313302.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.291921234130859,
|
|
"epoch": 1.3310223855663215,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004826580733694182,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.21558952778577806,
|
|
"num_tokens": 29322195.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.28344955444336,
|
|
"epoch": 1.3314400267290343,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004826466106954961,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.2102554976940155,
|
|
"num_tokens": 29331416.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.282169818878174,
|
|
"epoch": 1.3318576678917475,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048263514438647015,
|
|
"loss": 4.8271,
|
|
"mean_token_accuracy": 0.2224087417125702,
|
|
"num_tokens": 29340497.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.21466031074524,
|
|
"epoch": 1.3322753090544603,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000482623674442541,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.22387123703956605,
|
|
"num_tokens": 29349306.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.310687589645386,
|
|
"epoch": 1.3326929502171734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004826122008639096,
|
|
"loss": 4.8422,
|
|
"mean_token_accuracy": 0.216707281768322,
|
|
"num_tokens": 29358452.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.277312707901001,
|
|
"epoch": 1.3331105913798864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048260072365077675,
|
|
"loss": 4.905,
|
|
"mean_token_accuracy": 0.20958502888679503,
|
|
"num_tokens": 29367640.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.332236480712891,
|
|
"epoch": 1.3335282325425994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004825892428033432,
|
|
"loss": 4.8293,
|
|
"mean_token_accuracy": 0.21000433713197708,
|
|
"num_tokens": 29377352.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.231750392913819,
|
|
"epoch": 1.3339458737053125,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004825777583218102,
|
|
"loss": 4.8197,
|
|
"mean_token_accuracy": 0.2196902558207512,
|
|
"num_tokens": 29386802.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.164784240722656,
|
|
"epoch": 1.3343635148680253,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004825662702063787,
|
|
"loss": 4.709,
|
|
"mean_token_accuracy": 0.2261268451809883,
|
|
"num_tokens": 29395078.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.308338165283203,
|
|
"epoch": 1.3347811560307383,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004825547784572497,
|
|
"loss": 4.7838,
|
|
"mean_token_accuracy": 0.21984607726335526,
|
|
"num_tokens": 29403837.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.302309465408325,
|
|
"epoch": 1.3351987971934514,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004825432830746245,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.21466302126646042,
|
|
"num_tokens": 29412222.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.2896030902862545,
|
|
"epoch": 1.3356164383561644,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004825317840587044,
|
|
"loss": 4.7449,
|
|
"mean_token_accuracy": 0.22715822905302047,
|
|
"num_tokens": 29421632.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.30252890586853,
|
|
"epoch": 1.3360340795188774,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004825202814096905,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.21738906651735307,
|
|
"num_tokens": 29430768.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.397883749008178,
|
|
"epoch": 1.3364517206815905,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004825087751277843,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.21343861520290375,
|
|
"num_tokens": 29440280.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.383572149276733,
|
|
"epoch": 1.3368693618443035,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048249726521318716,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.2157854288816452,
|
|
"num_tokens": 29449850.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.27399582862854,
|
|
"epoch": 1.3372870030070163,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004824857516661008,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.22645305395126342,
|
|
"num_tokens": 29459233.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.317527866363525,
|
|
"epoch": 1.3377046441697293,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048247423448672647,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.21055445522069932,
|
|
"num_tokens": 29469351.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.279345417022705,
|
|
"epoch": 1.3381222853324424,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004824627136752659,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.21283113658428193,
|
|
"num_tokens": 29477653.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.291852903366089,
|
|
"epoch": 1.3385399264951554,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004824511892319209,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.22208804935216903,
|
|
"num_tokens": 29486944.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.23095006942749,
|
|
"epoch": 1.3389575676578684,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048243966115689305,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.22837453186511994,
|
|
"num_tokens": 29495791.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.3928319931030275,
|
|
"epoch": 1.3393752088205813,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004824281294503843,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.2093038007616997,
|
|
"num_tokens": 29505403.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.24312572479248,
|
|
"epoch": 1.3397928499832943,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004824165941125964,
|
|
"loss": 4.7073,
|
|
"mean_token_accuracy": 0.22437381595373154,
|
|
"num_tokens": 29515310.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.303864622116089,
|
|
"epoch": 1.3402104911460073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004824050551437315,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.2175702229142189,
|
|
"num_tokens": 29524824.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.258649826049805,
|
|
"epoch": 1.3406281323087204,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004823935125439912,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.21545723974704742,
|
|
"num_tokens": 29533667.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.32332034111023,
|
|
"epoch": 1.3410457734714334,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000482381966313578,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.21129701733589173,
|
|
"num_tokens": 29541745.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.230995941162109,
|
|
"epoch": 1.3414634146341464,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048237041645269387,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.2176070988178253,
|
|
"num_tokens": 29551004.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.215371990203858,
|
|
"epoch": 1.3418810557968595,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004823588629615409,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.22184584885835648,
|
|
"num_tokens": 29561061.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.164871263504028,
|
|
"epoch": 1.3422986969595723,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048234730584032143,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.2297421246767044,
|
|
"num_tokens": 29569689.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.28213152885437,
|
|
"epoch": 1.3427163381222853,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004823357450892379,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.21329832673072815,
|
|
"num_tokens": 29579576.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.271914339065551,
|
|
"epoch": 1.3431339792849983,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004823241807084925,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.23149037212133408,
|
|
"num_tokens": 29588531.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.2742386817932125,
|
|
"epoch": 1.3435516204477114,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048231261269828776,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.22081208229064941,
|
|
"num_tokens": 29596838.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.275674676895141,
|
|
"epoch": 1.3439692616104244,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048230104105882624,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.21578499376773835,
|
|
"num_tokens": 29606769.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.356088495254516,
|
|
"epoch": 1.3443869027731372,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004822894657903104,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.20633999407291412,
|
|
"num_tokens": 29616994.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.194810914993286,
|
|
"epoch": 1.3448045439358502,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000482277886892943,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.2262077137827873,
|
|
"num_tokens": 29626865.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.175069761276245,
|
|
"epoch": 1.3452221850985633,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004822663043669267,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.22472544759511948,
|
|
"num_tokens": 29636439.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.280018615722656,
|
|
"epoch": 1.3456398262612763,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048225471821246416,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.22714447230100632,
|
|
"num_tokens": 29645019.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.324591732025146,
|
|
"epoch": 1.3460574674239894,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004822431284297584,
|
|
"loss": 4.9826,
|
|
"mean_token_accuracy": 0.21157124936580657,
|
|
"num_tokens": 29654660.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.316455841064453,
|
|
"epoch": 1.3464751085867024,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004822315350190122,
|
|
"loss": 4.8937,
|
|
"mean_token_accuracy": 0.2079894423484802,
|
|
"num_tokens": 29662880.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.32862114906311,
|
|
"epoch": 1.3468927497494154,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048221993798042856,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.2107854813337326,
|
|
"num_tokens": 29672336.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.2715356826782225,
|
|
"epoch": 1.3473103909121282,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048220833731421045,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.21255273073911668,
|
|
"num_tokens": 29681495.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.316331672668457,
|
|
"epoch": 1.3477280320748413,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004821967330205609,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.22163201719522477,
|
|
"num_tokens": 29690214.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.281888771057129,
|
|
"epoch": 1.3481456732375543,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004821851250996832,
|
|
"loss": 4.8606,
|
|
"mean_token_accuracy": 0.21516398191452027,
|
|
"num_tokens": 29699309.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.256964588165284,
|
|
"epoch": 1.3485633144002673,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004821735135517805,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.21872822791337967,
|
|
"num_tokens": 29708741.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.274355363845825,
|
|
"epoch": 1.3489809555629804,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004821618983770561,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.215852053463459,
|
|
"num_tokens": 29717616.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.286669731140137,
|
|
"epoch": 1.3493985967256932,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048215027957571326,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.22109839022159578,
|
|
"num_tokens": 29726601.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.2605043888092045,
|
|
"epoch": 1.3498162378884062,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004821386571479555,
|
|
"loss": 4.87,
|
|
"mean_token_accuracy": 0.21611486673355101,
|
|
"num_tokens": 29736930.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.1844532012939455,
|
|
"epoch": 1.3502338790511192,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004821270310939861,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.22347864359617234,
|
|
"num_tokens": 29745980.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.263261842727661,
|
|
"epoch": 1.3506515202138323,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004821154014140088,
|
|
"loss": 4.847,
|
|
"mean_token_accuracy": 0.21705393344163895,
|
|
"num_tokens": 29755701.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.265316677093506,
|
|
"epoch": 1.3510691613765453,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004821037681082271,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.23095098584890367,
|
|
"num_tokens": 29763503.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.197755765914917,
|
|
"epoch": 1.3514868025392583,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004820921311768446,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.22632719874382018,
|
|
"num_tokens": 29771667.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.295534658432007,
|
|
"epoch": 1.3519044437019714,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048208049062006505,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.21189955472946168,
|
|
"num_tokens": 29780836.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.3152101039886475,
|
|
"epoch": 1.3523220848646842,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048206884643809224,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.21266047060489654,
|
|
"num_tokens": 29790397.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.2662882804870605,
|
|
"epoch": 1.3527397260273972,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048205719863113014,
|
|
"loss": 4.8728,
|
|
"mean_token_accuracy": 0.21444416493177415,
|
|
"num_tokens": 29799227.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.301491451263428,
|
|
"epoch": 1.3531573671901103,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004820455471993824,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.21104556620121,
|
|
"num_tokens": 29808182.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.308961200714111,
|
|
"epoch": 1.3535750083528233,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048203389214305326,
|
|
"loss": 4.9064,
|
|
"mean_token_accuracy": 0.2099243864417076,
|
|
"num_tokens": 29817843.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.2585423469543455,
|
|
"epoch": 1.3539926495155363,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004820222334623465,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.2179105520248413,
|
|
"num_tokens": 29827082.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.313271188735962,
|
|
"epoch": 1.3544102906782491,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048201057115746643,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.22026655972003936,
|
|
"num_tokens": 29836176.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.242667198181152,
|
|
"epoch": 1.3548279318409622,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004819989052286172,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.22285597622394562,
|
|
"num_tokens": 29845252.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.234277963638306,
|
|
"epoch": 1.3552455730036752,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004819872356760028,
|
|
"loss": 4.8186,
|
|
"mean_token_accuracy": 0.2173738121986389,
|
|
"num_tokens": 29854115.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.287095403671264,
|
|
"epoch": 1.3556632141663882,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048197556249982774,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.22456634193658828,
|
|
"num_tokens": 29861918.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.301160478591919,
|
|
"epoch": 1.3560808553291013,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004819638857002965,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.21553789228200912,
|
|
"num_tokens": 29871421.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.218049716949463,
|
|
"epoch": 1.3564984964918143,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048195220527761306,
|
|
"loss": 4.7789,
|
|
"mean_token_accuracy": 0.2235024467110634,
|
|
"num_tokens": 29880328.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.316504764556885,
|
|
"epoch": 1.3569161376545273,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048194052123198236,
|
|
"loss": 4.9506,
|
|
"mean_token_accuracy": 0.2092357575893402,
|
|
"num_tokens": 29889777.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.223725986480713,
|
|
"epoch": 1.3573337788172402,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048192883356360867,
|
|
"loss": 4.7996,
|
|
"mean_token_accuracy": 0.21612568199634552,
|
|
"num_tokens": 29898638.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.261117696762085,
|
|
"epoch": 1.3577514199799532,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004819171422726966,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.22188277691602706,
|
|
"num_tokens": 29907856.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.326128053665161,
|
|
"epoch": 1.3581690611426662,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048190544735945094,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.20861926376819612,
|
|
"num_tokens": 29916992.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.301455545425415,
|
|
"epoch": 1.3585867023053793,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004818937488240764,
|
|
"loss": 4.8289,
|
|
"mean_token_accuracy": 0.21786623746156691,
|
|
"num_tokens": 29926323.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.261235618591309,
|
|
"epoch": 1.3590043434680923,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048188204666677775,
|
|
"loss": 4.8559,
|
|
"mean_token_accuracy": 0.2179841548204422,
|
|
"num_tokens": 29935386.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.239242029190064,
|
|
"epoch": 1.359421984630805,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004818703408877598,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.21890747547149658,
|
|
"num_tokens": 29944741.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.301206493377686,
|
|
"epoch": 1.3598396257935181,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004818586314872276,
|
|
"loss": 4.7799,
|
|
"mean_token_accuracy": 0.22118382304906845,
|
|
"num_tokens": 29952407.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.275738906860352,
|
|
"epoch": 1.3602572669562312,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048184691846538596,
|
|
"loss": 4.8035,
|
|
"mean_token_accuracy": 0.20963550508022308,
|
|
"num_tokens": 29962315.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.287699890136719,
|
|
"epoch": 1.3606749081189442,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048183520182244006,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.21557831168174743,
|
|
"num_tokens": 29972070.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.255973672866821,
|
|
"epoch": 1.3610925492816572,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000481823481558595,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.2239009588956833,
|
|
"num_tokens": 29980416.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.302644300460815,
|
|
"epoch": 1.3615101904443703,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048181175767405594,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.22038675993680953,
|
|
"num_tokens": 29989436.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.295774984359741,
|
|
"epoch": 1.3619278316070833,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004818000301690282,
|
|
"loss": 4.7767,
|
|
"mean_token_accuracy": 0.2181136429309845,
|
|
"num_tokens": 29998295.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.2544238567352295,
|
|
"epoch": 1.3623454727697961,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004817882990437169,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.2109497994184494,
|
|
"num_tokens": 30007892.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.268147897720337,
|
|
"epoch": 1.3627631139325092,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048177656429832763,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.22457582503557205,
|
|
"num_tokens": 30016477.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.177196931838989,
|
|
"epoch": 1.3631807550952222,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048176482593306557,
|
|
"loss": 4.7875,
|
|
"mean_token_accuracy": 0.2236232951283455,
|
|
"num_tokens": 30025693.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.283549642562866,
|
|
"epoch": 1.3635983962579352,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048175308394813644,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.2148837313055992,
|
|
"num_tokens": 30034552.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.229987335205078,
|
|
"epoch": 1.3640160374206483,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004817413383437456,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.2241922914981842,
|
|
"num_tokens": 30043584.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.3088137149810795,
|
|
"epoch": 1.364433678583361,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048172958912009886,
|
|
"loss": 4.9237,
|
|
"mean_token_accuracy": 0.21217154562473298,
|
|
"num_tokens": 30053189.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.230805730819702,
|
|
"epoch": 1.364851319746074,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048171783627740176,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.2189761444926262,
|
|
"num_tokens": 30062144.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.305282688140869,
|
|
"epoch": 1.3652689609087871,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048170607981586023,
|
|
"loss": 4.804,
|
|
"mean_token_accuracy": 0.22481199353933334,
|
|
"num_tokens": 30071646.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.331385612487793,
|
|
"epoch": 1.3656866020715002,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004816943197356799,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.21772896498441696,
|
|
"num_tokens": 30081322.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.1878893852233885,
|
|
"epoch": 1.3661042432342132,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004816825560370667,
|
|
"loss": 4.7815,
|
|
"mean_token_accuracy": 0.22564320117235184,
|
|
"num_tokens": 30090059.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.35328049659729,
|
|
"epoch": 1.3665218843969262,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048167078872022657,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.21959954798221587,
|
|
"num_tokens": 30100924.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.2537233352661135,
|
|
"epoch": 1.3669395255596393,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048165901778536547,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.22366595417261123,
|
|
"num_tokens": 30109972.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.258938217163086,
|
|
"epoch": 1.367357166722352,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048164724323268956,
|
|
"loss": 4.8191,
|
|
"mean_token_accuracy": 0.21955471634864807,
|
|
"num_tokens": 30118705.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.319254779815674,
|
|
"epoch": 1.3677748078850651,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048163546506240493,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.21564025580883026,
|
|
"num_tokens": 30127631.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.2643115520477295,
|
|
"epoch": 1.3681924490477781,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004816236832747177,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.23105276226997376,
|
|
"num_tokens": 30136127.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.268324136734009,
|
|
"epoch": 1.3686100902104912,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004816118978698342,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.22224701792001725,
|
|
"num_tokens": 30145609.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.395208168029785,
|
|
"epoch": 1.3690277313732042,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004816001088479608,
|
|
"loss": 4.9224,
|
|
"mean_token_accuracy": 0.20469232946634291,
|
|
"num_tokens": 30155705.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.254632616043091,
|
|
"epoch": 1.369445372535917,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004815883162093037,
|
|
"loss": 4.8801,
|
|
"mean_token_accuracy": 0.2075851932168007,
|
|
"num_tokens": 30165549.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.207562732696533,
|
|
"epoch": 1.36986301369863,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048157651995406954,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.2209162548184395,
|
|
"num_tokens": 30174716.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.26080093383789,
|
|
"epoch": 1.370280654861343,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004815647200824647,
|
|
"loss": 4.774,
|
|
"mean_token_accuracy": 0.22019530236721038,
|
|
"num_tokens": 30184009.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.360458040237427,
|
|
"epoch": 1.3706982960240561,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048155291659469587,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.21362749189138414,
|
|
"num_tokens": 30193731.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.2902158260345455,
|
|
"epoch": 1.3711159371867692,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048154110949096945,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.20917462855577468,
|
|
"num_tokens": 30203643.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.253510236740112,
|
|
"epoch": 1.3715335783494822,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004815292987714924,
|
|
"loss": 4.825,
|
|
"mean_token_accuracy": 0.21496938318014144,
|
|
"num_tokens": 30212436.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.272972679138183,
|
|
"epoch": 1.3719512195121952,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004815174844364714,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.22041663974523545,
|
|
"num_tokens": 30221730.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.343939971923828,
|
|
"epoch": 1.372368860674908,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004815056664861133,
|
|
"loss": 4.8522,
|
|
"mean_token_accuracy": 0.214577354490757,
|
|
"num_tokens": 30230645.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.276606464385987,
|
|
"epoch": 1.372786501837621,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004814938449206248,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.22360716313123702,
|
|
"num_tokens": 30239513.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.209578561782837,
|
|
"epoch": 1.373204143000334,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048148201974021297,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.2263580232858658,
|
|
"num_tokens": 30248920.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.2145191669464115,
|
|
"epoch": 1.3736217841630471,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000481470190945085,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.22043373435735703,
|
|
"num_tokens": 30257851.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.244280099868774,
|
|
"epoch": 1.3740394253257602,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004814583585354477,
|
|
"loss": 4.8097,
|
|
"mean_token_accuracy": 0.228873810172081,
|
|
"num_tokens": 30267676.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.227118587493896,
|
|
"epoch": 1.374457066488473,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048144652251150836,
|
|
"loss": 4.6963,
|
|
"mean_token_accuracy": 0.22726818919181824,
|
|
"num_tokens": 30277744.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.3178825855255125,
|
|
"epoch": 1.374874707651186,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000481434682873474,
|
|
"loss": 4.8631,
|
|
"mean_token_accuracy": 0.2097412019968033,
|
|
"num_tokens": 30286578.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.362777853012085,
|
|
"epoch": 1.375292348813899,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004814228396215522,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.21524303108453752,
|
|
"num_tokens": 30295896.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.3246392726898195,
|
|
"epoch": 1.375709989976612,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004814109927559501,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.21222891062498092,
|
|
"num_tokens": 30305397.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.260698747634888,
|
|
"epoch": 1.3761276311393251,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004813991422768751,
|
|
"loss": 4.8731,
|
|
"mean_token_accuracy": 0.22065442949533462,
|
|
"num_tokens": 30314025.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.293504810333252,
|
|
"epoch": 1.3765452723020382,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048138728818453456,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.2167838156223297,
|
|
"num_tokens": 30324384.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.303888750076294,
|
|
"epoch": 1.3769629134647512,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048137543047913636,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.21703301817178727,
|
|
"num_tokens": 30333663.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.280086803436279,
|
|
"epoch": 1.377380554627464,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048136356916088764,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.21090778857469558,
|
|
"num_tokens": 30343603.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.348300218582153,
|
|
"epoch": 1.377798195790177,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048135170422999624,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.2121874436736107,
|
|
"num_tokens": 30352680.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.311864519119263,
|
|
"epoch": 1.37821583695289,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048133983568666994,
|
|
"loss": 4.8435,
|
|
"mean_token_accuracy": 0.22032315284013748,
|
|
"num_tokens": 30362597.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.375571775436401,
|
|
"epoch": 1.378633478115603,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004813279635311165,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.2060232624411583,
|
|
"num_tokens": 30372037.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.327482414245606,
|
|
"epoch": 1.3790511192783161,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004813160877635436,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.22302102893590928,
|
|
"num_tokens": 30380867.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.332609939575195,
|
|
"epoch": 1.379468760441029,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048130420838415926,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.21472752839326859,
|
|
"num_tokens": 30391181.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.340115547180176,
|
|
"epoch": 1.379886401603742,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048129232539317147,
|
|
"loss": 4.9067,
|
|
"mean_token_accuracy": 0.21503054052591325,
|
|
"num_tokens": 30400519.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.291983127593994,
|
|
"epoch": 1.380304042766455,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048128043879078816,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.21449117809534074,
|
|
"num_tokens": 30409570.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.359559392929077,
|
|
"epoch": 1.380721683929168,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004812685485772175,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.21769127994775772,
|
|
"num_tokens": 30418458.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.311871528625488,
|
|
"epoch": 1.381139325091881,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048125665475266756,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.22083571404218674,
|
|
"num_tokens": 30427933.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.369933176040649,
|
|
"epoch": 1.3815569662545941,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048124475731734667,
|
|
"loss": 4.9169,
|
|
"mean_token_accuracy": 0.21575738936662675,
|
|
"num_tokens": 30436825.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.355772256851196,
|
|
"epoch": 1.3819746074173072,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000481232856271463,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.21549161672592163,
|
|
"num_tokens": 30445367.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.381880235671997,
|
|
"epoch": 1.38239224858002,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048122095161522496,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.20866163223981857,
|
|
"num_tokens": 30455236.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.240172958374023,
|
|
"epoch": 1.382809889742733,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004812090433488409,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.21823325008153915,
|
|
"num_tokens": 30465003.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.273212623596192,
|
|
"epoch": 1.383227530905446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048119713147251944,
|
|
"loss": 4.7809,
|
|
"mean_token_accuracy": 0.2187251091003418,
|
|
"num_tokens": 30473686.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.306307315826416,
|
|
"epoch": 1.383645172068159,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048118521598646886,
|
|
"loss": 4.9058,
|
|
"mean_token_accuracy": 0.21794119775295256,
|
|
"num_tokens": 30482684.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.275683307647705,
|
|
"epoch": 1.384062813230872,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048117329689089793,
|
|
"loss": 4.7612,
|
|
"mean_token_accuracy": 0.21830566376447677,
|
|
"num_tokens": 30491356.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.300555944442749,
|
|
"epoch": 1.384480454393585,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048116137418601526,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.21943848580121994,
|
|
"num_tokens": 30500829.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.258255100250244,
|
|
"epoch": 1.384898095556298,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048114944787202955,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.21236622780561448,
|
|
"num_tokens": 30509759.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.245941781997681,
|
|
"epoch": 1.385315736719011,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048113751794914974,
|
|
"loss": 4.7586,
|
|
"mean_token_accuracy": 0.22416564524173738,
|
|
"num_tokens": 30518638.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.3142906665802006,
|
|
"epoch": 1.385733377881724,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048112558441758437,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.2171902447938919,
|
|
"num_tokens": 30527973.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.242215585708618,
|
|
"epoch": 1.386151019044437,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004811136472775426,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.22382502853870392,
|
|
"num_tokens": 30537120.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.330226898193359,
|
|
"epoch": 1.38656866020715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004811017065292334,
|
|
"loss": 4.8358,
|
|
"mean_token_accuracy": 0.21748751997947693,
|
|
"num_tokens": 30546372.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.334629344940185,
|
|
"epoch": 1.3869863013698631,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048108976217286576,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.21012108772993088,
|
|
"num_tokens": 30555377.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.228320932388305,
|
|
"epoch": 1.387403942532576,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004810778142086487,
|
|
"loss": 4.8187,
|
|
"mean_token_accuracy": 0.2208944484591484,
|
|
"num_tokens": 30565208.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.30337290763855,
|
|
"epoch": 1.387821583695289,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048106586263679146,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.2207646757364273,
|
|
"num_tokens": 30573230.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.2825579166412355,
|
|
"epoch": 1.388239224858002,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048105390745750324,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.22740151286125182,
|
|
"num_tokens": 30581570.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.289718675613403,
|
|
"epoch": 1.388656866020715,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048104194867099336,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.223678383231163,
|
|
"num_tokens": 30591091.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.265125179290772,
|
|
"epoch": 1.389074507183428,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048102998627747116,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.22187243551015853,
|
|
"num_tokens": 30601545.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.324801015853882,
|
|
"epoch": 1.3894921483461409,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000481018020277146,
|
|
"loss": 4.8709,
|
|
"mean_token_accuracy": 0.21874682754278182,
|
|
"num_tokens": 30610630.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.237151002883911,
|
|
"epoch": 1.389909789508854,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048100605067022753,
|
|
"loss": 4.7644,
|
|
"mean_token_accuracy": 0.22539368271827698,
|
|
"num_tokens": 30620015.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.347232389450073,
|
|
"epoch": 1.390327430671567,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048099407745692504,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.22692252844572067,
|
|
"num_tokens": 30628590.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.208021450042724,
|
|
"epoch": 1.39074507183428,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048098210063744827,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.22563837617635726,
|
|
"num_tokens": 30638624.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.253631925582885,
|
|
"epoch": 1.391162712996993,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048097012021200696,
|
|
"loss": 4.8775,
|
|
"mean_token_accuracy": 0.2115288645029068,
|
|
"num_tokens": 30648247.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.345826721191406,
|
|
"epoch": 1.391580354159706,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004809581361808108,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.2138332650065422,
|
|
"num_tokens": 30659045.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.325989294052124,
|
|
"epoch": 1.391997995322419,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004809461485440694,
|
|
"loss": 4.8534,
|
|
"mean_token_accuracy": 0.21633321195840835,
|
|
"num_tokens": 30668948.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.320825052261353,
|
|
"epoch": 1.392415636485132,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004809341573019929,
|
|
"loss": 4.7672,
|
|
"mean_token_accuracy": 0.23276773244142532,
|
|
"num_tokens": 30678818.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.212452173233032,
|
|
"epoch": 1.392833277647845,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004809221624547911,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.2231282636523247,
|
|
"num_tokens": 30687731.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.257723999023438,
|
|
"epoch": 1.393250918810558,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000480910164002674,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.21504144966602326,
|
|
"num_tokens": 30696880.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.291917133331299,
|
|
"epoch": 1.393668559973271,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048089816194585153,
|
|
"loss": 4.8035,
|
|
"mean_token_accuracy": 0.22099994570016862,
|
|
"num_tokens": 30706274.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.2672850608825685,
|
|
"epoch": 1.394086201135984,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004808861562845339,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.21896863877773284,
|
|
"num_tokens": 30715184.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.278675746917725,
|
|
"epoch": 1.3945038422986968,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004808741470189313,
|
|
"loss": 4.7691,
|
|
"mean_token_accuracy": 0.227993443608284,
|
|
"num_tokens": 30724501.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.2733738899230955,
|
|
"epoch": 1.39492148346141,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004808621341492541,
|
|
"loss": 4.7789,
|
|
"mean_token_accuracy": 0.21964177191257478,
|
|
"num_tokens": 30733496.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.211297130584716,
|
|
"epoch": 1.395339124624123,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004808501176757122,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.22708662897348403,
|
|
"num_tokens": 30742096.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.193476629257202,
|
|
"epoch": 1.395756765786836,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004808380975985163,
|
|
"loss": 4.7196,
|
|
"mean_token_accuracy": 0.2247098743915558,
|
|
"num_tokens": 30751452.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.269854164123535,
|
|
"epoch": 1.396174406949549,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004808260739178768,
|
|
"loss": 4.8593,
|
|
"mean_token_accuracy": 0.22129365801811218,
|
|
"num_tokens": 30760686.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.265927362442016,
|
|
"epoch": 1.396592048112262,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004808140466340041,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.21835942566394806,
|
|
"num_tokens": 30769374.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.2803929328918455,
|
|
"epoch": 1.397009689274975,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004808020157471087,
|
|
"loss": 4.8614,
|
|
"mean_token_accuracy": 0.21964432299137115,
|
|
"num_tokens": 30778910.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.26192798614502,
|
|
"epoch": 1.3974273304376879,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048078998125740136,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.22241308838129042,
|
|
"num_tokens": 30787844.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.2940146923065186,
|
|
"epoch": 1.3978449716004009,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004807779431650927,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.21737926751375197,
|
|
"num_tokens": 30797415.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.326129961013794,
|
|
"epoch": 1.398262612763114,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004807659014703934,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.2238194853067398,
|
|
"num_tokens": 30805595.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.292846202850342,
|
|
"epoch": 1.398680253925827,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004807538561735143,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.21729476153850555,
|
|
"num_tokens": 30813840.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.315155267715454,
|
|
"epoch": 1.39909789508854,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048074180727466636,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.22300129532814025,
|
|
"num_tokens": 30822208.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.314707899093628,
|
|
"epoch": 1.3995155362512528,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048072975477406036,
|
|
"loss": 4.9524,
|
|
"mean_token_accuracy": 0.20790649205446243,
|
|
"num_tokens": 30831804.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.259213209152222,
|
|
"epoch": 1.399933177413966,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004807176986719074,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.21989050656557083,
|
|
"num_tokens": 30841450.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.322894096374512,
|
|
"epoch": 1.4003508185766789,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048070563896841843,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.21846037805080415,
|
|
"num_tokens": 30849906.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.232669496536255,
|
|
"epoch": 1.400768459739392,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048069357566380474,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.21917097121477128,
|
|
"num_tokens": 30859643.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.202058792114258,
|
|
"epoch": 1.401186100902105,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048068150875827737,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.2261527732014656,
|
|
"num_tokens": 30868728.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.303447532653808,
|
|
"epoch": 1.401603742064818,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048066943825204764,
|
|
"loss": 4.7984,
|
|
"mean_token_accuracy": 0.2195439890027046,
|
|
"num_tokens": 30877253.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.2682078838348385,
|
|
"epoch": 1.402021383227531,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004806573641453268,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.21642992794513702,
|
|
"num_tokens": 30886118.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.236306190490723,
|
|
"epoch": 1.4024390243902438,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048064528643832627,
|
|
"loss": 4.8466,
|
|
"mean_token_accuracy": 0.21940123438835143,
|
|
"num_tokens": 30894533.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.274002456665039,
|
|
"epoch": 1.4028566655529568,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048063320513125747,
|
|
"loss": 4.7193,
|
|
"mean_token_accuracy": 0.21509934067726136,
|
|
"num_tokens": 30904934.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.2654601573944095,
|
|
"epoch": 1.4032743067156699,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004806211202243319,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.2255147010087967,
|
|
"num_tokens": 30913641.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.2151368141174315,
|
|
"epoch": 1.403691947878383,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048060903171776113,
|
|
"loss": 4.7338,
|
|
"mean_token_accuracy": 0.22013205289840698,
|
|
"num_tokens": 30922529.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.214554166793823,
|
|
"epoch": 1.404109589041096,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004805969396117567,
|
|
"loss": 4.8162,
|
|
"mean_token_accuracy": 0.21877792179584504,
|
|
"num_tokens": 30932059.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.3825188159942625,
|
|
"epoch": 1.4045272302038088,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048058484390653037,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.21375762820243835,
|
|
"num_tokens": 30941141.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.377021169662475,
|
|
"epoch": 1.404944871366522,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004805727446022939,
|
|
"loss": 4.8712,
|
|
"mean_token_accuracy": 0.22119322121143342,
|
|
"num_tokens": 30949785.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.221461009979248,
|
|
"epoch": 1.4053625125292348,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048056064169925904,
|
|
"loss": 4.7861,
|
|
"mean_token_accuracy": 0.21784835010766984,
|
|
"num_tokens": 30958421.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.1528573513031,
|
|
"epoch": 1.4057801536919479,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048054853519763786,
|
|
"loss": 4.7213,
|
|
"mean_token_accuracy": 0.2267108976840973,
|
|
"num_tokens": 30968177.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.293421506881714,
|
|
"epoch": 1.406197794854661,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004805364250976421,
|
|
"loss": 4.8142,
|
|
"mean_token_accuracy": 0.21742680072784423,
|
|
"num_tokens": 30978048.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.242422008514405,
|
|
"epoch": 1.406615436017374,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004805243113994837,
|
|
"loss": 4.8249,
|
|
"mean_token_accuracy": 0.2170426905155182,
|
|
"num_tokens": 30988588.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.333912467956543,
|
|
"epoch": 1.407033077180087,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004805121941033749,
|
|
"loss": 4.8114,
|
|
"mean_token_accuracy": 0.21498219519853592,
|
|
"num_tokens": 30998000.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.286445283889771,
|
|
"epoch": 1.4074507183427998,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004805000732095278,
|
|
"loss": 4.8413,
|
|
"mean_token_accuracy": 0.2161988854408264,
|
|
"num_tokens": 31007103.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.257005500793457,
|
|
"epoch": 1.4078683595055128,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004804879487181546,
|
|
"loss": 4.8263,
|
|
"mean_token_accuracy": 0.21489835679531097,
|
|
"num_tokens": 31016658.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.3202056884765625,
|
|
"epoch": 1.4082860006682258,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004804758206294675,
|
|
"loss": 4.955,
|
|
"mean_token_accuracy": 0.20811579525470733,
|
|
"num_tokens": 31026968.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.213185358047485,
|
|
"epoch": 1.4087036418309389,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004804636889436787,
|
|
"loss": 4.7723,
|
|
"mean_token_accuracy": 0.2221955120563507,
|
|
"num_tokens": 31035890.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.3011963844299315,
|
|
"epoch": 1.409121282993652,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048045155366100085,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.21497507095336915,
|
|
"num_tokens": 31045203.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.311357688903809,
|
|
"epoch": 1.4095389241563647,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004804394147816462,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.21187231093645095,
|
|
"num_tokens": 31055802.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.309376430511475,
|
|
"epoch": 1.409956565319078,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048042727230582726,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.2208852455019951,
|
|
"num_tokens": 31065434.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.217853164672851,
|
|
"epoch": 1.4103742064817908,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004804151262337568,
|
|
"loss": 4.7024,
|
|
"mean_token_accuracy": 0.22823773920536042,
|
|
"num_tokens": 31073931.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.343348264694214,
|
|
"epoch": 1.4107918476445038,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004804029765656471,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.20594609826803206,
|
|
"num_tokens": 31083068.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.208445978164673,
|
|
"epoch": 1.4112094888072169,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004803908233017111,
|
|
"loss": 4.7235,
|
|
"mean_token_accuracy": 0.22924202680587769,
|
|
"num_tokens": 31092306.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.259644269943237,
|
|
"epoch": 1.41162712996993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004803786664421616,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.2307792767882347,
|
|
"num_tokens": 31100540.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.240231037139893,
|
|
"epoch": 1.412044771132643,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048036650598721125,
|
|
"loss": 4.7665,
|
|
"mean_token_accuracy": 0.22073037028312684,
|
|
"num_tokens": 31110337.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.1568872928619385,
|
|
"epoch": 1.4124624122953557,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048035434193707306,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.22019674628973007,
|
|
"num_tokens": 31119985.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.1447906494140625,
|
|
"epoch": 1.4128800534580688,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048034217429195986,
|
|
"loss": 4.6714,
|
|
"mean_token_accuracy": 0.2196265310049057,
|
|
"num_tokens": 31128147.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.295936346054077,
|
|
"epoch": 1.4132976946207818,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048033000305208485,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.21518369466066362,
|
|
"num_tokens": 31137150.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.281672525405884,
|
|
"epoch": 1.4137153357834948,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048031782821766086,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.21945315599441528,
|
|
"num_tokens": 31145847.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.316950130462646,
|
|
"epoch": 1.4141329769462079,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048030564978890117,
|
|
"loss": 4.8547,
|
|
"mean_token_accuracy": 0.22526210844516753,
|
|
"num_tokens": 31154313.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.300012063980103,
|
|
"epoch": 1.4145506181089207,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000480293467766019,
|
|
"loss": 4.9129,
|
|
"mean_token_accuracy": 0.2143968567252159,
|
|
"num_tokens": 31164104.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.197739124298096,
|
|
"epoch": 1.414968259271634,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004802812821492276,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.23327806144952773,
|
|
"num_tokens": 31172833.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.253879690170288,
|
|
"epoch": 1.4153859004343468,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048026909293874016,
|
|
"loss": 4.857,
|
|
"mean_token_accuracy": 0.21374865472316742,
|
|
"num_tokens": 31182557.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.276986885070801,
|
|
"epoch": 1.4158035415970598,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004802569001347702,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.2206795558333397,
|
|
"num_tokens": 31191641.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.247214698791504,
|
|
"epoch": 1.4162211827597728,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048024470373753114,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.21994493454694747,
|
|
"num_tokens": 31200689.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.275757932662964,
|
|
"epoch": 1.4166388239224859,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048023250374723656,
|
|
"loss": 4.9125,
|
|
"mean_token_accuracy": 0.21546125113964082,
|
|
"num_tokens": 31209745.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.220325517654419,
|
|
"epoch": 1.417056465085199,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004802203001640998,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.2232554093003273,
|
|
"num_tokens": 31218802.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.2374320983886715,
|
|
"epoch": 1.4174741062479117,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004802080929883348,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.22684500813484193,
|
|
"num_tokens": 31227650.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.217737054824829,
|
|
"epoch": 1.4178917474106247,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004801958822201551,
|
|
"loss": 4.7576,
|
|
"mean_token_accuracy": 0.22586473673582078,
|
|
"num_tokens": 31236490.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.258280181884766,
|
|
"epoch": 1.4183093885733378,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048018366785977445,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.22189030200242996,
|
|
"num_tokens": 31245557.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.173541831970215,
|
|
"epoch": 1.4187270297360508,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048017144990740673,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.23069326281547547,
|
|
"num_tokens": 31253804.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.256619215011597,
|
|
"epoch": 1.4191446708987638,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004801592283632658,
|
|
"loss": 4.8169,
|
|
"mean_token_accuracy": 0.21956299096345902,
|
|
"num_tokens": 31262913.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.285276889801025,
|
|
"epoch": 1.4195623120614766,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048014700322756567,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.22183513641357422,
|
|
"num_tokens": 31271274.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.294334602355957,
|
|
"epoch": 1.41997995322419,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004801347745005203,
|
|
"loss": 4.7759,
|
|
"mean_token_accuracy": 0.21912173181772232,
|
|
"num_tokens": 31280599.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.274913549423218,
|
|
"epoch": 1.4203975943869027,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004801225421823437,
|
|
"loss": 4.7958,
|
|
"mean_token_accuracy": 0.22372929006814957,
|
|
"num_tokens": 31288986.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.31135139465332,
|
|
"epoch": 1.4208152355496158,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048011030627325015,
|
|
"loss": 4.8211,
|
|
"mean_token_accuracy": 0.22563154399394988,
|
|
"num_tokens": 31298979.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.21934232711792,
|
|
"epoch": 1.4212328767123288,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048009806677345394,
|
|
"loss": 4.7794,
|
|
"mean_token_accuracy": 0.22156376391649246,
|
|
"num_tokens": 31307502.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.168694543838501,
|
|
"epoch": 1.4216505178750418,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000480085823683169,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.22374029457569122,
|
|
"num_tokens": 31316146.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.240821647644043,
|
|
"epoch": 1.4220681590377549,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004800735770026099,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.22051823735237122,
|
|
"num_tokens": 31325542.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.297180461883545,
|
|
"epoch": 1.4224858002004677,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000480061326731991,
|
|
"loss": 4.8274,
|
|
"mean_token_accuracy": 0.21457253098487855,
|
|
"num_tokens": 31334718.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.29754753112793,
|
|
"epoch": 1.4229034413631807,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004800490728715267,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.21586796790361404,
|
|
"num_tokens": 31343635.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.261555624008179,
|
|
"epoch": 1.4233210825258937,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004800368154214317,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.21844661831855774,
|
|
"num_tokens": 31352488.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.27753643989563,
|
|
"epoch": 1.4237387236886068,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004800245543819203,
|
|
"loss": 4.8635,
|
|
"mean_token_accuracy": 0.21781919300556182,
|
|
"num_tokens": 31361788.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.206384992599487,
|
|
"epoch": 1.4241563648513198,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048001228975320736,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.21300319135189055,
|
|
"num_tokens": 31371190.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.306797075271606,
|
|
"epoch": 1.4245740060140326,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004800000215355075,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.21493760496377945,
|
|
"num_tokens": 31380696.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.382461929321289,
|
|
"epoch": 1.4249916471767459,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004799877497290355,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.21318895667791365,
|
|
"num_tokens": 31390129.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.283255624771118,
|
|
"epoch": 1.4254092883394587,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047997547433400615,
|
|
"loss": 4.8147,
|
|
"mean_token_accuracy": 0.2159486472606659,
|
|
"num_tokens": 31399697.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.239959096908569,
|
|
"epoch": 1.4258269295021717,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004799631953506345,
|
|
"loss": 4.8218,
|
|
"mean_token_accuracy": 0.21639081090688705,
|
|
"num_tokens": 31408873.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.2280378341674805,
|
|
"epoch": 1.4262445706648847,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047995091277913535,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.2276080936193466,
|
|
"num_tokens": 31416980.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.32972354888916,
|
|
"epoch": 1.4266622118275978,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047993862661972373,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.20821387469768524,
|
|
"num_tokens": 31425759.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.316296195983886,
|
|
"epoch": 1.4270798529903108,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004799263368726148,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.21442081034183502,
|
|
"num_tokens": 31435481.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.294007301330566,
|
|
"epoch": 1.4274974941530236,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004799140435380237,
|
|
"loss": 4.7502,
|
|
"mean_token_accuracy": 0.21692177504301072,
|
|
"num_tokens": 31443924.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.287622165679932,
|
|
"epoch": 1.4279151353157367,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047990174661616556,
|
|
"loss": 4.9078,
|
|
"mean_token_accuracy": 0.2080122709274292,
|
|
"num_tokens": 31453982.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.285589599609375,
|
|
"epoch": 1.4283327764784497,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047988944610725574,
|
|
"loss": 4.8548,
|
|
"mean_token_accuracy": 0.21931786984205245,
|
|
"num_tokens": 31463292.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.268381357192993,
|
|
"epoch": 1.4287504176411627,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004798771420115095,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.21862568855285644,
|
|
"num_tokens": 31472314.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.2760404586792,
|
|
"epoch": 1.4291680588038758,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004798648343291423,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.22184121012687683,
|
|
"num_tokens": 31482231.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.198423242568969,
|
|
"epoch": 1.4295856999665886,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047985252306036966,
|
|
"loss": 4.7254,
|
|
"mean_token_accuracy": 0.22504375725984574,
|
|
"num_tokens": 31491405.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.29863338470459,
|
|
"epoch": 1.4300033411293018,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047984020820540695,
|
|
"loss": 4.8887,
|
|
"mean_token_accuracy": 0.21110006868839265,
|
|
"num_tokens": 31501662.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.3125427722930905,
|
|
"epoch": 1.4304209822920146,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047982788976446984,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.21580710411071777,
|
|
"num_tokens": 31510671.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.2490404605865475,
|
|
"epoch": 1.4308386234547277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000479815567737774,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.22711486667394637,
|
|
"num_tokens": 31519309.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.237497568130493,
|
|
"epoch": 1.4312562646174407,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000479803242125535,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.2207527756690979,
|
|
"num_tokens": 31528540.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.328499603271484,
|
|
"epoch": 1.4316739057801537,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047979091292796886,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.21945418417453766,
|
|
"num_tokens": 31538035.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.344531059265137,
|
|
"epoch": 1.4320915469428668,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004797785801452911,
|
|
"loss": 4.8913,
|
|
"mean_token_accuracy": 0.2140820547938347,
|
|
"num_tokens": 31548197.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.302551984786987,
|
|
"epoch": 1.4325091881055796,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004797662437777179,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.2238239973783493,
|
|
"num_tokens": 31557268.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.274143886566162,
|
|
"epoch": 1.4329268292682926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047975390382546523,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.21575941592454911,
|
|
"num_tokens": 31566503.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.278494787216187,
|
|
"epoch": 1.4333444704310057,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047974156028874894,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.21701183617115022,
|
|
"num_tokens": 31575754.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.301041126251221,
|
|
"epoch": 1.4337621115937187,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004797292131677851,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.21304357200860977,
|
|
"num_tokens": 31585172.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.2014378070831295,
|
|
"epoch": 1.4341797527564317,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047971686246279014,
|
|
"loss": 4.8957,
|
|
"mean_token_accuracy": 0.21268403977155687,
|
|
"num_tokens": 31594011.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.22096471786499,
|
|
"epoch": 1.4345973939191445,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004797045081739799,
|
|
"loss": 4.7093,
|
|
"mean_token_accuracy": 0.2263554662466049,
|
|
"num_tokens": 31602598.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.295818519592285,
|
|
"epoch": 1.4350150350818578,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004796921503015709,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.21553684771060944,
|
|
"num_tokens": 31611589.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.316072750091553,
|
|
"epoch": 1.4354326762445706,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047967978884577944,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.21843010932207108,
|
|
"num_tokens": 31620502.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.31786413192749,
|
|
"epoch": 1.4358503174072836,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004796674238068219,
|
|
"loss": 4.9005,
|
|
"mean_token_accuracy": 0.2114043191075325,
|
|
"num_tokens": 31630209.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.314279556274414,
|
|
"epoch": 1.4362679585699967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047965505518491474,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.21531765311956405,
|
|
"num_tokens": 31639346.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.344510555267334,
|
|
"epoch": 1.4366855997327097,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047964268298027456,
|
|
"loss": 4.8594,
|
|
"mean_token_accuracy": 0.2155676543712616,
|
|
"num_tokens": 31647482.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.281497383117676,
|
|
"epoch": 1.4371032408954227,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047963030719311777,
|
|
"loss": 4.8039,
|
|
"mean_token_accuracy": 0.22649306952953338,
|
|
"num_tokens": 31656218.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.321406412124634,
|
|
"epoch": 1.4375208820581356,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004796179278236612,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.21249869763851165,
|
|
"num_tokens": 31665306.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.247590732574463,
|
|
"epoch": 1.4379385232208486,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004796055448721215,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.2223116487264633,
|
|
"num_tokens": 31673689.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.284969472885132,
|
|
"epoch": 1.4383561643835616,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047959315833871546,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.20838473737239838,
|
|
"num_tokens": 31683742.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.340119218826294,
|
|
"epoch": 1.4387738055462747,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047958076822365994,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.21804194748401642,
|
|
"num_tokens": 31693721.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.306851863861084,
|
|
"epoch": 1.4391914467089877,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047956837452717185,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.23064962029457092,
|
|
"num_tokens": 31703103.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.245442628860474,
|
|
"epoch": 1.4396090878717005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047955597724946803,
|
|
"loss": 4.7201,
|
|
"mean_token_accuracy": 0.2272111400961876,
|
|
"num_tokens": 31711718.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.258282852172852,
|
|
"epoch": 1.4400267290344138,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004795435763907656,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.22878654301166534,
|
|
"num_tokens": 31721248.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.2443074703216555,
|
|
"epoch": 1.4404443701971266,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004795311719512817,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.21526361256837845,
|
|
"num_tokens": 31730109.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.409416151046753,
|
|
"epoch": 1.4408620113598396,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047951876393123344,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.19838620275259017,
|
|
"num_tokens": 31739768.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.360007619857788,
|
|
"epoch": 1.4412796525225526,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047950635233083805,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.21526430547237396,
|
|
"num_tokens": 31749965.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.2614294528961185,
|
|
"epoch": 1.4416972936852657,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047949393715031275,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.22596008628606795,
|
|
"num_tokens": 31759112.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.263979864120484,
|
|
"epoch": 1.4421149348479787,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047948151838987505,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.22087164372205734,
|
|
"num_tokens": 31768535.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.225251817703247,
|
|
"epoch": 1.4425325760106915,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047946909604974205,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.22572326064109802,
|
|
"num_tokens": 31777088.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.214486169815063,
|
|
"epoch": 1.4429502171734045,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004794566701301315,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.22201289534568786,
|
|
"num_tokens": 31785895.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.327930021286011,
|
|
"epoch": 1.4433678583361176,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047944424063126083,
|
|
"loss": 4.9019,
|
|
"mean_token_accuracy": 0.21253300011157988,
|
|
"num_tokens": 31795404.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.326214218139649,
|
|
"epoch": 1.4437854994988306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004794318075533477,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.21221279948949814,
|
|
"num_tokens": 31804899.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.232150840759277,
|
|
"epoch": 1.4442031406615436,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004794193708966096,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.21999758630990982,
|
|
"num_tokens": 31814055.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.219102621078491,
|
|
"epoch": 1.4446207818242565,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047940693066126445,
|
|
"loss": 4.7856,
|
|
"mean_token_accuracy": 0.23007302284240722,
|
|
"num_tokens": 31823193.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.2569694995880125,
|
|
"epoch": 1.4450384229869697,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004793944868475299,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.21914637386798858,
|
|
"num_tokens": 31832359.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.243664741516113,
|
|
"epoch": 1.4454560641496825,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004793820394556238,
|
|
"loss": 4.7836,
|
|
"mean_token_accuracy": 0.22033315449953078,
|
|
"num_tokens": 31841477.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.313115072250366,
|
|
"epoch": 1.4458737053123956,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004793695884857641,
|
|
"loss": 4.8746,
|
|
"mean_token_accuracy": 0.20951167196035386,
|
|
"num_tokens": 31851068.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.259710359573364,
|
|
"epoch": 1.4462913464751086,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004793571339381687,
|
|
"loss": 4.7528,
|
|
"mean_token_accuracy": 0.21897256821393968,
|
|
"num_tokens": 31860026.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.298897409439087,
|
|
"epoch": 1.4467089876378216,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004793446758130558,
|
|
"loss": 4.7975,
|
|
"mean_token_accuracy": 0.22071501463651658,
|
|
"num_tokens": 31868654.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.220455026626587,
|
|
"epoch": 1.4471266288005347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047933221411064334,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.22867524176836013,
|
|
"num_tokens": 31877801.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.227400255203247,
|
|
"epoch": 1.4475442699632475,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004793197488311494,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.2144768789410591,
|
|
"num_tokens": 31887266.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.280453062057495,
|
|
"epoch": 1.4479619111259605,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047930727997479253,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.22756671607494355,
|
|
"num_tokens": 31895957.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.323996639251709,
|
|
"epoch": 1.4483795522886735,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004792948075417906,
|
|
"loss": 4.9242,
|
|
"mean_token_accuracy": 0.20810758024454118,
|
|
"num_tokens": 31904443.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.254662752151489,
|
|
"epoch": 1.4487971934513866,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004792823315323622,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.21913047283887863,
|
|
"num_tokens": 31913534.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.285975790023803,
|
|
"epoch": 1.4492148346140996,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004792698519467258,
|
|
"loss": 4.8757,
|
|
"mean_token_accuracy": 0.21447208076715468,
|
|
"num_tokens": 31922905.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.339520692825317,
|
|
"epoch": 1.4496324757768126,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004792573687850997,
|
|
"loss": 4.8772,
|
|
"mean_token_accuracy": 0.21392224431037904,
|
|
"num_tokens": 31932861.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.356969690322876,
|
|
"epoch": 1.4500501169395257,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004792448820477025,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.21440638452768326,
|
|
"num_tokens": 31941100.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.244165658950806,
|
|
"epoch": 1.4504677581022385,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004792323917347528,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.22405412644147873,
|
|
"num_tokens": 31949860.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.179469919204712,
|
|
"epoch": 1.4508853992649515,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004792198978464692,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.22189220935106277,
|
|
"num_tokens": 31958216.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.2007183074951175,
|
|
"epoch": 1.4513030404276646,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004792074003830705,
|
|
"loss": 4.7496,
|
|
"mean_token_accuracy": 0.22808489501476287,
|
|
"num_tokens": 31966967.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.250366258621216,
|
|
"epoch": 1.4517206815903776,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004791948993447754,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.2202363520860672,
|
|
"num_tokens": 31976852.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.235775184631348,
|
|
"epoch": 1.4521383227530906,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004791823947318029,
|
|
"loss": 4.74,
|
|
"mean_token_accuracy": 0.22789452224969864,
|
|
"num_tokens": 31985966.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.249679756164551,
|
|
"epoch": 1.4525559639158034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004791698865443717,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.22515203654766083,
|
|
"num_tokens": 31994897.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.238200044631958,
|
|
"epoch": 1.4529736050785165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047915737478270093,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.21337701976299286,
|
|
"num_tokens": 32004504.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.294959592819214,
|
|
"epoch": 1.4533912462412295,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004791448594470095,
|
|
"loss": 4.7836,
|
|
"mean_token_accuracy": 0.2222188502550125,
|
|
"num_tokens": 32012907.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.2547783851623535,
|
|
"epoch": 1.4538088874039425,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004791323405375167,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.226788492500782,
|
|
"num_tokens": 32021778.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.325270557403565,
|
|
"epoch": 1.4542265285666556,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004791198180544415,
|
|
"loss": 4.8219,
|
|
"mean_token_accuracy": 0.21917122453451157,
|
|
"num_tokens": 32030471.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.321711540222168,
|
|
"epoch": 1.4546441697293686,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004791072919980032,
|
|
"loss": 4.9242,
|
|
"mean_token_accuracy": 0.21635801941156388,
|
|
"num_tokens": 32039747.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.315752172470093,
|
|
"epoch": 1.4550618108920816,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047909476236842105,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.21722905784845353,
|
|
"num_tokens": 32048911.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.336231231689453,
|
|
"epoch": 1.4554794520547945,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004790822291659144,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.20664321333169938,
|
|
"num_tokens": 32058942.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.272485685348511,
|
|
"epoch": 1.4558970932175075,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047906969239070276,
|
|
"loss": 4.916,
|
|
"mean_token_accuracy": 0.20878497809171676,
|
|
"num_tokens": 32067828.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.2557121276855465,
|
|
"epoch": 1.4563147343802205,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047905715204300543,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.22583657801151275,
|
|
"num_tokens": 32077765.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.2849750995635985,
|
|
"epoch": 1.4567323755429336,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000479044608123042,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.22025974988937377,
|
|
"num_tokens": 32087525.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.401698398590088,
|
|
"epoch": 1.4571500167056466,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004790320606310322,
|
|
"loss": 4.9349,
|
|
"mean_token_accuracy": 0.21271487921476365,
|
|
"num_tokens": 32097005.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.325953006744385,
|
|
"epoch": 1.4575676578683594,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004790195095671956,
|
|
"loss": 4.8841,
|
|
"mean_token_accuracy": 0.21043621599674225,
|
|
"num_tokens": 32106761.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.323337030410767,
|
|
"epoch": 1.4579852990310724,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004790069549317518,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.21376934945583342,
|
|
"num_tokens": 32115803.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.148148441314698,
|
|
"epoch": 1.4584029401937855,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004789943967249207,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.22718789130449296,
|
|
"num_tokens": 32124889.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.214784097671509,
|
|
"epoch": 1.4588205813564985,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004789818349469222,
|
|
"loss": 4.8109,
|
|
"mean_token_accuracy": 0.22203223258256913,
|
|
"num_tokens": 32133765.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.349303770065307,
|
|
"epoch": 1.4592382225192115,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047896926959797615,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.21420350521802903,
|
|
"num_tokens": 32142890.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.285238456726074,
|
|
"epoch": 1.4596558636819246,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004789567006783025,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.2150263488292694,
|
|
"num_tokens": 32151791.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.259457969665528,
|
|
"epoch": 1.4600735048446376,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004789441281881213,
|
|
"loss": 4.8065,
|
|
"mean_token_accuracy": 0.22163389027118682,
|
|
"num_tokens": 32160313.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.273686122894287,
|
|
"epoch": 1.4604911460073504,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004789315521276526,
|
|
"loss": 4.7858,
|
|
"mean_token_accuracy": 0.2201757624745369,
|
|
"num_tokens": 32170044.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.407813835144043,
|
|
"epoch": 1.4609087871700634,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004789189724971167,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.21392222344875336,
|
|
"num_tokens": 32178907.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.246537828445435,
|
|
"epoch": 1.4613264283327765,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047890638929673366,
|
|
"loss": 4.7964,
|
|
"mean_token_accuracy": 0.21580641269683837,
|
|
"num_tokens": 32188197.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.30641393661499,
|
|
"epoch": 1.4617440694954895,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004788938025267238,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.21748044937849045,
|
|
"num_tokens": 32198206.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.40030689239502,
|
|
"epoch": 1.4621617106582026,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047888121218730756,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.2127794787287712,
|
|
"num_tokens": 32207306.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.268271970748901,
|
|
"epoch": 1.4625793518209154,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047886861827870533,
|
|
"loss": 4.808,
|
|
"mean_token_accuracy": 0.21990834027528763,
|
|
"num_tokens": 32215945.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.230125141143799,
|
|
"epoch": 1.4629969929836284,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004788560208011375,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.22350739538669587,
|
|
"num_tokens": 32224601.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.193854951858521,
|
|
"epoch": 1.4634146341463414,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004788434197548246,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.23015398681163787,
|
|
"num_tokens": 32233265.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.256111431121826,
|
|
"epoch": 1.4638322753090545,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004788308151399873,
|
|
"loss": 4.7176,
|
|
"mean_token_accuracy": 0.22821783870458603,
|
|
"num_tokens": 32242749.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.27417221069336,
|
|
"epoch": 1.4642499164717675,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047881820695684624,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.22417065501213074,
|
|
"num_tokens": 32251295.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.209272003173828,
|
|
"epoch": 1.4646675576344805,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004788055952056221,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.22189429700374602,
|
|
"num_tokens": 32261099.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.311027097702026,
|
|
"epoch": 1.4650851987971936,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047879297988653576,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.21376995146274566,
|
|
"num_tokens": 32269420.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.280711698532104,
|
|
"epoch": 1.4655028399599064,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047878036099980795,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.22199172526597977,
|
|
"num_tokens": 32278455.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.301870918273925,
|
|
"epoch": 1.4659204811226194,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047876773854565964,
|
|
"loss": 4.8779,
|
|
"mean_token_accuracy": 0.21314395517110823,
|
|
"num_tokens": 32287292.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.309709453582764,
|
|
"epoch": 1.4663381222853324,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004787551125243118,
|
|
"loss": 4.8905,
|
|
"mean_token_accuracy": 0.2118695482611656,
|
|
"num_tokens": 32296384.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.242944383621216,
|
|
"epoch": 1.4667557634480455,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004787424829359854,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.22519443333148956,
|
|
"num_tokens": 32304908.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.268173027038574,
|
|
"epoch": 1.4671734046107585,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004787298497809017,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.2245290145277977,
|
|
"num_tokens": 32314843.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.252808618545532,
|
|
"epoch": 1.4675910457734713,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004787172130592817,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.230888532102108,
|
|
"num_tokens": 32324101.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.296078014373779,
|
|
"epoch": 1.4680086869361844,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047870457277134667,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.22689754366874695,
|
|
"num_tokens": 32333736.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.299397706985474,
|
|
"epoch": 1.4684263280988974,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004786919289173179,
|
|
"loss": 4.8442,
|
|
"mean_token_accuracy": 0.22162485718727112,
|
|
"num_tokens": 32342369.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.281079053878784,
|
|
"epoch": 1.4688439692616104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047867928149741666,
|
|
"loss": 4.7937,
|
|
"mean_token_accuracy": 0.22583410739898682,
|
|
"num_tokens": 32351576.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.396808910369873,
|
|
"epoch": 1.4692616104243235,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047866663051186444,
|
|
"loss": 4.8485,
|
|
"mean_token_accuracy": 0.21383679807186126,
|
|
"num_tokens": 32360355.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.341749429702759,
|
|
"epoch": 1.4696792515870365,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004786539759608828,
|
|
"loss": 4.8461,
|
|
"mean_token_accuracy": 0.2172882229089737,
|
|
"num_tokens": 32368611.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.330942916870117,
|
|
"epoch": 1.4700968927497495,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047864131784469314,
|
|
"loss": 4.8767,
|
|
"mean_token_accuracy": 0.213530233502388,
|
|
"num_tokens": 32377753.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.367198801040649,
|
|
"epoch": 1.4705145339124623,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000478628656163517,
|
|
"loss": 4.927,
|
|
"mean_token_accuracy": 0.20660656988620757,
|
|
"num_tokens": 32388135.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.260892868041992,
|
|
"epoch": 1.4709321750751754,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004786159909175762,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.2189699038863182,
|
|
"num_tokens": 32397149.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.2335193157196045,
|
|
"epoch": 1.4713498162378884,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004786033221070924,
|
|
"loss": 4.7732,
|
|
"mean_token_accuracy": 0.22929864525794982,
|
|
"num_tokens": 32405811.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.316333150863647,
|
|
"epoch": 1.4717674574006014,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004785906497322873,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.22906550168991088,
|
|
"num_tokens": 32413800.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.295527458190918,
|
|
"epoch": 1.4721850985633145,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047857797379338284,
|
|
"loss": 4.8162,
|
|
"mean_token_accuracy": 0.22980988621711732,
|
|
"num_tokens": 32422462.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.30354905128479,
|
|
"epoch": 1.4726027397260273,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047856529429060097,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.21134640723466874,
|
|
"num_tokens": 32433149.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.211163902282715,
|
|
"epoch": 1.4730203808887403,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047855261122416355,
|
|
"loss": 4.7647,
|
|
"mean_token_accuracy": 0.22495341300964355,
|
|
"num_tokens": 32442033.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.365427398681641,
|
|
"epoch": 1.4734380220514534,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004785399245942926,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.2159499928355217,
|
|
"num_tokens": 32451189.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.334377765655518,
|
|
"epoch": 1.4738556632141664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004785272344012104,
|
|
"loss": 4.7799,
|
|
"mean_token_accuracy": 0.22501445710659027,
|
|
"num_tokens": 32459929.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.236249017715454,
|
|
"epoch": 1.4742733043768794,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004785145406451389,
|
|
"loss": 4.8442,
|
|
"mean_token_accuracy": 0.21689998209476472,
|
|
"num_tokens": 32468275.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.260120153427124,
|
|
"epoch": 1.4746909455395925,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004785018433263004,
|
|
"loss": 4.8031,
|
|
"mean_token_accuracy": 0.2212820291519165,
|
|
"num_tokens": 32477833.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.241527700424195,
|
|
"epoch": 1.4751085867023055,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047848914244491715,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.22393854409456254,
|
|
"num_tokens": 32486458.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.263593578338623,
|
|
"epoch": 1.4755262278650183,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004784764380012115,
|
|
"loss": 4.7924,
|
|
"mean_token_accuracy": 0.2202371522784233,
|
|
"num_tokens": 32495355.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.25322995185852,
|
|
"epoch": 1.4759438690277313,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047846372999540596,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.22011320143938065,
|
|
"num_tokens": 32504083.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.257873058319092,
|
|
"epoch": 1.4763615101904444,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047845101842772285,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.2173956200480461,
|
|
"num_tokens": 32513303.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.334642314910889,
|
|
"epoch": 1.4767791513531574,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047843830329838475,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.21308786571025848,
|
|
"num_tokens": 32522183.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.313490295410157,
|
|
"epoch": 1.4771967925158704,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047842558460761437,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.21585311889648437,
|
|
"num_tokens": 32531443.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.366477823257446,
|
|
"epoch": 1.4776144336785833,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047841286235563417,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.22662430107593537,
|
|
"num_tokens": 32539435.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.255370283126831,
|
|
"epoch": 1.4780320748412963,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047840013654266707,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.2217538669705391,
|
|
"num_tokens": 32548465.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.244399929046631,
|
|
"epoch": 1.4784497160040093,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004783874071689357,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.22304220944643022,
|
|
"num_tokens": 32556511.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.325777912139893,
|
|
"epoch": 1.4788673571667224,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047837467423466284,
|
|
"loss": 4.9486,
|
|
"mean_token_accuracy": 0.21331407576799394,
|
|
"num_tokens": 32566077.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.386956024169922,
|
|
"epoch": 1.4792849983294354,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047836193774007164,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.2179647222161293,
|
|
"num_tokens": 32575942.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.260339689254761,
|
|
"epoch": 1.4797026394921484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004783491976853849,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.22653325349092485,
|
|
"num_tokens": 32584595.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.255929231643677,
|
|
"epoch": 1.4801202806548615,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047833645407082564,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.22009471505880357,
|
|
"num_tokens": 32594048.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.218377685546875,
|
|
"epoch": 1.4805379218175743,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004783237068966171,
|
|
"loss": 4.6679,
|
|
"mean_token_accuracy": 0.22177694439888002,
|
|
"num_tokens": 32603197.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.251751470565796,
|
|
"epoch": 1.4809555629802873,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047831095616298225,
|
|
"loss": 4.7933,
|
|
"mean_token_accuracy": 0.21845372766256332,
|
|
"num_tokens": 32612882.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.291467332839966,
|
|
"epoch": 1.4813732041430003,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004782982018701444,
|
|
"loss": 4.8051,
|
|
"mean_token_accuracy": 0.2229726195335388,
|
|
"num_tokens": 32622425.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.369340658187866,
|
|
"epoch": 1.4817908453057134,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004782854440183268,
|
|
"loss": 4.8893,
|
|
"mean_token_accuracy": 0.21718989610671996,
|
|
"num_tokens": 32631295.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.396670579910278,
|
|
"epoch": 1.4822084864684264,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004782726826077528,
|
|
"loss": 4.8861,
|
|
"mean_token_accuracy": 0.21424686461687087,
|
|
"num_tokens": 32639476.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.3286120891571045,
|
|
"epoch": 1.4826261276311392,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047825991763864587,
|
|
"loss": 4.8114,
|
|
"mean_token_accuracy": 0.2202995851635933,
|
|
"num_tokens": 32648704.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.321578598022461,
|
|
"epoch": 1.4830437687938522,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047824714911122934,
|
|
"loss": 4.9047,
|
|
"mean_token_accuracy": 0.21491807848215103,
|
|
"num_tokens": 32658258.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.271150684356689,
|
|
"epoch": 1.4834614099565653,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047823437702572684,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.21705152839422226,
|
|
"num_tokens": 32668002.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.313354873657227,
|
|
"epoch": 1.4838790511192783,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000478221601382362,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.21334151774644852,
|
|
"num_tokens": 32677961.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.323838520050049,
|
|
"epoch": 1.4842966922819913,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047820882218135835,
|
|
"loss": 4.7733,
|
|
"mean_token_accuracy": 0.22372522652149202,
|
|
"num_tokens": 32687523.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.2541759490966795,
|
|
"epoch": 1.4847143334447044,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047819603942293964,
|
|
"loss": 4.7548,
|
|
"mean_token_accuracy": 0.2254379138350487,
|
|
"num_tokens": 32696563.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.320412063598633,
|
|
"epoch": 1.4851319746074174,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004781832531073297,
|
|
"loss": 4.8399,
|
|
"mean_token_accuracy": 0.21599726378917694,
|
|
"num_tokens": 32704928.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.362480211257934,
|
|
"epoch": 1.4855496157701302,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047817046323475246,
|
|
"loss": 4.8501,
|
|
"mean_token_accuracy": 0.21827216893434526,
|
|
"num_tokens": 32714228.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.30145034790039,
|
|
"epoch": 1.4859672569328433,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004781576698054316,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.21817476451396942,
|
|
"num_tokens": 32724164.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.249768686294556,
|
|
"epoch": 1.4863848980955563,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004781448728195912,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.2234729379415512,
|
|
"num_tokens": 32732516.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.383047199249267,
|
|
"epoch": 1.4868025392582693,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047813207227745527,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.2055261880159378,
|
|
"num_tokens": 32741819.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.286104154586792,
|
|
"epoch": 1.4872201804209824,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047811926817924785,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.22843676209449768,
|
|
"num_tokens": 32751255.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.391040802001953,
|
|
"epoch": 1.4876378215836952,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047810646052519324,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.21337485313415527,
|
|
"num_tokens": 32760275.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.290482759475708,
|
|
"epoch": 1.4880554627464082,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004780936493155155,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.22355690747499465,
|
|
"num_tokens": 32769146.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.300225734710693,
|
|
"epoch": 1.4884731039091212,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047808083455043893,
|
|
"loss": 4.9199,
|
|
"mean_token_accuracy": 0.2148368775844574,
|
|
"num_tokens": 32778523.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.293902492523193,
|
|
"epoch": 1.4888907450718343,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047806801623018804,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.23161514848470688,
|
|
"num_tokens": 32786746.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.2961883544921875,
|
|
"epoch": 1.4893083862345473,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000478055194354987,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.22935036718845367,
|
|
"num_tokens": 32796396.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.221328163146973,
|
|
"epoch": 1.4897260273972603,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047804236892506034,
|
|
"loss": 4.8527,
|
|
"mean_token_accuracy": 0.21854495406150817,
|
|
"num_tokens": 32806329.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.276891088485717,
|
|
"epoch": 1.4901436685599734,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047802953994063266,
|
|
"loss": 4.7966,
|
|
"mean_token_accuracy": 0.2229563131928444,
|
|
"num_tokens": 32815959.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.30662579536438,
|
|
"epoch": 1.4905613097226862,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047801670740192843,
|
|
"loss": 4.764,
|
|
"mean_token_accuracy": 0.2258842945098877,
|
|
"num_tokens": 32824762.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.187421274185181,
|
|
"epoch": 1.4909789508853992,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047800387130917245,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.22324408441781998,
|
|
"num_tokens": 32833949.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.280096817016601,
|
|
"epoch": 1.4913965920481123,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047799103166258926,
|
|
"loss": 4.8712,
|
|
"mean_token_accuracy": 0.2140750303864479,
|
|
"num_tokens": 32843428.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.3864686489105225,
|
|
"epoch": 1.4918142332108253,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047797818846240383,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.20824612975120543,
|
|
"num_tokens": 32853878.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.2832879543304445,
|
|
"epoch": 1.4922318743735383,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004779653417088408,
|
|
"loss": 4.829,
|
|
"mean_token_accuracy": 0.21352275013923644,
|
|
"num_tokens": 32863011.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.317557287216187,
|
|
"epoch": 1.4926495155362511,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047795249140212523,
|
|
"loss": 4.8273,
|
|
"mean_token_accuracy": 0.21895605623722075,
|
|
"num_tokens": 32872238.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.3017480850219725,
|
|
"epoch": 1.4930671566989642,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047793963754248195,
|
|
"loss": 4.8196,
|
|
"mean_token_accuracy": 0.22102758288383484,
|
|
"num_tokens": 32880382.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.3436225891113285,
|
|
"epoch": 1.4934847978616772,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000477926780130136,
|
|
"loss": 4.8412,
|
|
"mean_token_accuracy": 0.22306911945343016,
|
|
"num_tokens": 32889199.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.3595808982849125,
|
|
"epoch": 1.4939024390243902,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047791391916531255,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.21242752075195312,
|
|
"num_tokens": 32898867.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.381779956817627,
|
|
"epoch": 1.4943200801871033,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004779010546482367,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.20813236981630326,
|
|
"num_tokens": 32907947.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.363634777069092,
|
|
"epoch": 1.4947377213498163,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004778881865791337,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.2162915885448456,
|
|
"num_tokens": 32917045.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.283740663528443,
|
|
"epoch": 1.4951553625125293,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047787531495822866,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.22292320132255555,
|
|
"num_tokens": 32926644.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.279279994964599,
|
|
"epoch": 1.4955730036752422,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047786243978574706,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.21210137158632278,
|
|
"num_tokens": 32935920.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.329392004013061,
|
|
"epoch": 1.4959906448379552,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047784956106191435,
|
|
"loss": 4.8263,
|
|
"mean_token_accuracy": 0.2183072790503502,
|
|
"num_tokens": 32945561.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.286817455291748,
|
|
"epoch": 1.4964082860006682,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004778366787869559,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.21974204629659652,
|
|
"num_tokens": 32955531.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.226329565048218,
|
|
"epoch": 1.4968259271633813,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004778237929610971,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.22116090059280397,
|
|
"num_tokens": 32964001.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.33245439529419,
|
|
"epoch": 1.4972435683260943,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004778109035845638,
|
|
"loss": 4.8808,
|
|
"mean_token_accuracy": 0.21630948781967163,
|
|
"num_tokens": 32973707.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.346097373962403,
|
|
"epoch": 1.497661209488807,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047779801065758146,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.2171626180410385,
|
|
"num_tokens": 32983029.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.296395015716553,
|
|
"epoch": 1.4980788506515201,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004777851141803758,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.2222152903676033,
|
|
"num_tokens": 32992351.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.192914247512817,
|
|
"epoch": 1.4984964918142332,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004777722141531727,
|
|
"loss": 4.6724,
|
|
"mean_token_accuracy": 0.23397230207920075,
|
|
"num_tokens": 33001090.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.305735778808594,
|
|
"epoch": 1.4989141329769462,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047775931057619786,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.2091411679983139,
|
|
"num_tokens": 33010294.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.289077615737915,
|
|
"epoch": 1.4993317741396592,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004777464034496773,
|
|
"loss": 4.8093,
|
|
"mean_token_accuracy": 0.21918243169784546,
|
|
"num_tokens": 33018633.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.279358196258545,
|
|
"epoch": 1.4997494153023723,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004777334927738368,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.21603771150112153,
|
|
"num_tokens": 33028291.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.32351508140564,
|
|
"epoch": 1.5001670564650853,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047772057854890247,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.22147800475358964,
|
|
"num_tokens": 33036603.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.283132886886596,
|
|
"epoch": 1.5005846976277981,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047770766077510045,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.2203857570886612,
|
|
"num_tokens": 33045329.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.265207386016845,
|
|
"epoch": 1.5010023387905111,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047769473945265685,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.2216331884264946,
|
|
"num_tokens": 33054753.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.288540410995483,
|
|
"epoch": 1.5014199799532242,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004776818145817979,
|
|
"loss": 4.785,
|
|
"mean_token_accuracy": 0.22635905742645263,
|
|
"num_tokens": 33063469.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.305624961853027,
|
|
"epoch": 1.5018376211159372,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047766888616274973,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.20747569650411607,
|
|
"num_tokens": 33072247.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.311016178131103,
|
|
"epoch": 1.5022552622786502,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047765595419573876,
|
|
"loss": 4.8694,
|
|
"mean_token_accuracy": 0.21445884555578232,
|
|
"num_tokens": 33083505.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.305783605575561,
|
|
"epoch": 1.502672903441363,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047764301868099136,
|
|
"loss": 4.8427,
|
|
"mean_token_accuracy": 0.22278365194797517,
|
|
"num_tokens": 33094104.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.277665805816651,
|
|
"epoch": 1.5030905446040763,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047763007961873407,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.22469458132982253,
|
|
"num_tokens": 33102936.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.327852582931518,
|
|
"epoch": 1.5035081857667891,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004776171370091933,
|
|
"loss": 4.7856,
|
|
"mean_token_accuracy": 0.22410172671079637,
|
|
"num_tokens": 33111648.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 1.5035081857667891,
|
|
"eval_entropy": 5.034241828542724,
|
|
"eval_loss": 4.815392017364502,
|
|
"eval_mean_token_accuracy": 0.2311443372680282,
|
|
"eval_num_tokens": 33111648.0,
|
|
"eval_runtime": 20.9148,
|
|
"eval_samples_per_second": 1805.56,
|
|
"eval_steps_per_second": 225.725,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.318608808517456,
|
|
"epoch": 1.5039258269295022,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004776041908525956,
|
|
"loss": 4.8372,
|
|
"mean_token_accuracy": 0.2138799324631691,
|
|
"num_tokens": 33120235.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.238550233840942,
|
|
"epoch": 1.5043434680922152,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004775912411491677,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.222526615858078,
|
|
"num_tokens": 33129152.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.188835620880127,
|
|
"epoch": 1.504761109254928,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004775782878991363,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.22141108959913253,
|
|
"num_tokens": 33137907.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.219587326049805,
|
|
"epoch": 1.5051787504176413,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047756533110272813,
|
|
"loss": 4.7978,
|
|
"mean_token_accuracy": 0.22202111780643463,
|
|
"num_tokens": 33146001.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.30776686668396,
|
|
"epoch": 1.505596391580354,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047755237076016997,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.21523094326257705,
|
|
"num_tokens": 33155389.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.304296445846558,
|
|
"epoch": 1.506014032743067,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047753940687168876,
|
|
"loss": 4.8849,
|
|
"mean_token_accuracy": 0.21914305686950683,
|
|
"num_tokens": 33164965.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.285058259963989,
|
|
"epoch": 1.5064316739057801,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004775264394375114,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.2134084790945053,
|
|
"num_tokens": 33174590.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.270154571533203,
|
|
"epoch": 1.5068493150684932,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000477513468457865,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.21554263979196547,
|
|
"num_tokens": 33183063.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.33432035446167,
|
|
"epoch": 1.5072669562312062,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047750049393297656,
|
|
"loss": 4.9382,
|
|
"mean_token_accuracy": 0.20963274985551833,
|
|
"num_tokens": 33192198.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.388918209075928,
|
|
"epoch": 1.507684597393919,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047748751586307314,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.21317534148693085,
|
|
"num_tokens": 33202445.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.322739601135254,
|
|
"epoch": 1.5081022385566323,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047747453424838216,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.22215339541435242,
|
|
"num_tokens": 33211017.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.2124974727630615,
|
|
"epoch": 1.508519879719345,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047746154908913065,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.2281240329146385,
|
|
"num_tokens": 33220345.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.303214502334595,
|
|
"epoch": 1.5089375208820581,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000477448560385546,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.22477392107248306,
|
|
"num_tokens": 33229849.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.28147668838501,
|
|
"epoch": 1.5093551620447712,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004774355681378557,
|
|
"loss": 4.7652,
|
|
"mean_token_accuracy": 0.22069572955369948,
|
|
"num_tokens": 33239079.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.221800518035889,
|
|
"epoch": 1.509772803207484,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047742257234628703,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.22356918901205064,
|
|
"num_tokens": 33248048.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.183998394012451,
|
|
"epoch": 1.5101904443701972,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047740957301106756,
|
|
"loss": 4.7615,
|
|
"mean_token_accuracy": 0.2312118873000145,
|
|
"num_tokens": 33257173.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.252456951141357,
|
|
"epoch": 1.51060808553291,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000477396570132425,
|
|
"loss": 4.8405,
|
|
"mean_token_accuracy": 0.21840773671865463,
|
|
"num_tokens": 33266800.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.3615470886230465,
|
|
"epoch": 1.511025726695623,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047738356371058673,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.21398385167121886,
|
|
"num_tokens": 33276061.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.2664916038513185,
|
|
"epoch": 1.511443367858336,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004773705537457806,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.23129346817731858,
|
|
"num_tokens": 33284786.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.206458473205567,
|
|
"epoch": 1.5118610090210491,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047735754023823433,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.22089893519878387,
|
|
"num_tokens": 33293849.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.183123016357422,
|
|
"epoch": 1.5122786501837622,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004773445231881757,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.23099140524864198,
|
|
"num_tokens": 33303387.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.261825037002564,
|
|
"epoch": 1.512696291346475,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047733150259583274,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.21967170387506485,
|
|
"num_tokens": 33312502.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.240735149383545,
|
|
"epoch": 1.5131139325091882,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047731847846143325,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.2267971083521843,
|
|
"num_tokens": 33321909.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.209177446365357,
|
|
"epoch": 1.513531573671901,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004773054507852052,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.21895990669727325,
|
|
"num_tokens": 33331249.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.267993354797364,
|
|
"epoch": 1.513949214834614,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004772924195673768,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.22145768105983735,
|
|
"num_tokens": 33340850.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.335602712631226,
|
|
"epoch": 1.5143668559973271,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047727938480817604,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.21479852199554444,
|
|
"num_tokens": 33350429.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.325919580459595,
|
|
"epoch": 1.51478449716004,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047726634650783117,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.22299656569957732,
|
|
"num_tokens": 33359687.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.297553300857544,
|
|
"epoch": 1.5152021383227532,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004772533046665705,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.21607715189456939,
|
|
"num_tokens": 33368177.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.264574670791626,
|
|
"epoch": 1.515619779485466,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004772402592846222,
|
|
"loss": 4.854,
|
|
"mean_token_accuracy": 0.2212553068995476,
|
|
"num_tokens": 33376604.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.263040208816529,
|
|
"epoch": 1.516037420648179,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047722721036221467,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.218903049826622,
|
|
"num_tokens": 33385488.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.333210182189942,
|
|
"epoch": 1.516455061810892,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004772141578995765,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.21300768554210664,
|
|
"num_tokens": 33394524.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.32941689491272,
|
|
"epoch": 1.516872702973605,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047720110189693605,
|
|
"loss": 4.8504,
|
|
"mean_token_accuracy": 0.21748559921979904,
|
|
"num_tokens": 33404300.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.263907718658447,
|
|
"epoch": 1.5172903441363181,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047718804235452193,
|
|
"loss": 4.7767,
|
|
"mean_token_accuracy": 0.22068960666656495,
|
|
"num_tokens": 33414050.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.294311809539795,
|
|
"epoch": 1.517707985299031,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004771749792725628,
|
|
"loss": 4.9024,
|
|
"mean_token_accuracy": 0.22007565349340438,
|
|
"num_tokens": 33423981.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.236170101165771,
|
|
"epoch": 1.5181256264617442,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004771619126512873,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.22748786211013794,
|
|
"num_tokens": 33433104.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.323187685012817,
|
|
"epoch": 1.518543267624457,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047714884249092413,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.21665959805250168,
|
|
"num_tokens": 33442034.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.233287286758423,
|
|
"epoch": 1.51896090878717,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004771357687917021,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.22345245033502578,
|
|
"num_tokens": 33450431.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.310760831832885,
|
|
"epoch": 1.519378549949883,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047712269155385017,
|
|
"loss": 4.8992,
|
|
"mean_token_accuracy": 0.21858255416154862,
|
|
"num_tokens": 33459790.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.299194288253784,
|
|
"epoch": 1.519796191112596,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047710961077759736,
|
|
"loss": 4.899,
|
|
"mean_token_accuracy": 0.21899016797542573,
|
|
"num_tokens": 33468802.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.282428503036499,
|
|
"epoch": 1.5202138322753092,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047709652646317236,
|
|
"loss": 4.7712,
|
|
"mean_token_accuracy": 0.22390610128641128,
|
|
"num_tokens": 33477756.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.292450904846191,
|
|
"epoch": 1.520631473438022,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047708343861080447,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.21847040951251984,
|
|
"num_tokens": 33487410.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.28086371421814,
|
|
"epoch": 1.521049114600735,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004770703472207227,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.21863989531993866,
|
|
"num_tokens": 33496682.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.400879001617431,
|
|
"epoch": 1.521466755763448,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004770572522931563,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.21016725450754165,
|
|
"num_tokens": 33505754.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.306814479827881,
|
|
"epoch": 1.521884396926161,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004770441538283345,
|
|
"loss": 4.8334,
|
|
"mean_token_accuracy": 0.22277709394693374,
|
|
"num_tokens": 33514904.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.283735179901123,
|
|
"epoch": 1.522302038088874,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047703105182648656,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.2219722554087639,
|
|
"num_tokens": 33523684.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.266135120391846,
|
|
"epoch": 1.522719679251587,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004770179462878419,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.21979551613330842,
|
|
"num_tokens": 33533066.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.266787528991699,
|
|
"epoch": 1.5231373204143002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004770048372126299,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.2122822806239128,
|
|
"num_tokens": 33542048.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.298969650268555,
|
|
"epoch": 1.523554961577013,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004769917246010801,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.22426894158124924,
|
|
"num_tokens": 33550785.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.304665231704712,
|
|
"epoch": 1.523972602739726,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004769786084534219,
|
|
"loss": 4.7997,
|
|
"mean_token_accuracy": 0.2139256104826927,
|
|
"num_tokens": 33560141.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.326738262176514,
|
|
"epoch": 1.524390243902439,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047696548876988517,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.22007800191640853,
|
|
"num_tokens": 33568866.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.319538545608521,
|
|
"epoch": 1.5248078850651519,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004769523655506994,
|
|
"loss": 4.8196,
|
|
"mean_token_accuracy": 0.22050996869802475,
|
|
"num_tokens": 33579217.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.346672677993775,
|
|
"epoch": 1.5252255262278651,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004769392387960944,
|
|
"loss": 4.9158,
|
|
"mean_token_accuracy": 0.2081061750650406,
|
|
"num_tokens": 33589608.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.321429347991943,
|
|
"epoch": 1.525643167390578,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004769261085063,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.21477739214897157,
|
|
"num_tokens": 33599263.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.241789197921753,
|
|
"epoch": 1.526060808553291,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047691297468154594,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.222979573905468,
|
|
"num_tokens": 33607946.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.351760768890381,
|
|
"epoch": 1.526478449716004,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004768998373220622,
|
|
"loss": 4.9123,
|
|
"mean_token_accuracy": 0.21560951918363572,
|
|
"num_tokens": 33617194.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.308737564086914,
|
|
"epoch": 1.526896090878717,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004768866964280789,
|
|
"loss": 4.8455,
|
|
"mean_token_accuracy": 0.21825011521577836,
|
|
"num_tokens": 33626796.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.324506568908691,
|
|
"epoch": 1.52731373204143,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047687355199982584,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.21793431490659715,
|
|
"num_tokens": 33636290.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.261144018173217,
|
|
"epoch": 1.5277313732041429,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004768604040375333,
|
|
"loss": 4.8287,
|
|
"mean_token_accuracy": 0.22622082233428956,
|
|
"num_tokens": 33644489.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.22731647491455,
|
|
"epoch": 1.5281490143668561,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047684725254143137,
|
|
"loss": 4.7046,
|
|
"mean_token_accuracy": 0.2265630394220352,
|
|
"num_tokens": 33653677.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.235058879852295,
|
|
"epoch": 1.528566655529569,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004768340975117504,
|
|
"loss": 4.7861,
|
|
"mean_token_accuracy": 0.22620357125997542,
|
|
"num_tokens": 33662787.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.269359159469604,
|
|
"epoch": 1.528984296692282,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004768209389487205,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.23236947506666183,
|
|
"num_tokens": 33671167.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.275845766067505,
|
|
"epoch": 1.529401937854995,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004768077768525722,
|
|
"loss": 4.7429,
|
|
"mean_token_accuracy": 0.22399094551801682,
|
|
"num_tokens": 33679253.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.3665087699890135,
|
|
"epoch": 1.5298195790177078,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004767946112235359,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.2173101559281349,
|
|
"num_tokens": 33688863.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.2697686672210695,
|
|
"epoch": 1.530237220180421,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000476781442061842,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.21746994256973268,
|
|
"num_tokens": 33697201.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.336027431488037,
|
|
"epoch": 1.5306548613431339,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047676826936772097,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.21906785517930985,
|
|
"num_tokens": 33706075.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.317334079742432,
|
|
"epoch": 1.531072502505847,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047675509314140365,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.20717300921678544,
|
|
"num_tokens": 33715290.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.214284801483155,
|
|
"epoch": 1.53149014366856,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004767419133831206,
|
|
"loss": 4.7406,
|
|
"mean_token_accuracy": 0.23121742606163026,
|
|
"num_tokens": 33724508.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.3272685527801515,
|
|
"epoch": 1.531907784831273,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047672873009310234,
|
|
"loss": 4.8793,
|
|
"mean_token_accuracy": 0.22005631178617477,
|
|
"num_tokens": 33733333.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.234742021560669,
|
|
"epoch": 1.532325425993986,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047671554327157996,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.22682834416627884,
|
|
"num_tokens": 33741780.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.254080581665039,
|
|
"epoch": 1.5327430671566988,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047670235291878417,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.2262381613254547,
|
|
"num_tokens": 33750259.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.2995177745819095,
|
|
"epoch": 1.533160708319412,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004766891590349459,
|
|
"loss": 4.8638,
|
|
"mean_token_accuracy": 0.21482907086610795,
|
|
"num_tokens": 33760383.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.324284410476684,
|
|
"epoch": 1.533578349482125,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004766759616202961,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.22385908365249635,
|
|
"num_tokens": 33768524.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.243515491485596,
|
|
"epoch": 1.533995990644838,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004766627606750659,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.22288006246089936,
|
|
"num_tokens": 33777448.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.322894811630249,
|
|
"epoch": 1.534413631807551,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004766495561994863,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.22430841475725175,
|
|
"num_tokens": 33787316.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.329001998901367,
|
|
"epoch": 1.534831272970264,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004766363481937885,
|
|
"loss": 4.7392,
|
|
"mean_token_accuracy": 0.222852124273777,
|
|
"num_tokens": 33796945.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.322489166259766,
|
|
"epoch": 1.535248914132977,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047662313665820365,
|
|
"loss": 4.896,
|
|
"mean_token_accuracy": 0.20802460759878158,
|
|
"num_tokens": 33807866.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.286522102355957,
|
|
"epoch": 1.5356665552956899,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004766099215929632,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.2189749851822853,
|
|
"num_tokens": 33817298.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.259603118896484,
|
|
"epoch": 1.536084196458403,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047659670299829833,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.22566051185131072,
|
|
"num_tokens": 33826552.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.235876941680909,
|
|
"epoch": 1.536501837621116,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004765834808744405,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.21628189235925674,
|
|
"num_tokens": 33836800.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.265469980239868,
|
|
"epoch": 1.536919478783829,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047657025522162123,
|
|
"loss": 4.7889,
|
|
"mean_token_accuracy": 0.22655659019947053,
|
|
"num_tokens": 33846245.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.330809879302978,
|
|
"epoch": 1.537337119946542,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000476557026040072,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.22395222038030624,
|
|
"num_tokens": 33855100.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.2497953414917,
|
|
"epoch": 1.5377547611092548,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047654379333002446,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.22033191472291946,
|
|
"num_tokens": 33863307.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.279133892059326,
|
|
"epoch": 1.538172402271968,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047653055709171013,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.21521356999874114,
|
|
"num_tokens": 33871891.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.228801250457764,
|
|
"epoch": 1.5385900434346809,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047651731732536084,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.22170378118753434,
|
|
"num_tokens": 33880913.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.367957019805909,
|
|
"epoch": 1.539007684597394,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047650407403120845,
|
|
"loss": 4.867,
|
|
"mean_token_accuracy": 0.21443211585283278,
|
|
"num_tokens": 33889838.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.372717571258545,
|
|
"epoch": 1.539425325760107,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047649082720948455,
|
|
"loss": 4.8784,
|
|
"mean_token_accuracy": 0.21634087413549424,
|
|
"num_tokens": 33898989.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.33667402267456,
|
|
"epoch": 1.53984296692282,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047647757686042125,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.2234938234090805,
|
|
"num_tokens": 33907884.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.284723949432373,
|
|
"epoch": 1.540260608085533,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047646432298425047,
|
|
"loss": 4.8312,
|
|
"mean_token_accuracy": 0.22015070617198945,
|
|
"num_tokens": 33916762.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.2548192024230955,
|
|
"epoch": 1.5406782492482458,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047645106558120417,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.22544788867235183,
|
|
"num_tokens": 33925413.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.249109172821045,
|
|
"epoch": 1.541095890410959,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004764378046515145,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.22162603884935378,
|
|
"num_tokens": 33934247.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.259431314468384,
|
|
"epoch": 1.5415135315736719,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004764245401954136,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.23123425543308257,
|
|
"num_tokens": 33943610.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.402100849151611,
|
|
"epoch": 1.541931172736385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004764112722131337,
|
|
"loss": 5.0391,
|
|
"mean_token_accuracy": 0.20048276633024215,
|
|
"num_tokens": 33953447.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.31303448677063,
|
|
"epoch": 1.542348813899098,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047639800070490695,
|
|
"loss": 4.8595,
|
|
"mean_token_accuracy": 0.2208631694316864,
|
|
"num_tokens": 33962702.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.396822309494018,
|
|
"epoch": 1.5427664550618108,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004763847256709658,
|
|
"loss": 4.8551,
|
|
"mean_token_accuracy": 0.21195948570966722,
|
|
"num_tokens": 33972604.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.34452633857727,
|
|
"epoch": 1.543184096224524,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004763714471115427,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.20999842137098312,
|
|
"num_tokens": 33982443.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.293859434127808,
|
|
"epoch": 1.5436017373872368,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004763581650268699,
|
|
"loss": 4.8382,
|
|
"mean_token_accuracy": 0.22190821766853333,
|
|
"num_tokens": 33990688.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.35039587020874,
|
|
"epoch": 1.5440193785499499,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047634487941718016,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.21610284596681595,
|
|
"num_tokens": 33999657.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.355743312835694,
|
|
"epoch": 1.544437019712663,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004763315902827059,
|
|
"loss": 4.9085,
|
|
"mean_token_accuracy": 0.21199122369289397,
|
|
"num_tokens": 34009842.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.405810785293579,
|
|
"epoch": 1.544854660875376,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047631829762367976,
|
|
"loss": 4.9466,
|
|
"mean_token_accuracy": 0.20178544968366624,
|
|
"num_tokens": 34019600.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.335718393325806,
|
|
"epoch": 1.545272302038089,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004763050014403346,
|
|
"loss": 4.9127,
|
|
"mean_token_accuracy": 0.2127282828092575,
|
|
"num_tokens": 34028256.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.31299352645874,
|
|
"epoch": 1.5456899432008018,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047629170173290296,
|
|
"loss": 4.8543,
|
|
"mean_token_accuracy": 0.21771962940692902,
|
|
"num_tokens": 34037117.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.280047225952148,
|
|
"epoch": 1.546107584363515,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047627839850161784,
|
|
"loss": 4.8289,
|
|
"mean_token_accuracy": 0.22122913599014282,
|
|
"num_tokens": 34045697.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.3945691108703615,
|
|
"epoch": 1.5465252255262278,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047626509174671214,
|
|
"loss": 4.9398,
|
|
"mean_token_accuracy": 0.21112740486860276,
|
|
"num_tokens": 34055735.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.35765905380249,
|
|
"epoch": 1.5469428666889409,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004762517814684187,
|
|
"loss": 4.8926,
|
|
"mean_token_accuracy": 0.21722633689641951,
|
|
"num_tokens": 34065780.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.320284175872803,
|
|
"epoch": 1.547360507851654,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047623846766697056,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.21782790422439574,
|
|
"num_tokens": 34075314.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.337548828125,
|
|
"epoch": 1.5477781490143667,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047622515034260077,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.2200475037097931,
|
|
"num_tokens": 34085475.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.412576580047608,
|
|
"epoch": 1.54819579017708,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004762118294955426,
|
|
"loss": 4.8617,
|
|
"mean_token_accuracy": 0.217283995449543,
|
|
"num_tokens": 34094758.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.350254344940185,
|
|
"epoch": 1.5486134313397928,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004761985051260291,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.21771894246339799,
|
|
"num_tokens": 34103605.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.280366230010986,
|
|
"epoch": 1.5490310725025058,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047618517723429366,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.22169826179742813,
|
|
"num_tokens": 34112751.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.318319368362427,
|
|
"epoch": 1.5494487136652189,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047617184582056946,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.21579501926898956,
|
|
"num_tokens": 34121814.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.241071271896362,
|
|
"epoch": 1.549866354827932,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047615851088508995,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.22491102069616317,
|
|
"num_tokens": 34130297.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.280083179473877,
|
|
"epoch": 1.550283995990645,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047614517242808866,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.22155021727085114,
|
|
"num_tokens": 34138525.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.1894533157348635,
|
|
"epoch": 1.5507016371533577,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047613183044979885,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.2324893981218338,
|
|
"num_tokens": 34147029.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.324298095703125,
|
|
"epoch": 1.551119278316071,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047611848495045434,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.21599037945270538,
|
|
"num_tokens": 34155617.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.377641916275024,
|
|
"epoch": 1.5515369194787838,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047610513593028867,
|
|
"loss": 4.8269,
|
|
"mean_token_accuracy": 0.2217123731970787,
|
|
"num_tokens": 34164693.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.312805891036987,
|
|
"epoch": 1.5519545606414968,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004760917833895355,
|
|
"loss": 4.7889,
|
|
"mean_token_accuracy": 0.2250752940773964,
|
|
"num_tokens": 34173394.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.256941080093384,
|
|
"epoch": 1.5523722018042099,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004760784273284286,
|
|
"loss": 4.7937,
|
|
"mean_token_accuracy": 0.22855391949415207,
|
|
"num_tokens": 34182522.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.264952564239502,
|
|
"epoch": 1.5527898429669227,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004760650677472018,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.21644768714904786,
|
|
"num_tokens": 34192456.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.380393075942993,
|
|
"epoch": 1.553207484129636,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000476051704646089,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.21010150015354156,
|
|
"num_tokens": 34202360.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.320730972290039,
|
|
"epoch": 1.5536251252923488,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000476038338025324,
|
|
"loss": 4.8204,
|
|
"mean_token_accuracy": 0.21800391674041747,
|
|
"num_tokens": 34211892.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.292894172668457,
|
|
"epoch": 1.5540427664550618,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047602496788514103,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.22099056094884872,
|
|
"num_tokens": 34221776.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.276742887496948,
|
|
"epoch": 1.5544604076177748,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004760115942257739,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.22512018531560898,
|
|
"num_tokens": 34230564.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.215281820297241,
|
|
"epoch": 1.5548780487804879,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047599821704745693,
|
|
"loss": 4.7806,
|
|
"mean_token_accuracy": 0.22605032175779344,
|
|
"num_tokens": 34239871.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.321815443038941,
|
|
"epoch": 1.5552956899432009,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004759848363504243,
|
|
"loss": 4.8329,
|
|
"mean_token_accuracy": 0.22399494796991348,
|
|
"num_tokens": 34248881.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.358681297302246,
|
|
"epoch": 1.5557133311059137,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004759714521349101,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.22532059252262115,
|
|
"num_tokens": 34257596.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.26807541847229,
|
|
"epoch": 1.556130972268627,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004759580644011487,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.21758917570114136,
|
|
"num_tokens": 34267030.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.318641138076782,
|
|
"epoch": 1.5565486134313398,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004759446731493745,
|
|
"loss": 4.8293,
|
|
"mean_token_accuracy": 0.21837245374917985,
|
|
"num_tokens": 34276269.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.278700542449951,
|
|
"epoch": 1.5569662545940528,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000475931278379822,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.22205683439970017,
|
|
"num_tokens": 34285193.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.230660915374756,
|
|
"epoch": 1.5573838957567658,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004759178800927255,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.22713033556938172,
|
|
"num_tokens": 34294216.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.323127365112304,
|
|
"epoch": 1.5578015369194786,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004759044782883198,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.22466099560260772,
|
|
"num_tokens": 34302546.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.281742143630981,
|
|
"epoch": 1.558219178082192,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004758910729668392,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.22997610569000243,
|
|
"num_tokens": 34312176.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.370559597015381,
|
|
"epoch": 1.5586368192449047,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004758776641285187,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.21788477301597595,
|
|
"num_tokens": 34321836.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.2540552616119385,
|
|
"epoch": 1.5590544604076177,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004758642517735928,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.22219259887933732,
|
|
"num_tokens": 34330624.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.25706524848938,
|
|
"epoch": 1.5594721015703308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047585083590229643,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.23076718151569367,
|
|
"num_tokens": 34339239.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.344662046432495,
|
|
"epoch": 1.5598897427330438,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047583741651486443,
|
|
"loss": 4.8676,
|
|
"mean_token_accuracy": 0.2111652284860611,
|
|
"num_tokens": 34348823.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.232846736907959,
|
|
"epoch": 1.5603073838957568,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004758239936115317,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.22339696437120438,
|
|
"num_tokens": 34357844.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.289846324920655,
|
|
"epoch": 1.5607250250584697,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047581056719253324,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.22030248790979384,
|
|
"num_tokens": 34367055.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.401411247253418,
|
|
"epoch": 1.561142666221183,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004757971372581041,
|
|
"loss": 4.9573,
|
|
"mean_token_accuracy": 0.21910268664360047,
|
|
"num_tokens": 34377329.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.331189966201782,
|
|
"epoch": 1.5615603073838957,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047578370380847935,
|
|
"loss": 4.959,
|
|
"mean_token_accuracy": 0.2086846947669983,
|
|
"num_tokens": 34386508.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.317177629470825,
|
|
"epoch": 1.5619779485466088,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047577026684389413,
|
|
"loss": 4.8176,
|
|
"mean_token_accuracy": 0.21554824262857436,
|
|
"num_tokens": 34396075.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.36429500579834,
|
|
"epoch": 1.5623955897093218,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004757568263645838,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.21660960763692855,
|
|
"num_tokens": 34405409.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.317828750610351,
|
|
"epoch": 1.5628132308720346,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004757433823707835,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.21784473657608033,
|
|
"num_tokens": 34415559.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.341873550415039,
|
|
"epoch": 1.5632308720347479,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004757299348627287,
|
|
"loss": 4.8369,
|
|
"mean_token_accuracy": 0.2258772447705269,
|
|
"num_tokens": 34424137.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.224458980560303,
|
|
"epoch": 1.5636485131974607,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047571648384065477,
|
|
"loss": 4.832,
|
|
"mean_token_accuracy": 0.2219492882490158,
|
|
"num_tokens": 34433498.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.2929295063018795,
|
|
"epoch": 1.5640661543601737,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004757030293047972,
|
|
"loss": 4.7966,
|
|
"mean_token_accuracy": 0.22455836236476898,
|
|
"num_tokens": 34443218.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.302792882919311,
|
|
"epoch": 1.5644837955228867,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004756895712553915,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.21840295642614366,
|
|
"num_tokens": 34452981.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.290745449066162,
|
|
"epoch": 1.5649014366855998,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047567610969267326,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.21410537809133529,
|
|
"num_tokens": 34462763.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.240296316146851,
|
|
"epoch": 1.5653190778483128,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004756626446168782,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.2315189391374588,
|
|
"num_tokens": 34471841.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.410390615463257,
|
|
"epoch": 1.5657367190110256,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047564917602824203,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.2131902500987053,
|
|
"num_tokens": 34482280.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.429169464111328,
|
|
"epoch": 1.5661543601737389,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004756357039270004,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.21248093694448472,
|
|
"num_tokens": 34492774.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.3166890144348145,
|
|
"epoch": 1.5665720013364517,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047562222831338933,
|
|
"loss": 4.7565,
|
|
"mean_token_accuracy": 0.22405146062374115,
|
|
"num_tokens": 34501626.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.289518213272094,
|
|
"epoch": 1.5669896424991647,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047560874918764473,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.21258814930915831,
|
|
"num_tokens": 34510264.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.346960878372192,
|
|
"epoch": 1.5674072836618778,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047559526655000244,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.21173009276390076,
|
|
"num_tokens": 34520540.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.332462167739868,
|
|
"epoch": 1.5678249248245906,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004755817804006986,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.21725404411554336,
|
|
"num_tokens": 34529669.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.2903868675231935,
|
|
"epoch": 1.5682425659873038,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004755682907399692,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.21843009144067765,
|
|
"num_tokens": 34538802.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.299870395660401,
|
|
"epoch": 1.5686602071500166,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047555479756805055,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.21465496718883514,
|
|
"num_tokens": 34547583.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.280304908752441,
|
|
"epoch": 1.5690778483127297,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004755413008851786,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.220072640478611,
|
|
"num_tokens": 34556045.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.2538032054901125,
|
|
"epoch": 1.5694954894754427,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004755278006915899,
|
|
"loss": 4.676,
|
|
"mean_token_accuracy": 0.2354222282767296,
|
|
"num_tokens": 34564910.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.311500310897827,
|
|
"epoch": 1.5699131306381557,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047551429698752064,
|
|
"loss": 4.8725,
|
|
"mean_token_accuracy": 0.21741118282079697,
|
|
"num_tokens": 34573274.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.262680292129517,
|
|
"epoch": 1.5703307718008688,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047550078977320724,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.22271993905305862,
|
|
"num_tokens": 34583015.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.378917980194092,
|
|
"epoch": 1.5707484129635816,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004754872790488862,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.20876245945692062,
|
|
"num_tokens": 34592311.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.371283769607544,
|
|
"epoch": 1.5711660541262948,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000475473764814794,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.22317988127470018,
|
|
"num_tokens": 34600806.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.270185422897339,
|
|
"epoch": 1.5715836952890077,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047546024707116727,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.21435945332050324,
|
|
"num_tokens": 34609830.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.285937166213989,
|
|
"epoch": 1.5720013364517207,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047544672581824256,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.21358498632907869,
|
|
"num_tokens": 34618870.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.267854833602906,
|
|
"epoch": 1.5724189776144337,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004754332010562567,
|
|
"loss": 4.7166,
|
|
"mean_token_accuracy": 0.22426872849464416,
|
|
"num_tokens": 34628349.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.297967004776001,
|
|
"epoch": 1.5728366187771465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004754196727854463,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.21443159133195877,
|
|
"num_tokens": 34638492.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.343942022323608,
|
|
"epoch": 1.5732542599398598,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047540614100604836,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.22279983311891555,
|
|
"num_tokens": 34649084.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.323209571838379,
|
|
"epoch": 1.5736719011025726,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004753926057182997,
|
|
"loss": 4.8192,
|
|
"mean_token_accuracy": 0.22122442573308945,
|
|
"num_tokens": 34658392.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.274008083343506,
|
|
"epoch": 1.5740895422652856,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047537906692243716,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.21180291324853898,
|
|
"num_tokens": 34667727.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.298745012283325,
|
|
"epoch": 1.5745071834279987,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000475365524618698,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.22223596423864364,
|
|
"num_tokens": 34676260.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.433695459365845,
|
|
"epoch": 1.5749248245907117,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004753519788073191,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.2121237263083458,
|
|
"num_tokens": 34685145.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.284246206283569,
|
|
"epoch": 1.5753424657534247,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004753384294885376,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.23328480869531631,
|
|
"num_tokens": 34694035.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.277693462371826,
|
|
"epoch": 1.5757601069161375,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004753248766625908,
|
|
"loss": 4.8109,
|
|
"mean_token_accuracy": 0.2163689762353897,
|
|
"num_tokens": 34702634.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.269853353500366,
|
|
"epoch": 1.5761777480788508,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004753113203297159,
|
|
"loss": 4.8148,
|
|
"mean_token_accuracy": 0.21614917367696762,
|
|
"num_tokens": 34711925.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.245782375335693,
|
|
"epoch": 1.5765953892415636,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004752977604901502,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.23467011153697967,
|
|
"num_tokens": 34720131.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.301069021224976,
|
|
"epoch": 1.5770130304042767,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047528419714413107,
|
|
"loss": 4.8597,
|
|
"mean_token_accuracy": 0.2156160891056061,
|
|
"num_tokens": 34728869.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.2700286388397215,
|
|
"epoch": 1.5774306715669897,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047527063029189606,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.23266907781362534,
|
|
"num_tokens": 34737343.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.370336246490479,
|
|
"epoch": 1.5778483127297025,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004752570599336825,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.2152312085032463,
|
|
"num_tokens": 34746752.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.369347858428955,
|
|
"epoch": 1.5782659538924158,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047524348606972817,
|
|
"loss": 4.8498,
|
|
"mean_token_accuracy": 0.22120028138160705,
|
|
"num_tokens": 34755672.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.331867504119873,
|
|
"epoch": 1.5786835950551286,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047522990870027055,
|
|
"loss": 4.8635,
|
|
"mean_token_accuracy": 0.21329453438520432,
|
|
"num_tokens": 34764558.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.298849105834961,
|
|
"epoch": 1.5791012362178416,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004752163278255473,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.21369115859270096,
|
|
"num_tokens": 34773663.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.226781034469605,
|
|
"epoch": 1.5795188773805546,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004752027434457963,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.21975539475679398,
|
|
"num_tokens": 34782297.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.4156379222869875,
|
|
"epoch": 1.5799365185432677,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004751891555612552,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.20820710211992263,
|
|
"num_tokens": 34791734.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.341485214233399,
|
|
"epoch": 1.5803541597059807,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004751755641721621,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.22391262352466584,
|
|
"num_tokens": 34801187.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.278911161422729,
|
|
"epoch": 1.5807718008686935,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047516196927875474,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.22199028879404067,
|
|
"num_tokens": 34810084.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.405764102935791,
|
|
"epoch": 1.5811894420314068,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047514837088127117,
|
|
"loss": 4.9147,
|
|
"mean_token_accuracy": 0.2158913195133209,
|
|
"num_tokens": 34819160.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.259592866897583,
|
|
"epoch": 1.5816070831941196,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004751347689799494,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.23949646055698395,
|
|
"num_tokens": 34828272.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.253465080261231,
|
|
"epoch": 1.5820247243568326,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047512116357502766,
|
|
"loss": 4.7475,
|
|
"mean_token_accuracy": 0.2265564411878586,
|
|
"num_tokens": 34838030.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.293050289154053,
|
|
"epoch": 1.5824423655195456,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047510755466674407,
|
|
"loss": 4.856,
|
|
"mean_token_accuracy": 0.22048281878232956,
|
|
"num_tokens": 34846489.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.322943639755249,
|
|
"epoch": 1.5828600066822585,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047509394225533685,
|
|
"loss": 4.8097,
|
|
"mean_token_accuracy": 0.21951953321695328,
|
|
"num_tokens": 34855926.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.354677486419678,
|
|
"epoch": 1.5832776478449717,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004750803263410443,
|
|
"loss": 4.7919,
|
|
"mean_token_accuracy": 0.2239959493279457,
|
|
"num_tokens": 34865158.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.296063470840454,
|
|
"epoch": 1.5836952890076845,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004750667069241048,
|
|
"loss": 4.8848,
|
|
"mean_token_accuracy": 0.21207224130630492,
|
|
"num_tokens": 34875429.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.333180284500122,
|
|
"epoch": 1.5841129301703976,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004750530840047568,
|
|
"loss": 4.8446,
|
|
"mean_token_accuracy": 0.22190602123737335,
|
|
"num_tokens": 34885663.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.27138237953186,
|
|
"epoch": 1.5845305713331106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047503945758323873,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.22625853717327118,
|
|
"num_tokens": 34894976.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.334041881561279,
|
|
"epoch": 1.5849482124958236,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004750258276597892,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.2186779722571373,
|
|
"num_tokens": 34905630.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.259051895141601,
|
|
"epoch": 1.5853658536585367,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047501219423464673,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.2244519755244255,
|
|
"num_tokens": 34914906.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.245781373977661,
|
|
"epoch": 1.5857834948212495,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004749985573080501,
|
|
"loss": 4.7302,
|
|
"mean_token_accuracy": 0.22360887825489045,
|
|
"num_tokens": 34923274.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.304239130020141,
|
|
"epoch": 1.5862011359839627,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000474984916880238,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.22683696895837785,
|
|
"num_tokens": 34932085.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.266248369216919,
|
|
"epoch": 1.5866187771466755,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004749712729514491,
|
|
"loss": 4.8811,
|
|
"mean_token_accuracy": 0.21550805419683455,
|
|
"num_tokens": 34940871.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.355046701431275,
|
|
"epoch": 1.5870364183093886,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004749576255219225,
|
|
"loss": 4.9199,
|
|
"mean_token_accuracy": 0.21418577432632446,
|
|
"num_tokens": 34950703.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.402777004241943,
|
|
"epoch": 1.5874540594721016,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004749439745918969,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.21240184754133223,
|
|
"num_tokens": 34959988.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.324064064025879,
|
|
"epoch": 1.5878717006348144,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047493032016161134,
|
|
"loss": 4.8711,
|
|
"mean_token_accuracy": 0.2189060628414154,
|
|
"num_tokens": 34968608.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.346681880950928,
|
|
"epoch": 1.5882893417975277,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004749166622313049,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.20883533507585525,
|
|
"num_tokens": 34977200.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.349547004699707,
|
|
"epoch": 1.5887069829602405,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047490300080121667,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.22906010150909423,
|
|
"num_tokens": 34986403.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.2964191913604735,
|
|
"epoch": 1.5891246241229535,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047488933587158585,
|
|
"loss": 4.9014,
|
|
"mean_token_accuracy": 0.21396338045597077,
|
|
"num_tokens": 34995672.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.272713947296142,
|
|
"epoch": 1.5895422652856666,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004748756674426514,
|
|
"loss": 4.9214,
|
|
"mean_token_accuracy": 0.2147679701447487,
|
|
"num_tokens": 35004636.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.28773684501648,
|
|
"epoch": 1.5899599064483796,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000474861995514653,
|
|
"loss": 4.7429,
|
|
"mean_token_accuracy": 0.22529917657375337,
|
|
"num_tokens": 35014023.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.390324068069458,
|
|
"epoch": 1.5903775476110926,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004748483200878297,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.22211767882108688,
|
|
"num_tokens": 35023762.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.341156053543091,
|
|
"epoch": 1.5907951887738054,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000474834641162421,
|
|
"loss": 4.7778,
|
|
"mean_token_accuracy": 0.22274623513221742,
|
|
"num_tokens": 35032485.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.325122451782226,
|
|
"epoch": 1.5912128299365187,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047482095873866635,
|
|
"loss": 4.8691,
|
|
"mean_token_accuracy": 0.21396528780460358,
|
|
"num_tokens": 35041416.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.324957656860351,
|
|
"epoch": 1.5916304710992315,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004748072728168053,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.223506860435009,
|
|
"num_tokens": 35051223.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.2798233985900875,
|
|
"epoch": 1.5920481122619445,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004747935833970775,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.21700057238340378,
|
|
"num_tokens": 35060935.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.252585744857788,
|
|
"epoch": 1.5924657534246576,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004747798904797225,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.22514245361089708,
|
|
"num_tokens": 35070249.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.309111309051514,
|
|
"epoch": 1.5928833945873704,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047476619406497996,
|
|
"loss": 4.7815,
|
|
"mean_token_accuracy": 0.21784338504076003,
|
|
"num_tokens": 35079040.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.252698802947998,
|
|
"epoch": 1.5933010357500836,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004747524941530898,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.22413024306297302,
|
|
"num_tokens": 35087451.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.376547145843506,
|
|
"epoch": 1.5937186769127965,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004747387907442918,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.22026601433753967,
|
|
"num_tokens": 35096144.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.384009885787964,
|
|
"epoch": 1.5941363180755095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047472508383882586,
|
|
"loss": 4.8533,
|
|
"mean_token_accuracy": 0.21917724013328552,
|
|
"num_tokens": 35105547.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.3408411026000975,
|
|
"epoch": 1.5945539592382225,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004747113734369319,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.21825490295886993,
|
|
"num_tokens": 35114164.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.310673379898072,
|
|
"epoch": 1.5949716004009356,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004746976595388499,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.2163145825266838,
|
|
"num_tokens": 35125184.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.291650438308716,
|
|
"epoch": 1.5953892415636486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047468394214482,
|
|
"loss": 4.7371,
|
|
"mean_token_accuracy": 0.2282216802239418,
|
|
"num_tokens": 35134207.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.272513151168823,
|
|
"epoch": 1.5958068827263614,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004746702212550824,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.22488813996315002,
|
|
"num_tokens": 35143651.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.309198665618896,
|
|
"epoch": 1.5962245238890747,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047465649686987717,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.2170061871409416,
|
|
"num_tokens": 35152907.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.305409383773804,
|
|
"epoch": 1.5966421650517875,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004746427689894447,
|
|
"loss": 4.7584,
|
|
"mean_token_accuracy": 0.22892068475484847,
|
|
"num_tokens": 35161927.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.304594898223877,
|
|
"epoch": 1.5970598062145005,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004746290376140252,
|
|
"loss": 4.8324,
|
|
"mean_token_accuracy": 0.2167896330356598,
|
|
"num_tokens": 35171303.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.388915014266968,
|
|
"epoch": 1.5974774473772135,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004746153027438592,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.21512818485498428,
|
|
"num_tokens": 35181160.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.350850439071655,
|
|
"epoch": 1.5978950885399263,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004746015643791869,
|
|
"loss": 4.8695,
|
|
"mean_token_accuracy": 0.21539389193058014,
|
|
"num_tokens": 35190335.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.350998497009277,
|
|
"epoch": 1.5983127297026396,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000474587822520249,
|
|
"loss": 4.8901,
|
|
"mean_token_accuracy": 0.2164166361093521,
|
|
"num_tokens": 35200036.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.343748998641968,
|
|
"epoch": 1.5987303708653524,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004745740771672861,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.22331552505493163,
|
|
"num_tokens": 35208203.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.250031852722168,
|
|
"epoch": 1.5991480120280654,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004745603283205387,
|
|
"loss": 4.7388,
|
|
"mean_token_accuracy": 0.22787584364414215,
|
|
"num_tokens": 35216963.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.359557390213013,
|
|
"epoch": 1.5995656531907785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047454657598024755,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.21982156336307526,
|
|
"num_tokens": 35226170.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.250808763504028,
|
|
"epoch": 1.5999832943534915,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047453282014665334,
|
|
"loss": 4.719,
|
|
"mean_token_accuracy": 0.2254611998796463,
|
|
"num_tokens": 35234383.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.24186224937439,
|
|
"epoch": 1.6004009355162045,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047451906081999695,
|
|
"loss": 4.705,
|
|
"mean_token_accuracy": 0.23320845663547515,
|
|
"num_tokens": 35242771.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.2523643493652346,
|
|
"epoch": 1.6008185766789174,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004745052980005193,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.22948239296674727,
|
|
"num_tokens": 35251333.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.346852350234985,
|
|
"epoch": 1.6012362178416306,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004744915316884612,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.21388676166534423,
|
|
"num_tokens": 35260423.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.3400359630584715,
|
|
"epoch": 1.6016538590043434,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004744777618840637,
|
|
"loss": 4.7617,
|
|
"mean_token_accuracy": 0.22950063198804854,
|
|
"num_tokens": 35268838.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.350095748901367,
|
|
"epoch": 1.6020715001670565,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000474463988587568,
|
|
"loss": 4.9047,
|
|
"mean_token_accuracy": 0.21419601142406464,
|
|
"num_tokens": 35279395.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.358883666992187,
|
|
"epoch": 1.6024891413297695,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047445021179921495,
|
|
"loss": 4.825,
|
|
"mean_token_accuracy": 0.2144858121871948,
|
|
"num_tokens": 35289637.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.305075550079346,
|
|
"epoch": 1.6029067824924823,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004744364315192459,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.2188711479306221,
|
|
"num_tokens": 35299813.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.324653053283692,
|
|
"epoch": 1.6033244236551956,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047442264774790203,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.22228792905807496,
|
|
"num_tokens": 35308162.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.2884969234466555,
|
|
"epoch": 1.6037420648179084,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004744088604854248,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.2205485701560974,
|
|
"num_tokens": 35317232.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.321055889129639,
|
|
"epoch": 1.6041597059806214,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047439506973205527,
|
|
"loss": 4.7796,
|
|
"mean_token_accuracy": 0.2261677086353302,
|
|
"num_tokens": 35326011.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.2417233943939205,
|
|
"epoch": 1.6045773471433344,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004743812754880351,
|
|
"loss": 4.7105,
|
|
"mean_token_accuracy": 0.22620407491922379,
|
|
"num_tokens": 35333935.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.283054304122925,
|
|
"epoch": 1.6049949883060475,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004743674777536057,
|
|
"loss": 4.8152,
|
|
"mean_token_accuracy": 0.22060155421495437,
|
|
"num_tokens": 35343512.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.327441644668579,
|
|
"epoch": 1.6054126294687605,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004743536765290087,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.22088233083486558,
|
|
"num_tokens": 35353276.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.303109502792358,
|
|
"epoch": 1.6058302706314733,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047433987181448546,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.2250986725091934,
|
|
"num_tokens": 35362101.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.266646480560302,
|
|
"epoch": 1.6062479117941866,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004743260636102779,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.21892579644918442,
|
|
"num_tokens": 35370998.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.389833164215088,
|
|
"epoch": 1.6066655529568994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047431225191662776,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.20785731971263885,
|
|
"num_tokens": 35380347.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.346798658370972,
|
|
"epoch": 1.6070831941196124,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047429843673377664,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.22291916012763976,
|
|
"num_tokens": 35388586.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.309297323226929,
|
|
"epoch": 1.6075008352823255,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047428461806196646,
|
|
"loss": 4.8805,
|
|
"mean_token_accuracy": 0.222579462826252,
|
|
"num_tokens": 35397649.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.285496568679809,
|
|
"epoch": 1.6079184764450383,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004742707959014393,
|
|
"loss": 4.8219,
|
|
"mean_token_accuracy": 0.22365635484457017,
|
|
"num_tokens": 35405790.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.315665245056152,
|
|
"epoch": 1.6083361176077515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047425697025243693,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.21656886041164397,
|
|
"num_tokens": 35414389.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.281975507736206,
|
|
"epoch": 1.6087537587704643,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047424314111520134,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.22107585668563842,
|
|
"num_tokens": 35424909.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.3051064014434814,
|
|
"epoch": 1.6091713999331774,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004742293084899749,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.22540747970342637,
|
|
"num_tokens": 35434054.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.322884225845337,
|
|
"epoch": 1.6095890410958904,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004742154723769995,
|
|
"loss": 4.8181,
|
|
"mean_token_accuracy": 0.22224614918231964,
|
|
"num_tokens": 35443722.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.385793924331665,
|
|
"epoch": 1.6100066822586034,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004742016327765175,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.2175455927848816,
|
|
"num_tokens": 35453067.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.245986223220825,
|
|
"epoch": 1.6104243234213165,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004741877896887711,
|
|
"loss": 4.7179,
|
|
"mean_token_accuracy": 0.22753121256828307,
|
|
"num_tokens": 35462425.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.2841791152954105,
|
|
"epoch": 1.6108419645840293,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004741739431140027,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.22252241373062134,
|
|
"num_tokens": 35472037.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.2906732082366945,
|
|
"epoch": 1.6112596057467425,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047416009305245474,
|
|
"loss": 4.8328,
|
|
"mean_token_accuracy": 0.22214440256357193,
|
|
"num_tokens": 35481411.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.24709005355835,
|
|
"epoch": 1.6116772469094554,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004741462395043695,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.23325034976005554,
|
|
"num_tokens": 35490019.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.266236162185669,
|
|
"epoch": 1.6120948880721684,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047413238246998975,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.22447624653577805,
|
|
"num_tokens": 35499229.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.3194358348846436,
|
|
"epoch": 1.6125125292348814,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004741185219495579,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.21994250565767287,
|
|
"num_tokens": 35508473.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.297519826889038,
|
|
"epoch": 1.6129301703975942,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004741046579433166,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.22044393867254258,
|
|
"num_tokens": 35517887.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.290625381469726,
|
|
"epoch": 1.6133478115603075,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047409079045150865,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.2210768312215805,
|
|
"num_tokens": 35527470.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.339223003387451,
|
|
"epoch": 1.6137654527230203,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047407691947437677,
|
|
"loss": 4.8573,
|
|
"mean_token_accuracy": 0.22450193762779236,
|
|
"num_tokens": 35537670.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.298899936676025,
|
|
"epoch": 1.6141830938857333,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047406304501216375,
|
|
"loss": 4.8176,
|
|
"mean_token_accuracy": 0.2180238649249077,
|
|
"num_tokens": 35546903.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.323214960098267,
|
|
"epoch": 1.6146007350484464,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047404916706511255,
|
|
"loss": 4.7964,
|
|
"mean_token_accuracy": 0.2187105044722557,
|
|
"num_tokens": 35556198.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.408259105682373,
|
|
"epoch": 1.6150183762111594,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047403528563346603,
|
|
"loss": 4.9517,
|
|
"mean_token_accuracy": 0.20930270850658417,
|
|
"num_tokens": 35566381.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.2711278915405275,
|
|
"epoch": 1.6154360173738724,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047402140071746743,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.2270039737224579,
|
|
"num_tokens": 35575692.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.313700532913208,
|
|
"epoch": 1.6158536585365852,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047400751231735946,
|
|
"loss": 4.8058,
|
|
"mean_token_accuracy": 0.2164196789264679,
|
|
"num_tokens": 35584783.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.346177625656128,
|
|
"epoch": 1.6162712996992985,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047399362043338547,
|
|
"loss": 4.8386,
|
|
"mean_token_accuracy": 0.2163972571492195,
|
|
"num_tokens": 35595410.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.281248283386231,
|
|
"epoch": 1.6166889408620113,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004739797250657887,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.22341189682483673,
|
|
"num_tokens": 35604950.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.299550151824951,
|
|
"epoch": 1.6171065820247243,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047396582621481224,
|
|
"loss": 4.8455,
|
|
"mean_token_accuracy": 0.21139848083257676,
|
|
"num_tokens": 35614227.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.292137241363525,
|
|
"epoch": 1.6175242231874374,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047395192388069955,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.2205547347664833,
|
|
"num_tokens": 35623349.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.278601503372192,
|
|
"epoch": 1.6179418643501502,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047393801806369396,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.2322676196694374,
|
|
"num_tokens": 35632169.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.291388940811157,
|
|
"epoch": 1.6183595055128634,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047392410876403887,
|
|
"loss": 4.8832,
|
|
"mean_token_accuracy": 0.2158386766910553,
|
|
"num_tokens": 35642121.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.413608407974243,
|
|
"epoch": 1.6187771466755763,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047391019598197785,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.21899696737527846,
|
|
"num_tokens": 35651771.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.324362182617188,
|
|
"epoch": 1.6191947878382893,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004738962797177544,
|
|
"loss": 4.8326,
|
|
"mean_token_accuracy": 0.2170087292790413,
|
|
"num_tokens": 35661422.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.374948644638062,
|
|
"epoch": 1.6196124290010023,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004738823599716121,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.21388201266527176,
|
|
"num_tokens": 35672245.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.28096718788147,
|
|
"epoch": 1.6200300701637154,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047386843674379484,
|
|
"loss": 4.8316,
|
|
"mean_token_accuracy": 0.21355923116207123,
|
|
"num_tokens": 35681690.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.228851222991944,
|
|
"epoch": 1.6204477113264284,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004738545100345461,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.23406388461589814,
|
|
"num_tokens": 35690265.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.354303455352783,
|
|
"epoch": 1.6208653524891412,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047384057984410985,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.21774283647537232,
|
|
"num_tokens": 35699768.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.2919281959533695,
|
|
"epoch": 1.6212829936518545,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047382664617272985,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.21880585551261902,
|
|
"num_tokens": 35708785.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.320146369934082,
|
|
"epoch": 1.6217006348145673,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047381270902065013,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.21324510425329207,
|
|
"num_tokens": 35719224.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.331442594528198,
|
|
"epoch": 1.6221182759772803,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047379876838811463,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.2120247334241867,
|
|
"num_tokens": 35727830.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.352905988693237,
|
|
"epoch": 1.6225359171399933,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004737848242753674,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.22032132595777512,
|
|
"num_tokens": 35736818.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.2956102848052975,
|
|
"epoch": 1.6229535583027062,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004737708766826525,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.22008379250764848,
|
|
"num_tokens": 35746009.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.335573291778564,
|
|
"epoch": 1.6233711994654194,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004737569256102142,
|
|
"loss": 4.6963,
|
|
"mean_token_accuracy": 0.2322421371936798,
|
|
"num_tokens": 35754012.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.307722043991089,
|
|
"epoch": 1.6237888406281322,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047374297105829663,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.22061223834753035,
|
|
"num_tokens": 35763709.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.302915954589844,
|
|
"epoch": 1.6242064817908453,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047372901302714413,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.21951305568218232,
|
|
"num_tokens": 35773457.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.252918338775634,
|
|
"epoch": 1.6246241229535583,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047371505151700105,
|
|
"loss": 4.752,
|
|
"mean_token_accuracy": 0.22686156630516052,
|
|
"num_tokens": 35781713.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.290509366989136,
|
|
"epoch": 1.6250417641162713,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047370108652811186,
|
|
"loss": 4.7212,
|
|
"mean_token_accuracy": 0.22301321774721145,
|
|
"num_tokens": 35790796.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.274317789077759,
|
|
"epoch": 1.6254594052789844,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004736871180607209,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.22486741244792938,
|
|
"num_tokens": 35799919.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.373020219802856,
|
|
"epoch": 1.6258770464416972,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047367314611507276,
|
|
"loss": 4.9177,
|
|
"mean_token_accuracy": 0.21574167609214784,
|
|
"num_tokens": 35809642.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.358575677871704,
|
|
"epoch": 1.6262946876044104,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047365917069141215,
|
|
"loss": 4.841,
|
|
"mean_token_accuracy": 0.216886068880558,
|
|
"num_tokens": 35819020.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.422776985168457,
|
|
"epoch": 1.6267123287671232,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004736451917899835,
|
|
"loss": 4.8417,
|
|
"mean_token_accuracy": 0.22041900008916854,
|
|
"num_tokens": 35827657.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.30084376335144,
|
|
"epoch": 1.6271299699298363,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004736312094110317,
|
|
"loss": 4.8227,
|
|
"mean_token_accuracy": 0.21623564064502715,
|
|
"num_tokens": 35836727.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.232646322250366,
|
|
"epoch": 1.6275476110925493,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004736172235548016,
|
|
"loss": 4.7706,
|
|
"mean_token_accuracy": 0.21788598895072936,
|
|
"num_tokens": 35846251.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.336286640167236,
|
|
"epoch": 1.6279652522552621,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004736032342215378,
|
|
"loss": 4.7405,
|
|
"mean_token_accuracy": 0.22315747439861297,
|
|
"num_tokens": 35855736.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.324721813201904,
|
|
"epoch": 1.6283828934179754,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047358924141148543,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.23250928819179534,
|
|
"num_tokens": 35864630.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.360819339752197,
|
|
"epoch": 1.6288005345806882,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047357524512488925,
|
|
"loss": 4.8425,
|
|
"mean_token_accuracy": 0.21276190578937532,
|
|
"num_tokens": 35874021.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.304725646972656,
|
|
"epoch": 1.6292181757434012,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004735612453619944,
|
|
"loss": 4.8162,
|
|
"mean_token_accuracy": 0.22472977340221406,
|
|
"num_tokens": 35882696.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.370482063293457,
|
|
"epoch": 1.6296358169061143,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000473547242123046,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.21322971880435942,
|
|
"num_tokens": 35892887.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.29640154838562,
|
|
"epoch": 1.6300534580688273,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004735332354082891,
|
|
"loss": 4.737,
|
|
"mean_token_accuracy": 0.22805873602628707,
|
|
"num_tokens": 35901547.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.403277444839477,
|
|
"epoch": 1.6304710992315403,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047351922521796894,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.21910243183374406,
|
|
"num_tokens": 35910982.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.365507650375366,
|
|
"epoch": 1.6308887403942531,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004735052115523307,
|
|
"loss": 4.8431,
|
|
"mean_token_accuracy": 0.2146484762430191,
|
|
"num_tokens": 35920548.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.450023984909057,
|
|
"epoch": 1.6313063815569664,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004734911944116199,
|
|
"loss": 4.8525,
|
|
"mean_token_accuracy": 0.21653139740228652,
|
|
"num_tokens": 35930371.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.317417287826538,
|
|
"epoch": 1.6317240227196792,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047347717379608184,
|
|
"loss": 4.8835,
|
|
"mean_token_accuracy": 0.21473793387413026,
|
|
"num_tokens": 35939724.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.409931468963623,
|
|
"epoch": 1.6321416638823922,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047346314970596185,
|
|
"loss": 4.9836,
|
|
"mean_token_accuracy": 0.20475348234176635,
|
|
"num_tokens": 35949432.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.455109262466431,
|
|
"epoch": 1.6325593050451053,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047344912214150565,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.21276894062757493,
|
|
"num_tokens": 35958687.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.312507152557373,
|
|
"epoch": 1.632976946207818,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004734350911029586,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.21499143242836,
|
|
"num_tokens": 35967875.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.314566564559937,
|
|
"epoch": 1.6333945873705313,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047342105659056645,
|
|
"loss": 4.7735,
|
|
"mean_token_accuracy": 0.2303321346640587,
|
|
"num_tokens": 35977561.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.3222472190856935,
|
|
"epoch": 1.6338122285332441,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004734070186045749,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.22109345644712447,
|
|
"num_tokens": 35986733.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.32155408859253,
|
|
"epoch": 1.6342298696959572,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004733929771452296,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.22539404183626174,
|
|
"num_tokens": 35995779.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.326879835128784,
|
|
"epoch": 1.6346475108586702,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004733789322127764,
|
|
"loss": 4.8992,
|
|
"mean_token_accuracy": 0.21758927553892135,
|
|
"num_tokens": 36004601.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.253659629821778,
|
|
"epoch": 1.6350651520213833,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004733648838074613,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.22321848720312118,
|
|
"num_tokens": 36014356.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.28508186340332,
|
|
"epoch": 1.6354827931840963,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047335083192953,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.22806667238473893,
|
|
"num_tokens": 36023084.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.3156328201293945,
|
|
"epoch": 1.635900434346809,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004733367765792288,
|
|
"loss": 4.7824,
|
|
"mean_token_accuracy": 0.218247751891613,
|
|
"num_tokens": 36031462.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.293674564361572,
|
|
"epoch": 1.6363180755095224,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047332271775680346,
|
|
"loss": 4.7436,
|
|
"mean_token_accuracy": 0.2238544151186943,
|
|
"num_tokens": 36041107.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.290200185775757,
|
|
"epoch": 1.6367357166722352,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004733086554625004,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.22099656313657762,
|
|
"num_tokens": 36050026.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.278035593032837,
|
|
"epoch": 1.6371533578349482,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004732945896965654,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.21977763772010803,
|
|
"num_tokens": 36058858.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.34081997871399,
|
|
"epoch": 1.6375709989976612,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047328052045924506,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.21436552107334136,
|
|
"num_tokens": 36067995.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.306972694396973,
|
|
"epoch": 1.637988640160374,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004732664477507855,
|
|
"loss": 4.7752,
|
|
"mean_token_accuracy": 0.2263510048389435,
|
|
"num_tokens": 36077425.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.323351192474365,
|
|
"epoch": 1.6384062813230873,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047325237157143314,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.2193070650100708,
|
|
"num_tokens": 36086667.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.3249688148498535,
|
|
"epoch": 1.6388239224858,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047323829192143436,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.23448928892612458,
|
|
"num_tokens": 36095199.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.255830860137939,
|
|
"epoch": 1.6392415636485131,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047322420880103566,
|
|
"loss": 4.7543,
|
|
"mean_token_accuracy": 0.22482917308807374,
|
|
"num_tokens": 36104587.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.375017309188843,
|
|
"epoch": 1.6396592048112262,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004732101222104836,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.22551774829626084,
|
|
"num_tokens": 36114017.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.31274790763855,
|
|
"epoch": 1.6400768459739392,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004731960321500247,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.21762603372335435,
|
|
"num_tokens": 36122301.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.212916517257691,
|
|
"epoch": 1.6404944871366522,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004731819386199058,
|
|
"loss": 4.7935,
|
|
"mean_token_accuracy": 0.22405998557806014,
|
|
"num_tokens": 36131538.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.30731086730957,
|
|
"epoch": 1.640912128299365,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004731678416203734,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.21767142713069915,
|
|
"num_tokens": 36140472.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.338306427001953,
|
|
"epoch": 1.6413297694620783,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047315374115167446,
|
|
"loss": 4.78,
|
|
"mean_token_accuracy": 0.22885144650936126,
|
|
"num_tokens": 36148947.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.2739897727966305,
|
|
"epoch": 1.6417474106247911,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004731396372140558,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.22647954374551774,
|
|
"num_tokens": 36157895.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.2701578617095945,
|
|
"epoch": 1.6421650517875042,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004731255298077642,
|
|
"loss": 4.792,
|
|
"mean_token_accuracy": 0.227848319709301,
|
|
"num_tokens": 36168170.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.3247514247894285,
|
|
"epoch": 1.6425826929502172,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047311141893304675,
|
|
"loss": 4.8606,
|
|
"mean_token_accuracy": 0.21877095103263855,
|
|
"num_tokens": 36176864.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.392218494415284,
|
|
"epoch": 1.64300033411293,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004730973045901505,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.22109489291906356,
|
|
"num_tokens": 36186334.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.337657928466797,
|
|
"epoch": 1.6434179752756433,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047308318677932243,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.2219928339123726,
|
|
"num_tokens": 36194688.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.283237791061401,
|
|
"epoch": 1.643835616438356,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004730690655008097,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.22188614308834076,
|
|
"num_tokens": 36203962.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.375270938873291,
|
|
"epoch": 1.644253257601069,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004730549407548597,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.20881700217723848,
|
|
"num_tokens": 36212780.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.391975212097168,
|
|
"epoch": 1.6446708987637821,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047304081254171944,
|
|
"loss": 4.8406,
|
|
"mean_token_accuracy": 0.2184995025396347,
|
|
"num_tokens": 36221744.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.311130714416504,
|
|
"epoch": 1.6450885399264952,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004730266808616364,
|
|
"loss": 4.8864,
|
|
"mean_token_accuracy": 0.22035675793886184,
|
|
"num_tokens": 36231261.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.290738439559936,
|
|
"epoch": 1.6455061810892082,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000473012545714858,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.22421498745679855,
|
|
"num_tokens": 36240599.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.233507299423218,
|
|
"epoch": 1.645923822251921,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047299840710163157,
|
|
"loss": 4.6944,
|
|
"mean_token_accuracy": 0.23031417578458785,
|
|
"num_tokens": 36249402.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.32169017791748,
|
|
"epoch": 1.6463414634146343,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004729842650222047,
|
|
"loss": 4.7492,
|
|
"mean_token_accuracy": 0.22959329336881637,
|
|
"num_tokens": 36258379.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.276117992401123,
|
|
"epoch": 1.646759104577347,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047297011947682494,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.2270217016339302,
|
|
"num_tokens": 36267393.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.338778972625732,
|
|
"epoch": 1.6471767457400601,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047295597046574,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.22021548300981522,
|
|
"num_tokens": 36277542.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.328020906448364,
|
|
"epoch": 1.6475943869027732,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004729418179891975,
|
|
"loss": 4.8419,
|
|
"mean_token_accuracy": 0.21726250201463698,
|
|
"num_tokens": 36287623.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.252754211425781,
|
|
"epoch": 1.6480120280654862,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004729276620474452,
|
|
"loss": 4.7517,
|
|
"mean_token_accuracy": 0.22593628913164138,
|
|
"num_tokens": 36295828.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.337347745895386,
|
|
"epoch": 1.6484296692281992,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047291350264073095,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.21695781499147415,
|
|
"num_tokens": 36304825.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.340727663040161,
|
|
"epoch": 1.648847310390912,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047289933976930263,
|
|
"loss": 4.8489,
|
|
"mean_token_accuracy": 0.21732732355594636,
|
|
"num_tokens": 36313691.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.314030599594116,
|
|
"epoch": 1.6492649515536253,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004728851734334081,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.2240397721529007,
|
|
"num_tokens": 36323291.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.289039230346679,
|
|
"epoch": 1.649682592716338,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004728710036332954,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.21919687539339067,
|
|
"num_tokens": 36332859.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.323472404479981,
|
|
"epoch": 1.6501002338790511,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047285683036921275,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.22172388583421707,
|
|
"num_tokens": 36342049.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.261015462875366,
|
|
"epoch": 1.6505178750417642,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047284265364140794,
|
|
"loss": 4.7716,
|
|
"mean_token_accuracy": 0.22045544385910035,
|
|
"num_tokens": 36351512.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.342918014526367,
|
|
"epoch": 1.650935516204477,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004728284734501295,
|
|
"loss": 4.8582,
|
|
"mean_token_accuracy": 0.22005145400762557,
|
|
"num_tokens": 36361923.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.338381433486939,
|
|
"epoch": 1.6513531573671902,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004728142897956253,
|
|
"loss": 4.8753,
|
|
"mean_token_accuracy": 0.21627638936042787,
|
|
"num_tokens": 36370543.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.298936796188355,
|
|
"epoch": 1.651770798529903,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000472800102678144,
|
|
"loss": 4.7655,
|
|
"mean_token_accuracy": 0.2323388025164604,
|
|
"num_tokens": 36378465.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.360123634338379,
|
|
"epoch": 1.652188439692616,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047278591209793384,
|
|
"loss": 4.8547,
|
|
"mean_token_accuracy": 0.22160137593746185,
|
|
"num_tokens": 36387540.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.302610445022583,
|
|
"epoch": 1.6526060808553291,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004727717180552431,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.21538260579109192,
|
|
"num_tokens": 36397859.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.266460514068603,
|
|
"epoch": 1.6530237220180422,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047275752055032043,
|
|
"loss": 4.7303,
|
|
"mean_token_accuracy": 0.2319994404911995,
|
|
"num_tokens": 36406955.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.267104434967041,
|
|
"epoch": 1.6534413631807552,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047274331958341434,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.232094869017601,
|
|
"num_tokens": 36415499.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.2621471881866455,
|
|
"epoch": 1.653859004343468,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004727291151547733,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.21631978154182435,
|
|
"num_tokens": 36424348.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.235314989089966,
|
|
"epoch": 1.6542766455061813,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004727149072646463,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.22168879210948944,
|
|
"num_tokens": 36433134.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.204528665542602,
|
|
"epoch": 1.654694286668894,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047270069591328175,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.2328284963965416,
|
|
"num_tokens": 36442300.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.336764526367188,
|
|
"epoch": 1.655111927831607,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047268648110092857,
|
|
"loss": 4.8805,
|
|
"mean_token_accuracy": 0.2102848008275032,
|
|
"num_tokens": 36452265.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.334024906158447,
|
|
"epoch": 1.6555295689943201,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047267226282783555,
|
|
"loss": 4.8279,
|
|
"mean_token_accuracy": 0.22102102190256118,
|
|
"num_tokens": 36462009.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.390382432937622,
|
|
"epoch": 1.655947210157033,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004726580410942516,
|
|
"loss": 4.9291,
|
|
"mean_token_accuracy": 0.2121589943766594,
|
|
"num_tokens": 36470799.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.372810316085816,
|
|
"epoch": 1.6563648513197462,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047264381590042575,
|
|
"loss": 4.8165,
|
|
"mean_token_accuracy": 0.2135423094034195,
|
|
"num_tokens": 36479362.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.293213939666748,
|
|
"epoch": 1.656782492482459,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000472629587246607,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.21837999671697617,
|
|
"num_tokens": 36487773.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.275221824645996,
|
|
"epoch": 1.657200133645172,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047261535513304446,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.2308324545621872,
|
|
"num_tokens": 36496133.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.337469053268433,
|
|
"epoch": 1.657617774807885,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047260111955998725,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.22264433801174163,
|
|
"num_tokens": 36505392.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.342805576324463,
|
|
"epoch": 1.6580354159705981,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047258688052768456,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.2170650154352188,
|
|
"num_tokens": 36514876.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.307733774185181,
|
|
"epoch": 1.6584530571333111,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004725726380363857,
|
|
"loss": 4.7868,
|
|
"mean_token_accuracy": 0.2254001870751381,
|
|
"num_tokens": 36523828.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.3531042575836185,
|
|
"epoch": 1.658870698296024,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047255839208634005,
|
|
"loss": 4.8339,
|
|
"mean_token_accuracy": 0.220554718375206,
|
|
"num_tokens": 36532263.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.259338331222534,
|
|
"epoch": 1.6592883394587372,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047254414267779686,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.22504892945289612,
|
|
"num_tokens": 36541015.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.274966192245484,
|
|
"epoch": 1.65970598062145,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047252988981100576,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.21909792870283126,
|
|
"num_tokens": 36550254.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.32993369102478,
|
|
"epoch": 1.660123621784163,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004725156334862161,
|
|
"loss": 4.8726,
|
|
"mean_token_accuracy": 0.21073147505521775,
|
|
"num_tokens": 36560941.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.36404390335083,
|
|
"epoch": 1.660541262946876,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047250137370367755,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.21329906433820725,
|
|
"num_tokens": 36570443.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.334944725036621,
|
|
"epoch": 1.660958904109589,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047248711046363976,
|
|
"loss": 4.8461,
|
|
"mean_token_accuracy": 0.2160993590950966,
|
|
"num_tokens": 36580532.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.354849863052368,
|
|
"epoch": 1.6613765452723022,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004724728437663523,
|
|
"loss": 4.7982,
|
|
"mean_token_accuracy": 0.22061506062746047,
|
|
"num_tokens": 36589359.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.352704048156738,
|
|
"epoch": 1.661794186435015,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047245857361206506,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.21968763023614885,
|
|
"num_tokens": 36598229.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.262787246704102,
|
|
"epoch": 1.662211827597728,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047244430000102785,
|
|
"loss": 4.7809,
|
|
"mean_token_accuracy": 0.2281879410147667,
|
|
"num_tokens": 36607655.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.330818128585816,
|
|
"epoch": 1.662629468760441,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004724300229334905,
|
|
"loss": 4.8399,
|
|
"mean_token_accuracy": 0.21714794337749482,
|
|
"num_tokens": 36618060.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.324173259735107,
|
|
"epoch": 1.663047109923154,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047241574240970284,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.22307634651660918,
|
|
"num_tokens": 36627825.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.334656810760498,
|
|
"epoch": 1.663464751085867,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047240145842991513,
|
|
"loss": 4.7828,
|
|
"mean_token_accuracy": 0.22728732228279114,
|
|
"num_tokens": 36635971.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.245095300674438,
|
|
"epoch": 1.66388239224858,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047238717099437713,
|
|
"loss": 4.661,
|
|
"mean_token_accuracy": 0.2289886236190796,
|
|
"num_tokens": 36644340.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.29542727470398,
|
|
"epoch": 1.6643000334112932,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004723728801033392,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.2148413449525833,
|
|
"num_tokens": 36654371.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.244128179550171,
|
|
"epoch": 1.664717674574006,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004723585857570514,
|
|
"loss": 4.6852,
|
|
"mean_token_accuracy": 0.23645139634609222,
|
|
"num_tokens": 36663633.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.2548112869262695,
|
|
"epoch": 1.665135315736719,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000472344287955764,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.2328132137656212,
|
|
"num_tokens": 36673004.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.266137886047363,
|
|
"epoch": 1.665552956899432,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004723299866997273,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.23558776080608368,
|
|
"num_tokens": 36681323.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.361350107192993,
|
|
"epoch": 1.6659705980621449,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004723156819891917,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.20901050120592118,
|
|
"num_tokens": 36691128.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.279838943481446,
|
|
"epoch": 1.6663882392248581,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047230137382440747,
|
|
"loss": 4.7702,
|
|
"mean_token_accuracy": 0.22642129063606262,
|
|
"num_tokens": 36699759.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.25895586013794,
|
|
"epoch": 1.666805880387571,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004722870622056253,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.21926873475313186,
|
|
"num_tokens": 36708723.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.296369171142578,
|
|
"epoch": 1.667223521550284,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004722727471330956,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.22196488380432128,
|
|
"num_tokens": 36717488.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.230769157409668,
|
|
"epoch": 1.667641162712997,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000472258428607069,
|
|
"loss": 4.7508,
|
|
"mean_token_accuracy": 0.22414047569036483,
|
|
"num_tokens": 36726477.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.305932188034058,
|
|
"epoch": 1.66805880387571,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004722441066277961,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.22388747036457063,
|
|
"num_tokens": 36734676.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.325007438659668,
|
|
"epoch": 1.668476445038423,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047222978119552776,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.21687454730272293,
|
|
"num_tokens": 36744425.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.318854665756225,
|
|
"epoch": 1.6688940862011359,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047221545231051473,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.21891506016254425,
|
|
"num_tokens": 36754113.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.318398523330688,
|
|
"epoch": 1.6693117273638491,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004722011199730078,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.22408352196216583,
|
|
"num_tokens": 36763013.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.309564208984375,
|
|
"epoch": 1.669729368526562,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004721867841832579,
|
|
"loss": 4.8308,
|
|
"mean_token_accuracy": 0.22068686038255692,
|
|
"num_tokens": 36772115.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.3476416110992435,
|
|
"epoch": 1.670147009689275,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004721724449415159,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.213739837706089,
|
|
"num_tokens": 36781210.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.383375215530395,
|
|
"epoch": 1.670564650851988,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047215810224803304,
|
|
"loss": 4.8969,
|
|
"mean_token_accuracy": 0.21522207409143448,
|
|
"num_tokens": 36791131.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.263435697555542,
|
|
"epoch": 1.6709822920147008,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047214375610306016,
|
|
"loss": 4.6879,
|
|
"mean_token_accuracy": 0.23323297500610352,
|
|
"num_tokens": 36800618.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.309667301177979,
|
|
"epoch": 1.671399933177414,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047212940650684853,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.21674975603818894,
|
|
"num_tokens": 36809995.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.351333141326904,
|
|
"epoch": 1.671817574340127,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004721150534596495,
|
|
"loss": 4.8511,
|
|
"mean_token_accuracy": 0.21525840908288957,
|
|
"num_tokens": 36818492.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.351598167419434,
|
|
"epoch": 1.67223521550284,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000472100696961714,
|
|
"loss": 4.7938,
|
|
"mean_token_accuracy": 0.22239320874214172,
|
|
"num_tokens": 36827280.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.322577810287475,
|
|
"epoch": 1.672652856665553,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004720863370132937,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.21772578060626985,
|
|
"num_tokens": 36837931.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.3165021419525145,
|
|
"epoch": 1.673070497828266,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004720719736146398,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.21873608082532883,
|
|
"num_tokens": 36847581.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.309367656707764,
|
|
"epoch": 1.673488138990979,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047205760676600377,
|
|
"loss": 4.8005,
|
|
"mean_token_accuracy": 0.21929929554462432,
|
|
"num_tokens": 36857147.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.297761249542236,
|
|
"epoch": 1.6739057801536918,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004720432364676372,
|
|
"loss": 4.7869,
|
|
"mean_token_accuracy": 0.21593542248010636,
|
|
"num_tokens": 36866105.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.332561492919922,
|
|
"epoch": 1.674323421316405,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004720288627197915,
|
|
"loss": 4.7566,
|
|
"mean_token_accuracy": 0.22922542691230774,
|
|
"num_tokens": 36874631.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.263610315322876,
|
|
"epoch": 1.674741062479118,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004720144855227185,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.22919837683439254,
|
|
"num_tokens": 36884264.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.3429868698120115,
|
|
"epoch": 1.675158703641831,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004720001048766696,
|
|
"loss": 4.8248,
|
|
"mean_token_accuracy": 0.22116896361112595,
|
|
"num_tokens": 36893143.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.403996324539184,
|
|
"epoch": 1.675576344804544,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004719857207818969,
|
|
"loss": 4.8811,
|
|
"mean_token_accuracy": 0.21527831107378007,
|
|
"num_tokens": 36903026.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.412864065170288,
|
|
"epoch": 1.6759939859672568,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000471971333238652,
|
|
"loss": 4.9098,
|
|
"mean_token_accuracy": 0.21226051151752473,
|
|
"num_tokens": 36912737.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.400354242324829,
|
|
"epoch": 1.67641162712997,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047195694224718684,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.21798593699932098,
|
|
"num_tokens": 36921148.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.270614862442017,
|
|
"epoch": 1.6768292682926829,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047194254780775325,
|
|
"loss": 4.7035,
|
|
"mean_token_accuracy": 0.22765845209360122,
|
|
"num_tokens": 36930043.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.346696758270264,
|
|
"epoch": 1.677246909455396,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004719281499206034,
|
|
"loss": 4.8827,
|
|
"mean_token_accuracy": 0.21722278594970704,
|
|
"num_tokens": 36939124.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.421319580078125,
|
|
"epoch": 1.677664550618109,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047191374858598917,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.21545729786157608,
|
|
"num_tokens": 36948392.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.336479759216308,
|
|
"epoch": 1.678082191780822,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004718993438041628,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.2211568087339401,
|
|
"num_tokens": 36958019.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.329202556610108,
|
|
"epoch": 1.678499832943535,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047188493557537634,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.21575307250022888,
|
|
"num_tokens": 36966904.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.405393362045288,
|
|
"epoch": 1.6789174741062478,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004718705238998822,
|
|
"loss": 4.8532,
|
|
"mean_token_accuracy": 0.2202060267329216,
|
|
"num_tokens": 36976085.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.330231332778931,
|
|
"epoch": 1.679335115268961,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047185610877793245,
|
|
"loss": 4.7609,
|
|
"mean_token_accuracy": 0.2321527421474457,
|
|
"num_tokens": 36984345.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.273635053634644,
|
|
"epoch": 1.6797527564316739,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047184169020977965,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.2223561942577362,
|
|
"num_tokens": 36993133.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.306164312362671,
|
|
"epoch": 1.680170397594387,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047182726819567603,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.2200317934155464,
|
|
"num_tokens": 37002797.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.3615052700042725,
|
|
"epoch": 1.6805880387571,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047181284273587414,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.21827228963375092,
|
|
"num_tokens": 37012598.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.341164779663086,
|
|
"epoch": 1.6810056799198128,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047179841383062667,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.2302229419350624,
|
|
"num_tokens": 37022006.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.244860315322876,
|
|
"epoch": 1.681423321082526,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047178398148018606,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.22411924600601196,
|
|
"num_tokens": 37030713.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.274004888534546,
|
|
"epoch": 1.6818409622452388,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004717695456848049,
|
|
"loss": 4.7868,
|
|
"mean_token_accuracy": 0.22858939319849014,
|
|
"num_tokens": 37039347.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.383195590972901,
|
|
"epoch": 1.6822586034079519,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004717551064447361,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.21748354882001877,
|
|
"num_tokens": 37048010.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.245626401901245,
|
|
"epoch": 1.682676244570665,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004717406637602322,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.22489766925573348,
|
|
"num_tokens": 37056517.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.283848428726197,
|
|
"epoch": 1.683093885733378,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004717262176315462,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.21081955283880233,
|
|
"num_tokens": 37065085.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.293072462081909,
|
|
"epoch": 1.683511526896091,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000471711768058931,
|
|
"loss": 4.7528,
|
|
"mean_token_accuracy": 0.22447400093078612,
|
|
"num_tokens": 37074483.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.343703126907348,
|
|
"epoch": 1.6839291680588038,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004716973150426395,
|
|
"loss": 4.8466,
|
|
"mean_token_accuracy": 0.21719519495964051,
|
|
"num_tokens": 37083679.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.279517555236817,
|
|
"epoch": 1.684346809221517,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047168285858292477,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.22486519813537598,
|
|
"num_tokens": 37092258.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.329337930679321,
|
|
"epoch": 1.6847644503842298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047166839868003984,
|
|
"loss": 4.8793,
|
|
"mean_token_accuracy": 0.21599022150039673,
|
|
"num_tokens": 37101100.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.423484659194946,
|
|
"epoch": 1.6851820915469429,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047165393533423784,
|
|
"loss": 4.9138,
|
|
"mean_token_accuracy": 0.2143512025475502,
|
|
"num_tokens": 37110876.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.38759479522705,
|
|
"epoch": 1.685599732709656,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047163946854577194,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.22543130666017533,
|
|
"num_tokens": 37119770.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.284207153320312,
|
|
"epoch": 1.6860173738723687,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004716249983148955,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.22171466201543807,
|
|
"num_tokens": 37129173.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.2516473770141605,
|
|
"epoch": 1.686435015035082,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004716105246418618,
|
|
"loss": 4.746,
|
|
"mean_token_accuracy": 0.2264491304755211,
|
|
"num_tokens": 37138229.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.414290142059326,
|
|
"epoch": 1.6868526561977948,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004715960475269242,
|
|
"loss": 4.8913,
|
|
"mean_token_accuracy": 0.2164781302213669,
|
|
"num_tokens": 37147792.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.37946572303772,
|
|
"epoch": 1.6872702973605078,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004715815669703362,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.22427967935800552,
|
|
"num_tokens": 37156729.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.266779804229737,
|
|
"epoch": 1.6876879385232209,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047156708297235115,
|
|
"loss": 4.7986,
|
|
"mean_token_accuracy": 0.2213491603732109,
|
|
"num_tokens": 37165678.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.443931293487549,
|
|
"epoch": 1.6881055796859339,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004715525955332227,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.2146009996533394,
|
|
"num_tokens": 37174704.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.387531757354736,
|
|
"epoch": 1.688523220848647,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004715381046532046,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.21894580870866776,
|
|
"num_tokens": 37184548.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.292281770706177,
|
|
"epoch": 1.6889408620113597,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004715236103325503,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.21689402610063552,
|
|
"num_tokens": 37193668.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.264764213562012,
|
|
"epoch": 1.689358503174073,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047150911257151364,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.22046050429344177,
|
|
"num_tokens": 37202504.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.330307912826538,
|
|
"epoch": 1.6897761443367858,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004714946113703484,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.22900796830654144,
|
|
"num_tokens": 37212140.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.379762744903564,
|
|
"epoch": 1.6901937854994988,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004714801067293086,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.22130921185016633,
|
|
"num_tokens": 37221824.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.402457666397095,
|
|
"epoch": 1.6906114266622119,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047146559864864787,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.2221470981836319,
|
|
"num_tokens": 37231877.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.370903158187867,
|
|
"epoch": 1.6910290678249247,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047145108712862046,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.21625228971242905,
|
|
"num_tokens": 37240601.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.25229811668396,
|
|
"epoch": 1.691446708987638,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004714365721694803,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.22067857086658477,
|
|
"num_tokens": 37249645.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.335933971405029,
|
|
"epoch": 1.6918643501503507,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047142205377148145,
|
|
"loss": 4.7771,
|
|
"mean_token_accuracy": 0.22434858083724976,
|
|
"num_tokens": 37258170.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.299120903015137,
|
|
"epoch": 1.6922819913130638,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004714075319348781,
|
|
"loss": 4.8515,
|
|
"mean_token_accuracy": 0.21936890482902527,
|
|
"num_tokens": 37268045.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.327237701416015,
|
|
"epoch": 1.6926996324757768,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004713930066599246,
|
|
"loss": 4.8211,
|
|
"mean_token_accuracy": 0.22331664264202117,
|
|
"num_tokens": 37278558.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.314020347595215,
|
|
"epoch": 1.6931172736384899,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000471378477946875,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.22946884483098984,
|
|
"num_tokens": 37287119.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.329233837127686,
|
|
"epoch": 1.6935349148012029,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004713639457959838,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.216761577129364,
|
|
"num_tokens": 37296300.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.31353006362915,
|
|
"epoch": 1.6939525559639157,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004713494102075053,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.2246891215443611,
|
|
"num_tokens": 37305291.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.352481842041016,
|
|
"epoch": 1.694370197126629,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004713348711816942,
|
|
"loss": 4.7867,
|
|
"mean_token_accuracy": 0.22277884185314178,
|
|
"num_tokens": 37314441.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.339292812347412,
|
|
"epoch": 1.6947878382893418,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004713203287188047,
|
|
"loss": 4.8597,
|
|
"mean_token_accuracy": 0.22026642113924028,
|
|
"num_tokens": 37323516.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.339022827148438,
|
|
"epoch": 1.6952054794520548,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004713057828190916,
|
|
"loss": 4.7903,
|
|
"mean_token_accuracy": 0.2266659066081047,
|
|
"num_tokens": 37332651.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.354852533340454,
|
|
"epoch": 1.6956231206147678,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004712912334828094,
|
|
"loss": 4.8279,
|
|
"mean_token_accuracy": 0.21998680979013444,
|
|
"num_tokens": 37341580.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.4217140674591064,
|
|
"epoch": 1.6960407617774806,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047127668071021293,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.21479506641626359,
|
|
"num_tokens": 37351385.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.256928443908691,
|
|
"epoch": 1.696458402940194,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000471262124501557,
|
|
"loss": 4.6308,
|
|
"mean_token_accuracy": 0.2366157203912735,
|
|
"num_tokens": 37360893.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.319115447998047,
|
|
"epoch": 1.6968760441029067,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004712475648570962,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.22149871289730072,
|
|
"num_tokens": 37370301.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.306957197189331,
|
|
"epoch": 1.6972936852656197,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047123300177708563,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.2126660406589508,
|
|
"num_tokens": 37380881.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.274965381622314,
|
|
"epoch": 1.6977113264283328,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004712184352617801,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.2302049607038498,
|
|
"num_tokens": 37390167.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.4205175876617435,
|
|
"epoch": 1.6981289675910458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047120386531143476,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.2107751578092575,
|
|
"num_tokens": 37399163.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.414246082305908,
|
|
"epoch": 1.6985466087537588,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047118929192630453,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.2187577873468399,
|
|
"num_tokens": 37409047.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.364208078384399,
|
|
"epoch": 1.6989642499164717,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004711747151066446,
|
|
"loss": 4.7434,
|
|
"mean_token_accuracy": 0.22236093282699584,
|
|
"num_tokens": 37417936.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.224995183944702,
|
|
"epoch": 1.699381891079185,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047116013485271014,
|
|
"loss": 4.6642,
|
|
"mean_token_accuracy": 0.23245866000652313,
|
|
"num_tokens": 37426453.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.203199434280395,
|
|
"epoch": 1.6997995322418977,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004711455511647564,
|
|
"loss": 4.6341,
|
|
"mean_token_accuracy": 0.24415243566036224,
|
|
"num_tokens": 37435353.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.295854377746582,
|
|
"epoch": 1.7002171734046108,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047113096404303875,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.22236671000719072,
|
|
"num_tokens": 37444895.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.336739826202392,
|
|
"epoch": 1.7006348145673238,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004711163734878124,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.22311711460351943,
|
|
"num_tokens": 37454038.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.335724878311157,
|
|
"epoch": 1.7010524557300366,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004711017794993329,
|
|
"loss": 4.8139,
|
|
"mean_token_accuracy": 0.22338966578245162,
|
|
"num_tokens": 37463316.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.317788887023926,
|
|
"epoch": 1.7014700968927499,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047108718207785575,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.21813590228557586,
|
|
"num_tokens": 37473341.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.378574562072754,
|
|
"epoch": 1.7018877380554627,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004710725812236364,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.2225906178355217,
|
|
"num_tokens": 37482601.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.316276884078979,
|
|
"epoch": 1.7023053792181757,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004710579769369305,
|
|
"loss": 4.7529,
|
|
"mean_token_accuracy": 0.22469588220119477,
|
|
"num_tokens": 37491304.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.238398647308349,
|
|
"epoch": 1.7027230203808887,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004710433692179937,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.2248423457145691,
|
|
"num_tokens": 37500848.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.321542263031006,
|
|
"epoch": 1.7031406615436018,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004710287580670818,
|
|
"loss": 4.7008,
|
|
"mean_token_accuracy": 0.23383727073669433,
|
|
"num_tokens": 37509649.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.321341419219971,
|
|
"epoch": 1.7035583027063148,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047101414348445046,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.21701617538928986,
|
|
"num_tokens": 37519207.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.379060697555542,
|
|
"epoch": 1.7039759438690276,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047099952547035564,
|
|
"loss": 4.8641,
|
|
"mean_token_accuracy": 0.21243547201156615,
|
|
"num_tokens": 37528819.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.333892822265625,
|
|
"epoch": 1.7043935850317409,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004709849040250532,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.21946843415498735,
|
|
"num_tokens": 37538439.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.2835588455200195,
|
|
"epoch": 1.7048112261944537,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004709702791487991,
|
|
"loss": 4.7584,
|
|
"mean_token_accuracy": 0.22623568624258042,
|
|
"num_tokens": 37547758.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.314676237106323,
|
|
"epoch": 1.7052288673571667,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004709556508418494,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.22568043321371078,
|
|
"num_tokens": 37556693.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.330879497528076,
|
|
"epoch": 1.7056465085198798,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004709410191044601,
|
|
"loss": 4.863,
|
|
"mean_token_accuracy": 0.2200504571199417,
|
|
"num_tokens": 37564631.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.279616355895996,
|
|
"epoch": 1.7060641496825926,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004709263839368875,
|
|
"loss": 4.7083,
|
|
"mean_token_accuracy": 0.23047614395618438,
|
|
"num_tokens": 37573687.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.2731208324432375,
|
|
"epoch": 1.7064817908453058,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004709117453393876,
|
|
"loss": 4.7872,
|
|
"mean_token_accuracy": 0.22193126678466796,
|
|
"num_tokens": 37582652.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.238777208328247,
|
|
"epoch": 1.7068994320080186,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047089710331221687,
|
|
"loss": 4.6697,
|
|
"mean_token_accuracy": 0.23194426596164702,
|
|
"num_tokens": 37591242.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.403275203704834,
|
|
"epoch": 1.7073170731707317,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004708824578556315,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.2165134608745575,
|
|
"num_tokens": 37601527.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.393480443954468,
|
|
"epoch": 1.7077347143334447,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047086780896988796,
|
|
"loss": 4.8696,
|
|
"mean_token_accuracy": 0.2174868881702423,
|
|
"num_tokens": 37611100.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.343603420257568,
|
|
"epoch": 1.7081523554961577,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047085315665524257,
|
|
"loss": 4.7977,
|
|
"mean_token_accuracy": 0.22523289173841476,
|
|
"num_tokens": 37619386.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.353380012512207,
|
|
"epoch": 1.7085699966588708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000470838500911952,
|
|
"loss": 4.9058,
|
|
"mean_token_accuracy": 0.21741333305835725,
|
|
"num_tokens": 37628695.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.344249677658081,
|
|
"epoch": 1.7089876378215836,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004708238417402728,
|
|
"loss": 4.8252,
|
|
"mean_token_accuracy": 0.21592822670936584,
|
|
"num_tokens": 37637588.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.305620098114014,
|
|
"epoch": 1.7094052789842968,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047080917914046146,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.229872165620327,
|
|
"num_tokens": 37646114.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.3726612567901615,
|
|
"epoch": 1.7098229201470097,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047079451311277473,
|
|
"loss": 4.9311,
|
|
"mean_token_accuracy": 0.21349362283945084,
|
|
"num_tokens": 37654987.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.313350629806519,
|
|
"epoch": 1.7102405613097227,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004707798436574694,
|
|
"loss": 4.8154,
|
|
"mean_token_accuracy": 0.22258330285549163,
|
|
"num_tokens": 37664715.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.412056159973145,
|
|
"epoch": 1.7106582024724357,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047076517077480223,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.2208339586853981,
|
|
"num_tokens": 37675016.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.390104150772094,
|
|
"epoch": 1.7110758436351485,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004707504944650301,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.22090758085250856,
|
|
"num_tokens": 37683577.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.386032295227051,
|
|
"epoch": 1.7114934847978618,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047073581472840997,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.2127793863415718,
|
|
"num_tokens": 37692681.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.2503523349761965,
|
|
"epoch": 1.7119111259605746,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004707211315651988,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.2247542679309845,
|
|
"num_tokens": 37701698.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.292678308486939,
|
|
"epoch": 1.7123287671232876,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004707064449756536,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.21894725114107133,
|
|
"num_tokens": 37710450.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.325639152526856,
|
|
"epoch": 1.7127464082860007,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047069175496003147,
|
|
"loss": 4.8428,
|
|
"mean_token_accuracy": 0.21845187544822692,
|
|
"num_tokens": 37719201.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.445720577239991,
|
|
"epoch": 1.7131640494487137,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047067706151858967,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.22229698151350022,
|
|
"num_tokens": 37728671.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.3170473098754885,
|
|
"epoch": 1.7135816906114267,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004706623646515854,
|
|
"loss": 4.7618,
|
|
"mean_token_accuracy": 0.22723004966974258,
|
|
"num_tokens": 37737675.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.284847450256348,
|
|
"epoch": 1.7139993317741395,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047064766435927585,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.23101284950971604,
|
|
"num_tokens": 37746299.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.312711238861084,
|
|
"epoch": 1.7144169729368528,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047063296064191846,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.22507266253232955,
|
|
"num_tokens": 37755770.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.291530704498291,
|
|
"epoch": 1.7148346140995656,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047061825349977067,
|
|
"loss": 4.7981,
|
|
"mean_token_accuracy": 0.22180721312761306,
|
|
"num_tokens": 37765217.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.329059505462647,
|
|
"epoch": 1.7152522552622786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047060354293308976,
|
|
"loss": 4.7929,
|
|
"mean_token_accuracy": 0.23029616177082063,
|
|
"num_tokens": 37773891.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.284931182861328,
|
|
"epoch": 1.7156698964249917,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004705888289421335,
|
|
"loss": 4.8032,
|
|
"mean_token_accuracy": 0.22479795068502426,
|
|
"num_tokens": 37783323.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.391673183441162,
|
|
"epoch": 1.7160875375877045,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004705741115271593,
|
|
"loss": 4.8812,
|
|
"mean_token_accuracy": 0.2163634940981865,
|
|
"num_tokens": 37792436.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.320860576629639,
|
|
"epoch": 1.7165051787504177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004705593906884249,
|
|
"loss": 4.7736,
|
|
"mean_token_accuracy": 0.22282131761312485,
|
|
"num_tokens": 37802061.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.279473066329956,
|
|
"epoch": 1.7169228199131306,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047054466642618793,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.22736941128969193,
|
|
"num_tokens": 37811101.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.40201621055603,
|
|
"epoch": 1.7173404610758436,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047052993874070623,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.2235434025526047,
|
|
"num_tokens": 37820783.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.2861566066741945,
|
|
"epoch": 1.7177581022385566,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047051520763223754,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.22257934361696244,
|
|
"num_tokens": 37830075.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.2272443771362305,
|
|
"epoch": 1.7181757434012697,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047050047310103984,
|
|
"loss": 4.6857,
|
|
"mean_token_accuracy": 0.21929918378591537,
|
|
"num_tokens": 37838344.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.278378677368164,
|
|
"epoch": 1.7185933845639827,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047048573514737107,
|
|
"loss": 4.8032,
|
|
"mean_token_accuracy": 0.21604762524366378,
|
|
"num_tokens": 37847911.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.229360961914063,
|
|
"epoch": 1.7190110257266955,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047047099377148916,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.22533111721277238,
|
|
"num_tokens": 37857044.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.347934198379517,
|
|
"epoch": 1.7194286668894088,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004704562489736522,
|
|
"loss": 4.8053,
|
|
"mean_token_accuracy": 0.22954366505146026,
|
|
"num_tokens": 37865912.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.36924467086792,
|
|
"epoch": 1.7198463080521216,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004704415007541184,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.21834063082933425,
|
|
"num_tokens": 37875118.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.3245550155639645,
|
|
"epoch": 1.7202639492148346,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004704267491131458,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.22813383787870406,
|
|
"num_tokens": 37882891.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.296833419799805,
|
|
"epoch": 1.7206815903775476,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047041199405099273,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.2279655873775482,
|
|
"num_tokens": 37892274.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.227290248870849,
|
|
"epoch": 1.7210992315402605,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047039723556791744,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.23055737614631652,
|
|
"num_tokens": 37901061.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.2579026222229,
|
|
"epoch": 1.7215168727029737,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004703824736641785,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.23197514712810516,
|
|
"num_tokens": 37910253.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.302337741851806,
|
|
"epoch": 1.7219345138656865,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047036770834003405,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.22330283373594284,
|
|
"num_tokens": 37919453.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.243164920806885,
|
|
"epoch": 1.7223521550283996,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047035293959574273,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.23179217129945756,
|
|
"num_tokens": 37928462.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.325083923339844,
|
|
"epoch": 1.7227697961911126,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000470338167431563,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.22991938143968582,
|
|
"num_tokens": 37938631.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.357080030441284,
|
|
"epoch": 1.7231874373538256,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047032339184775366,
|
|
"loss": 4.8386,
|
|
"mean_token_accuracy": 0.21325672119855882,
|
|
"num_tokens": 37948490.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.197709846496582,
|
|
"epoch": 1.7236050785165387,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004703086128445731,
|
|
"loss": 4.6697,
|
|
"mean_token_accuracy": 0.23423713445663452,
|
|
"num_tokens": 37957861.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.242756319046021,
|
|
"epoch": 1.7240227196792515,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004702938304222803,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.22331817150115968,
|
|
"num_tokens": 37966587.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.284842777252197,
|
|
"epoch": 1.7244403608419647,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047027904458113386,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.21981953233480453,
|
|
"num_tokens": 37976295.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.463349199295044,
|
|
"epoch": 1.7248580020046775,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004702642553213927,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.20805847346782685,
|
|
"num_tokens": 37985525.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.406437253952026,
|
|
"epoch": 1.7252756431673906,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047024946264331564,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.2196572855114937,
|
|
"num_tokens": 37995656.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.331912708282471,
|
|
"epoch": 1.7256932843301036,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004702346665471618,
|
|
"loss": 4.8086,
|
|
"mean_token_accuracy": 0.22105959802865982,
|
|
"num_tokens": 38004790.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.406558561325073,
|
|
"epoch": 1.7261109254928164,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004702198670331901,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.21216520816087722,
|
|
"num_tokens": 38014244.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.288125228881836,
|
|
"epoch": 1.7265285666555297,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047020506410165965,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.23272543251514435,
|
|
"num_tokens": 38023756.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.310487699508667,
|
|
"epoch": 1.7269462078182425,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047019025775282955,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.22951357513666154,
|
|
"num_tokens": 38033402.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.3123914241790775,
|
|
"epoch": 1.7273638489809555,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000470175447986959,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.2164572909474373,
|
|
"num_tokens": 38042580.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.307598209381103,
|
|
"epoch": 1.7277814901436686,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004701606348043074,
|
|
"loss": 4.8705,
|
|
"mean_token_accuracy": 0.21688802987337114,
|
|
"num_tokens": 38051809.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.290947532653808,
|
|
"epoch": 1.7281991313063816,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004701458182051339,
|
|
"loss": 4.6894,
|
|
"mean_token_accuracy": 0.227748104929924,
|
|
"num_tokens": 38061053.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.29095983505249,
|
|
"epoch": 1.7286167724690946,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047013099818969797,
|
|
"loss": 4.7007,
|
|
"mean_token_accuracy": 0.22023290097713472,
|
|
"num_tokens": 38070190.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.276626682281494,
|
|
"epoch": 1.7290344136318074,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000470116174758259,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.21546647250652312,
|
|
"num_tokens": 38078049.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.376038217544556,
|
|
"epoch": 1.7294520547945207,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047010134791107663,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.22271060198545456,
|
|
"num_tokens": 38089130.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.358403587341309,
|
|
"epoch": 1.7298696959572335,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047008651764841034,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.22381841242313386,
|
|
"num_tokens": 38098484.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.324266529083252,
|
|
"epoch": 1.7302873371199465,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047007168397051956,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.22438666373491287,
|
|
"num_tokens": 38107982.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.312969493865967,
|
|
"epoch": 1.7307049782826596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047005684687766424,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.2260453999042511,
|
|
"num_tokens": 38116816.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.315784168243408,
|
|
"epoch": 1.7311226194453724,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004700420063701041,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.2312250867486,
|
|
"num_tokens": 38125752.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.3163703918457035,
|
|
"epoch": 1.7315402606080856,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004700271624480988,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.22267657220363618,
|
|
"num_tokens": 38135192.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.336136960983277,
|
|
"epoch": 1.7319579017707984,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047001231511190826,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.21208157241344452,
|
|
"num_tokens": 38144730.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.263150262832641,
|
|
"epoch": 1.7323755429335115,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004699974643617924,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.22583715319633485,
|
|
"num_tokens": 38153319.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.313226652145386,
|
|
"epoch": 1.7327931840962245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004699826101980112,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.2314824029803276,
|
|
"num_tokens": 38162067.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.377767086029053,
|
|
"epoch": 1.7332108252589375,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004699677526208248,
|
|
"loss": 4.904,
|
|
"mean_token_accuracy": 0.21598961353302001,
|
|
"num_tokens": 38170901.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.275607538223267,
|
|
"epoch": 1.7336284664216506,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046995289163049317,
|
|
"loss": 4.8031,
|
|
"mean_token_accuracy": 0.22046089321374893,
|
|
"num_tokens": 38179815.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.3333367824554445,
|
|
"epoch": 1.7340461075843634,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046993802722727646,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.21961943954229354,
|
|
"num_tokens": 38188816.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.324887466430664,
|
|
"epoch": 1.7344637487470767,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004699231594114349,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.22144197523593903,
|
|
"num_tokens": 38198447.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.392301034927368,
|
|
"epoch": 1.7348813899097895,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004699082881832289,
|
|
"loss": 4.8534,
|
|
"mean_token_accuracy": 0.21616208404302598,
|
|
"num_tokens": 38207075.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.3588972091674805,
|
|
"epoch": 1.7352990310725025,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046989341354291864,
|
|
"loss": 4.8446,
|
|
"mean_token_accuracy": 0.21544157862663268,
|
|
"num_tokens": 38216297.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.43871488571167,
|
|
"epoch": 1.7357166722352155,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004698785354907646,
|
|
"loss": 4.9685,
|
|
"mean_token_accuracy": 0.21354762017726897,
|
|
"num_tokens": 38225581.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.284009170532227,
|
|
"epoch": 1.7361343133979283,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004698636540270272,
|
|
"loss": 4.6593,
|
|
"mean_token_accuracy": 0.2324053794145584,
|
|
"num_tokens": 38234214.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.366745948791504,
|
|
"epoch": 1.7365519545606416,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004698487691519671,
|
|
"loss": 4.882,
|
|
"mean_token_accuracy": 0.21011290401220323,
|
|
"num_tokens": 38243859.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.348295068740844,
|
|
"epoch": 1.7369695957233544,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046983388086584463,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.2232753962278366,
|
|
"num_tokens": 38252667.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.207035160064697,
|
|
"epoch": 1.7373872368860674,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046981898916892054,
|
|
"loss": 4.6627,
|
|
"mean_token_accuracy": 0.22918970584869386,
|
|
"num_tokens": 38262216.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.312411546707153,
|
|
"epoch": 1.7378048780487805,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046980409406145555,
|
|
"loss": 4.8321,
|
|
"mean_token_accuracy": 0.22011353820562363,
|
|
"num_tokens": 38271672.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.239129686355591,
|
|
"epoch": 1.7382225192114935,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004697891955437105,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.2376766860485077,
|
|
"num_tokens": 38279907.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.30033507347107,
|
|
"epoch": 1.7386401603742065,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046977429361594596,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.23345008939504625,
|
|
"num_tokens": 38289099.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.282172679901123,
|
|
"epoch": 1.7390578015369194,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004697593882784231,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.2268650397658348,
|
|
"num_tokens": 38297754.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.352563190460205,
|
|
"epoch": 1.7394754426996326,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004697444795314027,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.22400525957345963,
|
|
"num_tokens": 38306429.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.360517883300782,
|
|
"epoch": 1.7398930838623454,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046972956737514573,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.21713157445192338,
|
|
"num_tokens": 38315505.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.317596292495727,
|
|
"epoch": 1.7403107250250585,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004697146518099133,
|
|
"loss": 4.8321,
|
|
"mean_token_accuracy": 0.2268203005194664,
|
|
"num_tokens": 38324439.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.338328075408936,
|
|
"epoch": 1.7407283661877715,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046969973283596657,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.2227073699235916,
|
|
"num_tokens": 38334145.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.314554691314697,
|
|
"epoch": 1.7411460073504843,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046968481045356656,
|
|
"loss": 4.7858,
|
|
"mean_token_accuracy": 0.22514547854661943,
|
|
"num_tokens": 38342811.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.271277332305909,
|
|
"epoch": 1.7415636485131976,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046966988466297464,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.22476049214601518,
|
|
"num_tokens": 38351072.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.315904235839843,
|
|
"epoch": 1.7419812896759104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046965495546445204,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.22594171315431594,
|
|
"num_tokens": 38360127.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.277794075012207,
|
|
"epoch": 1.7423989308386234,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046964002285826016,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.2200179800391197,
|
|
"num_tokens": 38368270.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.280609798431397,
|
|
"epoch": 1.7428165720013364,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004696250868446604,
|
|
"loss": 4.8396,
|
|
"mean_token_accuracy": 0.20939528644084932,
|
|
"num_tokens": 38376970.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.325243711471558,
|
|
"epoch": 1.7432342131640495,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046961014742391425,
|
|
"loss": 4.8539,
|
|
"mean_token_accuracy": 0.2221640020608902,
|
|
"num_tokens": 38387103.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.430210590362549,
|
|
"epoch": 1.7436518543267625,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046959520459628317,
|
|
"loss": 4.8169,
|
|
"mean_token_accuracy": 0.22235339134931564,
|
|
"num_tokens": 38395890.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.3862488746643065,
|
|
"epoch": 1.7440694954894753,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046958025836202886,
|
|
"loss": 4.8697,
|
|
"mean_token_accuracy": 0.21418158262968062,
|
|
"num_tokens": 38405868.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.327033424377442,
|
|
"epoch": 1.7444871366521886,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004695653087214128,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.21139095723628998,
|
|
"num_tokens": 38414854.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.266204118728638,
|
|
"epoch": 1.7449047778149014,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046955035567469695,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.22628467828035354,
|
|
"num_tokens": 38424158.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.3534932136535645,
|
|
"epoch": 1.7453224189776144,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046953539922214285,
|
|
"loss": 4.7981,
|
|
"mean_token_accuracy": 0.22273881137371063,
|
|
"num_tokens": 38433200.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.361927270889282,
|
|
"epoch": 1.7457400601403275,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004695204393640125,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.21383618414402009,
|
|
"num_tokens": 38442183.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.318702983856201,
|
|
"epoch": 1.7461577013030403,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046950547610056766,
|
|
"loss": 4.7413,
|
|
"mean_token_accuracy": 0.22116733342409134,
|
|
"num_tokens": 38451451.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.3361132621765135,
|
|
"epoch": 1.7465753424657535,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004694905094320703,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.22317564040422438,
|
|
"num_tokens": 38460043.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.280284786224366,
|
|
"epoch": 1.7469929836284663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046947553935878253,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.2210101753473282,
|
|
"num_tokens": 38470714.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.331559896469116,
|
|
"epoch": 1.7474106247911794,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004694605658809663,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.22515056729316713,
|
|
"num_tokens": 38480528.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.273655414581299,
|
|
"epoch": 1.7478282659538924,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004694455889988838,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.21817109733819962,
|
|
"num_tokens": 38490101.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.3743730068206785,
|
|
"epoch": 1.7482459071166054,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046943060871279725,
|
|
"loss": 4.9002,
|
|
"mean_token_accuracy": 0.2194093644618988,
|
|
"num_tokens": 38498624.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.3413561344146725,
|
|
"epoch": 1.7486635482793185,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046941562502296886,
|
|
"loss": 4.7038,
|
|
"mean_token_accuracy": 0.22814241647720337,
|
|
"num_tokens": 38506646.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.308951663970947,
|
|
"epoch": 1.7490811894420313,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004694006379296609,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.22932084053754806,
|
|
"num_tokens": 38516092.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.248348426818848,
|
|
"epoch": 1.7494988306047445,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046938564743313576,
|
|
"loss": 4.7449,
|
|
"mean_token_accuracy": 0.21733783334493637,
|
|
"num_tokens": 38526486.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.301684188842773,
|
|
"epoch": 1.7499164717674573,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046937065353365594,
|
|
"loss": 4.7479,
|
|
"mean_token_accuracy": 0.22684872150421143,
|
|
"num_tokens": 38535474.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.395938348770142,
|
|
"epoch": 1.7503341129301704,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046935565623148383,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.22458152025938033,
|
|
"num_tokens": 38544598.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.303765201568604,
|
|
"epoch": 1.7507517540928834,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046934065552688196,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.22105828374624253,
|
|
"num_tokens": 38553569.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.327154684066772,
|
|
"epoch": 1.7511693952555962,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004693256514201131,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.22325340211391448,
|
|
"num_tokens": 38563369.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.380122375488281,
|
|
"epoch": 1.7515870364183095,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046931064391143976,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.22026446610689163,
|
|
"num_tokens": 38573187.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.2802876949310305,
|
|
"epoch": 1.7520046775810223,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046929563300112466,
|
|
"loss": 4.6716,
|
|
"mean_token_accuracy": 0.24289790987968446,
|
|
"num_tokens": 38581014.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.240657377243042,
|
|
"epoch": 1.7524223187437353,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046928061868943067,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.2224986046552658,
|
|
"num_tokens": 38590445.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.286513805389404,
|
|
"epoch": 1.7528399599064484,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004692656009766206,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.22439124286174775,
|
|
"num_tokens": 38599372.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.408638954162598,
|
|
"epoch": 1.7532576010691614,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046925057986295734,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.21272225975990294,
|
|
"num_tokens": 38609000.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.357507562637329,
|
|
"epoch": 1.7536752422318744,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046923555534870385,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.22081125825643538,
|
|
"num_tokens": 38618420.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.27140064239502,
|
|
"epoch": 1.7540928833945872,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004692205274341232,
|
|
"loss": 4.7068,
|
|
"mean_token_accuracy": 0.2351261481642723,
|
|
"num_tokens": 38627577.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 1.7540928833945872,
|
|
"eval_entropy": 5.0557120942736145,
|
|
"eval_loss": 4.791766166687012,
|
|
"eval_mean_token_accuracy": 0.23329790720265944,
|
|
"eval_num_tokens": 38627577.0,
|
|
"eval_runtime": 20.8549,
|
|
"eval_samples_per_second": 1810.75,
|
|
"eval_steps_per_second": 226.374,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.360907173156738,
|
|
"epoch": 1.7545105245573005,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046920549611947834,
|
|
"loss": 4.8767,
|
|
"mean_token_accuracy": 0.2222430944442749,
|
|
"num_tokens": 38636837.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.338842582702637,
|
|
"epoch": 1.7549281657200133,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004691904614050326,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.2153557911515236,
|
|
"num_tokens": 38646734.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.394754791259766,
|
|
"epoch": 1.7553458068827263,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046917542329104903,
|
|
"loss": 4.9175,
|
|
"mean_token_accuracy": 0.22048242688179015,
|
|
"num_tokens": 38655990.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.340988397598267,
|
|
"epoch": 1.7557634480454394,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004691603817777909,
|
|
"loss": 4.7059,
|
|
"mean_token_accuracy": 0.2233254760503769,
|
|
"num_tokens": 38665235.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.3176970958709715,
|
|
"epoch": 1.7561810892081522,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046914533686552166,
|
|
"loss": 4.8065,
|
|
"mean_token_accuracy": 0.21556227654218674,
|
|
"num_tokens": 38675810.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.328128433227539,
|
|
"epoch": 1.7565987303708654,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004691302885545046,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.22366591542959213,
|
|
"num_tokens": 38684702.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.355241060256958,
|
|
"epoch": 1.7570163715335783,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004691152368450032,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.2177700951695442,
|
|
"num_tokens": 38694704.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.308628082275391,
|
|
"epoch": 1.7574340126962913,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046910018173728084,
|
|
"loss": 4.7261,
|
|
"mean_token_accuracy": 0.22507060766220094,
|
|
"num_tokens": 38702674.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.285755586624146,
|
|
"epoch": 1.7578516538590043,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004690851232316012,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.2305072382092476,
|
|
"num_tokens": 38711842.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.37118558883667,
|
|
"epoch": 1.7582692950217174,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046907006132822785,
|
|
"loss": 4.8274,
|
|
"mean_token_accuracy": 0.2248464748263359,
|
|
"num_tokens": 38721258.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.284417819976807,
|
|
"epoch": 1.7586869361844304,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046905499602742444,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.22053825706243516,
|
|
"num_tokens": 38730170.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.286902570724488,
|
|
"epoch": 1.7591045773471432,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046903992732945485,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.21668023467063904,
|
|
"num_tokens": 38739790.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.353579568862915,
|
|
"epoch": 1.7595222185098565,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046902485523458266,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.22837109863758087,
|
|
"num_tokens": 38748793.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.378729724884034,
|
|
"epoch": 1.7599398596725693,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046900977974307186,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.2120876595377922,
|
|
"num_tokens": 38758067.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.235297536849975,
|
|
"epoch": 1.7603575008352823,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004689947008551863,
|
|
"loss": 4.7112,
|
|
"mean_token_accuracy": 0.23336687833070754,
|
|
"num_tokens": 38767374.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.316353464126587,
|
|
"epoch": 1.7607751419979953,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004689796185711901,
|
|
"loss": 4.8461,
|
|
"mean_token_accuracy": 0.21874394714832307,
|
|
"num_tokens": 38776467.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.335316467285156,
|
|
"epoch": 1.7611927831607082,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046896453289134703,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.22940505146980286,
|
|
"num_tokens": 38785916.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.3950934410095215,
|
|
"epoch": 1.7616104243234214,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046894944381592143,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.22432608306407928,
|
|
"num_tokens": 38795271.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.347169017791748,
|
|
"epoch": 1.7620280654861342,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046893435134517735,
|
|
"loss": 4.8236,
|
|
"mean_token_accuracy": 0.22910459339618683,
|
|
"num_tokens": 38804806.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.30489821434021,
|
|
"epoch": 1.7624457066488475,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046891925547937907,
|
|
"loss": 4.6855,
|
|
"mean_token_accuracy": 0.23267927765846252,
|
|
"num_tokens": 38813465.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.328899908065796,
|
|
"epoch": 1.7628633478115603,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046890415621879075,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.21285195648670197,
|
|
"num_tokens": 38822208.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.335825681686401,
|
|
"epoch": 1.7632809889742733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004688890535636767,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.2270270422101021,
|
|
"num_tokens": 38831136.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.370437860488892,
|
|
"epoch": 1.7636986301369864,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004688739475143015,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.2245987817645073,
|
|
"num_tokens": 38840995.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.372144079208374,
|
|
"epoch": 1.7641162712996992,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046885883807092944,
|
|
"loss": 4.8857,
|
|
"mean_token_accuracy": 0.2211986243724823,
|
|
"num_tokens": 38850584.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.244695997238159,
|
|
"epoch": 1.7645339124624124,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046884372523382507,
|
|
"loss": 4.6424,
|
|
"mean_token_accuracy": 0.241389599442482,
|
|
"num_tokens": 38858869.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.338655090332031,
|
|
"epoch": 1.7649515536251252,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046882860900325296,
|
|
"loss": 4.8565,
|
|
"mean_token_accuracy": 0.2116616889834404,
|
|
"num_tokens": 38868701.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.384341049194336,
|
|
"epoch": 1.7653691947878383,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004688134893794777,
|
|
"loss": 4.9169,
|
|
"mean_token_accuracy": 0.21107658445835115,
|
|
"num_tokens": 38877785.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.4449018955230715,
|
|
"epoch": 1.7657868359505513,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046879836636276405,
|
|
"loss": 4.894,
|
|
"mean_token_accuracy": 0.2096040740609169,
|
|
"num_tokens": 38888397.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.372910404205323,
|
|
"epoch": 1.7662044771132643,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004687832399533767,
|
|
"loss": 4.8951,
|
|
"mean_token_accuracy": 0.21485867947340012,
|
|
"num_tokens": 38897458.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.41933765411377,
|
|
"epoch": 1.7666221182759774,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004687681101515805,
|
|
"loss": 4.8272,
|
|
"mean_token_accuracy": 0.22448185980319976,
|
|
"num_tokens": 38907536.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.37609748840332,
|
|
"epoch": 1.7670397594386902,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004687529769576403,
|
|
"loss": 4.8445,
|
|
"mean_token_accuracy": 0.22087595164775847,
|
|
"num_tokens": 38917340.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.319797515869141,
|
|
"epoch": 1.7674574006014034,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046873784037182106,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.21702436059713365,
|
|
"num_tokens": 38926964.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.3050579071044925,
|
|
"epoch": 1.7678750417641163,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046872270039438764,
|
|
"loss": 4.7344,
|
|
"mean_token_accuracy": 0.23361239731311798,
|
|
"num_tokens": 38936168.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.380273151397705,
|
|
"epoch": 1.7682926829268293,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004687075570256052,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.21675061732530593,
|
|
"num_tokens": 38945633.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.404670906066895,
|
|
"epoch": 1.7687103240895423,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046869241026573885,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.21610098630189895,
|
|
"num_tokens": 38955372.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.346735429763794,
|
|
"epoch": 1.7691279652522551,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046867726011505365,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.2189209207892418,
|
|
"num_tokens": 38965264.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.273779010772705,
|
|
"epoch": 1.7695456064149684,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004686621065738149,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.22025009244680405,
|
|
"num_tokens": 38975129.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.413763952255249,
|
|
"epoch": 1.7699632475776812,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046864694964228785,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.21618029624223709,
|
|
"num_tokens": 38985152.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.310215711593628,
|
|
"epoch": 1.7703808887403942,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004686317893207378,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.2210693657398224,
|
|
"num_tokens": 38995509.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.281908082962036,
|
|
"epoch": 1.7707985299031073,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004686166256094303,
|
|
"loss": 4.791,
|
|
"mean_token_accuracy": 0.2184680372476578,
|
|
"num_tokens": 39003743.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.313176918029785,
|
|
"epoch": 1.7712161710658203,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004686014585086307,
|
|
"loss": 4.8322,
|
|
"mean_token_accuracy": 0.22154945582151414,
|
|
"num_tokens": 39013324.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.314921522140503,
|
|
"epoch": 1.7716338122285333,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004685862880186045,
|
|
"loss": 4.8003,
|
|
"mean_token_accuracy": 0.2255464881658554,
|
|
"num_tokens": 39023268.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.34611496925354,
|
|
"epoch": 1.7720514533912461,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004685711141396173,
|
|
"loss": 4.8616,
|
|
"mean_token_accuracy": 0.21581173539161683,
|
|
"num_tokens": 39033516.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.338577699661255,
|
|
"epoch": 1.7724690945539594,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046855593687193474,
|
|
"loss": 4.8199,
|
|
"mean_token_accuracy": 0.21837185472249984,
|
|
"num_tokens": 39042280.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.269751405715942,
|
|
"epoch": 1.7728867357166722,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004685407562158226,
|
|
"loss": 4.794,
|
|
"mean_token_accuracy": 0.22988890558481218,
|
|
"num_tokens": 39051748.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.350153207778931,
|
|
"epoch": 1.7733043768793852,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004685255721715465,
|
|
"loss": 4.8466,
|
|
"mean_token_accuracy": 0.214113949239254,
|
|
"num_tokens": 39061703.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.399466323852539,
|
|
"epoch": 1.7737220180420983,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004685103847393723,
|
|
"loss": 4.8565,
|
|
"mean_token_accuracy": 0.22445153594017028,
|
|
"num_tokens": 39071115.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.310867547988892,
|
|
"epoch": 1.774139659204811,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046849519391956593,
|
|
"loss": 4.8187,
|
|
"mean_token_accuracy": 0.21154241114854813,
|
|
"num_tokens": 39080578.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.304015302658081,
|
|
"epoch": 1.7745573003675243,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004684799997123932,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.21761403530836104,
|
|
"num_tokens": 39090242.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.348058700561523,
|
|
"epoch": 1.7749749415302372,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004684648021181203,
|
|
"loss": 4.8582,
|
|
"mean_token_accuracy": 0.22018954157829285,
|
|
"num_tokens": 39099831.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.255354166030884,
|
|
"epoch": 1.7753925826929502,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046844960113701307,
|
|
"loss": 4.6432,
|
|
"mean_token_accuracy": 0.23478060811758042,
|
|
"num_tokens": 39109047.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.309629344940186,
|
|
"epoch": 1.7758102238556632,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046843439676933776,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.22269134521484374,
|
|
"num_tokens": 39117800.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.397587633132934,
|
|
"epoch": 1.7762278650183763,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046841918901536047,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.21974597722291947,
|
|
"num_tokens": 39127019.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.308803939819336,
|
|
"epoch": 1.7766455061810893,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004684039778753474,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.23034310787916185,
|
|
"num_tokens": 39135983.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.293127822875976,
|
|
"epoch": 1.777063147343802,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046838876334956507,
|
|
"loss": 4.749,
|
|
"mean_token_accuracy": 0.22432260364294052,
|
|
"num_tokens": 39145890.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.326159191131592,
|
|
"epoch": 1.7774807885065154,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004683735454382795,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.22214010655879973,
|
|
"num_tokens": 39154884.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.31813530921936,
|
|
"epoch": 1.7778984296692282,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004683583241417573,
|
|
"loss": 4.7715,
|
|
"mean_token_accuracy": 0.22261146306991578,
|
|
"num_tokens": 39164151.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.368152809143067,
|
|
"epoch": 1.7783160708319412,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004683430994602649,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.21086880713701248,
|
|
"num_tokens": 39173987.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.362380456924439,
|
|
"epoch": 1.7787337119946542,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046832787139406887,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.22277653813362122,
|
|
"num_tokens": 39183665.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.3412220001220705,
|
|
"epoch": 1.779151353157367,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004683126399434357,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.2337136298418045,
|
|
"num_tokens": 39192897.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.436523294448852,
|
|
"epoch": 1.7795689943200803,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004682974051086321,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.2128516510128975,
|
|
"num_tokens": 39202774.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.2855932235717775,
|
|
"epoch": 1.7799866354827931,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046828216688992466,
|
|
"loss": 4.772,
|
|
"mean_token_accuracy": 0.22551938146352768,
|
|
"num_tokens": 39212154.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.238538551330566,
|
|
"epoch": 1.7804042766455062,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004682669252875803,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.2310912176966667,
|
|
"num_tokens": 39221593.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.340345001220703,
|
|
"epoch": 1.7808219178082192,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046825168030186577,
|
|
"loss": 4.8399,
|
|
"mean_token_accuracy": 0.2232219472527504,
|
|
"num_tokens": 39230522.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.331210803985596,
|
|
"epoch": 1.7812395589709322,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000468236431933048,
|
|
"loss": 4.8555,
|
|
"mean_token_accuracy": 0.21904963850975037,
|
|
"num_tokens": 39240012.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.32345061302185,
|
|
"epoch": 1.7816572001336453,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004682211801813938,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.22418325245380402,
|
|
"num_tokens": 39248789.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.390567922592163,
|
|
"epoch": 1.782074841296358,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004682059250471703,
|
|
"loss": 4.8377,
|
|
"mean_token_accuracy": 0.22720763087272644,
|
|
"num_tokens": 39257864.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.378592395782471,
|
|
"epoch": 1.7824924824590713,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046819066653064454,
|
|
"loss": 4.7672,
|
|
"mean_token_accuracy": 0.21761315017938615,
|
|
"num_tokens": 39267137.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.308243703842163,
|
|
"epoch": 1.7829101236217841,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046817540463208357,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.21731578409671784,
|
|
"num_tokens": 39276511.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.311488199234009,
|
|
"epoch": 1.7833277647844972,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046816013935175465,
|
|
"loss": 4.7695,
|
|
"mean_token_accuracy": 0.2306961089372635,
|
|
"num_tokens": 39285053.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.290725517272949,
|
|
"epoch": 1.7837454059472102,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000468144870689925,
|
|
"loss": 4.7696,
|
|
"mean_token_accuracy": 0.22105641514062882,
|
|
"num_tokens": 39293536.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.384250020980835,
|
|
"epoch": 1.784163047109923,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004681295986468619,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.21398646980524064,
|
|
"num_tokens": 39303074.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.3333536148071286,
|
|
"epoch": 1.7845806882726363,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004681143232228328,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.21701694875955582,
|
|
"num_tokens": 39312148.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.341790390014649,
|
|
"epoch": 1.784998329435349,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046809904441810486,
|
|
"loss": 4.8234,
|
|
"mean_token_accuracy": 0.22503949105739593,
|
|
"num_tokens": 39321098.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.263268184661865,
|
|
"epoch": 1.7854159705980621,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004680837622329457,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.22656918466091155,
|
|
"num_tokens": 39329463.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.326938724517822,
|
|
"epoch": 1.7858336117607752,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046806847666762305,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.22317545413970946,
|
|
"num_tokens": 39339497.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.296004772186279,
|
|
"epoch": 1.7862512529234882,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004680531877224042,
|
|
"loss": 4.6705,
|
|
"mean_token_accuracy": 0.23852394968271257,
|
|
"num_tokens": 39348121.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.300499725341797,
|
|
"epoch": 1.7866688940862012,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046803789539755686,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.21956969797611237,
|
|
"num_tokens": 39358487.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.304026746749878,
|
|
"epoch": 1.787086535248914,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046802259969334887,
|
|
"loss": 4.8485,
|
|
"mean_token_accuracy": 0.2205999344587326,
|
|
"num_tokens": 39367493.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.2893023014068605,
|
|
"epoch": 1.7875041764116273,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004680073006100479,
|
|
"loss": 4.7929,
|
|
"mean_token_accuracy": 0.22078524976968766,
|
|
"num_tokens": 39376616.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.411026239395142,
|
|
"epoch": 1.78792181757434,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046799199814792186,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.21771973073482515,
|
|
"num_tokens": 39387079.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.256465911865234,
|
|
"epoch": 1.7883394587370531,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004679766923072386,
|
|
"loss": 4.6844,
|
|
"mean_token_accuracy": 0.23103365153074265,
|
|
"num_tokens": 39396198.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.369813346862793,
|
|
"epoch": 1.7887570998997662,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000467961383088266,
|
|
"loss": 4.903,
|
|
"mean_token_accuracy": 0.21788304597139357,
|
|
"num_tokens": 39405862.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.370705461502075,
|
|
"epoch": 1.789174741062479,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046794607049127217,
|
|
"loss": 4.8284,
|
|
"mean_token_accuracy": 0.22026977092027664,
|
|
"num_tokens": 39414352.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.387341785430908,
|
|
"epoch": 1.7895923822251922,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046793075451652513,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.2177259713411331,
|
|
"num_tokens": 39423653.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.352202653884888,
|
|
"epoch": 1.790010023387905,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046791543516429295,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.2228395476937294,
|
|
"num_tokens": 39432741.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.389963817596436,
|
|
"epoch": 1.790427664550618,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046790011243484387,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.2170472711324692,
|
|
"num_tokens": 39441837.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.328529500961304,
|
|
"epoch": 1.7908453057133311,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046788478632844616,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.22130663096904754,
|
|
"num_tokens": 39450393.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.266872930526733,
|
|
"epoch": 1.7912629468760441,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046786945684536806,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.22835344970226287,
|
|
"num_tokens": 39460226.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.284046697616577,
|
|
"epoch": 1.7916805880387572,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000467854123985878,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.2262886345386505,
|
|
"num_tokens": 39469072.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.301159477233886,
|
|
"epoch": 1.79209822920147,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004678387877502443,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.22043935358524322,
|
|
"num_tokens": 39477918.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.17331166267395,
|
|
"epoch": 1.7925158703641833,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046782344813873556,
|
|
"loss": 4.6639,
|
|
"mean_token_accuracy": 0.23490959107875825,
|
|
"num_tokens": 39487492.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.307119941711425,
|
|
"epoch": 1.792933511526896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046780810515162027,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.22721358388662338,
|
|
"num_tokens": 39496255.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.262496137619019,
|
|
"epoch": 1.793351152689609,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046779275878916694,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.232627671957016,
|
|
"num_tokens": 39504925.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.341439437866211,
|
|
"epoch": 1.7937687938523221,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046777740905164434,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.21964853703975679,
|
|
"num_tokens": 39514289.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.400147867202759,
|
|
"epoch": 1.794186435015035,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046776205593932114,
|
|
"loss": 4.8399,
|
|
"mean_token_accuracy": 0.2203590527176857,
|
|
"num_tokens": 39524421.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.383577632904053,
|
|
"epoch": 1.7946040761777482,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046774669945246616,
|
|
"loss": 4.7616,
|
|
"mean_token_accuracy": 0.22179278433322908,
|
|
"num_tokens": 39532866.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.366949462890625,
|
|
"epoch": 1.795021717340461,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004677313395913482,
|
|
"loss": 4.8651,
|
|
"mean_token_accuracy": 0.21473921835422516,
|
|
"num_tokens": 39542964.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.367677831649781,
|
|
"epoch": 1.795439358503174,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004677159763562361,
|
|
"loss": 4.8511,
|
|
"mean_token_accuracy": 0.21696348786354064,
|
|
"num_tokens": 39554127.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.304004526138305,
|
|
"epoch": 1.795856999665887,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046770060974739893,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.22630382925271988,
|
|
"num_tokens": 39563600.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.288436841964722,
|
|
"epoch": 1.7962746408286,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004676852397651055,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.2212396129965782,
|
|
"num_tokens": 39572502.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.3460746765136715,
|
|
"epoch": 1.7966922819913131,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004676698664096251,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.23030466735363006,
|
|
"num_tokens": 39581066.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.340942287445069,
|
|
"epoch": 1.797109923154026,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004676544896812268,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.22611986696720124,
|
|
"num_tokens": 39589784.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.34175181388855,
|
|
"epoch": 1.7975275643167392,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046763910958017973,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.21454847157001494,
|
|
"num_tokens": 39598561.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.289028739929199,
|
|
"epoch": 1.797945205479452,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046762372610675314,
|
|
"loss": 4.7033,
|
|
"mean_token_accuracy": 0.2289513796567917,
|
|
"num_tokens": 39607136.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.385676574707031,
|
|
"epoch": 1.798362846642165,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046760833926121645,
|
|
"loss": 4.8187,
|
|
"mean_token_accuracy": 0.22578808665275574,
|
|
"num_tokens": 39616371.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.297639274597168,
|
|
"epoch": 1.798780487804878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046759294904383887,
|
|
"loss": 4.8051,
|
|
"mean_token_accuracy": 0.22193602323532105,
|
|
"num_tokens": 39625556.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.332975149154663,
|
|
"epoch": 1.799198128967591,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004675775554548899,
|
|
"loss": 4.7415,
|
|
"mean_token_accuracy": 0.2235510379076004,
|
|
"num_tokens": 39635116.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.398444271087646,
|
|
"epoch": 1.7996157701303042,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046756215849463905,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.216711887717247,
|
|
"num_tokens": 39645523.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.392476367950439,
|
|
"epoch": 1.800033411293017,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046754675816335577,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.21292429864406587,
|
|
"num_tokens": 39654507.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.353671884536743,
|
|
"epoch": 1.80045105245573,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046753135446130973,
|
|
"loss": 4.7883,
|
|
"mean_token_accuracy": 0.22109669893980027,
|
|
"num_tokens": 39664587.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.375528717041016,
|
|
"epoch": 1.800868693618443,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004675159473887707,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.2109014868736267,
|
|
"num_tokens": 39674844.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.312663125991821,
|
|
"epoch": 1.801286334781156,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004675005369460081,
|
|
"loss": 4.7845,
|
|
"mean_token_accuracy": 0.22669218778610228,
|
|
"num_tokens": 39683894.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.307789993286133,
|
|
"epoch": 1.801703975943869,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000467485123133292,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.2195674881339073,
|
|
"num_tokens": 39693401.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.309783029556274,
|
|
"epoch": 1.802121617106582,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046746970595089207,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.21284393072128296,
|
|
"num_tokens": 39702506.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.34603853225708,
|
|
"epoch": 1.8025392582692952,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004674542853990783,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.22941326200962067,
|
|
"num_tokens": 39711252.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.3461309432983395,
|
|
"epoch": 1.802956899432008,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046743886147812054,
|
|
"loss": 4.8071,
|
|
"mean_token_accuracy": 0.21840073615312577,
|
|
"num_tokens": 39719803.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.270041227340698,
|
|
"epoch": 1.803374540594721,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004674234341882889,
|
|
"loss": 4.6719,
|
|
"mean_token_accuracy": 0.23680527359247208,
|
|
"num_tokens": 39728492.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.349958324432373,
|
|
"epoch": 1.803792181757434,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004674080035298535,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.21501430720090867,
|
|
"num_tokens": 39737703.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.347259998321533,
|
|
"epoch": 1.8042098229201469,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004673925695030843,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.22274115532636643,
|
|
"num_tokens": 39746529.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.451170873641968,
|
|
"epoch": 1.8046274640828601,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004673771321082517,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.2077428326010704,
|
|
"num_tokens": 39756398.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.374039125442505,
|
|
"epoch": 1.805045105245573,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004673616913456258,
|
|
"loss": 4.8824,
|
|
"mean_token_accuracy": 0.21606094837188722,
|
|
"num_tokens": 39766354.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.409621906280518,
|
|
"epoch": 1.805462746408286,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046734624721547687,
|
|
"loss": 4.9152,
|
|
"mean_token_accuracy": 0.21546536535024643,
|
|
"num_tokens": 39776089.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.323045921325684,
|
|
"epoch": 1.805880387570999,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046733079971807536,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.22513003796339034,
|
|
"num_tokens": 39785390.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.313414525985718,
|
|
"epoch": 1.806298028733712,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046731534885369175,
|
|
"loss": 4.6191,
|
|
"mean_token_accuracy": 0.24031467288732528,
|
|
"num_tokens": 39793837.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.318464899063111,
|
|
"epoch": 1.806715669896425,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004672998946225965,
|
|
"loss": 4.7917,
|
|
"mean_token_accuracy": 0.22270389199256896,
|
|
"num_tokens": 39802391.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.254596471786499,
|
|
"epoch": 1.8071333110591379,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046728443702506007,
|
|
"loss": 4.7845,
|
|
"mean_token_accuracy": 0.22608775347471238,
|
|
"num_tokens": 39812110.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.374943208694458,
|
|
"epoch": 1.8075509522218511,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046726897606135307,
|
|
"loss": 4.7986,
|
|
"mean_token_accuracy": 0.21837930679321288,
|
|
"num_tokens": 39821647.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.310822677612305,
|
|
"epoch": 1.807968593384564,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046725351173174627,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.2311965197324753,
|
|
"num_tokens": 39829520.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.349275016784668,
|
|
"epoch": 1.808386234547277,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004672380440365103,
|
|
"loss": 4.8698,
|
|
"mean_token_accuracy": 0.2236220806837082,
|
|
"num_tokens": 39839226.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.358958292007446,
|
|
"epoch": 1.80880387570999,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000467222572975916,
|
|
"loss": 4.7906,
|
|
"mean_token_accuracy": 0.23405847698450089,
|
|
"num_tokens": 39847937.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.306467580795288,
|
|
"epoch": 1.8092215168727028,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004672070985502342,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.22476162016391754,
|
|
"num_tokens": 39857293.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.245562505722046,
|
|
"epoch": 1.809639158035416,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046719162075973576,
|
|
"loss": 4.7235,
|
|
"mean_token_accuracy": 0.22660058438777925,
|
|
"num_tokens": 39867058.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.2479442119598385,
|
|
"epoch": 1.810056799198129,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004671761396046916,
|
|
"loss": 4.7103,
|
|
"mean_token_accuracy": 0.22976176738739013,
|
|
"num_tokens": 39876166.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.331583547592163,
|
|
"epoch": 1.810474440360842,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004671606550853729,
|
|
"loss": 4.858,
|
|
"mean_token_accuracy": 0.21674117743968963,
|
|
"num_tokens": 39885980.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.349196290969848,
|
|
"epoch": 1.810892081523555,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046714516720205057,
|
|
"loss": 4.8907,
|
|
"mean_token_accuracy": 0.2208524152636528,
|
|
"num_tokens": 39895263.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.34561972618103,
|
|
"epoch": 1.811309722686268,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046712967595499585,
|
|
"loss": 4.8986,
|
|
"mean_token_accuracy": 0.2126632273197174,
|
|
"num_tokens": 39904052.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.2147846698760985,
|
|
"epoch": 1.811727363848981,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004671141813444798,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.2263869896531105,
|
|
"num_tokens": 39913411.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.263957452774048,
|
|
"epoch": 1.8121450050116938,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046709868337077386,
|
|
"loss": 4.7027,
|
|
"mean_token_accuracy": 0.22990268915891648,
|
|
"num_tokens": 39922262.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.37642822265625,
|
|
"epoch": 1.812562646174407,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004670831820341491,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.21509760320186616,
|
|
"num_tokens": 39932067.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.400067615509033,
|
|
"epoch": 1.81298028733712,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046706767733487714,
|
|
"loss": 4.8548,
|
|
"mean_token_accuracy": 0.21994656324386597,
|
|
"num_tokens": 39941565.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.331675958633423,
|
|
"epoch": 1.813397928499833,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046705216927322925,
|
|
"loss": 4.6719,
|
|
"mean_token_accuracy": 0.22950104922056197,
|
|
"num_tokens": 39950569.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.284983730316162,
|
|
"epoch": 1.813815569662546,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000467036657849477,
|
|
"loss": 4.7207,
|
|
"mean_token_accuracy": 0.23075711578130723,
|
|
"num_tokens": 39959341.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.35752124786377,
|
|
"epoch": 1.8142332108252588,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004670211430638919,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.21831718534231187,
|
|
"num_tokens": 39968503.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.4011987209320065,
|
|
"epoch": 1.814650851987972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004670056249167455,
|
|
"loss": 4.8937,
|
|
"mean_token_accuracy": 0.2085566282272339,
|
|
"num_tokens": 39977717.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.293237495422363,
|
|
"epoch": 1.8150684931506849,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004669901034083096,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.22182734310626984,
|
|
"num_tokens": 39986066.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.426344871520996,
|
|
"epoch": 1.815486134313398,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046697457853885576,
|
|
"loss": 4.8806,
|
|
"mean_token_accuracy": 0.21840497702360154,
|
|
"num_tokens": 39995067.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.31282525062561,
|
|
"epoch": 1.815903775476111,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004669590503086559,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.22081243693828584,
|
|
"num_tokens": 40005102.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.318619966506958,
|
|
"epoch": 1.816321416638824,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046694351871798175,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.22349392920732497,
|
|
"num_tokens": 40013475.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.364097642898559,
|
|
"epoch": 1.816739057801537,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046692798376710533,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.22365783005952836,
|
|
"num_tokens": 40023083.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.210634040832519,
|
|
"epoch": 1.8171566989642498,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046691244545629847,
|
|
"loss": 4.7014,
|
|
"mean_token_accuracy": 0.23226906657218932,
|
|
"num_tokens": 40031462.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.367334270477295,
|
|
"epoch": 1.817574340126963,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004668969037858333,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.21852237433195115,
|
|
"num_tokens": 40040037.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.378074359893799,
|
|
"epoch": 1.8179919812896759,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046688135875598184,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.2215333551168442,
|
|
"num_tokens": 40049668.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.313532590866089,
|
|
"epoch": 1.818409622452389,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004668658103670161,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.21582211852073668,
|
|
"num_tokens": 40058080.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.394847393035889,
|
|
"epoch": 1.818827263615102,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046685025861920856,
|
|
"loss": 4.8625,
|
|
"mean_token_accuracy": 0.22243407368659973,
|
|
"num_tokens": 40067411.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.341232967376709,
|
|
"epoch": 1.8192449047778148,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004668347035128312,
|
|
"loss": 4.7697,
|
|
"mean_token_accuracy": 0.2215399771928787,
|
|
"num_tokens": 40076481.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.390822553634644,
|
|
"epoch": 1.819662545940528,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046681914504815653,
|
|
"loss": 4.9126,
|
|
"mean_token_accuracy": 0.22215962409973145,
|
|
"num_tokens": 40084981.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.338846111297608,
|
|
"epoch": 1.8200801871032408,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046680358322545687,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.2278887301683426,
|
|
"num_tokens": 40094219.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.326103401184082,
|
|
"epoch": 1.8204978282659539,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004667880180450045,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.22147365659475327,
|
|
"num_tokens": 40103833.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.365367317199707,
|
|
"epoch": 1.8209154694286669,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046677244950707204,
|
|
"loss": 4.854,
|
|
"mean_token_accuracy": 0.21816579550504683,
|
|
"num_tokens": 40112906.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.363131427764893,
|
|
"epoch": 1.82133311059138,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004667568776119321,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.21576280891895294,
|
|
"num_tokens": 40122080.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.309609508514404,
|
|
"epoch": 1.821750751754093,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004667413023598571,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.22389766126871108,
|
|
"num_tokens": 40131765.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.280176830291748,
|
|
"epoch": 1.8221683929168058,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004667257237511199,
|
|
"loss": 4.728,
|
|
"mean_token_accuracy": 0.22561855614185333,
|
|
"num_tokens": 40141084.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.308791017532348,
|
|
"epoch": 1.822586034079519,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046671014178599295,
|
|
"loss": 4.7622,
|
|
"mean_token_accuracy": 0.21926906406879426,
|
|
"num_tokens": 40149845.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.355204153060913,
|
|
"epoch": 1.8230036752422318,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046669455646474936,
|
|
"loss": 4.7786,
|
|
"mean_token_accuracy": 0.22415568828582763,
|
|
"num_tokens": 40159173.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.344823217391967,
|
|
"epoch": 1.8234213164049449,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046667896778766185,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.2205754593014717,
|
|
"num_tokens": 40168949.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.327023124694824,
|
|
"epoch": 1.823838957567658,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046666337575500315,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.21783947497606276,
|
|
"num_tokens": 40178886.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.338751935958863,
|
|
"epoch": 1.8242565987303707,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004666477803670464,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.22199992090463638,
|
|
"num_tokens": 40187562.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.3211816310882565,
|
|
"epoch": 1.824674239893084,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004666321816240646,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.2282288745045662,
|
|
"num_tokens": 40196910.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.3182916164398195,
|
|
"epoch": 1.8250918810557968,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004666165795263308,
|
|
"loss": 4.8104,
|
|
"mean_token_accuracy": 0.22644342631101608,
|
|
"num_tokens": 40206238.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.311196041107178,
|
|
"epoch": 1.8255095222185098,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004666009740741181,
|
|
"loss": 4.7937,
|
|
"mean_token_accuracy": 0.22937480211257935,
|
|
"num_tokens": 40215191.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.315855979919434,
|
|
"epoch": 1.8259271633812229,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046658536526769976,
|
|
"loss": 4.8035,
|
|
"mean_token_accuracy": 0.22049635350704194,
|
|
"num_tokens": 40224408.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.341051721572876,
|
|
"epoch": 1.8263448045439359,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004665697531073489,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.21891577094793319,
|
|
"num_tokens": 40233733.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.2845587730407715,
|
|
"epoch": 1.826762445706649,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000466554137593339,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.23507034480571748,
|
|
"num_tokens": 40242897.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.329348707199097,
|
|
"epoch": 1.8271800868693617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046653851872594334,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.22187591791152955,
|
|
"num_tokens": 40251936.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.384186744689941,
|
|
"epoch": 1.827597728032075,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004665228965054353,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.22028078585863115,
|
|
"num_tokens": 40260295.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.350235557556152,
|
|
"epoch": 1.8280153691947878,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004665072709320885,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.21835578829050065,
|
|
"num_tokens": 40270058.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.2714556694030765,
|
|
"epoch": 1.8284330103575008,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046649164200617633,
|
|
"loss": 4.6753,
|
|
"mean_token_accuracy": 0.23156288862228394,
|
|
"num_tokens": 40278599.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.375455236434936,
|
|
"epoch": 1.8288506515202139,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004664760097279725,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.21390042155981065,
|
|
"num_tokens": 40288591.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.336084604263306,
|
|
"epoch": 1.8292682926829267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004664603740977506,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.2283698469400406,
|
|
"num_tokens": 40297359.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.394135046005249,
|
|
"epoch": 1.82968593384564,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046644473511578443,
|
|
"loss": 4.9016,
|
|
"mean_token_accuracy": 0.2167123317718506,
|
|
"num_tokens": 40307130.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.383970499038696,
|
|
"epoch": 1.8301035750083527,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046642909278234775,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.22807247787714005,
|
|
"num_tokens": 40316065.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.3249258518219,
|
|
"epoch": 1.8305212161710658,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004664134470977143,
|
|
"loss": 4.8191,
|
|
"mean_token_accuracy": 0.21894822567701339,
|
|
"num_tokens": 40325808.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.364341735839844,
|
|
"epoch": 1.8309388573337788,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046639779806215815,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.22909789234399797,
|
|
"num_tokens": 40334632.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.328810405731201,
|
|
"epoch": 1.8313564984964918,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004663821456759532,
|
|
"loss": 4.81,
|
|
"mean_token_accuracy": 0.214262393116951,
|
|
"num_tokens": 40343803.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.316974210739136,
|
|
"epoch": 1.8317741396592049,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046636648993937326,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.22895658016204834,
|
|
"num_tokens": 40352743.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.371284866333008,
|
|
"epoch": 1.8321917808219177,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004663508308526927,
|
|
"loss": 4.832,
|
|
"mean_token_accuracy": 0.2234286442399025,
|
|
"num_tokens": 40361421.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.349265241622925,
|
|
"epoch": 1.832609421984631,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046633516841618547,
|
|
"loss": 4.7711,
|
|
"mean_token_accuracy": 0.22054440379142762,
|
|
"num_tokens": 40369860.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.376739740371704,
|
|
"epoch": 1.8330270631473438,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004663195026301258,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.2202886387705803,
|
|
"num_tokens": 40379095.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.3570630073547365,
|
|
"epoch": 1.8334447043100568,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004663038334947879,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.21967164129018785,
|
|
"num_tokens": 40388373.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.352050685882569,
|
|
"epoch": 1.8338623454727698,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004662881610104461,
|
|
"loss": 4.8264,
|
|
"mean_token_accuracy": 0.2182978570461273,
|
|
"num_tokens": 40398158.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.388954448699951,
|
|
"epoch": 1.8342799866354826,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000466272485177375,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.21130674481391906,
|
|
"num_tokens": 40407540.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.425385332107544,
|
|
"epoch": 1.834697627798196,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046625680599584864,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.2134237691760063,
|
|
"num_tokens": 40417445.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.412662076950073,
|
|
"epoch": 1.8351152689609087,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046624112346614166,
|
|
"loss": 4.8543,
|
|
"mean_token_accuracy": 0.2117933750152588,
|
|
"num_tokens": 40426873.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.378210115432739,
|
|
"epoch": 1.8355329101236217,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004662254375885287,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.22296128273010254,
|
|
"num_tokens": 40436072.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.328469467163086,
|
|
"epoch": 1.8359505512863348,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046620974836328425,
|
|
"loss": 4.7992,
|
|
"mean_token_accuracy": 0.22666240334510804,
|
|
"num_tokens": 40445599.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.373327255249023,
|
|
"epoch": 1.8363681924490478,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004661940557906829,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.21848830580711365,
|
|
"num_tokens": 40454982.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.278953981399536,
|
|
"epoch": 1.8367858336117608,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046617835987099957,
|
|
"loss": 4.6859,
|
|
"mean_token_accuracy": 0.22926678210496904,
|
|
"num_tokens": 40463794.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.283946847915649,
|
|
"epoch": 1.8372034747744737,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000466162660604509,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.23063957691192627,
|
|
"num_tokens": 40473139.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.3047820091247555,
|
|
"epoch": 1.837621115937187,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046614695799148575,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.2262912020087242,
|
|
"num_tokens": 40481942.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.398828506469727,
|
|
"epoch": 1.8380387570998997,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046613125203220506,
|
|
"loss": 4.7687,
|
|
"mean_token_accuracy": 0.22591395825147628,
|
|
"num_tokens": 40490428.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.401269578933716,
|
|
"epoch": 1.8384563982626128,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046611554272694175,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.21775696575641632,
|
|
"num_tokens": 40500185.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.318641519546508,
|
|
"epoch": 1.8388740394253258,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004660998300759707,
|
|
"loss": 4.8023,
|
|
"mean_token_accuracy": 0.22610743194818497,
|
|
"num_tokens": 40509205.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.304283857345581,
|
|
"epoch": 1.8392916805880386,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046608411407956726,
|
|
"loss": 4.724,
|
|
"mean_token_accuracy": 0.22258372902870177,
|
|
"num_tokens": 40518910.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.3855616569519045,
|
|
"epoch": 1.8397093217507519,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046606839473800626,
|
|
"loss": 4.8148,
|
|
"mean_token_accuracy": 0.225131094455719,
|
|
"num_tokens": 40526988.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.269553995132446,
|
|
"epoch": 1.8401269629134647,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004660526720515631,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.23242639154195785,
|
|
"num_tokens": 40536436.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.3383866310119625,
|
|
"epoch": 1.8405446040761777,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004660369460205128,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.2202915981411934,
|
|
"num_tokens": 40546341.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.423819828033447,
|
|
"epoch": 1.8409622452388907,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046602121664513104,
|
|
"loss": 4.927,
|
|
"mean_token_accuracy": 0.21657581627368927,
|
|
"num_tokens": 40556915.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.400114727020264,
|
|
"epoch": 1.8413798864016038,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046600548392569283,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.218313567340374,
|
|
"num_tokens": 40566881.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.26154932975769,
|
|
"epoch": 1.8417975275643168,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046598974786247365,
|
|
"loss": 4.674,
|
|
"mean_token_accuracy": 0.2278757244348526,
|
|
"num_tokens": 40574845.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.264815902709961,
|
|
"epoch": 1.8422151687270296,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004659740084557491,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.2345008745789528,
|
|
"num_tokens": 40583274.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.242912006378174,
|
|
"epoch": 1.8426328098897429,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004659582657057947,
|
|
"loss": 4.7013,
|
|
"mean_token_accuracy": 0.22523954659700393,
|
|
"num_tokens": 40592138.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.287030935287476,
|
|
"epoch": 1.8430504510524557,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000465942519612886,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.23079447597265243,
|
|
"num_tokens": 40600453.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.318706369400024,
|
|
"epoch": 1.8434680922151687,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004659267701772986,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.21390601098537446,
|
|
"num_tokens": 40610511.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.308894348144531,
|
|
"epoch": 1.8438857333778818,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004659110173993083,
|
|
"loss": 4.7104,
|
|
"mean_token_accuracy": 0.23016233295202254,
|
|
"num_tokens": 40619819.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.150425386428833,
|
|
"epoch": 1.8443033745405946,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004658952612791908,
|
|
"loss": 4.5941,
|
|
"mean_token_accuracy": 0.23740431070327758,
|
|
"num_tokens": 40628400.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.204916000366211,
|
|
"epoch": 1.8447210157033078,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000465879501817222,
|
|
"loss": 4.7404,
|
|
"mean_token_accuracy": 0.23083641529083251,
|
|
"num_tokens": 40637396.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.390710878372192,
|
|
"epoch": 1.8451386568660206,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046586373901367774,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.21848369389772415,
|
|
"num_tokens": 40645902.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.420822429656982,
|
|
"epoch": 1.8455562980287337,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000465847972868834,
|
|
"loss": 4.8466,
|
|
"mean_token_accuracy": 0.22554014027118682,
|
|
"num_tokens": 40656382.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.371750164031982,
|
|
"epoch": 1.8459739391914467,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004658322033829668,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.22063169181346892,
|
|
"num_tokens": 40665471.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.322684621810913,
|
|
"epoch": 1.8463915803541597,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046581643055635215,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.22808354943990708,
|
|
"num_tokens": 40674668.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.29788122177124,
|
|
"epoch": 1.8468092215168728,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046580065438926624,
|
|
"loss": 4.7301,
|
|
"mean_token_accuracy": 0.22511180490255356,
|
|
"num_tokens": 40683779.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.300827217102051,
|
|
"epoch": 1.8472268626795856,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004657848748819851,
|
|
"loss": 4.8224,
|
|
"mean_token_accuracy": 0.2197452649474144,
|
|
"num_tokens": 40692412.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.2252861022949215,
|
|
"epoch": 1.8476445038422988,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046576909203478517,
|
|
"loss": 4.6453,
|
|
"mean_token_accuracy": 0.23694164901971818,
|
|
"num_tokens": 40701652.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.449874305725098,
|
|
"epoch": 1.8480621450050116,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046575330584794263,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.21139971762895585,
|
|
"num_tokens": 40711149.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.392239379882812,
|
|
"epoch": 1.8484797861677247,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004657375163217338,
|
|
"loss": 4.8245,
|
|
"mean_token_accuracy": 0.2227652058005333,
|
|
"num_tokens": 40721014.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.321559715270996,
|
|
"epoch": 1.8488974273304377,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046572172345643527,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.22522309571504592,
|
|
"num_tokens": 40730645.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.261430931091309,
|
|
"epoch": 1.8493150684931505,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046570592725232333,
|
|
"loss": 4.6981,
|
|
"mean_token_accuracy": 0.23284206688404083,
|
|
"num_tokens": 40739620.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.266896152496338,
|
|
"epoch": 1.8497327096558638,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004656901277096746,
|
|
"loss": 4.76,
|
|
"mean_token_accuracy": 0.22742909640073777,
|
|
"num_tokens": 40748840.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.406991720199585,
|
|
"epoch": 1.8501503508185766,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004656743248287656,
|
|
"loss": 4.9214,
|
|
"mean_token_accuracy": 0.21287447363138198,
|
|
"num_tokens": 40757798.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.29442720413208,
|
|
"epoch": 1.8505679919812896,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004656585186098731,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.2270408570766449,
|
|
"num_tokens": 40766853.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.278590536117553,
|
|
"epoch": 1.8509856331440027,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004656427090532737,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.23091840147972106,
|
|
"num_tokens": 40775232.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.369508600234985,
|
|
"epoch": 1.8514032743067157,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046562689615924427,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.22246652245521545,
|
|
"num_tokens": 40783759.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.421086549758911,
|
|
"epoch": 1.8518209154694287,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004656110799280615,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.2214965596795082,
|
|
"num_tokens": 40792819.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.315679550170898,
|
|
"epoch": 1.8522385566321415,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046559526036000235,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.2245180696249008,
|
|
"num_tokens": 40801956.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.319981336593628,
|
|
"epoch": 1.8526561977948548,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046557943745534374,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.22110120356082916,
|
|
"num_tokens": 40812439.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.388884258270264,
|
|
"epoch": 1.8530738389575676,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046556361121436265,
|
|
"loss": 4.8834,
|
|
"mean_token_accuracy": 0.21338282972574235,
|
|
"num_tokens": 40822712.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.290718507766724,
|
|
"epoch": 1.8534914801202806,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046554778163733626,
|
|
"loss": 4.7482,
|
|
"mean_token_accuracy": 0.2209436297416687,
|
|
"num_tokens": 40831242.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.253593873977661,
|
|
"epoch": 1.8539091212829937,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046553194872454146,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.2334587961435318,
|
|
"num_tokens": 40839754.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.349786233901978,
|
|
"epoch": 1.8543267624457065,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046551611247625565,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.22229417264461518,
|
|
"num_tokens": 40848925.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.332039546966553,
|
|
"epoch": 1.8547444036084197,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004655002728927559,
|
|
"loss": 4.8078,
|
|
"mean_token_accuracy": 0.2228088304400444,
|
|
"num_tokens": 40857784.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.24169430732727,
|
|
"epoch": 1.8551620447711326,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046548442997431966,
|
|
"loss": 4.6186,
|
|
"mean_token_accuracy": 0.2400614619255066,
|
|
"num_tokens": 40866607.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.416183948516846,
|
|
"epoch": 1.8555796859338456,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004654685837212241,
|
|
"loss": 4.822,
|
|
"mean_token_accuracy": 0.22379968762397767,
|
|
"num_tokens": 40876730.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.301463222503662,
|
|
"epoch": 1.8559973270965586,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004654527341337468,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.2163375586271286,
|
|
"num_tokens": 40886482.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.324524164199829,
|
|
"epoch": 1.8564149682592717,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046543688121216504,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.22171374708414077,
|
|
"num_tokens": 40896704.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.307766675949097,
|
|
"epoch": 1.8568326094219847,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004654210249567565,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.22165955305099488,
|
|
"num_tokens": 40906665.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.324546480178833,
|
|
"epoch": 1.8572502505846975,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004654051653677988,
|
|
"loss": 4.8103,
|
|
"mean_token_accuracy": 0.22349947541952134,
|
|
"num_tokens": 40915838.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.2517005443573,
|
|
"epoch": 1.8576678917474108,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046538930244556927,
|
|
"loss": 4.757,
|
|
"mean_token_accuracy": 0.2166921690106392,
|
|
"num_tokens": 40924571.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.316838121414184,
|
|
"epoch": 1.8580855329101236,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046537343619034593,
|
|
"loss": 4.7588,
|
|
"mean_token_accuracy": 0.22904950380325317,
|
|
"num_tokens": 40934421.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.376737594604492,
|
|
"epoch": 1.8585031740728366,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046535756660240644,
|
|
"loss": 4.6345,
|
|
"mean_token_accuracy": 0.23409517109394073,
|
|
"num_tokens": 40943090.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.346120452880859,
|
|
"epoch": 1.8589208152355496,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004653416936820287,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.22564945816993714,
|
|
"num_tokens": 40952568.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.227886438369751,
|
|
"epoch": 1.8593384563982625,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004653258174294904,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.22316215187311172,
|
|
"num_tokens": 40961122.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.308889389038086,
|
|
"epoch": 1.8597560975609757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004653099378450696,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.2120559811592102,
|
|
"num_tokens": 40971117.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.338676261901855,
|
|
"epoch": 1.8601737387236885,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046529405492904427,
|
|
"loss": 4.7973,
|
|
"mean_token_accuracy": 0.22230071872472762,
|
|
"num_tokens": 40981151.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.253550481796265,
|
|
"epoch": 1.8605913798864016,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004652781686816925,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.224892495572567,
|
|
"num_tokens": 40990481.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.26201753616333,
|
|
"epoch": 1.8610090210491146,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004652622791032922,
|
|
"loss": 4.7302,
|
|
"mean_token_accuracy": 0.22334261536598204,
|
|
"num_tokens": 40999360.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.362600946426392,
|
|
"epoch": 1.8614266622118276,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046524638619412187,
|
|
"loss": 4.8842,
|
|
"mean_token_accuracy": 0.21398439705371858,
|
|
"num_tokens": 41009342.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.37716326713562,
|
|
"epoch": 1.8618443033745407,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046523048995445945,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.22589478492736817,
|
|
"num_tokens": 41018219.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.371154689788819,
|
|
"epoch": 1.8622619445372535,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046521459038458327,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.22536568194627762,
|
|
"num_tokens": 41027339.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.333800268173218,
|
|
"epoch": 1.8626795856999667,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046519868748477186,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.2239409402012825,
|
|
"num_tokens": 41036748.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.27505259513855,
|
|
"epoch": 1.8630972268626795,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046518278125530336,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.22922117114067078,
|
|
"num_tokens": 41046064.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.291925716400146,
|
|
"epoch": 1.8635148680253926,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004651668716964564,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.22675924599170685,
|
|
"num_tokens": 41055784.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.346319198608398,
|
|
"epoch": 1.8639325091881056,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046515095880850937,
|
|
"loss": 4.7394,
|
|
"mean_token_accuracy": 0.22768514603376389,
|
|
"num_tokens": 41065585.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.2934300899505615,
|
|
"epoch": 1.8643501503508184,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046513504259174104,
|
|
"loss": 4.7054,
|
|
"mean_token_accuracy": 0.23854216039180756,
|
|
"num_tokens": 41073531.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.379220485687256,
|
|
"epoch": 1.8647677915135317,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004651191230464299,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.21870528608560563,
|
|
"num_tokens": 41082370.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.268295192718506,
|
|
"epoch": 1.8651854326762445,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004651032001728546,
|
|
"loss": 4.7711,
|
|
"mean_token_accuracy": 0.2208670288324356,
|
|
"num_tokens": 41091025.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.368709230422974,
|
|
"epoch": 1.8656030738389575,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004650872739712941,
|
|
"loss": 4.8699,
|
|
"mean_token_accuracy": 0.21064681857824324,
|
|
"num_tokens": 41100846.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.365600538253784,
|
|
"epoch": 1.8660207150016705,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046507134444202694,
|
|
"loss": 4.7292,
|
|
"mean_token_accuracy": 0.22826676666736603,
|
|
"num_tokens": 41109885.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.331897115707397,
|
|
"epoch": 1.8664383561643836,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004650554115853321,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.22864848375320435,
|
|
"num_tokens": 41118478.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.275716829299927,
|
|
"epoch": 1.8668559973270966,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046503947540148857,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.23627809882164003,
|
|
"num_tokens": 41127605.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.3138326644897464,
|
|
"epoch": 1.8672736384898094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046502353589077523,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.2188823029398918,
|
|
"num_tokens": 41137850.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.285767316818237,
|
|
"epoch": 1.8676912796525227,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046500759305347116,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.23284513801336287,
|
|
"num_tokens": 41147452.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.302712106704712,
|
|
"epoch": 1.8681089208152355,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004649916468898555,
|
|
"loss": 4.692,
|
|
"mean_token_accuracy": 0.227798131108284,
|
|
"num_tokens": 41155946.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.3900469779968265,
|
|
"epoch": 1.8685265619779485,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004649756974002073,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.21609860956668853,
|
|
"num_tokens": 41165048.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.219330072402954,
|
|
"epoch": 1.8689442031406616,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004649597445848059,
|
|
"loss": 4.6222,
|
|
"mean_token_accuracy": 0.23636798411607743,
|
|
"num_tokens": 41174026.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.392475986480713,
|
|
"epoch": 1.8693618443033744,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004649437884439305,
|
|
"loss": 4.8288,
|
|
"mean_token_accuracy": 0.2224874421954155,
|
|
"num_tokens": 41183190.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.254263305664063,
|
|
"epoch": 1.8697794854660876,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004649278289778604,
|
|
"loss": 4.727,
|
|
"mean_token_accuracy": 0.22198239713907242,
|
|
"num_tokens": 41192070.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.221903467178345,
|
|
"epoch": 1.8701971266288004,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046491186618687514,
|
|
"loss": 4.7014,
|
|
"mean_token_accuracy": 0.23020272105932235,
|
|
"num_tokens": 41201166.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.341044330596924,
|
|
"epoch": 1.8706147677915135,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046489590007125397,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.2301286369562149,
|
|
"num_tokens": 41208998.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.333744668960572,
|
|
"epoch": 1.8710324089542265,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004648799306312766,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.23312823623418807,
|
|
"num_tokens": 41218206.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.249620962142944,
|
|
"epoch": 1.8714500501169395,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046486395786722237,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.2274901881814003,
|
|
"num_tokens": 41226345.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.286907291412353,
|
|
"epoch": 1.8718676912796526,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004648479817793711,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.2241570070385933,
|
|
"num_tokens": 41235641.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.3667059421539305,
|
|
"epoch": 1.8722853324423654,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004648320023680023,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.221302430331707,
|
|
"num_tokens": 41245308.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.330704689025879,
|
|
"epoch": 1.8727029736050786,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046481601963339593,
|
|
"loss": 4.8052,
|
|
"mean_token_accuracy": 0.22642115950584413,
|
|
"num_tokens": 41254030.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.403549909591675,
|
|
"epoch": 1.8731206147677915,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046480003357583154,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.22409734278917312,
|
|
"num_tokens": 41263449.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.42559175491333,
|
|
"epoch": 1.8735382559305045,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004647840441955892,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.2225114643573761,
|
|
"num_tokens": 41272379.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.3128917694091795,
|
|
"epoch": 1.8739558970932175,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004647680514929486,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.22898042798042298,
|
|
"num_tokens": 41281384.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.32051830291748,
|
|
"epoch": 1.8743735382559303,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046475205546818996,
|
|
"loss": 4.7017,
|
|
"mean_token_accuracy": 0.23574018627405166,
|
|
"num_tokens": 41290662.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.336128997802734,
|
|
"epoch": 1.8747911794186436,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004647360561215931,
|
|
"loss": 4.7961,
|
|
"mean_token_accuracy": 0.22263954877853392,
|
|
"num_tokens": 41300278.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.364693975448608,
|
|
"epoch": 1.8752088205813564,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046472005345343814,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.2257153108716011,
|
|
"num_tokens": 41309456.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.337533378601075,
|
|
"epoch": 1.8756264617440697,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004647040474640054,
|
|
"loss": 4.8614,
|
|
"mean_token_accuracy": 0.21656539291143417,
|
|
"num_tokens": 41318550.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.358349895477295,
|
|
"epoch": 1.8760441029067825,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004646880381535749,
|
|
"loss": 4.8418,
|
|
"mean_token_accuracy": 0.2225417897105217,
|
|
"num_tokens": 41327867.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.2927490234375,
|
|
"epoch": 1.8764617440694955,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000464672025522427,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.2297147050499916,
|
|
"num_tokens": 41337151.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.233954334259034,
|
|
"epoch": 1.8768793852322085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000464656009570842,
|
|
"loss": 4.6686,
|
|
"mean_token_accuracy": 0.2333948716521263,
|
|
"num_tokens": 41346205.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.337543773651123,
|
|
"epoch": 1.8772970263949214,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004646399902991002,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.2278922751545906,
|
|
"num_tokens": 41354288.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.318351364135742,
|
|
"epoch": 1.8777146675576346,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004646239677074821,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.22686468213796615,
|
|
"num_tokens": 41363366.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.316320991516113,
|
|
"epoch": 1.8781323087203474,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046460794179626827,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.22408687621355056,
|
|
"num_tokens": 41371778.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.304623031616211,
|
|
"epoch": 1.8785499498830605,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004645919125657391,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.2370823860168457,
|
|
"num_tokens": 41380035.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.422584295272827,
|
|
"epoch": 1.8789675910457735,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004645758800161754,
|
|
"loss": 4.9124,
|
|
"mean_token_accuracy": 0.21386350989341735,
|
|
"num_tokens": 41389819.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.366638994216919,
|
|
"epoch": 1.8793852322084865,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004645598441478577,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.21757938861846923,
|
|
"num_tokens": 41398704.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.398664665222168,
|
|
"epoch": 1.8798028733711996,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046454380496106665,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.21809352338314056,
|
|
"num_tokens": 41406634.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.317213106155395,
|
|
"epoch": 1.8802205145339124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004645277624560832,
|
|
"loss": 4.8383,
|
|
"mean_token_accuracy": 0.21287028193473817,
|
|
"num_tokens": 41416164.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.3561018943786625,
|
|
"epoch": 1.8806381556966256,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046451171663318815,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.22107122391462325,
|
|
"num_tokens": 41426100.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.471065521240234,
|
|
"epoch": 1.8810557968593384,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046449566749266237,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.21084764003753662,
|
|
"num_tokens": 41435901.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.375808668136597,
|
|
"epoch": 1.8814734380220515,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004644796150347868,
|
|
"loss": 4.8038,
|
|
"mean_token_accuracy": 0.22906512320041655,
|
|
"num_tokens": 41444416.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.336542463302612,
|
|
"epoch": 1.8818910791847645,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046446355925984257,
|
|
"loss": 4.8189,
|
|
"mean_token_accuracy": 0.22276512086391448,
|
|
"num_tokens": 41454477.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.381804084777832,
|
|
"epoch": 1.8823087203474773,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046444750016811064,
|
|
"loss": 4.8517,
|
|
"mean_token_accuracy": 0.2187905192375183,
|
|
"num_tokens": 41464156.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.417022609710694,
|
|
"epoch": 1.8827263615101906,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004644314377598722,
|
|
"loss": 4.808,
|
|
"mean_token_accuracy": 0.22140583842992784,
|
|
"num_tokens": 41473236.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.315921020507813,
|
|
"epoch": 1.8831440026729034,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004644153720354084,
|
|
"loss": 4.7922,
|
|
"mean_token_accuracy": 0.2255902260541916,
|
|
"num_tokens": 41482562.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.3589394092559814,
|
|
"epoch": 1.8835616438356164,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004643993029950005,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.22577932029962539,
|
|
"num_tokens": 41490405.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.429067087173462,
|
|
"epoch": 1.8839792849983295,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046438323063892985,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.21507659256458284,
|
|
"num_tokens": 41500188.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.3357932567596436,
|
|
"epoch": 1.8843969261610425,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046436715496747774,
|
|
"loss": 4.8103,
|
|
"mean_token_accuracy": 0.2137744888663292,
|
|
"num_tokens": 41509736.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.283964776992798,
|
|
"epoch": 1.8848145673237555,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004643510759809257,
|
|
"loss": 4.8176,
|
|
"mean_token_accuracy": 0.21865372210741044,
|
|
"num_tokens": 41519795.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.40634822845459,
|
|
"epoch": 1.8852322084864683,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004643349936795551,
|
|
"loss": 4.8165,
|
|
"mean_token_accuracy": 0.21702448576688765,
|
|
"num_tokens": 41529602.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.349994707107544,
|
|
"epoch": 1.8856498496491816,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004643189080636475,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.22576595097780228,
|
|
"num_tokens": 41538850.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.30688624382019,
|
|
"epoch": 1.8860674908118944,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046430281913348466,
|
|
"loss": 4.763,
|
|
"mean_token_accuracy": 0.2248399794101715,
|
|
"num_tokens": 41548099.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.394729518890381,
|
|
"epoch": 1.8864851319746074,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004642867268893481,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.21496876776218415,
|
|
"num_tokens": 41557288.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.309240007400513,
|
|
"epoch": 1.8869027731373205,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004642706313315194,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.2416210263967514,
|
|
"num_tokens": 41565938.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.393085479736328,
|
|
"epoch": 1.8873204143000333,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046425453246028056,
|
|
"loss": 4.8589,
|
|
"mean_token_accuracy": 0.21850441247224808,
|
|
"num_tokens": 41574984.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.361312770843506,
|
|
"epoch": 1.8877380554627465,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004642384302759133,
|
|
"loss": 4.7259,
|
|
"mean_token_accuracy": 0.2298301339149475,
|
|
"num_tokens": 41584020.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.396681451797486,
|
|
"epoch": 1.8881556966254593,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046422232477869957,
|
|
"loss": 4.843,
|
|
"mean_token_accuracy": 0.2182310402393341,
|
|
"num_tokens": 41594146.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.368730258941651,
|
|
"epoch": 1.8885733377881724,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004642062159689213,
|
|
"loss": 4.8706,
|
|
"mean_token_accuracy": 0.21830271929502487,
|
|
"num_tokens": 41603469.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.338352537155151,
|
|
"epoch": 1.8889909789508854,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046419010384686043,
|
|
"loss": 4.8178,
|
|
"mean_token_accuracy": 0.22717327922582625,
|
|
"num_tokens": 41613940.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.369731044769287,
|
|
"epoch": 1.8894086201135984,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000464173988412799,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.2280757188796997,
|
|
"num_tokens": 41623153.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.332021856307984,
|
|
"epoch": 1.8898262612763115,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046415786966701926,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.2188512459397316,
|
|
"num_tokens": 41632396.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.2716718196868895,
|
|
"epoch": 1.8902439024390243,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004641417476098034,
|
|
"loss": 4.6982,
|
|
"mean_token_accuracy": 0.22645082771778108,
|
|
"num_tokens": 41640727.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.219249153137207,
|
|
"epoch": 1.8906615436017375,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004641256222414335,
|
|
"loss": 4.5942,
|
|
"mean_token_accuracy": 0.23073157668113708,
|
|
"num_tokens": 41648805.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.352047252655029,
|
|
"epoch": 1.8910791847644504,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004641094935621919,
|
|
"loss": 4.8134,
|
|
"mean_token_accuracy": 0.2240023657679558,
|
|
"num_tokens": 41657356.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.305792379379272,
|
|
"epoch": 1.8914968259271634,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000464093361572361,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.22102490216493606,
|
|
"num_tokens": 41666525.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.270990991592408,
|
|
"epoch": 1.8919144670898764,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046407722627222326,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.2240580290555954,
|
|
"num_tokens": 41675113.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.447110366821289,
|
|
"epoch": 1.8923321082525892,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046406108766206103,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.21176548898220063,
|
|
"num_tokens": 41684283.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.34926404953003,
|
|
"epoch": 1.8927497494153025,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046404494574215683,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.22575774639844895,
|
|
"num_tokens": 41693751.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.2956214427948,
|
|
"epoch": 1.8931673905780153,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004640288005127933,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.22504038214683533,
|
|
"num_tokens": 41702776.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.294334793090821,
|
|
"epoch": 1.8935850317407283,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004640126519742532,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.22771501243114473,
|
|
"num_tokens": 41711567.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.382453966140747,
|
|
"epoch": 1.8940026729034414,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000463996500126819,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.225121209025383,
|
|
"num_tokens": 41720784.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.3246071338653564,
|
|
"epoch": 1.8944203140661544,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004639803449707737,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.2247438073158264,
|
|
"num_tokens": 41730775.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.301554441452026,
|
|
"epoch": 1.8948379552288674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046396418650639993,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.22948166429996492,
|
|
"num_tokens": 41740151.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.337240886688233,
|
|
"epoch": 1.8952555963915803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046394802473398065,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.22527604252099992,
|
|
"num_tokens": 41748469.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.356638956069946,
|
|
"epoch": 1.8956732375542935,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004639318596537986,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.21646025776863098,
|
|
"num_tokens": 41757771.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.2740966796875,
|
|
"epoch": 1.8960908787170063,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000463915691266137,
|
|
"loss": 4.7525,
|
|
"mean_token_accuracy": 0.2245550721883774,
|
|
"num_tokens": 41766979.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.237115478515625,
|
|
"epoch": 1.8965085198797194,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004638995195712789,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.22870079278945923,
|
|
"num_tokens": 41775094.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.398663425445557,
|
|
"epoch": 1.8969261610424324,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004638833445695073,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.2224266991019249,
|
|
"num_tokens": 41784608.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.374097156524658,
|
|
"epoch": 1.8973438022051452,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046386716626110544,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.22430313676595687,
|
|
"num_tokens": 41793789.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.365581083297729,
|
|
"epoch": 1.8977614433678585,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046385098464635645,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.2179864838719368,
|
|
"num_tokens": 41802928.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.4304098129272464,
|
|
"epoch": 1.8981790845305713,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004638347997255436,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.2153793156147003,
|
|
"num_tokens": 41812231.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.329684019088745,
|
|
"epoch": 1.8985967256932843,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004638186114989504,
|
|
"loss": 4.8161,
|
|
"mean_token_accuracy": 0.2257217586040497,
|
|
"num_tokens": 41820665.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.358800458908081,
|
|
"epoch": 1.8990143668559973,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004638024199668601,
|
|
"loss": 4.7704,
|
|
"mean_token_accuracy": 0.2257390722632408,
|
|
"num_tokens": 41829568.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.2973874568939205,
|
|
"epoch": 1.8994320080187104,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004637862251295561,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.2266514331102371,
|
|
"num_tokens": 41838360.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.298757839202881,
|
|
"epoch": 1.8998496491814234,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000463770026987322,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.22474293708801268,
|
|
"num_tokens": 41847050.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.3938579082489015,
|
|
"epoch": 1.9002672903441362,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046375382554044136,
|
|
"loss": 4.8039,
|
|
"mean_token_accuracy": 0.2217930570244789,
|
|
"num_tokens": 41856379.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.347357940673828,
|
|
"epoch": 1.9006849315068495,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004637376207891978,
|
|
"loss": 4.728,
|
|
"mean_token_accuracy": 0.23215217143297195,
|
|
"num_tokens": 41865139.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.329157543182373,
|
|
"epoch": 1.9011025726695623,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000463721412733875,
|
|
"loss": 4.7778,
|
|
"mean_token_accuracy": 0.22815433889627457,
|
|
"num_tokens": 41873955.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.320640516281128,
|
|
"epoch": 1.9015202138322753,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046370520137475673,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.22331796437501908,
|
|
"num_tokens": 41883771.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.353397703170776,
|
|
"epoch": 1.9019378549949884,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004636889867121268,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.21994677782058716,
|
|
"num_tokens": 41893411.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.291391372680664,
|
|
"epoch": 1.9023554961577012,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046367276874626894,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.2204860970377922,
|
|
"num_tokens": 41903612.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.3452873706817625,
|
|
"epoch": 1.9027731373204144,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004636565474774673,
|
|
"loss": 4.7382,
|
|
"mean_token_accuracy": 0.23231915086507798,
|
|
"num_tokens": 41912754.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.355625581741333,
|
|
"epoch": 1.9031907784831272,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046364032290600556,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.21641556471586226,
|
|
"num_tokens": 41922854.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.298409175872803,
|
|
"epoch": 1.9036084196458403,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000463624095032168,
|
|
"loss": 4.8169,
|
|
"mean_token_accuracy": 0.22753354012966157,
|
|
"num_tokens": 41932259.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.302412652969361,
|
|
"epoch": 1.9040260608085533,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046360786385623854,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.235756716132164,
|
|
"num_tokens": 41940833.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.3164284229278564,
|
|
"epoch": 1.9044437019712663,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004635916293785015,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.22957142144441606,
|
|
"num_tokens": 41949756.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.363380861282349,
|
|
"epoch": 1.9048613431339794,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004635753915992409,
|
|
"loss": 4.9024,
|
|
"mean_token_accuracy": 0.22380454391241072,
|
|
"num_tokens": 41959447.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.400155782699585,
|
|
"epoch": 1.9052789842966922,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000463559150518741,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.21438745260238648,
|
|
"num_tokens": 41968308.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.351159524917603,
|
|
"epoch": 1.9056966254594054,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004635429061372864,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.22704417109489441,
|
|
"num_tokens": 41976331.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.34469895362854,
|
|
"epoch": 1.9061142666221182,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046352665845516113,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.21670557856559752,
|
|
"num_tokens": 41985386.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.299899291992188,
|
|
"epoch": 1.9065319077848313,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004635104074726498,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.2269119590520859,
|
|
"num_tokens": 41993517.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.230906677246094,
|
|
"epoch": 1.9069495489475443,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004634941531900369,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.22150162905454635,
|
|
"num_tokens": 42002624.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.230711317062378,
|
|
"epoch": 1.9073671901102571,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046347789560760696,
|
|
"loss": 4.7645,
|
|
"mean_token_accuracy": 0.22811429053545,
|
|
"num_tokens": 42012128.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.28537073135376,
|
|
"epoch": 1.9077848312729704,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004634616347256446,
|
|
"loss": 4.6766,
|
|
"mean_token_accuracy": 0.2348896697163582,
|
|
"num_tokens": 42021243.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.350086641311646,
|
|
"epoch": 1.9082024724356832,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046344537054443443,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.2242290884256363,
|
|
"num_tokens": 42031397.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.435395669937134,
|
|
"epoch": 1.9086201135983962,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004634291030642613,
|
|
"loss": 4.8083,
|
|
"mean_token_accuracy": 0.22164314836263657,
|
|
"num_tokens": 42040560.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.27350001335144,
|
|
"epoch": 1.9090377547611093,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004634128322854098,
|
|
"loss": 4.7679,
|
|
"mean_token_accuracy": 0.22727012485265732,
|
|
"num_tokens": 42048824.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.315494585037231,
|
|
"epoch": 1.9094553959238223,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004633965582081649,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.21991240829229355,
|
|
"num_tokens": 42057460.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.363146543502808,
|
|
"epoch": 1.9098730370865353,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046338028083281154,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.21783364564180374,
|
|
"num_tokens": 42066829.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.411066246032715,
|
|
"epoch": 1.9102906782492481,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046336400015963453,
|
|
"loss": 4.8751,
|
|
"mean_token_accuracy": 0.22104400098323823,
|
|
"num_tokens": 42075518.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.3144361019134525,
|
|
"epoch": 1.9107083194119614,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000463347716188919,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.22480699867010118,
|
|
"num_tokens": 42083939.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.2901451110839846,
|
|
"epoch": 1.9111259605746742,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046333142892094996,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.23128153532743453,
|
|
"num_tokens": 42092229.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.361524343490601,
|
|
"epoch": 1.9115436017373872,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046331513835601263,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.21757018864154815,
|
|
"num_tokens": 42101876.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.323769855499267,
|
|
"epoch": 1.9119612429001003,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046329884449439207,
|
|
"loss": 4.7785,
|
|
"mean_token_accuracy": 0.2271995648741722,
|
|
"num_tokens": 42110710.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.422139978408813,
|
|
"epoch": 1.912378884062813,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046328254733637357,
|
|
"loss": 4.9179,
|
|
"mean_token_accuracy": 0.21120939999818802,
|
|
"num_tokens": 42120516.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.370522594451904,
|
|
"epoch": 1.9127965252255263,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004632662468822425,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.2245113432407379,
|
|
"num_tokens": 42129030.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.347481060028076,
|
|
"epoch": 1.9132141663882392,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004632499431322842,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.21856930553913118,
|
|
"num_tokens": 42138107.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.425073432922363,
|
|
"epoch": 1.9136318075509522,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000463233636086784,
|
|
"loss": 4.9264,
|
|
"mean_token_accuracy": 0.21923942416906356,
|
|
"num_tokens": 42147584.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.350834083557129,
|
|
"epoch": 1.9140494487136652,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046321732574602735,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.22339862883090972,
|
|
"num_tokens": 42156751.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.316245460510254,
|
|
"epoch": 1.9144670898763783,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046320101211029996,
|
|
"loss": 4.6855,
|
|
"mean_token_accuracy": 0.2344554141163826,
|
|
"num_tokens": 42165204.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.308655071258545,
|
|
"epoch": 1.9148847310390913,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046318469517988724,
|
|
"loss": 4.7875,
|
|
"mean_token_accuracy": 0.22494104951620103,
|
|
"num_tokens": 42174028.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.315175867080688,
|
|
"epoch": 1.915302372201804,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000463168374955075,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.22534334063529968,
|
|
"num_tokens": 42183658.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.393674516677857,
|
|
"epoch": 1.9157200133645174,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046315205143614873,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.22549811452627183,
|
|
"num_tokens": 42192509.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.415812397003174,
|
|
"epoch": 1.9161376545272302,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046313572462339437,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.21978492438793182,
|
|
"num_tokens": 42201919.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.358966732025147,
|
|
"epoch": 1.9165552956899432,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046311939451709776,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.21783962845802307,
|
|
"num_tokens": 42211027.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.407101249694824,
|
|
"epoch": 1.9169729368526562,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004631030611175447,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.21613630801439285,
|
|
"num_tokens": 42219677.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.441584491729737,
|
|
"epoch": 1.917390578015369,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046308672442502103,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.21712271720170975,
|
|
"num_tokens": 42228602.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.388484764099121,
|
|
"epoch": 1.9178082191780823,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000463070384439813,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.22277285307645797,
|
|
"num_tokens": 42238238.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.3454125881195065,
|
|
"epoch": 1.9182258603407951,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004630540411622064,
|
|
"loss": 4.8595,
|
|
"mean_token_accuracy": 0.2241231232881546,
|
|
"num_tokens": 42247499.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.299796199798584,
|
|
"epoch": 1.9186435015035082,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004630376945924875,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.23687113374471663,
|
|
"num_tokens": 42256761.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.425852537155151,
|
|
"epoch": 1.9190611426662212,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004630213447309424,
|
|
"loss": 4.8943,
|
|
"mean_token_accuracy": 0.2180474281311035,
|
|
"num_tokens": 42266062.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.358042907714844,
|
|
"epoch": 1.9194787838289342,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046300499157785725,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.22809043973684312,
|
|
"num_tokens": 42275510.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.360458946228027,
|
|
"epoch": 1.9198964249916473,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046298863513351854,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.21319668889045715,
|
|
"num_tokens": 42284905.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.329737186431885,
|
|
"epoch": 1.92031406615436,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046297227539821245,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.22839699387550355,
|
|
"num_tokens": 42294730.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.401728343963623,
|
|
"epoch": 1.9207317073170733,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004629559123722254,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.2245663210749626,
|
|
"num_tokens": 42304634.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.342271852493286,
|
|
"epoch": 1.9211493484797861,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046293954605584393,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.22318222522735595,
|
|
"num_tokens": 42313232.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.318824100494385,
|
|
"epoch": 1.9215669896424992,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004629231764493544,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.2228617936372757,
|
|
"num_tokens": 42322320.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.358847808837891,
|
|
"epoch": 1.9219846308052122,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004629068035530435,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.22365809082984925,
|
|
"num_tokens": 42331424.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.288037300109863,
|
|
"epoch": 1.922402271967925,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004628904273671978,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.21809837371110916,
|
|
"num_tokens": 42341759.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.262459993362427,
|
|
"epoch": 1.9228199131306383,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004628740478921041,
|
|
"loss": 4.7752,
|
|
"mean_token_accuracy": 0.2257354348897934,
|
|
"num_tokens": 42351000.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.355319499969482,
|
|
"epoch": 1.923237554293351,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046285766512804894,
|
|
"loss": 4.7822,
|
|
"mean_token_accuracy": 0.22748304158449173,
|
|
"num_tokens": 42360797.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.2946919918060305,
|
|
"epoch": 1.9236551954560641,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046284127907531925,
|
|
"loss": 4.6785,
|
|
"mean_token_accuracy": 0.2357401430606842,
|
|
"num_tokens": 42370067.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.365421009063721,
|
|
"epoch": 1.9240728366187771,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046282488973420187,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.2255071669816971,
|
|
"num_tokens": 42379857.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.378797245025635,
|
|
"epoch": 1.9244904777814902,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004628084971049837,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.22657367289066316,
|
|
"num_tokens": 42388776.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.275541210174561,
|
|
"epoch": 1.9249081189442032,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046279210118795175,
|
|
"loss": 4.6939,
|
|
"mean_token_accuracy": 0.2254546895623207,
|
|
"num_tokens": 42397362.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.33108959197998,
|
|
"epoch": 1.925325760106916,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000462775701983393,
|
|
"loss": 4.7716,
|
|
"mean_token_accuracy": 0.2186444252729416,
|
|
"num_tokens": 42405856.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.3664635181427,
|
|
"epoch": 1.9257434012696293,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004627592994915946,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.22033669352531432,
|
|
"num_tokens": 42415340.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.334213209152222,
|
|
"epoch": 1.926161042432342,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046274289371284357,
|
|
"loss": 4.7927,
|
|
"mean_token_accuracy": 0.2313535511493683,
|
|
"num_tokens": 42424113.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.319708681106567,
|
|
"epoch": 1.9265786835950551,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046272648464742733,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.23068034648895264,
|
|
"num_tokens": 42433833.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.334464597702026,
|
|
"epoch": 1.9269963247577682,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004627100722956329,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.23027272075414656,
|
|
"num_tokens": 42442652.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.299042558670044,
|
|
"epoch": 1.927413965920481,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046269365665774773,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.22560689449310303,
|
|
"num_tokens": 42452642.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.364777421951294,
|
|
"epoch": 1.9278316070831942,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046267723773405915,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.2288171872496605,
|
|
"num_tokens": 42460623.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.278945207595825,
|
|
"epoch": 1.928249248245907,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046266081552485467,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.22753577083349227,
|
|
"num_tokens": 42469963.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.40957293510437,
|
|
"epoch": 1.92866688940862,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046264439003042176,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.22149683386087418,
|
|
"num_tokens": 42479375.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.338114166259766,
|
|
"epoch": 1.9290845305713331,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046262796125104785,
|
|
"loss": 4.7363,
|
|
"mean_token_accuracy": 0.227643920481205,
|
|
"num_tokens": 42487837.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.339939022064209,
|
|
"epoch": 1.9295021717340461,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004626115291870206,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.22053870260715486,
|
|
"num_tokens": 42496666.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.326829671859741,
|
|
"epoch": 1.9299198128967592,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046259509383862784,
|
|
"loss": 4.7778,
|
|
"mean_token_accuracy": 0.21903801560401917,
|
|
"num_tokens": 42507195.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.389234209060669,
|
|
"epoch": 1.930337454059472,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004625786552061571,
|
|
"loss": 4.7201,
|
|
"mean_token_accuracy": 0.22944022715091705,
|
|
"num_tokens": 42515879.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.422722339630127,
|
|
"epoch": 1.9307550952221852,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004625622132898962,
|
|
"loss": 4.8863,
|
|
"mean_token_accuracy": 0.22190761417150498,
|
|
"num_tokens": 42524877.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.265072870254516,
|
|
"epoch": 1.931172736384898,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046254576809013297,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.2259867876768112,
|
|
"num_tokens": 42534019.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.380701732635498,
|
|
"epoch": 1.931590377547611,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004625293196071554,
|
|
"loss": 4.8642,
|
|
"mean_token_accuracy": 0.22040128260850905,
|
|
"num_tokens": 42543280.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.43496675491333,
|
|
"epoch": 1.9320080187103241,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004625128678412513,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.2165354683995247,
|
|
"num_tokens": 42553476.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.34492073059082,
|
|
"epoch": 1.932425659873037,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046249641279270866,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.22453453093767167,
|
|
"num_tokens": 42562502.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.330144548416138,
|
|
"epoch": 1.9328433010357502,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046247995446181575,
|
|
"loss": 4.7838,
|
|
"mean_token_accuracy": 0.22167977392673494,
|
|
"num_tokens": 42570947.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.345176267623901,
|
|
"epoch": 1.933260942198463,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004624634928488605,
|
|
"loss": 4.7612,
|
|
"mean_token_accuracy": 0.2218615159392357,
|
|
"num_tokens": 42579548.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.324291038513183,
|
|
"epoch": 1.933678583361176,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004624470279541312,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.2243815466761589,
|
|
"num_tokens": 42588006.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.434993505477905,
|
|
"epoch": 1.934096224523889,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046243055977791597,
|
|
"loss": 4.8503,
|
|
"mean_token_accuracy": 0.22247059345245362,
|
|
"num_tokens": 42597322.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.381885766983032,
|
|
"epoch": 1.934513865686602,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004624140883205033,
|
|
"loss": 4.7695,
|
|
"mean_token_accuracy": 0.22276908159255981,
|
|
"num_tokens": 42605942.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.363815021514893,
|
|
"epoch": 1.9349315068493151,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046239761358218135,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.2245242938399315,
|
|
"num_tokens": 42614870.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.378509140014648,
|
|
"epoch": 1.935349148012028,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004623811355632386,
|
|
"loss": 4.8031,
|
|
"mean_token_accuracy": 0.22399642765522004,
|
|
"num_tokens": 42624324.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.35901255607605,
|
|
"epoch": 1.9357667891747412,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046236465426396353,
|
|
"loss": 4.806,
|
|
"mean_token_accuracy": 0.2145366370677948,
|
|
"num_tokens": 42634120.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.314572286605835,
|
|
"epoch": 1.936184430337454,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004623481696846446,
|
|
"loss": 4.7427,
|
|
"mean_token_accuracy": 0.22749420255422592,
|
|
"num_tokens": 42642709.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.3261213302612305,
|
|
"epoch": 1.936602071500167,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004623316818255706,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.22027649581432343,
|
|
"num_tokens": 42652286.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.329609441757202,
|
|
"epoch": 1.93701971266288,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004623151906870299,
|
|
"loss": 4.7487,
|
|
"mean_token_accuracy": 0.22908680140972137,
|
|
"num_tokens": 42662195.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.408259582519531,
|
|
"epoch": 1.937437353825593,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004622986962693113,
|
|
"loss": 4.7821,
|
|
"mean_token_accuracy": 0.22139270901679992,
|
|
"num_tokens": 42671853.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.35794038772583,
|
|
"epoch": 1.9378549949883062,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004622821985727036,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.21898098438978195,
|
|
"num_tokens": 42681677.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.277017450332641,
|
|
"epoch": 1.938272636151019,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004622656975974956,
|
|
"loss": 4.6924,
|
|
"mean_token_accuracy": 0.22786052376031876,
|
|
"num_tokens": 42690686.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.307442045211792,
|
|
"epoch": 1.938690277313732,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046224919334397616,
|
|
"loss": 4.777,
|
|
"mean_token_accuracy": 0.2227792739868164,
|
|
"num_tokens": 42699967.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.348616743087769,
|
|
"epoch": 1.939107918476445,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046223268581243416,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.23049439191818238,
|
|
"num_tokens": 42708185.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.3301173686981205,
|
|
"epoch": 1.939525559639158,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046221617500315866,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.21941636353731156,
|
|
"num_tokens": 42717856.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.334117650985718,
|
|
"epoch": 1.939943200801871,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046219966091643865,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.22832887768745422,
|
|
"num_tokens": 42727036.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.353016757965088,
|
|
"epoch": 1.940360841964584,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046218314355256324,
|
|
"loss": 4.7687,
|
|
"mean_token_accuracy": 0.22796842008829116,
|
|
"num_tokens": 42736593.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.370742893218994,
|
|
"epoch": 1.9407784831272972,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004621666229118216,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.2289652094244957,
|
|
"num_tokens": 42745728.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.340032768249512,
|
|
"epoch": 1.94119612429001,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046215009899450296,
|
|
"loss": 4.7774,
|
|
"mean_token_accuracy": 0.22472720891237258,
|
|
"num_tokens": 42754638.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.3455750942230225,
|
|
"epoch": 1.941613765452723,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004621335718008965,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.2334648847579956,
|
|
"num_tokens": 42763474.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.393177700042725,
|
|
"epoch": 1.942031406615436,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046211704133129164,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.21493159532546996,
|
|
"num_tokens": 42772440.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.311613416671753,
|
|
"epoch": 1.9424490477781489,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046210050758597776,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.2349833220243454,
|
|
"num_tokens": 42780369.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.303716325759888,
|
|
"epoch": 1.9428666889408621,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046208397056524424,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.23223240822553634,
|
|
"num_tokens": 42789652.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.396537828445434,
|
|
"epoch": 1.943284330103575,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004620674302693807,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.21928228288888932,
|
|
"num_tokens": 42798067.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.35303373336792,
|
|
"epoch": 1.943701971266288,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004620508866986765,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.22323329299688338,
|
|
"num_tokens": 42806010.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.375158882141113,
|
|
"epoch": 1.944119612429001,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046203433985342145,
|
|
"loss": 4.7902,
|
|
"mean_token_accuracy": 0.22197066843509675,
|
|
"num_tokens": 42815596.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.311691427230835,
|
|
"epoch": 1.944537253591714,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004620177897339051,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.22842835783958435,
|
|
"num_tokens": 42824953.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.368335008621216,
|
|
"epoch": 1.944954894754427,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004620012363404173,
|
|
"loss": 4.8671,
|
|
"mean_token_accuracy": 0.21422386169433594,
|
|
"num_tokens": 42833737.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.431317901611328,
|
|
"epoch": 1.9453725359171399,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046198467967324783,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.2227482095360756,
|
|
"num_tokens": 42843674.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.309458827972412,
|
|
"epoch": 1.9457901770798531,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004619681197326863,
|
|
"loss": 4.691,
|
|
"mean_token_accuracy": 0.2302137181162834,
|
|
"num_tokens": 42852510.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.2241088390350345,
|
|
"epoch": 1.946207818242566,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004619515565190229,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.24196404814720154,
|
|
"num_tokens": 42860482.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.337975597381591,
|
|
"epoch": 1.946625459405279,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046193499003254737,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.21622670739889144,
|
|
"num_tokens": 42869413.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.445651197433472,
|
|
"epoch": 1.947043100567992,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004619184202735499,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.21692976951599122,
|
|
"num_tokens": 42879032.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.392802715301514,
|
|
"epoch": 1.9474607417307048,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004619018472423205,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.22952409237623214,
|
|
"num_tokens": 42887989.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.401260805130005,
|
|
"epoch": 1.947878382893418,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046188527093914925,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.21575934439897537,
|
|
"num_tokens": 42897268.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.360144567489624,
|
|
"epoch": 1.948296024056131,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004618686913643264,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.23058919310569764,
|
|
"num_tokens": 42906186.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.284453535079956,
|
|
"epoch": 1.948713665218844,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004618521085181421,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.22769676744937897,
|
|
"num_tokens": 42915457.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.392540788650512,
|
|
"epoch": 1.949131306381557,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046183552240088683,
|
|
"loss": 4.8604,
|
|
"mean_token_accuracy": 0.22080942392349243,
|
|
"num_tokens": 42925848.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.353642463684082,
|
|
"epoch": 1.94954894754427,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046181893301285075,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.22679605185985566,
|
|
"num_tokens": 42936084.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.287298631668091,
|
|
"epoch": 1.949966588706983,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004618023403543245,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.23349913358688354,
|
|
"num_tokens": 42945303.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.2532806396484375,
|
|
"epoch": 1.9503842298696958,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046178574442559835,
|
|
"loss": 4.7814,
|
|
"mean_token_accuracy": 0.21971433758735656,
|
|
"num_tokens": 42955144.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.380106449127197,
|
|
"epoch": 1.950801871032409,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004617691452269629,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.22762273401021957,
|
|
"num_tokens": 42964492.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.3367150783538815,
|
|
"epoch": 1.951219512195122,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004617525427587087,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.23009127080440522,
|
|
"num_tokens": 42973731.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.199634027481079,
|
|
"epoch": 1.951637153357835,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046173593702112655,
|
|
"loss": 4.6726,
|
|
"mean_token_accuracy": 0.24128359109163283,
|
|
"num_tokens": 42981892.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.30570240020752,
|
|
"epoch": 1.952054794520548,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000461719328014507,
|
|
"loss": 4.7312,
|
|
"mean_token_accuracy": 0.22858308106660843,
|
|
"num_tokens": 42990877.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.446249389648438,
|
|
"epoch": 1.9524724356832608,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046170271573914084,
|
|
"loss": 4.9138,
|
|
"mean_token_accuracy": 0.2159324824810028,
|
|
"num_tokens": 43001371.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.342397737503052,
|
|
"epoch": 1.952890076845974,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046168610019531894,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.22469851821660997,
|
|
"num_tokens": 43010651.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.370941829681397,
|
|
"epoch": 1.9533077180086869,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004616694813833322,
|
|
"loss": 4.7771,
|
|
"mean_token_accuracy": 0.22589681148529053,
|
|
"num_tokens": 43018883.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.3542852878570555,
|
|
"epoch": 1.9537253591714,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004616528593034713,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.22588163912296294,
|
|
"num_tokens": 43027760.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.323639059066773,
|
|
"epoch": 1.954143000334113,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004616362339560276,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.23140040934085845,
|
|
"num_tokens": 43038227.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.2689532279968265,
|
|
"epoch": 1.954560641496826,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046161960534129193,
|
|
"loss": 4.6547,
|
|
"mean_token_accuracy": 0.231761334836483,
|
|
"num_tokens": 43046792.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.303735971450806,
|
|
"epoch": 1.954978282659539,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004616029734595555,
|
|
"loss": 4.7417,
|
|
"mean_token_accuracy": 0.2206679791212082,
|
|
"num_tokens": 43055895.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.363902139663696,
|
|
"epoch": 1.9553959238222518,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004615863383111093,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.2201252669095993,
|
|
"num_tokens": 43065631.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.442596483230591,
|
|
"epoch": 1.955813564984965,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004615696998962447,
|
|
"loss": 4.883,
|
|
"mean_token_accuracy": 0.21817263066768647,
|
|
"num_tokens": 43074757.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.404494190216065,
|
|
"epoch": 1.9562312061476779,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004615530582152529,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.22788189798593522,
|
|
"num_tokens": 43084472.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.347333240509033,
|
|
"epoch": 1.956648847310391,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004615364132684253,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.21384414434432983,
|
|
"num_tokens": 43092726.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.323983240127563,
|
|
"epoch": 1.957066488473104,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004615197650560532,
|
|
"loss": 4.7511,
|
|
"mean_token_accuracy": 0.22194042652845383,
|
|
"num_tokens": 43101481.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.345565938949585,
|
|
"epoch": 1.9574841296358167,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004615031135784282,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.2254907250404358,
|
|
"num_tokens": 43110484.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.378557252883911,
|
|
"epoch": 1.95790177079853,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046148645883584155,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.2177823692560196,
|
|
"num_tokens": 43121532.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.33486590385437,
|
|
"epoch": 1.9583194119612428,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004614698008285851,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.23499378561973572,
|
|
"num_tokens": 43130976.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.3532017230987545,
|
|
"epoch": 1.9587370531239559,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046145313955695027,
|
|
"loss": 4.8491,
|
|
"mean_token_accuracy": 0.2175015315413475,
|
|
"num_tokens": 43139907.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.424727916717529,
|
|
"epoch": 1.9591546942866689,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004614364750212288,
|
|
"loss": 4.8827,
|
|
"mean_token_accuracy": 0.21857621222734452,
|
|
"num_tokens": 43149141.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.400527477264404,
|
|
"epoch": 1.959572335449382,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046141980722171246,
|
|
"loss": 4.8183,
|
|
"mean_token_accuracy": 0.22830750942230224,
|
|
"num_tokens": 43158206.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.308787441253662,
|
|
"epoch": 1.959989976612095,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046140313615869287,
|
|
"loss": 4.8489,
|
|
"mean_token_accuracy": 0.22200627028942108,
|
|
"num_tokens": 43168365.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.269458436965943,
|
|
"epoch": 1.9604076177748078,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046138646183246213,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.23065678477287294,
|
|
"num_tokens": 43176907.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.307368469238281,
|
|
"epoch": 1.960825258937521,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000461369784243312,
|
|
"loss": 4.6882,
|
|
"mean_token_accuracy": 0.23160689175128937,
|
|
"num_tokens": 43186978.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.312923574447632,
|
|
"epoch": 1.9612429001002338,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046135310339153455,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.22573700696229934,
|
|
"num_tokens": 43196502.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.3935622215271,
|
|
"epoch": 1.9616605412629469,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004613364192774216,
|
|
"loss": 4.8928,
|
|
"mean_token_accuracy": 0.21426387876272202,
|
|
"num_tokens": 43205555.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.377105665206909,
|
|
"epoch": 1.96207818242566,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046131973190126536,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.22822213768959046,
|
|
"num_tokens": 43214043.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.399217176437378,
|
|
"epoch": 1.9624958235883727,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046130304126335795,
|
|
"loss": 4.8442,
|
|
"mean_token_accuracy": 0.21499679535627364,
|
|
"num_tokens": 43223483.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.363875818252564,
|
|
"epoch": 1.962913464751086,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004612863473639915,
|
|
"loss": 4.787,
|
|
"mean_token_accuracy": 0.22704787403345109,
|
|
"num_tokens": 43231962.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.3165148258209225,
|
|
"epoch": 1.9633311059137988,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046126965020345834,
|
|
"loss": 4.786,
|
|
"mean_token_accuracy": 0.23162612468004226,
|
|
"num_tokens": 43240532.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.285922622680664,
|
|
"epoch": 1.9637487470765118,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004612529497820508,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.23055894523859025,
|
|
"num_tokens": 43249867.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.348906373977661,
|
|
"epoch": 1.9641663882392248,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004612362461000611,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.22053875923156738,
|
|
"num_tokens": 43259393.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.459563255310059,
|
|
"epoch": 1.9645840294019379,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046121953915778175,
|
|
"loss": 4.8719,
|
|
"mean_token_accuracy": 0.2218589588999748,
|
|
"num_tokens": 43269012.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.391697835922241,
|
|
"epoch": 1.965001670564651,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004612028289555052,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.22269368022680283,
|
|
"num_tokens": 43278032.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.3459821224212645,
|
|
"epoch": 1.9654193117273637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046118611549352407,
|
|
"loss": 4.8051,
|
|
"mean_token_accuracy": 0.225765198469162,
|
|
"num_tokens": 43287352.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.44348464012146,
|
|
"epoch": 1.965836952890077,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004611693987721308,
|
|
"loss": 4.8628,
|
|
"mean_token_accuracy": 0.21881084740161896,
|
|
"num_tokens": 43297048.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.323383712768555,
|
|
"epoch": 1.9662545940527898,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046115267879161823,
|
|
"loss": 4.7652,
|
|
"mean_token_accuracy": 0.2324044808745384,
|
|
"num_tokens": 43306461.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.348546314239502,
|
|
"epoch": 1.9666722352155028,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046113595555227885,
|
|
"loss": 4.7958,
|
|
"mean_token_accuracy": 0.22175424546003342,
|
|
"num_tokens": 43315906.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.399818086624146,
|
|
"epoch": 1.9670898763782159,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004611192290544055,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.22215022146701813,
|
|
"num_tokens": 43325433.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.3897120475769045,
|
|
"epoch": 1.9675075175409287,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046110249929829104,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.2199855551123619,
|
|
"num_tokens": 43333510.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.357300710678101,
|
|
"epoch": 1.967925158703642,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004610857662842283,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.22696593105793,
|
|
"num_tokens": 43342985.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.4229988098144535,
|
|
"epoch": 1.9683427998663547,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004610690300125103,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.2317747876048088,
|
|
"num_tokens": 43352894.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.366800689697266,
|
|
"epoch": 1.9687604410290678,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046105229048342994,
|
|
"loss": 4.8096,
|
|
"mean_token_accuracy": 0.21841714084148406,
|
|
"num_tokens": 43362667.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.347306585311889,
|
|
"epoch": 1.9691780821917808,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046103554769728026,
|
|
"loss": 4.7742,
|
|
"mean_token_accuracy": 0.22477197349071504,
|
|
"num_tokens": 43372212.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.303798961639404,
|
|
"epoch": 1.9695957233544938,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004610188016543544,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.23216002732515334,
|
|
"num_tokens": 43381958.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.368860960006714,
|
|
"epoch": 1.9700133645172069,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046100205235494554,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.22106949836015702,
|
|
"num_tokens": 43391641.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.384839963912964,
|
|
"epoch": 1.9704310056799197,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046098529979934677,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.22264018505811692,
|
|
"num_tokens": 43401261.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.307862949371338,
|
|
"epoch": 1.970848646842633,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004609685439878515,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.22495732009410857,
|
|
"num_tokens": 43409829.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.319575691223145,
|
|
"epoch": 1.9712662880053458,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000460951784920753,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.23175143748521804,
|
|
"num_tokens": 43418536.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.353875303268433,
|
|
"epoch": 1.9716839291680588,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004609350225983447,
|
|
"loss": 4.6987,
|
|
"mean_token_accuracy": 0.23075971901416778,
|
|
"num_tokens": 43427667.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.357557010650635,
|
|
"epoch": 1.9721015703307718,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046091825702092,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.2281002253293991,
|
|
"num_tokens": 43436986.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.3688063621521,
|
|
"epoch": 1.9725192114934846,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046090148818877244,
|
|
"loss": 4.8663,
|
|
"mean_token_accuracy": 0.2155781403183937,
|
|
"num_tokens": 43446969.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.379524993896484,
|
|
"epoch": 1.972936852656198,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004608847161021955,
|
|
"loss": 4.8894,
|
|
"mean_token_accuracy": 0.22230955809354783,
|
|
"num_tokens": 43456160.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.425421571731567,
|
|
"epoch": 1.9733544938189107,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000460867940761483,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.22047794610261917,
|
|
"num_tokens": 43465767.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.426051664352417,
|
|
"epoch": 1.9737721349816237,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004608511621669283,
|
|
"loss": 4.8413,
|
|
"mean_token_accuracy": 0.22308342158794403,
|
|
"num_tokens": 43474493.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.339240407943725,
|
|
"epoch": 1.9741897761443368,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046083438031882534,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.22024312913417815,
|
|
"num_tokens": 43483410.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.31900577545166,
|
|
"epoch": 1.9746074173070498,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004608175952174679,
|
|
"loss": 4.7173,
|
|
"mean_token_accuracy": 0.23079673945903778,
|
|
"num_tokens": 43492532.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.299218988418579,
|
|
"epoch": 1.9750250584697628,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004608008068631498,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.23556359261274337,
|
|
"num_tokens": 43501282.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.3601525783538815,
|
|
"epoch": 1.9754426996324757,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046078401525616493,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.21409368962049485,
|
|
"num_tokens": 43510355.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.351290845870972,
|
|
"epoch": 1.975860340795189,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004607672203968072,
|
|
"loss": 4.7724,
|
|
"mean_token_accuracy": 0.22691874504089354,
|
|
"num_tokens": 43519179.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.3540184020996096,
|
|
"epoch": 1.9762779819579017,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046075042228537074,
|
|
"loss": 4.8145,
|
|
"mean_token_accuracy": 0.22037032395601272,
|
|
"num_tokens": 43528306.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.466492557525635,
|
|
"epoch": 1.9766956231206148,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004607336209221494,
|
|
"loss": 4.918,
|
|
"mean_token_accuracy": 0.2143603503704071,
|
|
"num_tokens": 43537075.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.337781667709351,
|
|
"epoch": 1.9771132642833278,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004607168163074376,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.22612891644239425,
|
|
"num_tokens": 43545356.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.392222881317139,
|
|
"epoch": 1.9775309054460406,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004607000084415294,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.22047252357006072,
|
|
"num_tokens": 43555012.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.405001592636109,
|
|
"epoch": 1.9779485466087539,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046068319732471894,
|
|
"loss": 4.8802,
|
|
"mean_token_accuracy": 0.21619620472192763,
|
|
"num_tokens": 43565245.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.455084228515625,
|
|
"epoch": 1.9783661877714667,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004606663829573006,
|
|
"loss": 4.9485,
|
|
"mean_token_accuracy": 0.2132022723555565,
|
|
"num_tokens": 43574246.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.240306615829468,
|
|
"epoch": 1.9787838289341797,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004606495653395688,
|
|
"loss": 4.5962,
|
|
"mean_token_accuracy": 0.2412810355424881,
|
|
"num_tokens": 43582494.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.370383787155151,
|
|
"epoch": 1.9792014700968927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004606327444718179,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.22266065925359727,
|
|
"num_tokens": 43593289.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.366757106781006,
|
|
"epoch": 1.9796191112596058,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004606159203543423,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.227103890478611,
|
|
"num_tokens": 43602062.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.402761650085449,
|
|
"epoch": 1.9800367524223188,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004605990929874366,
|
|
"loss": 4.8493,
|
|
"mean_token_accuracy": 0.22035929709672927,
|
|
"num_tokens": 43610830.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.387441968917846,
|
|
"epoch": 1.9804543935850316,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004605822623713954,
|
|
"loss": 4.8181,
|
|
"mean_token_accuracy": 0.2208885669708252,
|
|
"num_tokens": 43619656.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.363733100891113,
|
|
"epoch": 1.9808720347477449,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046056542850651333,
|
|
"loss": 4.8321,
|
|
"mean_token_accuracy": 0.22701594233512878,
|
|
"num_tokens": 43629727.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.397048377990723,
|
|
"epoch": 1.9812896759104577,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000460548591393085,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.22830315083265304,
|
|
"num_tokens": 43638532.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.372563219070434,
|
|
"epoch": 1.9817073170731707,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046053175103140533,
|
|
"loss": 4.8755,
|
|
"mean_token_accuracy": 0.23102624714374542,
|
|
"num_tokens": 43647679.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.38691463470459,
|
|
"epoch": 1.9821249582358837,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046051490742176894,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.22098904401063918,
|
|
"num_tokens": 43656340.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.336601448059082,
|
|
"epoch": 1.9825425993985966,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004604980605644708,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.22303288280963898,
|
|
"num_tokens": 43665721.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.354690980911255,
|
|
"epoch": 1.9829602405613098,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004604812104598059,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.22697769850492477,
|
|
"num_tokens": 43674640.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.383276748657226,
|
|
"epoch": 1.9833778817240226,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004604643571080691,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.21847916543483734,
|
|
"num_tokens": 43683080.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.336496067047119,
|
|
"epoch": 1.9837955228867357,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046044750050955546,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.22969642877578736,
|
|
"num_tokens": 43691259.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.349008560180664,
|
|
"epoch": 1.9842131640494487,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046043064066456015,
|
|
"loss": 4.7782,
|
|
"mean_token_accuracy": 0.23050918132066728,
|
|
"num_tokens": 43699881.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.339365434646607,
|
|
"epoch": 1.9846308052121617,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046041377757337826,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.22638358771800995,
|
|
"num_tokens": 43708742.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.368357181549072,
|
|
"epoch": 1.9850484463748748,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046039691123630496,
|
|
"loss": 4.7704,
|
|
"mean_token_accuracy": 0.21993174850940705,
|
|
"num_tokens": 43718450.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.326651525497437,
|
|
"epoch": 1.9854660875375876,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046038004165363554,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.22169008404016494,
|
|
"num_tokens": 43728340.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.27455472946167,
|
|
"epoch": 1.9858837287003008,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046036316882566545,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.2220079183578491,
|
|
"num_tokens": 43737287.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.294991874694825,
|
|
"epoch": 1.9863013698630136,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046034629275268997,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.22813462615013122,
|
|
"num_tokens": 43745899.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.4410545349121096,
|
|
"epoch": 1.9867190110257267,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046032941343500443,
|
|
"loss": 4.8663,
|
|
"mean_token_accuracy": 0.21077335476875306,
|
|
"num_tokens": 43755109.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.349912214279175,
|
|
"epoch": 1.9871366521884397,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046031253087290455,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.23040236681699752,
|
|
"num_tokens": 43764216.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.346527767181397,
|
|
"epoch": 1.9875542933511525,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046029564506668567,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.21784185171127318,
|
|
"num_tokens": 43773267.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.420564031600952,
|
|
"epoch": 1.9879719345138658,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046027875601664355,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.21533062309026718,
|
|
"num_tokens": 43782558.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.423683166503906,
|
|
"epoch": 1.9883895756765786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004602618637230737,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.21542607247829437,
|
|
"num_tokens": 43791861.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.370199871063233,
|
|
"epoch": 1.9888072168392918,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000460244968186272,
|
|
"loss": 4.7372,
|
|
"mean_token_accuracy": 0.2258359283208847,
|
|
"num_tokens": 43801064.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.3173987865448,
|
|
"epoch": 1.9892248580020047,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046022806940653415,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.23230403810739517,
|
|
"num_tokens": 43810159.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.384043836593628,
|
|
"epoch": 1.9896424991647177,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000460211167384156,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.21869630813598634,
|
|
"num_tokens": 43819056.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.369189023971558,
|
|
"epoch": 1.9900601403274307,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046019426211943334,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.22987437695264817,
|
|
"num_tokens": 43828024.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.367882537841797,
|
|
"epoch": 1.9904777814901435,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004601773536126623,
|
|
"loss": 4.697,
|
|
"mean_token_accuracy": 0.23517916947603226,
|
|
"num_tokens": 43836915.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.326673316955566,
|
|
"epoch": 1.9908954226528568,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004601604418641387,
|
|
"loss": 4.7732,
|
|
"mean_token_accuracy": 0.22896008044481278,
|
|
"num_tokens": 43845661.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.379279708862304,
|
|
"epoch": 1.9913130638155696,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046014352687415866,
|
|
"loss": 4.8532,
|
|
"mean_token_accuracy": 0.21999939382076264,
|
|
"num_tokens": 43854876.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.313997411727906,
|
|
"epoch": 1.9917307049782826,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046012660864301846,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.22910288870334625,
|
|
"num_tokens": 43864750.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.385338830947876,
|
|
"epoch": 1.9921483461409957,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046010968717101404,
|
|
"loss": 4.8546,
|
|
"mean_token_accuracy": 0.21796601563692092,
|
|
"num_tokens": 43874889.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.341731834411621,
|
|
"epoch": 1.9925659873037087,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046009276245844176,
|
|
"loss": 4.7707,
|
|
"mean_token_accuracy": 0.21826266199350358,
|
|
"num_tokens": 43884462.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.335390090942383,
|
|
"epoch": 1.9929836284664217,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004600758345055979,
|
|
"loss": 4.7785,
|
|
"mean_token_accuracy": 0.22455381006002426,
|
|
"num_tokens": 43893739.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.379033041000366,
|
|
"epoch": 1.9934012696291346,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046005890331277875,
|
|
"loss": 4.8284,
|
|
"mean_token_accuracy": 0.22736723423004152,
|
|
"num_tokens": 43904172.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.382718944549561,
|
|
"epoch": 1.9938189107918478,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004600419688802807,
|
|
"loss": 4.8346,
|
|
"mean_token_accuracy": 0.22194003611803054,
|
|
"num_tokens": 43912824.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.3358642101287845,
|
|
"epoch": 1.9942365519545606,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046002503120840037,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.2225430950522423,
|
|
"num_tokens": 43921704.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.338908100128174,
|
|
"epoch": 1.9946541931172737,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000460008090297434,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.2249062955379486,
|
|
"num_tokens": 43930400.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.292525005340576,
|
|
"epoch": 1.9950718342799867,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045999114614767847,
|
|
"loss": 4.6933,
|
|
"mean_token_accuracy": 0.22569165378808975,
|
|
"num_tokens": 43939623.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.346911430358887,
|
|
"epoch": 1.9954894754426995,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004599741987594302,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.22033018618822098,
|
|
"num_tokens": 43948902.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.3240883350372314,
|
|
"epoch": 1.9959071166054128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004599572481329859,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.22294728457927704,
|
|
"num_tokens": 43958747.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.404444074630737,
|
|
"epoch": 1.9963247577681256,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004599402942686423,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.2172431766986847,
|
|
"num_tokens": 43968766.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.350545167922974,
|
|
"epoch": 1.9967423989308386,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004599233371666963,
|
|
"loss": 4.758,
|
|
"mean_token_accuracy": 0.22965958714485168,
|
|
"num_tokens": 43978212.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.349212408065796,
|
|
"epoch": 1.9971600400935516,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004599063768274447,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.22367707639932632,
|
|
"num_tokens": 43987167.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.351185846328735,
|
|
"epoch": 1.9975776812562647,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004598894132511843,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.22908274978399276,
|
|
"num_tokens": 43995405.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.353074312210083,
|
|
"epoch": 1.9979953224189777,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004598724464382123,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.22818587869405746,
|
|
"num_tokens": 44004062.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.3779853820800785,
|
|
"epoch": 1.9984129635816905,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045985547638882553,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.21994068026542662,
|
|
"num_tokens": 44013911.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.3707358837127686,
|
|
"epoch": 1.9988306047444038,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045983850310332117,
|
|
"loss": 4.8218,
|
|
"mean_token_accuracy": 0.2233565181493759,
|
|
"num_tokens": 44023366.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.2860761165618895,
|
|
"epoch": 1.9992482459071166,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004598215265819963,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.2328706979751587,
|
|
"num_tokens": 44031996.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.299000358581543,
|
|
"epoch": 1.9996658870698296,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004598045468251481,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.22866690456867217,
|
|
"num_tokens": 44041474.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.406021022796631,
|
|
"epoch": 2.0000835282325427,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004597875638330739,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.22545210719108583,
|
|
"num_tokens": 44050213.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.314444637298584,
|
|
"epoch": 2.0005011693952555,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045977057760607096,
|
|
"loss": 4.5896,
|
|
"mean_token_accuracy": 0.23973151296377182,
|
|
"num_tokens": 44058686.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.317176008224488,
|
|
"epoch": 2.0009188105579687,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004597535881444366,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.22892126441001892,
|
|
"num_tokens": 44068316.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.342790651321411,
|
|
"epoch": 2.0013364517206815,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045973659544846834,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.2324340298771858,
|
|
"num_tokens": 44077474.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.241012763977051,
|
|
"epoch": 2.001754092883395,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004597195995184637,
|
|
"loss": 4.6046,
|
|
"mean_token_accuracy": 0.24121250063180924,
|
|
"num_tokens": 44086334.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.380445528030395,
|
|
"epoch": 2.0021717340461076,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004597026003547201,
|
|
"loss": 4.7564,
|
|
"mean_token_accuracy": 0.22137524634599687,
|
|
"num_tokens": 44095543.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.414646291732788,
|
|
"epoch": 2.0025893752088204,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045968559795753493,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.22583145201206206,
|
|
"num_tokens": 44105162.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.347655344009399,
|
|
"epoch": 2.0030070163715337,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045966859232720626,
|
|
"loss": 4.7289,
|
|
"mean_token_accuracy": 0.22575407177209855,
|
|
"num_tokens": 44114087.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.455414772033691,
|
|
"epoch": 2.0034246575342465,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004596515834640316,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.22144805341959,
|
|
"num_tokens": 44123186.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.357424211502075,
|
|
"epoch": 2.0038422986969597,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004596345713683086,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.2321697100996971,
|
|
"num_tokens": 44132126.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.388561058044433,
|
|
"epoch": 2.0042599398596725,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045961755604033536,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.22440215349197387,
|
|
"num_tokens": 44141703.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.375655031204223,
|
|
"epoch": 2.0046775810223854,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004596005374804094,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.22794465720653534,
|
|
"num_tokens": 44150512.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.0046775810223854,
|
|
"eval_entropy": 5.059165792327845,
|
|
"eval_loss": 4.768747806549072,
|
|
"eval_mean_token_accuracy": 0.2366941027111281,
|
|
"eval_num_tokens": 44150512.0,
|
|
"eval_runtime": 20.8594,
|
|
"eval_samples_per_second": 1810.363,
|
|
"eval_steps_per_second": 226.325,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 5.392633152008057,
|
|
"epoch": 2.0050952221850986,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045958351568882883,
|
|
"loss": 4.7007,
|
|
"mean_token_accuracy": 0.22370530664920807,
|
|
"num_tokens": 44160209.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 5.380887889862061,
|
|
"epoch": 2.0055128633478114,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004595664906658917,
|
|
"loss": 4.7376,
|
|
"mean_token_accuracy": 0.2300131395459175,
|
|
"num_tokens": 44169005.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 5.346474552154541,
|
|
"epoch": 2.0059305045105247,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045954946241189606,
|
|
"loss": 4.7906,
|
|
"mean_token_accuracy": 0.21820925325155258,
|
|
"num_tokens": 44178750.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 5.3984386920928955,
|
|
"epoch": 2.0063481456732375,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045953243092713986,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.2189948305487633,
|
|
"num_tokens": 44188268.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 5.347973966598511,
|
|
"epoch": 2.0067657868359507,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045951539621192137,
|
|
"loss": 4.681,
|
|
"mean_token_accuracy": 0.232268089056015,
|
|
"num_tokens": 44197599.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 5.353358507156372,
|
|
"epoch": 2.0071834279986636,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004594983582665387,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.2212505057454109,
|
|
"num_tokens": 44207971.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 5.438537693023681,
|
|
"epoch": 2.0076010691613764,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004594813170912902,
|
|
"loss": 4.7819,
|
|
"mean_token_accuracy": 0.219252747297287,
|
|
"num_tokens": 44217387.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 5.392335033416748,
|
|
"epoch": 2.0080187103240896,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045946427268647424,
|
|
"loss": 4.7344,
|
|
"mean_token_accuracy": 0.2283961832523346,
|
|
"num_tokens": 44226103.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 5.330778121948242,
|
|
"epoch": 2.0084363514868024,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045944722505238914,
|
|
"loss": 4.7079,
|
|
"mean_token_accuracy": 0.22264567762613297,
|
|
"num_tokens": 44236081.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 5.383838939666748,
|
|
"epoch": 2.0088539926495157,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045943017418933324,
|
|
"loss": 4.7378,
|
|
"mean_token_accuracy": 0.22357877790927888,
|
|
"num_tokens": 44245934.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 5.340365028381347,
|
|
"epoch": 2.0092716338122285,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004594131200976053,
|
|
"loss": 4.7228,
|
|
"mean_token_accuracy": 0.22944151163101195,
|
|
"num_tokens": 44255629.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 5.312185049057007,
|
|
"epoch": 2.0096892749749413,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045939606277750356,
|
|
"loss": 4.6705,
|
|
"mean_token_accuracy": 0.2328661262989044,
|
|
"num_tokens": 44264954.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 5.291031360626221,
|
|
"epoch": 2.0101069161376546,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004593790022293269,
|
|
"loss": 4.6766,
|
|
"mean_token_accuracy": 0.2331065982580185,
|
|
"num_tokens": 44273739.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 5.3558924198150635,
|
|
"epoch": 2.0105245573003674,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004593619384533738,
|
|
"loss": 4.8358,
|
|
"mean_token_accuracy": 0.21633225977420806,
|
|
"num_tokens": 44283365.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 5.378579330444336,
|
|
"epoch": 2.0109421984630806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045934487144994306,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.22665239572525026,
|
|
"num_tokens": 44292257.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 5.495556259155274,
|
|
"epoch": 2.0113598396257935,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045932780121933354,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.22489568144083022,
|
|
"num_tokens": 44302539.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 5.3450439453125,
|
|
"epoch": 2.0117774807885067,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004593107277618439,
|
|
"loss": 4.6973,
|
|
"mean_token_accuracy": 0.2244582623243332,
|
|
"num_tokens": 44311812.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 5.2703102111816404,
|
|
"epoch": 2.0121951219512195,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004592936510777731,
|
|
"loss": 4.702,
|
|
"mean_token_accuracy": 0.23255476355552673,
|
|
"num_tokens": 44321015.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 5.4364255428314205,
|
|
"epoch": 2.0126127631139323,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045927657116742016,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.2174728810787201,
|
|
"num_tokens": 44330066.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 5.413190317153931,
|
|
"epoch": 2.0130304042766456,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000459259488031084,
|
|
"loss": 4.8633,
|
|
"mean_token_accuracy": 0.22233502864837645,
|
|
"num_tokens": 44339716.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 5.301387977600098,
|
|
"epoch": 2.0134480454393584,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004592424016690637,
|
|
"loss": 4.6111,
|
|
"mean_token_accuracy": 0.23213190883398055,
|
|
"num_tokens": 44348340.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 5.269318675994873,
|
|
"epoch": 2.0138656866020717,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045922531208165843,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.22517029941082,
|
|
"num_tokens": 44358045.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 5.367703771591186,
|
|
"epoch": 2.0142833277647845,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004592082192691673,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.23403931111097337,
|
|
"num_tokens": 44366962.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 5.2942033290863035,
|
|
"epoch": 2.0147009689274973,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045919112323188955,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.23539581447839736,
|
|
"num_tokens": 44376178.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 5.416565227508545,
|
|
"epoch": 2.0151186100902105,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004591740239701244,
|
|
"loss": 4.738,
|
|
"mean_token_accuracy": 0.22547851055860518,
|
|
"num_tokens": 44385271.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 5.3520771026611325,
|
|
"epoch": 2.0155362512529233,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045915692148417136,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.23977913111448287,
|
|
"num_tokens": 44394900.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 5.298025226593017,
|
|
"epoch": 2.0159538924156366,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004591398157743297,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.22924830317497252,
|
|
"num_tokens": 44403812.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 5.302218198776245,
|
|
"epoch": 2.0163715335783494,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045912270684089903,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.22945373207330705,
|
|
"num_tokens": 44413301.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 5.3325599193572994,
|
|
"epoch": 2.0167891747410627,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004591055946841786,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.23488772809505462,
|
|
"num_tokens": 44422334.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 5.4263622760772705,
|
|
"epoch": 2.0172068159037755,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045908847930446815,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.2161575198173523,
|
|
"num_tokens": 44432914.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 5.37202787399292,
|
|
"epoch": 2.0176244570664883,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004590713607020674,
|
|
"loss": 4.6604,
|
|
"mean_token_accuracy": 0.23862095326185226,
|
|
"num_tokens": 44442372.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 5.326254749298096,
|
|
"epoch": 2.0180420982292016,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045905423887727584,
|
|
"loss": 4.6363,
|
|
"mean_token_accuracy": 0.23546261638402938,
|
|
"num_tokens": 44450866.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 5.3203295230865475,
|
|
"epoch": 2.0184597393919144,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004590371138303933,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.2350994259119034,
|
|
"num_tokens": 44460224.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 5.355734920501709,
|
|
"epoch": 2.0188773805546276,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004590199855617195,
|
|
"loss": 4.7098,
|
|
"mean_token_accuracy": 0.22954981476068498,
|
|
"num_tokens": 44469231.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 5.356402492523193,
|
|
"epoch": 2.0192950217173404,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004590028540715544,
|
|
"loss": 4.6714,
|
|
"mean_token_accuracy": 0.2327609807252884,
|
|
"num_tokens": 44478415.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 5.34701623916626,
|
|
"epoch": 2.0197126628800532,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004589857193601978,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.2326667070388794,
|
|
"num_tokens": 44486648.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 5.341733121871949,
|
|
"epoch": 2.0201303040427665,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045896858142794976,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.2263301506638527,
|
|
"num_tokens": 44495111.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 5.336205339431762,
|
|
"epoch": 2.0205479452054793,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004589514402751103,
|
|
"loss": 4.6649,
|
|
"mean_token_accuracy": 0.2364634707570076,
|
|
"num_tokens": 44504021.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 5.390154457092285,
|
|
"epoch": 2.0209655863681926,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004589342959019794,
|
|
"loss": 4.7193,
|
|
"mean_token_accuracy": 0.22586629986763002,
|
|
"num_tokens": 44513337.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 5.31166558265686,
|
|
"epoch": 2.0213832275309054,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004589171483088572,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.23344297260046004,
|
|
"num_tokens": 44522206.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 5.315387105941772,
|
|
"epoch": 2.0218008686936186,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000458899997496044,
|
|
"loss": 4.8461,
|
|
"mean_token_accuracy": 0.22708484530448914,
|
|
"num_tokens": 44531030.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 5.391887140274048,
|
|
"epoch": 2.0222185098563314,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045888284346384003,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.2284735321998596,
|
|
"num_tokens": 44539844.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 5.379514503479004,
|
|
"epoch": 2.0226361510190443,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004588656862125454,
|
|
"loss": 4.6704,
|
|
"mean_token_accuracy": 0.24087538719177246,
|
|
"num_tokens": 44548420.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 5.3452263355255125,
|
|
"epoch": 2.0230537921817575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004588485257424608,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.23472421616315842,
|
|
"num_tokens": 44557597.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 5.312316417694092,
|
|
"epoch": 2.0234714333444703,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004588313620538863,
|
|
"loss": 4.6885,
|
|
"mean_token_accuracy": 0.2316751703619957,
|
|
"num_tokens": 44566281.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 5.391655015945434,
|
|
"epoch": 2.0238890745071836,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004588141951471226,
|
|
"loss": 4.8199,
|
|
"mean_token_accuracy": 0.221091128885746,
|
|
"num_tokens": 44575937.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 5.393732690811158,
|
|
"epoch": 2.0243067156698964,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045879702502247014,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.23324442356824876,
|
|
"num_tokens": 44585373.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 5.396694231033325,
|
|
"epoch": 2.024724356832609,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004587798516802296,
|
|
"loss": 4.7674,
|
|
"mean_token_accuracy": 0.2297140821814537,
|
|
"num_tokens": 44594526.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 5.391822624206543,
|
|
"epoch": 2.0251419979953225,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045876267512070146,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.2306074917316437,
|
|
"num_tokens": 44603128.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 5.355180501937866,
|
|
"epoch": 2.0255596391580353,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045874549534418644,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.22582618296146392,
|
|
"num_tokens": 44612492.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 5.344970226287842,
|
|
"epoch": 2.0259772803207485,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004587283123509855,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.22530316561460495,
|
|
"num_tokens": 44621086.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 5.342679882049561,
|
|
"epoch": 2.0263949214834613,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004587111261413992,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.22765694707632064,
|
|
"num_tokens": 44629813.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 5.387208127975464,
|
|
"epoch": 2.0268125626461746,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004586939367157285,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.21879158467054366,
|
|
"num_tokens": 44638888.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 5.32710075378418,
|
|
"epoch": 2.0272302038088874,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045867674407427435,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.23529054820537568,
|
|
"num_tokens": 44647617.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 5.3682421207427975,
|
|
"epoch": 2.0276478449716,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045865954821733767,
|
|
"loss": 4.6822,
|
|
"mean_token_accuracy": 0.227234648168087,
|
|
"num_tokens": 44657456.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 5.338464736938477,
|
|
"epoch": 2.0280654861343135,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045864234914521956,
|
|
"loss": 4.7047,
|
|
"mean_token_accuracy": 0.22539094388484954,
|
|
"num_tokens": 44667008.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 5.319937753677368,
|
|
"epoch": 2.0284831272970263,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004586251468582211,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.2317189708352089,
|
|
"num_tokens": 44675448.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 5.389148616790772,
|
|
"epoch": 2.0289007684597395,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004586079413566434,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.22027696222066878,
|
|
"num_tokens": 44684540.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 5.403631353378296,
|
|
"epoch": 2.0293184096224524,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045859073264078765,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.22432079017162324,
|
|
"num_tokens": 44693734.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 5.382337379455566,
|
|
"epoch": 2.029736050785165,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045857352071095514,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.22848997712135316,
|
|
"num_tokens": 44702407.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 5.3058305263519285,
|
|
"epoch": 2.0301536919478784,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004585563055674472,
|
|
"loss": 4.6443,
|
|
"mean_token_accuracy": 0.23812034577131272,
|
|
"num_tokens": 44711511.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 5.358152532577515,
|
|
"epoch": 2.0305713331105912,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045853908721056526,
|
|
"loss": 4.7369,
|
|
"mean_token_accuracy": 0.22783145904541016,
|
|
"num_tokens": 44720069.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 5.275671815872192,
|
|
"epoch": 2.0309889742733045,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045852186564061055,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.23515317738056182,
|
|
"num_tokens": 44728549.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 5.3646444320678714,
|
|
"epoch": 2.0314066154360173,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004585046408578847,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.22450118958950044,
|
|
"num_tokens": 44737753.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 5.378211402893067,
|
|
"epoch": 2.0318242565987306,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045848741286268923,
|
|
"loss": 4.7021,
|
|
"mean_token_accuracy": 0.22781268656253814,
|
|
"num_tokens": 44747591.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 5.301151418685913,
|
|
"epoch": 2.0322418977614434,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045847018165532576,
|
|
"loss": 4.815,
|
|
"mean_token_accuracy": 0.22900784760713577,
|
|
"num_tokens": 44756942.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 5.349484920501709,
|
|
"epoch": 2.032659538924156,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045845294723609596,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.22844923436641693,
|
|
"num_tokens": 44765492.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 5.32920355796814,
|
|
"epoch": 2.0330771800868694,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004584357096053014,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.23497850447893143,
|
|
"num_tokens": 44774433.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 5.425233602523804,
|
|
"epoch": 2.0334948212495823,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000458418468763244,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.2259715124964714,
|
|
"num_tokens": 44784107.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 5.375620889663696,
|
|
"epoch": 2.0339124624122955,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004584012247102255,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.22743880599737168,
|
|
"num_tokens": 44794234.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 5.2441778659820555,
|
|
"epoch": 2.0343301035750083,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004583839774465479,
|
|
"loss": 4.6201,
|
|
"mean_token_accuracy": 0.23878370970487595,
|
|
"num_tokens": 44802881.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 5.281685161590576,
|
|
"epoch": 2.034747744737721,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045836672697251293,
|
|
"loss": 4.7123,
|
|
"mean_token_accuracy": 0.231774041056633,
|
|
"num_tokens": 44812114.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 5.398759937286377,
|
|
"epoch": 2.0351653859004344,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004583494732884227,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.2201983243227005,
|
|
"num_tokens": 44821227.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 5.416930103302002,
|
|
"epoch": 2.035583027063147,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004583322163945792,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.22488769590854646,
|
|
"num_tokens": 44829703.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 5.382213163375854,
|
|
"epoch": 2.0360006682258605,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004583149562912847,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.22072433382272721,
|
|
"num_tokens": 44839400.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 5.270201921463013,
|
|
"epoch": 2.0364183093885733,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004582976929788411,
|
|
"loss": 4.689,
|
|
"mean_token_accuracy": 0.23209083825349808,
|
|
"num_tokens": 44848994.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 5.3161048412323,
|
|
"epoch": 2.0368359505512865,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004582804264575508,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.22679881304502486,
|
|
"num_tokens": 44857562.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 5.443898773193359,
|
|
"epoch": 2.0372535917139993,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000458263156727716,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.22298440039157869,
|
|
"num_tokens": 44867597.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 5.380709314346314,
|
|
"epoch": 2.037671232876712,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004582458837896391,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.2261164203286171,
|
|
"num_tokens": 44876678.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 5.302400255203247,
|
|
"epoch": 2.0380888740394254,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045822860764362235,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.22980901896953582,
|
|
"num_tokens": 44885847.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 5.343926239013672,
|
|
"epoch": 2.038506515202138,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004582113282899683,
|
|
"loss": 4.7776,
|
|
"mean_token_accuracy": 0.2259412258863449,
|
|
"num_tokens": 44896078.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 5.309862947463989,
|
|
"epoch": 2.0389241563648515,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004581940457289795,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.24192167818546295,
|
|
"num_tokens": 44904996.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 5.2771998882293705,
|
|
"epoch": 2.0393417975275643,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004581767599609584,
|
|
"loss": 4.6542,
|
|
"mean_token_accuracy": 0.23621727228164674,
|
|
"num_tokens": 44913488.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 5.398195457458496,
|
|
"epoch": 2.039759438690277,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004581594709862076,
|
|
"loss": 4.8515,
|
|
"mean_token_accuracy": 0.21280621439218522,
|
|
"num_tokens": 44922836.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 5.305184555053711,
|
|
"epoch": 2.0401770798529903,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045814217880502973,
|
|
"loss": 4.6559,
|
|
"mean_token_accuracy": 0.23526878654956818,
|
|
"num_tokens": 44932494.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 5.36963996887207,
|
|
"epoch": 2.040594721015703,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004581248834177276,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.22874077260494233,
|
|
"num_tokens": 44941572.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 5.300368070602417,
|
|
"epoch": 2.0410123621784164,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045810758482460397,
|
|
"loss": 4.7169,
|
|
"mean_token_accuracy": 0.225590218603611,
|
|
"num_tokens": 44949914.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 5.361369895935058,
|
|
"epoch": 2.0414300033411292,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004580902830259617,
|
|
"loss": 4.7658,
|
|
"mean_token_accuracy": 0.2267717033624649,
|
|
"num_tokens": 44958726.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 5.419687414169312,
|
|
"epoch": 2.0418476445038425,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045807297802210364,
|
|
"loss": 4.783,
|
|
"mean_token_accuracy": 0.22840218394994735,
|
|
"num_tokens": 44967204.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 5.330970525741577,
|
|
"epoch": 2.0422652856665553,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004580556698133327,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.22430592328310012,
|
|
"num_tokens": 44977043.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 5.383039331436157,
|
|
"epoch": 2.042682926829268,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004580383583999519,
|
|
"loss": 4.7816,
|
|
"mean_token_accuracy": 0.2188938945531845,
|
|
"num_tokens": 44986762.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 5.359033679962158,
|
|
"epoch": 2.0431005679919814,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004580210437822643,
|
|
"loss": 4.7086,
|
|
"mean_token_accuracy": 0.226274511218071,
|
|
"num_tokens": 44995513.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 5.377383089065551,
|
|
"epoch": 2.043518209154694,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004580037259605731,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.22948632389307022,
|
|
"num_tokens": 45005127.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 5.386111164093018,
|
|
"epoch": 2.0439358503174074,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004579864049351813,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.22605767399072646,
|
|
"num_tokens": 45013994.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 5.338684988021851,
|
|
"epoch": 2.0443534914801202,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004579690807063923,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.22522094547748567,
|
|
"num_tokens": 45024177.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 5.388187217712402,
|
|
"epoch": 2.0447711326428335,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004579517532745093,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.22699318677186966,
|
|
"num_tokens": 45033139.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 5.397950124740601,
|
|
"epoch": 2.0451887738055463,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045793442263983563,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.21898259222507477,
|
|
"num_tokens": 45043394.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 5.383217239379883,
|
|
"epoch": 2.045606414968259,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004579170888026747,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.2267278701066971,
|
|
"num_tokens": 45052015.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 5.311131954193115,
|
|
"epoch": 2.0460240561309724,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004578997517633299,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.22658319473266603,
|
|
"num_tokens": 45060836.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 5.312641525268555,
|
|
"epoch": 2.046441697293685,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045788241152210486,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.22518240958452224,
|
|
"num_tokens": 45070007.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 5.4194498538970945,
|
|
"epoch": 2.0468593384563984,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000457865068079303,
|
|
"loss": 4.7806,
|
|
"mean_token_accuracy": 0.22485383450984955,
|
|
"num_tokens": 45079984.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 5.376281976699829,
|
|
"epoch": 2.0472769796191113,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000457847721435228,
|
|
"loss": 4.6751,
|
|
"mean_token_accuracy": 0.2292617067694664,
|
|
"num_tokens": 45088676.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 5.341998672485351,
|
|
"epoch": 2.047694620781824,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045783037159018364,
|
|
"loss": 4.7854,
|
|
"mean_token_accuracy": 0.22752294540405274,
|
|
"num_tokens": 45098232.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 5.283925533294678,
|
|
"epoch": 2.0481122619445373,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045781301854447347,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.2321092188358307,
|
|
"num_tokens": 45107789.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 5.354871845245361,
|
|
"epoch": 2.04852990310725,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045779566229840144,
|
|
"loss": 4.7475,
|
|
"mean_token_accuracy": 0.22405931651592254,
|
|
"num_tokens": 45117824.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 5.442038917541504,
|
|
"epoch": 2.0489475442699634,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045777830285227125,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.21755823940038682,
|
|
"num_tokens": 45127625.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 5.349582481384277,
|
|
"epoch": 2.049365185432676,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004577609402063868,
|
|
"loss": 4.6877,
|
|
"mean_token_accuracy": 0.23130888789892196,
|
|
"num_tokens": 45135931.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 5.434735107421875,
|
|
"epoch": 2.049782826595389,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004577435743610522,
|
|
"loss": 4.8393,
|
|
"mean_token_accuracy": 0.22769405990839003,
|
|
"num_tokens": 45145690.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 5.459210348129273,
|
|
"epoch": 2.0502004677581023,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004577262053165713,
|
|
"loss": 4.9033,
|
|
"mean_token_accuracy": 0.21728067696094513,
|
|
"num_tokens": 45155455.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 5.417291450500488,
|
|
"epoch": 2.050618108920815,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004577088330732483,
|
|
"loss": 4.7657,
|
|
"mean_token_accuracy": 0.2310351774096489,
|
|
"num_tokens": 45164377.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 5.4868567943572994,
|
|
"epoch": 2.0510357500835283,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004576914576313872,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.21941159814596176,
|
|
"num_tokens": 45173037.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 5.395533895492553,
|
|
"epoch": 2.051453391246241,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004576740789912922,
|
|
"loss": 4.7341,
|
|
"mean_token_accuracy": 0.23273316621780396,
|
|
"num_tokens": 45182459.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 5.3000343322753904,
|
|
"epoch": 2.0518710324089544,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004576566971532676,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.23840043395757676,
|
|
"num_tokens": 45190744.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 5.381698036193848,
|
|
"epoch": 2.052288673571667,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004576393121176177,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.21872495710849763,
|
|
"num_tokens": 45198852.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 5.3443131923675535,
|
|
"epoch": 2.05270631473438,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045762192388464675,
|
|
"loss": 4.6634,
|
|
"mean_token_accuracy": 0.2391775518655777,
|
|
"num_tokens": 45207794.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 5.381850910186768,
|
|
"epoch": 2.0531239558970933,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004576045324546592,
|
|
"loss": 4.7028,
|
|
"mean_token_accuracy": 0.23762095868587493,
|
|
"num_tokens": 45216621.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 5.340626907348633,
|
|
"epoch": 2.053541597059806,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045758713782795946,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.22348456978797912,
|
|
"num_tokens": 45226801.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 5.317317962646484,
|
|
"epoch": 2.0539592382225194,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045756974000485216,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.22291072010993956,
|
|
"num_tokens": 45236575.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 5.425253057479859,
|
|
"epoch": 2.054376879385232,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045755233898564176,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.22435219138860701,
|
|
"num_tokens": 45245868.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 5.415348482131958,
|
|
"epoch": 2.0547945205479454,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045753493477063297,
|
|
"loss": 4.8146,
|
|
"mean_token_accuracy": 0.22335746884346008,
|
|
"num_tokens": 45256160.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 5.315018653869629,
|
|
"epoch": 2.0552121617106582,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004575175273601304,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.2307717889547348,
|
|
"num_tokens": 45265128.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 5.303972864151001,
|
|
"epoch": 2.055629802873371,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045750011675443886,
|
|
"loss": 4.6923,
|
|
"mean_token_accuracy": 0.22854253202676772,
|
|
"num_tokens": 45274825.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 5.279807996749878,
|
|
"epoch": 2.0560474440360843,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004574827029538631,
|
|
"loss": 4.6404,
|
|
"mean_token_accuracy": 0.23528321981430053,
|
|
"num_tokens": 45282585.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 5.348206663131714,
|
|
"epoch": 2.056465085198797,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004574652859587079,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.22152163982391357,
|
|
"num_tokens": 45292752.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 5.374705171585083,
|
|
"epoch": 2.0568827263615104,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045744786576927825,
|
|
"loss": 4.6616,
|
|
"mean_token_accuracy": 0.2351304978132248,
|
|
"num_tokens": 45302486.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 5.357350540161133,
|
|
"epoch": 2.057300367524223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004574304423858791,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.2215108945965767,
|
|
"num_tokens": 45311215.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 5.3551833152771,
|
|
"epoch": 2.057718008686936,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045741301580881557,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.22071012556552888,
|
|
"num_tokens": 45321800.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 5.250460386276245,
|
|
"epoch": 2.0581356498496493,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004573955860383925,
|
|
"loss": 4.7179,
|
|
"mean_token_accuracy": 0.2363354742527008,
|
|
"num_tokens": 45330621.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 5.344033527374267,
|
|
"epoch": 2.058553291012362,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004573781530749152,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.23298715204000472,
|
|
"num_tokens": 45340295.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 5.370867395401001,
|
|
"epoch": 2.0589709321750753,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045736071691868883,
|
|
"loss": 4.7819,
|
|
"mean_token_accuracy": 0.2226236194372177,
|
|
"num_tokens": 45350896.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 5.288927125930786,
|
|
"epoch": 2.059388573337788,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004573432775700185,
|
|
"loss": 4.6375,
|
|
"mean_token_accuracy": 0.23654357045888902,
|
|
"num_tokens": 45359462.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 5.42047152519226,
|
|
"epoch": 2.0598062145005014,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004573258350292097,
|
|
"loss": 4.7991,
|
|
"mean_token_accuracy": 0.21707727760076523,
|
|
"num_tokens": 45370272.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 5.3845373630523685,
|
|
"epoch": 2.060223855663214,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004573083892965677,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.2385641247034073,
|
|
"num_tokens": 45379745.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 5.3060845851898195,
|
|
"epoch": 2.060641496825927,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004572909403723978,
|
|
"loss": 4.5945,
|
|
"mean_token_accuracy": 0.24389150738716125,
|
|
"num_tokens": 45388599.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 5.306174325942993,
|
|
"epoch": 2.0610591379886403,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004572734882570057,
|
|
"loss": 4.7098,
|
|
"mean_token_accuracy": 0.2312918111681938,
|
|
"num_tokens": 45397246.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 5.369604825973511,
|
|
"epoch": 2.061476779151353,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045725603295069666,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.2181307703256607,
|
|
"num_tokens": 45406001.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 5.272917747497559,
|
|
"epoch": 2.0618944203140663,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004572385744537765,
|
|
"loss": 4.6581,
|
|
"mean_token_accuracy": 0.23151348680257797,
|
|
"num_tokens": 45414926.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 5.389466285705566,
|
|
"epoch": 2.062312061476779,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045722111276655066,
|
|
"loss": 4.754,
|
|
"mean_token_accuracy": 0.22405625730752946,
|
|
"num_tokens": 45423918.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 5.27608094215393,
|
|
"epoch": 2.062729702639492,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045720364788932486,
|
|
"loss": 4.621,
|
|
"mean_token_accuracy": 0.23679709434509277,
|
|
"num_tokens": 45433174.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 5.304968452453613,
|
|
"epoch": 2.063147343802205,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045718617982240496,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.23364595770835878,
|
|
"num_tokens": 45441660.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 5.406059265136719,
|
|
"epoch": 2.063564984964918,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004571687085660967,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.22025934755802154,
|
|
"num_tokens": 45451293.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 5.412761068344116,
|
|
"epoch": 2.0639826261276313,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045715123412070594,
|
|
"loss": 4.7436,
|
|
"mean_token_accuracy": 0.22609487622976304,
|
|
"num_tokens": 45460615.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 5.421054363250732,
|
|
"epoch": 2.064400267290344,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004571337564865385,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.2270621955394745,
|
|
"num_tokens": 45469404.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 5.458430194854737,
|
|
"epoch": 2.0648179084530573,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004571162756639004,
|
|
"loss": 4.8156,
|
|
"mean_token_accuracy": 0.2235592469573021,
|
|
"num_tokens": 45478900.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 5.301170444488525,
|
|
"epoch": 2.06523554961577,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004570987916530977,
|
|
"loss": 4.6484,
|
|
"mean_token_accuracy": 0.22495826482772827,
|
|
"num_tokens": 45488478.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 5.327271413803101,
|
|
"epoch": 2.065653190778483,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045708130445443646,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.22281068712472915,
|
|
"num_tokens": 45498421.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 5.3541796684265135,
|
|
"epoch": 2.0660708319411962,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045706381406822284,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.22558051347732544,
|
|
"num_tokens": 45507715.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 5.355970478057861,
|
|
"epoch": 2.066488473103909,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000457046320494763,
|
|
"loss": 4.7582,
|
|
"mean_token_accuracy": 0.22566883862018586,
|
|
"num_tokens": 45516524.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 5.362822437286377,
|
|
"epoch": 2.0669061142666223,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045702882373436317,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.22975497841835021,
|
|
"num_tokens": 45526058.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 5.376418352127075,
|
|
"epoch": 2.067323755429335,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004570113237873297,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.2248871922492981,
|
|
"num_tokens": 45535441.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 5.422372102737427,
|
|
"epoch": 2.067741396592048,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045699382065396893,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.21994227916002274,
|
|
"num_tokens": 45544355.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 5.388469552993774,
|
|
"epoch": 2.068159037754761,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004569763143345872,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.23365917950868606,
|
|
"num_tokens": 45553509.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 5.29692063331604,
|
|
"epoch": 2.068576678917474,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045695880482949107,
|
|
"loss": 4.5802,
|
|
"mean_token_accuracy": 0.2390886962413788,
|
|
"num_tokens": 45563016.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 5.334486579895019,
|
|
"epoch": 2.0689943200801872,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004569412921389871,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.2235408216714859,
|
|
"num_tokens": 45572242.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 5.318018293380737,
|
|
"epoch": 2.0694119612429,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004569237762633818,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.23044685870409012,
|
|
"num_tokens": 45581430.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 5.341419792175293,
|
|
"epoch": 2.0698296024056133,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045690625720298166,
|
|
"loss": 4.7017,
|
|
"mean_token_accuracy": 0.22590281814336777,
|
|
"num_tokens": 45590161.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 5.322350978851318,
|
|
"epoch": 2.070247243568326,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004568887349580937,
|
|
"loss": 4.7914,
|
|
"mean_token_accuracy": 0.21605796962976456,
|
|
"num_tokens": 45599243.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 5.324777746200562,
|
|
"epoch": 2.070664884731039,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045687120952902447,
|
|
"loss": 4.7188,
|
|
"mean_token_accuracy": 0.2329117923974991,
|
|
"num_tokens": 45607958.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 5.407842111587525,
|
|
"epoch": 2.071082525893752,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045685368091608075,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.2189605563879013,
|
|
"num_tokens": 45617243.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 5.350154733657837,
|
|
"epoch": 2.071500167056465,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045683614911956946,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.22401033192873002,
|
|
"num_tokens": 45627288.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 5.407224702835083,
|
|
"epoch": 2.0719178082191783,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004568186141397975,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.2290867730975151,
|
|
"num_tokens": 45636345.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 5.415159034729004,
|
|
"epoch": 2.072335449381891,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045680107597707186,
|
|
"loss": 4.737,
|
|
"mean_token_accuracy": 0.22838613241910935,
|
|
"num_tokens": 45645146.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 5.388048219680786,
|
|
"epoch": 2.072753090544604,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045678353463169953,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.21931652575731278,
|
|
"num_tokens": 45654509.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 5.362309885025025,
|
|
"epoch": 2.073170731707317,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004567659901039876,
|
|
"loss": 4.6809,
|
|
"mean_token_accuracy": 0.22970608323812486,
|
|
"num_tokens": 45663021.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 5.3560596942901615,
|
|
"epoch": 2.07358837287003,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004567484423942433,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.22924116253852844,
|
|
"num_tokens": 45671633.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 5.434768867492676,
|
|
"epoch": 2.074006014032743,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045673089150277365,
|
|
"loss": 4.8298,
|
|
"mean_token_accuracy": 0.223269547522068,
|
|
"num_tokens": 45681974.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 5.404663562774658,
|
|
"epoch": 2.074423655195456,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045671333742988604,
|
|
"loss": 4.7371,
|
|
"mean_token_accuracy": 0.22353960424661637,
|
|
"num_tokens": 45691939.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 5.559878396987915,
|
|
"epoch": 2.0748412963581693,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004566957801758878,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.21580324620008468,
|
|
"num_tokens": 45701689.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 5.3111389636993405,
|
|
"epoch": 2.075258937520882,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004566782197410861,
|
|
"loss": 4.6012,
|
|
"mean_token_accuracy": 0.2400829866528511,
|
|
"num_tokens": 45710523.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 5.334749746322632,
|
|
"epoch": 2.075676578683595,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004566606561257885,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.22797838896512984,
|
|
"num_tokens": 45719422.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 5.358555746078491,
|
|
"epoch": 2.076094219846308,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004566430893303025,
|
|
"loss": 4.7582,
|
|
"mean_token_accuracy": 0.22832330763339997,
|
|
"num_tokens": 45729052.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 5.333798837661743,
|
|
"epoch": 2.076511861009021,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004566255193549355,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.22955868244171143,
|
|
"num_tokens": 45739853.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 5.267929649353027,
|
|
"epoch": 2.076929502171734,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045660794619999524,
|
|
"loss": 4.6265,
|
|
"mean_token_accuracy": 0.24219631850719453,
|
|
"num_tokens": 45749433.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 5.351486349105835,
|
|
"epoch": 2.077347143334447,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004565903698657893,
|
|
"loss": 4.7241,
|
|
"mean_token_accuracy": 0.227825391292572,
|
|
"num_tokens": 45758771.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 5.419159841537476,
|
|
"epoch": 2.07776478449716,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045657279035262534,
|
|
"loss": 4.8664,
|
|
"mean_token_accuracy": 0.21120992600917815,
|
|
"num_tokens": 45767998.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 5.418992805480957,
|
|
"epoch": 2.078182425659873,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000456555207660811,
|
|
"loss": 4.849,
|
|
"mean_token_accuracy": 0.2239506497979164,
|
|
"num_tokens": 45777482.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 5.418926000595093,
|
|
"epoch": 2.078600066822586,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004565376217906543,
|
|
"loss": 4.7481,
|
|
"mean_token_accuracy": 0.22023271322250365,
|
|
"num_tokens": 45786996.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 5.455767965316772,
|
|
"epoch": 2.079017707985299,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045652003274246306,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.2257291093468666,
|
|
"num_tokens": 45796654.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 5.385164070129394,
|
|
"epoch": 2.079435349148012,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004565024405165452,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.22743392884731292,
|
|
"num_tokens": 45805086.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 5.394662094116211,
|
|
"epoch": 2.0798529903107252,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045648484511320853,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.22987860590219497,
|
|
"num_tokens": 45813034.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 5.306854200363159,
|
|
"epoch": 2.080270631473438,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045646724653276117,
|
|
"loss": 4.6272,
|
|
"mean_token_accuracy": 0.24079720973968505,
|
|
"num_tokens": 45821867.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 5.281816911697388,
|
|
"epoch": 2.080688272636151,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045644964477551124,
|
|
"loss": 4.6008,
|
|
"mean_token_accuracy": 0.2400273472070694,
|
|
"num_tokens": 45830640.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 5.283477067947388,
|
|
"epoch": 2.081105913798864,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000456432039841767,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.23865149021148682,
|
|
"num_tokens": 45839334.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 5.355232763290405,
|
|
"epoch": 2.081523554961577,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004564144317318364,
|
|
"loss": 4.7916,
|
|
"mean_token_accuracy": 0.2194241389632225,
|
|
"num_tokens": 45849253.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 5.416988563537598,
|
|
"epoch": 2.08194119612429,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045639682044602777,
|
|
"loss": 4.7674,
|
|
"mean_token_accuracy": 0.22283072769641876,
|
|
"num_tokens": 45858166.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 5.439301061630249,
|
|
"epoch": 2.082358837287003,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045637920598464956,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.22287579476833344,
|
|
"num_tokens": 45867658.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 5.345929956436157,
|
|
"epoch": 2.082776478449716,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045636158834800987,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.23382688015699388,
|
|
"num_tokens": 45876817.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 5.342687559127808,
|
|
"epoch": 2.083194119612429,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045634396753641736,
|
|
"loss": 4.7205,
|
|
"mean_token_accuracy": 0.23458823263645173,
|
|
"num_tokens": 45886019.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 5.407519865036011,
|
|
"epoch": 2.083611760775142,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004563263435501805,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.22198196351528168,
|
|
"num_tokens": 45894917.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 5.4221783638000485,
|
|
"epoch": 2.084029401937855,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004563087163896076,
|
|
"loss": 4.6588,
|
|
"mean_token_accuracy": 0.2345363587141037,
|
|
"num_tokens": 45903727.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 5.312986660003662,
|
|
"epoch": 2.084447043100568,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045629108605500747,
|
|
"loss": 4.6475,
|
|
"mean_token_accuracy": 0.23910930007696152,
|
|
"num_tokens": 45912217.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 5.366034269332886,
|
|
"epoch": 2.084864684263281,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045627345254668864,
|
|
"loss": 4.7992,
|
|
"mean_token_accuracy": 0.22242934107780457,
|
|
"num_tokens": 45921526.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 5.381333732604981,
|
|
"epoch": 2.085282325425994,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045625581586495977,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.2203475147485733,
|
|
"num_tokens": 45931115.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 5.402650308609009,
|
|
"epoch": 2.085699966588707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004562381760101297,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.21924566179513932,
|
|
"num_tokens": 45940323.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 5.411405420303344,
|
|
"epoch": 2.08611760775142,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004562205329825072,
|
|
"loss": 4.7142,
|
|
"mean_token_accuracy": 0.22581979930400847,
|
|
"num_tokens": 45949354.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 5.322289991378784,
|
|
"epoch": 2.086535248914133,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004562028867824012,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.21946716904640198,
|
|
"num_tokens": 45958899.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 5.351852989196777,
|
|
"epoch": 2.086952890076846,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045618523741012044,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.2350276902318001,
|
|
"num_tokens": 45967431.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 5.27474684715271,
|
|
"epoch": 2.087370531239559,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004561675848659741,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.2269982948899269,
|
|
"num_tokens": 45976185.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 5.267695379257202,
|
|
"epoch": 2.0877881724022718,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045614992915027103,
|
|
"loss": 4.5719,
|
|
"mean_token_accuracy": 0.24461012482643127,
|
|
"num_tokens": 45984648.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 5.269450902938843,
|
|
"epoch": 2.088205813564985,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045613227026332045,
|
|
"loss": 4.6509,
|
|
"mean_token_accuracy": 0.23115983605384827,
|
|
"num_tokens": 45993724.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 5.339711761474609,
|
|
"epoch": 2.088623454727698,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004561146082054314,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.23231004178524017,
|
|
"num_tokens": 46002998.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 5.325686931610107,
|
|
"epoch": 2.089041095890411,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004560969429769132,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.2325964480638504,
|
|
"num_tokens": 46010843.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 5.297151041030884,
|
|
"epoch": 2.089458737053124,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045607927457807503,
|
|
"loss": 4.635,
|
|
"mean_token_accuracy": 0.2397361606359482,
|
|
"num_tokens": 46019733.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 5.363168954849243,
|
|
"epoch": 2.089876378215837,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004560616030092261,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.22400563061237336,
|
|
"num_tokens": 46029754.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 5.339349889755249,
|
|
"epoch": 2.09029401937855,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004560439282706759,
|
|
"loss": 4.6464,
|
|
"mean_token_accuracy": 0.23328817635774612,
|
|
"num_tokens": 46037855.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 5.357065010070801,
|
|
"epoch": 2.090711660541263,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045602625036273385,
|
|
"loss": 4.7767,
|
|
"mean_token_accuracy": 0.22087235599756241,
|
|
"num_tokens": 46046176.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 5.423155498504639,
|
|
"epoch": 2.091129301703976,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045600856928570944,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.22961245477199554,
|
|
"num_tokens": 46055847.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 5.408601713180542,
|
|
"epoch": 2.091546942866689,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045599088503991205,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.21941450387239456,
|
|
"num_tokens": 46065763.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 5.359149837493897,
|
|
"epoch": 2.091964584029402,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004559731976256514,
|
|
"loss": 4.7789,
|
|
"mean_token_accuracy": 0.22125527113676072,
|
|
"num_tokens": 46074564.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 5.3592921733856205,
|
|
"epoch": 2.092382225192115,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045595550704323706,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.23016733378171922,
|
|
"num_tokens": 46083627.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 5.3492560386657715,
|
|
"epoch": 2.0927998663548277,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045593781329297876,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.2290765941143036,
|
|
"num_tokens": 46092997.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 5.405224275588989,
|
|
"epoch": 2.093217507517541,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045592011637518625,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.2174540564417839,
|
|
"num_tokens": 46103266.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 5.357687616348267,
|
|
"epoch": 2.093635148680254,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045590241629016933,
|
|
"loss": 4.6075,
|
|
"mean_token_accuracy": 0.2358526512980461,
|
|
"num_tokens": 46112896.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 5.341036796569824,
|
|
"epoch": 2.094052789842967,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045588471303823787,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.23515243977308273,
|
|
"num_tokens": 46121134.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 5.354607582092285,
|
|
"epoch": 2.09447043100568,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045586700661970174,
|
|
"loss": 4.711,
|
|
"mean_token_accuracy": 0.22624728530645372,
|
|
"num_tokens": 46130617.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 5.364838314056397,
|
|
"epoch": 2.094888072168393,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045584929703487107,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.22660114020109176,
|
|
"num_tokens": 46140584.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 5.331680679321289,
|
|
"epoch": 2.095305713331106,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004558315842840556,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.23240089267492295,
|
|
"num_tokens": 46150039.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 5.333059597015381,
|
|
"epoch": 2.0957233544938187,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004558138683675657,
|
|
"loss": 4.7238,
|
|
"mean_token_accuracy": 0.22347958981990815,
|
|
"num_tokens": 46158899.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 5.377329587936401,
|
|
"epoch": 2.096140995656532,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045579614928571135,
|
|
"loss": 4.7679,
|
|
"mean_token_accuracy": 0.222751222550869,
|
|
"num_tokens": 46167813.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 5.3083666324615475,
|
|
"epoch": 2.096558636819245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004557784270388028,
|
|
"loss": 4.6628,
|
|
"mean_token_accuracy": 0.2335493877530098,
|
|
"num_tokens": 46176440.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 5.311924123764038,
|
|
"epoch": 2.096976277981958,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045576070162715025,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.2321628212928772,
|
|
"num_tokens": 46186354.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 5.324186897277832,
|
|
"epoch": 2.097393919144671,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000455742973051064,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.22902601212263107,
|
|
"num_tokens": 46194819.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 5.373207092285156,
|
|
"epoch": 2.0978115603073837,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004557252413108545,
|
|
"loss": 4.8427,
|
|
"mean_token_accuracy": 0.217597496509552,
|
|
"num_tokens": 46205687.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 5.412643814086914,
|
|
"epoch": 2.098229201470097,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045570750640683207,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.21422950625419618,
|
|
"num_tokens": 46214990.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 5.353067064285279,
|
|
"epoch": 2.0986468426328098,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004556897683393073,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.224062742292881,
|
|
"num_tokens": 46224325.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 5.383762645721435,
|
|
"epoch": 2.099064483795523,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045567202710859056,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.21812717914581298,
|
|
"num_tokens": 46234199.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 5.362556028366089,
|
|
"epoch": 2.099482124958236,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004556542827149926,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.2313001573085785,
|
|
"num_tokens": 46243633.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 5.327725124359131,
|
|
"epoch": 2.099899766120949,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004556365351588239,
|
|
"loss": 4.6135,
|
|
"mean_token_accuracy": 0.2419717416167259,
|
|
"num_tokens": 46252994.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 5.335115003585815,
|
|
"epoch": 2.100317407283662,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045561878444039526,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.22960398346185684,
|
|
"num_tokens": 46262455.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 5.365865707397461,
|
|
"epoch": 2.1007350484463747,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045560103056001733,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.22181313037872313,
|
|
"num_tokens": 46271864.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 5.370267724990844,
|
|
"epoch": 2.101152689609088,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000455583273518001,
|
|
"loss": 4.6683,
|
|
"mean_token_accuracy": 0.235249362885952,
|
|
"num_tokens": 46281244.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 5.316329622268677,
|
|
"epoch": 2.1015703307718008,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004555655133146571,
|
|
"loss": 4.6767,
|
|
"mean_token_accuracy": 0.23000800460577012,
|
|
"num_tokens": 46291145.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 5.289380788803101,
|
|
"epoch": 2.101987971934514,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004555477499502965,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.2308528870344162,
|
|
"num_tokens": 46300484.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 5.378136730194091,
|
|
"epoch": 2.102405613097227,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004555299834252303,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.23588334918022155,
|
|
"num_tokens": 46309598.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 5.454927635192871,
|
|
"epoch": 2.1028232542599397,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004555122137397694,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.22050437033176423,
|
|
"num_tokens": 46318410.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 5.448730945587158,
|
|
"epoch": 2.103240895422653,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045549444089422486,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.21134490072727202,
|
|
"num_tokens": 46327011.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 5.400857973098755,
|
|
"epoch": 2.1036585365853657,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045547666488890794,
|
|
"loss": 4.7823,
|
|
"mean_token_accuracy": 0.2311396300792694,
|
|
"num_tokens": 46335935.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 5.347595119476319,
|
|
"epoch": 2.104076177748079,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004554588857241297,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.2260343238711357,
|
|
"num_tokens": 46344820.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 5.319770050048828,
|
|
"epoch": 2.104493818910792,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045544110340020155,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.2239694342017174,
|
|
"num_tokens": 46353484.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 5.378846073150635,
|
|
"epoch": 2.104911460073505,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004554233179174346,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.21676502376794815,
|
|
"num_tokens": 46362539.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 5.390982532501221,
|
|
"epoch": 2.105329101236218,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004554055292761403,
|
|
"loss": 4.7767,
|
|
"mean_token_accuracy": 0.22625141441822053,
|
|
"num_tokens": 46372750.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 5.39056248664856,
|
|
"epoch": 2.1057467423989307,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004553877374766301,
|
|
"loss": 4.7506,
|
|
"mean_token_accuracy": 0.22784820944070816,
|
|
"num_tokens": 46381891.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 5.368734121322632,
|
|
"epoch": 2.106164383561644,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045536994251921535,
|
|
"loss": 4.6904,
|
|
"mean_token_accuracy": 0.229325507581234,
|
|
"num_tokens": 46391013.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 5.3581289768219,
|
|
"epoch": 2.1065820247243567,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004553521444042077,
|
|
"loss": 4.7196,
|
|
"mean_token_accuracy": 0.22820031642913818,
|
|
"num_tokens": 46400527.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 5.38363561630249,
|
|
"epoch": 2.10699966588707,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045533434313191866,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.22507133334875107,
|
|
"num_tokens": 46409869.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 5.306622648239136,
|
|
"epoch": 2.107417307049783,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045531653870265994,
|
|
"loss": 4.6622,
|
|
"mean_token_accuracy": 0.233397176861763,
|
|
"num_tokens": 46418644.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 5.348274755477905,
|
|
"epoch": 2.1078349482124956,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004552987311167431,
|
|
"loss": 4.6988,
|
|
"mean_token_accuracy": 0.23820508867502213,
|
|
"num_tokens": 46427475.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 5.45969524383545,
|
|
"epoch": 2.108252589375209,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045528092037447994,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.21798892468214034,
|
|
"num_tokens": 46437322.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 5.377167415618897,
|
|
"epoch": 2.1086702305379217,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004552631064761822,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.22503737956285477,
|
|
"num_tokens": 46446193.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 5.368884563446045,
|
|
"epoch": 2.109087871700635,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004552452894221619,
|
|
"loss": 4.643,
|
|
"mean_token_accuracy": 0.23734878301620482,
|
|
"num_tokens": 46455351.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 5.383166122436523,
|
|
"epoch": 2.1095055128633478,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045522746921273084,
|
|
"loss": 4.7695,
|
|
"mean_token_accuracy": 0.22396730333566667,
|
|
"num_tokens": 46464056.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 5.355669450759888,
|
|
"epoch": 2.109923154026061,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045520964584820097,
|
|
"loss": 4.6479,
|
|
"mean_token_accuracy": 0.23865276724100112,
|
|
"num_tokens": 46472654.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 5.378890419006348,
|
|
"epoch": 2.110340795188774,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004551918193288844,
|
|
"loss": 4.7766,
|
|
"mean_token_accuracy": 0.22558291703462602,
|
|
"num_tokens": 46482075.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 5.295826721191406,
|
|
"epoch": 2.1107584363514866,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045517398965509297,
|
|
"loss": 4.6977,
|
|
"mean_token_accuracy": 0.23038031160831451,
|
|
"num_tokens": 46490353.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 5.32123818397522,
|
|
"epoch": 2.1111760775142,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045515615682713913,
|
|
"loss": 4.6582,
|
|
"mean_token_accuracy": 0.23385339677333833,
|
|
"num_tokens": 46499332.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 5.395078849792481,
|
|
"epoch": 2.1115937186769127,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045513832084533484,
|
|
"loss": 4.8096,
|
|
"mean_token_accuracy": 0.22078716456890107,
|
|
"num_tokens": 46508824.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 5.472176742553711,
|
|
"epoch": 2.112011359839626,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004551204817099924,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.22081484496593476,
|
|
"num_tokens": 46518262.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 5.408075332641602,
|
|
"epoch": 2.1124290010023388,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045510263942142416,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.2266035333275795,
|
|
"num_tokens": 46527463.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 5.368783807754516,
|
|
"epoch": 2.1128466421650516,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004550847939799424,
|
|
"loss": 4.7716,
|
|
"mean_token_accuracy": 0.22324675619602202,
|
|
"num_tokens": 46537380.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 5.3438177585601805,
|
|
"epoch": 2.113264283327765,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045506694538585956,
|
|
"loss": 4.7212,
|
|
"mean_token_accuracy": 0.22792674452066422,
|
|
"num_tokens": 46546664.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 5.342543125152588,
|
|
"epoch": 2.1136819244904776,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004550490936394881,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.2302517667412758,
|
|
"num_tokens": 46555180.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 5.487735176086426,
|
|
"epoch": 2.114099565653191,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004550312387411406,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.2175215095281601,
|
|
"num_tokens": 46565450.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 5.42468228340149,
|
|
"epoch": 2.1145172068159037,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004550133806911295,
|
|
"loss": 4.8324,
|
|
"mean_token_accuracy": 0.21740172654390336,
|
|
"num_tokens": 46574453.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 5.382725524902344,
|
|
"epoch": 2.114934847978617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004549955194897674,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.22873876988887787,
|
|
"num_tokens": 46584341.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 5.390816402435303,
|
|
"epoch": 2.11535248914133,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045497765513736717,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.22209714204072953,
|
|
"num_tokens": 46593247.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 5.399173212051392,
|
|
"epoch": 2.1157701303040426,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045495978763424147,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.22603109031915664,
|
|
"num_tokens": 46602410.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 5.397504568099976,
|
|
"epoch": 2.116187771466756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045494191698070295,
|
|
"loss": 4.6947,
|
|
"mean_token_accuracy": 0.23053646683692933,
|
|
"num_tokens": 46611348.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 5.430768203735352,
|
|
"epoch": 2.1166054126294687,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045492404317706473,
|
|
"loss": 4.8036,
|
|
"mean_token_accuracy": 0.21600472033023835,
|
|
"num_tokens": 46621416.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 5.40539140701294,
|
|
"epoch": 2.117023053792182,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004549061662236394,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.2160392940044403,
|
|
"num_tokens": 46631839.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 5.346385860443116,
|
|
"epoch": 2.1174406949548947,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004548882861207402,
|
|
"loss": 4.6672,
|
|
"mean_token_accuracy": 0.24129021316766738,
|
|
"num_tokens": 46640662.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 5.366729354858398,
|
|
"epoch": 2.1178583361176075,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045487040286868,
|
|
"loss": 4.7715,
|
|
"mean_token_accuracy": 0.22094326615333557,
|
|
"num_tokens": 46649399.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 5.332968139648438,
|
|
"epoch": 2.118275977280321,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045485251646777187,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.22711319625377654,
|
|
"num_tokens": 46658020.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 5.388934087753296,
|
|
"epoch": 2.1186936184430336,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004548346269183289,
|
|
"loss": 4.7617,
|
|
"mean_token_accuracy": 0.2297348126769066,
|
|
"num_tokens": 46666815.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 5.348256063461304,
|
|
"epoch": 2.119111259605747,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045481673422066444,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.22810722291469573,
|
|
"num_tokens": 46675582.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 5.405477666854859,
|
|
"epoch": 2.1195289007684597,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004547988383750915,
|
|
"loss": 4.8891,
|
|
"mean_token_accuracy": 0.21653376668691635,
|
|
"num_tokens": 46686385.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 5.3912254810333256,
|
|
"epoch": 2.119946541931173,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004547809393819235,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.22845643758773804,
|
|
"num_tokens": 46695445.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 5.4819916725158695,
|
|
"epoch": 2.1203641830938857,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004547630372414737,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.2333764910697937,
|
|
"num_tokens": 46704562.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 5.396270132064819,
|
|
"epoch": 2.1207818242565986,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004547451319540557,
|
|
"loss": 4.7975,
|
|
"mean_token_accuracy": 0.22750874012708663,
|
|
"num_tokens": 46713736.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 5.314209985733032,
|
|
"epoch": 2.121199465419312,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004547272235199826,
|
|
"loss": 4.7035,
|
|
"mean_token_accuracy": 0.2273292601108551,
|
|
"num_tokens": 46723160.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 5.347100877761841,
|
|
"epoch": 2.1216171065820246,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004547093119395683,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.22245726585388184,
|
|
"num_tokens": 46732840.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 5.3739954948425295,
|
|
"epoch": 2.122034747744738,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045469139721312607,
|
|
"loss": 4.7014,
|
|
"mean_token_accuracy": 0.2356152817606926,
|
|
"num_tokens": 46742483.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 5.294745779037475,
|
|
"epoch": 2.1224523889074507,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004546734793409697,
|
|
"loss": 4.6852,
|
|
"mean_token_accuracy": 0.23217298686504365,
|
|
"num_tokens": 46751217.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 5.325687456130981,
|
|
"epoch": 2.1228700300701635,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004546555583234128,
|
|
"loss": 4.6941,
|
|
"mean_token_accuracy": 0.22932607233524321,
|
|
"num_tokens": 46759978.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 5.393499374389648,
|
|
"epoch": 2.1232876712328768,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000454637634160769,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.2240721568465233,
|
|
"num_tokens": 46768635.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 5.400375747680664,
|
|
"epoch": 2.1237053123955896,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004546197068533523,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.22147650867700577,
|
|
"num_tokens": 46778123.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 5.409610939025879,
|
|
"epoch": 2.124122953558303,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004546017764014764,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.22361210733652115,
|
|
"num_tokens": 46787821.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 5.2962743759155275,
|
|
"epoch": 2.1245405947210156,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004545838428054552,
|
|
"loss": 4.7098,
|
|
"mean_token_accuracy": 0.2310318022966385,
|
|
"num_tokens": 46796419.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 5.385782384872437,
|
|
"epoch": 2.124958235883729,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004545659060656027,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.22373090386390687,
|
|
"num_tokens": 46805342.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 5.440685558319092,
|
|
"epoch": 2.1253758770464417,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004545479661822328,
|
|
"loss": 4.7842,
|
|
"mean_token_accuracy": 0.22498748004436492,
|
|
"num_tokens": 46813432.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 5.365459775924682,
|
|
"epoch": 2.1257935182091545,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045453002315565965,
|
|
"loss": 4.829,
|
|
"mean_token_accuracy": 0.2245471328496933,
|
|
"num_tokens": 46823023.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 5.403371047973633,
|
|
"epoch": 2.1262111593718678,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004545120769861974,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.23008822351694108,
|
|
"num_tokens": 46832187.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 5.408018016815186,
|
|
"epoch": 2.1266288005345806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004544941276741601,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.2328067645430565,
|
|
"num_tokens": 46840122.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 5.367001914978028,
|
|
"epoch": 2.127046441697294,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045447617521986205,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.23715525716543198,
|
|
"num_tokens": 46848854.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 5.389351177215576,
|
|
"epoch": 2.1274640828600067,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004544582196236175,
|
|
"loss": 4.7656,
|
|
"mean_token_accuracy": 0.22177284806966782,
|
|
"num_tokens": 46859182.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 5.356009197235108,
|
|
"epoch": 2.1278817240227195,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004544402608857409,
|
|
"loss": 4.6751,
|
|
"mean_token_accuracy": 0.2351835072040558,
|
|
"num_tokens": 46867856.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 5.318211793899536,
|
|
"epoch": 2.1282993651854327,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004544222990065464,
|
|
"loss": 4.732,
|
|
"mean_token_accuracy": 0.23190684616565704,
|
|
"num_tokens": 46876793.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 5.286184787750244,
|
|
"epoch": 2.1287170063481455,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045440433398634866,
|
|
"loss": 4.7044,
|
|
"mean_token_accuracy": 0.2332007497549057,
|
|
"num_tokens": 46885342.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 5.3623274803161625,
|
|
"epoch": 2.129134647510859,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004543863658254622,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.22549813836812974,
|
|
"num_tokens": 46895742.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 5.395967769622803,
|
|
"epoch": 2.1295522886735716,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004543683945242013,
|
|
"loss": 4.7299,
|
|
"mean_token_accuracy": 0.23274738043546678,
|
|
"num_tokens": 46905130.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 5.31242938041687,
|
|
"epoch": 2.129969929836285,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045435042008288093,
|
|
"loss": 4.7005,
|
|
"mean_token_accuracy": 0.2291135773062706,
|
|
"num_tokens": 46913939.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 5.384705448150635,
|
|
"epoch": 2.1303875709989977,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045433244250181535,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.23060660511255265,
|
|
"num_tokens": 46922308.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 5.394655323028564,
|
|
"epoch": 2.1308052121617105,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045431446178131966,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.22469123899936677,
|
|
"num_tokens": 46931472.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 5.283763647079468,
|
|
"epoch": 2.1312228533244237,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004542964779217085,
|
|
"loss": 4.6656,
|
|
"mean_token_accuracy": 0.22741523385047913,
|
|
"num_tokens": 46940017.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 5.221071720123291,
|
|
"epoch": 2.1316404944871366,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045427849092329655,
|
|
"loss": 4.6685,
|
|
"mean_token_accuracy": 0.22949012517929077,
|
|
"num_tokens": 46949045.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 5.321490907669068,
|
|
"epoch": 2.13205813564985,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045426050078639884,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.22872042059898376,
|
|
"num_tokens": 46957845.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 5.340193128585815,
|
|
"epoch": 2.1324757768125626,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004542425075113303,
|
|
"loss": 4.678,
|
|
"mean_token_accuracy": 0.23104740381240846,
|
|
"num_tokens": 46966932.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 5.356275129318237,
|
|
"epoch": 2.132893417975276,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045422451109840604,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.21741428822278977,
|
|
"num_tokens": 46976362.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 5.332284784317016,
|
|
"epoch": 2.1333110591379887,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045420651154794086,
|
|
"loss": 4.6997,
|
|
"mean_token_accuracy": 0.23286663889884948,
|
|
"num_tokens": 46985311.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 5.431962871551514,
|
|
"epoch": 2.1337287003007015,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045418850886025006,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.22418245375156404,
|
|
"num_tokens": 46994666.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 5.356616973876953,
|
|
"epoch": 2.1341463414634148,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045417050303564867,
|
|
"loss": 4.7066,
|
|
"mean_token_accuracy": 0.2263672396540642,
|
|
"num_tokens": 47003894.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 5.303135919570923,
|
|
"epoch": 2.1345639826261276,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045415249407445196,
|
|
"loss": 4.6482,
|
|
"mean_token_accuracy": 0.23410507589578627,
|
|
"num_tokens": 47012556.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 5.341859197616577,
|
|
"epoch": 2.134981623788841,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004541344819769751,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.22894951552152634,
|
|
"num_tokens": 47022085.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 5.283460283279419,
|
|
"epoch": 2.1353992649515536,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045411646674353365,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.23879650682210923,
|
|
"num_tokens": 47030759.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 5.341563606262207,
|
|
"epoch": 2.1358169061142664,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045409844837444283,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.22429345846176146,
|
|
"num_tokens": 47039877.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 5.2966907024383545,
|
|
"epoch": 2.1362345472769797,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045408042687001806,
|
|
"loss": 4.6987,
|
|
"mean_token_accuracy": 0.22978040277957917,
|
|
"num_tokens": 47049500.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 5.393493366241455,
|
|
"epoch": 2.1366521884396925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004540624022305749,
|
|
"loss": 4.7782,
|
|
"mean_token_accuracy": 0.22209029346704484,
|
|
"num_tokens": 47059377.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 5.359887218475341,
|
|
"epoch": 2.1370698296024058,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004540443744564288,
|
|
"loss": 4.7418,
|
|
"mean_token_accuracy": 0.2308061182498932,
|
|
"num_tokens": 47068263.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 5.471501684188842,
|
|
"epoch": 2.1374874707651186,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004540263435478953,
|
|
"loss": 4.868,
|
|
"mean_token_accuracy": 0.218233186006546,
|
|
"num_tokens": 47077752.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 5.384789657592774,
|
|
"epoch": 2.1379051119278314,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045400830950529037,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.22754673510789872,
|
|
"num_tokens": 47087013.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 5.249980831146241,
|
|
"epoch": 2.1383227530905446,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004539902723289294,
|
|
"loss": 4.673,
|
|
"mean_token_accuracy": 0.23367853760719298,
|
|
"num_tokens": 47096502.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 5.400604009628296,
|
|
"epoch": 2.1387403942532575,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045397223201912827,
|
|
"loss": 4.8242,
|
|
"mean_token_accuracy": 0.22835191935300828,
|
|
"num_tokens": 47105347.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 5.359413814544678,
|
|
"epoch": 2.1391580354159707,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004539541885762028,
|
|
"loss": 4.6423,
|
|
"mean_token_accuracy": 0.23521964699029924,
|
|
"num_tokens": 47114137.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 5.378511714935303,
|
|
"epoch": 2.1395756765786835,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004539361420004689,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.22769729495048524,
|
|
"num_tokens": 47123366.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 5.416688346862793,
|
|
"epoch": 2.139993317741397,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045391809229224236,
|
|
"loss": 4.7384,
|
|
"mean_token_accuracy": 0.22648655623197556,
|
|
"num_tokens": 47132129.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 5.382462406158448,
|
|
"epoch": 2.1404109589041096,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004539000394518393,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.22973586171865462,
|
|
"num_tokens": 47142860.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 5.36987338066101,
|
|
"epoch": 2.1408286000668224,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004538819834795757,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.22785934656858445,
|
|
"num_tokens": 47151942.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 5.362025737762451,
|
|
"epoch": 2.1412462412295357,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045386392437576765,
|
|
"loss": 4.7706,
|
|
"mean_token_accuracy": 0.22474676221609116,
|
|
"num_tokens": 47160770.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 5.344197607040405,
|
|
"epoch": 2.1416638823922485,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045384586214073134,
|
|
"loss": 4.7067,
|
|
"mean_token_accuracy": 0.22660271674394608,
|
|
"num_tokens": 47169514.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 5.392347145080566,
|
|
"epoch": 2.1420815235549617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045382779677478294,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.23002956211566924,
|
|
"num_tokens": 47178470.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 5.252346515655518,
|
|
"epoch": 2.1424991647176745,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045380972827823866,
|
|
"loss": 4.6352,
|
|
"mean_token_accuracy": 0.2354491725564003,
|
|
"num_tokens": 47187694.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 5.297541952133178,
|
|
"epoch": 2.142916805880388,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004537916566514149,
|
|
"loss": 4.6633,
|
|
"mean_token_accuracy": 0.2328769236803055,
|
|
"num_tokens": 47196205.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 5.35560564994812,
|
|
"epoch": 2.1433344470431006,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004537735818946279,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.22791447043418883,
|
|
"num_tokens": 47205834.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 5.3376575946807865,
|
|
"epoch": 2.1437520882058134,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004537555040081942,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.22144054919481276,
|
|
"num_tokens": 47215763.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 5.447649717330933,
|
|
"epoch": 2.1441697293685267,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045373742299243026,
|
|
"loss": 4.806,
|
|
"mean_token_accuracy": 0.2166961669921875,
|
|
"num_tokens": 47225536.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 5.413727807998657,
|
|
"epoch": 2.1445873705312395,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045371933884765246,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.21875484883785248,
|
|
"num_tokens": 47235104.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 5.362454652786255,
|
|
"epoch": 2.1450050116939527,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004537012515741777,
|
|
"loss": 4.7184,
|
|
"mean_token_accuracy": 0.22560519427061082,
|
|
"num_tokens": 47244312.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 5.339710474014282,
|
|
"epoch": 2.1454226528566656,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004536831611723223,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.2234885424375534,
|
|
"num_tokens": 47253174.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 5.366544389724732,
|
|
"epoch": 2.1458402940193784,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004536650676424032,
|
|
"loss": 4.718,
|
|
"mean_token_accuracy": 0.22519724816083908,
|
|
"num_tokens": 47262742.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 5.4530082702636715,
|
|
"epoch": 2.1462579351820916,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004536469709847369,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.22563534379005432,
|
|
"num_tokens": 47271667.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 5.324712896347046,
|
|
"epoch": 2.1466755763448044,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004536288711996404,
|
|
"loss": 4.6524,
|
|
"mean_token_accuracy": 0.2298920139670372,
|
|
"num_tokens": 47280462.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 5.399959135055542,
|
|
"epoch": 2.1470932175075177,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045361076828743054,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.2209169939160347,
|
|
"num_tokens": 47290834.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 5.373245763778686,
|
|
"epoch": 2.1475108586702305,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004535926622484242,
|
|
"loss": 4.6918,
|
|
"mean_token_accuracy": 0.2301689639687538,
|
|
"num_tokens": 47300002.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 5.415419054031372,
|
|
"epoch": 2.1479284998329433,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045357455308293816,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.22994741052389145,
|
|
"num_tokens": 47309299.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 5.320118951797485,
|
|
"epoch": 2.1483461409956566,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004535564407912898,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.2299659565091133,
|
|
"num_tokens": 47318680.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 5.366862106323242,
|
|
"epoch": 2.1487637821583694,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004535383253737959,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.22419558465480804,
|
|
"num_tokens": 47329841.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 5.426968812942505,
|
|
"epoch": 2.1491814233210826,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004535202068307737,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.21734667122364043,
|
|
"num_tokens": 47338962.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 5.370934915542603,
|
|
"epoch": 2.1495990644837955,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004535020851625405,
|
|
"loss": 4.7665,
|
|
"mean_token_accuracy": 0.2239397257566452,
|
|
"num_tokens": 47348230.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 5.386222553253174,
|
|
"epoch": 2.1500167056465087,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045348396036941336,
|
|
"loss": 4.7536,
|
|
"mean_token_accuracy": 0.22222590297460557,
|
|
"num_tokens": 47358694.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 5.3890598773956295,
|
|
"epoch": 2.1504343468092215,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004534658324517097,
|
|
"loss": 4.7172,
|
|
"mean_token_accuracy": 0.22537804394960403,
|
|
"num_tokens": 47368617.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 5.4339393138885494,
|
|
"epoch": 2.1508519879719343,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004534477014097468,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.2206864446401596,
|
|
"num_tokens": 47377902.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 5.429246139526367,
|
|
"epoch": 2.1512696291346476,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045342956724384205,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.2326589733362198,
|
|
"num_tokens": 47386337.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 5.3673553466796875,
|
|
"epoch": 2.1516872702973604,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000453411429954313,
|
|
"loss": 4.7194,
|
|
"mean_token_accuracy": 0.23230731189250947,
|
|
"num_tokens": 47395212.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 5.3498450756073,
|
|
"epoch": 2.1521049114600737,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004533932895414771,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.2284234419465065,
|
|
"num_tokens": 47404296.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 5.329205513000488,
|
|
"epoch": 2.1525225526227865,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045337514600565196,
|
|
"loss": 4.6711,
|
|
"mean_token_accuracy": 0.23773755580186845,
|
|
"num_tokens": 47413858.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 5.380400800704956,
|
|
"epoch": 2.1529401937854997,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045335699934715513,
|
|
"loss": 4.7413,
|
|
"mean_token_accuracy": 0.2233599528670311,
|
|
"num_tokens": 47422502.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 5.349911212921143,
|
|
"epoch": 2.1533578349482125,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045333884956630437,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.2297806918621063,
|
|
"num_tokens": 47431763.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 5.459933042526245,
|
|
"epoch": 2.1537754761109253,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045332069666341733,
|
|
"loss": 4.8722,
|
|
"mean_token_accuracy": 0.22187006920576097,
|
|
"num_tokens": 47441261.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 5.3634480953216555,
|
|
"epoch": 2.1541931172736386,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004533025406388119,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.22385022342205046,
|
|
"num_tokens": 47450028.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 5.385936498641968,
|
|
"epoch": 2.1546107584363514,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004532843814928059,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.22707061022520064,
|
|
"num_tokens": 47459617.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 5.35529899597168,
|
|
"epoch": 2.1550283995990647,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004532662192257172,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.23761700391769408,
|
|
"num_tokens": 47468748.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 5.366266584396362,
|
|
"epoch": 2.1554460407617775,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004532480538378637,
|
|
"loss": 4.6654,
|
|
"mean_token_accuracy": 0.23375680893659592,
|
|
"num_tokens": 47477294.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 5.417829608917236,
|
|
"epoch": 2.1558636819244903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045322988532956344,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.2197042226791382,
|
|
"num_tokens": 47486733.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 5.325346565246582,
|
|
"epoch": 2.1562813230872035,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045321171370113456,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.2269553005695343,
|
|
"num_tokens": 47495472.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 5.360689449310303,
|
|
"epoch": 2.1566989642499164,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004531935389528951,
|
|
"loss": 4.7786,
|
|
"mean_token_accuracy": 0.2276393800973892,
|
|
"num_tokens": 47505048.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 5.312276172637939,
|
|
"epoch": 2.1571166054126296,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004531753610851633,
|
|
"loss": 4.7192,
|
|
"mean_token_accuracy": 0.23348613530397416,
|
|
"num_tokens": 47513635.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 5.251234483718872,
|
|
"epoch": 2.1575342465753424,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004531571800982573,
|
|
"loss": 4.6639,
|
|
"mean_token_accuracy": 0.22962263375520706,
|
|
"num_tokens": 47522861.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 5.462471055984497,
|
|
"epoch": 2.1579518877380552,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045313899599249536,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.2178700715303421,
|
|
"num_tokens": 47531986.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 5.396896076202393,
|
|
"epoch": 2.1583695289007685,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045312080876819597,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.21320749074220657,
|
|
"num_tokens": 47542140.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 5.280851936340332,
|
|
"epoch": 2.1587871700634813,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004531026184256773,
|
|
"loss": 4.6233,
|
|
"mean_token_accuracy": 0.23800602555274963,
|
|
"num_tokens": 47550921.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 5.301435422897339,
|
|
"epoch": 2.1592048112261946,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000453084424965258,
|
|
"loss": 4.6138,
|
|
"mean_token_accuracy": 0.23539711982011796,
|
|
"num_tokens": 47560286.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 5.460071277618408,
|
|
"epoch": 2.1596224523889074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045306622838725644,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.2153361365199089,
|
|
"num_tokens": 47572089.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 5.371101713180542,
|
|
"epoch": 2.1600400935516206,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004530480286919912,
|
|
"loss": 4.7346,
|
|
"mean_token_accuracy": 0.22897447049617767,
|
|
"num_tokens": 47581602.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 5.3154980659484865,
|
|
"epoch": 2.1604577347143334,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000453029825879781,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.23275822699069976,
|
|
"num_tokens": 47591138.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 5.285853910446167,
|
|
"epoch": 2.1608753758770463,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045301161995094433,
|
|
"loss": 4.6684,
|
|
"mean_token_accuracy": 0.23136191219091415,
|
|
"num_tokens": 47600182.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 5.432312774658203,
|
|
"epoch": 2.1612930170397595,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045299341090579995,
|
|
"loss": 4.8698,
|
|
"mean_token_accuracy": 0.21968204528093338,
|
|
"num_tokens": 47610207.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 5.373563671112061,
|
|
"epoch": 2.1617106582024723,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004529751987446667,
|
|
"loss": 4.7112,
|
|
"mean_token_accuracy": 0.2277180939912796,
|
|
"num_tokens": 47620276.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 5.330798625946045,
|
|
"epoch": 2.1621282993651856,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004529569834678633,
|
|
"loss": 4.8237,
|
|
"mean_token_accuracy": 0.22592445462942123,
|
|
"num_tokens": 47630187.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 5.381160545349121,
|
|
"epoch": 2.1625459405278984,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004529387650757088,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.22707514613866805,
|
|
"num_tokens": 47639187.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 5.314398574829101,
|
|
"epoch": 2.1629635816906116,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045292054356852195,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.23052653521299363,
|
|
"num_tokens": 47649272.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 5.281086254119873,
|
|
"epoch": 2.1633812228533245,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004529023189466219,
|
|
"loss": 4.5986,
|
|
"mean_token_accuracy": 0.2394743412733078,
|
|
"num_tokens": 47658046.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 5.2616973400115965,
|
|
"epoch": 2.1637988640160373,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045288409121032756,
|
|
"loss": 4.585,
|
|
"mean_token_accuracy": 0.2460864007472992,
|
|
"num_tokens": 47666658.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 5.326224040985108,
|
|
"epoch": 2.1642165051787505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045286586035995813,
|
|
"loss": 4.6909,
|
|
"mean_token_accuracy": 0.23210193663835527,
|
|
"num_tokens": 47676455.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 5.318641996383667,
|
|
"epoch": 2.1646341463414633,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045284762639583265,
|
|
"loss": 4.6591,
|
|
"mean_token_accuracy": 0.23260608017444612,
|
|
"num_tokens": 47685518.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 5.306397819519043,
|
|
"epoch": 2.1650517875041766,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045282938931827046,
|
|
"loss": 4.7511,
|
|
"mean_token_accuracy": 0.2313137859106064,
|
|
"num_tokens": 47695070.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 5.373465919494629,
|
|
"epoch": 2.1654694286668894,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004528111491275907,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.22849372178316116,
|
|
"num_tokens": 47704650.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 5.368439626693726,
|
|
"epoch": 2.165887069829602,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004527929058241128,
|
|
"loss": 4.7732,
|
|
"mean_token_accuracy": 0.22813916504383086,
|
|
"num_tokens": 47714263.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 5.398768186569214,
|
|
"epoch": 2.1663047109923155,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045277465940815603,
|
|
"loss": 4.7815,
|
|
"mean_token_accuracy": 0.22962057888507842,
|
|
"num_tokens": 47723448.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 5.335836029052734,
|
|
"epoch": 2.1667223521550283,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004527564098800399,
|
|
"loss": 4.6947,
|
|
"mean_token_accuracy": 0.23776886612176895,
|
|
"num_tokens": 47731841.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 5.290688848495483,
|
|
"epoch": 2.1671399933177415,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004527381572400838,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.23292073905467986,
|
|
"num_tokens": 47741422.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 5.311442279815674,
|
|
"epoch": 2.1675576344804544,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045271990148860737,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.2282976448535919,
|
|
"num_tokens": 47750601.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 5.364507055282592,
|
|
"epoch": 2.167975275643167,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045270164262593013,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.22042539566755295,
|
|
"num_tokens": 47759992.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 5.2622551918029785,
|
|
"epoch": 2.1683929168058804,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004526833806523717,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.22731190025806428,
|
|
"num_tokens": 47769548.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 5.375529479980469,
|
|
"epoch": 2.1688105579685932,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045266511556825184,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.2160143420100212,
|
|
"num_tokens": 47778998.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 5.387628030776978,
|
|
"epoch": 2.1692281991313065,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045264684737389026,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.22836781144142151,
|
|
"num_tokens": 47787931.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 5.376529884338379,
|
|
"epoch": 2.1696458402940193,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045262857606960684,
|
|
"loss": 4.7093,
|
|
"mean_token_accuracy": 0.22901300638914107,
|
|
"num_tokens": 47797421.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 5.389787864685059,
|
|
"epoch": 2.1700634814567326,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045261030165572134,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.22351631373167039,
|
|
"num_tokens": 47807153.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 5.405753660202026,
|
|
"epoch": 2.1704811226194454,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004525920241325537,
|
|
"loss": 4.8083,
|
|
"mean_token_accuracy": 0.22898007333278655,
|
|
"num_tokens": 47816840.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 5.424396276473999,
|
|
"epoch": 2.170898763782158,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004525737435004239,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.2236946165561676,
|
|
"num_tokens": 47825997.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 5.40252423286438,
|
|
"epoch": 2.1713164049448714,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000452555459759652,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.22909159511327742,
|
|
"num_tokens": 47834106.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 5.36379976272583,
|
|
"epoch": 2.1717340461075842,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004525371729105581,
|
|
"loss": 4.6868,
|
|
"mean_token_accuracy": 0.23951881229877472,
|
|
"num_tokens": 47843161.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 5.329529714584351,
|
|
"epoch": 2.1721516872702975,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004525188829534622,
|
|
"loss": 4.6809,
|
|
"mean_token_accuracy": 0.23450845032930373,
|
|
"num_tokens": 47852396.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 5.386757326126099,
|
|
"epoch": 2.1725693284330103,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004525005898886847,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.23072062730789183,
|
|
"num_tokens": 47861070.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 5.37244143486023,
|
|
"epoch": 2.1729869695957236,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004524822937165456,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.22013227492570878,
|
|
"num_tokens": 47869771.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 5.404866647720337,
|
|
"epoch": 2.1734046107584364,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045246399443736536,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.22693028002977372,
|
|
"num_tokens": 47879447.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 5.375105667114258,
|
|
"epoch": 2.173822251921149,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045244569205146425,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.2328808143734932,
|
|
"num_tokens": 47887415.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 5.412017726898194,
|
|
"epoch": 2.1742398930838625,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004524273865591627,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.2199765056371689,
|
|
"num_tokens": 47896898.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 5.357611417770386,
|
|
"epoch": 2.1746575342465753,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045240907796078125,
|
|
"loss": 4.7345,
|
|
"mean_token_accuracy": 0.2302977979183197,
|
|
"num_tokens": 47906453.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 5.419206237792968,
|
|
"epoch": 2.1750751754092885,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004523907662566403,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.21722971498966218,
|
|
"num_tokens": 47916614.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 5.372795820236206,
|
|
"epoch": 2.1754928165720013,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045237245144706044,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.2220775604248047,
|
|
"num_tokens": 47925924.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 5.418214225769043,
|
|
"epoch": 2.175910457734714,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004523541335323624,
|
|
"loss": 4.7938,
|
|
"mean_token_accuracy": 0.22512005269527435,
|
|
"num_tokens": 47934706.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 5.443379926681518,
|
|
"epoch": 2.1763280988974274,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004523358125128667,
|
|
"loss": 4.8404,
|
|
"mean_token_accuracy": 0.21610290855169295,
|
|
"num_tokens": 47944885.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 5.3785165309906,
|
|
"epoch": 2.17674574006014,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004523174883888941,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.2268787533044815,
|
|
"num_tokens": 47953491.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 5.410818243026734,
|
|
"epoch": 2.1771633812228535,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004522991611607655,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.22205788046121597,
|
|
"num_tokens": 47962583.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 5.378811311721802,
|
|
"epoch": 2.1775810223855663,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045228083082880164,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.2277689665555954,
|
|
"num_tokens": 47971213.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 5.467317581176758,
|
|
"epoch": 2.177998663548279,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004522624973933234,
|
|
"loss": 4.8926,
|
|
"mean_token_accuracy": 0.21691239774227142,
|
|
"num_tokens": 47981001.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 5.409117317199707,
|
|
"epoch": 2.1784163047109923,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045224416085465195,
|
|
"loss": 4.7628,
|
|
"mean_token_accuracy": 0.22436207979917527,
|
|
"num_tokens": 47989765.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 5.443541860580444,
|
|
"epoch": 2.178833945873705,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045222582121310793,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.23593163937330247,
|
|
"num_tokens": 47999676.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 5.369239234924317,
|
|
"epoch": 2.1792515870364184,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045220747846901266,
|
|
"loss": 4.7533,
|
|
"mean_token_accuracy": 0.22576755285263062,
|
|
"num_tokens": 48009181.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 5.265188550949096,
|
|
"epoch": 2.1796692281991312,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045218913262268717,
|
|
"loss": 4.6177,
|
|
"mean_token_accuracy": 0.23892796486616136,
|
|
"num_tokens": 48018436.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 5.355170679092407,
|
|
"epoch": 2.1800868693618445,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045217078367445264,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.2311085045337677,
|
|
"num_tokens": 48027527.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 5.397193336486817,
|
|
"epoch": 2.1805045105245573,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045215243162463023,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.23384435325860978,
|
|
"num_tokens": 48037432.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 5.397238492965698,
|
|
"epoch": 2.18092215168727,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004521340764735413,
|
|
"loss": 4.8111,
|
|
"mean_token_accuracy": 0.22411797791719437,
|
|
"num_tokens": 48046037.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 5.340718364715576,
|
|
"epoch": 2.1813397928499834,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004521157182215071,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.22896413505077362,
|
|
"num_tokens": 48055197.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 5.4328044891357425,
|
|
"epoch": 2.181757434012696,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045209735686884913,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.20431748777627945,
|
|
"num_tokens": 48064152.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 5.373296689987183,
|
|
"epoch": 2.1821750751754094,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045207899241588874,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.22998717725276946,
|
|
"num_tokens": 48073765.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 5.378681087493897,
|
|
"epoch": 2.1825927163381222,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004520606248629474,
|
|
"loss": 4.6589,
|
|
"mean_token_accuracy": 0.24038797616958618,
|
|
"num_tokens": 48082816.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 5.385482740402222,
|
|
"epoch": 2.1830103575008355,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004520422542103467,
|
|
"loss": 4.7402,
|
|
"mean_token_accuracy": 0.23278848081827164,
|
|
"num_tokens": 48091841.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 5.286420583724976,
|
|
"epoch": 2.1834279986635483,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004520238804584083,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.2289387911558151,
|
|
"num_tokens": 48102162.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 5.369347763061524,
|
|
"epoch": 2.183845639826261,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004520055036074538,
|
|
"loss": 4.7234,
|
|
"mean_token_accuracy": 0.2303120583295822,
|
|
"num_tokens": 48111092.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 5.278242826461792,
|
|
"epoch": 2.1842632809889744,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004519871236578048,
|
|
"loss": 4.6199,
|
|
"mean_token_accuracy": 0.2324981912970543,
|
|
"num_tokens": 48119643.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 5.298744106292725,
|
|
"epoch": 2.184680922151687,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004519687406097832,
|
|
"loss": 4.6612,
|
|
"mean_token_accuracy": 0.2301903948187828,
|
|
"num_tokens": 48128685.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 5.265974712371826,
|
|
"epoch": 2.1850985633144004,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004519503544637107,
|
|
"loss": 4.714,
|
|
"mean_token_accuracy": 0.23948421627283095,
|
|
"num_tokens": 48137645.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 5.381018447875976,
|
|
"epoch": 2.1855162044771133,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045193196521990935,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.22716221064329148,
|
|
"num_tokens": 48147240.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 5.37736439704895,
|
|
"epoch": 2.185933845639826,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000451913572878701,
|
|
"loss": 4.7631,
|
|
"mean_token_accuracy": 0.22443698197603226,
|
|
"num_tokens": 48156992.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 5.436728048324585,
|
|
"epoch": 2.1863514868025393,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004518951774404076,
|
|
"loss": 4.787,
|
|
"mean_token_accuracy": 0.21932873725891114,
|
|
"num_tokens": 48165864.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 5.437303304672241,
|
|
"epoch": 2.186769127965252,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004518767789053511,
|
|
"loss": 4.8104,
|
|
"mean_token_accuracy": 0.2252473548054695,
|
|
"num_tokens": 48174676.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 5.325312757492066,
|
|
"epoch": 2.1871867691279654,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045185837727385373,
|
|
"loss": 4.6302,
|
|
"mean_token_accuracy": 0.23587611615657805,
|
|
"num_tokens": 48182838.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 5.448114442825317,
|
|
"epoch": 2.187604410290678,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004518399725462376,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.22204950898885728,
|
|
"num_tokens": 48192087.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 5.358176565170288,
|
|
"epoch": 2.188022051453391,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004518215647228248,
|
|
"loss": 4.7073,
|
|
"mean_token_accuracy": 0.2246343582868576,
|
|
"num_tokens": 48201020.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 5.400158166885376,
|
|
"epoch": 2.1884396926161043,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045180315380393776,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.22750307470560074,
|
|
"num_tokens": 48210672.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 5.3884202003479,
|
|
"epoch": 2.188857333778817,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004517847397898987,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.22494769245386123,
|
|
"num_tokens": 48220669.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 5.285698509216308,
|
|
"epoch": 2.1892749749415303,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045176632268102994,
|
|
"loss": 4.5688,
|
|
"mean_token_accuracy": 0.25006058663129804,
|
|
"num_tokens": 48230198.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 5.406609058380127,
|
|
"epoch": 2.189692616104243,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000451747902477654,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.21494995951652526,
|
|
"num_tokens": 48239854.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 5.428523349761963,
|
|
"epoch": 2.1901102572669564,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045172947918009317,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.21795451194047927,
|
|
"num_tokens": 48249239.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 5.392269515991211,
|
|
"epoch": 2.190527898429669,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004517110527886701,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.23205460608005524,
|
|
"num_tokens": 48258196.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 5.331954097747802,
|
|
"epoch": 2.190945539592382,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004516926233037074,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.22822188585996628,
|
|
"num_tokens": 48267102.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 5.35989465713501,
|
|
"epoch": 2.1913631807550953,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004516741907255276,
|
|
"loss": 4.7589,
|
|
"mean_token_accuracy": 0.22467005550861358,
|
|
"num_tokens": 48276273.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 5.33004059791565,
|
|
"epoch": 2.191780821917808,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004516557550544534,
|
|
"loss": 4.7388,
|
|
"mean_token_accuracy": 0.22703108936548233,
|
|
"num_tokens": 48284921.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 5.324785137176514,
|
|
"epoch": 2.1921984630805214,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004516373162908077,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.23227481096982955,
|
|
"num_tokens": 48293188.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 5.445643758773803,
|
|
"epoch": 2.192616104243234,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045161887443491297,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.22616838961839675,
|
|
"num_tokens": 48301898.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 5.400191402435302,
|
|
"epoch": 2.1930337454059474,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045160042948709235,
|
|
"loss": 4.6574,
|
|
"mean_token_accuracy": 0.236155104637146,
|
|
"num_tokens": 48310291.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 5.385968542098999,
|
|
"epoch": 2.1934513865686602,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045158198144766863,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.23224087655544282,
|
|
"num_tokens": 48318922.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 5.297179698944092,
|
|
"epoch": 2.193869027731373,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004515635303169648,
|
|
"loss": 4.7047,
|
|
"mean_token_accuracy": 0.240200474858284,
|
|
"num_tokens": 48327843.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 5.338867139816284,
|
|
"epoch": 2.1942866688940863,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045154507609530375,
|
|
"loss": 4.8043,
|
|
"mean_token_accuracy": 0.22838473469018936,
|
|
"num_tokens": 48336756.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 5.418330812454224,
|
|
"epoch": 2.194704310056799,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004515266187830087,
|
|
"loss": 4.8603,
|
|
"mean_token_accuracy": 0.21918679475784303,
|
|
"num_tokens": 48346813.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 5.415851593017578,
|
|
"epoch": 2.1951219512195124,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045150815838040275,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.23109295964241028,
|
|
"num_tokens": 48355416.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 5.523415184020996,
|
|
"epoch": 2.195539592382225,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045148969488780893,
|
|
"loss": 4.8614,
|
|
"mean_token_accuracy": 0.21604250967502595,
|
|
"num_tokens": 48364824.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 5.3737749576568605,
|
|
"epoch": 2.195957233544938,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004514712283055506,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.22563062161207198,
|
|
"num_tokens": 48375016.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 5.335462665557861,
|
|
"epoch": 2.1963748747076512,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004514527586339511,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.23549628853797913,
|
|
"num_tokens": 48383232.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 5.407355499267578,
|
|
"epoch": 2.196792515870364,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045143428587333354,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.22187615633010865,
|
|
"num_tokens": 48392374.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 5.406736612319946,
|
|
"epoch": 2.1972101570330773,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004514158100240214,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.21728114634752274,
|
|
"num_tokens": 48401471.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 5.433621168136597,
|
|
"epoch": 2.19762779819579,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004513973310863383,
|
|
"loss": 4.8167,
|
|
"mean_token_accuracy": 0.22005716264247893,
|
|
"num_tokens": 48410585.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 5.3736512660980225,
|
|
"epoch": 2.198045439358503,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045137884906060747,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.22765690535306932,
|
|
"num_tokens": 48419563.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 5.325711059570312,
|
|
"epoch": 2.198463080521216,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004513603639471526,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.23020009696483612,
|
|
"num_tokens": 48429801.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 5.354359865188599,
|
|
"epoch": 2.198880721683929,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004513418757462973,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.23054102510213853,
|
|
"num_tokens": 48437953.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 5.387688541412354,
|
|
"epoch": 2.1992983628466423,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045132338445836516,
|
|
"loss": 4.749,
|
|
"mean_token_accuracy": 0.22922405153512954,
|
|
"num_tokens": 48447733.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 5.3664933204650875,
|
|
"epoch": 2.199716004009355,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045130489008367997,
|
|
"loss": 4.6857,
|
|
"mean_token_accuracy": 0.23182185590267182,
|
|
"num_tokens": 48456530.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 5.333325910568237,
|
|
"epoch": 2.2001336451720683,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004512863926225655,
|
|
"loss": 4.7085,
|
|
"mean_token_accuracy": 0.23128093779087067,
|
|
"num_tokens": 48465607.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 5.3773338317871096,
|
|
"epoch": 2.200551286334781,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045126789207534544,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.2351269856095314,
|
|
"num_tokens": 48474112.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 5.3609294414520265,
|
|
"epoch": 2.200968927497494,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045124938844234386,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.23732156604528426,
|
|
"num_tokens": 48482677.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 5.340453958511352,
|
|
"epoch": 2.201386568660207,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045123088172388455,
|
|
"loss": 4.6549,
|
|
"mean_token_accuracy": 0.23512125313282012,
|
|
"num_tokens": 48491313.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 5.3419272899627686,
|
|
"epoch": 2.20180420982292,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045121237192029154,
|
|
"loss": 4.7622,
|
|
"mean_token_accuracy": 0.23414914458990096,
|
|
"num_tokens": 48501106.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 5.425551462173462,
|
|
"epoch": 2.2022218509856333,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045119385903188877,
|
|
"loss": 4.7538,
|
|
"mean_token_accuracy": 0.22526179105043412,
|
|
"num_tokens": 48511219.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 5.326708555221558,
|
|
"epoch": 2.202639492148346,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004511753430590004,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.23681213557720185,
|
|
"num_tokens": 48520436.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 5.335751056671143,
|
|
"epoch": 2.2030571333110593,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004511568240019507,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.222026489675045,
|
|
"num_tokens": 48531516.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 5.387621259689331,
|
|
"epoch": 2.203474774473772,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045113830186106367,
|
|
"loss": 4.6588,
|
|
"mean_token_accuracy": 0.23410428315401077,
|
|
"num_tokens": 48540512.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 5.415590810775757,
|
|
"epoch": 2.203892415636485,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004511197766366637,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.21902708560228348,
|
|
"num_tokens": 48550273.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 5.297098398208618,
|
|
"epoch": 2.2043100567991982,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045110124832907505,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.2327315554022789,
|
|
"num_tokens": 48558606.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 5.29793152809143,
|
|
"epoch": 2.204727697961911,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004510827169386221,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.22808943092823028,
|
|
"num_tokens": 48567167.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 5.3343038082122805,
|
|
"epoch": 2.2051453391246243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004510641824656292,
|
|
"loss": 4.7418,
|
|
"mean_token_accuracy": 0.22264289259910583,
|
|
"num_tokens": 48576275.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 5.3419736385345455,
|
|
"epoch": 2.205562980287337,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004510456449104208,
|
|
"loss": 4.7114,
|
|
"mean_token_accuracy": 0.2298141360282898,
|
|
"num_tokens": 48585217.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 5.349953985214233,
|
|
"epoch": 2.20598062145005,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004510271042733215,
|
|
"loss": 4.7071,
|
|
"mean_token_accuracy": 0.22593406736850738,
|
|
"num_tokens": 48594583.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 5.261810541152954,
|
|
"epoch": 2.206398262612763,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004510085605546559,
|
|
"loss": 4.6308,
|
|
"mean_token_accuracy": 0.24149596989154815,
|
|
"num_tokens": 48603677.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 5.405247020721435,
|
|
"epoch": 2.206815903775476,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045099001375474855,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.22645646184682847,
|
|
"num_tokens": 48614453.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 5.3121438980102536,
|
|
"epoch": 2.2072335449381892,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045097146387392423,
|
|
"loss": 4.723,
|
|
"mean_token_accuracy": 0.23553441166877748,
|
|
"num_tokens": 48622871.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 5.300861454010009,
|
|
"epoch": 2.207651186100902,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045095291091250755,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.22498246431350707,
|
|
"num_tokens": 48631466.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 5.3065448760986325,
|
|
"epoch": 2.2080688272636153,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004509343548708235,
|
|
"loss": 4.6554,
|
|
"mean_token_accuracy": 0.23823681771755217,
|
|
"num_tokens": 48640020.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 5.332465553283692,
|
|
"epoch": 2.208486468426328,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004509157957491966,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.23012900948524476,
|
|
"num_tokens": 48648428.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 5.350604391098022,
|
|
"epoch": 2.208904109589041,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045089723354795204,
|
|
"loss": 4.61,
|
|
"mean_token_accuracy": 0.2409459948539734,
|
|
"num_tokens": 48657232.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 5.25809531211853,
|
|
"epoch": 2.209321750751754,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004508786682674147,
|
|
"loss": 4.6266,
|
|
"mean_token_accuracy": 0.23388035893440245,
|
|
"num_tokens": 48665802.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 5.318109464645386,
|
|
"epoch": 2.209739391914467,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045086009990790956,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.24251673072576524,
|
|
"num_tokens": 48674622.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 5.293404293060303,
|
|
"epoch": 2.2101570330771803,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045084152846976166,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.23428912907838823,
|
|
"num_tokens": 48683365.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 5.358039712905883,
|
|
"epoch": 2.210574674239893,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045082295395329616,
|
|
"loss": 4.6936,
|
|
"mean_token_accuracy": 0.23233231157064438,
|
|
"num_tokens": 48693554.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 5.362673139572143,
|
|
"epoch": 2.210992315402606,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004508043763588382,
|
|
"loss": 4.7178,
|
|
"mean_token_accuracy": 0.23386016935110093,
|
|
"num_tokens": 48702892.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 5.386020612716675,
|
|
"epoch": 2.211409956565319,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045078579568671307,
|
|
"loss": 4.7394,
|
|
"mean_token_accuracy": 0.23202573955059053,
|
|
"num_tokens": 48712036.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 5.3939094066619875,
|
|
"epoch": 2.211827597728032,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004507672119372459,
|
|
"loss": 4.7881,
|
|
"mean_token_accuracy": 0.2282558336853981,
|
|
"num_tokens": 48721462.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 5.376084423065185,
|
|
"epoch": 2.212245238890745,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045074862511076215,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.22508648484945298,
|
|
"num_tokens": 48730542.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 5.353623914718628,
|
|
"epoch": 2.212662880053458,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004507300352075872,
|
|
"loss": 4.748,
|
|
"mean_token_accuracy": 0.22527074962854385,
|
|
"num_tokens": 48739477.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 5.415708684921265,
|
|
"epoch": 2.2130805212161713,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045071144222804646,
|
|
"loss": 4.7559,
|
|
"mean_token_accuracy": 0.23225770890712738,
|
|
"num_tokens": 48748945.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 5.389697170257568,
|
|
"epoch": 2.213498162378884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004506928461724654,
|
|
"loss": 4.7799,
|
|
"mean_token_accuracy": 0.22973280251026154,
|
|
"num_tokens": 48757762.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 5.503439235687256,
|
|
"epoch": 2.213915803541597,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045067424704116956,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.21877578049898147,
|
|
"num_tokens": 48767773.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 5.367960977554321,
|
|
"epoch": 2.21433344470431,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004506556448344846,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.22624098807573317,
|
|
"num_tokens": 48777499.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 5.35555067062378,
|
|
"epoch": 2.214751085867023,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004506370395527362,
|
|
"loss": 4.6723,
|
|
"mean_token_accuracy": 0.23263878226280213,
|
|
"num_tokens": 48786499.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 5.3793610572814945,
|
|
"epoch": 2.215168727029736,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045061843119624984,
|
|
"loss": 4.7794,
|
|
"mean_token_accuracy": 0.22980669289827346,
|
|
"num_tokens": 48795086.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 5.319449710845947,
|
|
"epoch": 2.215586368192449,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004505998197653516,
|
|
"loss": 4.6764,
|
|
"mean_token_accuracy": 0.224442557990551,
|
|
"num_tokens": 48804131.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 5.3518575668334964,
|
|
"epoch": 2.216004009355162,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004505812052603671,
|
|
"loss": 4.7819,
|
|
"mean_token_accuracy": 0.2223615050315857,
|
|
"num_tokens": 48812986.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 5.535912942886353,
|
|
"epoch": 2.216421650517875,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004505625876816222,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.22570284456014633,
|
|
"num_tokens": 48822200.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 5.50335578918457,
|
|
"epoch": 2.216839291680588,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045054396702944293,
|
|
"loss": 4.7876,
|
|
"mean_token_accuracy": 0.23095437586307527,
|
|
"num_tokens": 48831485.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 5.203760814666748,
|
|
"epoch": 2.217256932843301,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045052534330415525,
|
|
"loss": 4.5741,
|
|
"mean_token_accuracy": 0.24025067538022996,
|
|
"num_tokens": 48840515.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 5.284548091888428,
|
|
"epoch": 2.217674574006014,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045050671650608513,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.22599742263555528,
|
|
"num_tokens": 48849248.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 5.375699281692505,
|
|
"epoch": 2.2180922151687272,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004504880866355587,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.22310552150011062,
|
|
"num_tokens": 48858593.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 5.436180257797242,
|
|
"epoch": 2.21850985633144,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000450469453692902,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.21978774219751357,
|
|
"num_tokens": 48867859.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 5.404941415786743,
|
|
"epoch": 2.218927497494153,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045045081767844137,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.23846741765737534,
|
|
"num_tokens": 48877556.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 5.423662424087524,
|
|
"epoch": 2.219345138656866,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000450432178592503,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.22634944468736648,
|
|
"num_tokens": 48887468.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 5.382118082046508,
|
|
"epoch": 2.219762779819579,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004504135364354131,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.2354352667927742,
|
|
"num_tokens": 48895683.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 5.387938499450684,
|
|
"epoch": 2.220180420982292,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045039489120749816,
|
|
"loss": 4.806,
|
|
"mean_token_accuracy": 0.2235330194234848,
|
|
"num_tokens": 48904522.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 5.414706802368164,
|
|
"epoch": 2.220598062145005,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004503762429090845,
|
|
"loss": 4.8376,
|
|
"mean_token_accuracy": 0.22284009009599687,
|
|
"num_tokens": 48914091.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 5.378297185897827,
|
|
"epoch": 2.221015703307718,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004503575915404986,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.22982069700956345,
|
|
"num_tokens": 48922652.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 5.445856094360352,
|
|
"epoch": 2.221433344470431,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000450338937102067,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.21838423609733582,
|
|
"num_tokens": 48931512.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 5.351695346832275,
|
|
"epoch": 2.221850985633144,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045032027959411624,
|
|
"loss": 4.7444,
|
|
"mean_token_accuracy": 0.2244924858212471,
|
|
"num_tokens": 48940456.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 5.403873634338379,
|
|
"epoch": 2.222268626795857,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000450301619016973,
|
|
"loss": 4.8491,
|
|
"mean_token_accuracy": 0.22046782970428466,
|
|
"num_tokens": 48951109.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 5.391577577590942,
|
|
"epoch": 2.22268626795857,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045028295537096385,
|
|
"loss": 4.6831,
|
|
"mean_token_accuracy": 0.22998274117708206,
|
|
"num_tokens": 48959586.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 5.3277607440948485,
|
|
"epoch": 2.223103909121283,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045026428865641563,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.2301375150680542,
|
|
"num_tokens": 48968393.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 5.324921989440918,
|
|
"epoch": 2.223521550283996,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000450245618873655,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.2231983110308647,
|
|
"num_tokens": 48977483.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 5.4363319873809814,
|
|
"epoch": 2.223939191446709,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004502269460230089,
|
|
"loss": 4.7958,
|
|
"mean_token_accuracy": 0.21636474132537842,
|
|
"num_tokens": 48986568.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 5.394311189651489,
|
|
"epoch": 2.224356832609422,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004502082701048042,
|
|
"loss": 4.751,
|
|
"mean_token_accuracy": 0.2254468858242035,
|
|
"num_tokens": 48995952.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 5.3644624710083,
|
|
"epoch": 2.224774473772135,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045018959111936785,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.22081439793109894,
|
|
"num_tokens": 49006168.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 5.384062623977661,
|
|
"epoch": 2.225192114934848,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004501709090670268,
|
|
"loss": 4.7013,
|
|
"mean_token_accuracy": 0.23030392825603485,
|
|
"num_tokens": 49014903.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 5.362250137329101,
|
|
"epoch": 2.225609756097561,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004501522239481081,
|
|
"loss": 4.7558,
|
|
"mean_token_accuracy": 0.2335392251610756,
|
|
"num_tokens": 49024801.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 5.4019921779632565,
|
|
"epoch": 2.2260273972602738,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045013353576293897,
|
|
"loss": 4.7258,
|
|
"mean_token_accuracy": 0.2250186249613762,
|
|
"num_tokens": 49033822.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 5.420104932785034,
|
|
"epoch": 2.226445038422987,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045011484451184646,
|
|
"loss": 4.7198,
|
|
"mean_token_accuracy": 0.2304939240217209,
|
|
"num_tokens": 49044074.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 5.380058908462525,
|
|
"epoch": 2.2268626795857,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045009615019515783,
|
|
"loss": 4.7446,
|
|
"mean_token_accuracy": 0.22742853164672852,
|
|
"num_tokens": 49053090.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 5.277859449386597,
|
|
"epoch": 2.227280320748413,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045007745281320035,
|
|
"loss": 4.6995,
|
|
"mean_token_accuracy": 0.2332669362425804,
|
|
"num_tokens": 49061652.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 5.342133855819702,
|
|
"epoch": 2.227697961911126,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045005875236630124,
|
|
"loss": 4.6413,
|
|
"mean_token_accuracy": 0.2392354875802994,
|
|
"num_tokens": 49070196.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 5.393146228790283,
|
|
"epoch": 2.228115603073839,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045004004885478797,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.22739704996347426,
|
|
"num_tokens": 49079422.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 5.311677646636963,
|
|
"epoch": 2.228533244236552,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000450021342278988,
|
|
"loss": 4.7121,
|
|
"mean_token_accuracy": 0.22664135545492173,
|
|
"num_tokens": 49089010.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 5.308481597900391,
|
|
"epoch": 2.228950885399265,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004500026326392287,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.23609524220228195,
|
|
"num_tokens": 49097153.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 5.331559038162231,
|
|
"epoch": 2.229368526561978,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044998391993583773,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.2305062770843506,
|
|
"num_tokens": 49107741.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 5.426048421859742,
|
|
"epoch": 2.229786167724691,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004499652041691425,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.22978805452585221,
|
|
"num_tokens": 49117182.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 5.400413656234742,
|
|
"epoch": 2.230203808887404,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004499464853394709,
|
|
"loss": 4.8129,
|
|
"mean_token_accuracy": 0.22443142980337144,
|
|
"num_tokens": 49128036.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 5.372588157653809,
|
|
"epoch": 2.230621450050117,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044992776344715036,
|
|
"loss": 4.6912,
|
|
"mean_token_accuracy": 0.22996868044137955,
|
|
"num_tokens": 49137669.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 5.336092329025268,
|
|
"epoch": 2.23103909121283,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004499090384925088,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.22688684165477752,
|
|
"num_tokens": 49147447.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 5.357173061370849,
|
|
"epoch": 2.231456732375543,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044989031047587406,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.2224739044904709,
|
|
"num_tokens": 49156516.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 5.447793674468994,
|
|
"epoch": 2.231874373538256,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004498715793975738,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.22219735383987427,
|
|
"num_tokens": 49165735.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 5.381937074661255,
|
|
"epoch": 2.232292014700969,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044985284525793617,
|
|
"loss": 4.713,
|
|
"mean_token_accuracy": 0.22665748447179795,
|
|
"num_tokens": 49174389.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 5.3245481014251705,
|
|
"epoch": 2.232709655863682,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004498341080572889,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.2266136810183525,
|
|
"num_tokens": 49183521.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 5.315963888168335,
|
|
"epoch": 2.233127297026395,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044981536779596025,
|
|
"loss": 4.6975,
|
|
"mean_token_accuracy": 0.23404491245746611,
|
|
"num_tokens": 49192971.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 5.392995071411133,
|
|
"epoch": 2.233544938189108,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004497966244742781,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.2302754506468773,
|
|
"num_tokens": 49201502.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 5.33383092880249,
|
|
"epoch": 2.2339625793518207,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004497778780925706,
|
|
"loss": 4.6803,
|
|
"mean_token_accuracy": 0.23071939051151275,
|
|
"num_tokens": 49211096.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 5.4062422752380375,
|
|
"epoch": 2.234380220514534,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044975912865116604,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.22506039142608641,
|
|
"num_tokens": 49221447.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 5.3899468898773195,
|
|
"epoch": 2.234797861677247,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044974037615039253,
|
|
"loss": 4.7077,
|
|
"mean_token_accuracy": 0.22905313670635224,
|
|
"num_tokens": 49229572.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 5.408345365524292,
|
|
"epoch": 2.23521550283996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044972162059057837,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.22199991196393967,
|
|
"num_tokens": 49239184.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 5.337155103683472,
|
|
"epoch": 2.235633144002673,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044970286197205196,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.23097819834947586,
|
|
"num_tokens": 49248844.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 5.383642721176147,
|
|
"epoch": 2.2360507851653857,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004496841002951416,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.22505152225494385,
|
|
"num_tokens": 49258028.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 5.3644672393798825,
|
|
"epoch": 2.236468426328099,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004496653355601759,
|
|
"loss": 4.7324,
|
|
"mean_token_accuracy": 0.22671395689249038,
|
|
"num_tokens": 49267590.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 5.332528114318848,
|
|
"epoch": 2.2368860674908118,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004496465677674832,
|
|
"loss": 4.6506,
|
|
"mean_token_accuracy": 0.2366539403796196,
|
|
"num_tokens": 49275897.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 5.334475135803222,
|
|
"epoch": 2.237303708653525,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004496277969173921,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.22701346129179,
|
|
"num_tokens": 49285853.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 5.361167478561401,
|
|
"epoch": 2.237721349816238,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044960902301023126,
|
|
"loss": 4.6511,
|
|
"mean_token_accuracy": 0.23982570171356202,
|
|
"num_tokens": 49295129.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 5.254728651046753,
|
|
"epoch": 2.238138990978951,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004495902460463293,
|
|
"loss": 4.6031,
|
|
"mean_token_accuracy": 0.23951115608215331,
|
|
"num_tokens": 49304117.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 5.2955223560333256,
|
|
"epoch": 2.238556632141664,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004495714660260149,
|
|
"loss": 4.6266,
|
|
"mean_token_accuracy": 0.2359059914946556,
|
|
"num_tokens": 49312872.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 5.475673770904541,
|
|
"epoch": 2.2389742733043767,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044955268294961687,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.2192741811275482,
|
|
"num_tokens": 49322081.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 5.373735237121582,
|
|
"epoch": 2.23939191446709,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044953389681746405,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.23269926011562347,
|
|
"num_tokens": 49331288.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 5.343351125717163,
|
|
"epoch": 2.2398095556298028,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004495151076298852,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.2241105243563652,
|
|
"num_tokens": 49341135.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 5.354781770706177,
|
|
"epoch": 2.240227196792516,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004494963153872093,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.22688378244638444,
|
|
"num_tokens": 49350450.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 5.449353647232056,
|
|
"epoch": 2.240644837955229,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044947752008976546,
|
|
"loss": 4.7856,
|
|
"mean_token_accuracy": 0.2290486738085747,
|
|
"num_tokens": 49358719.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 5.3819921016693115,
|
|
"epoch": 2.241062479117942,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004494587217378826,
|
|
"loss": 4.6882,
|
|
"mean_token_accuracy": 0.23414604216814042,
|
|
"num_tokens": 49366976.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 5.313680601119995,
|
|
"epoch": 2.241480120280655,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044943992033188974,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.22564954161643982,
|
|
"num_tokens": 49376256.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 5.299866676330566,
|
|
"epoch": 2.2418977614433677,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004494211158721162,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.23152197599411012,
|
|
"num_tokens": 49385120.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 5.373221492767334,
|
|
"epoch": 2.242315402606081,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000449402308358891,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.2216133564710617,
|
|
"num_tokens": 49394960.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 5.2836061954498295,
|
|
"epoch": 2.242733043768794,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004493834977925435,
|
|
"loss": 4.6137,
|
|
"mean_token_accuracy": 0.23986971527338027,
|
|
"num_tokens": 49404332.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 5.312240076065064,
|
|
"epoch": 2.243150684931507,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044936468417340294,
|
|
"loss": 4.6793,
|
|
"mean_token_accuracy": 0.23104349672794341,
|
|
"num_tokens": 49413723.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 5.369065380096435,
|
|
"epoch": 2.24356832609422,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004493458675017987,
|
|
"loss": 4.766,
|
|
"mean_token_accuracy": 0.2263701468706131,
|
|
"num_tokens": 49423188.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 5.345139789581299,
|
|
"epoch": 2.2439859672569327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004493270477780602,
|
|
"loss": 4.7397,
|
|
"mean_token_accuracy": 0.2251250684261322,
|
|
"num_tokens": 49432826.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 5.351283311843872,
|
|
"epoch": 2.244403608419646,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044930822500251693,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.22899031937122344,
|
|
"num_tokens": 49442538.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 5.402729749679565,
|
|
"epoch": 2.2448212495823587,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044928939917549833,
|
|
"loss": 4.7752,
|
|
"mean_token_accuracy": 0.23088662475347518,
|
|
"num_tokens": 49451643.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 5.38027868270874,
|
|
"epoch": 2.245238890745072,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000449270570297334,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.2293269783258438,
|
|
"num_tokens": 49460866.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 5.385161876678467,
|
|
"epoch": 2.245656531907785,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004492517383683536,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.22016261368989945,
|
|
"num_tokens": 49470750.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 5.296191072463989,
|
|
"epoch": 2.2460741730704976,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044923290338888674,
|
|
"loss": 4.736,
|
|
"mean_token_accuracy": 0.22980506718158722,
|
|
"num_tokens": 49479841.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 5.325195550918579,
|
|
"epoch": 2.246491814233211,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004492140653592632,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.2252353012561798,
|
|
"num_tokens": 49488877.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 5.412055969238281,
|
|
"epoch": 2.2469094553959237,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044919522427981276,
|
|
"loss": 4.8064,
|
|
"mean_token_accuracy": 0.21964717507362366,
|
|
"num_tokens": 49498892.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 5.462562799453735,
|
|
"epoch": 2.247327096558637,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004491763801508652,
|
|
"loss": 4.8323,
|
|
"mean_token_accuracy": 0.21866886019706727,
|
|
"num_tokens": 49507444.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 5.342144250869751,
|
|
"epoch": 2.2477447377213498,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044915753297275046,
|
|
"loss": 4.7105,
|
|
"mean_token_accuracy": 0.23494422286748887,
|
|
"num_tokens": 49516710.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 5.354715585708618,
|
|
"epoch": 2.248162378884063,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044913868274579856,
|
|
"loss": 4.7804,
|
|
"mean_token_accuracy": 0.23296496719121934,
|
|
"num_tokens": 49526945.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 5.302438402175904,
|
|
"epoch": 2.248580020046776,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044911982947033925,
|
|
"loss": 4.6317,
|
|
"mean_token_accuracy": 0.2330892339348793,
|
|
"num_tokens": 49536058.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 5.359683609008789,
|
|
"epoch": 2.2489976612094886,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004491009731467028,
|
|
"loss": 4.697,
|
|
"mean_token_accuracy": 0.23527924567461014,
|
|
"num_tokens": 49544761.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 5.457814407348633,
|
|
"epoch": 2.249415302372202,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004490821137752193,
|
|
"loss": 4.8336,
|
|
"mean_token_accuracy": 0.21608732789754867,
|
|
"num_tokens": 49553933.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 5.367505359649658,
|
|
"epoch": 2.2498329435349147,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004490632513562188,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.2290711969137192,
|
|
"num_tokens": 49563668.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 5.380937957763672,
|
|
"epoch": 2.250250584697628,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004490443858900316,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.22161647230386733,
|
|
"num_tokens": 49573830.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 5.340496397018432,
|
|
"epoch": 2.2506682258603408,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044902551737698785,
|
|
"loss": 4.7035,
|
|
"mean_token_accuracy": 0.234065243601799,
|
|
"num_tokens": 49582396.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 5.389429903030395,
|
|
"epoch": 2.251085867023054,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044900664581741805,
|
|
"loss": 4.6875,
|
|
"mean_token_accuracy": 0.23401308208703994,
|
|
"num_tokens": 49590918.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 5.403487014770508,
|
|
"epoch": 2.251503508185767,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004489877712116524,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.2267523631453514,
|
|
"num_tokens": 49600365.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 5.35978217124939,
|
|
"epoch": 2.2519211493484796,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004489688935600214,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.2239774465560913,
|
|
"num_tokens": 49610002.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 5.346573162078857,
|
|
"epoch": 2.252338790511193,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044895001286285557,
|
|
"loss": 4.7069,
|
|
"mean_token_accuracy": 0.23516086637973785,
|
|
"num_tokens": 49619085.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 5.2595783233642575,
|
|
"epoch": 2.2527564316739057,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044893112912048526,
|
|
"loss": 4.6055,
|
|
"mean_token_accuracy": 0.23483640998601912,
|
|
"num_tokens": 49627753.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 5.33183069229126,
|
|
"epoch": 2.253174072836619,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004489122423332413,
|
|
"loss": 4.6829,
|
|
"mean_token_accuracy": 0.23159523010253907,
|
|
"num_tokens": 49637377.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 5.340338230133057,
|
|
"epoch": 2.253591713999332,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044889335250145415,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.22957806587219237,
|
|
"num_tokens": 49645323.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 5.358348417282104,
|
|
"epoch": 2.2540093551620446,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004488744596254545,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.22165994048118592,
|
|
"num_tokens": 49655076.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 5.339782428741455,
|
|
"epoch": 2.254426996324758,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044885556370557317,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.22943418622016906,
|
|
"num_tokens": 49664518.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 5.282127380371094,
|
|
"epoch": 2.2548446374874707,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000448836664742141,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.24658196568489074,
|
|
"num_tokens": 49673530.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 5.3918805599212645,
|
|
"epoch": 2.255262278650184,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004488177627354887,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.2164018541574478,
|
|
"num_tokens": 49682716.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 2.255262278650184,
|
|
"eval_entropy": 5.04668585755668,
|
|
"eval_loss": 4.761164665222168,
|
|
"eval_mean_token_accuracy": 0.23855983886021068,
|
|
"eval_num_tokens": 49682716.0,
|
|
"eval_runtime": 20.9389,
|
|
"eval_samples_per_second": 1803.487,
|
|
"eval_steps_per_second": 225.466,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"entropy": 5.364469289779663,
|
|
"epoch": 2.2556799198128967,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044879885768594726,
|
|
"loss": 4.6623,
|
|
"mean_token_accuracy": 0.2266843020915985,
|
|
"num_tokens": 49691726.0,
|
|
"step": 27005
|
|
},
|
|
{
|
|
"entropy": 5.2676033020019535,
|
|
"epoch": 2.2560975609756095,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044877994959384757,
|
|
"loss": 4.6417,
|
|
"mean_token_accuracy": 0.23136099874973298,
|
|
"num_tokens": 49701021.0,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"entropy": 5.289566850662231,
|
|
"epoch": 2.256515202138323,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004487610384595207,
|
|
"loss": 4.7022,
|
|
"mean_token_accuracy": 0.23013101369142533,
|
|
"num_tokens": 49710583.0,
|
|
"step": 27015
|
|
},
|
|
{
|
|
"entropy": 5.345097303390503,
|
|
"epoch": 2.2569328433010356,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004487421242832977,
|
|
"loss": 4.7732,
|
|
"mean_token_accuracy": 0.22793676406145097,
|
|
"num_tokens": 49718365.0,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"entropy": 5.305244874954224,
|
|
"epoch": 2.257350484463749,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004487232070655097,
|
|
"loss": 4.6829,
|
|
"mean_token_accuracy": 0.23235071450471878,
|
|
"num_tokens": 49728340.0,
|
|
"step": 27025
|
|
},
|
|
{
|
|
"entropy": 5.303273344039917,
|
|
"epoch": 2.2577681256264617,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004487042868064878,
|
|
"loss": 4.6099,
|
|
"mean_token_accuracy": 0.23773182928562164,
|
|
"num_tokens": 49736061.0,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"entropy": 5.3292210578918455,
|
|
"epoch": 2.258185766789175,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004486853635065634,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.24057495296001435,
|
|
"num_tokens": 49744797.0,
|
|
"step": 27035
|
|
},
|
|
{
|
|
"entropy": 5.357313013076782,
|
|
"epoch": 2.2586034079518877,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044866643716606747,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.23455278873443602,
|
|
"num_tokens": 49754118.0,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"entropy": 5.450014877319336,
|
|
"epoch": 2.2590210491146006,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004486475077853316,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.20979419052600862,
|
|
"num_tokens": 49764721.0,
|
|
"step": 27045
|
|
},
|
|
{
|
|
"entropy": 5.421188735961914,
|
|
"epoch": 2.259438690277314,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044862857536468717,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.22993599772453308,
|
|
"num_tokens": 49773013.0,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"entropy": 5.412183475494385,
|
|
"epoch": 2.2598563314400266,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004486096399044654,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.22197015285491944,
|
|
"num_tokens": 49781608.0,
|
|
"step": 27055
|
|
},
|
|
{
|
|
"entropy": 5.463369274139405,
|
|
"epoch": 2.26027397260274,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000448590701404998,
|
|
"loss": 4.7978,
|
|
"mean_token_accuracy": 0.22691858559846878,
|
|
"num_tokens": 49791136.0,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"entropy": 5.342419195175171,
|
|
"epoch": 2.2606916137654527,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044857175986661634,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.2335827499628067,
|
|
"num_tokens": 49800656.0,
|
|
"step": 27065
|
|
},
|
|
{
|
|
"entropy": 5.43376841545105,
|
|
"epoch": 2.261109254928166,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004485528152896522,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.2120130851864815,
|
|
"num_tokens": 49810528.0,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"entropy": 5.345539999008179,
|
|
"epoch": 2.2615268960908788,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044853386767443706,
|
|
"loss": 4.7079,
|
|
"mean_token_accuracy": 0.22623407691717148,
|
|
"num_tokens": 49819979.0,
|
|
"step": 27075
|
|
},
|
|
{
|
|
"entropy": 5.41168851852417,
|
|
"epoch": 2.2619445372535916,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044851491702130265,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.22828410863876342,
|
|
"num_tokens": 49828656.0,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"entropy": 5.4384807586669925,
|
|
"epoch": 2.262362178416305,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044849596333058087,
|
|
"loss": 4.8145,
|
|
"mean_token_accuracy": 0.21771150231361389,
|
|
"num_tokens": 49838103.0,
|
|
"step": 27085
|
|
},
|
|
{
|
|
"entropy": 5.421938276290893,
|
|
"epoch": 2.2627798195790176,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044847700660260325,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.2233412966132164,
|
|
"num_tokens": 49847863.0,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"entropy": 5.364582347869873,
|
|
"epoch": 2.263197460741731,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004484580468377019,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.23012881278991698,
|
|
"num_tokens": 49857608.0,
|
|
"step": 27095
|
|
},
|
|
{
|
|
"entropy": 5.320289087295532,
|
|
"epoch": 2.2636151019044437,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004484390840362086,
|
|
"loss": 4.6545,
|
|
"mean_token_accuracy": 0.23206588476896287,
|
|
"num_tokens": 49867805.0,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"entropy": 5.377006006240845,
|
|
"epoch": 2.2640327430671565,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044842011819845546,
|
|
"loss": 4.8167,
|
|
"mean_token_accuracy": 0.22539640218019485,
|
|
"num_tokens": 49877456.0,
|
|
"step": 27105
|
|
},
|
|
{
|
|
"entropy": 5.429482126235962,
|
|
"epoch": 2.2644503842298698,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044840114932477435,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.22876336872577668,
|
|
"num_tokens": 49886179.0,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"entropy": 5.426284742355347,
|
|
"epoch": 2.2648680253925826,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004483821774154975,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.22748418301343917,
|
|
"num_tokens": 49895765.0,
|
|
"step": 27115
|
|
},
|
|
{
|
|
"entropy": 5.32300705909729,
|
|
"epoch": 2.265285666555296,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044836320247095674,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.21537286937236785,
|
|
"num_tokens": 49904921.0,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"entropy": 5.383469009399414,
|
|
"epoch": 2.2657033077180087,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004483442244914846,
|
|
"loss": 4.7674,
|
|
"mean_token_accuracy": 0.2275724545121193,
|
|
"num_tokens": 49913464.0,
|
|
"step": 27125
|
|
},
|
|
{
|
|
"entropy": 5.445236682891846,
|
|
"epoch": 2.2661209488807215,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004483252434774131,
|
|
"loss": 4.809,
|
|
"mean_token_accuracy": 0.22749846428632736,
|
|
"num_tokens": 49922893.0,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"entropy": 5.312892246246338,
|
|
"epoch": 2.2665385900434347,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004483062594290746,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.23464658856391907,
|
|
"num_tokens": 49932011.0,
|
|
"step": 27135
|
|
},
|
|
{
|
|
"entropy": 5.411193227767944,
|
|
"epoch": 2.2669562312061475,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004482872723468014,
|
|
"loss": 4.8748,
|
|
"mean_token_accuracy": 0.2171336144208908,
|
|
"num_tokens": 49940971.0,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"entropy": 5.420598125457763,
|
|
"epoch": 2.267373872368861,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044826828223092584,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.22489215731620787,
|
|
"num_tokens": 49951533.0,
|
|
"step": 27145
|
|
},
|
|
{
|
|
"entropy": 5.390815114974975,
|
|
"epoch": 2.2677915135315736,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004482492890817806,
|
|
"loss": 4.7325,
|
|
"mean_token_accuracy": 0.2321700394153595,
|
|
"num_tokens": 49960842.0,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"entropy": 5.440605688095093,
|
|
"epoch": 2.268209154694287,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044823029289969786,
|
|
"loss": 4.8134,
|
|
"mean_token_accuracy": 0.22310034334659576,
|
|
"num_tokens": 49970814.0,
|
|
"step": 27155
|
|
},
|
|
{
|
|
"entropy": 5.405471897125244,
|
|
"epoch": 2.2686267958569997,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004482112936850104,
|
|
"loss": 4.7609,
|
|
"mean_token_accuracy": 0.2285582035779953,
|
|
"num_tokens": 49980912.0,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"entropy": 5.3750481605529785,
|
|
"epoch": 2.2690444370197125,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044819229143805076,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.2318999007344246,
|
|
"num_tokens": 49990404.0,
|
|
"step": 27165
|
|
},
|
|
{
|
|
"entropy": 5.289481782913208,
|
|
"epoch": 2.2694620781824257,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004481732861591516,
|
|
"loss": 4.6225,
|
|
"mean_token_accuracy": 0.24608243107795716,
|
|
"num_tokens": 50000569.0,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"entropy": 5.361290788650512,
|
|
"epoch": 2.2698797193451385,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004481542778486456,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.22674432396888733,
|
|
"num_tokens": 50009332.0,
|
|
"step": 27175
|
|
},
|
|
{
|
|
"entropy": 5.413444185256958,
|
|
"epoch": 2.270297360507852,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004481352665068654,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.22073016315698624,
|
|
"num_tokens": 50019184.0,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"entropy": 5.462376260757447,
|
|
"epoch": 2.2707150016705646,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044811625213414416,
|
|
"loss": 4.8682,
|
|
"mean_token_accuracy": 0.22149171084165573,
|
|
"num_tokens": 50028522.0,
|
|
"step": 27185
|
|
},
|
|
{
|
|
"entropy": 5.444062423706055,
|
|
"epoch": 2.271132642833278,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004480972347308145,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.2243826597929001,
|
|
"num_tokens": 50037850.0,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"entropy": 5.29498143196106,
|
|
"epoch": 2.2715502839959907,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004480782142972093,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.23750431686639786,
|
|
"num_tokens": 50047096.0,
|
|
"step": 27195
|
|
},
|
|
{
|
|
"entropy": 5.3518720149993895,
|
|
"epoch": 2.2719679251587035,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044805919083366175,
|
|
"loss": 4.7192,
|
|
"mean_token_accuracy": 0.23057142198085784,
|
|
"num_tokens": 50055847.0,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"entropy": 5.4382117748260494,
|
|
"epoch": 2.2723855663214167,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044804016434050466,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.21474291384220123,
|
|
"num_tokens": 50064498.0,
|
|
"step": 27205
|
|
},
|
|
{
|
|
"entropy": 5.375942230224609,
|
|
"epoch": 2.2728032074841296,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004480211348180712,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.2271009013056755,
|
|
"num_tokens": 50072831.0,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"entropy": 5.435658884048462,
|
|
"epoch": 2.273220848646843,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044800210226669454,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.23007547110319138,
|
|
"num_tokens": 50082559.0,
|
|
"step": 27215
|
|
},
|
|
{
|
|
"entropy": 5.3677643775939945,
|
|
"epoch": 2.2736384898095556,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004479830666867078,
|
|
"loss": 4.7272,
|
|
"mean_token_accuracy": 0.23320724368095397,
|
|
"num_tokens": 50091853.0,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"entropy": 5.3551915168762205,
|
|
"epoch": 2.2740561309722684,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004479640280784443,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.22917393893003463,
|
|
"num_tokens": 50100601.0,
|
|
"step": 27225
|
|
},
|
|
{
|
|
"entropy": 5.368950271606446,
|
|
"epoch": 2.2744737721349817,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004479449864422373,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.23042903691530228,
|
|
"num_tokens": 50108841.0,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"entropy": 5.3913544654846195,
|
|
"epoch": 2.2748914132976945,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004479259417784201,
|
|
"loss": 4.7305,
|
|
"mean_token_accuracy": 0.22518024295568467,
|
|
"num_tokens": 50117755.0,
|
|
"step": 27235
|
|
},
|
|
{
|
|
"entropy": 5.341958951950073,
|
|
"epoch": 2.2753090544604078,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044790689408732623,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.24282892495393754,
|
|
"num_tokens": 50127164.0,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"entropy": 5.346871423721313,
|
|
"epoch": 2.2757266956231206,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044788784336928896,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.2332880452275276,
|
|
"num_tokens": 50136537.0,
|
|
"step": 27245
|
|
},
|
|
{
|
|
"entropy": 5.45116605758667,
|
|
"epoch": 2.2761443367858334,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004478687896246419,
|
|
"loss": 4.7436,
|
|
"mean_token_accuracy": 0.21985872685909272,
|
|
"num_tokens": 50146037.0,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"entropy": 5.434715509414673,
|
|
"epoch": 2.2765619779485466,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044784973285371863,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.2210255429148674,
|
|
"num_tokens": 50154607.0,
|
|
"step": 27255
|
|
},
|
|
{
|
|
"entropy": 5.411314058303833,
|
|
"epoch": 2.2769796191112595,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044783067305685274,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.22781735211610793,
|
|
"num_tokens": 50163801.0,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"entropy": 5.425826740264893,
|
|
"epoch": 2.2773972602739727,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004478116102343778,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.21285127550363542,
|
|
"num_tokens": 50174237.0,
|
|
"step": 27265
|
|
},
|
|
{
|
|
"entropy": 5.402630090713501,
|
|
"epoch": 2.2778149014366855,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004477925443866277,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.22725216597318648,
|
|
"num_tokens": 50184354.0,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"entropy": 5.436352348327636,
|
|
"epoch": 2.278232542599399,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000447773475513936,
|
|
"loss": 4.7914,
|
|
"mean_token_accuracy": 0.22268939018249512,
|
|
"num_tokens": 50194286.0,
|
|
"step": 27275
|
|
},
|
|
{
|
|
"entropy": 5.35895414352417,
|
|
"epoch": 2.2786501837621116,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044775440361663677,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.22904674410820008,
|
|
"num_tokens": 50203631.0,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"entropy": 5.413873624801636,
|
|
"epoch": 2.2790678249248244,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044773532869506373,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.22292735278606415,
|
|
"num_tokens": 50213509.0,
|
|
"step": 27285
|
|
},
|
|
{
|
|
"entropy": 5.4739892959594725,
|
|
"epoch": 2.2794854660875377,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004477162507495508,
|
|
"loss": 4.7978,
|
|
"mean_token_accuracy": 0.22382587641477586,
|
|
"num_tokens": 50222747.0,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"entropy": 5.433874702453613,
|
|
"epoch": 2.2799031072502505,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000447697169780432,
|
|
"loss": 4.7885,
|
|
"mean_token_accuracy": 0.23141258656978608,
|
|
"num_tokens": 50232711.0,
|
|
"step": 27295
|
|
},
|
|
{
|
|
"entropy": 5.295932960510254,
|
|
"epoch": 2.2803207484129637,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044767808578804135,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.24244193136692047,
|
|
"num_tokens": 50241253.0,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"entropy": 5.237687444686889,
|
|
"epoch": 2.2807383895756765,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044765899877271306,
|
|
"loss": 4.6247,
|
|
"mean_token_accuracy": 0.23505074232816697,
|
|
"num_tokens": 50249559.0,
|
|
"step": 27305
|
|
},
|
|
{
|
|
"entropy": 5.40864667892456,
|
|
"epoch": 2.28115603073839,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044763990873478106,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.2162240281701088,
|
|
"num_tokens": 50259442.0,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"entropy": 5.463083362579345,
|
|
"epoch": 2.2815736719011026,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044762081567457966,
|
|
"loss": 4.8086,
|
|
"mean_token_accuracy": 0.22551487237215043,
|
|
"num_tokens": 50268468.0,
|
|
"step": 27315
|
|
},
|
|
{
|
|
"entropy": 5.3571457862854,
|
|
"epoch": 2.2819913130638154,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004476017195924432,
|
|
"loss": 4.6744,
|
|
"mean_token_accuracy": 0.2280961975455284,
|
|
"num_tokens": 50278342.0,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"entropy": 5.306190395355225,
|
|
"epoch": 2.2824089542265287,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044758262048870574,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.23490245789289474,
|
|
"num_tokens": 50287364.0,
|
|
"step": 27325
|
|
},
|
|
{
|
|
"entropy": 5.3939605236053465,
|
|
"epoch": 2.2828265953892415,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044756351836370184,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.22261526435613632,
|
|
"num_tokens": 50297306.0,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"entropy": 5.469374465942383,
|
|
"epoch": 2.2832442365519547,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004475444132177659,
|
|
"loss": 4.7235,
|
|
"mean_token_accuracy": 0.2292528674006462,
|
|
"num_tokens": 50306774.0,
|
|
"step": 27335
|
|
},
|
|
{
|
|
"entropy": 5.465151977539063,
|
|
"epoch": 2.2836618777146676,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004475253050512322,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.22696371972560883,
|
|
"num_tokens": 50316492.0,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"entropy": 5.328539037704468,
|
|
"epoch": 2.2840795188773804,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044750619386443543,
|
|
"loss": 4.702,
|
|
"mean_token_accuracy": 0.22713532596826552,
|
|
"num_tokens": 50324950.0,
|
|
"step": 27345
|
|
},
|
|
{
|
|
"entropy": 5.481173849105835,
|
|
"epoch": 2.2844971600400936,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044748707965771005,
|
|
"loss": 4.8686,
|
|
"mean_token_accuracy": 0.2149311900138855,
|
|
"num_tokens": 50334383.0,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"entropy": 5.382570409774781,
|
|
"epoch": 2.2849148012028064,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044746796243139077,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.22320755422115326,
|
|
"num_tokens": 50343929.0,
|
|
"step": 27355
|
|
},
|
|
{
|
|
"entropy": 5.416476202011109,
|
|
"epoch": 2.2853324423655197,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044744884218581217,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.22087730467319489,
|
|
"num_tokens": 50352975.0,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"entropy": 5.44249963760376,
|
|
"epoch": 2.2857500835282325,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000447429718921309,
|
|
"loss": 4.7965,
|
|
"mean_token_accuracy": 0.22508372813463212,
|
|
"num_tokens": 50362800.0,
|
|
"step": 27365
|
|
},
|
|
{
|
|
"entropy": 5.404685831069946,
|
|
"epoch": 2.2861677246909453,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004474105926382161,
|
|
"loss": 4.76,
|
|
"mean_token_accuracy": 0.2259646624326706,
|
|
"num_tokens": 50372496.0,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"entropy": 5.3558595180511475,
|
|
"epoch": 2.2865853658536586,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004473914633368683,
|
|
"loss": 4.6975,
|
|
"mean_token_accuracy": 0.2283862665295601,
|
|
"num_tokens": 50380634.0,
|
|
"step": 27375
|
|
},
|
|
{
|
|
"entropy": 5.412303733825683,
|
|
"epoch": 2.2870030070163714,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004473723310176003,
|
|
"loss": 4.6724,
|
|
"mean_token_accuracy": 0.2327238842844963,
|
|
"num_tokens": 50389318.0,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"entropy": 5.38389949798584,
|
|
"epoch": 2.2874206481790846,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004473531956807471,
|
|
"loss": 4.7576,
|
|
"mean_token_accuracy": 0.2350121557712555,
|
|
"num_tokens": 50398507.0,
|
|
"step": 27385
|
|
},
|
|
{
|
|
"entropy": 5.3514289379119875,
|
|
"epoch": 2.2878382893417974,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044733405732664394,
|
|
"loss": 4.6365,
|
|
"mean_token_accuracy": 0.23345893919467925,
|
|
"num_tokens": 50406905.0,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"entropy": 5.370051860809326,
|
|
"epoch": 2.2882559305045107,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004473149159556255,
|
|
"loss": 4.6876,
|
|
"mean_token_accuracy": 0.23177244514226913,
|
|
"num_tokens": 50415959.0,
|
|
"step": 27395
|
|
},
|
|
{
|
|
"entropy": 5.446520137786865,
|
|
"epoch": 2.2886735716672235,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044729577156802714,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.22543460130691528,
|
|
"num_tokens": 50425364.0,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"entropy": 5.411801290512085,
|
|
"epoch": 2.2890912128299363,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004472766241641839,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.23013967126607895,
|
|
"num_tokens": 50434349.0,
|
|
"step": 27405
|
|
},
|
|
{
|
|
"entropy": 5.360850811004639,
|
|
"epoch": 2.2895088539926496,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000447257473744431,
|
|
"loss": 4.6671,
|
|
"mean_token_accuracy": 0.23500752300024033,
|
|
"num_tokens": 50442964.0,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"entropy": 5.388306760787964,
|
|
"epoch": 2.2899264951553624,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004472383203091036,
|
|
"loss": 4.7928,
|
|
"mean_token_accuracy": 0.22238726317882537,
|
|
"num_tokens": 50451625.0,
|
|
"step": 27415
|
|
},
|
|
{
|
|
"entropy": 5.322992897033691,
|
|
"epoch": 2.2903441363180757,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004472191638585371,
|
|
"loss": 4.6198,
|
|
"mean_token_accuracy": 0.2362431362271309,
|
|
"num_tokens": 50460062.0,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"entropy": 5.347992372512818,
|
|
"epoch": 2.2907617774807885,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044720000439306694,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.23826332539319992,
|
|
"num_tokens": 50468207.0,
|
|
"step": 27425
|
|
},
|
|
{
|
|
"entropy": 5.437510013580322,
|
|
"epoch": 2.2911794186435017,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044718084191302826,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.21937444806098938,
|
|
"num_tokens": 50478151.0,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"entropy": 5.419134616851807,
|
|
"epoch": 2.2915970598062145,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044716167641875685,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.22655171304941177,
|
|
"num_tokens": 50487180.0,
|
|
"step": 27435
|
|
},
|
|
{
|
|
"entropy": 5.322187995910644,
|
|
"epoch": 2.2920147009689273,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000447142507910588,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.23010540902614593,
|
|
"num_tokens": 50495661.0,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"entropy": 5.424182367324829,
|
|
"epoch": 2.2924323421316406,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044712333638885726,
|
|
"loss": 4.788,
|
|
"mean_token_accuracy": 0.2233033537864685,
|
|
"num_tokens": 50505854.0,
|
|
"step": 27445
|
|
},
|
|
{
|
|
"entropy": 5.415794086456299,
|
|
"epoch": 2.2928499832943534,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044710416185390043,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.22599804699420928,
|
|
"num_tokens": 50514788.0,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"entropy": 5.31867733001709,
|
|
"epoch": 2.2932676244570667,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004470849843060531,
|
|
"loss": 4.6672,
|
|
"mean_token_accuracy": 0.23323253393173218,
|
|
"num_tokens": 50523537.0,
|
|
"step": 27455
|
|
},
|
|
{
|
|
"entropy": 5.403687953948975,
|
|
"epoch": 2.2936852656197795,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044706580374565094,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.2216360792517662,
|
|
"num_tokens": 50533165.0,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"entropy": 5.405066871643067,
|
|
"epoch": 2.2941029067824923,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004470466201730298,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.23133814483880996,
|
|
"num_tokens": 50541531.0,
|
|
"step": 27465
|
|
},
|
|
{
|
|
"entropy": 5.3644397258758545,
|
|
"epoch": 2.2945205479452055,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004470274335885254,
|
|
"loss": 4.6485,
|
|
"mean_token_accuracy": 0.23470414727926253,
|
|
"num_tokens": 50551097.0,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"entropy": 5.35936975479126,
|
|
"epoch": 2.2949381891079184,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004470082439924737,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.23169442564249038,
|
|
"num_tokens": 50559796.0,
|
|
"step": 27475
|
|
},
|
|
{
|
|
"entropy": 5.413824129104614,
|
|
"epoch": 2.2953558302706316,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004469890513852107,
|
|
"loss": 4.829,
|
|
"mean_token_accuracy": 0.22189085483551024,
|
|
"num_tokens": 50568671.0,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"entropy": 5.465255880355835,
|
|
"epoch": 2.2957734714333444,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004469698557670724,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.228995580971241,
|
|
"num_tokens": 50577396.0,
|
|
"step": 27485
|
|
},
|
|
{
|
|
"entropy": 5.450553321838379,
|
|
"epoch": 2.2961911125960572,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004469506571383947,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.22806156277656556,
|
|
"num_tokens": 50587018.0,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"entropy": 5.4372107028961185,
|
|
"epoch": 2.2966087537587705,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004469314554995137,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.22426481992006303,
|
|
"num_tokens": 50596026.0,
|
|
"step": 27495
|
|
},
|
|
{
|
|
"entropy": 5.3396186351776125,
|
|
"epoch": 2.2970263949214833,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044691225085076577,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.2341657117009163,
|
|
"num_tokens": 50604973.0,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"entropy": 5.411998224258423,
|
|
"epoch": 2.2974440360841966,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004468930431924869,
|
|
"loss": 4.7916,
|
|
"mean_token_accuracy": 0.2210130512714386,
|
|
"num_tokens": 50613686.0,
|
|
"step": 27505
|
|
},
|
|
{
|
|
"entropy": 5.459649610519409,
|
|
"epoch": 2.2978616772469094,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044687383252501337,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.22780072391033174,
|
|
"num_tokens": 50622840.0,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"entropy": 5.314360189437866,
|
|
"epoch": 2.2982793184096226,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004468546188486815,
|
|
"loss": 4.7059,
|
|
"mean_token_accuracy": 0.23292877078056334,
|
|
"num_tokens": 50631818.0,
|
|
"step": 27515
|
|
},
|
|
{
|
|
"entropy": 5.390988349914551,
|
|
"epoch": 2.2986969595723354,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044683540216382766,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.22787616401910782,
|
|
"num_tokens": 50640472.0,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"entropy": 5.334067535400391,
|
|
"epoch": 2.2991146007350483,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004468161824707883,
|
|
"loss": 4.6675,
|
|
"mean_token_accuracy": 0.2321887195110321,
|
|
"num_tokens": 50649513.0,
|
|
"step": 27525
|
|
},
|
|
{
|
|
"entropy": 5.327361965179444,
|
|
"epoch": 2.2995322418977615,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044679695976989985,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.2346477821469307,
|
|
"num_tokens": 50659028.0,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"entropy": 5.393758392333984,
|
|
"epoch": 2.2999498830604743,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044677773406149885,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.22469715774059296,
|
|
"num_tokens": 50668888.0,
|
|
"step": 27535
|
|
},
|
|
{
|
|
"entropy": 5.377136945724487,
|
|
"epoch": 2.3003675242231876,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044675850534592185,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.23139477521181107,
|
|
"num_tokens": 50678094.0,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"entropy": 5.328443288803101,
|
|
"epoch": 2.3007851653859004,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044673927362350545,
|
|
"loss": 4.6384,
|
|
"mean_token_accuracy": 0.24341416954994202,
|
|
"num_tokens": 50686692.0,
|
|
"step": 27545
|
|
},
|
|
{
|
|
"entropy": 5.4512224197387695,
|
|
"epoch": 2.3012028065486136,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044672003889458634,
|
|
"loss": 4.8202,
|
|
"mean_token_accuracy": 0.22777036130428313,
|
|
"num_tokens": 50695579.0,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"entropy": 5.348003482818603,
|
|
"epoch": 2.3016204477113265,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044670080115950117,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.22644865214824678,
|
|
"num_tokens": 50704205.0,
|
|
"step": 27555
|
|
},
|
|
{
|
|
"entropy": 5.4272901058197025,
|
|
"epoch": 2.3020380888740393,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044668156041858696,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.22466479390859603,
|
|
"num_tokens": 50713926.0,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"entropy": 5.515174198150635,
|
|
"epoch": 2.3024557300367525,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044666231667218025,
|
|
"loss": 4.7968,
|
|
"mean_token_accuracy": 0.2287001669406891,
|
|
"num_tokens": 50723732.0,
|
|
"step": 27565
|
|
},
|
|
{
|
|
"entropy": 5.349796438217163,
|
|
"epoch": 2.3028733711994653,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044664306992061816,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.23358023464679717,
|
|
"num_tokens": 50732572.0,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"entropy": 5.417532253265381,
|
|
"epoch": 2.3032910123621786,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044662382016423747,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.22180649340152742,
|
|
"num_tokens": 50741145.0,
|
|
"step": 27575
|
|
},
|
|
{
|
|
"entropy": 5.428276443481446,
|
|
"epoch": 2.3037086535248914,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004466045674033752,
|
|
"loss": 4.7993,
|
|
"mean_token_accuracy": 0.22516714185476303,
|
|
"num_tokens": 50749966.0,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"entropy": 5.390534400939941,
|
|
"epoch": 2.304126294687604,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004465853116383684,
|
|
"loss": 4.7626,
|
|
"mean_token_accuracy": 0.22870133370161055,
|
|
"num_tokens": 50759263.0,
|
|
"step": 27585
|
|
},
|
|
{
|
|
"entropy": 5.30103554725647,
|
|
"epoch": 2.3045439358503175,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044656605286955424,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.23249426186084748,
|
|
"num_tokens": 50768071.0,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"entropy": 5.363286685943604,
|
|
"epoch": 2.3049615770130303,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004465467910972698,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.23267930299043654,
|
|
"num_tokens": 50777658.0,
|
|
"step": 27595
|
|
},
|
|
{
|
|
"entropy": 5.4288787841796875,
|
|
"epoch": 2.3053792181757435,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004465275263218523,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.21651002764701843,
|
|
"num_tokens": 50788438.0,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"entropy": 5.359398365020752,
|
|
"epoch": 2.3057968593384564,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044650825854363895,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.23442934453487396,
|
|
"num_tokens": 50797459.0,
|
|
"step": 27605
|
|
},
|
|
{
|
|
"entropy": 5.313268566131592,
|
|
"epoch": 2.306214500501169,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004464889877629671,
|
|
"loss": 4.6417,
|
|
"mean_token_accuracy": 0.23545913696289061,
|
|
"num_tokens": 50806088.0,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"entropy": 5.342066097259521,
|
|
"epoch": 2.3066321416638824,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004464697139801741,
|
|
"loss": 4.7067,
|
|
"mean_token_accuracy": 0.22558947503566742,
|
|
"num_tokens": 50815567.0,
|
|
"step": 27615
|
|
},
|
|
{
|
|
"entropy": 5.329489994049072,
|
|
"epoch": 2.3070497828265952,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044645043719559736,
|
|
"loss": 4.7007,
|
|
"mean_token_accuracy": 0.23778141885995865,
|
|
"num_tokens": 50824519.0,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"entropy": 5.387922763824463,
|
|
"epoch": 2.3074674239893085,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044643115740957437,
|
|
"loss": 4.8081,
|
|
"mean_token_accuracy": 0.22986097633838654,
|
|
"num_tokens": 50834875.0,
|
|
"step": 27625
|
|
},
|
|
{
|
|
"entropy": 5.409820127487182,
|
|
"epoch": 2.3078850651520213,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004464118746224426,
|
|
"loss": 4.7352,
|
|
"mean_token_accuracy": 0.22855871468782424,
|
|
"num_tokens": 50843668.0,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"entropy": 5.483788537979126,
|
|
"epoch": 2.3083027063147346,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004463925888345396,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.21804707497358322,
|
|
"num_tokens": 50853291.0,
|
|
"step": 27635
|
|
},
|
|
{
|
|
"entropy": 5.392756175994873,
|
|
"epoch": 2.3087203474774474,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044637330004620307,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.21591972857713698,
|
|
"num_tokens": 50863392.0,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"entropy": 5.396314430236816,
|
|
"epoch": 2.3091379886401606,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044635400825777065,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.22784025818109513,
|
|
"num_tokens": 50871857.0,
|
|
"step": 27645
|
|
},
|
|
{
|
|
"entropy": 5.3654529571533205,
|
|
"epoch": 2.3095556298028734,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044633471346957996,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.22998603135347367,
|
|
"num_tokens": 50882171.0,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"entropy": 5.293976879119873,
|
|
"epoch": 2.3099732709655862,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044631541568196896,
|
|
"loss": 4.5574,
|
|
"mean_token_accuracy": 0.24223127514123916,
|
|
"num_tokens": 50890925.0,
|
|
"step": 27655
|
|
},
|
|
{
|
|
"entropy": 5.365966796875,
|
|
"epoch": 2.3103909121282995,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044629611489527537,
|
|
"loss": 4.7325,
|
|
"mean_token_accuracy": 0.23505425900220872,
|
|
"num_tokens": 50900555.0,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"entropy": 5.2986866474151615,
|
|
"epoch": 2.3108085532910123,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004462768111098371,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.23978685736656188,
|
|
"num_tokens": 50908763.0,
|
|
"step": 27665
|
|
},
|
|
{
|
|
"entropy": 5.363543748855591,
|
|
"epoch": 2.3112261944537256,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044625750432599213,
|
|
"loss": 4.6286,
|
|
"mean_token_accuracy": 0.2377873882651329,
|
|
"num_tokens": 50916906.0,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"entropy": 5.3984438419342045,
|
|
"epoch": 2.3116438356164384,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044623819454407844,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.21503139287233353,
|
|
"num_tokens": 50926338.0,
|
|
"step": 27675
|
|
},
|
|
{
|
|
"entropy": 5.339470291137696,
|
|
"epoch": 2.312061476779151,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000446218881764434,
|
|
"loss": 4.752,
|
|
"mean_token_accuracy": 0.23287664353847504,
|
|
"num_tokens": 50935392.0,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"entropy": 5.403706359863281,
|
|
"epoch": 2.3124791179418644,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044619956598739686,
|
|
"loss": 4.7974,
|
|
"mean_token_accuracy": 0.21982675194740295,
|
|
"num_tokens": 50945078.0,
|
|
"step": 27685
|
|
},
|
|
{
|
|
"entropy": 5.384136819839478,
|
|
"epoch": 2.3128967591045773,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044618024721330523,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.22991780638694764,
|
|
"num_tokens": 50955091.0,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"entropy": 5.392030954360962,
|
|
"epoch": 2.3133144002672905,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004461609254424974,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.2297029048204422,
|
|
"num_tokens": 50964730.0,
|
|
"step": 27695
|
|
},
|
|
{
|
|
"entropy": 5.325143146514892,
|
|
"epoch": 2.3137320414300033,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044614160067531157,
|
|
"loss": 4.7209,
|
|
"mean_token_accuracy": 0.22977918684482573,
|
|
"num_tokens": 50973666.0,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"entropy": 5.404541110992431,
|
|
"epoch": 2.314149682592716,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000446122272912086,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.22139997482299806,
|
|
"num_tokens": 50983339.0,
|
|
"step": 27705
|
|
},
|
|
{
|
|
"entropy": 5.392119216918945,
|
|
"epoch": 2.3145673237554294,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000446102942153159,
|
|
"loss": 4.7351,
|
|
"mean_token_accuracy": 0.23018548488616944,
|
|
"num_tokens": 50993563.0,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"entropy": 5.405501222610473,
|
|
"epoch": 2.314984964918142,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004460836083988691,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.22564245015382767,
|
|
"num_tokens": 51002179.0,
|
|
"step": 27715
|
|
},
|
|
{
|
|
"entropy": 5.3349216938018795,
|
|
"epoch": 2.3154026060808555,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044606427164955466,
|
|
"loss": 4.6692,
|
|
"mean_token_accuracy": 0.22879480421543122,
|
|
"num_tokens": 51010770.0,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"entropy": 5.315031099319458,
|
|
"epoch": 2.3158202472435683,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004460449319055543,
|
|
"loss": 4.7259,
|
|
"mean_token_accuracy": 0.23489696085453032,
|
|
"num_tokens": 51021224.0,
|
|
"step": 27725
|
|
},
|
|
{
|
|
"entropy": 5.3464587211608885,
|
|
"epoch": 2.316237888406281,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004460255891672064,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.2310359761118889,
|
|
"num_tokens": 51030425.0,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"entropy": 5.450985145568848,
|
|
"epoch": 2.3166555295689943,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044600624343484985,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.22566400468349457,
|
|
"num_tokens": 51040135.0,
|
|
"step": 27735
|
|
},
|
|
{
|
|
"entropy": 5.420936441421508,
|
|
"epoch": 2.317073170731707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004459868947088231,
|
|
"loss": 4.87,
|
|
"mean_token_accuracy": 0.21579479426145554,
|
|
"num_tokens": 51050696.0,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"entropy": 5.440863800048828,
|
|
"epoch": 2.3174908118944204,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044596754298946494,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.22809036523103715,
|
|
"num_tokens": 51060092.0,
|
|
"step": 27745
|
|
},
|
|
{
|
|
"entropy": 5.392760419845581,
|
|
"epoch": 2.3179084530571332,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044594818827711416,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.2322557657957077,
|
|
"num_tokens": 51069139.0,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"entropy": 5.285678815841675,
|
|
"epoch": 2.3183260942198465,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004459288305721095,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.2319744661450386,
|
|
"num_tokens": 51078262.0,
|
|
"step": 27755
|
|
},
|
|
{
|
|
"entropy": 5.336404705047608,
|
|
"epoch": 2.3187437353825593,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044590946987479,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.22732846885919572,
|
|
"num_tokens": 51088679.0,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"entropy": 5.3087231636047365,
|
|
"epoch": 2.3191613765452725,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004458901061854944,
|
|
"loss": 4.6718,
|
|
"mean_token_accuracy": 0.2376331567764282,
|
|
"num_tokens": 51097673.0,
|
|
"step": 27765
|
|
},
|
|
{
|
|
"entropy": 5.41782660484314,
|
|
"epoch": 2.3195790177079854,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044587073950456193,
|
|
"loss": 4.7415,
|
|
"mean_token_accuracy": 0.23207009583711624,
|
|
"num_tokens": 51107546.0,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"entropy": 5.38443808555603,
|
|
"epoch": 2.319996658870698,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004458513698323314,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.2220276728272438,
|
|
"num_tokens": 51116860.0,
|
|
"step": 27775
|
|
},
|
|
{
|
|
"entropy": 5.388207721710205,
|
|
"epoch": 2.3204143000334114,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000445831997169142,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.2363876760005951,
|
|
"num_tokens": 51125815.0,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"entropy": 5.409389019012451,
|
|
"epoch": 2.3208319411961242,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004458126215153329,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.2201610192656517,
|
|
"num_tokens": 51134561.0,
|
|
"step": 27785
|
|
},
|
|
{
|
|
"entropy": 5.392703723907471,
|
|
"epoch": 2.3212495823588375,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044579324287124324,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.2273118704557419,
|
|
"num_tokens": 51143506.0,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"entropy": 5.4580662727355955,
|
|
"epoch": 2.3216672235215503,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044577386123721225,
|
|
"loss": 4.758,
|
|
"mean_token_accuracy": 0.22353655695915223,
|
|
"num_tokens": 51152632.0,
|
|
"step": 27795
|
|
},
|
|
{
|
|
"entropy": 5.413925409317017,
|
|
"epoch": 2.322084864684263,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044575447661357925,
|
|
"loss": 4.8562,
|
|
"mean_token_accuracy": 0.21583721339702605,
|
|
"num_tokens": 51162947.0,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"entropy": 5.358142232894897,
|
|
"epoch": 2.3225025058469764,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044573508900068367,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.22884246259927749,
|
|
"num_tokens": 51172030.0,
|
|
"step": 27805
|
|
},
|
|
{
|
|
"entropy": 5.326413154602051,
|
|
"epoch": 2.322920147009689,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004457156983988648,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.2318372368812561,
|
|
"num_tokens": 51181009.0,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"entropy": 5.410072946548462,
|
|
"epoch": 2.3233377881724024,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044569630480846214,
|
|
"loss": 4.6678,
|
|
"mean_token_accuracy": 0.2389258399605751,
|
|
"num_tokens": 51189731.0,
|
|
"step": 27815
|
|
},
|
|
{
|
|
"entropy": 5.367194604873657,
|
|
"epoch": 2.3237554293351153,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004456769082298152,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.23029836118221284,
|
|
"num_tokens": 51199726.0,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"entropy": 5.310690879821777,
|
|
"epoch": 2.324173070497828,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044565750866326355,
|
|
"loss": 4.695,
|
|
"mean_token_accuracy": 0.23013212233781816,
|
|
"num_tokens": 51209068.0,
|
|
"step": 27825
|
|
},
|
|
{
|
|
"entropy": 5.34373984336853,
|
|
"epoch": 2.3245907116605413,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004456381061091467,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.231328321993351,
|
|
"num_tokens": 51217766.0,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"entropy": 5.398011541366577,
|
|
"epoch": 2.325008352823254,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044561870056780445,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.22801769971847535,
|
|
"num_tokens": 51227134.0,
|
|
"step": 27835
|
|
},
|
|
{
|
|
"entropy": 5.392002916336059,
|
|
"epoch": 2.3254259939859674,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004455992920395766,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.2294964984059334,
|
|
"num_tokens": 51236059.0,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"entropy": 5.416830587387085,
|
|
"epoch": 2.32584363514868,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044557988052480263,
|
|
"loss": 4.8687,
|
|
"mean_token_accuracy": 0.22038200348615647,
|
|
"num_tokens": 51245730.0,
|
|
"step": 27845
|
|
},
|
|
{
|
|
"entropy": 5.390984439849854,
|
|
"epoch": 2.326261276311393,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044556046602382257,
|
|
"loss": 4.6782,
|
|
"mean_token_accuracy": 0.23183195739984513,
|
|
"num_tokens": 51254633.0,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"entropy": 5.397922229766846,
|
|
"epoch": 2.3266789174741063,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004455410485369763,
|
|
"loss": 4.7956,
|
|
"mean_token_accuracy": 0.22336153984069823,
|
|
"num_tokens": 51264264.0,
|
|
"step": 27855
|
|
},
|
|
{
|
|
"entropy": 5.365548086166382,
|
|
"epoch": 2.327096558636819,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004455216280646037,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.2217654764652252,
|
|
"num_tokens": 51273376.0,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"entropy": 5.291700029373169,
|
|
"epoch": 2.3275141997995323,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004455022046070446,
|
|
"loss": 4.6828,
|
|
"mean_token_accuracy": 0.23429778069257737,
|
|
"num_tokens": 51282623.0,
|
|
"step": 27865
|
|
},
|
|
{
|
|
"entropy": 5.33694019317627,
|
|
"epoch": 2.327931840962245,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044548277816463925,
|
|
"loss": 4.7305,
|
|
"mean_token_accuracy": 0.2294708102941513,
|
|
"num_tokens": 51291543.0,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"entropy": 5.4313191890716555,
|
|
"epoch": 2.3283494821249584,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044546334873772777,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.23342469185590745,
|
|
"num_tokens": 51300455.0,
|
|
"step": 27875
|
|
},
|
|
{
|
|
"entropy": 5.317810821533203,
|
|
"epoch": 2.328767123287671,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044544391632665004,
|
|
"loss": 4.5893,
|
|
"mean_token_accuracy": 0.23112478852272034,
|
|
"num_tokens": 51308871.0,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"entropy": 5.3012693405151365,
|
|
"epoch": 2.3291847644503845,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004454244809317465,
|
|
"loss": 4.6267,
|
|
"mean_token_accuracy": 0.22906017750501634,
|
|
"num_tokens": 51318132.0,
|
|
"step": 27885
|
|
},
|
|
{
|
|
"entropy": 5.428406476974487,
|
|
"epoch": 2.3296024056130973,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044540504255335717,
|
|
"loss": 4.7418,
|
|
"mean_token_accuracy": 0.22823238223791123,
|
|
"num_tokens": 51326573.0,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"entropy": 5.3920752048492435,
|
|
"epoch": 2.33002004677581,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004453856011918225,
|
|
"loss": 4.6937,
|
|
"mean_token_accuracy": 0.22832405418157578,
|
|
"num_tokens": 51336139.0,
|
|
"step": 27895
|
|
},
|
|
{
|
|
"entropy": 5.376460123062134,
|
|
"epoch": 2.3304376879385234,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044536615684748286,
|
|
"loss": 4.7359,
|
|
"mean_token_accuracy": 0.22682781666517257,
|
|
"num_tokens": 51345163.0,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"entropy": 5.342420625686645,
|
|
"epoch": 2.330855329101236,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004453467095206785,
|
|
"loss": 4.7329,
|
|
"mean_token_accuracy": 0.23459365963935852,
|
|
"num_tokens": 51354305.0,
|
|
"step": 27905
|
|
},
|
|
{
|
|
"entropy": 5.319091939926148,
|
|
"epoch": 2.3312729702639494,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004453272592117499,
|
|
"loss": 4.64,
|
|
"mean_token_accuracy": 0.2387798547744751,
|
|
"num_tokens": 51362732.0,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"entropy": 5.341764116287232,
|
|
"epoch": 2.3316906114266622,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004453078059210377,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.23040912598371505,
|
|
"num_tokens": 51372802.0,
|
|
"step": 27915
|
|
},
|
|
{
|
|
"entropy": 5.30605936050415,
|
|
"epoch": 2.332108252589375,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044528834964888234,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.2319173887372017,
|
|
"num_tokens": 51382618.0,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"entropy": 5.373288965225219,
|
|
"epoch": 2.3325258937520883,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044526889039562444,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.23319050818681716,
|
|
"num_tokens": 51392089.0,
|
|
"step": 27925
|
|
},
|
|
{
|
|
"entropy": 5.3981400489807125,
|
|
"epoch": 2.332943534914801,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044524942816160463,
|
|
"loss": 4.7221,
|
|
"mean_token_accuracy": 0.23089904338121414,
|
|
"num_tokens": 51401323.0,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"entropy": 5.368358373641968,
|
|
"epoch": 2.3333611760775144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044522996294716374,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.23253413140773774,
|
|
"num_tokens": 51410079.0,
|
|
"step": 27935
|
|
},
|
|
{
|
|
"entropy": 5.290966033935547,
|
|
"epoch": 2.333778817240227,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044521049475264237,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.2270950496196747,
|
|
"num_tokens": 51418638.0,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"entropy": 5.420559024810791,
|
|
"epoch": 2.33419645840294,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004451910235783814,
|
|
"loss": 4.8908,
|
|
"mean_token_accuracy": 0.2153969720005989,
|
|
"num_tokens": 51428766.0,
|
|
"step": 27945
|
|
},
|
|
{
|
|
"entropy": 5.427033090591431,
|
|
"epoch": 2.3346140995656532,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044517154942472166,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.22340804487466812,
|
|
"num_tokens": 51437828.0,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"entropy": 5.42007155418396,
|
|
"epoch": 2.335031740728366,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004451520722920042,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.23034802675247193,
|
|
"num_tokens": 51448070.0,
|
|
"step": 27955
|
|
},
|
|
{
|
|
"entropy": 5.379032897949219,
|
|
"epoch": 2.3354493818910793,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004451325921805698,
|
|
"loss": 4.6685,
|
|
"mean_token_accuracy": 0.231216099858284,
|
|
"num_tokens": 51457990.0,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"entropy": 5.356552314758301,
|
|
"epoch": 2.335867023053792,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004451131090907597,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.22617693841457367,
|
|
"num_tokens": 51466323.0,
|
|
"step": 27965
|
|
},
|
|
{
|
|
"entropy": 5.3489100456237795,
|
|
"epoch": 2.336284664216505,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004450936230229148,
|
|
"loss": 4.7384,
|
|
"mean_token_accuracy": 0.2236715540289879,
|
|
"num_tokens": 51476958.0,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"entropy": 5.319940805435181,
|
|
"epoch": 2.336702305379218,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004450741339773763,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.22595396190881728,
|
|
"num_tokens": 51486843.0,
|
|
"step": 27975
|
|
},
|
|
{
|
|
"entropy": 5.372927904129028,
|
|
"epoch": 2.337119946541931,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044505464195448535,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.23174765408039094,
|
|
"num_tokens": 51496331.0,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"entropy": 5.441558027267456,
|
|
"epoch": 2.3375375877046443,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044503514695458325,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.2282472461462021,
|
|
"num_tokens": 51505693.0,
|
|
"step": 27985
|
|
},
|
|
{
|
|
"entropy": 5.45585069656372,
|
|
"epoch": 2.337955228867357,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004450156489780112,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.22922765761613845,
|
|
"num_tokens": 51514753.0,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"entropy": 5.425260162353515,
|
|
"epoch": 2.3383728700300703,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004449961480251106,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.22273804098367692,
|
|
"num_tokens": 51524082.0,
|
|
"step": 27995
|
|
},
|
|
{
|
|
"entropy": 5.329915475845337,
|
|
"epoch": 2.338790511192783,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004449766440962227,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.22948428988456726,
|
|
"num_tokens": 51533437.0,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"entropy": 5.358106517791748,
|
|
"epoch": 2.3392081523554964,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004449571371916891,
|
|
"loss": 4.6234,
|
|
"mean_token_accuracy": 0.23677614331245422,
|
|
"num_tokens": 51542612.0,
|
|
"step": 28005
|
|
},
|
|
{
|
|
"entropy": 5.369526481628418,
|
|
"epoch": 2.339625793518209,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004449376273118513,
|
|
"loss": 4.6442,
|
|
"mean_token_accuracy": 0.23736046701669694,
|
|
"num_tokens": 51551292.0,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"entropy": 5.405413436889648,
|
|
"epoch": 2.340043434680922,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004449181144570507,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.23540704995393752,
|
|
"num_tokens": 51560203.0,
|
|
"step": 28015
|
|
},
|
|
{
|
|
"entropy": 5.401927089691162,
|
|
"epoch": 2.3404610758436353,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000444898598627629,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.22499743700027466,
|
|
"num_tokens": 51569716.0,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"entropy": 5.410361480712891,
|
|
"epoch": 2.340878717006348,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004448790798239278,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.2196816846728325,
|
|
"num_tokens": 51578409.0,
|
|
"step": 28025
|
|
},
|
|
{
|
|
"entropy": 5.406339359283447,
|
|
"epoch": 2.3412963581690613,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044485955804628884,
|
|
"loss": 4.8763,
|
|
"mean_token_accuracy": 0.22518949806690217,
|
|
"num_tokens": 51587846.0,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"entropy": 5.42322006225586,
|
|
"epoch": 2.341713999331774,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044484003329505384,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.23008097261190413,
|
|
"num_tokens": 51596393.0,
|
|
"step": 28035
|
|
},
|
|
{
|
|
"entropy": 5.439142894744873,
|
|
"epoch": 2.342131640494487,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004448205055705647,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.22904713600873947,
|
|
"num_tokens": 51605521.0,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"entropy": 5.432538890838623,
|
|
"epoch": 2.3425492816572,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004448009748731631,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.22401028126478195,
|
|
"num_tokens": 51614770.0,
|
|
"step": 28045
|
|
},
|
|
{
|
|
"entropy": 5.416646671295166,
|
|
"epoch": 2.342966922819913,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004447814412031911,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.23382193297147752,
|
|
"num_tokens": 51623249.0,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"entropy": 5.412762260437011,
|
|
"epoch": 2.3433845639826263,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044476190456099057,
|
|
"loss": 4.7576,
|
|
"mean_token_accuracy": 0.23050956726074218,
|
|
"num_tokens": 51632974.0,
|
|
"step": 28055
|
|
},
|
|
{
|
|
"entropy": 5.43150897026062,
|
|
"epoch": 2.343802205145339,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004447423649469036,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.22362082004547118,
|
|
"num_tokens": 51641204.0,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"entropy": 5.301835918426514,
|
|
"epoch": 2.344219846308052,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004447228223612722,
|
|
"loss": 4.608,
|
|
"mean_token_accuracy": 0.23524699956178666,
|
|
"num_tokens": 51650316.0,
|
|
"step": 28065
|
|
},
|
|
{
|
|
"entropy": 5.367113542556763,
|
|
"epoch": 2.344637487470765,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004447032768044385,
|
|
"loss": 4.7736,
|
|
"mean_token_accuracy": 0.2284172937273979,
|
|
"num_tokens": 51659164.0,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"entropy": 5.377324151992798,
|
|
"epoch": 2.345055128633478,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004446837282767447,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.22489485889673233,
|
|
"num_tokens": 51667982.0,
|
|
"step": 28075
|
|
},
|
|
{
|
|
"entropy": 5.420134019851685,
|
|
"epoch": 2.3454727697961912,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044466417677853294,
|
|
"loss": 4.7696,
|
|
"mean_token_accuracy": 0.22847577184438705,
|
|
"num_tokens": 51677397.0,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"entropy": 5.4118856430053714,
|
|
"epoch": 2.345890410958904,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004446446223101456,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.22426797151565553,
|
|
"num_tokens": 51686462.0,
|
|
"step": 28085
|
|
},
|
|
{
|
|
"entropy": 5.4343616485595705,
|
|
"epoch": 2.346308052121617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044462506487192487,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.22098887264728545,
|
|
"num_tokens": 51696654.0,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"entropy": 5.408044481277466,
|
|
"epoch": 2.34672569328433,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044460550446421323,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.22347769439220427,
|
|
"num_tokens": 51706005.0,
|
|
"step": 28095
|
|
},
|
|
{
|
|
"entropy": 5.380002117156982,
|
|
"epoch": 2.347143334447043,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000444585941087353,
|
|
"loss": 4.7572,
|
|
"mean_token_accuracy": 0.2291354238986969,
|
|
"num_tokens": 51715543.0,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"entropy": 5.358696460723877,
|
|
"epoch": 2.347560975609756,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004445663747416868,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.23013058602809905,
|
|
"num_tokens": 51723599.0,
|
|
"step": 28105
|
|
},
|
|
{
|
|
"entropy": 5.437763261795044,
|
|
"epoch": 2.347978616772469,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044454680542755715,
|
|
"loss": 4.8298,
|
|
"mean_token_accuracy": 0.2211619347333908,
|
|
"num_tokens": 51732850.0,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"entropy": 5.4581526756286625,
|
|
"epoch": 2.3483962579351823,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004445272331453066,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.21905423998832702,
|
|
"num_tokens": 51742601.0,
|
|
"step": 28115
|
|
},
|
|
{
|
|
"entropy": 5.446474552154541,
|
|
"epoch": 2.348813899097895,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044450765789527777,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.22407064139842986,
|
|
"num_tokens": 51751675.0,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"entropy": 5.370361232757569,
|
|
"epoch": 2.3492315402606083,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004444880796778133,
|
|
"loss": 4.8507,
|
|
"mean_token_accuracy": 0.22326358854770662,
|
|
"num_tokens": 51761122.0,
|
|
"step": 28125
|
|
},
|
|
{
|
|
"entropy": 5.42660608291626,
|
|
"epoch": 2.349649181423321,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000444468498493256,
|
|
"loss": 4.7938,
|
|
"mean_token_accuracy": 0.22474224716424943,
|
|
"num_tokens": 51770337.0,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"entropy": 5.391828107833862,
|
|
"epoch": 2.350066822586034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044444891434194863,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.22444844841957093,
|
|
"num_tokens": 51779630.0,
|
|
"step": 28135
|
|
},
|
|
{
|
|
"entropy": 5.343986225128174,
|
|
"epoch": 2.350484463748747,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004444293272242341,
|
|
"loss": 4.6152,
|
|
"mean_token_accuracy": 0.24301958829164505,
|
|
"num_tokens": 51788885.0,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"entropy": 5.357543706893921,
|
|
"epoch": 2.35090210491146,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044440973714045517,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.22074829190969467,
|
|
"num_tokens": 51798152.0,
|
|
"step": 28145
|
|
},
|
|
{
|
|
"entropy": 5.3705061912536625,
|
|
"epoch": 2.3513197460741733,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044439014409095495,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.229402531683445,
|
|
"num_tokens": 51807853.0,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"entropy": 5.440174245834351,
|
|
"epoch": 2.351737387236886,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004443705480760763,
|
|
"loss": 4.8178,
|
|
"mean_token_accuracy": 0.2287849724292755,
|
|
"num_tokens": 51817403.0,
|
|
"step": 28155
|
|
},
|
|
{
|
|
"entropy": 5.390271425247192,
|
|
"epoch": 2.352155028399599,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044435094909616243,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.22158074527978897,
|
|
"num_tokens": 51826527.0,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"entropy": 5.521900081634522,
|
|
"epoch": 2.352572669562312,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004443313471515562,
|
|
"loss": 4.8849,
|
|
"mean_token_accuracy": 0.22052320539951326,
|
|
"num_tokens": 51835743.0,
|
|
"step": 28165
|
|
},
|
|
{
|
|
"entropy": 5.425949573516846,
|
|
"epoch": 2.352990310725025,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044431174224260106,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.2199959322810173,
|
|
"num_tokens": 51845465.0,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"entropy": 5.382152414321899,
|
|
"epoch": 2.353407951887738,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044429213436964,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.22315984070301056,
|
|
"num_tokens": 51855242.0,
|
|
"step": 28175
|
|
},
|
|
{
|
|
"entropy": 5.364200210571289,
|
|
"epoch": 2.353825593050451,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044427252353301637,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.2398575186729431,
|
|
"num_tokens": 51864142.0,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"entropy": 5.374310731887817,
|
|
"epoch": 2.354243234213164,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044425290973307345,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.2382204607129097,
|
|
"num_tokens": 51873555.0,
|
|
"step": 28185
|
|
},
|
|
{
|
|
"entropy": 5.2931219100952145,
|
|
"epoch": 2.354660875375877,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044423329297015463,
|
|
"loss": 4.6655,
|
|
"mean_token_accuracy": 0.2345789283514023,
|
|
"num_tokens": 51882629.0,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"entropy": 5.373160362243652,
|
|
"epoch": 2.35507851653859,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044421367324460335,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.2271423950791359,
|
|
"num_tokens": 51891639.0,
|
|
"step": 28195
|
|
},
|
|
{
|
|
"entropy": 5.337223386764526,
|
|
"epoch": 2.355496157701303,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004441940505567629,
|
|
"loss": 4.6274,
|
|
"mean_token_accuracy": 0.2329893469810486,
|
|
"num_tokens": 51900187.0,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"entropy": 5.418652105331421,
|
|
"epoch": 2.355913798864016,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044417442490697704,
|
|
"loss": 4.7417,
|
|
"mean_token_accuracy": 0.22882442623376847,
|
|
"num_tokens": 51909002.0,
|
|
"step": 28205
|
|
},
|
|
{
|
|
"entropy": 5.450887393951416,
|
|
"epoch": 2.356331440026729,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044415479629558924,
|
|
"loss": 4.868,
|
|
"mean_token_accuracy": 0.21852020025253296,
|
|
"num_tokens": 51919066.0,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"entropy": 5.429631614685059,
|
|
"epoch": 2.356749081189442,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044413516472294315,
|
|
"loss": 4.7823,
|
|
"mean_token_accuracy": 0.2214414283633232,
|
|
"num_tokens": 51928266.0,
|
|
"step": 28215
|
|
},
|
|
{
|
|
"entropy": 5.440970945358276,
|
|
"epoch": 2.357166722352155,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004441155301893823,
|
|
"loss": 4.8398,
|
|
"mean_token_accuracy": 0.22301701754331588,
|
|
"num_tokens": 51937646.0,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"entropy": 5.34411768913269,
|
|
"epoch": 2.357584363514868,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004440958926952506,
|
|
"loss": 4.5849,
|
|
"mean_token_accuracy": 0.24832870066165924,
|
|
"num_tokens": 51945802.0,
|
|
"step": 28225
|
|
},
|
|
{
|
|
"entropy": 5.393584442138672,
|
|
"epoch": 2.358002004677581,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004440762522408917,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.2235674574971199,
|
|
"num_tokens": 51956024.0,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"entropy": 5.368795728683471,
|
|
"epoch": 2.358419645840294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004440566088266496,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.22714948654174805,
|
|
"num_tokens": 51965299.0,
|
|
"step": 28235
|
|
},
|
|
{
|
|
"entropy": 5.371533489227295,
|
|
"epoch": 2.358837287003007,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00044403696245286803,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.2317616954445839,
|
|
"num_tokens": 51974138.0,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"entropy": 5.335828542709351,
|
|
"epoch": 2.3592549281657202,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044401731311989086,
|
|
"loss": 4.7429,
|
|
"mean_token_accuracy": 0.22825599759817122,
|
|
"num_tokens": 51983770.0,
|
|
"step": 28245
|
|
},
|
|
{
|
|
"entropy": 5.339383220672607,
|
|
"epoch": 2.359672569328433,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004439976608280623,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.23014907985925676,
|
|
"num_tokens": 51992294.0,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"entropy": 5.455265140533447,
|
|
"epoch": 2.360090210491146,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044397800557772614,
|
|
"loss": 4.7781,
|
|
"mean_token_accuracy": 0.22510463744401932,
|
|
"num_tokens": 52001605.0,
|
|
"step": 28255
|
|
},
|
|
{
|
|
"entropy": 5.399804162979126,
|
|
"epoch": 2.360507851653859,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044395834736922675,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.23378841876983641,
|
|
"num_tokens": 52010335.0,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"entropy": 5.293305778503418,
|
|
"epoch": 2.360925492816572,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004439386862029081,
|
|
"loss": 4.6511,
|
|
"mean_token_accuracy": 0.23325383961200713,
|
|
"num_tokens": 52020170.0,
|
|
"step": 28265
|
|
},
|
|
{
|
|
"entropy": 5.358352565765381,
|
|
"epoch": 2.361343133979285,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004439190220791143,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.23020158261060714,
|
|
"num_tokens": 52030917.0,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"entropy": 5.401070165634155,
|
|
"epoch": 2.361760775141998,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044389935499818974,
|
|
"loss": 4.7759,
|
|
"mean_token_accuracy": 0.22725788205862046,
|
|
"num_tokens": 52041172.0,
|
|
"step": 28275
|
|
},
|
|
{
|
|
"entropy": 5.421737480163574,
|
|
"epoch": 2.362178416304711,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004438796849604786,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.22760927081108093,
|
|
"num_tokens": 52050955.0,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"entropy": 5.36243748664856,
|
|
"epoch": 2.362596057467424,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044386001196632536,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.23171285390853882,
|
|
"num_tokens": 52060196.0,
|
|
"step": 28285
|
|
},
|
|
{
|
|
"entropy": 5.3928721904754635,
|
|
"epoch": 2.363013698630137,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004438403360160744,
|
|
"loss": 4.7483,
|
|
"mean_token_accuracy": 0.22491587549448014,
|
|
"num_tokens": 52069375.0,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"entropy": 5.3820888042449955,
|
|
"epoch": 2.36343133979285,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044382065711007,
|
|
"loss": 4.7128,
|
|
"mean_token_accuracy": 0.23340352177619933,
|
|
"num_tokens": 52078209.0,
|
|
"step": 28295
|
|
},
|
|
{
|
|
"entropy": 5.364979934692383,
|
|
"epoch": 2.363848980955563,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044380097524865684,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.2355582520365715,
|
|
"num_tokens": 52086822.0,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"entropy": 5.449280881881714,
|
|
"epoch": 2.3642666221182758,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044378129043217947,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.22589343339204787,
|
|
"num_tokens": 52096011.0,
|
|
"step": 28305
|
|
},
|
|
{
|
|
"entropy": 5.415456962585449,
|
|
"epoch": 2.364684263280989,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004437616026609824,
|
|
"loss": 4.7263,
|
|
"mean_token_accuracy": 0.23050745874643325,
|
|
"num_tokens": 52104348.0,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"entropy": 5.437323665618896,
|
|
"epoch": 2.365101904443702,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044374191193541037,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.23256176263093947,
|
|
"num_tokens": 52113083.0,
|
|
"step": 28315
|
|
},
|
|
{
|
|
"entropy": 5.292365550994873,
|
|
"epoch": 2.365519545606415,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044372221825580803,
|
|
"loss": 4.5953,
|
|
"mean_token_accuracy": 0.2393650472164154,
|
|
"num_tokens": 52121726.0,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"entropy": 5.365315771102905,
|
|
"epoch": 2.365937186769128,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044370252162252016,
|
|
"loss": 4.7839,
|
|
"mean_token_accuracy": 0.22971192598342896,
|
|
"num_tokens": 52131515.0,
|
|
"step": 28325
|
|
},
|
|
{
|
|
"entropy": 5.401596117019653,
|
|
"epoch": 2.366354827931841,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004436828220358916,
|
|
"loss": 4.7029,
|
|
"mean_token_accuracy": 0.23041129410266875,
|
|
"num_tokens": 52140252.0,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"entropy": 5.407889938354492,
|
|
"epoch": 2.366772469094554,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004436631194962672,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.22648240625858307,
|
|
"num_tokens": 52150353.0,
|
|
"step": 28335
|
|
},
|
|
{
|
|
"entropy": 5.337881135940552,
|
|
"epoch": 2.3671901102572668,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044364341400399186,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.23038874119520186,
|
|
"num_tokens": 52160280.0,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"entropy": 5.461440372467041,
|
|
"epoch": 2.36760775141998,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044362370555941057,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.21620583534240723,
|
|
"num_tokens": 52169989.0,
|
|
"step": 28345
|
|
},
|
|
{
|
|
"entropy": 5.413643217086792,
|
|
"epoch": 2.368025392582693,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004436039941628684,
|
|
"loss": 4.6709,
|
|
"mean_token_accuracy": 0.23012629002332688,
|
|
"num_tokens": 52179535.0,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"entropy": 5.314334535598755,
|
|
"epoch": 2.368443033745406,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004435842798147103,
|
|
"loss": 4.5858,
|
|
"mean_token_accuracy": 0.24505581855773925,
|
|
"num_tokens": 52188809.0,
|
|
"step": 28355
|
|
},
|
|
{
|
|
"entropy": 5.324526309967041,
|
|
"epoch": 2.368860674908119,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044356456251528145,
|
|
"loss": 4.7047,
|
|
"mean_token_accuracy": 0.23168366998434067,
|
|
"num_tokens": 52197758.0,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"entropy": 5.347491455078125,
|
|
"epoch": 2.369278316070832,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004435448422649271,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.22931664884090425,
|
|
"num_tokens": 52206461.0,
|
|
"step": 28365
|
|
},
|
|
{
|
|
"entropy": 5.428837537765503,
|
|
"epoch": 2.369695957233545,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004435251190639923,
|
|
"loss": 4.7394,
|
|
"mean_token_accuracy": 0.22603759169578552,
|
|
"num_tokens": 52215786.0,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"entropy": 5.437855052947998,
|
|
"epoch": 2.370113598396258,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044350539291282247,
|
|
"loss": 4.7529,
|
|
"mean_token_accuracy": 0.23178843706846236,
|
|
"num_tokens": 52224668.0,
|
|
"step": 28375
|
|
},
|
|
{
|
|
"entropy": 5.475491189956665,
|
|
"epoch": 2.370531239558971,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004434856638117629,
|
|
"loss": 4.766,
|
|
"mean_token_accuracy": 0.2243983656167984,
|
|
"num_tokens": 52233999.0,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"entropy": 5.310170602798462,
|
|
"epoch": 2.370948880721684,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044346593176115904,
|
|
"loss": 4.6605,
|
|
"mean_token_accuracy": 0.23937495797872543,
|
|
"num_tokens": 52243015.0,
|
|
"step": 28385
|
|
},
|
|
{
|
|
"entropy": 5.277654790878296,
|
|
"epoch": 2.371366521884397,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044344619676135624,
|
|
"loss": 4.6031,
|
|
"mean_token_accuracy": 0.2465329498052597,
|
|
"num_tokens": 52251748.0,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"entropy": 5.362578439712524,
|
|
"epoch": 2.37178416304711,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004434264588127,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.23319754600524903,
|
|
"num_tokens": 52261228.0,
|
|
"step": 28395
|
|
},
|
|
{
|
|
"entropy": 5.418520545959472,
|
|
"epoch": 2.3722018042098227,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044340671791553586,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.23202747702598572,
|
|
"num_tokens": 52270464.0,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"entropy": 5.402713584899902,
|
|
"epoch": 2.372619445372536,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004433869740702094,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.2325638249516487,
|
|
"num_tokens": 52279888.0,
|
|
"step": 28405
|
|
},
|
|
{
|
|
"entropy": 5.374608993530273,
|
|
"epoch": 2.373037086535249,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004433672272770663,
|
|
"loss": 4.6671,
|
|
"mean_token_accuracy": 0.24039666652679442,
|
|
"num_tokens": 52288618.0,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"entropy": 5.392922496795654,
|
|
"epoch": 2.373454727697962,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044334747753645224,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.22083509266376494,
|
|
"num_tokens": 52298001.0,
|
|
"step": 28415
|
|
},
|
|
{
|
|
"entropy": 5.38304328918457,
|
|
"epoch": 2.373872368860675,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004433277248487129,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.22859397232532502,
|
|
"num_tokens": 52306863.0,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"entropy": 5.400743579864502,
|
|
"epoch": 2.3742900100233877,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004433079692141941,
|
|
"loss": 4.6733,
|
|
"mean_token_accuracy": 0.22803252786397935,
|
|
"num_tokens": 52315445.0,
|
|
"step": 28425
|
|
},
|
|
{
|
|
"entropy": 5.369304084777832,
|
|
"epoch": 2.374707651186101,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044328821063324177,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.23170218467712403,
|
|
"num_tokens": 52324478.0,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"entropy": 5.360057687759399,
|
|
"epoch": 2.3751252923488138,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004432684491062017,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.22586797475814818,
|
|
"num_tokens": 52333136.0,
|
|
"step": 28435
|
|
},
|
|
{
|
|
"entropy": 5.42145528793335,
|
|
"epoch": 2.375542933511527,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044324868463341987,
|
|
"loss": 4.8682,
|
|
"mean_token_accuracy": 0.21789483428001405,
|
|
"num_tokens": 52343490.0,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"entropy": 5.399306917190552,
|
|
"epoch": 2.37596057467424,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044322891721524233,
|
|
"loss": 4.7856,
|
|
"mean_token_accuracy": 0.22599010467529296,
|
|
"num_tokens": 52352628.0,
|
|
"step": 28445
|
|
},
|
|
{
|
|
"entropy": 5.359013938903809,
|
|
"epoch": 2.376378215836953,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044320914685201516,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.23080869317054747,
|
|
"num_tokens": 52361947.0,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"entropy": 5.425225400924683,
|
|
"epoch": 2.376795856999666,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004431893735440843,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.21945746541023253,
|
|
"num_tokens": 52371251.0,
|
|
"step": 28455
|
|
},
|
|
{
|
|
"entropy": 5.3901159286499025,
|
|
"epoch": 2.3772134981623787,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044316959729179603,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.24514175355434417,
|
|
"num_tokens": 52380681.0,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"entropy": 5.410763168334961,
|
|
"epoch": 2.377631139325092,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044314981809549656,
|
|
"loss": 4.6957,
|
|
"mean_token_accuracy": 0.23120894134044648,
|
|
"num_tokens": 52390059.0,
|
|
"step": 28465
|
|
},
|
|
{
|
|
"entropy": 5.398440742492676,
|
|
"epoch": 2.3780487804878048,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004431300359555321,
|
|
"loss": 4.7835,
|
|
"mean_token_accuracy": 0.22082301378250122,
|
|
"num_tokens": 52399574.0,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"entropy": 5.418309259414673,
|
|
"epoch": 2.378466421650518,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000443110250872249,
|
|
"loss": 4.8431,
|
|
"mean_token_accuracy": 0.2234470546245575,
|
|
"num_tokens": 52408926.0,
|
|
"step": 28475
|
|
},
|
|
{
|
|
"entropy": 5.415352058410645,
|
|
"epoch": 2.378884062813231,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004430904628459935,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.23048232942819596,
|
|
"num_tokens": 52418052.0,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"entropy": 5.421278810501098,
|
|
"epoch": 2.379301703975944,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044307067187711227,
|
|
"loss": 4.6996,
|
|
"mean_token_accuracy": 0.2368422970175743,
|
|
"num_tokens": 52427422.0,
|
|
"step": 28485
|
|
},
|
|
{
|
|
"entropy": 5.40242714881897,
|
|
"epoch": 2.379719345138657,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004430508779659516,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.22682836800813674,
|
|
"num_tokens": 52436535.0,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"entropy": 5.359876585006714,
|
|
"epoch": 2.3801369863013697,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044303108111285795,
|
|
"loss": 4.783,
|
|
"mean_token_accuracy": 0.22941616475582122,
|
|
"num_tokens": 52445640.0,
|
|
"step": 28495
|
|
},
|
|
{
|
|
"entropy": 5.47340497970581,
|
|
"epoch": 2.380554627464083,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044301128131817805,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.2240764543414116,
|
|
"num_tokens": 52454715.0,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"entropy": 5.460416221618653,
|
|
"epoch": 2.380972268626796,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044299147858225835,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.221024090051651,
|
|
"num_tokens": 52464015.0,
|
|
"step": 28505
|
|
},
|
|
{
|
|
"entropy": 5.412580728530884,
|
|
"epoch": 2.381389909789509,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004429716729054456,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.22809793055057526,
|
|
"num_tokens": 52472927.0,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"entropy": 5.473847150802612,
|
|
"epoch": 2.381807550952222,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004429518642880866,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.22007295936346055,
|
|
"num_tokens": 52482417.0,
|
|
"step": 28515
|
|
},
|
|
{
|
|
"entropy": 5.387412643432617,
|
|
"epoch": 2.3822251921149347,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044293205273052805,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.22576129287481309,
|
|
"num_tokens": 52491294.0,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"entropy": 5.46290693283081,
|
|
"epoch": 2.382642833277648,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004429122382331168,
|
|
"loss": 4.7965,
|
|
"mean_token_accuracy": 0.2262161120772362,
|
|
"num_tokens": 52500253.0,
|
|
"step": 28525
|
|
},
|
|
{
|
|
"entropy": 5.364185953140259,
|
|
"epoch": 2.3830604744403607,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044289242079619955,
|
|
"loss": 4.7397,
|
|
"mean_token_accuracy": 0.2305501863360405,
|
|
"num_tokens": 52509828.0,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"entropy": 5.365272140502929,
|
|
"epoch": 2.383478115603074,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044287260042012353,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.23240405917167664,
|
|
"num_tokens": 52518781.0,
|
|
"step": 28535
|
|
},
|
|
{
|
|
"entropy": 5.387305498123169,
|
|
"epoch": 2.383895756765787,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004428527771052355,
|
|
"loss": 4.7293,
|
|
"mean_token_accuracy": 0.2314716950058937,
|
|
"num_tokens": 52528102.0,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"entropy": 5.523526906967163,
|
|
"epoch": 2.3843133979284996,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044283295085188263,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.22591321766376496,
|
|
"num_tokens": 52537609.0,
|
|
"step": 28545
|
|
},
|
|
{
|
|
"entropy": 5.388740587234497,
|
|
"epoch": 2.384731039091213,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044281312166041196,
|
|
"loss": 4.7801,
|
|
"mean_token_accuracy": 0.22876622080802916,
|
|
"num_tokens": 52547169.0,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"entropy": 5.32680492401123,
|
|
"epoch": 2.3851486802539257,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004427932895311705,
|
|
"loss": 4.7142,
|
|
"mean_token_accuracy": 0.22300879806280136,
|
|
"num_tokens": 52556220.0,
|
|
"step": 28555
|
|
},
|
|
{
|
|
"entropy": 5.405286550521851,
|
|
"epoch": 2.385566321416639,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004427734544645055,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.22028934806585312,
|
|
"num_tokens": 52565736.0,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"entropy": 5.4284590721130375,
|
|
"epoch": 2.3859839625793517,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044275361646076427,
|
|
"loss": 4.7414,
|
|
"mean_token_accuracy": 0.22556877583265306,
|
|
"num_tokens": 52575222.0,
|
|
"step": 28565
|
|
},
|
|
{
|
|
"entropy": 5.400477457046509,
|
|
"epoch": 2.386401603742065,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044273377552029415,
|
|
"loss": 4.6835,
|
|
"mean_token_accuracy": 0.23328679502010347,
|
|
"num_tokens": 52584726.0,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"entropy": 5.439052295684815,
|
|
"epoch": 2.386819244904778,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004427139316434423,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.22870814353227614,
|
|
"num_tokens": 52595080.0,
|
|
"step": 28575
|
|
},
|
|
{
|
|
"entropy": 5.44851861000061,
|
|
"epoch": 2.3872368860674906,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004426940848305563,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.22287874668836594,
|
|
"num_tokens": 52604692.0,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"entropy": 5.372374820709228,
|
|
"epoch": 2.387654527230204,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004426742350819834,
|
|
"loss": 4.7228,
|
|
"mean_token_accuracy": 0.22312608361244202,
|
|
"num_tokens": 52613697.0,
|
|
"step": 28585
|
|
},
|
|
{
|
|
"entropy": 5.374864196777343,
|
|
"epoch": 2.3880721683929167,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044265438239807117,
|
|
"loss": 4.759,
|
|
"mean_token_accuracy": 0.22962836176156998,
|
|
"num_tokens": 52622048.0,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"entropy": 5.30686731338501,
|
|
"epoch": 2.38848980955563,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004426345267791672,
|
|
"loss": 4.6566,
|
|
"mean_token_accuracy": 0.2404000297188759,
|
|
"num_tokens": 52631939.0,
|
|
"step": 28595
|
|
},
|
|
{
|
|
"entropy": 5.354315948486328,
|
|
"epoch": 2.3889074507183428,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044261466822561907,
|
|
"loss": 4.6957,
|
|
"mean_token_accuracy": 0.23254175186157228,
|
|
"num_tokens": 52641651.0,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"entropy": 5.431296539306641,
|
|
"epoch": 2.389325091881056,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004425948067377744,
|
|
"loss": 4.7302,
|
|
"mean_token_accuracy": 0.22694515734910964,
|
|
"num_tokens": 52650863.0,
|
|
"step": 28605
|
|
},
|
|
{
|
|
"entropy": 5.414656782150269,
|
|
"epoch": 2.389742733043769,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044257494231598094,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.2220442160964012,
|
|
"num_tokens": 52659892.0,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"entropy": 5.430906486511231,
|
|
"epoch": 2.3901603742064816,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004425550749605863,
|
|
"loss": 4.7435,
|
|
"mean_token_accuracy": 0.22981210500001908,
|
|
"num_tokens": 52669381.0,
|
|
"step": 28615
|
|
},
|
|
{
|
|
"entropy": 5.506579828262329,
|
|
"epoch": 2.390578015369195,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044253520467193855,
|
|
"loss": 4.7784,
|
|
"mean_token_accuracy": 0.23490912914276124,
|
|
"num_tokens": 52678742.0,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"entropy": 5.437662363052368,
|
|
"epoch": 2.3909956565319077,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044251533145038525,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.2237069383263588,
|
|
"num_tokens": 52688494.0,
|
|
"step": 28625
|
|
},
|
|
{
|
|
"entropy": 5.366949081420898,
|
|
"epoch": 2.391413297694621,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004424954552962744,
|
|
"loss": 4.649,
|
|
"mean_token_accuracy": 0.23568470776081085,
|
|
"num_tokens": 52696778.0,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"entropy": 5.354764366149903,
|
|
"epoch": 2.3918309388573338,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044247557620995416,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.23145704269409179,
|
|
"num_tokens": 52706031.0,
|
|
"step": 28635
|
|
},
|
|
{
|
|
"entropy": 5.36942229270935,
|
|
"epoch": 2.3922485800200466,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004424556941917723,
|
|
"loss": 4.7212,
|
|
"mean_token_accuracy": 0.2315387174487114,
|
|
"num_tokens": 52715513.0,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"entropy": 5.486468410491943,
|
|
"epoch": 2.39266622118276,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044243580924207686,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.21575754582881929,
|
|
"num_tokens": 52724622.0,
|
|
"step": 28645
|
|
},
|
|
{
|
|
"entropy": 5.361154508590698,
|
|
"epoch": 2.3930838623454727,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004424159213612161,
|
|
"loss": 4.7104,
|
|
"mean_token_accuracy": 0.23399640023708343,
|
|
"num_tokens": 52733879.0,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"entropy": 5.28439040184021,
|
|
"epoch": 2.393501503508186,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004423960305495381,
|
|
"loss": 4.59,
|
|
"mean_token_accuracy": 0.24599614590406418,
|
|
"num_tokens": 52742656.0,
|
|
"step": 28655
|
|
},
|
|
{
|
|
"entropy": 5.374270629882813,
|
|
"epoch": 2.3939191446708987,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004423761368073911,
|
|
"loss": 4.8256,
|
|
"mean_token_accuracy": 0.2196326285600662,
|
|
"num_tokens": 52753073.0,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"entropy": 5.411734485626221,
|
|
"epoch": 2.3943367858336115,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004423562401351234,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.22972435355186463,
|
|
"num_tokens": 52761891.0,
|
|
"step": 28665
|
|
},
|
|
{
|
|
"entropy": 5.396840333938599,
|
|
"epoch": 2.394754426996325,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004423363405330833,
|
|
"loss": 4.6936,
|
|
"mean_token_accuracy": 0.22827819883823394,
|
|
"num_tokens": 52772175.0,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"entropy": 5.360507917404175,
|
|
"epoch": 2.3951720681590376,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044231643800161897,
|
|
"loss": 4.785,
|
|
"mean_token_accuracy": 0.22239958643913268,
|
|
"num_tokens": 52783073.0,
|
|
"step": 28675
|
|
},
|
|
{
|
|
"entropy": 5.364916133880615,
|
|
"epoch": 2.395589709321751,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004422965325410791,
|
|
"loss": 4.6616,
|
|
"mean_token_accuracy": 0.23041170090436935,
|
|
"num_tokens": 52791949.0,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"entropy": 5.342698669433593,
|
|
"epoch": 2.3960073504844637,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044227662415181207,
|
|
"loss": 4.6297,
|
|
"mean_token_accuracy": 0.2343047484755516,
|
|
"num_tokens": 52800912.0,
|
|
"step": 28685
|
|
},
|
|
{
|
|
"entropy": 5.390856075286865,
|
|
"epoch": 2.396424991647177,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044225671283416634,
|
|
"loss": 4.7333,
|
|
"mean_token_accuracy": 0.22879370748996736,
|
|
"num_tokens": 52810419.0,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"entropy": 5.372116327285767,
|
|
"epoch": 2.3968426328098897,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044223679858849057,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.23465648144483567,
|
|
"num_tokens": 52819148.0,
|
|
"step": 28695
|
|
},
|
|
{
|
|
"entropy": 5.421080493927002,
|
|
"epoch": 2.3972602739726026,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004422168814151333,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.22094304412603377,
|
|
"num_tokens": 52828494.0,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"entropy": 5.363852071762085,
|
|
"epoch": 2.397677915135316,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044219696131444326,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.22311259657144547,
|
|
"num_tokens": 52837279.0,
|
|
"step": 28705
|
|
},
|
|
{
|
|
"entropy": 5.411848163604736,
|
|
"epoch": 2.3980955562980286,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044217703828676913,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.23445226550102233,
|
|
"num_tokens": 52846319.0,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"entropy": 5.369479417800903,
|
|
"epoch": 2.398513197460742,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044215711233245973,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.22765202671289445,
|
|
"num_tokens": 52855005.0,
|
|
"step": 28715
|
|
},
|
|
{
|
|
"entropy": 5.420650005340576,
|
|
"epoch": 2.3989308386234547,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044213718345186394,
|
|
"loss": 4.847,
|
|
"mean_token_accuracy": 0.22725979834795,
|
|
"num_tokens": 52864805.0,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"entropy": 5.368721675872803,
|
|
"epoch": 2.399348479786168,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044211725164533045,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.23250133842229842,
|
|
"num_tokens": 52873808.0,
|
|
"step": 28725
|
|
},
|
|
{
|
|
"entropy": 5.398081588745117,
|
|
"epoch": 2.3997661209488808,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044209731691320837,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.22851529270410537,
|
|
"num_tokens": 52882564.0,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"entropy": 5.43393383026123,
|
|
"epoch": 2.4001837621115936,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004420773792558467,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.21672514826059341,
|
|
"num_tokens": 52891271.0,
|
|
"step": 28735
|
|
},
|
|
{
|
|
"entropy": 5.321554899215698,
|
|
"epoch": 2.400601403274307,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004420574386735943,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.2246988072991371,
|
|
"num_tokens": 52900075.0,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"entropy": 5.314008569717407,
|
|
"epoch": 2.4010190444370196,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044203749516680035,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.22636969834566117,
|
|
"num_tokens": 52908744.0,
|
|
"step": 28745
|
|
},
|
|
{
|
|
"entropy": 5.352547264099121,
|
|
"epoch": 2.401436685599733,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044201754873581396,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.22776031047105788,
|
|
"num_tokens": 52918242.0,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"entropy": 5.437715721130371,
|
|
"epoch": 2.4018543267624457,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044199759938098437,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.2284854918718338,
|
|
"num_tokens": 52927453.0,
|
|
"step": 28755
|
|
},
|
|
{
|
|
"entropy": 5.365739345550537,
|
|
"epoch": 2.4022719679251585,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044197764710266087,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.24121983647346495,
|
|
"num_tokens": 52935467.0,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"entropy": 5.498942470550537,
|
|
"epoch": 2.4026896090878718,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004419576919011926,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.2206419214606285,
|
|
"num_tokens": 52944770.0,
|
|
"step": 28765
|
|
},
|
|
{
|
|
"entropy": 5.3695393085479735,
|
|
"epoch": 2.4031072502505846,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044193773377692886,
|
|
"loss": 4.7077,
|
|
"mean_token_accuracy": 0.2348148688673973,
|
|
"num_tokens": 52953679.0,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"entropy": 5.31843147277832,
|
|
"epoch": 2.403524891413298,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044191777273021933,
|
|
"loss": 4.6888,
|
|
"mean_token_accuracy": 0.23033461570739747,
|
|
"num_tokens": 52962101.0,
|
|
"step": 28775
|
|
},
|
|
{
|
|
"entropy": 5.282098484039307,
|
|
"epoch": 2.4039425325760106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004418978087614131,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.22791157364845277,
|
|
"num_tokens": 52971661.0,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"entropy": 5.439041471481323,
|
|
"epoch": 2.4043601737387235,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044187784187085994,
|
|
"loss": 4.7861,
|
|
"mean_token_accuracy": 0.22635803520679473,
|
|
"num_tokens": 52981091.0,
|
|
"step": 28785
|
|
},
|
|
{
|
|
"entropy": 5.517042732238769,
|
|
"epoch": 2.4047778149014367,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004418578720589093,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.21949746161699296,
|
|
"num_tokens": 52990392.0,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"entropy": 5.400527095794677,
|
|
"epoch": 2.4051954560641495,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004418378993259107,
|
|
"loss": 4.7872,
|
|
"mean_token_accuracy": 0.21735044270753862,
|
|
"num_tokens": 52999203.0,
|
|
"step": 28795
|
|
},
|
|
{
|
|
"entropy": 5.496014976501465,
|
|
"epoch": 2.405613097226863,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004418179236722139,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.22718100398778915,
|
|
"num_tokens": 53009421.0,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"entropy": 5.368659210205078,
|
|
"epoch": 2.4060307383895756,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004417979450981685,
|
|
"loss": 4.6849,
|
|
"mean_token_accuracy": 0.23256046772003175,
|
|
"num_tokens": 53018968.0,
|
|
"step": 28805
|
|
},
|
|
{
|
|
"entropy": 5.469293689727783,
|
|
"epoch": 2.406448379552289,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044177796360412436,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.22314151674509047,
|
|
"num_tokens": 53027708.0,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"entropy": 5.4453741073608395,
|
|
"epoch": 2.4068660207150017,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004417579791904312,
|
|
"loss": 4.8245,
|
|
"mean_token_accuracy": 0.23085595071315765,
|
|
"num_tokens": 53036373.0,
|
|
"step": 28815
|
|
},
|
|
{
|
|
"entropy": 5.480477237701416,
|
|
"epoch": 2.4072836618777145,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004417379918574388,
|
|
"loss": 4.8783,
|
|
"mean_token_accuracy": 0.22245279401540757,
|
|
"num_tokens": 53046138.0,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"entropy": 5.394808292388916,
|
|
"epoch": 2.4077013030404277,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004417180016054972,
|
|
"loss": 4.7262,
|
|
"mean_token_accuracy": 0.22169752568006515,
|
|
"num_tokens": 53055039.0,
|
|
"step": 28825
|
|
},
|
|
{
|
|
"entropy": 5.392445611953735,
|
|
"epoch": 2.4081189442031405,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044169800843495637,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.23042660355567932,
|
|
"num_tokens": 53064901.0,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"entropy": 5.366193723678589,
|
|
"epoch": 2.408536585365854,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004416780123461662,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.22836054414510726,
|
|
"num_tokens": 53074138.0,
|
|
"step": 28835
|
|
},
|
|
{
|
|
"entropy": 5.398206329345703,
|
|
"epoch": 2.4089542265285666,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044165801333947676,
|
|
"loss": 4.6815,
|
|
"mean_token_accuracy": 0.2277270331978798,
|
|
"num_tokens": 53083020.0,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"entropy": 5.346680927276611,
|
|
"epoch": 2.40937186769128,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004416380114152382,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.22999702095985414,
|
|
"num_tokens": 53092141.0,
|
|
"step": 28845
|
|
},
|
|
{
|
|
"entropy": 5.338938426971436,
|
|
"epoch": 2.4097895088539927,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044161800657380076,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.23083262890577316,
|
|
"num_tokens": 53101305.0,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"entropy": 5.420418691635132,
|
|
"epoch": 2.4102071500167055,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004415979988155145,
|
|
"loss": 4.7347,
|
|
"mean_token_accuracy": 0.22760097682476044,
|
|
"num_tokens": 53109946.0,
|
|
"step": 28855
|
|
},
|
|
{
|
|
"entropy": 5.456103420257568,
|
|
"epoch": 2.4106247911794187,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004415779881407297,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.22931060940027237,
|
|
"num_tokens": 53118369.0,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"entropy": 5.407188987731933,
|
|
"epoch": 2.4110424323421316,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004415579745497967,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.2261349990963936,
|
|
"num_tokens": 53127389.0,
|
|
"step": 28865
|
|
},
|
|
{
|
|
"entropy": 5.417479848861694,
|
|
"epoch": 2.411460073504845,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004415379580430659,
|
|
"loss": 4.7858,
|
|
"mean_token_accuracy": 0.2221845418214798,
|
|
"num_tokens": 53136055.0,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"entropy": 5.426269578933716,
|
|
"epoch": 2.4118777146675576,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044151793862088766,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.22959114164113997,
|
|
"num_tokens": 53145687.0,
|
|
"step": 28875
|
|
},
|
|
{
|
|
"entropy": 5.428430080413818,
|
|
"epoch": 2.4122953558302704,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004414979162836125,
|
|
"loss": 4.7802,
|
|
"mean_token_accuracy": 0.22283071279525757,
|
|
"num_tokens": 53155667.0,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"entropy": 5.3821979522705075,
|
|
"epoch": 2.4127129969929837,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004414778910315909,
|
|
"loss": 4.6896,
|
|
"mean_token_accuracy": 0.23698603063821794,
|
|
"num_tokens": 53164615.0,
|
|
"step": 28885
|
|
},
|
|
{
|
|
"entropy": 5.41722559928894,
|
|
"epoch": 2.4131306381556965,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044145786286517343,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.21988503485918046,
|
|
"num_tokens": 53174139.0,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"entropy": 5.5113747119903564,
|
|
"epoch": 2.4135482793184098,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004414378317847107,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.22122853100299836,
|
|
"num_tokens": 53182019.0,
|
|
"step": 28895
|
|
},
|
|
{
|
|
"entropy": 5.319045925140381,
|
|
"epoch": 2.4139659204811226,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044141779779055334,
|
|
"loss": 4.6975,
|
|
"mean_token_accuracy": 0.22969240993261336,
|
|
"num_tokens": 53191312.0,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"entropy": 5.388501787185669,
|
|
"epoch": 2.4143835616438354,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044139776088305215,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.2300321266055107,
|
|
"num_tokens": 53200027.0,
|
|
"step": 28905
|
|
},
|
|
{
|
|
"entropy": 5.400146532058716,
|
|
"epoch": 2.4148012028065486,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044137772106255793,
|
|
"loss": 4.7568,
|
|
"mean_token_accuracy": 0.22427498996257783,
|
|
"num_tokens": 53209841.0,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"entropy": 5.530630970001221,
|
|
"epoch": 2.4152188439692615,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044135767832942136,
|
|
"loss": 4.9508,
|
|
"mean_token_accuracy": 0.21718590408563615,
|
|
"num_tokens": 53219717.0,
|
|
"step": 28915
|
|
},
|
|
{
|
|
"entropy": 5.397390604019165,
|
|
"epoch": 2.4156364851319747,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004413376326839934,
|
|
"loss": 4.6704,
|
|
"mean_token_accuracy": 0.227475868165493,
|
|
"num_tokens": 53228886.0,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"entropy": 5.4479837894439695,
|
|
"epoch": 2.4160541262946875,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044131758412662493,
|
|
"loss": 4.7389,
|
|
"mean_token_accuracy": 0.23026295006275177,
|
|
"num_tokens": 53237314.0,
|
|
"step": 28925
|
|
},
|
|
{
|
|
"entropy": 5.3384651184082035,
|
|
"epoch": 2.4164717674574008,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000441297532657667,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.23166489750146865,
|
|
"num_tokens": 53246502.0,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"entropy": 5.372961139678955,
|
|
"epoch": 2.4168894086201136,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004412774782774705,
|
|
"loss": 4.7392,
|
|
"mean_token_accuracy": 0.2193666934967041,
|
|
"num_tokens": 53256004.0,
|
|
"step": 28935
|
|
},
|
|
{
|
|
"entropy": 5.440959310531616,
|
|
"epoch": 2.417307049782827,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004412574209863867,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.22517893165349961,
|
|
"num_tokens": 53264301.0,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"entropy": 5.389838314056396,
|
|
"epoch": 2.4177246909455397,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004412373607847666,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.23489674925804138,
|
|
"num_tokens": 53272664.0,
|
|
"step": 28945
|
|
},
|
|
{
|
|
"entropy": 5.38965072631836,
|
|
"epoch": 2.4181423321082525,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044121729767296135,
|
|
"loss": 4.7676,
|
|
"mean_token_accuracy": 0.22163309156894684,
|
|
"num_tokens": 53282210.0,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"entropy": 5.427611064910889,
|
|
"epoch": 2.4185599732709657,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044119723165132225,
|
|
"loss": 4.8236,
|
|
"mean_token_accuracy": 0.22313446998596193,
|
|
"num_tokens": 53291328.0,
|
|
"step": 28955
|
|
},
|
|
{
|
|
"entropy": 5.39740777015686,
|
|
"epoch": 2.4189776144336785,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044117716272020055,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.22277988791465758,
|
|
"num_tokens": 53301332.0,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"entropy": 5.4571737289428714,
|
|
"epoch": 2.419395255596392,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004411570908799476,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.2255611926317215,
|
|
"num_tokens": 53310699.0,
|
|
"step": 28965
|
|
},
|
|
{
|
|
"entropy": 5.377430963516235,
|
|
"epoch": 2.4198128967591046,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044113701613091483,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.2245086669921875,
|
|
"num_tokens": 53319760.0,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"entropy": 5.382736301422119,
|
|
"epoch": 2.4202305379218174,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044111693847345354,
|
|
"loss": 4.6732,
|
|
"mean_token_accuracy": 0.2276574581861496,
|
|
"num_tokens": 53328781.0,
|
|
"step": 28975
|
|
},
|
|
{
|
|
"entropy": 5.452405309677124,
|
|
"epoch": 2.4206481790845307,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004410968579079153,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.23377197831869126,
|
|
"num_tokens": 53337071.0,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"entropy": 5.391851472854614,
|
|
"epoch": 2.4210658202472435,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044107677443465165,
|
|
"loss": 4.6971,
|
|
"mean_token_accuracy": 0.2334704205393791,
|
|
"num_tokens": 53346480.0,
|
|
"step": 28985
|
|
},
|
|
{
|
|
"entropy": 5.369611310958862,
|
|
"epoch": 2.4214834614099567,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044105668805401415,
|
|
"loss": 4.772,
|
|
"mean_token_accuracy": 0.233786740899086,
|
|
"num_tokens": 53355784.0,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"entropy": 5.364492034912109,
|
|
"epoch": 2.4219011025726696,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044103659876635443,
|
|
"loss": 4.7584,
|
|
"mean_token_accuracy": 0.22306487411260606,
|
|
"num_tokens": 53364793.0,
|
|
"step": 28995
|
|
},
|
|
{
|
|
"entropy": 5.482856512069702,
|
|
"epoch": 2.4223187437353824,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004410165065720242,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.2227955237030983,
|
|
"num_tokens": 53374473.0,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"entropy": 5.3968103408813475,
|
|
"epoch": 2.4227363848980956,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004409964114713752,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.23171005696058272,
|
|
"num_tokens": 53383453.0,
|
|
"step": 29005
|
|
},
|
|
{
|
|
"entropy": 5.480267763137817,
|
|
"epoch": 2.4231540260608084,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004409763134647592,
|
|
"loss": 4.7896,
|
|
"mean_token_accuracy": 0.22377347946166992,
|
|
"num_tokens": 53392628.0,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"entropy": 5.437080049514771,
|
|
"epoch": 2.4235716672235217,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000440956212552528,
|
|
"loss": 4.7291,
|
|
"mean_token_accuracy": 0.2344120442867279,
|
|
"num_tokens": 53402614.0,
|
|
"step": 29015
|
|
},
|
|
{
|
|
"entropy": 5.459388494491577,
|
|
"epoch": 2.4239893083862345,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004409361087350336,
|
|
"loss": 4.9199,
|
|
"mean_token_accuracy": 0.21179779767990112,
|
|
"num_tokens": 53412851.0,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"entropy": 5.386501836776733,
|
|
"epoch": 2.4244069495489473,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004409160020126279,
|
|
"loss": 4.72,
|
|
"mean_token_accuracy": 0.23195608854293823,
|
|
"num_tokens": 53422116.0,
|
|
"step": 29025
|
|
},
|
|
{
|
|
"entropy": 5.360678052902221,
|
|
"epoch": 2.4248245907116606,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004408958923856628,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.23453813940286636,
|
|
"num_tokens": 53431213.0,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"entropy": 5.392141580581665,
|
|
"epoch": 2.4252422318743734,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044087577985449047,
|
|
"loss": 4.7582,
|
|
"mean_token_accuracy": 0.23312479257583618,
|
|
"num_tokens": 53439292.0,
|
|
"step": 29035
|
|
},
|
|
{
|
|
"entropy": 5.39617223739624,
|
|
"epoch": 2.4256598730370866,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004408556644194629,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.23423349112272263,
|
|
"num_tokens": 53447932.0,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"entropy": 5.3681717872619625,
|
|
"epoch": 2.4260775141997994,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004408355460809323,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.22855910360813142,
|
|
"num_tokens": 53457847.0,
|
|
"step": 29045
|
|
},
|
|
{
|
|
"entropy": 5.404831647872925,
|
|
"epoch": 2.4264951553625127,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044081542483925086,
|
|
"loss": 4.6509,
|
|
"mean_token_accuracy": 0.23474004119634628,
|
|
"num_tokens": 53466106.0,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"entropy": 5.35557541847229,
|
|
"epoch": 2.4269127965252255,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004407953006947708,
|
|
"loss": 4.6641,
|
|
"mean_token_accuracy": 0.24323884397745132,
|
|
"num_tokens": 53474516.0,
|
|
"step": 29055
|
|
},
|
|
{
|
|
"entropy": 5.315648174285888,
|
|
"epoch": 2.4273304376879388,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044077517364784455,
|
|
"loss": 4.6835,
|
|
"mean_token_accuracy": 0.23576981127262114,
|
|
"num_tokens": 53483640.0,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"entropy": 5.420190954208374,
|
|
"epoch": 2.4277480788506516,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044075504369882416,
|
|
"loss": 4.7874,
|
|
"mean_token_accuracy": 0.22715888768434525,
|
|
"num_tokens": 53492987.0,
|
|
"step": 29065
|
|
},
|
|
{
|
|
"entropy": 5.428604412078857,
|
|
"epoch": 2.4281657200133644,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004407349108480623,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.21881183683872224,
|
|
"num_tokens": 53502319.0,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"entropy": 5.396295356750488,
|
|
"epoch": 2.4285833611760776,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044071477509591126,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.23094467520713807,
|
|
"num_tokens": 53511739.0,
|
|
"step": 29075
|
|
},
|
|
{
|
|
"entropy": 5.461222314834595,
|
|
"epoch": 2.4290010023387905,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004406946364427237,
|
|
"loss": 4.8029,
|
|
"mean_token_accuracy": 0.2236310213804245,
|
|
"num_tokens": 53521369.0,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"entropy": 5.414917230606079,
|
|
"epoch": 2.4294186435015037,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044067449488885207,
|
|
"loss": 4.6671,
|
|
"mean_token_accuracy": 0.23774565756320953,
|
|
"num_tokens": 53530697.0,
|
|
"step": 29085
|
|
},
|
|
{
|
|
"entropy": 5.381976699829101,
|
|
"epoch": 2.4298362846642165,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044065435043464903,
|
|
"loss": 4.7393,
|
|
"mean_token_accuracy": 0.23000258207321167,
|
|
"num_tokens": 53539105.0,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"entropy": 5.422103977203369,
|
|
"epoch": 2.4302539258269293,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004406342030804671,
|
|
"loss": 4.8726,
|
|
"mean_token_accuracy": 0.2208527147769928,
|
|
"num_tokens": 53548537.0,
|
|
"step": 29095
|
|
},
|
|
{
|
|
"entropy": 5.339265441894531,
|
|
"epoch": 2.4306715669896426,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004406140528266591,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.23115672469139098,
|
|
"num_tokens": 53557467.0,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"entropy": 5.4229350090026855,
|
|
"epoch": 2.4310892081523554,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044059389967357774,
|
|
"loss": 4.8146,
|
|
"mean_token_accuracy": 0.22446488887071608,
|
|
"num_tokens": 53566970.0,
|
|
"step": 29105
|
|
},
|
|
{
|
|
"entropy": 5.4039021015167235,
|
|
"epoch": 2.4315068493150687,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044057374362157587,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.2240094691514969,
|
|
"num_tokens": 53576320.0,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"entropy": 5.337706089019775,
|
|
"epoch": 2.4319244904777815,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044055358467100627,
|
|
"loss": 4.6931,
|
|
"mean_token_accuracy": 0.23858672529459,
|
|
"num_tokens": 53585135.0,
|
|
"step": 29115
|
|
},
|
|
{
|
|
"entropy": 5.366051387786865,
|
|
"epoch": 2.4323421316404943,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044053342282222196,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.22858193516731262,
|
|
"num_tokens": 53594138.0,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"entropy": 5.381672954559326,
|
|
"epoch": 2.4327597728032075,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004405132580755758,
|
|
"loss": 4.6508,
|
|
"mean_token_accuracy": 0.2361499086022377,
|
|
"num_tokens": 53603133.0,
|
|
"step": 29125
|
|
},
|
|
{
|
|
"entropy": 5.427303123474121,
|
|
"epoch": 2.4331774139659204,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044049309043142084,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.22772350311279296,
|
|
"num_tokens": 53612219.0,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"entropy": 5.378885173797608,
|
|
"epoch": 2.4335950551286336,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004404729198901101,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.22006214708089827,
|
|
"num_tokens": 53621548.0,
|
|
"step": 29135
|
|
},
|
|
{
|
|
"entropy": 5.493011045455932,
|
|
"epoch": 2.4340126962913464,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044045274645199665,
|
|
"loss": 4.858,
|
|
"mean_token_accuracy": 0.22423142194747925,
|
|
"num_tokens": 53631376.0,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"entropy": 5.393495798110962,
|
|
"epoch": 2.4344303374540592,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004404325701174338,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.23347554504871368,
|
|
"num_tokens": 53639965.0,
|
|
"step": 29145
|
|
},
|
|
{
|
|
"entropy": 5.3128705501556395,
|
|
"epoch": 2.4348479786167725,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004404123908867747,
|
|
"loss": 4.6301,
|
|
"mean_token_accuracy": 0.23117214888334275,
|
|
"num_tokens": 53649799.0,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"entropy": 5.315077877044677,
|
|
"epoch": 2.4352656197794853,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00044039220876037255,
|
|
"loss": 4.7263,
|
|
"mean_token_accuracy": 0.2327072039246559,
|
|
"num_tokens": 53658612.0,
|
|
"step": 29155
|
|
},
|
|
{
|
|
"entropy": 5.39487509727478,
|
|
"epoch": 2.4356832609421986,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004403720237385808,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.22927132099866868,
|
|
"num_tokens": 53667197.0,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"entropy": 5.275224876403809,
|
|
"epoch": 2.4361009021049114,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044035183582175264,
|
|
"loss": 4.6405,
|
|
"mean_token_accuracy": 0.23749839514493942,
|
|
"num_tokens": 53675953.0,
|
|
"step": 29165
|
|
},
|
|
{
|
|
"entropy": 5.424673700332642,
|
|
"epoch": 2.4365185432676246,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044033164501024153,
|
|
"loss": 4.8189,
|
|
"mean_token_accuracy": 0.23074691146612167,
|
|
"num_tokens": 53685135.0,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"entropy": 5.464889049530029,
|
|
"epoch": 2.4369361844303374,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000440311451304401,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.22392071783542633,
|
|
"num_tokens": 53694024.0,
|
|
"step": 29175
|
|
},
|
|
{
|
|
"entropy": 5.4336268424987795,
|
|
"epoch": 2.4373538255930507,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044029125470458445,
|
|
"loss": 4.7707,
|
|
"mean_token_accuracy": 0.22266102582216263,
|
|
"num_tokens": 53703699.0,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"entropy": 5.323811483383179,
|
|
"epoch": 2.4377714667557635,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004402710552111456,
|
|
"loss": 4.6484,
|
|
"mean_token_accuracy": 0.23351801335811614,
|
|
"num_tokens": 53713121.0,
|
|
"step": 29185
|
|
},
|
|
{
|
|
"entropy": 5.341347599029541,
|
|
"epoch": 2.4381891079184763,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044025085282443807,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.23390483111143112,
|
|
"num_tokens": 53721896.0,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"entropy": 5.349221515655517,
|
|
"epoch": 2.4386067490811896,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044023064754481535,
|
|
"loss": 4.6859,
|
|
"mean_token_accuracy": 0.23337300717830659,
|
|
"num_tokens": 53731085.0,
|
|
"step": 29195
|
|
},
|
|
{
|
|
"entropy": 5.3550268650054935,
|
|
"epoch": 2.4390243902439024,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004402104393726313,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.22744798213243483,
|
|
"num_tokens": 53739816.0,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"entropy": 5.325896263122559,
|
|
"epoch": 2.4394420314066156,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004401902283082396,
|
|
"loss": 4.6963,
|
|
"mean_token_accuracy": 0.23466522097587586,
|
|
"num_tokens": 53748495.0,
|
|
"step": 29205
|
|
},
|
|
{
|
|
"entropy": 5.48150405883789,
|
|
"epoch": 2.4398596725693285,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044017001435199413,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.22464798241853715,
|
|
"num_tokens": 53758622.0,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"entropy": 5.445885372161865,
|
|
"epoch": 2.4402773137320413,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004401497975042487,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.21601729691028596,
|
|
"num_tokens": 53769867.0,
|
|
"step": 29215
|
|
},
|
|
{
|
|
"entropy": 5.50061993598938,
|
|
"epoch": 2.4406949548947545,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044012957776535735,
|
|
"loss": 4.8722,
|
|
"mean_token_accuracy": 0.22055047154426574,
|
|
"num_tokens": 53780217.0,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"entropy": 5.413617324829102,
|
|
"epoch": 2.4411125960574673,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004401093551356739,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.23709283471107484,
|
|
"num_tokens": 53788977.0,
|
|
"step": 29225
|
|
},
|
|
{
|
|
"entropy": 5.381994009017944,
|
|
"epoch": 2.4415302372201806,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044008912961555246,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.22551191449165345,
|
|
"num_tokens": 53797955.0,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"entropy": 5.299093770980835,
|
|
"epoch": 2.4419478783828934,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004400689012053472,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.234041990339756,
|
|
"num_tokens": 53806929.0,
|
|
"step": 29235
|
|
},
|
|
{
|
|
"entropy": 5.354500246047974,
|
|
"epoch": 2.442365519545606,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000440048669905412,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.233074913918972,
|
|
"num_tokens": 53816071.0,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"entropy": 5.424254131317139,
|
|
"epoch": 2.4427831607083195,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044002843571610124,
|
|
"loss": 4.6831,
|
|
"mean_token_accuracy": 0.22915804237127305,
|
|
"num_tokens": 53824376.0,
|
|
"step": 29245
|
|
},
|
|
{
|
|
"entropy": 5.37452974319458,
|
|
"epoch": 2.4432008018710323,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000440008198637769,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.23551491349935533,
|
|
"num_tokens": 53833504.0,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"entropy": 5.380328607559204,
|
|
"epoch": 2.4436184430337455,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004399879586707697,
|
|
"loss": 4.7418,
|
|
"mean_token_accuracy": 0.22707620412111282,
|
|
"num_tokens": 53842027.0,
|
|
"step": 29255
|
|
},
|
|
{
|
|
"entropy": 5.406660795211792,
|
|
"epoch": 2.4440360841964583,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004399677158154576,
|
|
"loss": 4.7417,
|
|
"mean_token_accuracy": 0.2357712060213089,
|
|
"num_tokens": 53849895.0,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"entropy": 5.45488429069519,
|
|
"epoch": 2.444453725359171,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000439947470072187,
|
|
"loss": 4.8326,
|
|
"mean_token_accuracy": 0.2220374971628189,
|
|
"num_tokens": 53860030.0,
|
|
"step": 29265
|
|
},
|
|
{
|
|
"entropy": 5.408830547332764,
|
|
"epoch": 2.4448713665218844,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004399272214413124,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.22746570110321046,
|
|
"num_tokens": 53869298.0,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"entropy": 5.410628986358643,
|
|
"epoch": 2.4452890076845972,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004399069699231883,
|
|
"loss": 4.7009,
|
|
"mean_token_accuracy": 0.2266298770904541,
|
|
"num_tokens": 53878019.0,
|
|
"step": 29275
|
|
},
|
|
{
|
|
"entropy": 5.439551925659179,
|
|
"epoch": 2.4457066488473105,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043988671551816914,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.22559793144464493,
|
|
"num_tokens": 53886783.0,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"entropy": 5.4483616828918455,
|
|
"epoch": 2.4461242900100233,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043986645822660956,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.24050463289022445,
|
|
"num_tokens": 53895459.0,
|
|
"step": 29285
|
|
},
|
|
{
|
|
"entropy": 5.408515739440918,
|
|
"epoch": 2.4465419311727366,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043984619804886423,
|
|
"loss": 4.8272,
|
|
"mean_token_accuracy": 0.22597333043813705,
|
|
"num_tokens": 53904901.0,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"entropy": 5.407435941696167,
|
|
"epoch": 2.4469595723354494,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004398259349852877,
|
|
"loss": 4.7703,
|
|
"mean_token_accuracy": 0.22532115280628204,
|
|
"num_tokens": 53913170.0,
|
|
"step": 29295
|
|
},
|
|
{
|
|
"entropy": 5.3188337802886965,
|
|
"epoch": 2.4473772134981626,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043980566903623487,
|
|
"loss": 4.6229,
|
|
"mean_token_accuracy": 0.23381292223930358,
|
|
"num_tokens": 53921950.0,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"entropy": 5.404751586914062,
|
|
"epoch": 2.4477948546608754,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004397854002020604,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.22694683969020843,
|
|
"num_tokens": 53930984.0,
|
|
"step": 29305
|
|
},
|
|
{
|
|
"entropy": 5.448578691482544,
|
|
"epoch": 2.4482124958235882,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043976512848311906,
|
|
"loss": 4.8031,
|
|
"mean_token_accuracy": 0.22281621694564818,
|
|
"num_tokens": 53941498.0,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"entropy": 5.310285854339599,
|
|
"epoch": 2.4486301369863015,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004397448538797659,
|
|
"loss": 4.6911,
|
|
"mean_token_accuracy": 0.23191599994897844,
|
|
"num_tokens": 53950229.0,
|
|
"step": 29315
|
|
},
|
|
{
|
|
"entropy": 5.43267240524292,
|
|
"epoch": 2.4490477781490143,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004397245763923557,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.22297449707984923,
|
|
"num_tokens": 53959227.0,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"entropy": 5.493699932098389,
|
|
"epoch": 2.4494654193117276,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004397042960212436,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.21792176365852356,
|
|
"num_tokens": 53967895.0,
|
|
"step": 29325
|
|
},
|
|
{
|
|
"entropy": 5.489964008331299,
|
|
"epoch": 2.4498830604744404,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004396840127667845,
|
|
"loss": 4.8285,
|
|
"mean_token_accuracy": 0.22281801253557204,
|
|
"num_tokens": 53977822.0,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"entropy": 5.4223020553588865,
|
|
"epoch": 2.450300701637153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004396637266293335,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.22888536304235457,
|
|
"num_tokens": 53986924.0,
|
|
"step": 29335
|
|
},
|
|
{
|
|
"entropy": 5.40077953338623,
|
|
"epoch": 2.4507183427998664,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004396434376092458,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.2281498581171036,
|
|
"num_tokens": 53996482.0,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"entropy": 5.368122863769531,
|
|
"epoch": 2.4511359839625793,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004396231457068765,
|
|
"loss": 4.6683,
|
|
"mean_token_accuracy": 0.23976296186447144,
|
|
"num_tokens": 54005717.0,
|
|
"step": 29345
|
|
},
|
|
{
|
|
"entropy": 5.297445344924927,
|
|
"epoch": 2.4515536251252925,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043960285092258097,
|
|
"loss": 4.5858,
|
|
"mean_token_accuracy": 0.23883695751428605,
|
|
"num_tokens": 54013825.0,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"entropy": 5.403757333755493,
|
|
"epoch": 2.4519712662880053,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004395825532567143,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.22712235599756242,
|
|
"num_tokens": 54022975.0,
|
|
"step": 29355
|
|
},
|
|
{
|
|
"entropy": 5.448872327804565,
|
|
"epoch": 2.452388907450718,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000439562252709632,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.22415267378091813,
|
|
"num_tokens": 54031035.0,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"entropy": 5.457181119918824,
|
|
"epoch": 2.4528065486134314,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004395419492816894,
|
|
"loss": 4.7071,
|
|
"mean_token_accuracy": 0.2369937092065811,
|
|
"num_tokens": 54040424.0,
|
|
"step": 29365
|
|
},
|
|
{
|
|
"entropy": 5.381383943557739,
|
|
"epoch": 2.453224189776144,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004395216429732418,
|
|
"loss": 4.6959,
|
|
"mean_token_accuracy": 0.230035762488842,
|
|
"num_tokens": 54049960.0,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"entropy": 5.394305610656739,
|
|
"epoch": 2.4536418309388575,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043950133378464485,
|
|
"loss": 4.7487,
|
|
"mean_token_accuracy": 0.22019579112529755,
|
|
"num_tokens": 54058332.0,
|
|
"step": 29375
|
|
},
|
|
{
|
|
"entropy": 5.321247291564942,
|
|
"epoch": 2.4540594721015703,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004394810217162541,
|
|
"loss": 4.5994,
|
|
"mean_token_accuracy": 0.23812661319971085,
|
|
"num_tokens": 54067049.0,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"entropy": 5.39507098197937,
|
|
"epoch": 2.454477113264283,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004394607067684251,
|
|
"loss": 4.7338,
|
|
"mean_token_accuracy": 0.2298256441950798,
|
|
"num_tokens": 54076200.0,
|
|
"step": 29385
|
|
},
|
|
{
|
|
"entropy": 5.414413499832153,
|
|
"epoch": 2.4548947544269963,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043944038894151336,
|
|
"loss": 4.7193,
|
|
"mean_token_accuracy": 0.22699918150901793,
|
|
"num_tokens": 54084374.0,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"entropy": 5.4234260559082035,
|
|
"epoch": 2.455312395589709,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004394200682358748,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.23023731112480164,
|
|
"num_tokens": 54093618.0,
|
|
"step": 29395
|
|
},
|
|
{
|
|
"entropy": 5.408598709106445,
|
|
"epoch": 2.4557300367524224,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004393997446518649,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.23325581550598146,
|
|
"num_tokens": 54102942.0,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"entropy": 5.268873786926269,
|
|
"epoch": 2.456147677915135,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004393794181898397,
|
|
"loss": 4.6444,
|
|
"mean_token_accuracy": 0.23814296275377272,
|
|
"num_tokens": 54111331.0,
|
|
"step": 29405
|
|
},
|
|
{
|
|
"entropy": 5.352477407455444,
|
|
"epoch": 2.4565653190778485,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004393590888501548,
|
|
"loss": 4.6705,
|
|
"mean_token_accuracy": 0.234475776553154,
|
|
"num_tokens": 54119920.0,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"entropy": 5.314004278182983,
|
|
"epoch": 2.4569829602405613,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004393387566331663,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.2358105704188347,
|
|
"num_tokens": 54129813.0,
|
|
"step": 29415
|
|
},
|
|
{
|
|
"entropy": 5.372016048431396,
|
|
"epoch": 2.4574006014032745,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043931842153923,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.2340753123164177,
|
|
"num_tokens": 54138369.0,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"entropy": 5.3716949939727785,
|
|
"epoch": 2.4578182425659874,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000439298083568702,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.22653894424438475,
|
|
"num_tokens": 54147622.0,
|
|
"step": 29425
|
|
},
|
|
{
|
|
"entropy": 5.42792820930481,
|
|
"epoch": 2.4582358837287,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004392777427219382,
|
|
"loss": 4.8274,
|
|
"mean_token_accuracy": 0.22263960391283036,
|
|
"num_tokens": 54156619.0,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"entropy": 5.403077459335327,
|
|
"epoch": 2.4586535248914134,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043925739899929484,
|
|
"loss": 4.6656,
|
|
"mean_token_accuracy": 0.23189163506031035,
|
|
"num_tokens": 54166525.0,
|
|
"step": 29435
|
|
},
|
|
{
|
|
"entropy": 5.353473949432373,
|
|
"epoch": 2.4590711660541262,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000439237052401128,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.23610591143369675,
|
|
"num_tokens": 54174955.0,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"entropy": 5.36930022239685,
|
|
"epoch": 2.4594888072168395,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043921670292779386,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.22914269864559172,
|
|
"num_tokens": 54185389.0,
|
|
"step": 29445
|
|
},
|
|
{
|
|
"entropy": 5.414495468139648,
|
|
"epoch": 2.4599064483795523,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004391963505796487,
|
|
"loss": 4.6988,
|
|
"mean_token_accuracy": 0.2356942042708397,
|
|
"num_tokens": 54194797.0,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"entropy": 5.43429217338562,
|
|
"epoch": 2.460324089542265,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004391759953570487,
|
|
"loss": 4.7732,
|
|
"mean_token_accuracy": 0.2266702339053154,
|
|
"num_tokens": 54203815.0,
|
|
"step": 29455
|
|
},
|
|
{
|
|
"entropy": 5.3749720573425295,
|
|
"epoch": 2.4607417307049784,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004391556372603503,
|
|
"loss": 4.7707,
|
|
"mean_token_accuracy": 0.2183392509818077,
|
|
"num_tokens": 54213075.0,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"entropy": 5.493234014511108,
|
|
"epoch": 2.461159371867691,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043913527628990984,
|
|
"loss": 4.8658,
|
|
"mean_token_accuracy": 0.21892457604408264,
|
|
"num_tokens": 54222551.0,
|
|
"step": 29465
|
|
},
|
|
{
|
|
"entropy": 5.363258647918701,
|
|
"epoch": 2.4615770130304044,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043911491244608386,
|
|
"loss": 4.6787,
|
|
"mean_token_accuracy": 0.2361874058842659,
|
|
"num_tokens": 54232294.0,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"entropy": 5.420360898971557,
|
|
"epoch": 2.4619946541931172,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004390945457292288,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.22506672888994217,
|
|
"num_tokens": 54241293.0,
|
|
"step": 29475
|
|
},
|
|
{
|
|
"entropy": 5.368663549423218,
|
|
"epoch": 2.46241229535583,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004390741761397012,
|
|
"loss": 4.7172,
|
|
"mean_token_accuracy": 0.23176800161600114,
|
|
"num_tokens": 54249801.0,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"entropy": 5.3798106670379635,
|
|
"epoch": 2.4628299365185433,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043905380367785757,
|
|
"loss": 4.6539,
|
|
"mean_token_accuracy": 0.23509243428707122,
|
|
"num_tokens": 54257747.0,
|
|
"step": 29485
|
|
},
|
|
{
|
|
"entropy": 5.415013933181763,
|
|
"epoch": 2.463247577681256,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004390334283440547,
|
|
"loss": 4.74,
|
|
"mean_token_accuracy": 0.23586136996746063,
|
|
"num_tokens": 54266050.0,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"entropy": 5.440028238296509,
|
|
"epoch": 2.4636652188439694,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043901305013864923,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.23072872310876846,
|
|
"num_tokens": 54275318.0,
|
|
"step": 29495
|
|
},
|
|
{
|
|
"entropy": 5.370812320709229,
|
|
"epoch": 2.464082860006682,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043899266906199784,
|
|
"loss": 4.723,
|
|
"mean_token_accuracy": 0.23604340106248856,
|
|
"num_tokens": 54284623.0,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"entropy": 5.429168033599853,
|
|
"epoch": 2.464500501169395,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004389722851144574,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.23221891075372697,
|
|
"num_tokens": 54293876.0,
|
|
"step": 29505
|
|
},
|
|
{
|
|
"entropy": 5.450435400009155,
|
|
"epoch": 2.4649181423321083,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043895189829638485,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.2182914912700653,
|
|
"num_tokens": 54303133.0,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"entropy": 5.453667879104614,
|
|
"epoch": 2.465335783494821,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004389315086081368,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.22946372479200364,
|
|
"num_tokens": 54311725.0,
|
|
"step": 29515
|
|
},
|
|
{
|
|
"entropy": 5.408078670501709,
|
|
"epoch": 2.4657534246575343,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043891111605007043,
|
|
"loss": 4.651,
|
|
"mean_token_accuracy": 0.2425609901547432,
|
|
"num_tokens": 54320268.0,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"entropy": 5.295914840698242,
|
|
"epoch": 2.466171065820247,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004388907206225427,
|
|
"loss": 4.6933,
|
|
"mean_token_accuracy": 0.23526401817798615,
|
|
"num_tokens": 54328833.0,
|
|
"step": 29525
|
|
},
|
|
{
|
|
"entropy": 5.354218530654907,
|
|
"epoch": 2.4665887069829604,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004388703223259106,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.2350412681698799,
|
|
"num_tokens": 54337556.0,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"entropy": 5.459948015213013,
|
|
"epoch": 2.467006348145673,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043884992116053137,
|
|
"loss": 4.7935,
|
|
"mean_token_accuracy": 0.2275543197989464,
|
|
"num_tokens": 54346170.0,
|
|
"step": 29535
|
|
},
|
|
{
|
|
"entropy": 5.393099641799926,
|
|
"epoch": 2.4674239893083865,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043882951712676183,
|
|
"loss": 4.7066,
|
|
"mean_token_accuracy": 0.231057870388031,
|
|
"num_tokens": 54355328.0,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"entropy": 5.359944152832031,
|
|
"epoch": 2.4678416304710993,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043880911022495955,
|
|
"loss": 4.6665,
|
|
"mean_token_accuracy": 0.2353191614151001,
|
|
"num_tokens": 54364445.0,
|
|
"step": 29545
|
|
},
|
|
{
|
|
"entropy": 5.410159254074097,
|
|
"epoch": 2.468259271633812,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004387887004554816,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.2241741418838501,
|
|
"num_tokens": 54373407.0,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"entropy": 5.312722635269165,
|
|
"epoch": 2.4686769127965253,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004387682878186852,
|
|
"loss": 4.6297,
|
|
"mean_token_accuracy": 0.23991039544343948,
|
|
"num_tokens": 54381116.0,
|
|
"step": 29555
|
|
},
|
|
{
|
|
"entropy": 5.428947448730469,
|
|
"epoch": 2.469094553959238,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004387478723149279,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.22075800597667694,
|
|
"num_tokens": 54390174.0,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"entropy": 5.422424268722534,
|
|
"epoch": 2.4695121951219514,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043872745394456697,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.2294096902012825,
|
|
"num_tokens": 54399893.0,
|
|
"step": 29565
|
|
},
|
|
{
|
|
"entropy": 5.47906174659729,
|
|
"epoch": 2.4699298362846642,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043870703270795986,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.2218276396393776,
|
|
"num_tokens": 54410037.0,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"entropy": 5.3781908512115475,
|
|
"epoch": 2.470347477447377,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004386866086054641,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.2337907761335373,
|
|
"num_tokens": 54419128.0,
|
|
"step": 29575
|
|
},
|
|
{
|
|
"entropy": 5.404659223556519,
|
|
"epoch": 2.4707651186100903,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043866618163743723,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.2335675597190857,
|
|
"num_tokens": 54428351.0,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"entropy": 5.402598237991333,
|
|
"epoch": 2.471182759772803,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043864575180423685,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.23404883593320847,
|
|
"num_tokens": 54437728.0,
|
|
"step": 29585
|
|
},
|
|
{
|
|
"entropy": 5.559029006958008,
|
|
"epoch": 2.4716004009355164,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00043862531910622056,
|
|
"loss": 4.8154,
|
|
"mean_token_accuracy": 0.21892910152673722,
|
|
"num_tokens": 54446504.0,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"entropy": 5.449546194076538,
|
|
"epoch": 2.472018042098229,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043860488354374613,
|
|
"loss": 4.8015,
|
|
"mean_token_accuracy": 0.2222814679145813,
|
|
"num_tokens": 54456078.0,
|
|
"step": 29595
|
|
},
|
|
{
|
|
"entropy": 5.304742336273193,
|
|
"epoch": 2.472435683260942,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043858444511717126,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.23497312068939208,
|
|
"num_tokens": 54465713.0,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"entropy": 5.330724430084229,
|
|
"epoch": 2.4728533244236552,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043856400382685383,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.23765061497688295,
|
|
"num_tokens": 54473803.0,
|
|
"step": 29605
|
|
},
|
|
{
|
|
"entropy": 5.377138090133667,
|
|
"epoch": 2.473270965586368,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004385435596731516,
|
|
"loss": 4.7565,
|
|
"mean_token_accuracy": 0.23210886269807815,
|
|
"num_tokens": 54482920.0,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"entropy": 5.395461082458496,
|
|
"epoch": 2.4736886067490813,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043852311265642246,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.2314550146460533,
|
|
"num_tokens": 54491556.0,
|
|
"step": 29615
|
|
},
|
|
{
|
|
"entropy": 5.3875127792358395,
|
|
"epoch": 2.474106247911794,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043850266277702446,
|
|
"loss": 4.6737,
|
|
"mean_token_accuracy": 0.23230537623167039,
|
|
"num_tokens": 54500169.0,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"entropy": 5.378681707382202,
|
|
"epoch": 2.4745238890745074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004384822100353155,
|
|
"loss": 4.6808,
|
|
"mean_token_accuracy": 0.23327601701021194,
|
|
"num_tokens": 54508973.0,
|
|
"step": 29625
|
|
},
|
|
{
|
|
"entropy": 5.396377897262573,
|
|
"epoch": 2.47494153023722,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004384617544316537,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.22487622499465942,
|
|
"num_tokens": 54518450.0,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"entropy": 5.382870626449585,
|
|
"epoch": 2.475359171399933,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043844129596639714,
|
|
"loss": 4.7038,
|
|
"mean_token_accuracy": 0.22637565732002257,
|
|
"num_tokens": 54527986.0,
|
|
"step": 29635
|
|
},
|
|
{
|
|
"entropy": 5.344627904891968,
|
|
"epoch": 2.4757768125626463,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000438420834639904,
|
|
"loss": 4.6518,
|
|
"mean_token_accuracy": 0.23551854193210603,
|
|
"num_tokens": 54536792.0,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"entropy": 5.484889364242553,
|
|
"epoch": 2.476194453725359,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043840037045253234,
|
|
"loss": 4.9192,
|
|
"mean_token_accuracy": 0.21776298433542252,
|
|
"num_tokens": 54547225.0,
|
|
"step": 29645
|
|
},
|
|
{
|
|
"entropy": 5.479263067245483,
|
|
"epoch": 2.4766120948880723,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004383799034046405,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.22516784965991973,
|
|
"num_tokens": 54557732.0,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"entropy": 5.45164384841919,
|
|
"epoch": 2.477029736050785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004383594334965869,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.2246097132563591,
|
|
"num_tokens": 54567510.0,
|
|
"step": 29655
|
|
},
|
|
{
|
|
"entropy": 5.449235677719116,
|
|
"epoch": 2.4774473772134984,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004383389607287297,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.22899818867444993,
|
|
"num_tokens": 54577619.0,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"entropy": 5.300570249557495,
|
|
"epoch": 2.477865018376211,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004383184851014274,
|
|
"loss": 4.647,
|
|
"mean_token_accuracy": 0.23177456855773926,
|
|
"num_tokens": 54586752.0,
|
|
"step": 29665
|
|
},
|
|
{
|
|
"entropy": 5.33514552116394,
|
|
"epoch": 2.478282659538924,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043829800661503843,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.22748497724533082,
|
|
"num_tokens": 54595757.0,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"entropy": 5.404862689971924,
|
|
"epoch": 2.4787003007016373,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043827752526992125,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.22964914739131928,
|
|
"num_tokens": 54605134.0,
|
|
"step": 29675
|
|
},
|
|
{
|
|
"entropy": 5.3439967155456545,
|
|
"epoch": 2.47911794186435,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043825704106643454,
|
|
"loss": 4.6201,
|
|
"mean_token_accuracy": 0.23544954508543015,
|
|
"num_tokens": 54614471.0,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"entropy": 5.40575270652771,
|
|
"epoch": 2.4795355830270633,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043823655400493676,
|
|
"loss": 4.749,
|
|
"mean_token_accuracy": 0.22753578275442124,
|
|
"num_tokens": 54623466.0,
|
|
"step": 29685
|
|
},
|
|
{
|
|
"entropy": 5.338783645629883,
|
|
"epoch": 2.479953224189776,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043821606408578665,
|
|
"loss": 4.7014,
|
|
"mean_token_accuracy": 0.23261882811784745,
|
|
"num_tokens": 54632898.0,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"entropy": 5.460416507720947,
|
|
"epoch": 2.480370865352489,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004381955713093428,
|
|
"loss": 4.7564,
|
|
"mean_token_accuracy": 0.22881269752979277,
|
|
"num_tokens": 54642934.0,
|
|
"step": 29695
|
|
},
|
|
{
|
|
"entropy": 5.386788940429687,
|
|
"epoch": 2.480788506515202,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043817507567596415,
|
|
"loss": 4.6871,
|
|
"mean_token_accuracy": 0.23478034883737564,
|
|
"num_tokens": 54652602.0,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"entropy": 5.464125299453736,
|
|
"epoch": 2.481206147677915,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043815457718600933,
|
|
"loss": 4.7861,
|
|
"mean_token_accuracy": 0.22042740881443024,
|
|
"num_tokens": 54661801.0,
|
|
"step": 29705
|
|
},
|
|
{
|
|
"entropy": 5.416866159439087,
|
|
"epoch": 2.4816237888406283,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004381340758398372,
|
|
"loss": 4.7611,
|
|
"mean_token_accuracy": 0.2330602914094925,
|
|
"num_tokens": 54671977.0,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"entropy": 5.346208333969116,
|
|
"epoch": 2.482041430003341,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043811357163780676,
|
|
"loss": 4.6477,
|
|
"mean_token_accuracy": 0.23559416979551315,
|
|
"num_tokens": 54681820.0,
|
|
"step": 29715
|
|
},
|
|
{
|
|
"entropy": 5.386127519607544,
|
|
"epoch": 2.482459071166054,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004380930645802769,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.2267420098185539,
|
|
"num_tokens": 54690713.0,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"entropy": 5.458346843719482,
|
|
"epoch": 2.482876712328767,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004380725546676067,
|
|
"loss": 4.7852,
|
|
"mean_token_accuracy": 0.2251571699976921,
|
|
"num_tokens": 54700808.0,
|
|
"step": 29725
|
|
},
|
|
{
|
|
"entropy": 5.337960529327392,
|
|
"epoch": 2.48329435349148,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043805204190015503,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.23667239844799043,
|
|
"num_tokens": 54708415.0,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"entropy": 5.2802809715271,
|
|
"epoch": 2.4837119946541932,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004380315262782811,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.2275606080889702,
|
|
"num_tokens": 54716887.0,
|
|
"step": 29735
|
|
},
|
|
{
|
|
"entropy": 5.450356435775757,
|
|
"epoch": 2.484129635816906,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004380110078023441,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.22041373550891877,
|
|
"num_tokens": 54727103.0,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"entropy": 5.358030986785889,
|
|
"epoch": 2.4845472769796193,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004379904864727032,
|
|
"loss": 4.6399,
|
|
"mean_token_accuracy": 0.23266790956258773,
|
|
"num_tokens": 54735405.0,
|
|
"step": 29745
|
|
},
|
|
{
|
|
"entropy": 5.4348897457122805,
|
|
"epoch": 2.484964918142332,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043796996228971766,
|
|
"loss": 4.7984,
|
|
"mean_token_accuracy": 0.21962178200483323,
|
|
"num_tokens": 54745278.0,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"entropy": 5.4057698249816895,
|
|
"epoch": 2.485382559305045,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004379494352537467,
|
|
"loss": 4.7208,
|
|
"mean_token_accuracy": 0.2332587018609047,
|
|
"num_tokens": 54753632.0,
|
|
"step": 29755
|
|
},
|
|
{
|
|
"entropy": 5.438232183456421,
|
|
"epoch": 2.485800200467758,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004379289053651498,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.21670896857976912,
|
|
"num_tokens": 54763924.0,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"entropy": 5.334457111358643,
|
|
"epoch": 2.486217841630471,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004379083726242862,
|
|
"loss": 4.6141,
|
|
"mean_token_accuracy": 0.23617784380912782,
|
|
"num_tokens": 54772747.0,
|
|
"step": 29765
|
|
},
|
|
{
|
|
"entropy": 5.422698163986206,
|
|
"epoch": 2.4866354827931842,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004378878370315156,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.23548030406236647,
|
|
"num_tokens": 54782325.0,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"entropy": 5.390041875839233,
|
|
"epoch": 2.487053123955897,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004378672985871972,
|
|
"loss": 4.7079,
|
|
"mean_token_accuracy": 0.22906575351953506,
|
|
"num_tokens": 54791359.0,
|
|
"step": 29775
|
|
},
|
|
{
|
|
"entropy": 5.378809213638306,
|
|
"epoch": 2.4874707651186103,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043784675729169076,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.2316167265176773,
|
|
"num_tokens": 54800281.0,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"entropy": 5.352039098739624,
|
|
"epoch": 2.487888406281323,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004378262131453558,
|
|
"loss": 4.6556,
|
|
"mean_token_accuracy": 0.23248500972986222,
|
|
"num_tokens": 54808954.0,
|
|
"step": 29785
|
|
},
|
|
{
|
|
"entropy": 5.455753135681152,
|
|
"epoch": 2.488306047444036,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000437805666148552,
|
|
"loss": 4.7301,
|
|
"mean_token_accuracy": 0.23937533646821976,
|
|
"num_tokens": 54817542.0,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"entropy": 5.381435537338257,
|
|
"epoch": 2.488723688606749,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043778511630163905,
|
|
"loss": 4.711,
|
|
"mean_token_accuracy": 0.2275310918688774,
|
|
"num_tokens": 54826189.0,
|
|
"step": 29795
|
|
},
|
|
{
|
|
"entropy": 5.42578353881836,
|
|
"epoch": 2.489141329769462,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043776456360497665,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.22576287388801575,
|
|
"num_tokens": 54835352.0,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"entropy": 5.4518403053283695,
|
|
"epoch": 2.4895589709321753,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004377440080589247,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.22453192472457886,
|
|
"num_tokens": 54844917.0,
|
|
"step": 29805
|
|
},
|
|
{
|
|
"entropy": 5.431290340423584,
|
|
"epoch": 2.489976612094888,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000437723449663843,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.2238757371902466,
|
|
"num_tokens": 54854489.0,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"entropy": 5.39858603477478,
|
|
"epoch": 2.490394253257601,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004377028884200914,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.2206752970814705,
|
|
"num_tokens": 54864462.0,
|
|
"step": 29815
|
|
},
|
|
{
|
|
"entropy": 5.366853046417236,
|
|
"epoch": 2.490811894420314,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004376823243280298,
|
|
"loss": 4.7173,
|
|
"mean_token_accuracy": 0.22817000150680541,
|
|
"num_tokens": 54873958.0,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"entropy": 5.394676733016968,
|
|
"epoch": 2.491229535583027,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004376617573880185,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.24113839268684387,
|
|
"num_tokens": 54882553.0,
|
|
"step": 29825
|
|
},
|
|
{
|
|
"entropy": 5.383571004867553,
|
|
"epoch": 2.49164717674574,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004376411876004172,
|
|
"loss": 4.7479,
|
|
"mean_token_accuracy": 0.2289193317294121,
|
|
"num_tokens": 54891618.0,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"entropy": 5.429444456100464,
|
|
"epoch": 2.492064817908453,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004376206149655862,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.234710456430912,
|
|
"num_tokens": 54900621.0,
|
|
"step": 29835
|
|
},
|
|
{
|
|
"entropy": 5.395053386688232,
|
|
"epoch": 2.492482459071166,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004376000394838856,
|
|
"loss": 4.6998,
|
|
"mean_token_accuracy": 0.23723892420530318,
|
|
"num_tokens": 54909116.0,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"entropy": 5.4060866355896,
|
|
"epoch": 2.492900100233879,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004375794611556755,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.22718409299850464,
|
|
"num_tokens": 54917940.0,
|
|
"step": 29845
|
|
},
|
|
{
|
|
"entropy": 5.3361447811126705,
|
|
"epoch": 2.493317741396592,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004375588799813163,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.22266752272844315,
|
|
"num_tokens": 54927548.0,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"entropy": 5.415119218826294,
|
|
"epoch": 2.493735382559305,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004375382959611682,
|
|
"loss": 4.7919,
|
|
"mean_token_accuracy": 0.22643722146749495,
|
|
"num_tokens": 54937157.0,
|
|
"step": 29855
|
|
},
|
|
{
|
|
"entropy": 5.4393504619598385,
|
|
"epoch": 2.494153023722018,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043751770909559155,
|
|
"loss": 4.7344,
|
|
"mean_token_accuracy": 0.22297911643981932,
|
|
"num_tokens": 54946851.0,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"entropy": 5.432677316665649,
|
|
"epoch": 2.4945706648847312,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043749711938494693,
|
|
"loss": 4.8032,
|
|
"mean_token_accuracy": 0.2238169565796852,
|
|
"num_tokens": 54956686.0,
|
|
"step": 29865
|
|
},
|
|
{
|
|
"entropy": 5.42267861366272,
|
|
"epoch": 2.494988306047444,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043747652682959455,
|
|
"loss": 4.7129,
|
|
"mean_token_accuracy": 0.22923504114151,
|
|
"num_tokens": 54965233.0,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"entropy": 5.403764343261718,
|
|
"epoch": 2.495405947210157,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004374559314298949,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.2320734217762947,
|
|
"num_tokens": 54973647.0,
|
|
"step": 29875
|
|
},
|
|
{
|
|
"entropy": 5.395562314987183,
|
|
"epoch": 2.49582358837287,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043743533318620873,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.22294308692216874,
|
|
"num_tokens": 54982550.0,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"entropy": 5.3296126365661625,
|
|
"epoch": 2.496241229535583,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043741473209889654,
|
|
"loss": 4.6399,
|
|
"mean_token_accuracy": 0.23441592305898667,
|
|
"num_tokens": 54991137.0,
|
|
"step": 29885
|
|
},
|
|
{
|
|
"entropy": 5.326698875427246,
|
|
"epoch": 2.496658870698296,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004373941281683189,
|
|
"loss": 4.7217,
|
|
"mean_token_accuracy": 0.23178104907274247,
|
|
"num_tokens": 55000271.0,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"entropy": 5.446249055862427,
|
|
"epoch": 2.497076511861009,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004373735213948366,
|
|
"loss": 4.8202,
|
|
"mean_token_accuracy": 0.2258245036005974,
|
|
"num_tokens": 55009379.0,
|
|
"step": 29895
|
|
},
|
|
{
|
|
"entropy": 5.369227266311645,
|
|
"epoch": 2.4974941530237222,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043735291177881045,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.23679138869047164,
|
|
"num_tokens": 55018562.0,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"entropy": 5.408477878570556,
|
|
"epoch": 2.497911794186435,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000437332299320601,
|
|
"loss": 4.773,
|
|
"mean_token_accuracy": 0.22847001403570175,
|
|
"num_tokens": 55027429.0,
|
|
"step": 29905
|
|
},
|
|
{
|
|
"entropy": 5.455473613739014,
|
|
"epoch": 2.498329435349148,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004373116840205693,
|
|
"loss": 4.7803,
|
|
"mean_token_accuracy": 0.2210561916232109,
|
|
"num_tokens": 55037510.0,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"entropy": 5.402144145965576,
|
|
"epoch": 2.498747076511861,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043729106587907625,
|
|
"loss": 4.7058,
|
|
"mean_token_accuracy": 0.23474055379629136,
|
|
"num_tokens": 55046944.0,
|
|
"step": 29915
|
|
},
|
|
{
|
|
"entropy": 5.326596784591675,
|
|
"epoch": 2.499164717674574,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043727044489648263,
|
|
"loss": 4.694,
|
|
"mean_token_accuracy": 0.23187075555324554,
|
|
"num_tokens": 55056281.0,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"entropy": 5.313770341873169,
|
|
"epoch": 2.499582358837287,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004372498210731497,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.231804695725441,
|
|
"num_tokens": 55064764.0,
|
|
"step": 29925
|
|
},
|
|
{
|
|
"entropy": 5.4129866600036625,
|
|
"epoch": 2.5,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043722919440943833,
|
|
"loss": 4.7579,
|
|
"mean_token_accuracy": 0.22607941478490828,
|
|
"num_tokens": 55074054.0,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"entropy": 5.382832956314087,
|
|
"epoch": 2.500417641162713,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004372085649057095,
|
|
"loss": 4.7121,
|
|
"mean_token_accuracy": 0.23528579473495484,
|
|
"num_tokens": 55082623.0,
|
|
"step": 29935
|
|
},
|
|
{
|
|
"entropy": 5.443752861022949,
|
|
"epoch": 2.500835282325426,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043718793256232463,
|
|
"loss": 4.7876,
|
|
"mean_token_accuracy": 0.22626014351844786,
|
|
"num_tokens": 55092057.0,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"entropy": 5.369237661361694,
|
|
"epoch": 2.501252923488139,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043716729737964475,
|
|
"loss": 4.6621,
|
|
"mean_token_accuracy": 0.2362334907054901,
|
|
"num_tokens": 55099887.0,
|
|
"step": 29945
|
|
},
|
|
{
|
|
"entropy": 5.418674039840698,
|
|
"epoch": 2.501670564650852,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043714665935803103,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.2302424728870392,
|
|
"num_tokens": 55108143.0,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"entropy": 5.412570762634277,
|
|
"epoch": 2.502088205813565,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043712601849784494,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.22632782012224198,
|
|
"num_tokens": 55117920.0,
|
|
"step": 29955
|
|
},
|
|
{
|
|
"entropy": 5.523916530609131,
|
|
"epoch": 2.5025058469762778,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043710537479944774,
|
|
"loss": 4.8183,
|
|
"mean_token_accuracy": 0.22859721034765243,
|
|
"num_tokens": 55128557.0,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"entropy": 5.33575930595398,
|
|
"epoch": 2.502923488138991,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043708472826320085,
|
|
"loss": 4.6609,
|
|
"mean_token_accuracy": 0.23161069601774215,
|
|
"num_tokens": 55137886.0,
|
|
"step": 29965
|
|
},
|
|
{
|
|
"entropy": 5.447540616989135,
|
|
"epoch": 2.503341129301704,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004370640788894656,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.22322786897420882,
|
|
"num_tokens": 55146986.0,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"entropy": 5.373906183242798,
|
|
"epoch": 2.503758770464417,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004370434266786037,
|
|
"loss": 4.7338,
|
|
"mean_token_accuracy": 0.2271803468465805,
|
|
"num_tokens": 55156190.0,
|
|
"step": 29975
|
|
},
|
|
{
|
|
"entropy": 5.432717609405517,
|
|
"epoch": 2.50417641162713,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004370227716309765,
|
|
"loss": 4.7022,
|
|
"mean_token_accuracy": 0.23355211615562438,
|
|
"num_tokens": 55165591.0,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"entropy": 5.417412996292114,
|
|
"epoch": 2.5045940527898427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043700211374694565,
|
|
"loss": 4.7112,
|
|
"mean_token_accuracy": 0.2255741149187088,
|
|
"num_tokens": 55174865.0,
|
|
"step": 29985
|
|
},
|
|
{
|
|
"entropy": 5.4440148830413815,
|
|
"epoch": 2.505011693952556,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004369814530268728,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.227877613902092,
|
|
"num_tokens": 55183199.0,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"entropy": 5.498405790328979,
|
|
"epoch": 2.505429335115269,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004369607894711196,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.22385574579238893,
|
|
"num_tokens": 55192258.0,
|
|
"step": 29995
|
|
},
|
|
{
|
|
"entropy": 5.412606191635132,
|
|
"epoch": 2.505846976277982,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004369401230800479,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.23561923950910568,
|
|
"num_tokens": 55200886.0,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 2.505846976277982,
|
|
"eval_entropy": 5.10311834596522,
|
|
"eval_loss": 4.752662181854248,
|
|
"eval_mean_token_accuracy": 0.23992045934208872,
|
|
"eval_num_tokens": 55200886.0,
|
|
"eval_runtime": 20.8952,
|
|
"eval_samples_per_second": 1807.259,
|
|
"eval_steps_per_second": 225.937,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"entropy": 5.423791074752808,
|
|
"epoch": 2.506264617440695,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004369194538540194,
|
|
"loss": 4.7303,
|
|
"mean_token_accuracy": 0.22500932663679124,
|
|
"num_tokens": 55210553.0,
|
|
"step": 30005
|
|
},
|
|
{
|
|
"entropy": 5.415908861160278,
|
|
"epoch": 2.506682258603408,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043689878179339593,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.22649856209754943,
|
|
"num_tokens": 55219807.0,
|
|
"step": 30010
|
|
},
|
|
{
|
|
"entropy": 5.341967296600342,
|
|
"epoch": 2.507099899766121,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004368781068985394,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.23046391159296037,
|
|
"num_tokens": 55228970.0,
|
|
"step": 30015
|
|
},
|
|
{
|
|
"entropy": 5.386670923233032,
|
|
"epoch": 2.507517540928834,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004368574291698118,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.22777438014745713,
|
|
"num_tokens": 55238688.0,
|
|
"step": 30020
|
|
},
|
|
{
|
|
"entropy": 5.423647356033325,
|
|
"epoch": 2.507935182091547,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000436836748607575,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.23166073709726334,
|
|
"num_tokens": 55247971.0,
|
|
"step": 30025
|
|
},
|
|
{
|
|
"entropy": 5.427230262756348,
|
|
"epoch": 2.50835282325426,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004368160652121912,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.23486043959856034,
|
|
"num_tokens": 55257806.0,
|
|
"step": 30030
|
|
},
|
|
{
|
|
"entropy": 5.3977806091308596,
|
|
"epoch": 2.508770464416973,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004367953789840224,
|
|
"loss": 4.7558,
|
|
"mean_token_accuracy": 0.23126026690006257,
|
|
"num_tokens": 55267339.0,
|
|
"step": 30035
|
|
},
|
|
{
|
|
"entropy": 5.429531669616699,
|
|
"epoch": 2.509188105579686,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043677468992343074,
|
|
"loss": 4.7896,
|
|
"mean_token_accuracy": 0.22193440049886703,
|
|
"num_tokens": 55277374.0,
|
|
"step": 30040
|
|
},
|
|
{
|
|
"entropy": 5.528741073608399,
|
|
"epoch": 2.509605746742399,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043675399803077837,
|
|
"loss": 4.8405,
|
|
"mean_token_accuracy": 0.22009692639112471,
|
|
"num_tokens": 55286979.0,
|
|
"step": 30045
|
|
},
|
|
{
|
|
"entropy": 5.3589174270629885,
|
|
"epoch": 2.510023387905112,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004367333033064275,
|
|
"loss": 4.6391,
|
|
"mean_token_accuracy": 0.23373558074235917,
|
|
"num_tokens": 55295999.0,
|
|
"step": 30050
|
|
},
|
|
{
|
|
"entropy": 5.364858388900757,
|
|
"epoch": 2.5104410290678247,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004367126057507405,
|
|
"loss": 4.7711,
|
|
"mean_token_accuracy": 0.22377174645662307,
|
|
"num_tokens": 55304977.0,
|
|
"step": 30055
|
|
},
|
|
{
|
|
"entropy": 5.4361128330230715,
|
|
"epoch": 2.510858670230538,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004366919053640797,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.23421557247638702,
|
|
"num_tokens": 55314545.0,
|
|
"step": 30060
|
|
},
|
|
{
|
|
"entropy": 5.378316640853882,
|
|
"epoch": 2.511276311393251,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004366712021468076,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.23552292436361313,
|
|
"num_tokens": 55323546.0,
|
|
"step": 30065
|
|
},
|
|
{
|
|
"entropy": 5.331956195831299,
|
|
"epoch": 2.511693952555964,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043665049609928634,
|
|
"loss": 4.5846,
|
|
"mean_token_accuracy": 0.23506942093372346,
|
|
"num_tokens": 55332756.0,
|
|
"step": 30070
|
|
},
|
|
{
|
|
"entropy": 5.486721038818359,
|
|
"epoch": 2.512111593718677,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004366297872218786,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.21762748509645463,
|
|
"num_tokens": 55341864.0,
|
|
"step": 30075
|
|
},
|
|
{
|
|
"entropy": 5.3958922863006595,
|
|
"epoch": 2.5125292348813897,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043660907551494696,
|
|
"loss": 4.6933,
|
|
"mean_token_accuracy": 0.23273458927869797,
|
|
"num_tokens": 55351756.0,
|
|
"step": 30080
|
|
},
|
|
{
|
|
"entropy": 5.469833850860596,
|
|
"epoch": 2.512946876044103,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043658836097885387,
|
|
"loss": 4.8015,
|
|
"mean_token_accuracy": 0.22630574256181718,
|
|
"num_tokens": 55360959.0,
|
|
"step": 30085
|
|
},
|
|
{
|
|
"entropy": 5.4231174945831295,
|
|
"epoch": 2.5133645172068158,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043656764361396194,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.2314963921904564,
|
|
"num_tokens": 55371026.0,
|
|
"step": 30090
|
|
},
|
|
{
|
|
"entropy": 5.389787578582764,
|
|
"epoch": 2.513782158369529,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000436546923420634,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.23303772509098053,
|
|
"num_tokens": 55380091.0,
|
|
"step": 30095
|
|
},
|
|
{
|
|
"entropy": 5.343807554244995,
|
|
"epoch": 2.514199799532242,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043652620039923276,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.23093310743570328,
|
|
"num_tokens": 55388934.0,
|
|
"step": 30100
|
|
},
|
|
{
|
|
"entropy": 5.338000249862671,
|
|
"epoch": 2.5146174406949546,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004365054745501209,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.22780354470014572,
|
|
"num_tokens": 55397643.0,
|
|
"step": 30105
|
|
},
|
|
{
|
|
"entropy": 5.401426458358765,
|
|
"epoch": 2.515035081857668,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043648474587366134,
|
|
"loss": 4.7885,
|
|
"mean_token_accuracy": 0.2233349412679672,
|
|
"num_tokens": 55406953.0,
|
|
"step": 30110
|
|
},
|
|
{
|
|
"entropy": 5.342070913314819,
|
|
"epoch": 2.515452723020381,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004364640143702169,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.2367730751633644,
|
|
"num_tokens": 55416623.0,
|
|
"step": 30115
|
|
},
|
|
{
|
|
"entropy": 5.512736129760742,
|
|
"epoch": 2.515870364183094,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004364432800401505,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.2236717790365219,
|
|
"num_tokens": 55425818.0,
|
|
"step": 30120
|
|
},
|
|
{
|
|
"entropy": 5.539351511001587,
|
|
"epoch": 2.5162880053458068,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043642254288382514,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.21907095313072206,
|
|
"num_tokens": 55435104.0,
|
|
"step": 30125
|
|
},
|
|
{
|
|
"entropy": 5.374376630783081,
|
|
"epoch": 2.51670564650852,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004364018029016039,
|
|
"loss": 4.6546,
|
|
"mean_token_accuracy": 0.2362278252840042,
|
|
"num_tokens": 55443873.0,
|
|
"step": 30130
|
|
},
|
|
{
|
|
"entropy": 5.38408408164978,
|
|
"epoch": 2.517123287671233,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004363810600938498,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.2339485064148903,
|
|
"num_tokens": 55453780.0,
|
|
"step": 30135
|
|
},
|
|
{
|
|
"entropy": 5.411511421203613,
|
|
"epoch": 2.517540928833946,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043636031446092605,
|
|
"loss": 4.8566,
|
|
"mean_token_accuracy": 0.21859269738197326,
|
|
"num_tokens": 55463648.0,
|
|
"step": 30140
|
|
},
|
|
{
|
|
"entropy": 5.429401540756226,
|
|
"epoch": 2.517958569996659,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043633956600319575,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.23166637420654296,
|
|
"num_tokens": 55473318.0,
|
|
"step": 30145
|
|
},
|
|
{
|
|
"entropy": 5.444087314605713,
|
|
"epoch": 2.5183762111593717,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043631881472102214,
|
|
"loss": 4.8521,
|
|
"mean_token_accuracy": 0.21951081454753876,
|
|
"num_tokens": 55482511.0,
|
|
"step": 30150
|
|
},
|
|
{
|
|
"entropy": 5.41182861328125,
|
|
"epoch": 2.518793852322085,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043629806061476847,
|
|
"loss": 4.7529,
|
|
"mean_token_accuracy": 0.22694206535816192,
|
|
"num_tokens": 55491432.0,
|
|
"step": 30155
|
|
},
|
|
{
|
|
"entropy": 5.374487829208374,
|
|
"epoch": 2.519211493484798,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004362773036847981,
|
|
"loss": 4.7564,
|
|
"mean_token_accuracy": 0.22849340587854386,
|
|
"num_tokens": 55500825.0,
|
|
"step": 30160
|
|
},
|
|
{
|
|
"entropy": 5.435398578643799,
|
|
"epoch": 2.519629134647511,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043625654393147445,
|
|
"loss": 4.778,
|
|
"mean_token_accuracy": 0.22428959608078003,
|
|
"num_tokens": 55509907.0,
|
|
"step": 30165
|
|
},
|
|
{
|
|
"entropy": 5.5038148880004885,
|
|
"epoch": 2.520046775810224,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004362357813551608,
|
|
"loss": 4.888,
|
|
"mean_token_accuracy": 0.22180519998073578,
|
|
"num_tokens": 55519875.0,
|
|
"step": 30170
|
|
},
|
|
{
|
|
"entropy": 5.390713500976562,
|
|
"epoch": 2.5204644169729367,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043621501595622077,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.230639086663723,
|
|
"num_tokens": 55529438.0,
|
|
"step": 30175
|
|
},
|
|
{
|
|
"entropy": 5.48800630569458,
|
|
"epoch": 2.52088205813565,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004361942477350178,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.22584673017263412,
|
|
"num_tokens": 55537975.0,
|
|
"step": 30180
|
|
},
|
|
{
|
|
"entropy": 5.4963359355926515,
|
|
"epoch": 2.5212996992983627,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004361734766919156,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.21676354110240936,
|
|
"num_tokens": 55547217.0,
|
|
"step": 30185
|
|
},
|
|
{
|
|
"entropy": 5.490426874160766,
|
|
"epoch": 2.521717340461076,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004361527028272776,
|
|
"loss": 4.7658,
|
|
"mean_token_accuracy": 0.22897921055555343,
|
|
"num_tokens": 55556050.0,
|
|
"step": 30190
|
|
},
|
|
{
|
|
"entropy": 5.411978387832642,
|
|
"epoch": 2.522134981623789,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043613192614146753,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.22538394778966903,
|
|
"num_tokens": 55565393.0,
|
|
"step": 30195
|
|
},
|
|
{
|
|
"entropy": 5.3676855087280275,
|
|
"epoch": 2.5225526227865016,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004361111466348492,
|
|
"loss": 4.658,
|
|
"mean_token_accuracy": 0.23804374933242797,
|
|
"num_tokens": 55574060.0,
|
|
"step": 30200
|
|
},
|
|
{
|
|
"entropy": 5.435537672042846,
|
|
"epoch": 2.522970263949215,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043609036430778623,
|
|
"loss": 4.8221,
|
|
"mean_token_accuracy": 0.2211818739771843,
|
|
"num_tokens": 55583251.0,
|
|
"step": 30205
|
|
},
|
|
{
|
|
"entropy": 5.484495210647583,
|
|
"epoch": 2.5233879051119277,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004360695791606426,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.2219051569700241,
|
|
"num_tokens": 55593515.0,
|
|
"step": 30210
|
|
},
|
|
{
|
|
"entropy": 5.51997447013855,
|
|
"epoch": 2.523805546274641,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004360487911937821,
|
|
"loss": 4.8331,
|
|
"mean_token_accuracy": 0.23399408906698227,
|
|
"num_tokens": 55602359.0,
|
|
"step": 30215
|
|
},
|
|
{
|
|
"entropy": 5.408414649963379,
|
|
"epoch": 2.5242231874373537,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004360280004075687,
|
|
"loss": 4.7249,
|
|
"mean_token_accuracy": 0.23028683960437774,
|
|
"num_tokens": 55611679.0,
|
|
"step": 30220
|
|
},
|
|
{
|
|
"entropy": 5.3660670757293705,
|
|
"epoch": 2.5246408286000666,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004360072068023662,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.23473993837833404,
|
|
"num_tokens": 55621633.0,
|
|
"step": 30225
|
|
},
|
|
{
|
|
"entropy": 5.386089754104614,
|
|
"epoch": 2.52505846976278,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043598641037853885,
|
|
"loss": 4.7199,
|
|
"mean_token_accuracy": 0.2287565365433693,
|
|
"num_tokens": 55629821.0,
|
|
"step": 30230
|
|
},
|
|
{
|
|
"entropy": 5.300311040878296,
|
|
"epoch": 2.525476110925493,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043596561113645055,
|
|
"loss": 4.6012,
|
|
"mean_token_accuracy": 0.23344292789697646,
|
|
"num_tokens": 55638898.0,
|
|
"step": 30235
|
|
},
|
|
{
|
|
"entropy": 5.308493709564209,
|
|
"epoch": 2.525893752088206,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004359448090764655,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.22641401290893554,
|
|
"num_tokens": 55648309.0,
|
|
"step": 30240
|
|
},
|
|
{
|
|
"entropy": 5.481334495544433,
|
|
"epoch": 2.5263113932509187,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043592400419894785,
|
|
"loss": 4.8588,
|
|
"mean_token_accuracy": 0.22298458516597747,
|
|
"num_tokens": 55657889.0,
|
|
"step": 30245
|
|
},
|
|
{
|
|
"entropy": 5.4094525337219235,
|
|
"epoch": 2.526729034413632,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004359031965042617,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.22352273315191268,
|
|
"num_tokens": 55666743.0,
|
|
"step": 30250
|
|
},
|
|
{
|
|
"entropy": 5.379319334030152,
|
|
"epoch": 2.5271466755763448,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043588238599277156,
|
|
"loss": 4.6184,
|
|
"mean_token_accuracy": 0.23868315070867538,
|
|
"num_tokens": 55675821.0,
|
|
"step": 30255
|
|
},
|
|
{
|
|
"entropy": 5.476091766357422,
|
|
"epoch": 2.527564316739058,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043586157266484155,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.22239787727594376,
|
|
"num_tokens": 55685623.0,
|
|
"step": 30260
|
|
},
|
|
{
|
|
"entropy": 5.3692880153656,
|
|
"epoch": 2.527981957901771,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004358407565208361,
|
|
"loss": 4.6491,
|
|
"mean_token_accuracy": 0.2402884542942047,
|
|
"num_tokens": 55694017.0,
|
|
"step": 30265
|
|
},
|
|
{
|
|
"entropy": 5.374551391601562,
|
|
"epoch": 2.5283995990644836,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043581993756111956,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.2319558873772621,
|
|
"num_tokens": 55703685.0,
|
|
"step": 30270
|
|
},
|
|
{
|
|
"entropy": 5.363803672790527,
|
|
"epoch": 2.528817240227197,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004357991157860565,
|
|
"loss": 4.6582,
|
|
"mean_token_accuracy": 0.24210412353277205,
|
|
"num_tokens": 55711555.0,
|
|
"step": 30275
|
|
},
|
|
{
|
|
"entropy": 5.401615858078003,
|
|
"epoch": 2.5292348813899097,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004357782911960113,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.22852274626493455,
|
|
"num_tokens": 55720313.0,
|
|
"step": 30280
|
|
},
|
|
{
|
|
"entropy": 5.371994495391846,
|
|
"epoch": 2.529652522552623,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004357574637913486,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.23082095831632615,
|
|
"num_tokens": 55729092.0,
|
|
"step": 30285
|
|
},
|
|
{
|
|
"entropy": 5.382747650146484,
|
|
"epoch": 2.5300701637153358,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000435736633572433,
|
|
"loss": 4.6613,
|
|
"mean_token_accuracy": 0.23748982697725296,
|
|
"num_tokens": 55738843.0,
|
|
"step": 30290
|
|
},
|
|
{
|
|
"entropy": 5.429867792129516,
|
|
"epoch": 2.5304878048780486,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004357158005396291,
|
|
"loss": 4.8287,
|
|
"mean_token_accuracy": 0.23325731307268144,
|
|
"num_tokens": 55749070.0,
|
|
"step": 30295
|
|
},
|
|
{
|
|
"entropy": 5.369428730010986,
|
|
"epoch": 2.530905446040762,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043569496469330173,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.23181213140487672,
|
|
"num_tokens": 55758327.0,
|
|
"step": 30300
|
|
},
|
|
{
|
|
"entropy": 5.447902584075928,
|
|
"epoch": 2.5313230872034747,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004356741260338156,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.2250952109694481,
|
|
"num_tokens": 55767344.0,
|
|
"step": 30305
|
|
},
|
|
{
|
|
"entropy": 5.484054231643677,
|
|
"epoch": 2.531740728366188,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043565328456153534,
|
|
"loss": 4.8725,
|
|
"mean_token_accuracy": 0.22633780241012574,
|
|
"num_tokens": 55776905.0,
|
|
"step": 30310
|
|
},
|
|
{
|
|
"entropy": 5.457772731781006,
|
|
"epoch": 2.5321583695289007,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004356324402768261,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.22324300855398177,
|
|
"num_tokens": 55785442.0,
|
|
"step": 30315
|
|
},
|
|
{
|
|
"entropy": 5.3862358093261715,
|
|
"epoch": 2.5325760106916135,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004356115931800526,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.22733277082443237,
|
|
"num_tokens": 55794917.0,
|
|
"step": 30320
|
|
},
|
|
{
|
|
"entropy": 5.327774953842163,
|
|
"epoch": 2.532993651854327,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004355907432715798,
|
|
"loss": 4.6846,
|
|
"mean_token_accuracy": 0.23431101441383362,
|
|
"num_tokens": 55803249.0,
|
|
"step": 30325
|
|
},
|
|
{
|
|
"entropy": 5.3217696189880375,
|
|
"epoch": 2.5334112930170396,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043556989055177275,
|
|
"loss": 4.6609,
|
|
"mean_token_accuracy": 0.2303989127278328,
|
|
"num_tokens": 55811604.0,
|
|
"step": 30330
|
|
},
|
|
{
|
|
"entropy": 5.392407846450806,
|
|
"epoch": 2.533828934179753,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043554903502099644,
|
|
"loss": 4.6642,
|
|
"mean_token_accuracy": 0.23911133259534836,
|
|
"num_tokens": 55820818.0,
|
|
"step": 30335
|
|
},
|
|
{
|
|
"entropy": 5.409308624267578,
|
|
"epoch": 2.5342465753424657,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043552817667961616,
|
|
"loss": 4.7785,
|
|
"mean_token_accuracy": 0.23251317888498307,
|
|
"num_tokens": 55830171.0,
|
|
"step": 30340
|
|
},
|
|
{
|
|
"entropy": 5.321734762191772,
|
|
"epoch": 2.5346642165051785,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00043550731552799676,
|
|
"loss": 4.6495,
|
|
"mean_token_accuracy": 0.24005132615566255,
|
|
"num_tokens": 55838748.0,
|
|
"step": 30345
|
|
},
|
|
{
|
|
"entropy": 5.332164239883423,
|
|
"epoch": 2.5350818576678917,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043548645156650376,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.2374616026878357,
|
|
"num_tokens": 55847672.0,
|
|
"step": 30350
|
|
},
|
|
{
|
|
"entropy": 5.482332229614258,
|
|
"epoch": 2.535499498830605,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004354655847955021,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.2208193600177765,
|
|
"num_tokens": 55856822.0,
|
|
"step": 30355
|
|
},
|
|
{
|
|
"entropy": 5.455265378952026,
|
|
"epoch": 2.535917139993318,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043544471521535726,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.22483633160591127,
|
|
"num_tokens": 55867463.0,
|
|
"step": 30360
|
|
},
|
|
{
|
|
"entropy": 5.459638977050782,
|
|
"epoch": 2.5363347811560306,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043542384282643467,
|
|
"loss": 4.875,
|
|
"mean_token_accuracy": 0.21376618146896362,
|
|
"num_tokens": 55877108.0,
|
|
"step": 30365
|
|
},
|
|
{
|
|
"entropy": 5.367516756057739,
|
|
"epoch": 2.536752422318744,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004354029676290995,
|
|
"loss": 4.6551,
|
|
"mean_token_accuracy": 0.2329222798347473,
|
|
"num_tokens": 55886504.0,
|
|
"step": 30370
|
|
},
|
|
{
|
|
"entropy": 5.435014629364014,
|
|
"epoch": 2.5371700634814567,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004353820896237173,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.2327360287308693,
|
|
"num_tokens": 55895296.0,
|
|
"step": 30375
|
|
},
|
|
{
|
|
"entropy": 5.4158367156982425,
|
|
"epoch": 2.53758770464417,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004353612088106536,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.2262675106525421,
|
|
"num_tokens": 55904151.0,
|
|
"step": 30380
|
|
},
|
|
{
|
|
"entropy": 5.381781673431396,
|
|
"epoch": 2.5380053458068828,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043534032519027395,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.23955601900815965,
|
|
"num_tokens": 55912667.0,
|
|
"step": 30385
|
|
},
|
|
{
|
|
"entropy": 5.455927848815918,
|
|
"epoch": 2.5384229869695956,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004353194387629438,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.22969920039176941,
|
|
"num_tokens": 55922647.0,
|
|
"step": 30390
|
|
},
|
|
{
|
|
"entropy": 5.357419681549072,
|
|
"epoch": 2.538840628132309,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000435298549529029,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.23214212507009507,
|
|
"num_tokens": 55932040.0,
|
|
"step": 30395
|
|
},
|
|
{
|
|
"entropy": 5.479633331298828,
|
|
"epoch": 2.5392582692950216,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043527765748889506,
|
|
"loss": 4.8749,
|
|
"mean_token_accuracy": 0.22384901195764542,
|
|
"num_tokens": 55940882.0,
|
|
"step": 30400
|
|
},
|
|
{
|
|
"entropy": 5.340934991836548,
|
|
"epoch": 2.539675910457735,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004352567626429079,
|
|
"loss": 4.64,
|
|
"mean_token_accuracy": 0.23400330394506455,
|
|
"num_tokens": 55949522.0,
|
|
"step": 30405
|
|
},
|
|
{
|
|
"entropy": 5.389507579803467,
|
|
"epoch": 2.5400935516204477,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004352358649914331,
|
|
"loss": 4.6741,
|
|
"mean_token_accuracy": 0.2342064008116722,
|
|
"num_tokens": 55957529.0,
|
|
"step": 30410
|
|
},
|
|
{
|
|
"entropy": 5.4505198955535885,
|
|
"epoch": 2.5405111927831605,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043521496453483667,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.2314548060297966,
|
|
"num_tokens": 55967400.0,
|
|
"step": 30415
|
|
},
|
|
{
|
|
"entropy": 5.472900485992431,
|
|
"epoch": 2.5409288339458738,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043519406127348435,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.23421982526779175,
|
|
"num_tokens": 55976262.0,
|
|
"step": 30420
|
|
},
|
|
{
|
|
"entropy": 5.37012734413147,
|
|
"epoch": 2.5413464751085866,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004351731552077423,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.22664946019649507,
|
|
"num_tokens": 55985751.0,
|
|
"step": 30425
|
|
},
|
|
{
|
|
"entropy": 5.383597373962402,
|
|
"epoch": 2.5417641162713,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004351522463379763,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.23026393800973893,
|
|
"num_tokens": 55995365.0,
|
|
"step": 30430
|
|
},
|
|
{
|
|
"entropy": 5.396692276000977,
|
|
"epoch": 2.5421817574340126,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004351313346645525,
|
|
"loss": 4.7382,
|
|
"mean_token_accuracy": 0.22682445794343947,
|
|
"num_tokens": 56004271.0,
|
|
"step": 30435
|
|
},
|
|
{
|
|
"entropy": 5.416529989242553,
|
|
"epoch": 2.5425993985967255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004351104201878368,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.23112488389015198,
|
|
"num_tokens": 56013326.0,
|
|
"step": 30440
|
|
},
|
|
{
|
|
"entropy": 5.397369527816773,
|
|
"epoch": 2.5430170397594387,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004350895029081956,
|
|
"loss": 4.722,
|
|
"mean_token_accuracy": 0.23196004182100297,
|
|
"num_tokens": 56021664.0,
|
|
"step": 30445
|
|
},
|
|
{
|
|
"entropy": 5.406113719940185,
|
|
"epoch": 2.5434346809221515,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043506858282599487,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.23141489177942276,
|
|
"num_tokens": 56030030.0,
|
|
"step": 30450
|
|
},
|
|
{
|
|
"entropy": 5.370901346206665,
|
|
"epoch": 2.543852322084865,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000435047659941601,
|
|
"loss": 4.7406,
|
|
"mean_token_accuracy": 0.23100733608007432,
|
|
"num_tokens": 56039939.0,
|
|
"step": 30455
|
|
},
|
|
{
|
|
"entropy": 5.379622316360473,
|
|
"epoch": 2.5442699632475776,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043502673425538016,
|
|
"loss": 4.6996,
|
|
"mean_token_accuracy": 0.23625823408365249,
|
|
"num_tokens": 56048534.0,
|
|
"step": 30460
|
|
},
|
|
{
|
|
"entropy": 5.389765644073487,
|
|
"epoch": 2.5446876044102904,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043500580576769874,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.23606862276792526,
|
|
"num_tokens": 56057242.0,
|
|
"step": 30465
|
|
},
|
|
{
|
|
"entropy": 5.417363977432251,
|
|
"epoch": 2.5451052455730037,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000434984874478923,
|
|
"loss": 4.6963,
|
|
"mean_token_accuracy": 0.22844147682189941,
|
|
"num_tokens": 56065615.0,
|
|
"step": 30470
|
|
},
|
|
{
|
|
"entropy": 5.367451524734497,
|
|
"epoch": 2.545522886735717,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043496394038941956,
|
|
"loss": 4.6539,
|
|
"mean_token_accuracy": 0.23719373792409898,
|
|
"num_tokens": 56074351.0,
|
|
"step": 30475
|
|
},
|
|
{
|
|
"entropy": 5.323174285888672,
|
|
"epoch": 2.5459405278984297,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043494300349955473,
|
|
"loss": 4.6829,
|
|
"mean_token_accuracy": 0.2309495523571968,
|
|
"num_tokens": 56083915.0,
|
|
"step": 30480
|
|
},
|
|
{
|
|
"entropy": 5.441232204437256,
|
|
"epoch": 2.5463581690611425,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004349220638096952,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.21846399158239366,
|
|
"num_tokens": 56093424.0,
|
|
"step": 30485
|
|
},
|
|
{
|
|
"entropy": 5.474236059188843,
|
|
"epoch": 2.546775810223856,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004349011213202073,
|
|
"loss": 4.7822,
|
|
"mean_token_accuracy": 0.22910756766796112,
|
|
"num_tokens": 56103798.0,
|
|
"step": 30490
|
|
},
|
|
{
|
|
"entropy": 5.473706817626953,
|
|
"epoch": 2.5471934513865686,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043488017603145787,
|
|
"loss": 4.7941,
|
|
"mean_token_accuracy": 0.2240170955657959,
|
|
"num_tokens": 56113841.0,
|
|
"step": 30495
|
|
},
|
|
{
|
|
"entropy": 5.469012928009033,
|
|
"epoch": 2.547611092549282,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00043485922794381357,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.21874167770147324,
|
|
"num_tokens": 56123294.0,
|
|
"step": 30500
|
|
},
|
|
{
|
|
"entropy": 5.4069061279296875,
|
|
"epoch": 2.5480287337119947,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043483827705764094,
|
|
"loss": 4.678,
|
|
"mean_token_accuracy": 0.23785399794578552,
|
|
"num_tokens": 56133041.0,
|
|
"step": 30505
|
|
},
|
|
{
|
|
"entropy": 5.387673473358154,
|
|
"epoch": 2.5484463748747075,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043481732337330697,
|
|
"loss": 4.801,
|
|
"mean_token_accuracy": 0.22776921838521957,
|
|
"num_tokens": 56142796.0,
|
|
"step": 30510
|
|
},
|
|
{
|
|
"entropy": 5.411862897872925,
|
|
"epoch": 2.5488640160374207,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043479636689117834,
|
|
"loss": 4.7832,
|
|
"mean_token_accuracy": 0.22640788853168486,
|
|
"num_tokens": 56152912.0,
|
|
"step": 30515
|
|
},
|
|
{
|
|
"entropy": 5.4353540420532225,
|
|
"epoch": 2.5492816572001336,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043477540761162196,
|
|
"loss": 4.7621,
|
|
"mean_token_accuracy": 0.22860835492610931,
|
|
"num_tokens": 56161860.0,
|
|
"step": 30520
|
|
},
|
|
{
|
|
"entropy": 5.332320022583008,
|
|
"epoch": 2.549699298362847,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004347544455350047,
|
|
"loss": 4.7779,
|
|
"mean_token_accuracy": 0.22967534363269806,
|
|
"num_tokens": 56171525.0,
|
|
"step": 30525
|
|
},
|
|
{
|
|
"entropy": 5.403562355041504,
|
|
"epoch": 2.5501169395255596,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043473348066169363,
|
|
"loss": 4.7234,
|
|
"mean_token_accuracy": 0.2315102845430374,
|
|
"num_tokens": 56181219.0,
|
|
"step": 30530
|
|
},
|
|
{
|
|
"entropy": 5.399260377883911,
|
|
"epoch": 2.5505345806882724,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004347125129920557,
|
|
"loss": 4.6671,
|
|
"mean_token_accuracy": 0.239765502512455,
|
|
"num_tokens": 56189983.0,
|
|
"step": 30535
|
|
},
|
|
{
|
|
"entropy": 5.432582092285156,
|
|
"epoch": 2.5509522218509857,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004346915425264581,
|
|
"loss": 4.7254,
|
|
"mean_token_accuracy": 0.23195880204439162,
|
|
"num_tokens": 56199150.0,
|
|
"step": 30540
|
|
},
|
|
{
|
|
"entropy": 5.398118734359741,
|
|
"epoch": 2.5513698630136985,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004346705692652677,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.22590308040380477,
|
|
"num_tokens": 56208550.0,
|
|
"step": 30545
|
|
},
|
|
{
|
|
"entropy": 5.291116333007812,
|
|
"epoch": 2.5517875041764118,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004346495932088518,
|
|
"loss": 4.6054,
|
|
"mean_token_accuracy": 0.2393333375453949,
|
|
"num_tokens": 56217487.0,
|
|
"step": 30550
|
|
},
|
|
{
|
|
"entropy": 5.379245233535767,
|
|
"epoch": 2.5522051453391246,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004346286143575776,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.22713688313961028,
|
|
"num_tokens": 56226969.0,
|
|
"step": 30555
|
|
},
|
|
{
|
|
"entropy": 5.4839764595031735,
|
|
"epoch": 2.5526227865018374,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043460763271181235,
|
|
"loss": 4.871,
|
|
"mean_token_accuracy": 0.2150127872824669,
|
|
"num_tokens": 56236223.0,
|
|
"step": 30560
|
|
},
|
|
{
|
|
"entropy": 5.370949697494507,
|
|
"epoch": 2.5530404276645506,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043458664827192333,
|
|
"loss": 4.6523,
|
|
"mean_token_accuracy": 0.24224052280187608,
|
|
"num_tokens": 56246319.0,
|
|
"step": 30565
|
|
},
|
|
{
|
|
"entropy": 5.453644466400147,
|
|
"epoch": 2.5534580688272634,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004345656610382781,
|
|
"loss": 4.8706,
|
|
"mean_token_accuracy": 0.21890200227499007,
|
|
"num_tokens": 56256270.0,
|
|
"step": 30570
|
|
},
|
|
{
|
|
"entropy": 5.430059003829956,
|
|
"epoch": 2.5538757099899767,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004345446710112438,
|
|
"loss": 4.7661,
|
|
"mean_token_accuracy": 0.22310336232185363,
|
|
"num_tokens": 56265454.0,
|
|
"step": 30575
|
|
},
|
|
{
|
|
"entropy": 5.409324789047242,
|
|
"epoch": 2.5542933511526895,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043452367819118797,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.23158619701862335,
|
|
"num_tokens": 56274986.0,
|
|
"step": 30580
|
|
},
|
|
{
|
|
"entropy": 5.39954195022583,
|
|
"epoch": 2.5547109923154023,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043450268257847814,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.2285177081823349,
|
|
"num_tokens": 56284608.0,
|
|
"step": 30585
|
|
},
|
|
{
|
|
"entropy": 5.3773369789123535,
|
|
"epoch": 2.5551286334781156,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004344816841734819,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.24019262492656707,
|
|
"num_tokens": 56292508.0,
|
|
"step": 30590
|
|
},
|
|
{
|
|
"entropy": 5.40998387336731,
|
|
"epoch": 2.555546274640829,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004344606829765668,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.2307053789496422,
|
|
"num_tokens": 56302338.0,
|
|
"step": 30595
|
|
},
|
|
{
|
|
"entropy": 5.377691841125488,
|
|
"epoch": 2.5559639158035417,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004344396789881005,
|
|
"loss": 4.7394,
|
|
"mean_token_accuracy": 0.2275781363248825,
|
|
"num_tokens": 56311147.0,
|
|
"step": 30600
|
|
},
|
|
{
|
|
"entropy": 5.372974967956543,
|
|
"epoch": 2.5563815569662545,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004344186722084507,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.23183318674564363,
|
|
"num_tokens": 56320614.0,
|
|
"step": 30605
|
|
},
|
|
{
|
|
"entropy": 5.433148956298828,
|
|
"epoch": 2.5567991981289677,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043439766263798506,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.22795265913009644,
|
|
"num_tokens": 56330411.0,
|
|
"step": 30610
|
|
},
|
|
{
|
|
"entropy": 5.448651075363159,
|
|
"epoch": 2.5572168392916805,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043437665027707155,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.22824213057756423,
|
|
"num_tokens": 56339644.0,
|
|
"step": 30615
|
|
},
|
|
{
|
|
"entropy": 5.428284788131714,
|
|
"epoch": 2.557634480454394,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043435563512607796,
|
|
"loss": 4.7417,
|
|
"mean_token_accuracy": 0.2250593274831772,
|
|
"num_tokens": 56348533.0,
|
|
"step": 30620
|
|
},
|
|
{
|
|
"entropy": 5.472752475738526,
|
|
"epoch": 2.5580521216171066,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004343346171853722,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.22649480402469635,
|
|
"num_tokens": 56358533.0,
|
|
"step": 30625
|
|
},
|
|
{
|
|
"entropy": 5.385382843017578,
|
|
"epoch": 2.5584697627798194,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004343135964553221,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.22710342854261398,
|
|
"num_tokens": 56367739.0,
|
|
"step": 30630
|
|
},
|
|
{
|
|
"entropy": 5.409988784790039,
|
|
"epoch": 2.5588874039425327,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004342925729362957,
|
|
"loss": 4.6918,
|
|
"mean_token_accuracy": 0.23177322894334793,
|
|
"num_tokens": 56375315.0,
|
|
"step": 30635
|
|
},
|
|
{
|
|
"entropy": 5.386263847351074,
|
|
"epoch": 2.5593050451052455,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004342715466286611,
|
|
"loss": 4.7083,
|
|
"mean_token_accuracy": 0.24445956200361252,
|
|
"num_tokens": 56384226.0,
|
|
"step": 30640
|
|
},
|
|
{
|
|
"entropy": 5.4245867252349855,
|
|
"epoch": 2.5597226862679587,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043425051753278633,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.23105483800172805,
|
|
"num_tokens": 56393249.0,
|
|
"step": 30645
|
|
},
|
|
{
|
|
"entropy": 5.459629392623901,
|
|
"epoch": 2.5601403274306715,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004342294856490397,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.22317050099372865,
|
|
"num_tokens": 56402701.0,
|
|
"step": 30650
|
|
},
|
|
{
|
|
"entropy": 5.406945085525512,
|
|
"epoch": 2.5605579685933844,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043420845097778913,
|
|
"loss": 4.713,
|
|
"mean_token_accuracy": 0.2326946437358856,
|
|
"num_tokens": 56411927.0,
|
|
"step": 30655
|
|
},
|
|
{
|
|
"entropy": 5.487747764587402,
|
|
"epoch": 2.5609756097560976,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000434187413519403,
|
|
"loss": 4.8974,
|
|
"mean_token_accuracy": 0.22355912923812865,
|
|
"num_tokens": 56421852.0,
|
|
"step": 30660
|
|
},
|
|
{
|
|
"entropy": 5.446980237960815,
|
|
"epoch": 2.5613932509188104,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043416637327424955,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.2306005984544754,
|
|
"num_tokens": 56431428.0,
|
|
"step": 30665
|
|
},
|
|
{
|
|
"entropy": 5.383371257781983,
|
|
"epoch": 2.5618108920815237,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004341453302426972,
|
|
"loss": 4.6539,
|
|
"mean_token_accuracy": 0.24010222405195236,
|
|
"num_tokens": 56440339.0,
|
|
"step": 30670
|
|
},
|
|
{
|
|
"entropy": 5.421497869491577,
|
|
"epoch": 2.5622285332442365,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004341242844251143,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.22967879027128218,
|
|
"num_tokens": 56450407.0,
|
|
"step": 30675
|
|
},
|
|
{
|
|
"entropy": 5.401152801513672,
|
|
"epoch": 2.5626461744069493,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004341032358218692,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.22959268987178802,
|
|
"num_tokens": 56460357.0,
|
|
"step": 30680
|
|
},
|
|
{
|
|
"entropy": 5.4920325756073,
|
|
"epoch": 2.5630638155696626,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043408218443333056,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.22652546614408492,
|
|
"num_tokens": 56469433.0,
|
|
"step": 30685
|
|
},
|
|
{
|
|
"entropy": 5.357493686676025,
|
|
"epoch": 2.563481456732376,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043406113025986666,
|
|
"loss": 4.6814,
|
|
"mean_token_accuracy": 0.23469629734754563,
|
|
"num_tokens": 56478608.0,
|
|
"step": 30690
|
|
},
|
|
{
|
|
"entropy": 5.312928295135498,
|
|
"epoch": 2.5638990978950886,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004340400733018463,
|
|
"loss": 4.6785,
|
|
"mean_token_accuracy": 0.23347722738981247,
|
|
"num_tokens": 56487904.0,
|
|
"step": 30695
|
|
},
|
|
{
|
|
"entropy": 5.461118602752686,
|
|
"epoch": 2.5643167390578014,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000434019013559638,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.2250363662838936,
|
|
"num_tokens": 56498126.0,
|
|
"step": 30700
|
|
},
|
|
{
|
|
"entropy": 5.378251695632935,
|
|
"epoch": 2.5647343802205147,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043399795103361046,
|
|
"loss": 4.6591,
|
|
"mean_token_accuracy": 0.23808930814266205,
|
|
"num_tokens": 56506400.0,
|
|
"step": 30705
|
|
},
|
|
{
|
|
"entropy": 5.4153587341308596,
|
|
"epoch": 2.5651520213832275,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043397688572413236,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.22291564345359802,
|
|
"num_tokens": 56516458.0,
|
|
"step": 30710
|
|
},
|
|
{
|
|
"entropy": 5.285874557495117,
|
|
"epoch": 2.5655696625459408,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043395581763157256,
|
|
"loss": 4.6537,
|
|
"mean_token_accuracy": 0.23763910830020904,
|
|
"num_tokens": 56524586.0,
|
|
"step": 30715
|
|
},
|
|
{
|
|
"entropy": 5.395794296264649,
|
|
"epoch": 2.5659873037086536,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043393474675629983,
|
|
"loss": 4.7291,
|
|
"mean_token_accuracy": 0.22927890717983246,
|
|
"num_tokens": 56533797.0,
|
|
"step": 30720
|
|
},
|
|
{
|
|
"entropy": 5.41659984588623,
|
|
"epoch": 2.5664049448713664,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043391367309868304,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.22865692377090455,
|
|
"num_tokens": 56543976.0,
|
|
"step": 30725
|
|
},
|
|
{
|
|
"entropy": 5.455238389968872,
|
|
"epoch": 2.5668225860340796,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043389259665909107,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.22445666342973708,
|
|
"num_tokens": 56553421.0,
|
|
"step": 30730
|
|
},
|
|
{
|
|
"entropy": 5.433267831802368,
|
|
"epoch": 2.5672402271967925,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000433871517437893,
|
|
"loss": 4.8447,
|
|
"mean_token_accuracy": 0.22022606581449508,
|
|
"num_tokens": 56562780.0,
|
|
"step": 30735
|
|
},
|
|
{
|
|
"entropy": 5.37127366065979,
|
|
"epoch": 2.5676578683595057,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043385043543545777,
|
|
"loss": 4.6763,
|
|
"mean_token_accuracy": 0.2339548721909523,
|
|
"num_tokens": 56571186.0,
|
|
"step": 30740
|
|
},
|
|
{
|
|
"entropy": 5.389149570465088,
|
|
"epoch": 2.5680755095222185,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00043382935065215444,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.23387662321329117,
|
|
"num_tokens": 56579282.0,
|
|
"step": 30745
|
|
},
|
|
{
|
|
"entropy": 5.4164787292480465,
|
|
"epoch": 2.5684931506849313,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043380826308835226,
|
|
"loss": 4.7387,
|
|
"mean_token_accuracy": 0.22583054304122924,
|
|
"num_tokens": 56587962.0,
|
|
"step": 30750
|
|
},
|
|
{
|
|
"entropy": 5.435262537002563,
|
|
"epoch": 2.5689107918476446,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043378717274442015,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.22446165829896927,
|
|
"num_tokens": 56598075.0,
|
|
"step": 30755
|
|
},
|
|
{
|
|
"entropy": 5.374977970123291,
|
|
"epoch": 2.5693284330103574,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043376607962072747,
|
|
"loss": 4.7397,
|
|
"mean_token_accuracy": 0.22783450186252593,
|
|
"num_tokens": 56607363.0,
|
|
"step": 30760
|
|
},
|
|
{
|
|
"entropy": 5.403298330307007,
|
|
"epoch": 2.5697460741730707,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043374498371764344,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.23343340456485748,
|
|
"num_tokens": 56616041.0,
|
|
"step": 30765
|
|
},
|
|
{
|
|
"entropy": 5.476054573059082,
|
|
"epoch": 2.5701637153357835,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043372388503553743,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.22229037433862686,
|
|
"num_tokens": 56625901.0,
|
|
"step": 30770
|
|
},
|
|
{
|
|
"entropy": 5.376545858383179,
|
|
"epoch": 2.5705813564984963,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043370278357477874,
|
|
"loss": 4.7333,
|
|
"mean_token_accuracy": 0.2268967807292938,
|
|
"num_tokens": 56636255.0,
|
|
"step": 30775
|
|
},
|
|
{
|
|
"entropy": 5.314780330657959,
|
|
"epoch": 2.5709989976612095,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043368167933573675,
|
|
"loss": 4.7085,
|
|
"mean_token_accuracy": 0.23182590454816818,
|
|
"num_tokens": 56645045.0,
|
|
"step": 30780
|
|
},
|
|
{
|
|
"entropy": 5.412514352798462,
|
|
"epoch": 2.5714166388239224,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000433660572318781,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.2303946301341057,
|
|
"num_tokens": 56653063.0,
|
|
"step": 30785
|
|
},
|
|
{
|
|
"entropy": 5.364907741546631,
|
|
"epoch": 2.5718342799866356,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000433639462524281,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.22809321731328963,
|
|
"num_tokens": 56663060.0,
|
|
"step": 30790
|
|
},
|
|
{
|
|
"entropy": 5.361563491821289,
|
|
"epoch": 2.5722519211493484,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004336183499526062,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.23318155258893966,
|
|
"num_tokens": 56672134.0,
|
|
"step": 30795
|
|
},
|
|
{
|
|
"entropy": 5.393728160858155,
|
|
"epoch": 2.5726695623120612,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043359723460412625,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.229044871032238,
|
|
"num_tokens": 56681182.0,
|
|
"step": 30800
|
|
},
|
|
{
|
|
"entropy": 5.346535158157349,
|
|
"epoch": 2.5730872034747745,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004335761164792108,
|
|
"loss": 4.6342,
|
|
"mean_token_accuracy": 0.2366880252957344,
|
|
"num_tokens": 56689375.0,
|
|
"step": 30805
|
|
},
|
|
{
|
|
"entropy": 5.376699209213257,
|
|
"epoch": 2.5735048446374877,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004335549955782296,
|
|
"loss": 4.8113,
|
|
"mean_token_accuracy": 0.22472745925188065,
|
|
"num_tokens": 56699190.0,
|
|
"step": 30810
|
|
},
|
|
{
|
|
"entropy": 5.409239006042481,
|
|
"epoch": 2.5739224858002006,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004335338719015523,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.23417028933763503,
|
|
"num_tokens": 56708332.0,
|
|
"step": 30815
|
|
},
|
|
{
|
|
"entropy": 5.5131385803222654,
|
|
"epoch": 2.5743401269629134,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004335127454495488,
|
|
"loss": 4.8015,
|
|
"mean_token_accuracy": 0.2291201114654541,
|
|
"num_tokens": 56718163.0,
|
|
"step": 30820
|
|
},
|
|
{
|
|
"entropy": 5.444262981414795,
|
|
"epoch": 2.5747577681256266,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004334916162225889,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.2309918522834778,
|
|
"num_tokens": 56727976.0,
|
|
"step": 30825
|
|
},
|
|
{
|
|
"entropy": 5.4447657585144045,
|
|
"epoch": 2.5751754092883394,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004334704842210424,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.22502074986696244,
|
|
"num_tokens": 56738161.0,
|
|
"step": 30830
|
|
},
|
|
{
|
|
"entropy": 5.4078371047973635,
|
|
"epoch": 2.5755930504510527,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004334493494452794,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.22574800997972488,
|
|
"num_tokens": 56747672.0,
|
|
"step": 30835
|
|
},
|
|
{
|
|
"entropy": 5.348168754577637,
|
|
"epoch": 2.5760106916137655,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004334282118956697,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.2414929285645485,
|
|
"num_tokens": 56756923.0,
|
|
"step": 30840
|
|
},
|
|
{
|
|
"entropy": 5.461438703536987,
|
|
"epoch": 2.5764283327764783,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004334070715725836,
|
|
"loss": 4.7789,
|
|
"mean_token_accuracy": 0.22331375181674956,
|
|
"num_tokens": 56766030.0,
|
|
"step": 30845
|
|
},
|
|
{
|
|
"entropy": 5.370172357559204,
|
|
"epoch": 2.5768459739391916,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043338592847639093,
|
|
"loss": 4.6912,
|
|
"mean_token_accuracy": 0.22501573711633682,
|
|
"num_tokens": 56775208.0,
|
|
"step": 30850
|
|
},
|
|
{
|
|
"entropy": 5.501514196395874,
|
|
"epoch": 2.5772636151019044,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004333647826074619,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.2274039402604103,
|
|
"num_tokens": 56784221.0,
|
|
"step": 30855
|
|
},
|
|
{
|
|
"entropy": 5.383337116241455,
|
|
"epoch": 2.5776812562646176,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004333436339661668,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.23272556513547898,
|
|
"num_tokens": 56792089.0,
|
|
"step": 30860
|
|
},
|
|
{
|
|
"entropy": 5.371153688430786,
|
|
"epoch": 2.5780988974273304,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043332248255287584,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.22732594311237336,
|
|
"num_tokens": 56802346.0,
|
|
"step": 30865
|
|
},
|
|
{
|
|
"entropy": 5.494209718704224,
|
|
"epoch": 2.5785165385900433,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043330132836795916,
|
|
"loss": 4.7262,
|
|
"mean_token_accuracy": 0.231801600754261,
|
|
"num_tokens": 56811326.0,
|
|
"step": 30870
|
|
},
|
|
{
|
|
"entropy": 5.374024534225464,
|
|
"epoch": 2.5789341797527565,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043328017141178724,
|
|
"loss": 4.6013,
|
|
"mean_token_accuracy": 0.24331562221050262,
|
|
"num_tokens": 56820382.0,
|
|
"step": 30875
|
|
},
|
|
{
|
|
"entropy": 5.351992988586426,
|
|
"epoch": 2.5793518209154693,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043325901168473035,
|
|
"loss": 4.6941,
|
|
"mean_token_accuracy": 0.2286241129040718,
|
|
"num_tokens": 56830678.0,
|
|
"step": 30880
|
|
},
|
|
{
|
|
"entropy": 5.371480417251587,
|
|
"epoch": 2.5797694620781826,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043323784918715896,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.23304911255836486,
|
|
"num_tokens": 56840457.0,
|
|
"step": 30885
|
|
},
|
|
{
|
|
"entropy": 5.38492784500122,
|
|
"epoch": 2.5801871032408954,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043321668391944364,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.22860937267541886,
|
|
"num_tokens": 56849360.0,
|
|
"step": 30890
|
|
},
|
|
{
|
|
"entropy": 5.505064535140991,
|
|
"epoch": 2.580604744403608,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004331955158819547,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.21708064824342727,
|
|
"num_tokens": 56858514.0,
|
|
"step": 30895
|
|
},
|
|
{
|
|
"entropy": 5.462736940383911,
|
|
"epoch": 2.5810223855663215,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043317434507506285,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.230266971886158,
|
|
"num_tokens": 56867800.0,
|
|
"step": 30900
|
|
},
|
|
{
|
|
"entropy": 5.423477125167847,
|
|
"epoch": 2.5814400267290343,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043315317149913876,
|
|
"loss": 4.7022,
|
|
"mean_token_accuracy": 0.22442665994167327,
|
|
"num_tokens": 56876777.0,
|
|
"step": 30905
|
|
},
|
|
{
|
|
"entropy": 5.455527019500733,
|
|
"epoch": 2.5818576678917475,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000433131995154553,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.2287987232208252,
|
|
"num_tokens": 56885937.0,
|
|
"step": 30910
|
|
},
|
|
{
|
|
"entropy": 5.445904397964478,
|
|
"epoch": 2.5822753090544603,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004331108160416764,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.22321175485849382,
|
|
"num_tokens": 56895340.0,
|
|
"step": 30915
|
|
},
|
|
{
|
|
"entropy": 5.382023048400879,
|
|
"epoch": 2.582692950217173,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004330896341608795,
|
|
"loss": 4.7104,
|
|
"mean_token_accuracy": 0.23490604907274246,
|
|
"num_tokens": 56903975.0,
|
|
"step": 30920
|
|
},
|
|
{
|
|
"entropy": 5.414637660980224,
|
|
"epoch": 2.5831105913798864,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00043306844951253336,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.22694577425718307,
|
|
"num_tokens": 56913396.0,
|
|
"step": 30925
|
|
},
|
|
{
|
|
"entropy": 5.426852416992188,
|
|
"epoch": 2.5835282325425997,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043304726209700874,
|
|
"loss": 4.7464,
|
|
"mean_token_accuracy": 0.2339709669351578,
|
|
"num_tokens": 56923161.0,
|
|
"step": 30930
|
|
},
|
|
{
|
|
"entropy": 5.411038446426391,
|
|
"epoch": 2.5839458737053125,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004330260719146765,
|
|
"loss": 4.7357,
|
|
"mean_token_accuracy": 0.23094506561756134,
|
|
"num_tokens": 56932449.0,
|
|
"step": 30935
|
|
},
|
|
{
|
|
"entropy": 5.374940729141235,
|
|
"epoch": 2.5843635148680253,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004330048789659077,
|
|
"loss": 4.7649,
|
|
"mean_token_accuracy": 0.22788375616073608,
|
|
"num_tokens": 56941146.0,
|
|
"step": 30940
|
|
},
|
|
{
|
|
"entropy": 5.331237173080444,
|
|
"epoch": 2.5847811560307385,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043298368325107335,
|
|
"loss": 4.6305,
|
|
"mean_token_accuracy": 0.23965259343385698,
|
|
"num_tokens": 56949909.0,
|
|
"step": 30945
|
|
},
|
|
{
|
|
"entropy": 5.40610556602478,
|
|
"epoch": 2.5851987971934514,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004329624847705444,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.23139673918485643,
|
|
"num_tokens": 56960291.0,
|
|
"step": 30950
|
|
},
|
|
{
|
|
"entropy": 5.441065502166748,
|
|
"epoch": 2.5856164383561646,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043294128352469195,
|
|
"loss": 4.8569,
|
|
"mean_token_accuracy": 0.2171184778213501,
|
|
"num_tokens": 56970490.0,
|
|
"step": 30955
|
|
},
|
|
{
|
|
"entropy": 5.42565131187439,
|
|
"epoch": 2.5860340795188774,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043292007951388733,
|
|
"loss": 4.7991,
|
|
"mean_token_accuracy": 0.22697241008281707,
|
|
"num_tokens": 56979763.0,
|
|
"step": 30960
|
|
},
|
|
{
|
|
"entropy": 5.435798501968383,
|
|
"epoch": 2.5864517206815902,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043289887273850167,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.22680962979793548,
|
|
"num_tokens": 56989932.0,
|
|
"step": 30965
|
|
},
|
|
{
|
|
"entropy": 5.473071908950805,
|
|
"epoch": 2.5868693618443035,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000432877663198906,
|
|
"loss": 4.7302,
|
|
"mean_token_accuracy": 0.2299581378698349,
|
|
"num_tokens": 56999263.0,
|
|
"step": 30970
|
|
},
|
|
{
|
|
"entropy": 5.43573784828186,
|
|
"epoch": 2.5872870030070163,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004328564508954719,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.22391457706689835,
|
|
"num_tokens": 57009243.0,
|
|
"step": 30975
|
|
},
|
|
{
|
|
"entropy": 5.3002049922943115,
|
|
"epoch": 2.5877046441697296,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004328352358285706,
|
|
"loss": 4.6279,
|
|
"mean_token_accuracy": 0.23701755702495575,
|
|
"num_tokens": 57018154.0,
|
|
"step": 30980
|
|
},
|
|
{
|
|
"entropy": 5.528954219818115,
|
|
"epoch": 2.5881222853324424,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043281401799857356,
|
|
"loss": 4.8306,
|
|
"mean_token_accuracy": 0.22165221422910691,
|
|
"num_tokens": 57027237.0,
|
|
"step": 30985
|
|
},
|
|
{
|
|
"entropy": 5.449864387512207,
|
|
"epoch": 2.588539926495155,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004327927974058521,
|
|
"loss": 4.699,
|
|
"mean_token_accuracy": 0.23248489052057267,
|
|
"num_tokens": 57036426.0,
|
|
"step": 30990
|
|
},
|
|
{
|
|
"entropy": 5.378016471862793,
|
|
"epoch": 2.5889575676578684,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004327715740507778,
|
|
"loss": 4.7974,
|
|
"mean_token_accuracy": 0.23240807950496672,
|
|
"num_tokens": 57044233.0,
|
|
"step": 30995
|
|
},
|
|
{
|
|
"entropy": 5.3407878398895265,
|
|
"epoch": 2.5893752088205813,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004327503479337222,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.21159770488739013,
|
|
"num_tokens": 57054222.0,
|
|
"step": 31000
|
|
},
|
|
{
|
|
"entropy": 5.485877847671508,
|
|
"epoch": 2.5897928499832945,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043272911905505696,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.22745629847049714,
|
|
"num_tokens": 57062990.0,
|
|
"step": 31005
|
|
},
|
|
{
|
|
"entropy": 5.411457777023315,
|
|
"epoch": 2.5902104911460073,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004327078874151535,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.22275907099246978,
|
|
"num_tokens": 57071769.0,
|
|
"step": 31010
|
|
},
|
|
{
|
|
"entropy": 5.466904783248902,
|
|
"epoch": 2.59062813230872,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004326866530143838,
|
|
"loss": 4.7559,
|
|
"mean_token_accuracy": 0.2312343642115593,
|
|
"num_tokens": 57080171.0,
|
|
"step": 31015
|
|
},
|
|
{
|
|
"entropy": 5.474861717224121,
|
|
"epoch": 2.5910457734714334,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043266541585311924,
|
|
"loss": 4.7573,
|
|
"mean_token_accuracy": 0.23149360567331315,
|
|
"num_tokens": 57089241.0,
|
|
"step": 31020
|
|
},
|
|
{
|
|
"entropy": 5.50553879737854,
|
|
"epoch": 2.591463414634146,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004326441759317319,
|
|
"loss": 4.7961,
|
|
"mean_token_accuracy": 0.2266148254275322,
|
|
"num_tokens": 57098037.0,
|
|
"step": 31025
|
|
},
|
|
{
|
|
"entropy": 5.435415172576905,
|
|
"epoch": 2.5918810557968595,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004326229332505934,
|
|
"loss": 4.7724,
|
|
"mean_token_accuracy": 0.2202361211180687,
|
|
"num_tokens": 57108322.0,
|
|
"step": 31030
|
|
},
|
|
{
|
|
"entropy": 5.36614990234375,
|
|
"epoch": 2.5922986969595723,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004326016878100759,
|
|
"loss": 4.656,
|
|
"mean_token_accuracy": 0.23689694851636886,
|
|
"num_tokens": 57117131.0,
|
|
"step": 31035
|
|
},
|
|
{
|
|
"entropy": 5.429508256912231,
|
|
"epoch": 2.592716338122285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043258043961055104,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.2321256071329117,
|
|
"num_tokens": 57126278.0,
|
|
"step": 31040
|
|
},
|
|
{
|
|
"entropy": 5.452889060974121,
|
|
"epoch": 2.5931339792849983,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043255918865239097,
|
|
"loss": 4.7853,
|
|
"mean_token_accuracy": 0.22858980745077134,
|
|
"num_tokens": 57135163.0,
|
|
"step": 31045
|
|
},
|
|
{
|
|
"entropy": 5.395955276489258,
|
|
"epoch": 2.5935516204477116,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043253793493596755,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.22567499727010726,
|
|
"num_tokens": 57144368.0,
|
|
"step": 31050
|
|
},
|
|
{
|
|
"entropy": 5.326499986648559,
|
|
"epoch": 2.5939692616104244,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000432516678461653,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.2317060649394989,
|
|
"num_tokens": 57153421.0,
|
|
"step": 31055
|
|
},
|
|
{
|
|
"entropy": 5.429731035232544,
|
|
"epoch": 2.594386902773137,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004324954192298194,
|
|
"loss": 4.8023,
|
|
"mean_token_accuracy": 0.221725033223629,
|
|
"num_tokens": 57163238.0,
|
|
"step": 31060
|
|
},
|
|
{
|
|
"entropy": 5.5066282749176025,
|
|
"epoch": 2.5948045439358505,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043247415724083886,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.22145408838987352,
|
|
"num_tokens": 57172711.0,
|
|
"step": 31065
|
|
},
|
|
{
|
|
"entropy": 5.381226825714111,
|
|
"epoch": 2.5952221850985633,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043245289249508375,
|
|
"loss": 4.7319,
|
|
"mean_token_accuracy": 0.23940217047929763,
|
|
"num_tokens": 57181841.0,
|
|
"step": 31070
|
|
},
|
|
{
|
|
"entropy": 5.382895183563233,
|
|
"epoch": 2.5956398262612765,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004324316249929261,
|
|
"loss": 4.7705,
|
|
"mean_token_accuracy": 0.22905328273773193,
|
|
"num_tokens": 57191195.0,
|
|
"step": 31075
|
|
},
|
|
{
|
|
"entropy": 5.345392322540283,
|
|
"epoch": 2.5960574674239894,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004324103547347384,
|
|
"loss": 4.6083,
|
|
"mean_token_accuracy": 0.24334110766649247,
|
|
"num_tokens": 57200050.0,
|
|
"step": 31080
|
|
},
|
|
{
|
|
"entropy": 5.529708051681519,
|
|
"epoch": 2.596475108586702,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043238908172089306,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.23208047300577164,
|
|
"num_tokens": 57208296.0,
|
|
"step": 31085
|
|
},
|
|
{
|
|
"entropy": 5.3533164978027346,
|
|
"epoch": 2.5968927497494154,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043236780595176227,
|
|
"loss": 4.6534,
|
|
"mean_token_accuracy": 0.22895254343748092,
|
|
"num_tokens": 57217658.0,
|
|
"step": 31090
|
|
},
|
|
{
|
|
"entropy": 5.379064846038818,
|
|
"epoch": 2.5973103909121282,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004323465274277187,
|
|
"loss": 4.6787,
|
|
"mean_token_accuracy": 0.23229332119226456,
|
|
"num_tokens": 57227573.0,
|
|
"step": 31095
|
|
},
|
|
{
|
|
"entropy": 5.395743083953858,
|
|
"epoch": 2.5977280320748415,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004323252461491347,
|
|
"loss": 4.6879,
|
|
"mean_token_accuracy": 0.2328898549079895,
|
|
"num_tokens": 57236958.0,
|
|
"step": 31100
|
|
},
|
|
{
|
|
"entropy": 5.372080755233765,
|
|
"epoch": 2.5981456732375543,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004323039621163829,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.23471452444791793,
|
|
"num_tokens": 57246064.0,
|
|
"step": 31105
|
|
},
|
|
{
|
|
"entropy": 5.458103370666504,
|
|
"epoch": 2.598563314400267,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000432282675329836,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.22166488468647003,
|
|
"num_tokens": 57257162.0,
|
|
"step": 31110
|
|
},
|
|
{
|
|
"entropy": 5.484768438339233,
|
|
"epoch": 2.5989809555629804,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043226138578986644,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.22140570133924484,
|
|
"num_tokens": 57266080.0,
|
|
"step": 31115
|
|
},
|
|
{
|
|
"entropy": 5.461832046508789,
|
|
"epoch": 2.599398596725693,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043224009349684706,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.22421905845403672,
|
|
"num_tokens": 57274717.0,
|
|
"step": 31120
|
|
},
|
|
{
|
|
"entropy": 5.411962223052979,
|
|
"epoch": 2.5998162378884064,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004322187984511506,
|
|
"loss": 4.7822,
|
|
"mean_token_accuracy": 0.21908472925424577,
|
|
"num_tokens": 57283691.0,
|
|
"step": 31125
|
|
},
|
|
{
|
|
"entropy": 5.377672290802002,
|
|
"epoch": 2.6002338790511192,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004321975006531498,
|
|
"loss": 4.645,
|
|
"mean_token_accuracy": 0.22904274314641954,
|
|
"num_tokens": 57291393.0,
|
|
"step": 31130
|
|
},
|
|
{
|
|
"entropy": 5.385932159423828,
|
|
"epoch": 2.600651520213832,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004321762001032175,
|
|
"loss": 4.6844,
|
|
"mean_token_accuracy": 0.23233415931463242,
|
|
"num_tokens": 57300188.0,
|
|
"step": 31135
|
|
},
|
|
{
|
|
"entropy": 5.4621861457824705,
|
|
"epoch": 2.6010691613765453,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043215489680172665,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.2138139471411705,
|
|
"num_tokens": 57309306.0,
|
|
"step": 31140
|
|
},
|
|
{
|
|
"entropy": 5.492809391021728,
|
|
"epoch": 2.601486802539258,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004321335907490502,
|
|
"loss": 4.7517,
|
|
"mean_token_accuracy": 0.23154487013816832,
|
|
"num_tokens": 57319149.0,
|
|
"step": 31145
|
|
},
|
|
{
|
|
"entropy": 5.423986101150513,
|
|
"epoch": 2.6019044437019714,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004321122819455611,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.22470861673355103,
|
|
"num_tokens": 57328766.0,
|
|
"step": 31150
|
|
},
|
|
{
|
|
"entropy": 5.476986122131348,
|
|
"epoch": 2.602322084864684,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043209097039163233,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.22245965152978897,
|
|
"num_tokens": 57338231.0,
|
|
"step": 31155
|
|
},
|
|
{
|
|
"entropy": 5.372414684295654,
|
|
"epoch": 2.602739726027397,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043206965608763706,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.22807756662368775,
|
|
"num_tokens": 57347307.0,
|
|
"step": 31160
|
|
},
|
|
{
|
|
"entropy": 5.412220907211304,
|
|
"epoch": 2.6031573671901103,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004320483390339484,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.23053208887577056,
|
|
"num_tokens": 57356143.0,
|
|
"step": 31165
|
|
},
|
|
{
|
|
"entropy": 5.443920135498047,
|
|
"epoch": 2.6035750083528235,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004320270192309395,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.2234425038099289,
|
|
"num_tokens": 57366283.0,
|
|
"step": 31170
|
|
},
|
|
{
|
|
"entropy": 5.457408046722412,
|
|
"epoch": 2.6039926495155363,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004320056966789836,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.22805003672838212,
|
|
"num_tokens": 57375781.0,
|
|
"step": 31175
|
|
},
|
|
{
|
|
"entropy": 5.453712081909179,
|
|
"epoch": 2.604410290678249,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043198437137845403,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.23045883923768998,
|
|
"num_tokens": 57384851.0,
|
|
"step": 31180
|
|
},
|
|
{
|
|
"entropy": 5.4567482471466064,
|
|
"epoch": 2.6048279318409624,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043196304332972414,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.22652985006570817,
|
|
"num_tokens": 57393843.0,
|
|
"step": 31185
|
|
},
|
|
{
|
|
"entropy": 5.420685338973999,
|
|
"epoch": 2.605245573003675,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043194171253316716,
|
|
"loss": 4.7652,
|
|
"mean_token_accuracy": 0.22545958012342454,
|
|
"num_tokens": 57403248.0,
|
|
"step": 31190
|
|
},
|
|
{
|
|
"entropy": 5.412853813171386,
|
|
"epoch": 2.6056632141663885,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043192037898915665,
|
|
"loss": 4.6856,
|
|
"mean_token_accuracy": 0.23658900260925292,
|
|
"num_tokens": 57412626.0,
|
|
"step": 31195
|
|
},
|
|
{
|
|
"entropy": 5.4177610874176025,
|
|
"epoch": 2.6060808553291013,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000431899042698066,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.22364269345998763,
|
|
"num_tokens": 57421747.0,
|
|
"step": 31200
|
|
},
|
|
{
|
|
"entropy": 5.497723340988159,
|
|
"epoch": 2.606498496491814,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004318777036602687,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.2149125248193741,
|
|
"num_tokens": 57431106.0,
|
|
"step": 31205
|
|
},
|
|
{
|
|
"entropy": 5.430987358093262,
|
|
"epoch": 2.6069161376545273,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043185636187613837,
|
|
"loss": 4.6522,
|
|
"mean_token_accuracy": 0.232648828625679,
|
|
"num_tokens": 57440210.0,
|
|
"step": 31210
|
|
},
|
|
{
|
|
"entropy": 5.443003368377686,
|
|
"epoch": 2.60733377881724,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004318350173460487,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.22190670073032379,
|
|
"num_tokens": 57449012.0,
|
|
"step": 31215
|
|
},
|
|
{
|
|
"entropy": 5.420175457000733,
|
|
"epoch": 2.6077514199799534,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004318136700703731,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.2255436211824417,
|
|
"num_tokens": 57457143.0,
|
|
"step": 31220
|
|
},
|
|
{
|
|
"entropy": 5.41495361328125,
|
|
"epoch": 2.6081690611426662,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004317923200494856,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.23868829756975174,
|
|
"num_tokens": 57465791.0,
|
|
"step": 31225
|
|
},
|
|
{
|
|
"entropy": 5.36677885055542,
|
|
"epoch": 2.608586702305379,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043177096728375976,
|
|
"loss": 4.7227,
|
|
"mean_token_accuracy": 0.23476005345582962,
|
|
"num_tokens": 57474749.0,
|
|
"step": 31230
|
|
},
|
|
{
|
|
"entropy": 5.406745481491089,
|
|
"epoch": 2.6090043434680923,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00043174961177356946,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.2265260249376297,
|
|
"num_tokens": 57484895.0,
|
|
"step": 31235
|
|
},
|
|
{
|
|
"entropy": 5.394655370712281,
|
|
"epoch": 2.609421984630805,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004317282535192885,
|
|
"loss": 4.673,
|
|
"mean_token_accuracy": 0.2413452759385109,
|
|
"num_tokens": 57493751.0,
|
|
"step": 31240
|
|
},
|
|
{
|
|
"entropy": 5.336488533020019,
|
|
"epoch": 2.6098396257935184,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043170689252129083,
|
|
"loss": 4.6472,
|
|
"mean_token_accuracy": 0.2427459701895714,
|
|
"num_tokens": 57503096.0,
|
|
"step": 31245
|
|
},
|
|
{
|
|
"entropy": 5.3809349060058596,
|
|
"epoch": 2.610257266956231,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004316855287799504,
|
|
"loss": 4.671,
|
|
"mean_token_accuracy": 0.23352120965719222,
|
|
"num_tokens": 57512667.0,
|
|
"step": 31250
|
|
},
|
|
{
|
|
"entropy": 5.401343488693238,
|
|
"epoch": 2.610674908118944,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043166416229564107,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.22705168575048446,
|
|
"num_tokens": 57522404.0,
|
|
"step": 31255
|
|
},
|
|
{
|
|
"entropy": 5.3526074409484865,
|
|
"epoch": 2.6110925492816572,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043164279306873713,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.24244944751262665,
|
|
"num_tokens": 57531213.0,
|
|
"step": 31260
|
|
},
|
|
{
|
|
"entropy": 5.526385021209717,
|
|
"epoch": 2.61151019044437,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043162142109961246,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.2168389603495598,
|
|
"num_tokens": 57540943.0,
|
|
"step": 31265
|
|
},
|
|
{
|
|
"entropy": 5.480331897735596,
|
|
"epoch": 2.6119278316070833,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004316000463886414,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.21834308207035064,
|
|
"num_tokens": 57550054.0,
|
|
"step": 31270
|
|
},
|
|
{
|
|
"entropy": 5.479838418960571,
|
|
"epoch": 2.612345472769796,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004315786689361979,
|
|
"loss": 4.8083,
|
|
"mean_token_accuracy": 0.22244430780410768,
|
|
"num_tokens": 57559683.0,
|
|
"step": 31275
|
|
},
|
|
{
|
|
"entropy": 5.441186094284058,
|
|
"epoch": 2.612763113932509,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043155728874265636,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.2240137666463852,
|
|
"num_tokens": 57569446.0,
|
|
"step": 31280
|
|
},
|
|
{
|
|
"entropy": 5.401070547103882,
|
|
"epoch": 2.613180755095222,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043153590580839106,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.2364581674337387,
|
|
"num_tokens": 57578468.0,
|
|
"step": 31285
|
|
},
|
|
{
|
|
"entropy": 5.413363790512085,
|
|
"epoch": 2.6135983962579354,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043151452013377636,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.22346725016832353,
|
|
"num_tokens": 57587017.0,
|
|
"step": 31290
|
|
},
|
|
{
|
|
"entropy": 5.518985462188721,
|
|
"epoch": 2.6140160374206483,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043149313171918647,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.22311476320028306,
|
|
"num_tokens": 57596688.0,
|
|
"step": 31295
|
|
},
|
|
{
|
|
"entropy": 5.425390577316284,
|
|
"epoch": 2.614433678583361,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043147174056499605,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.23382444828748702,
|
|
"num_tokens": 57606595.0,
|
|
"step": 31300
|
|
},
|
|
{
|
|
"entropy": 5.482967758178711,
|
|
"epoch": 2.6148513197460743,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043145034667157935,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.22140233367681503,
|
|
"num_tokens": 57616413.0,
|
|
"step": 31305
|
|
},
|
|
{
|
|
"entropy": 5.556047677993774,
|
|
"epoch": 2.615268960908787,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004314289500393111,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.23025297969579697,
|
|
"num_tokens": 57625903.0,
|
|
"step": 31310
|
|
},
|
|
{
|
|
"entropy": 5.354466295242309,
|
|
"epoch": 2.6156866020715004,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043140755066856573,
|
|
"loss": 4.6895,
|
|
"mean_token_accuracy": 0.23832606971263887,
|
|
"num_tokens": 57635315.0,
|
|
"step": 31315
|
|
},
|
|
{
|
|
"entropy": 5.345906496047974,
|
|
"epoch": 2.616104243234213,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000431386148559718,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.24728319942951202,
|
|
"num_tokens": 57643806.0,
|
|
"step": 31320
|
|
},
|
|
{
|
|
"entropy": 5.337897062301636,
|
|
"epoch": 2.616521884396926,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043136474371314245,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.23071033656597137,
|
|
"num_tokens": 57654030.0,
|
|
"step": 31325
|
|
},
|
|
{
|
|
"entropy": 5.4367012023925785,
|
|
"epoch": 2.6169395255596393,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004313433361292138,
|
|
"loss": 4.6549,
|
|
"mean_token_accuracy": 0.23953430652618407,
|
|
"num_tokens": 57663141.0,
|
|
"step": 31330
|
|
},
|
|
{
|
|
"entropy": 5.482894420623779,
|
|
"epoch": 2.617357166722352,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043132192580830694,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.22965666949748992,
|
|
"num_tokens": 57672943.0,
|
|
"step": 31335
|
|
},
|
|
{
|
|
"entropy": 5.4027588844299315,
|
|
"epoch": 2.6177748078850653,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043130051275079654,
|
|
"loss": 4.7146,
|
|
"mean_token_accuracy": 0.22849104553461075,
|
|
"num_tokens": 57682086.0,
|
|
"step": 31340
|
|
},
|
|
{
|
|
"entropy": 5.410283470153809,
|
|
"epoch": 2.618192449047778,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004312790969570575,
|
|
"loss": 4.75,
|
|
"mean_token_accuracy": 0.22749173790216445,
|
|
"num_tokens": 57691229.0,
|
|
"step": 31345
|
|
},
|
|
{
|
|
"entropy": 5.488824796676636,
|
|
"epoch": 2.618610090210491,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004312576784274648,
|
|
"loss": 4.7583,
|
|
"mean_token_accuracy": 0.23498995304107667,
|
|
"num_tokens": 57700057.0,
|
|
"step": 31350
|
|
},
|
|
{
|
|
"entropy": 5.443768119812011,
|
|
"epoch": 2.619027731373204,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004312362571623934,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.2236515149474144,
|
|
"num_tokens": 57709498.0,
|
|
"step": 31355
|
|
},
|
|
{
|
|
"entropy": 5.385638666152954,
|
|
"epoch": 2.619445372535917,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004312148331622182,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.23449270576238632,
|
|
"num_tokens": 57718719.0,
|
|
"step": 31360
|
|
},
|
|
{
|
|
"entropy": 5.421152353286743,
|
|
"epoch": 2.6198630136986303,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004311934064273143,
|
|
"loss": 4.6527,
|
|
"mean_token_accuracy": 0.2394082397222519,
|
|
"num_tokens": 57727225.0,
|
|
"step": 31365
|
|
},
|
|
{
|
|
"entropy": 5.333876323699951,
|
|
"epoch": 2.620280654861343,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004311719769580569,
|
|
"loss": 4.6641,
|
|
"mean_token_accuracy": 0.23737524896860124,
|
|
"num_tokens": 57736027.0,
|
|
"step": 31370
|
|
},
|
|
{
|
|
"entropy": 5.322188425064087,
|
|
"epoch": 2.620698296024056,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043115054475482094,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.23267854899168014,
|
|
"num_tokens": 57745456.0,
|
|
"step": 31375
|
|
},
|
|
{
|
|
"entropy": 5.425999927520752,
|
|
"epoch": 2.621115937186769,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004311291098179818,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.22562548518180847,
|
|
"num_tokens": 57754689.0,
|
|
"step": 31380
|
|
},
|
|
{
|
|
"entropy": 5.371222639083863,
|
|
"epoch": 2.621533578349482,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043110767214791466,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.2246508538722992,
|
|
"num_tokens": 57763759.0,
|
|
"step": 31385
|
|
},
|
|
{
|
|
"entropy": 5.413341426849366,
|
|
"epoch": 2.6219512195121952,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004310862317449948,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.23879784047603608,
|
|
"num_tokens": 57772765.0,
|
|
"step": 31390
|
|
},
|
|
{
|
|
"entropy": 5.440600395202637,
|
|
"epoch": 2.622368860674908,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004310647886095976,
|
|
"loss": 4.7781,
|
|
"mean_token_accuracy": 0.22385387122631073,
|
|
"num_tokens": 57783831.0,
|
|
"step": 31395
|
|
},
|
|
{
|
|
"entropy": 5.465164232254028,
|
|
"epoch": 2.622786501837621,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004310433427420984,
|
|
"loss": 4.6972,
|
|
"mean_token_accuracy": 0.2386787563562393,
|
|
"num_tokens": 57792439.0,
|
|
"step": 31400
|
|
},
|
|
{
|
|
"entropy": 5.377551698684693,
|
|
"epoch": 2.623204143000334,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043102189414287255,
|
|
"loss": 4.7536,
|
|
"mean_token_accuracy": 0.231057246029377,
|
|
"num_tokens": 57802280.0,
|
|
"step": 31405
|
|
},
|
|
{
|
|
"entropy": 5.395186901092529,
|
|
"epoch": 2.6236217841630474,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004310004428122958,
|
|
"loss": 4.7372,
|
|
"mean_token_accuracy": 0.23829162120819092,
|
|
"num_tokens": 57811631.0,
|
|
"step": 31410
|
|
},
|
|
{
|
|
"entropy": 5.434224796295166,
|
|
"epoch": 2.62403942532576,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043097898875074344,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.23191796690225602,
|
|
"num_tokens": 57821286.0,
|
|
"step": 31415
|
|
},
|
|
{
|
|
"entropy": 5.434793424606323,
|
|
"epoch": 2.624457066488473,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004309575319585912,
|
|
"loss": 4.6866,
|
|
"mean_token_accuracy": 0.229402557015419,
|
|
"num_tokens": 57830446.0,
|
|
"step": 31420
|
|
},
|
|
{
|
|
"entropy": 5.3965301513671875,
|
|
"epoch": 2.6248747076511862,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043093607243621456,
|
|
"loss": 4.6654,
|
|
"mean_token_accuracy": 0.24019920378923415,
|
|
"num_tokens": 57839203.0,
|
|
"step": 31425
|
|
},
|
|
{
|
|
"entropy": 5.346830701828003,
|
|
"epoch": 2.625292348813899,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004309146101839893,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.2294820874929428,
|
|
"num_tokens": 57848251.0,
|
|
"step": 31430
|
|
},
|
|
{
|
|
"entropy": 5.3612267017364506,
|
|
"epoch": 2.6257099899766123,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004308931452022911,
|
|
"loss": 4.6638,
|
|
"mean_token_accuracy": 0.2365813136100769,
|
|
"num_tokens": 57856832.0,
|
|
"step": 31435
|
|
},
|
|
{
|
|
"entropy": 5.468215799331665,
|
|
"epoch": 2.626127631139325,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004308716774914957,
|
|
"loss": 4.7917,
|
|
"mean_token_accuracy": 0.22668386697769166,
|
|
"num_tokens": 57866678.0,
|
|
"step": 31440
|
|
},
|
|
{
|
|
"entropy": 5.5231773376464846,
|
|
"epoch": 2.626545272302038,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043085020705197906,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.22735357135534287,
|
|
"num_tokens": 57875764.0,
|
|
"step": 31445
|
|
},
|
|
{
|
|
"entropy": 5.417800855636597,
|
|
"epoch": 2.626962913464751,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00043082873388411696,
|
|
"loss": 4.7372,
|
|
"mean_token_accuracy": 0.23097061961889268,
|
|
"num_tokens": 57884964.0,
|
|
"step": 31450
|
|
},
|
|
{
|
|
"entropy": 5.458452463150024,
|
|
"epoch": 2.627380554627464,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043080725798828526,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.22506797462701797,
|
|
"num_tokens": 57893625.0,
|
|
"step": 31455
|
|
},
|
|
{
|
|
"entropy": 5.411754989624024,
|
|
"epoch": 2.6277981957901773,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004307857793648599,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.23464318811893464,
|
|
"num_tokens": 57902267.0,
|
|
"step": 31460
|
|
},
|
|
{
|
|
"entropy": 5.396504259109497,
|
|
"epoch": 2.62821583695289,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004307642980142171,
|
|
"loss": 4.6305,
|
|
"mean_token_accuracy": 0.23936177641153336,
|
|
"num_tokens": 57910681.0,
|
|
"step": 31465
|
|
},
|
|
{
|
|
"entropy": 5.41993522644043,
|
|
"epoch": 2.628633478115603,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043074281393673265,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.22906717658042908,
|
|
"num_tokens": 57920589.0,
|
|
"step": 31470
|
|
},
|
|
{
|
|
"entropy": 5.396758699417115,
|
|
"epoch": 2.629051119278316,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043072132713278273,
|
|
"loss": 4.7064,
|
|
"mean_token_accuracy": 0.22958751022815704,
|
|
"num_tokens": 57930095.0,
|
|
"step": 31475
|
|
},
|
|
{
|
|
"entropy": 5.410706329345703,
|
|
"epoch": 2.629468760441029,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043069983760274367,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.23287194967269897,
|
|
"num_tokens": 57939615.0,
|
|
"step": 31480
|
|
},
|
|
{
|
|
"entropy": 5.445499610900879,
|
|
"epoch": 2.629886401603742,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043067834534699144,
|
|
"loss": 4.7413,
|
|
"mean_token_accuracy": 0.23075013905763625,
|
|
"num_tokens": 57948843.0,
|
|
"step": 31485
|
|
},
|
|
{
|
|
"entropy": 5.4416954040527346,
|
|
"epoch": 2.630304042766455,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043065685036590244,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.21818286925554276,
|
|
"num_tokens": 57958510.0,
|
|
"step": 31490
|
|
},
|
|
{
|
|
"entropy": 5.352393865585327,
|
|
"epoch": 2.630721683929168,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043063535265985283,
|
|
"loss": 4.5722,
|
|
"mean_token_accuracy": 0.24264301210641862,
|
|
"num_tokens": 57968129.0,
|
|
"step": 31495
|
|
},
|
|
{
|
|
"entropy": 5.372502326965332,
|
|
"epoch": 2.631139325091881,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043061385222921915,
|
|
"loss": 4.7338,
|
|
"mean_token_accuracy": 0.21795769035816193,
|
|
"num_tokens": 57977920.0,
|
|
"step": 31500
|
|
},
|
|
{
|
|
"entropy": 5.466513442993164,
|
|
"epoch": 2.631556966254594,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004305923490743777,
|
|
"loss": 4.794,
|
|
"mean_token_accuracy": 0.22300015091896058,
|
|
"num_tokens": 57987216.0,
|
|
"step": 31505
|
|
},
|
|
{
|
|
"entropy": 5.440924644470215,
|
|
"epoch": 2.631974607417307,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004305708431957048,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.23070013672113418,
|
|
"num_tokens": 57996558.0,
|
|
"step": 31510
|
|
},
|
|
{
|
|
"entropy": 5.37262806892395,
|
|
"epoch": 2.63239224858002,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004305493345935769,
|
|
"loss": 4.6858,
|
|
"mean_token_accuracy": 0.23311375826597214,
|
|
"num_tokens": 58005220.0,
|
|
"step": 31515
|
|
},
|
|
{
|
|
"entropy": 5.391414165496826,
|
|
"epoch": 2.632809889742733,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043052782326837084,
|
|
"loss": 4.6457,
|
|
"mean_token_accuracy": 0.24600802958011628,
|
|
"num_tokens": 58014841.0,
|
|
"step": 31520
|
|
},
|
|
{
|
|
"entropy": 5.380635929107666,
|
|
"epoch": 2.633227530905446,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000430506309220463,
|
|
"loss": 4.728,
|
|
"mean_token_accuracy": 0.22954854518175125,
|
|
"num_tokens": 58023797.0,
|
|
"step": 31525
|
|
},
|
|
{
|
|
"entropy": 5.401755619049072,
|
|
"epoch": 2.6336451720681593,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004304847924502301,
|
|
"loss": 4.7334,
|
|
"mean_token_accuracy": 0.23002512454986573,
|
|
"num_tokens": 58032931.0,
|
|
"step": 31530
|
|
},
|
|
{
|
|
"entropy": 5.422118091583252,
|
|
"epoch": 2.634062813230872,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043046327295804865,
|
|
"loss": 4.6995,
|
|
"mean_token_accuracy": 0.23192201405763627,
|
|
"num_tokens": 58042171.0,
|
|
"step": 31535
|
|
},
|
|
{
|
|
"entropy": 5.349216508865356,
|
|
"epoch": 2.634480454393585,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004304417507442955,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.22899571061134338,
|
|
"num_tokens": 58050610.0,
|
|
"step": 31540
|
|
},
|
|
{
|
|
"entropy": 5.377249240875244,
|
|
"epoch": 2.634898095556298,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004304202258093473,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.23687273859977723,
|
|
"num_tokens": 58059962.0,
|
|
"step": 31545
|
|
},
|
|
{
|
|
"entropy": 5.355459260940552,
|
|
"epoch": 2.635315736719011,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043039869815358114,
|
|
"loss": 4.6245,
|
|
"mean_token_accuracy": 0.24187495261430741,
|
|
"num_tokens": 58069265.0,
|
|
"step": 31550
|
|
},
|
|
{
|
|
"entropy": 5.361703538894654,
|
|
"epoch": 2.6357333778817242,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004303771677773736,
|
|
"loss": 4.6687,
|
|
"mean_token_accuracy": 0.2347027763724327,
|
|
"num_tokens": 58078931.0,
|
|
"step": 31555
|
|
},
|
|
{
|
|
"entropy": 5.349208354949951,
|
|
"epoch": 2.636151019044437,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004303556346811018,
|
|
"loss": 4.6474,
|
|
"mean_token_accuracy": 0.2364671289920807,
|
|
"num_tokens": 58088110.0,
|
|
"step": 31560
|
|
},
|
|
{
|
|
"entropy": 5.388768529891967,
|
|
"epoch": 2.63656866020715,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004303340988651425,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.23427185714244841,
|
|
"num_tokens": 58096975.0,
|
|
"step": 31565
|
|
},
|
|
{
|
|
"entropy": 5.448207139968872,
|
|
"epoch": 2.636986301369863,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004303125603298729,
|
|
"loss": 4.7529,
|
|
"mean_token_accuracy": 0.22799225598573686,
|
|
"num_tokens": 58106633.0,
|
|
"step": 31570
|
|
},
|
|
{
|
|
"entropy": 5.527147817611694,
|
|
"epoch": 2.637403942532576,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043029101907567004,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.2229709431529045,
|
|
"num_tokens": 58115705.0,
|
|
"step": 31575
|
|
},
|
|
{
|
|
"entropy": 5.439976930618286,
|
|
"epoch": 2.637821583695289,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004302694751029108,
|
|
"loss": 4.7395,
|
|
"mean_token_accuracy": 0.2243765264749527,
|
|
"num_tokens": 58124191.0,
|
|
"step": 31580
|
|
},
|
|
{
|
|
"entropy": 5.4118681907653805,
|
|
"epoch": 2.638239224858002,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004302479284119727,
|
|
"loss": 4.7973,
|
|
"mean_token_accuracy": 0.22855288833379744,
|
|
"num_tokens": 58133911.0,
|
|
"step": 31585
|
|
},
|
|
{
|
|
"entropy": 5.356329154968262,
|
|
"epoch": 2.638656866020715,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043022637900323263,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.22570270746946336,
|
|
"num_tokens": 58143299.0,
|
|
"step": 31590
|
|
},
|
|
{
|
|
"entropy": 5.402457141876221,
|
|
"epoch": 2.639074507183428,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004302048268770679,
|
|
"loss": 4.6779,
|
|
"mean_token_accuracy": 0.23627127408981324,
|
|
"num_tokens": 58151890.0,
|
|
"step": 31595
|
|
},
|
|
{
|
|
"entropy": 5.398305511474609,
|
|
"epoch": 2.639492148346141,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043018327203385594,
|
|
"loss": 4.6975,
|
|
"mean_token_accuracy": 0.23471319377422334,
|
|
"num_tokens": 58161381.0,
|
|
"step": 31600
|
|
},
|
|
{
|
|
"entropy": 5.467829990386963,
|
|
"epoch": 2.639909789508854,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000430161714473974,
|
|
"loss": 4.81,
|
|
"mean_token_accuracy": 0.2224802404642105,
|
|
"num_tokens": 58170818.0,
|
|
"step": 31605
|
|
},
|
|
{
|
|
"entropy": 5.471386241912842,
|
|
"epoch": 2.640327430671567,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043014015419779947,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.23645532727241517,
|
|
"num_tokens": 58180050.0,
|
|
"step": 31610
|
|
},
|
|
{
|
|
"entropy": 5.4136803150177,
|
|
"epoch": 2.6407450718342798,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004301185912057097,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.23259456902742387,
|
|
"num_tokens": 58188252.0,
|
|
"step": 31615
|
|
},
|
|
{
|
|
"entropy": 5.391478157043457,
|
|
"epoch": 2.641162712996993,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043009702549808243,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.22365082055330276,
|
|
"num_tokens": 58196772.0,
|
|
"step": 31620
|
|
},
|
|
{
|
|
"entropy": 5.415581560134887,
|
|
"epoch": 2.641580354159706,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043007545707529496,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.22365630716085433,
|
|
"num_tokens": 58205986.0,
|
|
"step": 31625
|
|
},
|
|
{
|
|
"entropy": 5.490849590301513,
|
|
"epoch": 2.641997995322419,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000430053885937725,
|
|
"loss": 4.7853,
|
|
"mean_token_accuracy": 0.22574782818555833,
|
|
"num_tokens": 58214596.0,
|
|
"step": 31630
|
|
},
|
|
{
|
|
"entropy": 5.487821006774903,
|
|
"epoch": 2.642415636485132,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043003231208575004,
|
|
"loss": 4.7736,
|
|
"mean_token_accuracy": 0.22880037873983383,
|
|
"num_tokens": 58224011.0,
|
|
"step": 31635
|
|
},
|
|
{
|
|
"entropy": 5.3903735160827635,
|
|
"epoch": 2.6428332776478447,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043001073551974796,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.23455408364534377,
|
|
"num_tokens": 58233175.0,
|
|
"step": 31640
|
|
},
|
|
{
|
|
"entropy": 5.477379226684571,
|
|
"epoch": 2.643250918810558,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042998915624009625,
|
|
"loss": 4.7986,
|
|
"mean_token_accuracy": 0.2292703226208687,
|
|
"num_tokens": 58242496.0,
|
|
"step": 31645
|
|
},
|
|
{
|
|
"entropy": 5.4111778259277346,
|
|
"epoch": 2.643668559973271,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004299675742471729,
|
|
"loss": 4.7061,
|
|
"mean_token_accuracy": 0.23399268388748168,
|
|
"num_tokens": 58251361.0,
|
|
"step": 31650
|
|
},
|
|
{
|
|
"entropy": 5.460116720199585,
|
|
"epoch": 2.644086201135984,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042994598954135553,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.22788984179496766,
|
|
"num_tokens": 58260892.0,
|
|
"step": 31655
|
|
},
|
|
{
|
|
"entropy": 5.4501852035522464,
|
|
"epoch": 2.644503842298697,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004299244021230222,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.23407524675130845,
|
|
"num_tokens": 58270109.0,
|
|
"step": 31660
|
|
},
|
|
{
|
|
"entropy": 5.535852479934692,
|
|
"epoch": 2.64492148346141,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004299028119925507,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.2316957712173462,
|
|
"num_tokens": 58278700.0,
|
|
"step": 31665
|
|
},
|
|
{
|
|
"entropy": 5.46738600730896,
|
|
"epoch": 2.645339124624123,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00042988121915031894,
|
|
"loss": 4.7696,
|
|
"mean_token_accuracy": 0.23133862316608428,
|
|
"num_tokens": 58288671.0,
|
|
"step": 31670
|
|
},
|
|
{
|
|
"entropy": 5.412708473205567,
|
|
"epoch": 2.645756765786836,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004298596235967051,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.23120681047439576,
|
|
"num_tokens": 58297428.0,
|
|
"step": 31675
|
|
},
|
|
{
|
|
"entropy": 5.452157402038575,
|
|
"epoch": 2.646174406949549,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004298380253320871,
|
|
"loss": 4.7924,
|
|
"mean_token_accuracy": 0.233041013777256,
|
|
"num_tokens": 58306863.0,
|
|
"step": 31680
|
|
},
|
|
{
|
|
"entropy": 5.398284530639648,
|
|
"epoch": 2.646592048112262,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004298164243568431,
|
|
"loss": 4.7622,
|
|
"mean_token_accuracy": 0.23013418465852736,
|
|
"num_tokens": 58315701.0,
|
|
"step": 31685
|
|
},
|
|
{
|
|
"entropy": 5.407986402511597,
|
|
"epoch": 2.647009689274975,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004297948206713513,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.2278590127825737,
|
|
"num_tokens": 58324805.0,
|
|
"step": 31690
|
|
},
|
|
{
|
|
"entropy": 5.496236133575439,
|
|
"epoch": 2.647427330437688,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042977321427598974,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.22665422260761262,
|
|
"num_tokens": 58332885.0,
|
|
"step": 31695
|
|
},
|
|
{
|
|
"entropy": 5.402540111541748,
|
|
"epoch": 2.647844971600401,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004297516051711368,
|
|
"loss": 4.7631,
|
|
"mean_token_accuracy": 0.22510351836681367,
|
|
"num_tokens": 58343447.0,
|
|
"step": 31700
|
|
},
|
|
{
|
|
"entropy": 5.462151908874512,
|
|
"epoch": 2.648262612763114,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004297299933571708,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.22448192536830902,
|
|
"num_tokens": 58352807.0,
|
|
"step": 31705
|
|
},
|
|
{
|
|
"entropy": 5.471954679489135,
|
|
"epoch": 2.6486802539258267,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004297083788344699,
|
|
"loss": 4.7862,
|
|
"mean_token_accuracy": 0.22672003358602524,
|
|
"num_tokens": 58361683.0,
|
|
"step": 31710
|
|
},
|
|
{
|
|
"entropy": 5.505906105041504,
|
|
"epoch": 2.64909789508854,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042968676160341275,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.2316339522600174,
|
|
"num_tokens": 58370760.0,
|
|
"step": 31715
|
|
},
|
|
{
|
|
"entropy": 5.362879896163941,
|
|
"epoch": 2.649515536251253,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004296651416643775,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.2349376931786537,
|
|
"num_tokens": 58379931.0,
|
|
"step": 31720
|
|
},
|
|
{
|
|
"entropy": 5.358081102371216,
|
|
"epoch": 2.649933177413966,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042964351901774285,
|
|
"loss": 4.6191,
|
|
"mean_token_accuracy": 0.23761540204286574,
|
|
"num_tokens": 58388320.0,
|
|
"step": 31725
|
|
},
|
|
{
|
|
"entropy": 5.385337448120117,
|
|
"epoch": 2.650350818576679,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004296218936638873,
|
|
"loss": 4.7611,
|
|
"mean_token_accuracy": 0.22706762105226516,
|
|
"num_tokens": 58397610.0,
|
|
"step": 31730
|
|
},
|
|
{
|
|
"entropy": 5.458831024169922,
|
|
"epoch": 2.6507684597393917,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042960026560318927,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.23113042414188384,
|
|
"num_tokens": 58407156.0,
|
|
"step": 31735
|
|
},
|
|
{
|
|
"entropy": 5.5481291770935055,
|
|
"epoch": 2.651186100902105,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042957863483602756,
|
|
"loss": 4.9407,
|
|
"mean_token_accuracy": 0.22041870057582855,
|
|
"num_tokens": 58416900.0,
|
|
"step": 31740
|
|
},
|
|
{
|
|
"entropy": 5.379819059371949,
|
|
"epoch": 2.6516037420648177,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042955700136278077,
|
|
"loss": 4.6452,
|
|
"mean_token_accuracy": 0.2316603884100914,
|
|
"num_tokens": 58425714.0,
|
|
"step": 31745
|
|
},
|
|
{
|
|
"entropy": 5.322326374053955,
|
|
"epoch": 2.652021383227531,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004295353651838276,
|
|
"loss": 4.5861,
|
|
"mean_token_accuracy": 0.24167529493570328,
|
|
"num_tokens": 58433910.0,
|
|
"step": 31750
|
|
},
|
|
{
|
|
"entropy": 5.461162090301514,
|
|
"epoch": 2.652439024390244,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042951372629954695,
|
|
"loss": 4.835,
|
|
"mean_token_accuracy": 0.2262863352894783,
|
|
"num_tokens": 58443339.0,
|
|
"step": 31755
|
|
},
|
|
{
|
|
"entropy": 5.4671266078948975,
|
|
"epoch": 2.6528566655529566,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004294920847103174,
|
|
"loss": 4.7178,
|
|
"mean_token_accuracy": 0.23773647993803024,
|
|
"num_tokens": 58451481.0,
|
|
"step": 31760
|
|
},
|
|
{
|
|
"entropy": 5.402890825271607,
|
|
"epoch": 2.65327430671567,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004294704404165181,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.23133123219013213,
|
|
"num_tokens": 58461970.0,
|
|
"step": 31765
|
|
},
|
|
{
|
|
"entropy": 5.420374250411987,
|
|
"epoch": 2.653691947878383,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042944879341852763,
|
|
"loss": 4.7779,
|
|
"mean_token_accuracy": 0.2255830019712448,
|
|
"num_tokens": 58471210.0,
|
|
"step": 31770
|
|
},
|
|
{
|
|
"entropy": 5.41015043258667,
|
|
"epoch": 2.654109589041096,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004294271437167252,
|
|
"loss": 4.687,
|
|
"mean_token_accuracy": 0.23502199202775956,
|
|
"num_tokens": 58480808.0,
|
|
"step": 31775
|
|
},
|
|
{
|
|
"entropy": 5.489868593215943,
|
|
"epoch": 2.6545272302038088,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042940549131148976,
|
|
"loss": 4.8706,
|
|
"mean_token_accuracy": 0.21837962716817855,
|
|
"num_tokens": 58490514.0,
|
|
"step": 31780
|
|
},
|
|
{
|
|
"entropy": 5.43584623336792,
|
|
"epoch": 2.654944871366522,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004293838362032003,
|
|
"loss": 4.8386,
|
|
"mean_token_accuracy": 0.2173655852675438,
|
|
"num_tokens": 58499894.0,
|
|
"step": 31785
|
|
},
|
|
{
|
|
"entropy": 5.470716381072998,
|
|
"epoch": 2.655362512529235,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042936217839223596,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.22869028002023697,
|
|
"num_tokens": 58510531.0,
|
|
"step": 31790
|
|
},
|
|
{
|
|
"entropy": 5.3833081245422365,
|
|
"epoch": 2.655780153691948,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00042934051787897593,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.2330917790532112,
|
|
"num_tokens": 58519542.0,
|
|
"step": 31795
|
|
},
|
|
{
|
|
"entropy": 5.377819919586182,
|
|
"epoch": 2.656197794854661,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042931885466379935,
|
|
"loss": 4.666,
|
|
"mean_token_accuracy": 0.23696959763765335,
|
|
"num_tokens": 58528883.0,
|
|
"step": 31800
|
|
},
|
|
{
|
|
"entropy": 5.355402517318725,
|
|
"epoch": 2.6566154360173737,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004292971887470854,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.23906223028898238,
|
|
"num_tokens": 58538185.0,
|
|
"step": 31805
|
|
},
|
|
{
|
|
"entropy": 5.446252965927124,
|
|
"epoch": 2.657033077180087,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042927552012921353,
|
|
"loss": 4.8096,
|
|
"mean_token_accuracy": 0.23095522224903106,
|
|
"num_tokens": 58547933.0,
|
|
"step": 31810
|
|
},
|
|
{
|
|
"entropy": 5.403446626663208,
|
|
"epoch": 2.6574507183428,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042925384881056284,
|
|
"loss": 4.6373,
|
|
"mean_token_accuracy": 0.24392432123422622,
|
|
"num_tokens": 58557291.0,
|
|
"step": 31815
|
|
},
|
|
{
|
|
"entropy": 5.343201398849487,
|
|
"epoch": 2.657868359505513,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042923217479151296,
|
|
"loss": 4.6227,
|
|
"mean_token_accuracy": 0.23865900933742523,
|
|
"num_tokens": 58565693.0,
|
|
"step": 31820
|
|
},
|
|
{
|
|
"entropy": 5.41650505065918,
|
|
"epoch": 2.658286000668226,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042921049807244317,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.22845156043767928,
|
|
"num_tokens": 58574557.0,
|
|
"step": 31825
|
|
},
|
|
{
|
|
"entropy": 5.490013933181762,
|
|
"epoch": 2.6587036418309387,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000429188818653733,
|
|
"loss": 4.8032,
|
|
"mean_token_accuracy": 0.22567256391048432,
|
|
"num_tokens": 58582820.0,
|
|
"step": 31830
|
|
},
|
|
{
|
|
"entropy": 5.33582181930542,
|
|
"epoch": 2.659121282993652,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004291671365357619,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.22567607164382936,
|
|
"num_tokens": 58591559.0,
|
|
"step": 31835
|
|
},
|
|
{
|
|
"entropy": 5.485949325561523,
|
|
"epoch": 2.6595389241563647,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042914545171890964,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.2199707806110382,
|
|
"num_tokens": 58600788.0,
|
|
"step": 31840
|
|
},
|
|
{
|
|
"entropy": 5.394095516204834,
|
|
"epoch": 2.659956565319078,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042912376420355553,
|
|
"loss": 4.6109,
|
|
"mean_token_accuracy": 0.24558391869068147,
|
|
"num_tokens": 58609742.0,
|
|
"step": 31845
|
|
},
|
|
{
|
|
"entropy": 5.4223949909210205,
|
|
"epoch": 2.660374206481791,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004291020739900796,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.23015946596860887,
|
|
"num_tokens": 58619162.0,
|
|
"step": 31850
|
|
},
|
|
{
|
|
"entropy": 5.383369302749633,
|
|
"epoch": 2.6607918476445036,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004290803810788612,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.22414842545986174,
|
|
"num_tokens": 58628873.0,
|
|
"step": 31855
|
|
},
|
|
{
|
|
"entropy": 5.398911809921264,
|
|
"epoch": 2.661209488807217,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004290586854702804,
|
|
"loss": 4.7513,
|
|
"mean_token_accuracy": 0.22642432451248168,
|
|
"num_tokens": 58638180.0,
|
|
"step": 31860
|
|
},
|
|
{
|
|
"entropy": 5.361574983596801,
|
|
"epoch": 2.6616271299699297,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042903698716471677,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.23337641060352327,
|
|
"num_tokens": 58647303.0,
|
|
"step": 31865
|
|
},
|
|
{
|
|
"entropy": 5.514426231384277,
|
|
"epoch": 2.662044771132643,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004290152861625503,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.22158770114183426,
|
|
"num_tokens": 58656724.0,
|
|
"step": 31870
|
|
},
|
|
{
|
|
"entropy": 5.510994148254395,
|
|
"epoch": 2.6624624122953557,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042899358246416085,
|
|
"loss": 4.8357,
|
|
"mean_token_accuracy": 0.22384967505931855,
|
|
"num_tokens": 58666670.0,
|
|
"step": 31875
|
|
},
|
|
{
|
|
"entropy": 5.442826271057129,
|
|
"epoch": 2.6628800534580686,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042897187606992846,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.23396514505147933,
|
|
"num_tokens": 58675608.0,
|
|
"step": 31880
|
|
},
|
|
{
|
|
"entropy": 5.432993412017822,
|
|
"epoch": 2.663297694620782,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004289501669802329,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.22479955554008485,
|
|
"num_tokens": 58685470.0,
|
|
"step": 31885
|
|
},
|
|
{
|
|
"entropy": 5.498930597305298,
|
|
"epoch": 2.663715335783495,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004289284551954545,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.21964718103408815,
|
|
"num_tokens": 58695610.0,
|
|
"step": 31890
|
|
},
|
|
{
|
|
"entropy": 5.466250658035278,
|
|
"epoch": 2.664132976946208,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004289067407159731,
|
|
"loss": 4.7858,
|
|
"mean_token_accuracy": 0.22801918387413025,
|
|
"num_tokens": 58705608.0,
|
|
"step": 31895
|
|
},
|
|
{
|
|
"entropy": 5.392834949493408,
|
|
"epoch": 2.6645506181089207,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042888502354216897,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.23381246775388717,
|
|
"num_tokens": 58714575.0,
|
|
"step": 31900
|
|
},
|
|
{
|
|
"entropy": 5.497903680801391,
|
|
"epoch": 2.664968259271634,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042886330367442234,
|
|
"loss": 4.8505,
|
|
"mean_token_accuracy": 0.2194787159562111,
|
|
"num_tokens": 58724748.0,
|
|
"step": 31905
|
|
},
|
|
{
|
|
"entropy": 5.496000576019287,
|
|
"epoch": 2.6653859004343468,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042884158111311326,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.21824890971183777,
|
|
"num_tokens": 58734388.0,
|
|
"step": 31910
|
|
},
|
|
{
|
|
"entropy": 5.462161302566528,
|
|
"epoch": 2.66580354159706,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004288198558586222,
|
|
"loss": 4.6848,
|
|
"mean_token_accuracy": 0.2354566529393196,
|
|
"num_tokens": 58742328.0,
|
|
"step": 31915
|
|
},
|
|
{
|
|
"entropy": 5.41898889541626,
|
|
"epoch": 2.666221182759773,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004287981279113294,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.2304101899266243,
|
|
"num_tokens": 58750788.0,
|
|
"step": 31920
|
|
},
|
|
{
|
|
"entropy": 5.355776166915893,
|
|
"epoch": 2.6666388239224856,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004287763972716152,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.23490179181098939,
|
|
"num_tokens": 58759305.0,
|
|
"step": 31925
|
|
},
|
|
{
|
|
"entropy": 5.434147024154663,
|
|
"epoch": 2.667056465085199,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042875466393986017,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.2236884742975235,
|
|
"num_tokens": 58768358.0,
|
|
"step": 31930
|
|
},
|
|
{
|
|
"entropy": 5.434093332290649,
|
|
"epoch": 2.6674741062479117,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004287329279164445,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.2381390690803528,
|
|
"num_tokens": 58778005.0,
|
|
"step": 31935
|
|
},
|
|
{
|
|
"entropy": 5.469102907180786,
|
|
"epoch": 2.667891747410625,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042871118920174907,
|
|
"loss": 4.8733,
|
|
"mean_token_accuracy": 0.21394875943660735,
|
|
"num_tokens": 58787457.0,
|
|
"step": 31940
|
|
},
|
|
{
|
|
"entropy": 5.443015146255493,
|
|
"epoch": 2.6683093885733378,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004286894477961541,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.22355760186910628,
|
|
"num_tokens": 58796671.0,
|
|
"step": 31945
|
|
},
|
|
{
|
|
"entropy": 5.4074578285217285,
|
|
"epoch": 2.6687270297360506,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042866770370004044,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.23879951238632202,
|
|
"num_tokens": 58805685.0,
|
|
"step": 31950
|
|
},
|
|
{
|
|
"entropy": 5.50084662437439,
|
|
"epoch": 2.669144670898764,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004286459569137886,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.21999227702617646,
|
|
"num_tokens": 58816453.0,
|
|
"step": 31955
|
|
},
|
|
{
|
|
"entropy": 5.3814362525939945,
|
|
"epoch": 2.6695623120614766,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004286242074377794,
|
|
"loss": 4.6134,
|
|
"mean_token_accuracy": 0.24136081486940383,
|
|
"num_tokens": 58825684.0,
|
|
"step": 31960
|
|
},
|
|
{
|
|
"entropy": 5.358729505538941,
|
|
"epoch": 2.66997995322419,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004286024552723935,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.23088269978761672,
|
|
"num_tokens": 58834481.0,
|
|
"step": 31965
|
|
},
|
|
{
|
|
"entropy": 5.321752214431763,
|
|
"epoch": 2.6703975943869027,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042858070041801175,
|
|
"loss": 4.6581,
|
|
"mean_token_accuracy": 0.23724394291639328,
|
|
"num_tokens": 58843631.0,
|
|
"step": 31970
|
|
},
|
|
{
|
|
"entropy": 5.41853289604187,
|
|
"epoch": 2.6708152355496155,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042855894287501493,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.22821198552846908,
|
|
"num_tokens": 58852415.0,
|
|
"step": 31975
|
|
},
|
|
{
|
|
"entropy": 5.427923631668091,
|
|
"epoch": 2.671232876712329,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042853718264378404,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.23591353744268417,
|
|
"num_tokens": 58862016.0,
|
|
"step": 31980
|
|
},
|
|
{
|
|
"entropy": 5.35386471748352,
|
|
"epoch": 2.671650517875042,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042851541972469996,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.23364635556936264,
|
|
"num_tokens": 58871163.0,
|
|
"step": 31985
|
|
},
|
|
{
|
|
"entropy": 5.4092553615570065,
|
|
"epoch": 2.672068159037755,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042849365411814355,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.2257334277033806,
|
|
"num_tokens": 58880075.0,
|
|
"step": 31990
|
|
},
|
|
{
|
|
"entropy": 5.388456106185913,
|
|
"epoch": 2.6724858002004677,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004284718858244961,
|
|
"loss": 4.657,
|
|
"mean_token_accuracy": 0.24103645533323287,
|
|
"num_tokens": 58887835.0,
|
|
"step": 31995
|
|
},
|
|
{
|
|
"entropy": 5.382199716567993,
|
|
"epoch": 2.672903441363181,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042845011484413846,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.2240549385547638,
|
|
"num_tokens": 58897085.0,
|
|
"step": 32000
|
|
},
|
|
{
|
|
"entropy": 5.290623664855957,
|
|
"epoch": 2.6733210825258937,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004284283411774519,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.2332237333059311,
|
|
"num_tokens": 58905768.0,
|
|
"step": 32005
|
|
},
|
|
{
|
|
"entropy": 5.501474189758301,
|
|
"epoch": 2.673738723688607,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042840656482481755,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.22255013585090638,
|
|
"num_tokens": 58915773.0,
|
|
"step": 32010
|
|
},
|
|
{
|
|
"entropy": 5.541213321685791,
|
|
"epoch": 2.67415636485132,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004283847857866167,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.22352199852466584,
|
|
"num_tokens": 58925586.0,
|
|
"step": 32015
|
|
},
|
|
{
|
|
"entropy": 5.466714668273926,
|
|
"epoch": 2.6745740060140326,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042836300406323035,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.22616318762302398,
|
|
"num_tokens": 58934777.0,
|
|
"step": 32020
|
|
},
|
|
{
|
|
"entropy": 5.351398134231568,
|
|
"epoch": 2.674991647176746,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00042834121965504014,
|
|
"loss": 4.7392,
|
|
"mean_token_accuracy": 0.22847728282213212,
|
|
"num_tokens": 58943825.0,
|
|
"step": 32025
|
|
},
|
|
{
|
|
"entropy": 5.429032468795777,
|
|
"epoch": 2.6754092883394587,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042831943256242726,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.23688563108444213,
|
|
"num_tokens": 58952880.0,
|
|
"step": 32030
|
|
},
|
|
{
|
|
"entropy": 5.453562450408936,
|
|
"epoch": 2.675826929502172,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004282976427857732,
|
|
"loss": 4.6946,
|
|
"mean_token_accuracy": 0.2316868245601654,
|
|
"num_tokens": 58962499.0,
|
|
"step": 32035
|
|
},
|
|
{
|
|
"entropy": 5.3699009895324705,
|
|
"epoch": 2.6762445706648847,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004282758503254594,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.2308954492211342,
|
|
"num_tokens": 58972184.0,
|
|
"step": 32040
|
|
},
|
|
{
|
|
"entropy": 5.398865461349487,
|
|
"epoch": 2.6766622118275976,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042825405518186725,
|
|
"loss": 4.6093,
|
|
"mean_token_accuracy": 0.2393256351351738,
|
|
"num_tokens": 58980638.0,
|
|
"step": 32045
|
|
},
|
|
{
|
|
"entropy": 5.4447540760040285,
|
|
"epoch": 2.677079852990311,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042823225735537845,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.21956534832715988,
|
|
"num_tokens": 58989821.0,
|
|
"step": 32050
|
|
},
|
|
{
|
|
"entropy": 5.421336078643799,
|
|
"epoch": 2.6774974941530236,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004282104568463745,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.23236604779958725,
|
|
"num_tokens": 58998444.0,
|
|
"step": 32055
|
|
},
|
|
{
|
|
"entropy": 5.407837152481079,
|
|
"epoch": 2.677915135315737,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004281886536552372,
|
|
"loss": 4.7785,
|
|
"mean_token_accuracy": 0.2270081728696823,
|
|
"num_tokens": 59007870.0,
|
|
"step": 32060
|
|
},
|
|
{
|
|
"entropy": 5.444981718063355,
|
|
"epoch": 2.6783327764784497,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000428166847782348,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.23409246802330017,
|
|
"num_tokens": 59017443.0,
|
|
"step": 32065
|
|
},
|
|
{
|
|
"entropy": 5.432879781723022,
|
|
"epoch": 2.6787504176411625,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004281450392280889,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.23064881414175034,
|
|
"num_tokens": 59027256.0,
|
|
"step": 32070
|
|
},
|
|
{
|
|
"entropy": 5.460900449752808,
|
|
"epoch": 2.6791680588038758,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004281232279928414,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.2271011158823967,
|
|
"num_tokens": 59036520.0,
|
|
"step": 32075
|
|
},
|
|
{
|
|
"entropy": 5.4584324836730955,
|
|
"epoch": 2.6795856999665886,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004281014140769875,
|
|
"loss": 4.8064,
|
|
"mean_token_accuracy": 0.22482476383447647,
|
|
"num_tokens": 59045823.0,
|
|
"step": 32080
|
|
},
|
|
{
|
|
"entropy": 5.444145059585571,
|
|
"epoch": 2.680003341129302,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042807959748090914,
|
|
"loss": 4.7445,
|
|
"mean_token_accuracy": 0.23087820559740066,
|
|
"num_tokens": 59055316.0,
|
|
"step": 32085
|
|
},
|
|
{
|
|
"entropy": 5.328996562957764,
|
|
"epoch": 2.6804209822920146,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004280577782049881,
|
|
"loss": 4.6689,
|
|
"mean_token_accuracy": 0.23452950417995452,
|
|
"num_tokens": 59064423.0,
|
|
"step": 32090
|
|
},
|
|
{
|
|
"entropy": 5.438174724578857,
|
|
"epoch": 2.6808386234547275,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042803595624960647,
|
|
"loss": 4.8606,
|
|
"mean_token_accuracy": 0.2161121651530266,
|
|
"num_tokens": 59074212.0,
|
|
"step": 32095
|
|
},
|
|
{
|
|
"entropy": 5.3940346240997314,
|
|
"epoch": 2.6812562646174407,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042801413161514613,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.23735784292221068,
|
|
"num_tokens": 59083098.0,
|
|
"step": 32100
|
|
},
|
|
{
|
|
"entropy": 5.418869209289551,
|
|
"epoch": 2.681673905780154,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042799230430198935,
|
|
"loss": 4.7543,
|
|
"mean_token_accuracy": 0.23328539878129959,
|
|
"num_tokens": 59091709.0,
|
|
"step": 32105
|
|
},
|
|
{
|
|
"entropy": 5.48459644317627,
|
|
"epoch": 2.6820915469428668,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000427970474310518,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.2297848105430603,
|
|
"num_tokens": 59100495.0,
|
|
"step": 32110
|
|
},
|
|
{
|
|
"entropy": 5.476607418060302,
|
|
"epoch": 2.6825091881055796,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042794864164111447,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.22060655504465104,
|
|
"num_tokens": 59109507.0,
|
|
"step": 32115
|
|
},
|
|
{
|
|
"entropy": 5.489801263809204,
|
|
"epoch": 2.682926829268293,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004279268062941608,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.2365238681435585,
|
|
"num_tokens": 59119132.0,
|
|
"step": 32120
|
|
},
|
|
{
|
|
"entropy": 5.464415597915649,
|
|
"epoch": 2.6833444704310057,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004279049682700394,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.22643856853246688,
|
|
"num_tokens": 59128049.0,
|
|
"step": 32125
|
|
},
|
|
{
|
|
"entropy": 5.473463869094848,
|
|
"epoch": 2.683762111593719,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042788312756913234,
|
|
"loss": 4.7424,
|
|
"mean_token_accuracy": 0.22333249747753142,
|
|
"num_tokens": 59137292.0,
|
|
"step": 32130
|
|
},
|
|
{
|
|
"entropy": 5.47728123664856,
|
|
"epoch": 2.6841797527564317,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004278612841918222,
|
|
"loss": 4.8174,
|
|
"mean_token_accuracy": 0.2248702183365822,
|
|
"num_tokens": 59146210.0,
|
|
"step": 32135
|
|
},
|
|
{
|
|
"entropy": 5.450788784027099,
|
|
"epoch": 2.6845973939191445,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004278394381384912,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.23281573355197907,
|
|
"num_tokens": 59155968.0,
|
|
"step": 32140
|
|
},
|
|
{
|
|
"entropy": 5.4802186489105225,
|
|
"epoch": 2.685015035081858,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042781758940952194,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.22958308160305024,
|
|
"num_tokens": 59165824.0,
|
|
"step": 32145
|
|
},
|
|
{
|
|
"entropy": 5.428841209411621,
|
|
"epoch": 2.6854326762445706,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004277957380052968,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.23934177905321122,
|
|
"num_tokens": 59174467.0,
|
|
"step": 32150
|
|
},
|
|
{
|
|
"entropy": 5.343202304840088,
|
|
"epoch": 2.685850317407284,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042777388392619835,
|
|
"loss": 4.6336,
|
|
"mean_token_accuracy": 0.23204592168331145,
|
|
"num_tokens": 59184159.0,
|
|
"step": 32155
|
|
},
|
|
{
|
|
"entropy": 5.414599943161011,
|
|
"epoch": 2.6862679585699967,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004277520271726092,
|
|
"loss": 4.758,
|
|
"mean_token_accuracy": 0.2292665034532547,
|
|
"num_tokens": 59193488.0,
|
|
"step": 32160
|
|
},
|
|
{
|
|
"entropy": 5.436441278457641,
|
|
"epoch": 2.6866855997327095,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004277301677449119,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.2291592001914978,
|
|
"num_tokens": 59203643.0,
|
|
"step": 32165
|
|
},
|
|
{
|
|
"entropy": 5.3646568775177,
|
|
"epoch": 2.6871032408954227,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042770830564348915,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.23836151957511903,
|
|
"num_tokens": 59212962.0,
|
|
"step": 32170
|
|
},
|
|
{
|
|
"entropy": 5.41069655418396,
|
|
"epoch": 2.6875208820581356,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042768644086872384,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.2227283626794815,
|
|
"num_tokens": 59222798.0,
|
|
"step": 32175
|
|
},
|
|
{
|
|
"entropy": 5.461535358428955,
|
|
"epoch": 2.687938523220849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004276645734209984,
|
|
"loss": 4.8195,
|
|
"mean_token_accuracy": 0.2295589804649353,
|
|
"num_tokens": 59232301.0,
|
|
"step": 32180
|
|
},
|
|
{
|
|
"entropy": 5.426508569717408,
|
|
"epoch": 2.6883561643835616,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000427642703300696,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.2292003944516182,
|
|
"num_tokens": 59241953.0,
|
|
"step": 32185
|
|
},
|
|
{
|
|
"entropy": 5.5367227554321286,
|
|
"epoch": 2.6887738055462744,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004276208305081993,
|
|
"loss": 4.825,
|
|
"mean_token_accuracy": 0.22088743895292282,
|
|
"num_tokens": 59251297.0,
|
|
"step": 32190
|
|
},
|
|
{
|
|
"entropy": 5.508566236495971,
|
|
"epoch": 2.6891914467089877,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004275989550438912,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.22938425689935685,
|
|
"num_tokens": 59260037.0,
|
|
"step": 32195
|
|
},
|
|
{
|
|
"entropy": 5.420720148086548,
|
|
"epoch": 2.6896090878717005,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004275770769081547,
|
|
"loss": 4.8271,
|
|
"mean_token_accuracy": 0.22264094054698944,
|
|
"num_tokens": 59269136.0,
|
|
"step": 32200
|
|
},
|
|
{
|
|
"entropy": 5.4297209739685055,
|
|
"epoch": 2.6900267290344138,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004275551961013729,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.22850022315979004,
|
|
"num_tokens": 59278211.0,
|
|
"step": 32205
|
|
},
|
|
{
|
|
"entropy": 5.474798011779785,
|
|
"epoch": 2.6904443701971266,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042753331262392866,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.2222692236304283,
|
|
"num_tokens": 59286596.0,
|
|
"step": 32210
|
|
},
|
|
{
|
|
"entropy": 5.416497707366943,
|
|
"epoch": 2.6908620113598394,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042751142647620515,
|
|
"loss": 4.6812,
|
|
"mean_token_accuracy": 0.22995756417512894,
|
|
"num_tokens": 59294893.0,
|
|
"step": 32215
|
|
},
|
|
{
|
|
"entropy": 5.397786235809326,
|
|
"epoch": 2.6912796525225526,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042748953765858565,
|
|
"loss": 4.7205,
|
|
"mean_token_accuracy": 0.23689034283161164,
|
|
"num_tokens": 59304621.0,
|
|
"step": 32220
|
|
},
|
|
{
|
|
"entropy": 5.422366094589234,
|
|
"epoch": 2.691697293685266,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004274676461714532,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.22575433552265167,
|
|
"num_tokens": 59313429.0,
|
|
"step": 32225
|
|
},
|
|
{
|
|
"entropy": 5.475253772735596,
|
|
"epoch": 2.6921149348479787,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042744575201519115,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.2136428877711296,
|
|
"num_tokens": 59323323.0,
|
|
"step": 32230
|
|
},
|
|
{
|
|
"entropy": 5.529261207580566,
|
|
"epoch": 2.6925325760106915,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042742385519018263,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.22368322163820267,
|
|
"num_tokens": 59333070.0,
|
|
"step": 32235
|
|
},
|
|
{
|
|
"entropy": 5.4876197338104244,
|
|
"epoch": 2.6929502171734048,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004274019556968111,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.22465800493955612,
|
|
"num_tokens": 59342303.0,
|
|
"step": 32240
|
|
},
|
|
{
|
|
"entropy": 5.3919148445129395,
|
|
"epoch": 2.6933678583361176,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042738005353545986,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.23461746871471406,
|
|
"num_tokens": 59351465.0,
|
|
"step": 32245
|
|
},
|
|
{
|
|
"entropy": 5.379517555236816,
|
|
"epoch": 2.693785499498831,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042735814870651235,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.22576892077922822,
|
|
"num_tokens": 59360696.0,
|
|
"step": 32250
|
|
},
|
|
{
|
|
"entropy": 5.408247756958008,
|
|
"epoch": 2.6942031406615436,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004273362412103521,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.22649952322244643,
|
|
"num_tokens": 59369819.0,
|
|
"step": 32255
|
|
},
|
|
{
|
|
"entropy": 5.429743432998658,
|
|
"epoch": 2.6946207818242565,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004273143310473625,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.2268100708723068,
|
|
"num_tokens": 59378599.0,
|
|
"step": 32260
|
|
},
|
|
{
|
|
"entropy": 5.449157810211181,
|
|
"epoch": 2.6950384229869697,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042729241821792726,
|
|
"loss": 4.7965,
|
|
"mean_token_accuracy": 0.2232994943857193,
|
|
"num_tokens": 59389598.0,
|
|
"step": 32265
|
|
},
|
|
{
|
|
"entropy": 5.466340208053589,
|
|
"epoch": 2.6954560641496825,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004272705027224299,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.22758531719446182,
|
|
"num_tokens": 59399279.0,
|
|
"step": 32270
|
|
},
|
|
{
|
|
"entropy": 5.404340076446533,
|
|
"epoch": 2.695873705312396,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004272485845612541,
|
|
"loss": 4.7493,
|
|
"mean_token_accuracy": 0.228022301197052,
|
|
"num_tokens": 59407601.0,
|
|
"step": 32275
|
|
},
|
|
{
|
|
"entropy": 5.456568908691406,
|
|
"epoch": 2.6962913464751086,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042722666373478356,
|
|
"loss": 4.7579,
|
|
"mean_token_accuracy": 0.23077490478754042,
|
|
"num_tokens": 59417177.0,
|
|
"step": 32280
|
|
},
|
|
{
|
|
"entropy": 5.409773683547973,
|
|
"epoch": 2.6967089876378214,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042720474024340204,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.23956024050712585,
|
|
"num_tokens": 59425370.0,
|
|
"step": 32285
|
|
},
|
|
{
|
|
"entropy": 5.429311466217041,
|
|
"epoch": 2.6971266288005347,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004271828140874934,
|
|
"loss": 4.7404,
|
|
"mean_token_accuracy": 0.23249354362487792,
|
|
"num_tokens": 59435272.0,
|
|
"step": 32290
|
|
},
|
|
{
|
|
"entropy": 5.40433349609375,
|
|
"epoch": 2.6975442699632475,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042716088526744127,
|
|
"loss": 4.7247,
|
|
"mean_token_accuracy": 0.2369535192847252,
|
|
"num_tokens": 59443962.0,
|
|
"step": 32295
|
|
},
|
|
{
|
|
"entropy": 5.353915691375732,
|
|
"epoch": 2.6979619111259607,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004271389537836299,
|
|
"loss": 4.6436,
|
|
"mean_token_accuracy": 0.24155512303113938,
|
|
"num_tokens": 59452758.0,
|
|
"step": 32300
|
|
},
|
|
{
|
|
"entropy": 5.459602499008179,
|
|
"epoch": 2.6983795522886735,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042711701963644283,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.2311217725276947,
|
|
"num_tokens": 59461280.0,
|
|
"step": 32305
|
|
},
|
|
{
|
|
"entropy": 5.4000067710876465,
|
|
"epoch": 2.6987971934513864,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00042709508282626424,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.2296201467514038,
|
|
"num_tokens": 59470231.0,
|
|
"step": 32310
|
|
},
|
|
{
|
|
"entropy": 5.458942651748657,
|
|
"epoch": 2.6992148346140996,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042707314335347827,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.22144837975502013,
|
|
"num_tokens": 59480788.0,
|
|
"step": 32315
|
|
},
|
|
{
|
|
"entropy": 5.468065452575684,
|
|
"epoch": 2.6996324757768124,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042705120121846877,
|
|
"loss": 4.8234,
|
|
"mean_token_accuracy": 0.22293221950531006,
|
|
"num_tokens": 59490920.0,
|
|
"step": 32320
|
|
},
|
|
{
|
|
"entropy": 5.425590085983276,
|
|
"epoch": 2.7000501169395257,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042702925642162,
|
|
"loss": 4.6774,
|
|
"mean_token_accuracy": 0.23469514548778533,
|
|
"num_tokens": 59499324.0,
|
|
"step": 32325
|
|
},
|
|
{
|
|
"entropy": 5.471005582809449,
|
|
"epoch": 2.7004677581022385,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042700730896331606,
|
|
"loss": 4.8176,
|
|
"mean_token_accuracy": 0.2242877885699272,
|
|
"num_tokens": 59508329.0,
|
|
"step": 32330
|
|
},
|
|
{
|
|
"entropy": 5.485252046585083,
|
|
"epoch": 2.7008853992649513,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004269853588439413,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.2307128593325615,
|
|
"num_tokens": 59516799.0,
|
|
"step": 32335
|
|
},
|
|
{
|
|
"entropy": 5.457732057571411,
|
|
"epoch": 2.7013030404276646,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042696340606387977,
|
|
"loss": 4.7529,
|
|
"mean_token_accuracy": 0.23001119047403334,
|
|
"num_tokens": 59526097.0,
|
|
"step": 32340
|
|
},
|
|
{
|
|
"entropy": 5.430255699157715,
|
|
"epoch": 2.701720681590378,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000426941450623516,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.21818379014730455,
|
|
"num_tokens": 59535287.0,
|
|
"step": 32345
|
|
},
|
|
{
|
|
"entropy": 5.502930974960327,
|
|
"epoch": 2.7021383227530906,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042691949252323427,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.22785204648971558,
|
|
"num_tokens": 59545232.0,
|
|
"step": 32350
|
|
},
|
|
{
|
|
"entropy": 5.42777304649353,
|
|
"epoch": 2.7025559639158034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004268975317634188,
|
|
"loss": 4.7772,
|
|
"mean_token_accuracy": 0.2329085126519203,
|
|
"num_tokens": 59553977.0,
|
|
"step": 32355
|
|
},
|
|
{
|
|
"entropy": 5.3618405818939205,
|
|
"epoch": 2.7029736050785167,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042687556834445435,
|
|
"loss": 4.7839,
|
|
"mean_token_accuracy": 0.22535396367311478,
|
|
"num_tokens": 59563027.0,
|
|
"step": 32360
|
|
},
|
|
{
|
|
"entropy": 5.345184564590454,
|
|
"epoch": 2.7033912462412295,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004268536022667252,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.23415356278419494,
|
|
"num_tokens": 59570943.0,
|
|
"step": 32365
|
|
},
|
|
{
|
|
"entropy": 5.452250957489014,
|
|
"epoch": 2.7038088874039428,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042683163353061595,
|
|
"loss": 4.8068,
|
|
"mean_token_accuracy": 0.22921504378318786,
|
|
"num_tokens": 59581323.0,
|
|
"step": 32370
|
|
},
|
|
{
|
|
"entropy": 5.3403349876403805,
|
|
"epoch": 2.7042265285666556,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042680966213651126,
|
|
"loss": 4.7326,
|
|
"mean_token_accuracy": 0.23134378343820572,
|
|
"num_tokens": 59590429.0,
|
|
"step": 32375
|
|
},
|
|
{
|
|
"entropy": 5.2689167022705075,
|
|
"epoch": 2.7046441697293684,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004267876880847956,
|
|
"loss": 4.5198,
|
|
"mean_token_accuracy": 0.25469638109207154,
|
|
"num_tokens": 59598547.0,
|
|
"step": 32380
|
|
},
|
|
{
|
|
"entropy": 5.47523980140686,
|
|
"epoch": 2.7050618108920816,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004267657113758538,
|
|
"loss": 4.7097,
|
|
"mean_token_accuracy": 0.22929637432098388,
|
|
"num_tokens": 59607807.0,
|
|
"step": 32385
|
|
},
|
|
{
|
|
"entropy": 5.4284826755523685,
|
|
"epoch": 2.7054794520547945,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042674373201007055,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.23271564245224,
|
|
"num_tokens": 59616591.0,
|
|
"step": 32390
|
|
},
|
|
{
|
|
"entropy": 5.406485748291016,
|
|
"epoch": 2.7058970932175077,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004267217499878306,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.23941934257745742,
|
|
"num_tokens": 59625162.0,
|
|
"step": 32395
|
|
},
|
|
{
|
|
"entropy": 5.398001718521118,
|
|
"epoch": 2.7063147343802205,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042669976530951883,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.23867933601140975,
|
|
"num_tokens": 59633776.0,
|
|
"step": 32400
|
|
},
|
|
{
|
|
"entropy": 5.460727214813232,
|
|
"epoch": 2.7067323755429333,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042667777797552003,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.2169395625591278,
|
|
"num_tokens": 59642439.0,
|
|
"step": 32405
|
|
},
|
|
{
|
|
"entropy": 5.460124826431274,
|
|
"epoch": 2.7071500167056466,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042665578798621915,
|
|
"loss": 4.7094,
|
|
"mean_token_accuracy": 0.2324140653014183,
|
|
"num_tokens": 59651241.0,
|
|
"step": 32410
|
|
},
|
|
{
|
|
"entropy": 5.496953678131104,
|
|
"epoch": 2.7075676578683594,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042663379534200113,
|
|
"loss": 4.8196,
|
|
"mean_token_accuracy": 0.21909418553113938,
|
|
"num_tokens": 59660577.0,
|
|
"step": 32415
|
|
},
|
|
{
|
|
"entropy": 5.379875659942627,
|
|
"epoch": 2.7079852990310727,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004266118000432511,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.23706575036048888,
|
|
"num_tokens": 59669256.0,
|
|
"step": 32420
|
|
},
|
|
{
|
|
"entropy": 5.378234004974365,
|
|
"epoch": 2.7084029401937855,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042658980209035394,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.2399098053574562,
|
|
"num_tokens": 59678240.0,
|
|
"step": 32425
|
|
},
|
|
{
|
|
"entropy": 5.496398687362671,
|
|
"epoch": 2.7088205813564983,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042656780148369477,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.215800142288208,
|
|
"num_tokens": 59688519.0,
|
|
"step": 32430
|
|
},
|
|
{
|
|
"entropy": 5.5265453338623045,
|
|
"epoch": 2.7092382225192115,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004265457982236589,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.22457510083913804,
|
|
"num_tokens": 59697482.0,
|
|
"step": 32435
|
|
},
|
|
{
|
|
"entropy": 5.495690965652466,
|
|
"epoch": 2.7096558636819243,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004265237923106314,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.22451904267072678,
|
|
"num_tokens": 59706893.0,
|
|
"step": 32440
|
|
},
|
|
{
|
|
"entropy": 5.386654806137085,
|
|
"epoch": 2.7100735048446376,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042650178374499753,
|
|
"loss": 4.6449,
|
|
"mean_token_accuracy": 0.2378942623734474,
|
|
"num_tokens": 59715678.0,
|
|
"step": 32445
|
|
},
|
|
{
|
|
"entropy": 5.4010350704193115,
|
|
"epoch": 2.7104911460073504,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042647977252714247,
|
|
"loss": 4.6502,
|
|
"mean_token_accuracy": 0.23965227007865905,
|
|
"num_tokens": 59724818.0,
|
|
"step": 32450
|
|
},
|
|
{
|
|
"entropy": 5.304353713989258,
|
|
"epoch": 2.7109087871700632,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004264577586574518,
|
|
"loss": 4.6401,
|
|
"mean_token_accuracy": 0.22952704429626464,
|
|
"num_tokens": 59733341.0,
|
|
"step": 32455
|
|
},
|
|
{
|
|
"entropy": 5.42564435005188,
|
|
"epoch": 2.7113264283327765,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042643574213631065,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.22934530526399613,
|
|
"num_tokens": 59742504.0,
|
|
"step": 32460
|
|
},
|
|
{
|
|
"entropy": 5.487045860290527,
|
|
"epoch": 2.7117440694954897,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004264137229641046,
|
|
"loss": 4.6721,
|
|
"mean_token_accuracy": 0.23897803276777269,
|
|
"num_tokens": 59751749.0,
|
|
"step": 32465
|
|
},
|
|
{
|
|
"entropy": 5.4613744735717775,
|
|
"epoch": 2.7121617106582026,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000426391701141219,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.22620781064033507,
|
|
"num_tokens": 59761045.0,
|
|
"step": 32470
|
|
},
|
|
{
|
|
"entropy": 5.400437498092652,
|
|
"epoch": 2.7125793518209154,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00042636967666803954,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.23331323117017747,
|
|
"num_tokens": 59770147.0,
|
|
"step": 32475
|
|
},
|
|
{
|
|
"entropy": 5.428000974655151,
|
|
"epoch": 2.7129969929836286,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042634764954495167,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.228806833922863,
|
|
"num_tokens": 59779624.0,
|
|
"step": 32480
|
|
},
|
|
{
|
|
"entropy": 5.552933311462402,
|
|
"epoch": 2.7134146341463414,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042632561977234095,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.22081844061613082,
|
|
"num_tokens": 59789366.0,
|
|
"step": 32485
|
|
},
|
|
{
|
|
"entropy": 5.459925889968872,
|
|
"epoch": 2.7138322753090547,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004263035873505932,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.22630944699048997,
|
|
"num_tokens": 59798043.0,
|
|
"step": 32490
|
|
},
|
|
{
|
|
"entropy": 5.440889883041382,
|
|
"epoch": 2.7142499164717675,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004262815522800939,
|
|
"loss": 4.7888,
|
|
"mean_token_accuracy": 0.22712805718183518,
|
|
"num_tokens": 59807207.0,
|
|
"step": 32495
|
|
},
|
|
{
|
|
"entropy": 5.376827907562256,
|
|
"epoch": 2.7146675576344803,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004262595145612291,
|
|
"loss": 4.6184,
|
|
"mean_token_accuracy": 0.24031611382961274,
|
|
"num_tokens": 59817004.0,
|
|
"step": 32500
|
|
},
|
|
{
|
|
"entropy": 5.413744735717773,
|
|
"epoch": 2.7150851987971936,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042623747419438427,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.22849223166704177,
|
|
"num_tokens": 59825714.0,
|
|
"step": 32505
|
|
},
|
|
{
|
|
"entropy": 5.460908269882202,
|
|
"epoch": 2.7155028399599064,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004262154311799455,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.22949152886867524,
|
|
"num_tokens": 59834410.0,
|
|
"step": 32510
|
|
},
|
|
{
|
|
"entropy": 5.459351015090943,
|
|
"epoch": 2.7159204811226196,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004261933855182985,
|
|
"loss": 4.7589,
|
|
"mean_token_accuracy": 0.2336454600095749,
|
|
"num_tokens": 59843629.0,
|
|
"step": 32515
|
|
},
|
|
{
|
|
"entropy": 5.450310564041137,
|
|
"epoch": 2.7163381222853324,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042617133720982943,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.2217938095331192,
|
|
"num_tokens": 59852902.0,
|
|
"step": 32520
|
|
},
|
|
{
|
|
"entropy": 5.4750278949737545,
|
|
"epoch": 2.7167557634480453,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042614928625492397,
|
|
"loss": 4.8168,
|
|
"mean_token_accuracy": 0.22066746801137924,
|
|
"num_tokens": 59861434.0,
|
|
"step": 32525
|
|
},
|
|
{
|
|
"entropy": 5.4105407238006595,
|
|
"epoch": 2.7171734046107585,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042612723265396846,
|
|
"loss": 4.7417,
|
|
"mean_token_accuracy": 0.2281976044178009,
|
|
"num_tokens": 59871591.0,
|
|
"step": 32530
|
|
},
|
|
{
|
|
"entropy": 5.3535877704620365,
|
|
"epoch": 2.7175910457734713,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004261051764073488,
|
|
"loss": 4.617,
|
|
"mean_token_accuracy": 0.24405760765075685,
|
|
"num_tokens": 59880615.0,
|
|
"step": 32535
|
|
},
|
|
{
|
|
"entropy": 5.446588182449341,
|
|
"epoch": 2.7180086869361846,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042608311751545115,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.23002767115831374,
|
|
"num_tokens": 59889558.0,
|
|
"step": 32540
|
|
},
|
|
{
|
|
"entropy": 5.435208559036255,
|
|
"epoch": 2.7184263280988974,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042606105597866163,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.23411190658807754,
|
|
"num_tokens": 59897794.0,
|
|
"step": 32545
|
|
},
|
|
{
|
|
"entropy": 5.453890228271485,
|
|
"epoch": 2.71884396926161,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004260389917973665,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.22369581311941147,
|
|
"num_tokens": 59908074.0,
|
|
"step": 32550
|
|
},
|
|
{
|
|
"entropy": 5.395512104034424,
|
|
"epoch": 2.7192616104243235,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000426016924971952,
|
|
"loss": 4.7129,
|
|
"mean_token_accuracy": 0.22830307632684707,
|
|
"num_tokens": 59916986.0,
|
|
"step": 32555
|
|
},
|
|
{
|
|
"entropy": 5.400221920013427,
|
|
"epoch": 2.7196792515870363,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042599485550280446,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.23951339572668076,
|
|
"num_tokens": 59925539.0,
|
|
"step": 32560
|
|
},
|
|
{
|
|
"entropy": 5.453431224822998,
|
|
"epoch": 2.7200968927497495,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042597278339031024,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.22827242016792298,
|
|
"num_tokens": 59933732.0,
|
|
"step": 32565
|
|
},
|
|
{
|
|
"entropy": 5.365598344802857,
|
|
"epoch": 2.7205145339124623,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004259507086348557,
|
|
"loss": 4.6764,
|
|
"mean_token_accuracy": 0.24206455647945405,
|
|
"num_tokens": 59942217.0,
|
|
"step": 32570
|
|
},
|
|
{
|
|
"entropy": 5.453941726684571,
|
|
"epoch": 2.720932175075175,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042592863123682735,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.2277915894985199,
|
|
"num_tokens": 59951750.0,
|
|
"step": 32575
|
|
},
|
|
{
|
|
"entropy": 5.484683799743652,
|
|
"epoch": 2.7213498162378884,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004259065511966116,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.21938928812742234,
|
|
"num_tokens": 59961054.0,
|
|
"step": 32580
|
|
},
|
|
{
|
|
"entropy": 5.428251552581787,
|
|
"epoch": 2.7217674574006017,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000425884468514595,
|
|
"loss": 4.811,
|
|
"mean_token_accuracy": 0.21833496689796447,
|
|
"num_tokens": 59971345.0,
|
|
"step": 32585
|
|
},
|
|
{
|
|
"entropy": 5.382559204101563,
|
|
"epoch": 2.7221850985633145,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042586238319116423,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.23741691410541535,
|
|
"num_tokens": 59980919.0,
|
|
"step": 32590
|
|
},
|
|
{
|
|
"entropy": 5.44204044342041,
|
|
"epoch": 2.7226027397260273,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042584029522670574,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.2342733472585678,
|
|
"num_tokens": 59990881.0,
|
|
"step": 32595
|
|
},
|
|
{
|
|
"entropy": 5.519461393356323,
|
|
"epoch": 2.7230203808887405,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004258182046216064,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.22800659835338594,
|
|
"num_tokens": 60000556.0,
|
|
"step": 32600
|
|
},
|
|
{
|
|
"entropy": 5.461036586761475,
|
|
"epoch": 2.7234380220514534,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004257961113762528,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.23031457364559174,
|
|
"num_tokens": 60009674.0,
|
|
"step": 32605
|
|
},
|
|
{
|
|
"entropy": 5.433201313018799,
|
|
"epoch": 2.7238556632141666,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004257740154910318,
|
|
"loss": 4.7686,
|
|
"mean_token_accuracy": 0.22488052994012833,
|
|
"num_tokens": 60019915.0,
|
|
"step": 32610
|
|
},
|
|
{
|
|
"entropy": 5.477294111251831,
|
|
"epoch": 2.7242733043768794,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004257519169663302,
|
|
"loss": 4.8078,
|
|
"mean_token_accuracy": 0.22397722750902177,
|
|
"num_tokens": 60029384.0,
|
|
"step": 32615
|
|
},
|
|
{
|
|
"entropy": 5.419218635559082,
|
|
"epoch": 2.7246909455395922,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042572981580253475,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.23020431995391846,
|
|
"num_tokens": 60038763.0,
|
|
"step": 32620
|
|
},
|
|
{
|
|
"entropy": 5.440821123123169,
|
|
"epoch": 2.7251085867023055,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042570771200003255,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.2288417786359787,
|
|
"num_tokens": 60048131.0,
|
|
"step": 32625
|
|
},
|
|
{
|
|
"entropy": 5.377781391143799,
|
|
"epoch": 2.7255262278650183,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042568560555921033,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.23061842620372772,
|
|
"num_tokens": 60056962.0,
|
|
"step": 32630
|
|
},
|
|
{
|
|
"entropy": 5.449056005477905,
|
|
"epoch": 2.7259438690277316,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004256634964804553,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.23000657707452773,
|
|
"num_tokens": 60066818.0,
|
|
"step": 32635
|
|
},
|
|
{
|
|
"entropy": 5.470345783233642,
|
|
"epoch": 2.7263615101904444,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042564138476415433,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.22734445780515672,
|
|
"num_tokens": 60075635.0,
|
|
"step": 32640
|
|
},
|
|
{
|
|
"entropy": 5.481350374221802,
|
|
"epoch": 2.726779151353157,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042561927041069467,
|
|
"loss": 4.8279,
|
|
"mean_token_accuracy": 0.2285577729344368,
|
|
"num_tokens": 60084531.0,
|
|
"step": 32645
|
|
},
|
|
{
|
|
"entropy": 5.458984327316284,
|
|
"epoch": 2.7271967925158704,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042559715342046334,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.23078854233026505,
|
|
"num_tokens": 60092992.0,
|
|
"step": 32650
|
|
},
|
|
{
|
|
"entropy": 5.443885612487793,
|
|
"epoch": 2.7276144336785833,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004255750337938475,
|
|
"loss": 4.7293,
|
|
"mean_token_accuracy": 0.2333437457680702,
|
|
"num_tokens": 60101804.0,
|
|
"step": 32655
|
|
},
|
|
{
|
|
"entropy": 5.489739274978637,
|
|
"epoch": 2.7280320748412965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042555291153123455,
|
|
"loss": 4.8029,
|
|
"mean_token_accuracy": 0.22242973148822784,
|
|
"num_tokens": 60111417.0,
|
|
"step": 32660
|
|
},
|
|
{
|
|
"entropy": 5.399100399017334,
|
|
"epoch": 2.7284497160040093,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042553078663301163,
|
|
"loss": 4.67,
|
|
"mean_token_accuracy": 0.2358178436756134,
|
|
"num_tokens": 60120154.0,
|
|
"step": 32665
|
|
},
|
|
{
|
|
"entropy": 5.517854881286621,
|
|
"epoch": 2.728867357166722,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042550865909956606,
|
|
"loss": 4.8242,
|
|
"mean_token_accuracy": 0.22255531698465347,
|
|
"num_tokens": 60128762.0,
|
|
"step": 32670
|
|
},
|
|
{
|
|
"entropy": 5.3780663967132565,
|
|
"epoch": 2.7292849983294354,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042548652893128526,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.22862303406000137,
|
|
"num_tokens": 60138091.0,
|
|
"step": 32675
|
|
},
|
|
{
|
|
"entropy": 5.418385982513428,
|
|
"epoch": 2.729702639492148,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004254643961285567,
|
|
"loss": 4.6964,
|
|
"mean_token_accuracy": 0.23698006123304366,
|
|
"num_tokens": 60146937.0,
|
|
"step": 32680
|
|
},
|
|
{
|
|
"entropy": 5.407784557342529,
|
|
"epoch": 2.7301202806548615,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042544226069176765,
|
|
"loss": 4.7005,
|
|
"mean_token_accuracy": 0.23572575449943542,
|
|
"num_tokens": 60155790.0,
|
|
"step": 32685
|
|
},
|
|
{
|
|
"entropy": 5.335832118988037,
|
|
"epoch": 2.7305379218175743,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004254201226213059,
|
|
"loss": 4.678,
|
|
"mean_token_accuracy": 0.23162378668785094,
|
|
"num_tokens": 60165620.0,
|
|
"step": 32690
|
|
},
|
|
{
|
|
"entropy": 5.423841524124145,
|
|
"epoch": 2.730955562980287,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004253979819175587,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.2322519302368164,
|
|
"num_tokens": 60175544.0,
|
|
"step": 32695
|
|
},
|
|
{
|
|
"entropy": 5.505679368972778,
|
|
"epoch": 2.7313732041430003,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042537583858091383,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.21859996020793915,
|
|
"num_tokens": 60184177.0,
|
|
"step": 32700
|
|
},
|
|
{
|
|
"entropy": 5.374436378479004,
|
|
"epoch": 2.7317908453057136,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004253536926117589,
|
|
"loss": 4.6636,
|
|
"mean_token_accuracy": 0.23779192119836806,
|
|
"num_tokens": 60192417.0,
|
|
"step": 32705
|
|
},
|
|
{
|
|
"entropy": 5.4619968891143795,
|
|
"epoch": 2.7322084864684264,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004253315440104816,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.22831991612911223,
|
|
"num_tokens": 60201679.0,
|
|
"step": 32710
|
|
},
|
|
{
|
|
"entropy": 5.439006757736206,
|
|
"epoch": 2.732626127631139,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042530939277746964,
|
|
"loss": 4.7565,
|
|
"mean_token_accuracy": 0.2368316262960434,
|
|
"num_tokens": 60210228.0,
|
|
"step": 32715
|
|
},
|
|
{
|
|
"entropy": 5.361882066726684,
|
|
"epoch": 2.7330437687938525,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004252872389131109,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.22940310835838318,
|
|
"num_tokens": 60218958.0,
|
|
"step": 32720
|
|
},
|
|
{
|
|
"entropy": 5.39995584487915,
|
|
"epoch": 2.7334614099565653,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004252650824177931,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.2317496955394745,
|
|
"num_tokens": 60228490.0,
|
|
"step": 32725
|
|
},
|
|
{
|
|
"entropy": 5.51305775642395,
|
|
"epoch": 2.7338790511192785,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004252429232919042,
|
|
"loss": 4.808,
|
|
"mean_token_accuracy": 0.22710608690977097,
|
|
"num_tokens": 60238289.0,
|
|
"step": 32730
|
|
},
|
|
{
|
|
"entropy": 5.360678434371948,
|
|
"epoch": 2.7342966922819913,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000425220761535832,
|
|
"loss": 4.627,
|
|
"mean_token_accuracy": 0.23485117703676223,
|
|
"num_tokens": 60247731.0,
|
|
"step": 32735
|
|
},
|
|
{
|
|
"entropy": 5.560712146759033,
|
|
"epoch": 2.734714333444704,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004251985971499647,
|
|
"loss": 4.9095,
|
|
"mean_token_accuracy": 0.2236405000090599,
|
|
"num_tokens": 60257073.0,
|
|
"step": 32740
|
|
},
|
|
{
|
|
"entropy": 5.430507707595825,
|
|
"epoch": 2.7351319746074174,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042517643013469,
|
|
"loss": 4.6141,
|
|
"mean_token_accuracy": 0.2438857525587082,
|
|
"num_tokens": 60265354.0,
|
|
"step": 32745
|
|
},
|
|
{
|
|
"entropy": 5.489490175247193,
|
|
"epoch": 2.7355496157701302,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004251542604903962,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.21876829713582993,
|
|
"num_tokens": 60275456.0,
|
|
"step": 32750
|
|
},
|
|
{
|
|
"entropy": 5.4471066951751705,
|
|
"epoch": 2.7359672569328435,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004251320882174713,
|
|
"loss": 4.8709,
|
|
"mean_token_accuracy": 0.2160676658153534,
|
|
"num_tokens": 60284051.0,
|
|
"step": 32755
|
|
},
|
|
{
|
|
"entropy": 5.43744421005249,
|
|
"epoch": 2.7363848980955563,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004251099133163035,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.22438902854919435,
|
|
"num_tokens": 60293590.0,
|
|
"step": 32760
|
|
},
|
|
{
|
|
"entropy": 5.49513840675354,
|
|
"epoch": 2.736802539258269,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000425087735787281,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.22880372703075408,
|
|
"num_tokens": 60302107.0,
|
|
"step": 32765
|
|
},
|
|
{
|
|
"entropy": 5.474967288970947,
|
|
"epoch": 2.7372201804209824,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042506555563079194,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.2343543753027916,
|
|
"num_tokens": 60311212.0,
|
|
"step": 32770
|
|
},
|
|
{
|
|
"entropy": 5.4514776229858395,
|
|
"epoch": 2.737637821583695,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004250433728472248,
|
|
"loss": 4.7661,
|
|
"mean_token_accuracy": 0.23065460622310638,
|
|
"num_tokens": 60320282.0,
|
|
"step": 32775
|
|
},
|
|
{
|
|
"entropy": 5.4770444393157955,
|
|
"epoch": 2.7380554627464084,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004250211874369678,
|
|
"loss": 4.7543,
|
|
"mean_token_accuracy": 0.23140043765306473,
|
|
"num_tokens": 60328386.0,
|
|
"step": 32780
|
|
},
|
|
{
|
|
"entropy": 5.472996091842651,
|
|
"epoch": 2.7384731039091212,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004249989994004093,
|
|
"loss": 4.7794,
|
|
"mean_token_accuracy": 0.2231406167149544,
|
|
"num_tokens": 60338210.0,
|
|
"step": 32785
|
|
},
|
|
{
|
|
"entropy": 5.449555253982544,
|
|
"epoch": 2.738890745071834,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042497680873793776,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.23818451166152954,
|
|
"num_tokens": 60347347.0,
|
|
"step": 32790
|
|
},
|
|
{
|
|
"entropy": 5.474704265594482,
|
|
"epoch": 2.7393083862345473,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004249546154499416,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.22561423778533934,
|
|
"num_tokens": 60356211.0,
|
|
"step": 32795
|
|
},
|
|
{
|
|
"entropy": 5.459455776214599,
|
|
"epoch": 2.73972602739726,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042493241953680947,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.22636576294898986,
|
|
"num_tokens": 60365678.0,
|
|
"step": 32800
|
|
},
|
|
{
|
|
"entropy": 5.480133676528931,
|
|
"epoch": 2.7401436685599734,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042491022099892985,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.22789292186498641,
|
|
"num_tokens": 60375243.0,
|
|
"step": 32805
|
|
},
|
|
{
|
|
"entropy": 5.446429824829101,
|
|
"epoch": 2.740561309722686,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004248880198366913,
|
|
"loss": 4.7803,
|
|
"mean_token_accuracy": 0.23220909386873245,
|
|
"num_tokens": 60385087.0,
|
|
"step": 32810
|
|
},
|
|
{
|
|
"entropy": 5.4270713329315186,
|
|
"epoch": 2.740978950885399,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004248658160504827,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.23434729725122452,
|
|
"num_tokens": 60394340.0,
|
|
"step": 32815
|
|
},
|
|
{
|
|
"entropy": 5.497195720672607,
|
|
"epoch": 2.7413965920481123,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042484360964069247,
|
|
"loss": 4.7508,
|
|
"mean_token_accuracy": 0.22797499746084213,
|
|
"num_tokens": 60404537.0,
|
|
"step": 32820
|
|
},
|
|
{
|
|
"entropy": 5.319706296920776,
|
|
"epoch": 2.7418142332108255,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004248214006077095,
|
|
"loss": 4.6194,
|
|
"mean_token_accuracy": 0.2339175432920456,
|
|
"num_tokens": 60414124.0,
|
|
"step": 32825
|
|
},
|
|
{
|
|
"entropy": 5.333511304855347,
|
|
"epoch": 2.7422318743735383,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042479918895192253,
|
|
"loss": 4.6055,
|
|
"mean_token_accuracy": 0.23762009143829346,
|
|
"num_tokens": 60422719.0,
|
|
"step": 32830
|
|
},
|
|
{
|
|
"entropy": 5.382656192779541,
|
|
"epoch": 2.742649515536251,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042477697467372056,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.23646707236766815,
|
|
"num_tokens": 60430877.0,
|
|
"step": 32835
|
|
},
|
|
{
|
|
"entropy": 5.4058637619018555,
|
|
"epoch": 2.7430671566989644,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042475475777349234,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.23099207729101182,
|
|
"num_tokens": 60440320.0,
|
|
"step": 32840
|
|
},
|
|
{
|
|
"entropy": 5.406830739974976,
|
|
"epoch": 2.743484797861677,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042473253825162674,
|
|
"loss": 4.661,
|
|
"mean_token_accuracy": 0.2336544081568718,
|
|
"num_tokens": 60449442.0,
|
|
"step": 32845
|
|
},
|
|
{
|
|
"entropy": 5.421196365356446,
|
|
"epoch": 2.7439024390243905,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004247103161085129,
|
|
"loss": 4.683,
|
|
"mean_token_accuracy": 0.2381543755531311,
|
|
"num_tokens": 60458176.0,
|
|
"step": 32850
|
|
},
|
|
{
|
|
"entropy": 5.398896932601929,
|
|
"epoch": 2.7443200801871033,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042468809134453973,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.23046116083860396,
|
|
"num_tokens": 60466842.0,
|
|
"step": 32855
|
|
},
|
|
{
|
|
"entropy": 5.425730276107788,
|
|
"epoch": 2.744737721349816,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004246658639600963,
|
|
"loss": 4.7349,
|
|
"mean_token_accuracy": 0.234592005610466,
|
|
"num_tokens": 60475591.0,
|
|
"step": 32860
|
|
},
|
|
{
|
|
"entropy": 5.4372735023498535,
|
|
"epoch": 2.7451553625125293,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004246436339555719,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.23268225491046907,
|
|
"num_tokens": 60485263.0,
|
|
"step": 32865
|
|
},
|
|
{
|
|
"entropy": 5.409551286697388,
|
|
"epoch": 2.745573003675242,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042462140133135544,
|
|
"loss": 4.7198,
|
|
"mean_token_accuracy": 0.23430089205503463,
|
|
"num_tokens": 60494256.0,
|
|
"step": 32870
|
|
},
|
|
{
|
|
"entropy": 5.333911180496216,
|
|
"epoch": 2.7459906448379554,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004245991660878363,
|
|
"loss": 4.6306,
|
|
"mean_token_accuracy": 0.23962439149618148,
|
|
"num_tokens": 60502920.0,
|
|
"step": 32875
|
|
},
|
|
{
|
|
"entropy": 5.375351810455323,
|
|
"epoch": 2.746408286000668,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004245769282254037,
|
|
"loss": 4.6452,
|
|
"mean_token_accuracy": 0.23808274418115616,
|
|
"num_tokens": 60511827.0,
|
|
"step": 32880
|
|
},
|
|
{
|
|
"entropy": 5.509831666946411,
|
|
"epoch": 2.746825927163381,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042455468774444695,
|
|
"loss": 4.8111,
|
|
"mean_token_accuracy": 0.22550977617502213,
|
|
"num_tokens": 60521602.0,
|
|
"step": 32885
|
|
},
|
|
{
|
|
"entropy": 5.411307954788208,
|
|
"epoch": 2.7472435683260943,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042453244464535524,
|
|
"loss": 4.6055,
|
|
"mean_token_accuracy": 0.23931146115064622,
|
|
"num_tokens": 60531016.0,
|
|
"step": 32890
|
|
},
|
|
{
|
|
"entropy": 5.413117408752441,
|
|
"epoch": 2.747661209488807,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004245101989285182,
|
|
"loss": 4.7069,
|
|
"mean_token_accuracy": 0.23361075967550277,
|
|
"num_tokens": 60540112.0,
|
|
"step": 32895
|
|
},
|
|
{
|
|
"entropy": 5.3618861675262455,
|
|
"epoch": 2.7480788506515204,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004244879505943252,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.23552263230085374,
|
|
"num_tokens": 60549577.0,
|
|
"step": 32900
|
|
},
|
|
{
|
|
"entropy": 5.466446781158448,
|
|
"epoch": 2.748496491814233,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042446569964316557,
|
|
"loss": 4.7927,
|
|
"mean_token_accuracy": 0.22531332522630693,
|
|
"num_tokens": 60558874.0,
|
|
"step": 32905
|
|
},
|
|
{
|
|
"entropy": 5.471700763702392,
|
|
"epoch": 2.748914132976946,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000424443446075429,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.22934701442718505,
|
|
"num_tokens": 60568252.0,
|
|
"step": 32910
|
|
},
|
|
{
|
|
"entropy": 5.392409181594848,
|
|
"epoch": 2.7493317741396592,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004244211898915051,
|
|
"loss": 4.5982,
|
|
"mean_token_accuracy": 0.2373628184199333,
|
|
"num_tokens": 60577184.0,
|
|
"step": 32915
|
|
},
|
|
{
|
|
"entropy": 5.357753419876099,
|
|
"epoch": 2.749749415302372,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004243989310917833,
|
|
"loss": 4.7025,
|
|
"mean_token_accuracy": 0.23039115369319915,
|
|
"num_tokens": 60585679.0,
|
|
"step": 32920
|
|
},
|
|
{
|
|
"entropy": 5.374269151687622,
|
|
"epoch": 2.7501670564650853,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042437666967665345,
|
|
"loss": 4.752,
|
|
"mean_token_accuracy": 0.2309184893965721,
|
|
"num_tokens": 60595010.0,
|
|
"step": 32925
|
|
},
|
|
{
|
|
"entropy": 5.425641298294067,
|
|
"epoch": 2.750584697627798,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042435440564650526,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.22883764952421187,
|
|
"num_tokens": 60604240.0,
|
|
"step": 32930
|
|
},
|
|
{
|
|
"entropy": 5.456607818603516,
|
|
"epoch": 2.751002338790511,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004243321390017283,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.22780599147081376,
|
|
"num_tokens": 60613817.0,
|
|
"step": 32935
|
|
},
|
|
{
|
|
"entropy": 5.456977033615113,
|
|
"epoch": 2.751419979953224,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004243098697427125,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.22624539732933044,
|
|
"num_tokens": 60622366.0,
|
|
"step": 32940
|
|
},
|
|
{
|
|
"entropy": 5.416637754440307,
|
|
"epoch": 2.7518376211159374,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042428759786984773,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.23291873037815095,
|
|
"num_tokens": 60630906.0,
|
|
"step": 32945
|
|
},
|
|
{
|
|
"entropy": 5.3540589809417725,
|
|
"epoch": 2.7522552622786502,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004242653233835239,
|
|
"loss": 4.6903,
|
|
"mean_token_accuracy": 0.23626415878534318,
|
|
"num_tokens": 60640920.0,
|
|
"step": 32950
|
|
},
|
|
{
|
|
"entropy": 5.433735275268555,
|
|
"epoch": 2.752672903441363,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042424304628413086,
|
|
"loss": 4.7196,
|
|
"mean_token_accuracy": 0.23409203588962554,
|
|
"num_tokens": 60650194.0,
|
|
"step": 32955
|
|
},
|
|
{
|
|
"entropy": 5.527790832519531,
|
|
"epoch": 2.7530905446040763,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004242207665720587,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.21642821729183198,
|
|
"num_tokens": 60659824.0,
|
|
"step": 32960
|
|
},
|
|
{
|
|
"entropy": 5.447765254974366,
|
|
"epoch": 2.753508185766789,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042419848424769737,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.2295029267668724,
|
|
"num_tokens": 60669298.0,
|
|
"step": 32965
|
|
},
|
|
{
|
|
"entropy": 5.419130134582519,
|
|
"epoch": 2.7539258269295024,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000424176199311437,
|
|
"loss": 4.7349,
|
|
"mean_token_accuracy": 0.22872669249773026,
|
|
"num_tokens": 60679491.0,
|
|
"step": 32970
|
|
},
|
|
{
|
|
"entropy": 5.499425888061523,
|
|
"epoch": 2.754343468092215,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042415391176366763,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.2221421033143997,
|
|
"num_tokens": 60688975.0,
|
|
"step": 32975
|
|
},
|
|
{
|
|
"entropy": 5.3930501461029055,
|
|
"epoch": 2.754761109254928,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004241316216047796,
|
|
"loss": 4.679,
|
|
"mean_token_accuracy": 0.23032561540603638,
|
|
"num_tokens": 60697914.0,
|
|
"step": 32980
|
|
},
|
|
{
|
|
"entropy": 5.4073292255401615,
|
|
"epoch": 2.7551787504176413,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042410932883516297,
|
|
"loss": 4.6581,
|
|
"mean_token_accuracy": 0.24051516652107238,
|
|
"num_tokens": 60706690.0,
|
|
"step": 32985
|
|
},
|
|
{
|
|
"entropy": 5.389511442184448,
|
|
"epoch": 2.755596391580354,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004240870334552081,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.22526548504829408,
|
|
"num_tokens": 60715377.0,
|
|
"step": 32990
|
|
},
|
|
{
|
|
"entropy": 5.427191066741943,
|
|
"epoch": 2.7560140327430673,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042406473546530523,
|
|
"loss": 4.7334,
|
|
"mean_token_accuracy": 0.23837073296308517,
|
|
"num_tokens": 60724021.0,
|
|
"step": 32995
|
|
},
|
|
{
|
|
"entropy": 5.44439172744751,
|
|
"epoch": 2.75643167390578,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042404243486584463,
|
|
"loss": 4.8269,
|
|
"mean_token_accuracy": 0.224353888630867,
|
|
"num_tokens": 60733174.0,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"epoch": 2.75643167390578,
|
|
"eval_entropy": 5.0947631533634254,
|
|
"eval_loss": 4.746384143829346,
|
|
"eval_mean_token_accuracy": 0.2414254041590243,
|
|
"eval_num_tokens": 60733174.0,
|
|
"eval_runtime": 20.8494,
|
|
"eval_samples_per_second": 1811.226,
|
|
"eval_steps_per_second": 226.433,
|
|
"step": 33000
|
|
},
|
|
{
|
|
"entropy": 5.495709800720215,
|
|
"epoch": 2.756849315068493,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042402013165721697,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.23508381545543672,
|
|
"num_tokens": 60742133.0,
|
|
"step": 33005
|
|
},
|
|
{
|
|
"entropy": 5.400050306320191,
|
|
"epoch": 2.757266956231206,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042399782583981246,
|
|
"loss": 4.6616,
|
|
"mean_token_accuracy": 0.23909589201211928,
|
|
"num_tokens": 60751411.0,
|
|
"step": 33010
|
|
},
|
|
{
|
|
"entropy": 5.401443099975586,
|
|
"epoch": 2.757684597393919,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004239755174140216,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.22415843605995178,
|
|
"num_tokens": 60760348.0,
|
|
"step": 33015
|
|
},
|
|
{
|
|
"entropy": 5.485536098480225,
|
|
"epoch": 2.7581022385566323,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042395320638023503,
|
|
"loss": 4.8663,
|
|
"mean_token_accuracy": 0.22408373653888702,
|
|
"num_tokens": 60770956.0,
|
|
"step": 33020
|
|
},
|
|
{
|
|
"entropy": 5.43631420135498,
|
|
"epoch": 2.758519879719345,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042393089273884334,
|
|
"loss": 4.6354,
|
|
"mean_token_accuracy": 0.23588058352470398,
|
|
"num_tokens": 60780035.0,
|
|
"step": 33025
|
|
},
|
|
{
|
|
"entropy": 5.392746782302856,
|
|
"epoch": 2.758937520882058,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004239085764902371,
|
|
"loss": 4.652,
|
|
"mean_token_accuracy": 0.23695774823427201,
|
|
"num_tokens": 60788776.0,
|
|
"step": 33030
|
|
},
|
|
{
|
|
"entropy": 5.418508052825928,
|
|
"epoch": 2.759355162044771,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000423886257634807,
|
|
"loss": 4.7508,
|
|
"mean_token_accuracy": 0.22382327169179916,
|
|
"num_tokens": 60798997.0,
|
|
"step": 33035
|
|
},
|
|
{
|
|
"entropy": 5.394012832641602,
|
|
"epoch": 2.759772803207484,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004238639361729436,
|
|
"loss": 4.705,
|
|
"mean_token_accuracy": 0.23092301338911056,
|
|
"num_tokens": 60808210.0,
|
|
"step": 33040
|
|
},
|
|
{
|
|
"entropy": 5.483762598037719,
|
|
"epoch": 2.7601904443701972,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042384161210503793,
|
|
"loss": 4.7885,
|
|
"mean_token_accuracy": 0.23366443812847137,
|
|
"num_tokens": 60817085.0,
|
|
"step": 33045
|
|
},
|
|
{
|
|
"entropy": 5.4550862312316895,
|
|
"epoch": 2.76060808553291,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042381928543148067,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.2255952924489975,
|
|
"num_tokens": 60825655.0,
|
|
"step": 33050
|
|
},
|
|
{
|
|
"entropy": 5.514960622787475,
|
|
"epoch": 2.761025726695623,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004237969561526627,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.22372699528932571,
|
|
"num_tokens": 60834614.0,
|
|
"step": 33055
|
|
},
|
|
{
|
|
"entropy": 5.512369632720947,
|
|
"epoch": 2.761443367858336,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042377462426897486,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.2187386706471443,
|
|
"num_tokens": 60844125.0,
|
|
"step": 33060
|
|
},
|
|
{
|
|
"entropy": 5.491197872161865,
|
|
"epoch": 2.7618610090210494,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042375228978080813,
|
|
"loss": 4.8038,
|
|
"mean_token_accuracy": 0.22898170500993728,
|
|
"num_tokens": 60853890.0,
|
|
"step": 33065
|
|
},
|
|
{
|
|
"entropy": 5.440730619430542,
|
|
"epoch": 2.762278650183762,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042372995268855356,
|
|
"loss": 4.7299,
|
|
"mean_token_accuracy": 0.22952430844306945,
|
|
"num_tokens": 60863291.0,
|
|
"step": 33070
|
|
},
|
|
{
|
|
"entropy": 5.330861616134643,
|
|
"epoch": 2.762696291346475,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004237076129926022,
|
|
"loss": 4.5723,
|
|
"mean_token_accuracy": 0.24494338035583496,
|
|
"num_tokens": 60871567.0,
|
|
"step": 33075
|
|
},
|
|
{
|
|
"entropy": 5.418831729888916,
|
|
"epoch": 2.7631139325091882,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042368527069334494,
|
|
"loss": 4.8368,
|
|
"mean_token_accuracy": 0.22070488780736924,
|
|
"num_tokens": 60881490.0,
|
|
"step": 33080
|
|
},
|
|
{
|
|
"entropy": 5.399544286727905,
|
|
"epoch": 2.763531573671901,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004236629257911731,
|
|
"loss": 4.6719,
|
|
"mean_token_accuracy": 0.23674714118242263,
|
|
"num_tokens": 60890258.0,
|
|
"step": 33085
|
|
},
|
|
{
|
|
"entropy": 5.441626262664795,
|
|
"epoch": 2.7639492148346143,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004236405782864778,
|
|
"loss": 4.6827,
|
|
"mean_token_accuracy": 0.24001528918743134,
|
|
"num_tokens": 60898813.0,
|
|
"step": 33090
|
|
},
|
|
{
|
|
"entropy": 5.44432225227356,
|
|
"epoch": 2.764366855997327,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004236182281796503,
|
|
"loss": 4.7354,
|
|
"mean_token_accuracy": 0.23368222862482071,
|
|
"num_tokens": 60907175.0,
|
|
"step": 33095
|
|
},
|
|
{
|
|
"entropy": 5.375434827804566,
|
|
"epoch": 2.76478449716004,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004235958754710818,
|
|
"loss": 4.6763,
|
|
"mean_token_accuracy": 0.2423104926943779,
|
|
"num_tokens": 60916302.0,
|
|
"step": 33100
|
|
},
|
|
{
|
|
"entropy": 5.352597045898437,
|
|
"epoch": 2.765202138322753,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004235735201611636,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.2337867096066475,
|
|
"num_tokens": 60926364.0,
|
|
"step": 33105
|
|
},
|
|
{
|
|
"entropy": 5.403194999694824,
|
|
"epoch": 2.765619779485466,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004235511622502871,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.22847364395856856,
|
|
"num_tokens": 60935900.0,
|
|
"step": 33110
|
|
},
|
|
{
|
|
"entropy": 5.484148550033569,
|
|
"epoch": 2.7660374206481793,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004235288017388437,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.2324792340397835,
|
|
"num_tokens": 60945089.0,
|
|
"step": 33115
|
|
},
|
|
{
|
|
"entropy": 5.45942792892456,
|
|
"epoch": 2.766455061810892,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042350643862722485,
|
|
"loss": 4.6582,
|
|
"mean_token_accuracy": 0.22936524152755738,
|
|
"num_tokens": 60953836.0,
|
|
"step": 33120
|
|
},
|
|
{
|
|
"entropy": 5.516995668411255,
|
|
"epoch": 2.766872702973605,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042348407291582216,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.22012866884469987,
|
|
"num_tokens": 60964284.0,
|
|
"step": 33125
|
|
},
|
|
{
|
|
"entropy": 5.463539934158325,
|
|
"epoch": 2.767290344136318,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004234617046050268,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.22612233012914656,
|
|
"num_tokens": 60974080.0,
|
|
"step": 33130
|
|
},
|
|
{
|
|
"entropy": 5.409484434127807,
|
|
"epoch": 2.767707985299031,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004234393336952308,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.2350718155503273,
|
|
"num_tokens": 60983052.0,
|
|
"step": 33135
|
|
},
|
|
{
|
|
"entropy": 5.3775963306427,
|
|
"epoch": 2.768125626461744,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004234169601868255,
|
|
"loss": 4.7495,
|
|
"mean_token_accuracy": 0.23522440493106841,
|
|
"num_tokens": 60991889.0,
|
|
"step": 33140
|
|
},
|
|
{
|
|
"entropy": 5.4197381973266605,
|
|
"epoch": 2.768543267624457,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042339458408020267,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.23402654528617858,
|
|
"num_tokens": 60999632.0,
|
|
"step": 33145
|
|
},
|
|
{
|
|
"entropy": 5.479872369766236,
|
|
"epoch": 2.76896090878717,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042337220537575393,
|
|
"loss": 4.7766,
|
|
"mean_token_accuracy": 0.22505978494882584,
|
|
"num_tokens": 61008562.0,
|
|
"step": 33150
|
|
},
|
|
{
|
|
"entropy": 5.513475513458252,
|
|
"epoch": 2.769378549949883,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004233498240738713,
|
|
"loss": 4.9084,
|
|
"mean_token_accuracy": 0.21624882519245148,
|
|
"num_tokens": 61017771.0,
|
|
"step": 33155
|
|
},
|
|
{
|
|
"entropy": 5.440673780441284,
|
|
"epoch": 2.769796191112596,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042332744017494633,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.22702165246009826,
|
|
"num_tokens": 61026726.0,
|
|
"step": 33160
|
|
},
|
|
{
|
|
"entropy": 5.384874582290649,
|
|
"epoch": 2.770213832275309,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000423305053679371,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.23177667260169982,
|
|
"num_tokens": 61035845.0,
|
|
"step": 33165
|
|
},
|
|
{
|
|
"entropy": 5.377288341522217,
|
|
"epoch": 2.770631473438022,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004232826645875372,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.23291835337877273,
|
|
"num_tokens": 61045030.0,
|
|
"step": 33170
|
|
},
|
|
{
|
|
"entropy": 5.439267778396607,
|
|
"epoch": 2.7710491146007348,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042326027289983685,
|
|
"loss": 4.8128,
|
|
"mean_token_accuracy": 0.22633379697799683,
|
|
"num_tokens": 61054913.0,
|
|
"step": 33175
|
|
},
|
|
{
|
|
"entropy": 5.4669270515441895,
|
|
"epoch": 2.771466755763448,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042323787861666204,
|
|
"loss": 4.8226,
|
|
"mean_token_accuracy": 0.2238104373216629,
|
|
"num_tokens": 61063933.0,
|
|
"step": 33180
|
|
},
|
|
{
|
|
"entropy": 5.525402545928955,
|
|
"epoch": 2.7718843969261613,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042321548173840465,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.21829794049263002,
|
|
"num_tokens": 61074082.0,
|
|
"step": 33185
|
|
},
|
|
{
|
|
"entropy": 5.601138257980347,
|
|
"epoch": 2.772302038088874,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004231930822654569,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.2134447067975998,
|
|
"num_tokens": 61083739.0,
|
|
"step": 33190
|
|
},
|
|
{
|
|
"entropy": 5.511513900756836,
|
|
"epoch": 2.772719679251587,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042317068019821075,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.2201155826449394,
|
|
"num_tokens": 61092677.0,
|
|
"step": 33195
|
|
},
|
|
{
|
|
"entropy": 5.399616956710815,
|
|
"epoch": 2.7731373204143,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004231482755370586,
|
|
"loss": 4.7502,
|
|
"mean_token_accuracy": 0.22454276829957961,
|
|
"num_tokens": 61101573.0,
|
|
"step": 33200
|
|
},
|
|
{
|
|
"entropy": 5.370667552947998,
|
|
"epoch": 2.773554961577013,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042312586828239254,
|
|
"loss": 4.7359,
|
|
"mean_token_accuracy": 0.23264486491680145,
|
|
"num_tokens": 61112068.0,
|
|
"step": 33205
|
|
},
|
|
{
|
|
"entropy": 5.501892709732056,
|
|
"epoch": 2.7739726027397262,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004231034584346048,
|
|
"loss": 4.7823,
|
|
"mean_token_accuracy": 0.23295338153839112,
|
|
"num_tokens": 61120358.0,
|
|
"step": 33210
|
|
},
|
|
{
|
|
"entropy": 5.429426860809326,
|
|
"epoch": 2.774390243902439,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042308104599408783,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.23694044053554536,
|
|
"num_tokens": 61129115.0,
|
|
"step": 33215
|
|
},
|
|
{
|
|
"entropy": 5.39046277999878,
|
|
"epoch": 2.774807885065152,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004230586309612339,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.22847985476255417,
|
|
"num_tokens": 61137665.0,
|
|
"step": 33220
|
|
},
|
|
{
|
|
"entropy": 5.346419811248779,
|
|
"epoch": 2.775225526227865,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004230362133364354,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.2301655188202858,
|
|
"num_tokens": 61146969.0,
|
|
"step": 33225
|
|
},
|
|
{
|
|
"entropy": 5.468424510955811,
|
|
"epoch": 2.775643167390578,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042301379312008477,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.23252363055944442,
|
|
"num_tokens": 61157157.0,
|
|
"step": 33230
|
|
},
|
|
{
|
|
"entropy": 5.463711547851562,
|
|
"epoch": 2.776060808553291,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004229913703125745,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.22539781928062438,
|
|
"num_tokens": 61165822.0,
|
|
"step": 33235
|
|
},
|
|
{
|
|
"entropy": 5.347081851959229,
|
|
"epoch": 2.776478449716004,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042296894491429716,
|
|
"loss": 4.6295,
|
|
"mean_token_accuracy": 0.23388551771640778,
|
|
"num_tokens": 61174323.0,
|
|
"step": 33240
|
|
},
|
|
{
|
|
"entropy": 5.429993677139282,
|
|
"epoch": 2.776896090878717,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004229465169256454,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.23190235942602158,
|
|
"num_tokens": 61182674.0,
|
|
"step": 33245
|
|
},
|
|
{
|
|
"entropy": 5.372732067108155,
|
|
"epoch": 2.77731373204143,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042292408634701166,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.221816286444664,
|
|
"num_tokens": 61192314.0,
|
|
"step": 33250
|
|
},
|
|
{
|
|
"entropy": 5.388928604125977,
|
|
"epoch": 2.777731373204143,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004229016531787889,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.2473736047744751,
|
|
"num_tokens": 61201105.0,
|
|
"step": 33255
|
|
},
|
|
{
|
|
"entropy": 5.428817224502564,
|
|
"epoch": 2.778149014366856,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042287921742136957,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.23277933597564698,
|
|
"num_tokens": 61210779.0,
|
|
"step": 33260
|
|
},
|
|
{
|
|
"entropy": 5.44574294090271,
|
|
"epoch": 2.778566655529569,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042285677907514656,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.23256296962499617,
|
|
"num_tokens": 61220271.0,
|
|
"step": 33265
|
|
},
|
|
{
|
|
"entropy": 5.456341361999511,
|
|
"epoch": 2.7789842966922818,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042283433814051263,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.22954341769218445,
|
|
"num_tokens": 61230122.0,
|
|
"step": 33270
|
|
},
|
|
{
|
|
"entropy": 5.547919273376465,
|
|
"epoch": 2.779401937854995,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042281189461786074,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.21944978088140488,
|
|
"num_tokens": 61239662.0,
|
|
"step": 33275
|
|
},
|
|
{
|
|
"entropy": 5.503703308105469,
|
|
"epoch": 2.779819579017708,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004227894485075837,
|
|
"loss": 4.76,
|
|
"mean_token_accuracy": 0.22802115678787233,
|
|
"num_tokens": 61249084.0,
|
|
"step": 33280
|
|
},
|
|
{
|
|
"entropy": 5.45844407081604,
|
|
"epoch": 2.780237220180421,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004227669998100744,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.23872262090444565,
|
|
"num_tokens": 61258409.0,
|
|
"step": 33285
|
|
},
|
|
{
|
|
"entropy": 5.401421642303466,
|
|
"epoch": 2.780654861343134,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042274454852572583,
|
|
"loss": 4.7618,
|
|
"mean_token_accuracy": 0.23136370480060578,
|
|
"num_tokens": 61267154.0,
|
|
"step": 33290
|
|
},
|
|
{
|
|
"entropy": 5.307435607910156,
|
|
"epoch": 2.7810725025058467,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042272209465493124,
|
|
"loss": 4.7083,
|
|
"mean_token_accuracy": 0.23517477065324782,
|
|
"num_tokens": 61276676.0,
|
|
"step": 33295
|
|
},
|
|
{
|
|
"entropy": 5.488946151733399,
|
|
"epoch": 2.78149014366856,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004226996381980835,
|
|
"loss": 4.7927,
|
|
"mean_token_accuracy": 0.22870563119649887,
|
|
"num_tokens": 61286772.0,
|
|
"step": 33300
|
|
},
|
|
{
|
|
"entropy": 5.483941841125488,
|
|
"epoch": 2.781907784831273,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004226771791555758,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.22682220190763475,
|
|
"num_tokens": 61296367.0,
|
|
"step": 33305
|
|
},
|
|
{
|
|
"entropy": 5.38672947883606,
|
|
"epoch": 2.782325425993986,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004226547175278014,
|
|
"loss": 4.6129,
|
|
"mean_token_accuracy": 0.23000577837228775,
|
|
"num_tokens": 61304684.0,
|
|
"step": 33310
|
|
},
|
|
{
|
|
"entropy": 5.414334678649903,
|
|
"epoch": 2.782743067156699,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004226322533151534,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.23717360943555832,
|
|
"num_tokens": 61313498.0,
|
|
"step": 33315
|
|
},
|
|
{
|
|
"entropy": 5.427906274795532,
|
|
"epoch": 2.783160708319412,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004226097865180251,
|
|
"loss": 4.7705,
|
|
"mean_token_accuracy": 0.22875715494155885,
|
|
"num_tokens": 61323581.0,
|
|
"step": 33320
|
|
},
|
|
{
|
|
"entropy": 5.430377435684204,
|
|
"epoch": 2.783578349482125,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042258731713680974,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.23285626471042634,
|
|
"num_tokens": 61332652.0,
|
|
"step": 33325
|
|
},
|
|
{
|
|
"entropy": 5.480805778503418,
|
|
"epoch": 2.783995990644838,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004225648451719008,
|
|
"loss": 4.7617,
|
|
"mean_token_accuracy": 0.22891125679016114,
|
|
"num_tokens": 61342889.0,
|
|
"step": 33330
|
|
},
|
|
{
|
|
"entropy": 5.410197591781616,
|
|
"epoch": 2.784413631807551,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004225423706236917,
|
|
"loss": 4.6435,
|
|
"mean_token_accuracy": 0.2285031259059906,
|
|
"num_tokens": 61351752.0,
|
|
"step": 33335
|
|
},
|
|
{
|
|
"entropy": 5.466511964797974,
|
|
"epoch": 2.784831272970264,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004225198934925757,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.2246442586183548,
|
|
"num_tokens": 61361738.0,
|
|
"step": 33340
|
|
},
|
|
{
|
|
"entropy": 5.504147291183472,
|
|
"epoch": 2.785248914132977,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004224974137789464,
|
|
"loss": 4.8259,
|
|
"mean_token_accuracy": 0.22791751325130463,
|
|
"num_tokens": 61371356.0,
|
|
"step": 33345
|
|
},
|
|
{
|
|
"entropy": 5.461645984649659,
|
|
"epoch": 2.78566655529569,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004224749314831973,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.23211933076381683,
|
|
"num_tokens": 61380361.0,
|
|
"step": 33350
|
|
},
|
|
{
|
|
"entropy": 5.4062371253967285,
|
|
"epoch": 2.786084196458403,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004224524466057221,
|
|
"loss": 4.7509,
|
|
"mean_token_accuracy": 0.2357277512550354,
|
|
"num_tokens": 61390012.0,
|
|
"step": 33355
|
|
},
|
|
{
|
|
"entropy": 5.3504949569702145,
|
|
"epoch": 2.786501837621116,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004224299591469143,
|
|
"loss": 4.6311,
|
|
"mean_token_accuracy": 0.2371895432472229,
|
|
"num_tokens": 61398885.0,
|
|
"step": 33360
|
|
},
|
|
{
|
|
"entropy": 5.475194597244263,
|
|
"epoch": 2.7869194787838287,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004224074691071676,
|
|
"loss": 4.7847,
|
|
"mean_token_accuracy": 0.2331683963537216,
|
|
"num_tokens": 61407903.0,
|
|
"step": 33365
|
|
},
|
|
{
|
|
"entropy": 5.446944999694824,
|
|
"epoch": 2.787337119946542,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042238497648687567,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.22995753288269044,
|
|
"num_tokens": 61415985.0,
|
|
"step": 33370
|
|
},
|
|
{
|
|
"entropy": 5.399547863006592,
|
|
"epoch": 2.787754761109255,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042236248128643244,
|
|
"loss": 4.6621,
|
|
"mean_token_accuracy": 0.2434764251112938,
|
|
"num_tokens": 61425497.0,
|
|
"step": 33375
|
|
},
|
|
{
|
|
"entropy": 5.375925779342651,
|
|
"epoch": 2.788172402271968,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004223399835062315,
|
|
"loss": 4.7363,
|
|
"mean_token_accuracy": 0.22353924065828323,
|
|
"num_tokens": 61434356.0,
|
|
"step": 33380
|
|
},
|
|
{
|
|
"entropy": 5.344713258743286,
|
|
"epoch": 2.788590043434681,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042231748314666684,
|
|
"loss": 4.6201,
|
|
"mean_token_accuracy": 0.2444722592830658,
|
|
"num_tokens": 61443515.0,
|
|
"step": 33385
|
|
},
|
|
{
|
|
"entropy": 5.428676319122315,
|
|
"epoch": 2.7890076845973937,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004222949802081323,
|
|
"loss": 4.8056,
|
|
"mean_token_accuracy": 0.22994106113910676,
|
|
"num_tokens": 61453038.0,
|
|
"step": 33390
|
|
},
|
|
{
|
|
"entropy": 5.560382509231568,
|
|
"epoch": 2.789425325760107,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042227247469102175,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.2150271102786064,
|
|
"num_tokens": 61463121.0,
|
|
"step": 33395
|
|
},
|
|
{
|
|
"entropy": 5.556697607040405,
|
|
"epoch": 2.78984296692282,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004222499665957294,
|
|
"loss": 4.8396,
|
|
"mean_token_accuracy": 0.22241674661636351,
|
|
"num_tokens": 61473278.0,
|
|
"step": 33400
|
|
},
|
|
{
|
|
"entropy": 5.35151777267456,
|
|
"epoch": 2.790260608085533,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042222745592264903,
|
|
"loss": 4.6453,
|
|
"mean_token_accuracy": 0.24362739324569702,
|
|
"num_tokens": 61481886.0,
|
|
"step": 33405
|
|
},
|
|
{
|
|
"entropy": 5.395909929275513,
|
|
"epoch": 2.790678249248246,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042220494267217483,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.22451921552419662,
|
|
"num_tokens": 61491321.0,
|
|
"step": 33410
|
|
},
|
|
{
|
|
"entropy": 5.464831829071045,
|
|
"epoch": 2.791095890410959,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000422182426844701,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.23254866003990174,
|
|
"num_tokens": 61500735.0,
|
|
"step": 33415
|
|
},
|
|
{
|
|
"entropy": 5.348952960968018,
|
|
"epoch": 2.791513531573672,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004221599084406216,
|
|
"loss": 4.6648,
|
|
"mean_token_accuracy": 0.23299601674079895,
|
|
"num_tokens": 61509301.0,
|
|
"step": 33420
|
|
},
|
|
{
|
|
"entropy": 5.394913101196289,
|
|
"epoch": 2.791931172736385,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004221373874603308,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.22928172051906587,
|
|
"num_tokens": 61517924.0,
|
|
"step": 33425
|
|
},
|
|
{
|
|
"entropy": 5.455283689498901,
|
|
"epoch": 2.792348813899098,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00042211486390422297,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.2284949913620949,
|
|
"num_tokens": 61526779.0,
|
|
"step": 33430
|
|
},
|
|
{
|
|
"entropy": 5.454493236541748,
|
|
"epoch": 2.7927664550618108,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042209233777269235,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.2297800213098526,
|
|
"num_tokens": 61535086.0,
|
|
"step": 33435
|
|
},
|
|
{
|
|
"entropy": 5.532036256790161,
|
|
"epoch": 2.793184096224524,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00042206980906613333,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.2251140892505646,
|
|
"num_tokens": 61544781.0,
|
|
"step": 33440
|
|
},
|
|
{
|
|
"entropy": 5.463252449035645,
|
|
"epoch": 2.793601737387237,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004220472777849403,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.22298696190118789,
|
|
"num_tokens": 61553525.0,
|
|
"step": 33445
|
|
},
|
|
{
|
|
"entropy": 5.414364194869995,
|
|
"epoch": 2.79401937854995,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042202474392950763,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.22948024719953536,
|
|
"num_tokens": 61563461.0,
|
|
"step": 33450
|
|
},
|
|
{
|
|
"entropy": 5.381535148620605,
|
|
"epoch": 2.794437019712663,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004220022075002298,
|
|
"loss": 4.693,
|
|
"mean_token_accuracy": 0.2348783180117607,
|
|
"num_tokens": 61572796.0,
|
|
"step": 33455
|
|
},
|
|
{
|
|
"entropy": 5.481488752365112,
|
|
"epoch": 2.7948546608753757,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004219796684975014,
|
|
"loss": 4.8134,
|
|
"mean_token_accuracy": 0.2280736446380615,
|
|
"num_tokens": 61583378.0,
|
|
"step": 33460
|
|
},
|
|
{
|
|
"entropy": 5.490743494033813,
|
|
"epoch": 2.795272302038089,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042195712692171705,
|
|
"loss": 4.6762,
|
|
"mean_token_accuracy": 0.23686252981424333,
|
|
"num_tokens": 61592548.0,
|
|
"step": 33465
|
|
},
|
|
{
|
|
"entropy": 5.417566776275635,
|
|
"epoch": 2.7956899432008018,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004219345827732712,
|
|
"loss": 4.7826,
|
|
"mean_token_accuracy": 0.227620168030262,
|
|
"num_tokens": 61601824.0,
|
|
"step": 33470
|
|
},
|
|
{
|
|
"entropy": 5.399462938308716,
|
|
"epoch": 2.796107584363515,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004219120360525588,
|
|
"loss": 4.774,
|
|
"mean_token_accuracy": 0.2249727427959442,
|
|
"num_tokens": 61610661.0,
|
|
"step": 33475
|
|
},
|
|
{
|
|
"entropy": 5.508162975311279,
|
|
"epoch": 2.796525225526228,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004218894867599742,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.22615938186645507,
|
|
"num_tokens": 61619767.0,
|
|
"step": 33480
|
|
},
|
|
{
|
|
"entropy": 5.496485376358033,
|
|
"epoch": 2.7969428666889407,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042186693489591244,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.22410755902528762,
|
|
"num_tokens": 61628814.0,
|
|
"step": 33485
|
|
},
|
|
{
|
|
"entropy": 5.460276079177857,
|
|
"epoch": 2.797360507851654,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004218443804607681,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.22228437215089797,
|
|
"num_tokens": 61637371.0,
|
|
"step": 33490
|
|
},
|
|
{
|
|
"entropy": 5.396058654785156,
|
|
"epoch": 2.7977781490143667,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042182182345493614,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.23757508099079133,
|
|
"num_tokens": 61647524.0,
|
|
"step": 33495
|
|
},
|
|
{
|
|
"entropy": 5.420983791351318,
|
|
"epoch": 2.79819579017708,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004217992638788114,
|
|
"loss": 4.7616,
|
|
"mean_token_accuracy": 0.22267068177461624,
|
|
"num_tokens": 61657017.0,
|
|
"step": 33500
|
|
},
|
|
{
|
|
"entropy": 5.422987079620361,
|
|
"epoch": 2.798613431339793,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004217767017327889,
|
|
"loss": 4.7055,
|
|
"mean_token_accuracy": 0.2290121152997017,
|
|
"num_tokens": 61666292.0,
|
|
"step": 33505
|
|
},
|
|
{
|
|
"entropy": 5.39193024635315,
|
|
"epoch": 2.7990310725025056,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004217541370172635,
|
|
"loss": 4.637,
|
|
"mean_token_accuracy": 0.24779886454343797,
|
|
"num_tokens": 61675827.0,
|
|
"step": 33510
|
|
},
|
|
{
|
|
"entropy": 5.419218873977661,
|
|
"epoch": 2.799448713665219,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042173156973263044,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.22576598972082138,
|
|
"num_tokens": 61685551.0,
|
|
"step": 33515
|
|
},
|
|
{
|
|
"entropy": 5.366899538040161,
|
|
"epoch": 2.799866354827932,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004217089998792845,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.22841031700372696,
|
|
"num_tokens": 61695621.0,
|
|
"step": 33520
|
|
},
|
|
{
|
|
"entropy": 5.433220672607422,
|
|
"epoch": 2.800283995990645,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004216864274576209,
|
|
"loss": 4.7782,
|
|
"mean_token_accuracy": 0.23299862295389176,
|
|
"num_tokens": 61704111.0,
|
|
"step": 33525
|
|
},
|
|
{
|
|
"entropy": 5.426457834243775,
|
|
"epoch": 2.8007016371533577,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004216638524680349,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.2301204338669777,
|
|
"num_tokens": 61713002.0,
|
|
"step": 33530
|
|
},
|
|
{
|
|
"entropy": 5.505002069473266,
|
|
"epoch": 2.801119278316071,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042164127491092155,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.22347741723060607,
|
|
"num_tokens": 61723504.0,
|
|
"step": 33535
|
|
},
|
|
{
|
|
"entropy": 5.537602853775025,
|
|
"epoch": 2.801536919478784,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004216186947866762,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.22911435663700103,
|
|
"num_tokens": 61732097.0,
|
|
"step": 33540
|
|
},
|
|
{
|
|
"entropy": 5.333215284347534,
|
|
"epoch": 2.801954560641497,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042159611209569416,
|
|
"loss": 4.561,
|
|
"mean_token_accuracy": 0.24885254353284836,
|
|
"num_tokens": 61741178.0,
|
|
"step": 33545
|
|
},
|
|
{
|
|
"entropy": 5.468288135528565,
|
|
"epoch": 2.80237220180421,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042157352683837063,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.22392159551382065,
|
|
"num_tokens": 61750491.0,
|
|
"step": 33550
|
|
},
|
|
{
|
|
"entropy": 5.477854061126709,
|
|
"epoch": 2.8027898429669227,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004215509390151012,
|
|
"loss": 4.7612,
|
|
"mean_token_accuracy": 0.22509251683950424,
|
|
"num_tokens": 61759853.0,
|
|
"step": 33555
|
|
},
|
|
{
|
|
"entropy": 5.4986261367797855,
|
|
"epoch": 2.803207484129636,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000421528348626281,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.22525855749845505,
|
|
"num_tokens": 61769912.0,
|
|
"step": 33560
|
|
},
|
|
{
|
|
"entropy": 5.442655849456787,
|
|
"epoch": 2.8036251252923488,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042150575567230584,
|
|
"loss": 4.6888,
|
|
"mean_token_accuracy": 0.23863814920186996,
|
|
"num_tokens": 61778771.0,
|
|
"step": 33565
|
|
},
|
|
{
|
|
"entropy": 5.466619634628296,
|
|
"epoch": 2.804042766455062,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042148316015357107,
|
|
"loss": 4.8297,
|
|
"mean_token_accuracy": 0.2262602612376213,
|
|
"num_tokens": 61788158.0,
|
|
"step": 33570
|
|
},
|
|
{
|
|
"entropy": 5.4725292205810545,
|
|
"epoch": 2.804460407617775,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004214605620704722,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.23199591040611267,
|
|
"num_tokens": 61797041.0,
|
|
"step": 33575
|
|
},
|
|
{
|
|
"entropy": 5.433987188339233,
|
|
"epoch": 2.8048780487804876,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042143796142340496,
|
|
"loss": 4.7588,
|
|
"mean_token_accuracy": 0.2251203715801239,
|
|
"num_tokens": 61806288.0,
|
|
"step": 33580
|
|
},
|
|
{
|
|
"entropy": 5.343543004989624,
|
|
"epoch": 2.805295689943201,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042141535821276497,
|
|
"loss": 4.5691,
|
|
"mean_token_accuracy": 0.23906662613153457,
|
|
"num_tokens": 61814446.0,
|
|
"step": 33585
|
|
},
|
|
{
|
|
"entropy": 5.393551254272461,
|
|
"epoch": 2.8057133311059137,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042139275243894777,
|
|
"loss": 4.699,
|
|
"mean_token_accuracy": 0.23497755378484725,
|
|
"num_tokens": 61823270.0,
|
|
"step": 33590
|
|
},
|
|
{
|
|
"entropy": 5.501671218872071,
|
|
"epoch": 2.806130972268627,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042137014410234926,
|
|
"loss": 4.8494,
|
|
"mean_token_accuracy": 0.2180665299296379,
|
|
"num_tokens": 61832390.0,
|
|
"step": 33595
|
|
},
|
|
{
|
|
"entropy": 5.437448740005493,
|
|
"epoch": 2.8065486134313398,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042134753320336517,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.22464732974767684,
|
|
"num_tokens": 61842205.0,
|
|
"step": 33600
|
|
},
|
|
{
|
|
"entropy": 5.496826791763306,
|
|
"epoch": 2.8069662545940526,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004213249197423914,
|
|
"loss": 4.7839,
|
|
"mean_token_accuracy": 0.23150747418403625,
|
|
"num_tokens": 61851188.0,
|
|
"step": 33605
|
|
},
|
|
{
|
|
"entropy": 5.457132720947266,
|
|
"epoch": 2.807383895756766,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004213023037198238,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.23633160442113876,
|
|
"num_tokens": 61859044.0,
|
|
"step": 33610
|
|
},
|
|
{
|
|
"entropy": 5.37388048171997,
|
|
"epoch": 2.8078015369194786,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042127968513605823,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.23423778861761094,
|
|
"num_tokens": 61868454.0,
|
|
"step": 33615
|
|
},
|
|
{
|
|
"entropy": 5.474864482879639,
|
|
"epoch": 2.808219178082192,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042125706399149073,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.22343826591968535,
|
|
"num_tokens": 61878174.0,
|
|
"step": 33620
|
|
},
|
|
{
|
|
"entropy": 5.363915252685547,
|
|
"epoch": 2.8086368192449047,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00042123444028651725,
|
|
"loss": 4.6594,
|
|
"mean_token_accuracy": 0.24059453159570693,
|
|
"num_tokens": 61886667.0,
|
|
"step": 33625
|
|
},
|
|
{
|
|
"entropy": 5.362934875488281,
|
|
"epoch": 2.8090544604076175,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00042121181402153394,
|
|
"loss": 4.7341,
|
|
"mean_token_accuracy": 0.2340187430381775,
|
|
"num_tokens": 61895325.0,
|
|
"step": 33630
|
|
},
|
|
{
|
|
"entropy": 5.509302711486816,
|
|
"epoch": 2.809472101570331,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042118918519693665,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.22586360424757004,
|
|
"num_tokens": 61904023.0,
|
|
"step": 33635
|
|
},
|
|
{
|
|
"entropy": 5.407810974121094,
|
|
"epoch": 2.809889742733044,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042116655381312193,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.23818399012088776,
|
|
"num_tokens": 61912969.0,
|
|
"step": 33640
|
|
},
|
|
{
|
|
"entropy": 5.4143064498901365,
|
|
"epoch": 2.810307383895757,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00042114391987048557,
|
|
"loss": 4.7821,
|
|
"mean_token_accuracy": 0.22692669481039046,
|
|
"num_tokens": 61922784.0,
|
|
"step": 33645
|
|
},
|
|
{
|
|
"entropy": 5.460780811309815,
|
|
"epoch": 2.8107250250584697,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042112128336942406,
|
|
"loss": 4.7749,
|
|
"mean_token_accuracy": 0.217376247048378,
|
|
"num_tokens": 61931566.0,
|
|
"step": 33650
|
|
},
|
|
{
|
|
"entropy": 5.407707738876343,
|
|
"epoch": 2.811142666221183,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004210986443103335,
|
|
"loss": 4.6646,
|
|
"mean_token_accuracy": 0.23870478123426436,
|
|
"num_tokens": 61941159.0,
|
|
"step": 33655
|
|
},
|
|
{
|
|
"entropy": 5.469215250015258,
|
|
"epoch": 2.8115603073838957,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042107600269361046,
|
|
"loss": 4.8152,
|
|
"mean_token_accuracy": 0.22968502789735795,
|
|
"num_tokens": 61951499.0,
|
|
"step": 33660
|
|
},
|
|
{
|
|
"entropy": 5.440696048736572,
|
|
"epoch": 2.811977948546609,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042105335851965104,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.23315698206424712,
|
|
"num_tokens": 61960264.0,
|
|
"step": 33665
|
|
},
|
|
{
|
|
"entropy": 5.411399555206299,
|
|
"epoch": 2.812395589709322,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004210307117888519,
|
|
"loss": 4.7169,
|
|
"mean_token_accuracy": 0.22796459943056108,
|
|
"num_tokens": 61970048.0,
|
|
"step": 33670
|
|
},
|
|
{
|
|
"entropy": 5.533080196380615,
|
|
"epoch": 2.8128132308720346,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042100806250160925,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.226394447684288,
|
|
"num_tokens": 61979566.0,
|
|
"step": 33675
|
|
},
|
|
{
|
|
"entropy": 5.352292013168335,
|
|
"epoch": 2.813230872034748,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004209854106583198,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.23765629678964614,
|
|
"num_tokens": 61988207.0,
|
|
"step": 33680
|
|
},
|
|
{
|
|
"entropy": 5.463638162612915,
|
|
"epoch": 2.8136485131974607,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042096275625938,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.22855826020240783,
|
|
"num_tokens": 61996380.0,
|
|
"step": 33685
|
|
},
|
|
{
|
|
"entropy": 5.405395030975342,
|
|
"epoch": 2.814066154360174,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00042094009930518643,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.22802185863256455,
|
|
"num_tokens": 62005828.0,
|
|
"step": 33690
|
|
},
|
|
{
|
|
"entropy": 5.4786458015441895,
|
|
"epoch": 2.8144837955228867,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042091743979613574,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.22526467740535736,
|
|
"num_tokens": 62015362.0,
|
|
"step": 33695
|
|
},
|
|
{
|
|
"entropy": 5.460593843460083,
|
|
"epoch": 2.8149014366855996,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004208947777326246,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.22671339511871338,
|
|
"num_tokens": 62024163.0,
|
|
"step": 33700
|
|
},
|
|
{
|
|
"entropy": 5.433579063415527,
|
|
"epoch": 2.815319077848313,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042087211311504986,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.22778719812631607,
|
|
"num_tokens": 62032838.0,
|
|
"step": 33705
|
|
},
|
|
{
|
|
"entropy": 5.451165294647216,
|
|
"epoch": 2.8157367190110256,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00042084944594380813,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.23960573673248292,
|
|
"num_tokens": 62041100.0,
|
|
"step": 33710
|
|
},
|
|
{
|
|
"entropy": 5.403571939468383,
|
|
"epoch": 2.816154360173739,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00042082677621929626,
|
|
"loss": 4.5919,
|
|
"mean_token_accuracy": 0.24093523919582366,
|
|
"num_tokens": 62050145.0,
|
|
"step": 33715
|
|
},
|
|
{
|
|
"entropy": 5.443765115737915,
|
|
"epoch": 2.8165720013364517,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004208041039419113,
|
|
"loss": 4.752,
|
|
"mean_token_accuracy": 0.22868067920207977,
|
|
"num_tokens": 62059872.0,
|
|
"step": 33720
|
|
},
|
|
{
|
|
"entropy": 5.47868709564209,
|
|
"epoch": 2.8169896424991645,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042078142911204983,
|
|
"loss": 4.7464,
|
|
"mean_token_accuracy": 0.22949992418289183,
|
|
"num_tokens": 62068277.0,
|
|
"step": 33725
|
|
},
|
|
{
|
|
"entropy": 5.435953140258789,
|
|
"epoch": 2.8174072836618778,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000420758751730109,
|
|
"loss": 4.6922,
|
|
"mean_token_accuracy": 0.2314399152994156,
|
|
"num_tokens": 62077846.0,
|
|
"step": 33730
|
|
},
|
|
{
|
|
"entropy": 5.41121735572815,
|
|
"epoch": 2.8178249248245906,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042073607179648575,
|
|
"loss": 4.6718,
|
|
"mean_token_accuracy": 0.23801256120204925,
|
|
"num_tokens": 62085873.0,
|
|
"step": 33735
|
|
},
|
|
{
|
|
"entropy": 5.441615438461303,
|
|
"epoch": 2.818242565987304,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004207133893115772,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.223519928753376,
|
|
"num_tokens": 62096259.0,
|
|
"step": 33740
|
|
},
|
|
{
|
|
"entropy": 5.4524298191070555,
|
|
"epoch": 2.8186602071500166,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004206907042757803,
|
|
"loss": 4.6807,
|
|
"mean_token_accuracy": 0.23402602672576905,
|
|
"num_tokens": 62105414.0,
|
|
"step": 33745
|
|
},
|
|
{
|
|
"entropy": 5.342502737045288,
|
|
"epoch": 2.8190778483127295,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042066801668949236,
|
|
"loss": 4.6754,
|
|
"mean_token_accuracy": 0.2370680093765259,
|
|
"num_tokens": 62114403.0,
|
|
"step": 33750
|
|
},
|
|
{
|
|
"entropy": 5.490218782424927,
|
|
"epoch": 2.8194954894754427,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004206453265531104,
|
|
"loss": 4.7299,
|
|
"mean_token_accuracy": 0.23141276687383652,
|
|
"num_tokens": 62123189.0,
|
|
"step": 33755
|
|
},
|
|
{
|
|
"entropy": 5.369875240325928,
|
|
"epoch": 2.819913130638156,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00042062263386703167,
|
|
"loss": 4.6808,
|
|
"mean_token_accuracy": 0.23329296261072158,
|
|
"num_tokens": 62131454.0,
|
|
"step": 33760
|
|
},
|
|
{
|
|
"entropy": 5.439621162414551,
|
|
"epoch": 2.8203307718008688,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042059993863165343,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.23410929888486862,
|
|
"num_tokens": 62140621.0,
|
|
"step": 33765
|
|
},
|
|
{
|
|
"entropy": 5.3837944030761715,
|
|
"epoch": 2.8207484129635816,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000420577240847373,
|
|
"loss": 4.6386,
|
|
"mean_token_accuracy": 0.2379056066274643,
|
|
"num_tokens": 62149076.0,
|
|
"step": 33770
|
|
},
|
|
{
|
|
"entropy": 5.447785758972168,
|
|
"epoch": 2.821166054126295,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004205545405145878,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.2357306718826294,
|
|
"num_tokens": 62159410.0,
|
|
"step": 33775
|
|
},
|
|
{
|
|
"entropy": 5.431653165817261,
|
|
"epoch": 2.8215836952890077,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004205318376336952,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.22770473957061768,
|
|
"num_tokens": 62169119.0,
|
|
"step": 33780
|
|
},
|
|
{
|
|
"entropy": 5.447134304046631,
|
|
"epoch": 2.822001336451721,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042050913220509253,
|
|
"loss": 4.6894,
|
|
"mean_token_accuracy": 0.23386161178350448,
|
|
"num_tokens": 62177524.0,
|
|
"step": 33785
|
|
},
|
|
{
|
|
"entropy": 5.4926595211029055,
|
|
"epoch": 2.8224189776144337,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004204864242291773,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.23331730514764787,
|
|
"num_tokens": 62187321.0,
|
|
"step": 33790
|
|
},
|
|
{
|
|
"entropy": 5.4036811828613285,
|
|
"epoch": 2.8228366187771465,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042046371370634716,
|
|
"loss": 4.6668,
|
|
"mean_token_accuracy": 0.23247658014297484,
|
|
"num_tokens": 62196111.0,
|
|
"step": 33795
|
|
},
|
|
{
|
|
"entropy": 5.358927011489868,
|
|
"epoch": 2.82325425993986,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00042044100063699964,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.2343767389655113,
|
|
"num_tokens": 62204583.0,
|
|
"step": 33800
|
|
},
|
|
{
|
|
"entropy": 5.40944881439209,
|
|
"epoch": 2.8236719011025726,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004204182850215323,
|
|
"loss": 4.6999,
|
|
"mean_token_accuracy": 0.23104202449321748,
|
|
"num_tokens": 62213508.0,
|
|
"step": 33805
|
|
},
|
|
{
|
|
"entropy": 5.432546949386596,
|
|
"epoch": 2.824089542265286,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00042039556686034285,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.2288640931248665,
|
|
"num_tokens": 62222082.0,
|
|
"step": 33810
|
|
},
|
|
{
|
|
"entropy": 5.469789838790893,
|
|
"epoch": 2.8245071834279987,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000420372846153829,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.23098768144845963,
|
|
"num_tokens": 62230645.0,
|
|
"step": 33815
|
|
},
|
|
{
|
|
"entropy": 5.4522881507873535,
|
|
"epoch": 2.8249248245907115,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042035012290238846,
|
|
"loss": 4.7332,
|
|
"mean_token_accuracy": 0.23245172053575516,
|
|
"num_tokens": 62239053.0,
|
|
"step": 33820
|
|
},
|
|
{
|
|
"entropy": 5.418198299407959,
|
|
"epoch": 2.8253424657534247,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004203273971064191,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.23907754570245743,
|
|
"num_tokens": 62247917.0,
|
|
"step": 33825
|
|
},
|
|
{
|
|
"entropy": 5.476995992660522,
|
|
"epoch": 2.8257601069161375,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004203046687663187,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.22217017859220506,
|
|
"num_tokens": 62257960.0,
|
|
"step": 33830
|
|
},
|
|
{
|
|
"entropy": 5.461917591094971,
|
|
"epoch": 2.826177748078851,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004202819378824851,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.2283305749297142,
|
|
"num_tokens": 62267860.0,
|
|
"step": 33835
|
|
},
|
|
{
|
|
"entropy": 5.385287094116211,
|
|
"epoch": 2.8265953892415636,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004202592044553165,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.23580105006694793,
|
|
"num_tokens": 62276384.0,
|
|
"step": 33840
|
|
},
|
|
{
|
|
"entropy": 5.505171251296997,
|
|
"epoch": 2.8270130304042764,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042023646848521047,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.22062212824821473,
|
|
"num_tokens": 62285218.0,
|
|
"step": 33845
|
|
},
|
|
{
|
|
"entropy": 5.468848037719726,
|
|
"epoch": 2.8274306715669897,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042021372997256537,
|
|
"loss": 4.8402,
|
|
"mean_token_accuracy": 0.22423197478055953,
|
|
"num_tokens": 62295025.0,
|
|
"step": 33850
|
|
},
|
|
{
|
|
"entropy": 5.442469882965088,
|
|
"epoch": 2.8278483127297025,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000420190988917779,
|
|
"loss": 4.6915,
|
|
"mean_token_accuracy": 0.2296220064163208,
|
|
"num_tokens": 62304105.0,
|
|
"step": 33855
|
|
},
|
|
{
|
|
"entropy": 5.504158353805542,
|
|
"epoch": 2.8282659538924158,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004201682453212497,
|
|
"loss": 4.7395,
|
|
"mean_token_accuracy": 0.22741297334432603,
|
|
"num_tokens": 62312975.0,
|
|
"step": 33860
|
|
},
|
|
{
|
|
"entropy": 5.410829782485962,
|
|
"epoch": 2.8286835950551286,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042014549918337554,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.21945772767066957,
|
|
"num_tokens": 62323500.0,
|
|
"step": 33865
|
|
},
|
|
{
|
|
"entropy": 5.453650617599488,
|
|
"epoch": 2.8291012362178414,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00042012275050455465,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.2361259713768959,
|
|
"num_tokens": 62332355.0,
|
|
"step": 33870
|
|
},
|
|
{
|
|
"entropy": 5.452075624465943,
|
|
"epoch": 2.8295188773805546,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004200999992851853,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.23071514666080475,
|
|
"num_tokens": 62341001.0,
|
|
"step": 33875
|
|
},
|
|
{
|
|
"entropy": 5.415407276153564,
|
|
"epoch": 2.829936518543268,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042007724552566597,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.23371044248342515,
|
|
"num_tokens": 62350277.0,
|
|
"step": 33880
|
|
},
|
|
{
|
|
"entropy": 5.498395299911499,
|
|
"epoch": 2.8303541597059807,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042005448922639464,
|
|
"loss": 4.7875,
|
|
"mean_token_accuracy": 0.22794700264930726,
|
|
"num_tokens": 62360994.0,
|
|
"step": 33885
|
|
},
|
|
{
|
|
"entropy": 5.472200489044189,
|
|
"epoch": 2.8307718008686935,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042003173038777,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.2295188620686531,
|
|
"num_tokens": 62370018.0,
|
|
"step": 33890
|
|
},
|
|
{
|
|
"entropy": 5.524008274078369,
|
|
"epoch": 2.8311894420314068,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004200089690101903,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.22016733586788179,
|
|
"num_tokens": 62379491.0,
|
|
"step": 33895
|
|
},
|
|
{
|
|
"entropy": 5.49320421218872,
|
|
"epoch": 2.8316070831941196,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041998620509405406,
|
|
"loss": 4.767,
|
|
"mean_token_accuracy": 0.23084125071763992,
|
|
"num_tokens": 62388913.0,
|
|
"step": 33900
|
|
},
|
|
{
|
|
"entropy": 5.3770959854125975,
|
|
"epoch": 2.832024724356833,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004199634386397598,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.2294148936867714,
|
|
"num_tokens": 62398355.0,
|
|
"step": 33905
|
|
},
|
|
{
|
|
"entropy": 5.417689847946167,
|
|
"epoch": 2.8324423655195456,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000419940669647706,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.23662375807762145,
|
|
"num_tokens": 62407611.0,
|
|
"step": 33910
|
|
},
|
|
{
|
|
"entropy": 5.399895334243775,
|
|
"epoch": 2.8328600066822585,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004199178981182913,
|
|
"loss": 4.6915,
|
|
"mean_token_accuracy": 0.23684027642011643,
|
|
"num_tokens": 62415839.0,
|
|
"step": 33915
|
|
},
|
|
{
|
|
"entropy": 5.439511823654175,
|
|
"epoch": 2.8332776478449717,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004198951240519144,
|
|
"loss": 4.7881,
|
|
"mean_token_accuracy": 0.23282505869865416,
|
|
"num_tokens": 62425348.0,
|
|
"step": 33920
|
|
},
|
|
{
|
|
"entropy": 5.457370376586914,
|
|
"epoch": 2.8336952890076845,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00041987234744897395,
|
|
"loss": 4.7705,
|
|
"mean_token_accuracy": 0.22821400910615922,
|
|
"num_tokens": 62434777.0,
|
|
"step": 33925
|
|
},
|
|
{
|
|
"entropy": 5.499370670318603,
|
|
"epoch": 2.834112930170398,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041984956830986865,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.2296674817800522,
|
|
"num_tokens": 62444042.0,
|
|
"step": 33930
|
|
},
|
|
{
|
|
"entropy": 5.495995998382568,
|
|
"epoch": 2.8345305713331106,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004198267866349973,
|
|
"loss": 4.753,
|
|
"mean_token_accuracy": 0.2341696009039879,
|
|
"num_tokens": 62452830.0,
|
|
"step": 33935
|
|
},
|
|
{
|
|
"entropy": 5.419987773895263,
|
|
"epoch": 2.8349482124958234,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004198040024247587,
|
|
"loss": 4.7072,
|
|
"mean_token_accuracy": 0.23588670790195465,
|
|
"num_tokens": 62461915.0,
|
|
"step": 33940
|
|
},
|
|
{
|
|
"entropy": 5.503597354888916,
|
|
"epoch": 2.8353658536585367,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004197812156795518,
|
|
"loss": 4.8589,
|
|
"mean_token_accuracy": 0.22327813804149627,
|
|
"num_tokens": 62471913.0,
|
|
"step": 33945
|
|
},
|
|
{
|
|
"entropy": 5.5207842826843265,
|
|
"epoch": 2.8357834948212495,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004197584263997754,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.23042023032903672,
|
|
"num_tokens": 62481426.0,
|
|
"step": 33950
|
|
},
|
|
{
|
|
"entropy": 5.443979120254516,
|
|
"epoch": 2.8362011359839627,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004197356345858285,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.22600235939025878,
|
|
"num_tokens": 62490032.0,
|
|
"step": 33955
|
|
},
|
|
{
|
|
"entropy": 5.492171430587769,
|
|
"epoch": 2.8366187771466755,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041971284023811014,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.23072744011878968,
|
|
"num_tokens": 62498885.0,
|
|
"step": 33960
|
|
},
|
|
{
|
|
"entropy": 5.452267837524414,
|
|
"epoch": 2.8370364183093884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041969004335701927,
|
|
"loss": 4.7322,
|
|
"mean_token_accuracy": 0.2240218475461006,
|
|
"num_tokens": 62507360.0,
|
|
"step": 33965
|
|
},
|
|
{
|
|
"entropy": 5.324628162384033,
|
|
"epoch": 2.8374540594721016,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000419667243942955,
|
|
"loss": 4.6038,
|
|
"mean_token_accuracy": 0.2447515606880188,
|
|
"num_tokens": 62515853.0,
|
|
"step": 33970
|
|
},
|
|
{
|
|
"entropy": 5.415292119979858,
|
|
"epoch": 2.8378717006348144,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004196444419963166,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.2332013577222824,
|
|
"num_tokens": 62524657.0,
|
|
"step": 33975
|
|
},
|
|
{
|
|
"entropy": 5.4464020252227785,
|
|
"epoch": 2.8382893417975277,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004196216375175031,
|
|
"loss": 4.7027,
|
|
"mean_token_accuracy": 0.23257376551628112,
|
|
"num_tokens": 62534315.0,
|
|
"step": 33980
|
|
},
|
|
{
|
|
"entropy": 5.362808275222778,
|
|
"epoch": 2.8387069829602405,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004195988305069137,
|
|
"loss": 4.6326,
|
|
"mean_token_accuracy": 0.2346166342496872,
|
|
"num_tokens": 62542849.0,
|
|
"step": 33985
|
|
},
|
|
{
|
|
"entropy": 5.456616067886353,
|
|
"epoch": 2.8391246241229533,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004195760209649478,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.22678258866071702,
|
|
"num_tokens": 62552511.0,
|
|
"step": 33990
|
|
},
|
|
{
|
|
"entropy": 5.434292936325074,
|
|
"epoch": 2.8395422652856666,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004195532088920045,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.22677716612815857,
|
|
"num_tokens": 62561843.0,
|
|
"step": 33995
|
|
},
|
|
{
|
|
"entropy": 5.5168084621429445,
|
|
"epoch": 2.83995990644838,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041953039428848336,
|
|
"loss": 4.8114,
|
|
"mean_token_accuracy": 0.2308693140745163,
|
|
"num_tokens": 62570740.0,
|
|
"step": 34000
|
|
},
|
|
{
|
|
"entropy": 5.57452244758606,
|
|
"epoch": 2.8403775476110926,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004195075771547837,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.21188478469848632,
|
|
"num_tokens": 62580586.0,
|
|
"step": 34005
|
|
},
|
|
{
|
|
"entropy": 5.492715358734131,
|
|
"epoch": 2.8407951887738054,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000419484757491305,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.2339845046401024,
|
|
"num_tokens": 62589100.0,
|
|
"step": 34010
|
|
},
|
|
{
|
|
"entropy": 5.361545181274414,
|
|
"epoch": 2.8412128299365187,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004194619352984467,
|
|
"loss": 4.6329,
|
|
"mean_token_accuracy": 0.2444048672914505,
|
|
"num_tokens": 62597699.0,
|
|
"step": 34015
|
|
},
|
|
{
|
|
"entropy": 5.304409456253052,
|
|
"epoch": 2.8416304710992315,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041943911057660817,
|
|
"loss": 4.6093,
|
|
"mean_token_accuracy": 0.23992493152618408,
|
|
"num_tokens": 62606300.0,
|
|
"step": 34020
|
|
},
|
|
{
|
|
"entropy": 5.458078479766845,
|
|
"epoch": 2.8420481122619448,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004194162833261893,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.23521386831998825,
|
|
"num_tokens": 62615125.0,
|
|
"step": 34025
|
|
},
|
|
{
|
|
"entropy": 5.513993453979492,
|
|
"epoch": 2.8424657534246576,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004193934535475895,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.2294066771864891,
|
|
"num_tokens": 62624378.0,
|
|
"step": 34030
|
|
},
|
|
{
|
|
"entropy": 5.368931579589844,
|
|
"epoch": 2.8428833945873704,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041937062124120856,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.23182959407567977,
|
|
"num_tokens": 62634385.0,
|
|
"step": 34035
|
|
},
|
|
{
|
|
"entropy": 5.414034128189087,
|
|
"epoch": 2.8433010357500836,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041934778640744603,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.24047823250293732,
|
|
"num_tokens": 62643785.0,
|
|
"step": 34040
|
|
},
|
|
{
|
|
"entropy": 5.446942281723023,
|
|
"epoch": 2.8437186769127965,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041932494904670174,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.2273451417684555,
|
|
"num_tokens": 62652620.0,
|
|
"step": 34045
|
|
},
|
|
{
|
|
"entropy": 5.416902160644531,
|
|
"epoch": 2.8441363180755097,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004193021091593756,
|
|
"loss": 4.7825,
|
|
"mean_token_accuracy": 0.22244780957698823,
|
|
"num_tokens": 62660933.0,
|
|
"step": 34050
|
|
},
|
|
{
|
|
"entropy": 5.478260469436646,
|
|
"epoch": 2.8445539592382225,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041927926674586725,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.22890748530626298,
|
|
"num_tokens": 62670424.0,
|
|
"step": 34055
|
|
},
|
|
{
|
|
"entropy": 5.399382734298706,
|
|
"epoch": 2.8449716004009353,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004192564218065768,
|
|
"loss": 4.5776,
|
|
"mean_token_accuracy": 0.24515916854143144,
|
|
"num_tokens": 62678458.0,
|
|
"step": 34060
|
|
},
|
|
{
|
|
"entropy": 5.354115724563599,
|
|
"epoch": 2.8453892415636486,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004192335743419039,
|
|
"loss": 4.7305,
|
|
"mean_token_accuracy": 0.22946215122938157,
|
|
"num_tokens": 62688442.0,
|
|
"step": 34065
|
|
},
|
|
{
|
|
"entropy": 5.421118879318238,
|
|
"epoch": 2.8458068827263614,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004192107243522487,
|
|
"loss": 4.7278,
|
|
"mean_token_accuracy": 0.23039072453975679,
|
|
"num_tokens": 62697400.0,
|
|
"step": 34070
|
|
},
|
|
{
|
|
"entropy": 5.4105840682983395,
|
|
"epoch": 2.8462245238890747,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041918787183801114,
|
|
"loss": 4.6352,
|
|
"mean_token_accuracy": 0.24782051146030426,
|
|
"num_tokens": 62705802.0,
|
|
"step": 34075
|
|
},
|
|
{
|
|
"entropy": 5.413667869567871,
|
|
"epoch": 2.8466421650517875,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041916501679959144,
|
|
"loss": 4.7264,
|
|
"mean_token_accuracy": 0.2359856992959976,
|
|
"num_tokens": 62714966.0,
|
|
"step": 34080
|
|
},
|
|
{
|
|
"entropy": 5.395496416091919,
|
|
"epoch": 2.8470598062145003,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00041914215923738945,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.23127270638942718,
|
|
"num_tokens": 62723682.0,
|
|
"step": 34085
|
|
},
|
|
{
|
|
"entropy": 5.407907199859619,
|
|
"epoch": 2.8474774473772135,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041911929915180556,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.23452963232994078,
|
|
"num_tokens": 62731932.0,
|
|
"step": 34090
|
|
},
|
|
{
|
|
"entropy": 5.33707275390625,
|
|
"epoch": 2.8478950885399263,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004190964365432398,
|
|
"loss": 4.7034,
|
|
"mean_token_accuracy": 0.24101134538650512,
|
|
"num_tokens": 62740849.0,
|
|
"step": 34095
|
|
},
|
|
{
|
|
"entropy": 5.3875409126281735,
|
|
"epoch": 2.8483127297026396,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041907357141209256,
|
|
"loss": 4.7003,
|
|
"mean_token_accuracy": 0.22778227180242538,
|
|
"num_tokens": 62750731.0,
|
|
"step": 34100
|
|
},
|
|
{
|
|
"entropy": 5.381349754333496,
|
|
"epoch": 2.8487303708653524,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004190507037587639,
|
|
"loss": 4.6682,
|
|
"mean_token_accuracy": 0.24155887365341186,
|
|
"num_tokens": 62759380.0,
|
|
"step": 34105
|
|
},
|
|
{
|
|
"entropy": 5.522170925140381,
|
|
"epoch": 2.8491480120280652,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041902783358365445,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.23092434257268907,
|
|
"num_tokens": 62768083.0,
|
|
"step": 34110
|
|
},
|
|
{
|
|
"entropy": 5.456162452697754,
|
|
"epoch": 2.8495656531907785,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041900496088716427,
|
|
"loss": 4.7874,
|
|
"mean_token_accuracy": 0.23166220635175705,
|
|
"num_tokens": 62777119.0,
|
|
"step": 34115
|
|
},
|
|
{
|
|
"entropy": 5.437535667419434,
|
|
"epoch": 2.8499832943534917,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000418982085669694,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.2336061790585518,
|
|
"num_tokens": 62786438.0,
|
|
"step": 34120
|
|
},
|
|
{
|
|
"entropy": 5.508305501937866,
|
|
"epoch": 2.8504009355162045,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000418959207931644,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.23153961151838304,
|
|
"num_tokens": 62795545.0,
|
|
"step": 34125
|
|
},
|
|
{
|
|
"entropy": 5.357604217529297,
|
|
"epoch": 2.8508185766789174,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004189363276734147,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.23526223599910737,
|
|
"num_tokens": 62804430.0,
|
|
"step": 34130
|
|
},
|
|
{
|
|
"entropy": 5.4380495071411135,
|
|
"epoch": 2.8512362178416306,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004189134448954068,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.23106092512607573,
|
|
"num_tokens": 62813546.0,
|
|
"step": 34135
|
|
},
|
|
{
|
|
"entropy": 5.398921155929566,
|
|
"epoch": 2.8516538590043434,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041889055959802075,
|
|
"loss": 4.7044,
|
|
"mean_token_accuracy": 0.23420335352420807,
|
|
"num_tokens": 62822662.0,
|
|
"step": 34140
|
|
},
|
|
{
|
|
"entropy": 5.4496674060821535,
|
|
"epoch": 2.8520715001670567,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004188676717816572,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.23864172846078874,
|
|
"num_tokens": 62831908.0,
|
|
"step": 34145
|
|
},
|
|
{
|
|
"entropy": 5.553746843338013,
|
|
"epoch": 2.8524891413297695,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041884478144671704,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.22187095135450363,
|
|
"num_tokens": 62842280.0,
|
|
"step": 34150
|
|
},
|
|
{
|
|
"entropy": 5.466306400299072,
|
|
"epoch": 2.8529067824924823,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041882188859360077,
|
|
"loss": 4.7538,
|
|
"mean_token_accuracy": 0.23604350239038469,
|
|
"num_tokens": 62851192.0,
|
|
"step": 34155
|
|
},
|
|
{
|
|
"entropy": 5.413847255706787,
|
|
"epoch": 2.8533244236551956,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004187989932227092,
|
|
"loss": 4.7263,
|
|
"mean_token_accuracy": 0.23744501620531083,
|
|
"num_tokens": 62860478.0,
|
|
"step": 34160
|
|
},
|
|
{
|
|
"entropy": 5.431878232955933,
|
|
"epoch": 2.8537420648179084,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00041877609533444324,
|
|
"loss": 4.6148,
|
|
"mean_token_accuracy": 0.23458416312932967,
|
|
"num_tokens": 62868730.0,
|
|
"step": 34165
|
|
},
|
|
{
|
|
"entropy": 5.5055460929870605,
|
|
"epoch": 2.8541597059806216,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004187531949292036,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.22501910626888275,
|
|
"num_tokens": 62877696.0,
|
|
"step": 34170
|
|
},
|
|
{
|
|
"entropy": 5.374400663375854,
|
|
"epoch": 2.8545773471433344,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004187302920073912,
|
|
"loss": 4.6697,
|
|
"mean_token_accuracy": 0.23859286606311797,
|
|
"num_tokens": 62887186.0,
|
|
"step": 34175
|
|
},
|
|
{
|
|
"entropy": 5.474287986755371,
|
|
"epoch": 2.8549949883060473,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041870738656940717,
|
|
"loss": 4.7422,
|
|
"mean_token_accuracy": 0.23752839118242264,
|
|
"num_tokens": 62895884.0,
|
|
"step": 34180
|
|
},
|
|
{
|
|
"entropy": 5.500210475921631,
|
|
"epoch": 2.8554126294687605,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004186844786156522,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.22064692080020903,
|
|
"num_tokens": 62905638.0,
|
|
"step": 34185
|
|
},
|
|
{
|
|
"entropy": 5.502090883255005,
|
|
"epoch": 2.8558302706314733,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004186615681465276,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.22339258790016175,
|
|
"num_tokens": 62914950.0,
|
|
"step": 34190
|
|
},
|
|
{
|
|
"entropy": 5.411666631698608,
|
|
"epoch": 2.8562479117941866,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041863865516243427,
|
|
"loss": 4.6063,
|
|
"mean_token_accuracy": 0.24381286650896072,
|
|
"num_tokens": 62922853.0,
|
|
"step": 34195
|
|
},
|
|
{
|
|
"entropy": 5.495005941390991,
|
|
"epoch": 2.8566655529568994,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004186157396637734,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.22556659430265427,
|
|
"num_tokens": 62932860.0,
|
|
"step": 34200
|
|
},
|
|
{
|
|
"entropy": 5.425306892395019,
|
|
"epoch": 2.857083194119612,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041859282165094614,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.22914117574691772,
|
|
"num_tokens": 62941644.0,
|
|
"step": 34205
|
|
},
|
|
{
|
|
"entropy": 5.34062237739563,
|
|
"epoch": 2.8575008352823255,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041856990112435367,
|
|
"loss": 4.5563,
|
|
"mean_token_accuracy": 0.24555965960025788,
|
|
"num_tokens": 62950917.0,
|
|
"step": 34210
|
|
},
|
|
{
|
|
"entropy": 5.460931825637817,
|
|
"epoch": 2.8579184764450383,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004185469780843972,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.22538062036037446,
|
|
"num_tokens": 62960333.0,
|
|
"step": 34215
|
|
},
|
|
{
|
|
"entropy": 5.479816198348999,
|
|
"epoch": 2.8583361176077515,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004185240525314783,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.21947630494832993,
|
|
"num_tokens": 62970072.0,
|
|
"step": 34220
|
|
},
|
|
{
|
|
"entropy": 5.438523292541504,
|
|
"epoch": 2.8587537587704643,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000418501124465998,
|
|
"loss": 4.7161,
|
|
"mean_token_accuracy": 0.24050892442464827,
|
|
"num_tokens": 62978166.0,
|
|
"step": 34225
|
|
},
|
|
{
|
|
"entropy": 5.421845531463623,
|
|
"epoch": 2.859171399933177,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004184781938883577,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.22981459349393846,
|
|
"num_tokens": 62986077.0,
|
|
"step": 34230
|
|
},
|
|
{
|
|
"entropy": 5.511395788192749,
|
|
"epoch": 2.8595890410958904,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000418455260798959,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.23300791531801224,
|
|
"num_tokens": 62994910.0,
|
|
"step": 34235
|
|
},
|
|
{
|
|
"entropy": 5.367281150817871,
|
|
"epoch": 2.8600066822586037,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041843232519820316,
|
|
"loss": 4.672,
|
|
"mean_token_accuracy": 0.2353745147585869,
|
|
"num_tokens": 63005645.0,
|
|
"step": 34240
|
|
},
|
|
{
|
|
"entropy": 5.403001928329468,
|
|
"epoch": 2.8604243234213165,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004184093870864919,
|
|
"loss": 4.7606,
|
|
"mean_token_accuracy": 0.2323825776576996,
|
|
"num_tokens": 63013945.0,
|
|
"step": 34245
|
|
},
|
|
{
|
|
"entropy": 5.365687417984009,
|
|
"epoch": 2.8608419645840293,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004183864464642267,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.2385045111179352,
|
|
"num_tokens": 63022374.0,
|
|
"step": 34250
|
|
},
|
|
{
|
|
"entropy": 5.44087929725647,
|
|
"epoch": 2.8612596057467425,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041836350333180917,
|
|
"loss": 4.7234,
|
|
"mean_token_accuracy": 0.2348891854286194,
|
|
"num_tokens": 63031234.0,
|
|
"step": 34255
|
|
},
|
|
{
|
|
"entropy": 5.501255655288697,
|
|
"epoch": 2.8616772469094554,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041834055768964095,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.22969659864902497,
|
|
"num_tokens": 63041076.0,
|
|
"step": 34260
|
|
},
|
|
{
|
|
"entropy": 5.495843076705933,
|
|
"epoch": 2.8620948880721686,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004183176095381238,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.22891981452703475,
|
|
"num_tokens": 63050540.0,
|
|
"step": 34265
|
|
},
|
|
{
|
|
"entropy": 5.385352945327758,
|
|
"epoch": 2.8625125292348814,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041829465887765924,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.23739949762821197,
|
|
"num_tokens": 63059809.0,
|
|
"step": 34270
|
|
},
|
|
{
|
|
"entropy": 5.398359251022339,
|
|
"epoch": 2.8629301703975942,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041827170570864924,
|
|
"loss": 4.6607,
|
|
"mean_token_accuracy": 0.23894880563020707,
|
|
"num_tokens": 63068966.0,
|
|
"step": 34275
|
|
},
|
|
{
|
|
"entropy": 5.478898382186889,
|
|
"epoch": 2.8633478115603075,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004182487500314956,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.2326610043644905,
|
|
"num_tokens": 63078951.0,
|
|
"step": 34280
|
|
},
|
|
{
|
|
"entropy": 5.450309896469117,
|
|
"epoch": 2.8637654527230203,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041822579184660016,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.22132471352815627,
|
|
"num_tokens": 63088190.0,
|
|
"step": 34285
|
|
},
|
|
{
|
|
"entropy": 5.485007286071777,
|
|
"epoch": 2.8641830938857336,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00041820283115436485,
|
|
"loss": 4.8431,
|
|
"mean_token_accuracy": 0.22622969150543212,
|
|
"num_tokens": 63097720.0,
|
|
"step": 34290
|
|
},
|
|
{
|
|
"entropy": 5.436275577545166,
|
|
"epoch": 2.8646007350484464,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004181798679551916,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.2345675364136696,
|
|
"num_tokens": 63107264.0,
|
|
"step": 34295
|
|
},
|
|
{
|
|
"entropy": 5.460720443725586,
|
|
"epoch": 2.865018376211159,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004181569022494824,
|
|
"loss": 4.7734,
|
|
"mean_token_accuracy": 0.2212267503142357,
|
|
"num_tokens": 63117394.0,
|
|
"step": 34300
|
|
},
|
|
{
|
|
"entropy": 5.462193775177002,
|
|
"epoch": 2.8654360173738724,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004181339340376393,
|
|
"loss": 4.8252,
|
|
"mean_token_accuracy": 0.21759601086378097,
|
|
"num_tokens": 63126681.0,
|
|
"step": 34305
|
|
},
|
|
{
|
|
"entropy": 5.4078936100006105,
|
|
"epoch": 2.8658536585365852,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004181109633200644,
|
|
"loss": 4.619,
|
|
"mean_token_accuracy": 0.24367257207632065,
|
|
"num_tokens": 63137034.0,
|
|
"step": 34310
|
|
},
|
|
{
|
|
"entropy": 5.404347658157349,
|
|
"epoch": 2.8662712996992985,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004180879900971598,
|
|
"loss": 4.6599,
|
|
"mean_token_accuracy": 0.23888720571994781,
|
|
"num_tokens": 63145305.0,
|
|
"step": 34315
|
|
},
|
|
{
|
|
"entropy": 5.419365644454956,
|
|
"epoch": 2.8666889408620113,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00041806501436932774,
|
|
"loss": 4.7078,
|
|
"mean_token_accuracy": 0.22929971367120744,
|
|
"num_tokens": 63154121.0,
|
|
"step": 34320
|
|
},
|
|
{
|
|
"entropy": 5.397580528259278,
|
|
"epoch": 2.867106582024724,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004180420361369704,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.21860488951206208,
|
|
"num_tokens": 63163536.0,
|
|
"step": 34325
|
|
},
|
|
{
|
|
"entropy": 5.439347457885742,
|
|
"epoch": 2.8675242231874374,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041801905540049,
|
|
"loss": 4.7022,
|
|
"mean_token_accuracy": 0.23312899619340896,
|
|
"num_tokens": 63173315.0,
|
|
"step": 34330
|
|
},
|
|
{
|
|
"entropy": 5.413225793838501,
|
|
"epoch": 2.86794186435015,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004179960721602889,
|
|
"loss": 4.6536,
|
|
"mean_token_accuracy": 0.23925240188837052,
|
|
"num_tokens": 63181704.0,
|
|
"step": 34335
|
|
},
|
|
{
|
|
"entropy": 5.46129846572876,
|
|
"epoch": 2.8683595055128634,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041797308641676944,
|
|
"loss": 4.7513,
|
|
"mean_token_accuracy": 0.23044389933347703,
|
|
"num_tokens": 63191405.0,
|
|
"step": 34340
|
|
},
|
|
{
|
|
"entropy": 5.455594158172607,
|
|
"epoch": 2.8687771466755763,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000417950098170334,
|
|
"loss": 4.8323,
|
|
"mean_token_accuracy": 0.21927736401557923,
|
|
"num_tokens": 63200834.0,
|
|
"step": 34345
|
|
},
|
|
{
|
|
"entropy": 5.48407301902771,
|
|
"epoch": 2.869194787838289,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000417927107421385,
|
|
"loss": 4.8579,
|
|
"mean_token_accuracy": 0.21792044788599013,
|
|
"num_tokens": 63210263.0,
|
|
"step": 34350
|
|
},
|
|
{
|
|
"entropy": 5.428701448440552,
|
|
"epoch": 2.8696124290010023,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041790411417032497,
|
|
"loss": 4.7047,
|
|
"mean_token_accuracy": 0.23058223128318786,
|
|
"num_tokens": 63219715.0,
|
|
"step": 34355
|
|
},
|
|
{
|
|
"entropy": 5.381285953521728,
|
|
"epoch": 2.8700300701637156,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00041788111841755646,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.23768653720617294,
|
|
"num_tokens": 63228087.0,
|
|
"step": 34360
|
|
},
|
|
{
|
|
"entropy": 5.527647495269775,
|
|
"epoch": 2.8704477113264284,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004178581201634819,
|
|
"loss": 4.786,
|
|
"mean_token_accuracy": 0.23501149117946624,
|
|
"num_tokens": 63236456.0,
|
|
"step": 34365
|
|
},
|
|
{
|
|
"entropy": 5.474264621734619,
|
|
"epoch": 2.870865352489141,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041783511940850405,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.22789261639118194,
|
|
"num_tokens": 63245441.0,
|
|
"step": 34370
|
|
},
|
|
{
|
|
"entropy": 5.46087875366211,
|
|
"epoch": 2.8712829936518545,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041781211615302545,
|
|
"loss": 4.7537,
|
|
"mean_token_accuracy": 0.2245974451303482,
|
|
"num_tokens": 63254496.0,
|
|
"step": 34375
|
|
},
|
|
{
|
|
"entropy": 5.440568161010742,
|
|
"epoch": 2.8717006348145673,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004177891103974489,
|
|
"loss": 4.6637,
|
|
"mean_token_accuracy": 0.23281244784593583,
|
|
"num_tokens": 63263841.0,
|
|
"step": 34380
|
|
},
|
|
{
|
|
"entropy": 5.453335475921631,
|
|
"epoch": 2.8721182759772805,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00041776610214217707,
|
|
"loss": 4.7935,
|
|
"mean_token_accuracy": 0.22424372136592866,
|
|
"num_tokens": 63272574.0,
|
|
"step": 34385
|
|
},
|
|
{
|
|
"entropy": 5.5118364810943605,
|
|
"epoch": 2.8725359171399933,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004177430913876128,
|
|
"loss": 4.8308,
|
|
"mean_token_accuracy": 0.2193298354744911,
|
|
"num_tokens": 63281845.0,
|
|
"step": 34390
|
|
},
|
|
{
|
|
"entropy": 5.430322790145874,
|
|
"epoch": 2.872953558302706,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004177200781341588,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.22900592535734177,
|
|
"num_tokens": 63290741.0,
|
|
"step": 34395
|
|
},
|
|
{
|
|
"entropy": 5.424002647399902,
|
|
"epoch": 2.8733711994654194,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004176970623822182,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.2312885493040085,
|
|
"num_tokens": 63299857.0,
|
|
"step": 34400
|
|
},
|
|
{
|
|
"entropy": 5.501570796966552,
|
|
"epoch": 2.8737888406281322,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004176740441321936,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.216765920817852,
|
|
"num_tokens": 63309726.0,
|
|
"step": 34405
|
|
},
|
|
{
|
|
"entropy": 5.562469625473023,
|
|
"epoch": 2.8742064817908455,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041765102338448825,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.2211703598499298,
|
|
"num_tokens": 63318834.0,
|
|
"step": 34410
|
|
},
|
|
{
|
|
"entropy": 5.455828237533569,
|
|
"epoch": 2.8746241229535583,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041762800013950496,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.23836415708065034,
|
|
"num_tokens": 63327604.0,
|
|
"step": 34415
|
|
},
|
|
{
|
|
"entropy": 5.442818546295166,
|
|
"epoch": 2.875041764116271,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041760497439764685,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.23649181574583053,
|
|
"num_tokens": 63336623.0,
|
|
"step": 34420
|
|
},
|
|
{
|
|
"entropy": 5.4130207061767575,
|
|
"epoch": 2.8754594052789844,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000417581946159317,
|
|
"loss": 4.6302,
|
|
"mean_token_accuracy": 0.23232814073562622,
|
|
"num_tokens": 63345224.0,
|
|
"step": 34425
|
|
},
|
|
{
|
|
"entropy": 5.498785018920898,
|
|
"epoch": 2.875877046441697,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041755891542491854,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.2264842852950096,
|
|
"num_tokens": 63353450.0,
|
|
"step": 34430
|
|
},
|
|
{
|
|
"entropy": 5.427803421020508,
|
|
"epoch": 2.8762946876044104,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041753588219485473,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.22691455036401748,
|
|
"num_tokens": 63362272.0,
|
|
"step": 34435
|
|
},
|
|
{
|
|
"entropy": 5.488486289978027,
|
|
"epoch": 2.8767123287671232,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004175128464695287,
|
|
"loss": 4.7706,
|
|
"mean_token_accuracy": 0.22908532619476318,
|
|
"num_tokens": 63371289.0,
|
|
"step": 34440
|
|
},
|
|
{
|
|
"entropy": 5.404630708694458,
|
|
"epoch": 2.877129969929836,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041748980824934376,
|
|
"loss": 4.673,
|
|
"mean_token_accuracy": 0.23096625059843062,
|
|
"num_tokens": 63379734.0,
|
|
"step": 34445
|
|
},
|
|
{
|
|
"entropy": 5.399175214767456,
|
|
"epoch": 2.8775476110925493,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004174667675347032,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.23807730823755263,
|
|
"num_tokens": 63388414.0,
|
|
"step": 34450
|
|
},
|
|
{
|
|
"entropy": 5.362833881378174,
|
|
"epoch": 2.877965252255262,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004174437243260104,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.2310833677649498,
|
|
"num_tokens": 63397906.0,
|
|
"step": 34455
|
|
},
|
|
{
|
|
"entropy": 5.410326051712036,
|
|
"epoch": 2.8783828934179754,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004174206786236687,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.23478136509656905,
|
|
"num_tokens": 63406652.0,
|
|
"step": 34460
|
|
},
|
|
{
|
|
"entropy": 5.443180990219116,
|
|
"epoch": 2.878800534580688,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041739763042808166,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.23456289917230605,
|
|
"num_tokens": 63416630.0,
|
|
"step": 34465
|
|
},
|
|
{
|
|
"entropy": 5.44725079536438,
|
|
"epoch": 2.879218175743401,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041737457973965264,
|
|
"loss": 4.7642,
|
|
"mean_token_accuracy": 0.23454587608575822,
|
|
"num_tokens": 63425278.0,
|
|
"step": 34470
|
|
},
|
|
{
|
|
"entropy": 5.473770332336426,
|
|
"epoch": 2.8796358169061143,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00041735152655878523,
|
|
"loss": 4.8736,
|
|
"mean_token_accuracy": 0.23497296273708343,
|
|
"num_tokens": 63434162.0,
|
|
"step": 34475
|
|
},
|
|
{
|
|
"entropy": 5.438444185256958,
|
|
"epoch": 2.8800534580688275,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000417328470885883,
|
|
"loss": 4.7015,
|
|
"mean_token_accuracy": 0.23651163578033446,
|
|
"num_tokens": 63443475.0,
|
|
"step": 34480
|
|
},
|
|
{
|
|
"entropy": 5.43589415550232,
|
|
"epoch": 2.8804710992315403,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00041730541272134964,
|
|
"loss": 4.6552,
|
|
"mean_token_accuracy": 0.22813935279846193,
|
|
"num_tokens": 63452840.0,
|
|
"step": 34485
|
|
},
|
|
{
|
|
"entropy": 5.370504903793335,
|
|
"epoch": 2.880888740394253,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004172823520655887,
|
|
"loss": 4.7493,
|
|
"mean_token_accuracy": 0.22712796777486802,
|
|
"num_tokens": 63462120.0,
|
|
"step": 34490
|
|
},
|
|
{
|
|
"entropy": 5.400694370269775,
|
|
"epoch": 2.8813063815569664,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00041725928891900386,
|
|
"loss": 4.6309,
|
|
"mean_token_accuracy": 0.24698080122470856,
|
|
"num_tokens": 63470179.0,
|
|
"step": 34495
|
|
},
|
|
{
|
|
"entropy": 5.510091781616211,
|
|
"epoch": 2.881724022719679,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041723622328199893,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.22570740729570388,
|
|
"num_tokens": 63479660.0,
|
|
"step": 34500
|
|
},
|
|
{
|
|
"entropy": 5.418975830078125,
|
|
"epoch": 2.8821416638823925,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004172131551549778,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.2272743374109268,
|
|
"num_tokens": 63489011.0,
|
|
"step": 34505
|
|
},
|
|
{
|
|
"entropy": 5.494166374206543,
|
|
"epoch": 2.8825593050451053,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004171900845383441,
|
|
"loss": 4.8267,
|
|
"mean_token_accuracy": 0.23005935698747634,
|
|
"num_tokens": 63498312.0,
|
|
"step": 34510
|
|
},
|
|
{
|
|
"entropy": 5.466031217575074,
|
|
"epoch": 2.882976946207818,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041716701143250184,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.2342124402523041,
|
|
"num_tokens": 63508631.0,
|
|
"step": 34515
|
|
},
|
|
{
|
|
"entropy": 5.492269372940063,
|
|
"epoch": 2.8833945873705313,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000417143935837855,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.22487257272005082,
|
|
"num_tokens": 63517675.0,
|
|
"step": 34520
|
|
},
|
|
{
|
|
"entropy": 5.439898443222046,
|
|
"epoch": 2.883812228533244,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004171208577548074,
|
|
"loss": 4.7772,
|
|
"mean_token_accuracy": 0.2216387391090393,
|
|
"num_tokens": 63526184.0,
|
|
"step": 34525
|
|
},
|
|
{
|
|
"entropy": 5.378620910644531,
|
|
"epoch": 2.8842298696959574,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041709777718376315,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.24248403012752534,
|
|
"num_tokens": 63534886.0,
|
|
"step": 34530
|
|
},
|
|
{
|
|
"entropy": 5.417487764358521,
|
|
"epoch": 2.88464751085867,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041707469412512616,
|
|
"loss": 4.6913,
|
|
"mean_token_accuracy": 0.23671503216028214,
|
|
"num_tokens": 63545687.0,
|
|
"step": 34535
|
|
},
|
|
{
|
|
"entropy": 5.488008069992065,
|
|
"epoch": 2.885065152021383,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041705160857930077,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.22899603545665742,
|
|
"num_tokens": 63555309.0,
|
|
"step": 34540
|
|
},
|
|
{
|
|
"entropy": 5.440210485458374,
|
|
"epoch": 2.8854827931840963,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004170285205466909,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.2294408604502678,
|
|
"num_tokens": 63564641.0,
|
|
"step": 34545
|
|
},
|
|
{
|
|
"entropy": 5.425672483444214,
|
|
"epoch": 2.885900434346809,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004170054300277009,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.22808676809072495,
|
|
"num_tokens": 63573957.0,
|
|
"step": 34550
|
|
},
|
|
{
|
|
"entropy": 5.503890419006348,
|
|
"epoch": 2.8863180755095224,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004169823370227348,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.230757175385952,
|
|
"num_tokens": 63583000.0,
|
|
"step": 34555
|
|
},
|
|
{
|
|
"entropy": 5.512708139419556,
|
|
"epoch": 2.886735716672235,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041695924153219713,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.22167030423879625,
|
|
"num_tokens": 63591669.0,
|
|
"step": 34560
|
|
},
|
|
{
|
|
"entropy": 5.53018102645874,
|
|
"epoch": 2.887153357834948,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004169361435564919,
|
|
"loss": 4.8189,
|
|
"mean_token_accuracy": 0.2243010386824608,
|
|
"num_tokens": 63601420.0,
|
|
"step": 34565
|
|
},
|
|
{
|
|
"entropy": 5.455017805099487,
|
|
"epoch": 2.8875709989976612,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004169130430960237,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.2263488218188286,
|
|
"num_tokens": 63610850.0,
|
|
"step": 34570
|
|
},
|
|
{
|
|
"entropy": 5.485540103912354,
|
|
"epoch": 2.887988640160374,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004168899401511969,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.23510864228010178,
|
|
"num_tokens": 63619737.0,
|
|
"step": 34575
|
|
},
|
|
{
|
|
"entropy": 5.375499296188354,
|
|
"epoch": 2.8884062813230873,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004168668347224158,
|
|
"loss": 4.6687,
|
|
"mean_token_accuracy": 0.22607187181711197,
|
|
"num_tokens": 63628347.0,
|
|
"step": 34580
|
|
},
|
|
{
|
|
"entropy": 5.460916185379029,
|
|
"epoch": 2.8888239224858,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041684372681008506,
|
|
"loss": 4.7655,
|
|
"mean_token_accuracy": 0.22415265589952468,
|
|
"num_tokens": 63637432.0,
|
|
"step": 34585
|
|
},
|
|
{
|
|
"entropy": 5.416240882873535,
|
|
"epoch": 2.889241563648513,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004168206164146092,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.2341986835002899,
|
|
"num_tokens": 63646478.0,
|
|
"step": 34590
|
|
},
|
|
{
|
|
"entropy": 5.466029119491577,
|
|
"epoch": 2.889659204811226,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041679750353639265,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.21976589560508727,
|
|
"num_tokens": 63656821.0,
|
|
"step": 34595
|
|
},
|
|
{
|
|
"entropy": 5.476933240890503,
|
|
"epoch": 2.8900768459739394,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041677438817584023,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.23539381325244904,
|
|
"num_tokens": 63665991.0,
|
|
"step": 34600
|
|
},
|
|
{
|
|
"entropy": 5.453360986709595,
|
|
"epoch": 2.8904944871366522,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041675127033335643,
|
|
"loss": 4.7439,
|
|
"mean_token_accuracy": 0.22770127207040786,
|
|
"num_tokens": 63674962.0,
|
|
"step": 34605
|
|
},
|
|
{
|
|
"entropy": 5.467220830917358,
|
|
"epoch": 2.890912128299365,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000416728150009346,
|
|
"loss": 4.7852,
|
|
"mean_token_accuracy": 0.22571492791175843,
|
|
"num_tokens": 63685154.0,
|
|
"step": 34610
|
|
},
|
|
{
|
|
"entropy": 5.471195936203003,
|
|
"epoch": 2.8913297694620783,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041670502720421367,
|
|
"loss": 4.7305,
|
|
"mean_token_accuracy": 0.23024802654981613,
|
|
"num_tokens": 63695132.0,
|
|
"step": 34615
|
|
},
|
|
{
|
|
"entropy": 5.444866418838501,
|
|
"epoch": 2.891747410624791,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004166819019183643,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.23299162536859513,
|
|
"num_tokens": 63703638.0,
|
|
"step": 34620
|
|
},
|
|
{
|
|
"entropy": 5.499794816970825,
|
|
"epoch": 2.8921650517875044,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004166587741522027,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.2217629596590996,
|
|
"num_tokens": 63712713.0,
|
|
"step": 34625
|
|
},
|
|
{
|
|
"entropy": 5.499707889556885,
|
|
"epoch": 2.892582692950217,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004166356439061338,
|
|
"loss": 4.7534,
|
|
"mean_token_accuracy": 0.2335818126797676,
|
|
"num_tokens": 63722279.0,
|
|
"step": 34630
|
|
},
|
|
{
|
|
"entropy": 5.376636171340943,
|
|
"epoch": 2.89300033411293,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041661251118056236,
|
|
"loss": 4.6581,
|
|
"mean_token_accuracy": 0.23513972163200378,
|
|
"num_tokens": 63731347.0,
|
|
"step": 34635
|
|
},
|
|
{
|
|
"entropy": 5.4641541004180905,
|
|
"epoch": 2.8934179752756433,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004165893759758935,
|
|
"loss": 4.6894,
|
|
"mean_token_accuracy": 0.2351265788078308,
|
|
"num_tokens": 63740712.0,
|
|
"step": 34640
|
|
},
|
|
{
|
|
"entropy": 5.454435348510742,
|
|
"epoch": 2.893835616438356,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004165662382925322,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.22593940049409866,
|
|
"num_tokens": 63750018.0,
|
|
"step": 34645
|
|
},
|
|
{
|
|
"entropy": 5.4580726146698,
|
|
"epoch": 2.8942532576010693,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041654309813088353,
|
|
"loss": 4.7708,
|
|
"mean_token_accuracy": 0.23478951305150986,
|
|
"num_tokens": 63759492.0,
|
|
"step": 34650
|
|
},
|
|
{
|
|
"entropy": 5.54604024887085,
|
|
"epoch": 2.894670898763782,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004165199554913525,
|
|
"loss": 4.8115,
|
|
"mean_token_accuracy": 0.22911703139543532,
|
|
"num_tokens": 63769361.0,
|
|
"step": 34655
|
|
},
|
|
{
|
|
"entropy": 5.474279403686523,
|
|
"epoch": 2.895088539926495,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004164968103743443,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.22291247248649598,
|
|
"num_tokens": 63779367.0,
|
|
"step": 34660
|
|
},
|
|
{
|
|
"entropy": 5.476709222793579,
|
|
"epoch": 2.895506181089208,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041647366278026415,
|
|
"loss": 4.7823,
|
|
"mean_token_accuracy": 0.23017982691526412,
|
|
"num_tokens": 63788850.0,
|
|
"step": 34665
|
|
},
|
|
{
|
|
"entropy": 5.385573530197144,
|
|
"epoch": 2.895923822251921,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004164505127095172,
|
|
"loss": 4.6138,
|
|
"mean_token_accuracy": 0.24325916469097136,
|
|
"num_tokens": 63798076.0,
|
|
"step": 34670
|
|
},
|
|
{
|
|
"entropy": 5.4037786483764645,
|
|
"epoch": 2.8963414634146343,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004164273601625088,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.2353105589747429,
|
|
"num_tokens": 63807553.0,
|
|
"step": 34675
|
|
},
|
|
{
|
|
"entropy": 5.5530092239379885,
|
|
"epoch": 2.896759104577347,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041640420513964414,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.2180825874209404,
|
|
"num_tokens": 63817663.0,
|
|
"step": 34680
|
|
},
|
|
{
|
|
"entropy": 5.566191005706787,
|
|
"epoch": 2.89717674574006,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004163810476413287,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.2214255914092064,
|
|
"num_tokens": 63826652.0,
|
|
"step": 34685
|
|
},
|
|
{
|
|
"entropy": 5.428584623336792,
|
|
"epoch": 2.897594386902773,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041635788766796795,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.23672729432582856,
|
|
"num_tokens": 63835704.0,
|
|
"step": 34690
|
|
},
|
|
{
|
|
"entropy": 5.401886796951294,
|
|
"epoch": 2.8980120280654864,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004163347252199671,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.2317776009440422,
|
|
"num_tokens": 63844844.0,
|
|
"step": 34695
|
|
},
|
|
{
|
|
"entropy": 5.42690896987915,
|
|
"epoch": 2.8984296692281992,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004163115602977318,
|
|
"loss": 4.7644,
|
|
"mean_token_accuracy": 0.23287310004234313,
|
|
"num_tokens": 63853589.0,
|
|
"step": 34700
|
|
},
|
|
{
|
|
"entropy": 5.479241418838501,
|
|
"epoch": 2.898847310390912,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041628839290166754,
|
|
"loss": 4.7784,
|
|
"mean_token_accuracy": 0.23575250059366226,
|
|
"num_tokens": 63863426.0,
|
|
"step": 34705
|
|
},
|
|
{
|
|
"entropy": 5.406384134292603,
|
|
"epoch": 2.8992649515536253,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004162652230321799,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.2339847654104233,
|
|
"num_tokens": 63873484.0,
|
|
"step": 34710
|
|
},
|
|
{
|
|
"entropy": 5.509574556350708,
|
|
"epoch": 2.899682592716338,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004162420506896745,
|
|
"loss": 4.7695,
|
|
"mean_token_accuracy": 0.23141494989395142,
|
|
"num_tokens": 63883504.0,
|
|
"step": 34715
|
|
},
|
|
{
|
|
"entropy": 5.420056772232056,
|
|
"epoch": 2.9001002338790514,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004162188758745569,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.23679575324058533,
|
|
"num_tokens": 63892978.0,
|
|
"step": 34720
|
|
},
|
|
{
|
|
"entropy": 5.448184776306152,
|
|
"epoch": 2.900517875041764,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000416195698587233,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.22588256597518921,
|
|
"num_tokens": 63903601.0,
|
|
"step": 34725
|
|
},
|
|
{
|
|
"entropy": 5.438631916046143,
|
|
"epoch": 2.900935516204477,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041617251882810843,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.238840152323246,
|
|
"num_tokens": 63912562.0,
|
|
"step": 34730
|
|
},
|
|
{
|
|
"entropy": 5.463531398773194,
|
|
"epoch": 2.9013531573671902,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000416149336597589,
|
|
"loss": 4.7724,
|
|
"mean_token_accuracy": 0.23107641488313674,
|
|
"num_tokens": 63921787.0,
|
|
"step": 34735
|
|
},
|
|
{
|
|
"entropy": 5.408797550201416,
|
|
"epoch": 2.901770798529903,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004161261518960804,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.22982185930013657,
|
|
"num_tokens": 63931062.0,
|
|
"step": 34740
|
|
},
|
|
{
|
|
"entropy": 5.449146890640259,
|
|
"epoch": 2.9021884396926163,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041610296472398875,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.23461076915264129,
|
|
"num_tokens": 63940045.0,
|
|
"step": 34745
|
|
},
|
|
{
|
|
"entropy": 5.515280485153198,
|
|
"epoch": 2.902606080855329,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004160797750817199,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.2306615710258484,
|
|
"num_tokens": 63949524.0,
|
|
"step": 34750
|
|
},
|
|
{
|
|
"entropy": 5.4760411262512205,
|
|
"epoch": 2.903023722018042,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004160565829696797,
|
|
"loss": 4.7429,
|
|
"mean_token_accuracy": 0.2272467255592346,
|
|
"num_tokens": 63958953.0,
|
|
"step": 34755
|
|
},
|
|
{
|
|
"entropy": 5.519264125823975,
|
|
"epoch": 2.903441363180755,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041603338838827413,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.22255536317825317,
|
|
"num_tokens": 63968735.0,
|
|
"step": 34760
|
|
},
|
|
{
|
|
"entropy": 5.468580865859986,
|
|
"epoch": 2.903859004343468,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041601019133790946,
|
|
"loss": 4.7749,
|
|
"mean_token_accuracy": 0.2366337075829506,
|
|
"num_tokens": 63977765.0,
|
|
"step": 34765
|
|
},
|
|
{
|
|
"entropy": 5.466966772079468,
|
|
"epoch": 2.9042766455061813,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041598699181899165,
|
|
"loss": 4.7484,
|
|
"mean_token_accuracy": 0.23324145376682281,
|
|
"num_tokens": 63987278.0,
|
|
"step": 34770
|
|
},
|
|
{
|
|
"entropy": 5.433448410034179,
|
|
"epoch": 2.904694286668894,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004159637898319268,
|
|
"loss": 4.7537,
|
|
"mean_token_accuracy": 0.22669663280248642,
|
|
"num_tokens": 63996621.0,
|
|
"step": 34775
|
|
},
|
|
{
|
|
"entropy": 5.520322370529175,
|
|
"epoch": 2.905111927831607,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041594058537712113,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.2251855880022049,
|
|
"num_tokens": 64004817.0,
|
|
"step": 34780
|
|
},
|
|
{
|
|
"entropy": 5.468614721298218,
|
|
"epoch": 2.90552956899432,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041591737845498097,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.23421159386634827,
|
|
"num_tokens": 64014810.0,
|
|
"step": 34785
|
|
},
|
|
{
|
|
"entropy": 5.371458911895752,
|
|
"epoch": 2.905947210157033,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004158941690659123,
|
|
"loss": 4.6474,
|
|
"mean_token_accuracy": 0.24099169820547103,
|
|
"num_tokens": 64024021.0,
|
|
"step": 34790
|
|
},
|
|
{
|
|
"entropy": 5.475556802749634,
|
|
"epoch": 2.906364851319746,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041587095721032174,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.21934166699647903,
|
|
"num_tokens": 64033726.0,
|
|
"step": 34795
|
|
},
|
|
{
|
|
"entropy": 5.445285034179688,
|
|
"epoch": 2.906782492482459,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004158477428886155,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.23089072853326797,
|
|
"num_tokens": 64043482.0,
|
|
"step": 34800
|
|
},
|
|
{
|
|
"entropy": 5.5020294189453125,
|
|
"epoch": 2.907200133645172,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004158245261011999,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.2280726671218872,
|
|
"num_tokens": 64052536.0,
|
|
"step": 34805
|
|
},
|
|
{
|
|
"entropy": 5.439874076843262,
|
|
"epoch": 2.907617774807885,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004158013068484816,
|
|
"loss": 4.6876,
|
|
"mean_token_accuracy": 0.23848337829113006,
|
|
"num_tokens": 64061288.0,
|
|
"step": 34810
|
|
},
|
|
{
|
|
"entropy": 5.412546539306641,
|
|
"epoch": 2.9080354159705983,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041577808513086677,
|
|
"loss": 4.7547,
|
|
"mean_token_accuracy": 0.2282973676919937,
|
|
"num_tokens": 64071141.0,
|
|
"step": 34815
|
|
},
|
|
{
|
|
"entropy": 5.4916651248931885,
|
|
"epoch": 2.908453057133311,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041575486094876226,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.22706075012683868,
|
|
"num_tokens": 64080657.0,
|
|
"step": 34820
|
|
},
|
|
{
|
|
"entropy": 5.513967657089234,
|
|
"epoch": 2.908870698296024,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041573163430257435,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.2314266011118889,
|
|
"num_tokens": 64089595.0,
|
|
"step": 34825
|
|
},
|
|
{
|
|
"entropy": 5.591676425933838,
|
|
"epoch": 2.909288339458737,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004157084051927099,
|
|
"loss": 4.7674,
|
|
"mean_token_accuracy": 0.2304691791534424,
|
|
"num_tokens": 64097980.0,
|
|
"step": 34830
|
|
},
|
|
{
|
|
"entropy": 5.496571111679077,
|
|
"epoch": 2.90970598062145,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004156851736195753,
|
|
"loss": 4.8412,
|
|
"mean_token_accuracy": 0.22898642271757125,
|
|
"num_tokens": 64107848.0,
|
|
"step": 34835
|
|
},
|
|
{
|
|
"entropy": 5.464176177978516,
|
|
"epoch": 2.9101236217841633,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004156619395835775,
|
|
"loss": 4.8107,
|
|
"mean_token_accuracy": 0.22758155614137648,
|
|
"num_tokens": 64117264.0,
|
|
"step": 34840
|
|
},
|
|
{
|
|
"entropy": 5.514653539657592,
|
|
"epoch": 2.910541262946876,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00041563870308512313,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.2325210839509964,
|
|
"num_tokens": 64126115.0,
|
|
"step": 34845
|
|
},
|
|
{
|
|
"entropy": 5.519900131225586,
|
|
"epoch": 2.910958904109589,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000415615464124619,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.22845164984464644,
|
|
"num_tokens": 64135053.0,
|
|
"step": 34850
|
|
},
|
|
{
|
|
"entropy": 5.491886377334595,
|
|
"epoch": 2.911376545272302,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041559222270247186,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.23567525744438172,
|
|
"num_tokens": 64144008.0,
|
|
"step": 34855
|
|
},
|
|
{
|
|
"entropy": 5.466952276229859,
|
|
"epoch": 2.911794186435015,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004155689788190886,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.23534658104181289,
|
|
"num_tokens": 64153288.0,
|
|
"step": 34860
|
|
},
|
|
{
|
|
"entropy": 5.402505159378052,
|
|
"epoch": 2.9122118275977282,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041554573247487624,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.2364509657025337,
|
|
"num_tokens": 64162492.0,
|
|
"step": 34865
|
|
},
|
|
{
|
|
"entropy": 5.382042598724365,
|
|
"epoch": 2.912629468760441,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041552248367024164,
|
|
"loss": 4.6305,
|
|
"mean_token_accuracy": 0.23457163125276564,
|
|
"num_tokens": 64171260.0,
|
|
"step": 34870
|
|
},
|
|
{
|
|
"entropy": 5.4760393619537355,
|
|
"epoch": 2.913047109923154,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041549923240559173,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.22657996863126756,
|
|
"num_tokens": 64181158.0,
|
|
"step": 34875
|
|
},
|
|
{
|
|
"entropy": 5.499052953720093,
|
|
"epoch": 2.913464751085867,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004154759786813338,
|
|
"loss": 4.8226,
|
|
"mean_token_accuracy": 0.22196921408176423,
|
|
"num_tokens": 64189327.0,
|
|
"step": 34880
|
|
},
|
|
{
|
|
"entropy": 5.482493734359741,
|
|
"epoch": 2.91388239224858,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004154527224978746,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.23605631589889525,
|
|
"num_tokens": 64198508.0,
|
|
"step": 34885
|
|
},
|
|
{
|
|
"entropy": 5.387004852294922,
|
|
"epoch": 2.914300033411293,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041542946385562154,
|
|
"loss": 4.648,
|
|
"mean_token_accuracy": 0.23121312856674195,
|
|
"num_tokens": 64207216.0,
|
|
"step": 34890
|
|
},
|
|
{
|
|
"entropy": 5.45161509513855,
|
|
"epoch": 2.914717674574006,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004154062027549817,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.22752996832132338,
|
|
"num_tokens": 64216517.0,
|
|
"step": 34895
|
|
},
|
|
{
|
|
"entropy": 5.435899543762207,
|
|
"epoch": 2.915135315736719,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00041538293919636223,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.245024973154068,
|
|
"num_tokens": 64225509.0,
|
|
"step": 34900
|
|
},
|
|
{
|
|
"entropy": 5.479071521759034,
|
|
"epoch": 2.915552956899432,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041535967318017037,
|
|
"loss": 4.7503,
|
|
"mean_token_accuracy": 0.2216125547885895,
|
|
"num_tokens": 64233786.0,
|
|
"step": 34905
|
|
},
|
|
{
|
|
"entropy": 5.396238565444946,
|
|
"epoch": 2.915970598062145,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041533640470681356,
|
|
"loss": 4.6521,
|
|
"mean_token_accuracy": 0.23495120257139207,
|
|
"num_tokens": 64242766.0,
|
|
"step": 34910
|
|
},
|
|
{
|
|
"entropy": 5.4279172897338865,
|
|
"epoch": 2.916388239224858,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004153131337766991,
|
|
"loss": 4.7025,
|
|
"mean_token_accuracy": 0.22907793074846267,
|
|
"num_tokens": 64252759.0,
|
|
"step": 34915
|
|
},
|
|
{
|
|
"entropy": 5.37427134513855,
|
|
"epoch": 2.916805880387571,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041528986039023416,
|
|
"loss": 4.7086,
|
|
"mean_token_accuracy": 0.23397228121757507,
|
|
"num_tokens": 64262390.0,
|
|
"step": 34920
|
|
},
|
|
{
|
|
"entropy": 5.485769033432007,
|
|
"epoch": 2.9172235215502837,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004152665845478265,
|
|
"loss": 4.835,
|
|
"mean_token_accuracy": 0.22232805341482162,
|
|
"num_tokens": 64271797.0,
|
|
"step": 34925
|
|
},
|
|
{
|
|
"entropy": 5.530103540420532,
|
|
"epoch": 2.917641162712997,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004152433062498834,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.22035193890333177,
|
|
"num_tokens": 64280982.0,
|
|
"step": 34930
|
|
},
|
|
{
|
|
"entropy": 5.48516001701355,
|
|
"epoch": 2.9180588038757103,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041522002549681245,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.2325693130493164,
|
|
"num_tokens": 64289542.0,
|
|
"step": 34935
|
|
},
|
|
{
|
|
"entropy": 5.501918935775757,
|
|
"epoch": 2.918476445038423,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004151967422890211,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.23060595542192458,
|
|
"num_tokens": 64298638.0,
|
|
"step": 34940
|
|
},
|
|
{
|
|
"entropy": 5.405947875976563,
|
|
"epoch": 2.918894086201136,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041517345662691707,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.22414298206567765,
|
|
"num_tokens": 64307698.0,
|
|
"step": 34945
|
|
},
|
|
{
|
|
"entropy": 5.501819038391114,
|
|
"epoch": 2.919311727363849,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004151501685109079,
|
|
"loss": 4.7927,
|
|
"mean_token_accuracy": 0.23378607779741287,
|
|
"num_tokens": 64316435.0,
|
|
"step": 34950
|
|
},
|
|
{
|
|
"entropy": 5.457168102264404,
|
|
"epoch": 2.919729368526562,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004151268779414014,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.2399871215224266,
|
|
"num_tokens": 64325474.0,
|
|
"step": 34955
|
|
},
|
|
{
|
|
"entropy": 5.403924465179443,
|
|
"epoch": 2.920147009689275,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004151035849188053,
|
|
"loss": 4.6924,
|
|
"mean_token_accuracy": 0.23463729172945022,
|
|
"num_tokens": 64333690.0,
|
|
"step": 34960
|
|
},
|
|
{
|
|
"entropy": 5.441748428344726,
|
|
"epoch": 2.920564650851988,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004150802894435271,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.22568330764770508,
|
|
"num_tokens": 64342933.0,
|
|
"step": 34965
|
|
},
|
|
{
|
|
"entropy": 5.480485725402832,
|
|
"epoch": 2.920982292014701,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000415056991515975,
|
|
"loss": 4.6821,
|
|
"mean_token_accuracy": 0.23654484748840332,
|
|
"num_tokens": 64351577.0,
|
|
"step": 34970
|
|
},
|
|
{
|
|
"entropy": 5.501284074783325,
|
|
"epoch": 2.921399933177414,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041503369113655655,
|
|
"loss": 4.8154,
|
|
"mean_token_accuracy": 0.2250494986772537,
|
|
"num_tokens": 64360574.0,
|
|
"step": 34975
|
|
},
|
|
{
|
|
"entropy": 5.5680553913116455,
|
|
"epoch": 2.921817574340127,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004150103883056799,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.2201998621225357,
|
|
"num_tokens": 64369670.0,
|
|
"step": 34980
|
|
},
|
|
{
|
|
"entropy": 5.424123048782349,
|
|
"epoch": 2.92223521550284,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041498708302375277,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.23427943140268326,
|
|
"num_tokens": 64378937.0,
|
|
"step": 34985
|
|
},
|
|
{
|
|
"entropy": 5.460099744796753,
|
|
"epoch": 2.922652856665553,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041496377529118327,
|
|
"loss": 4.8751,
|
|
"mean_token_accuracy": 0.2207508310675621,
|
|
"num_tokens": 64388391.0,
|
|
"step": 34990
|
|
},
|
|
{
|
|
"entropy": 5.4333741664886475,
|
|
"epoch": 2.923070497828266,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004149404651083794,
|
|
"loss": 4.7198,
|
|
"mean_token_accuracy": 0.23202987760305405,
|
|
"num_tokens": 64397561.0,
|
|
"step": 34995
|
|
},
|
|
{
|
|
"entropy": 5.431120729446411,
|
|
"epoch": 2.923488138990979,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004149171524757493,
|
|
"loss": 4.654,
|
|
"mean_token_accuracy": 0.23818611204624177,
|
|
"num_tokens": 64407025.0,
|
|
"step": 35000
|
|
},
|
|
{
|
|
"entropy": 5.453897905349732,
|
|
"epoch": 2.923905780153692,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041489383739370093,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.22990001887083053,
|
|
"num_tokens": 64416084.0,
|
|
"step": 35005
|
|
},
|
|
{
|
|
"entropy": 5.445341396331787,
|
|
"epoch": 2.924323421316405,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00041487051986264264,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.22646587193012238,
|
|
"num_tokens": 64424456.0,
|
|
"step": 35010
|
|
},
|
|
{
|
|
"entropy": 5.428807640075684,
|
|
"epoch": 2.924741062479118,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00041484719988298254,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.22784603238105774,
|
|
"num_tokens": 64432585.0,
|
|
"step": 35015
|
|
},
|
|
{
|
|
"entropy": 5.43085823059082,
|
|
"epoch": 2.9251587036418307,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004148238774551288,
|
|
"loss": 4.7198,
|
|
"mean_token_accuracy": 0.23135450184345246,
|
|
"num_tokens": 64441588.0,
|
|
"step": 35020
|
|
},
|
|
{
|
|
"entropy": 5.357577753067017,
|
|
"epoch": 2.925576344804544,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041480055257948976,
|
|
"loss": 4.6301,
|
|
"mean_token_accuracy": 0.2399807393550873,
|
|
"num_tokens": 64450900.0,
|
|
"step": 35025
|
|
},
|
|
{
|
|
"entropy": 5.3912781238555905,
|
|
"epoch": 2.925993985967257,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004147772252564739,
|
|
"loss": 4.7262,
|
|
"mean_token_accuracy": 0.23072319775819777,
|
|
"num_tokens": 64460238.0,
|
|
"step": 35030
|
|
},
|
|
{
|
|
"entropy": 5.435874319076538,
|
|
"epoch": 2.92641162712997,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041475389548648934,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.21969443708658218,
|
|
"num_tokens": 64469259.0,
|
|
"step": 35035
|
|
},
|
|
{
|
|
"entropy": 5.421699953079224,
|
|
"epoch": 2.926829268292683,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004147305632699447,
|
|
"loss": 4.694,
|
|
"mean_token_accuracy": 0.2423102766275406,
|
|
"num_tokens": 64477929.0,
|
|
"step": 35040
|
|
},
|
|
{
|
|
"entropy": 5.501858329772949,
|
|
"epoch": 2.9272469094553957,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004147072286072483,
|
|
"loss": 4.8475,
|
|
"mean_token_accuracy": 0.21754785776138305,
|
|
"num_tokens": 64487209.0,
|
|
"step": 35045
|
|
},
|
|
{
|
|
"entropy": 5.385307121276855,
|
|
"epoch": 2.927664550618109,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004146838914988087,
|
|
"loss": 4.6371,
|
|
"mean_token_accuracy": 0.23937476873397828,
|
|
"num_tokens": 64495258.0,
|
|
"step": 35050
|
|
},
|
|
{
|
|
"entropy": 5.46028151512146,
|
|
"epoch": 2.928082191780822,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004146605519450345,
|
|
"loss": 4.6812,
|
|
"mean_token_accuracy": 0.23276206851005554,
|
|
"num_tokens": 64504213.0,
|
|
"step": 35055
|
|
},
|
|
{
|
|
"entropy": 5.375036144256592,
|
|
"epoch": 2.928499832943535,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041463720994633417,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.22157876938581467,
|
|
"num_tokens": 64514036.0,
|
|
"step": 35060
|
|
},
|
|
{
|
|
"entropy": 5.34125394821167,
|
|
"epoch": 2.928917474106248,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004146138655031165,
|
|
"loss": 4.5766,
|
|
"mean_token_accuracy": 0.23919955790042877,
|
|
"num_tokens": 64522917.0,
|
|
"step": 35065
|
|
},
|
|
{
|
|
"entropy": 5.452179956436157,
|
|
"epoch": 2.929335115268961,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041459051861578996,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.23702345490455629,
|
|
"num_tokens": 64531586.0,
|
|
"step": 35070
|
|
},
|
|
{
|
|
"entropy": 5.485323476791382,
|
|
"epoch": 2.929752756431674,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041456716928476336,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.23212043195962906,
|
|
"num_tokens": 64542670.0,
|
|
"step": 35075
|
|
},
|
|
{
|
|
"entropy": 5.429648160934448,
|
|
"epoch": 2.930170397594387,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004145438175104455,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.2389295816421509,
|
|
"num_tokens": 64551155.0,
|
|
"step": 35080
|
|
},
|
|
{
|
|
"entropy": 5.477827739715576,
|
|
"epoch": 2.9305880387571,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004145204632932451,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.22355481535196303,
|
|
"num_tokens": 64559732.0,
|
|
"step": 35085
|
|
},
|
|
{
|
|
"entropy": 5.366867542266846,
|
|
"epoch": 2.9310056799198128,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004144971066335711,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.23792721182107926,
|
|
"num_tokens": 64568566.0,
|
|
"step": 35090
|
|
},
|
|
{
|
|
"entropy": 5.354608869552612,
|
|
"epoch": 2.931423321082526,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041447374753183233,
|
|
"loss": 4.6529,
|
|
"mean_token_accuracy": 0.23840927928686143,
|
|
"num_tokens": 64577700.0,
|
|
"step": 35095
|
|
},
|
|
{
|
|
"entropy": 5.3916332721710205,
|
|
"epoch": 2.931840962245239,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004144503859884377,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.23715971112251283,
|
|
"num_tokens": 64587260.0,
|
|
"step": 35100
|
|
},
|
|
{
|
|
"entropy": 5.552102947235108,
|
|
"epoch": 2.932258603407952,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041442702200379623,
|
|
"loss": 4.843,
|
|
"mean_token_accuracy": 0.22233431786298752,
|
|
"num_tokens": 64596038.0,
|
|
"step": 35105
|
|
},
|
|
{
|
|
"entropy": 5.459207534790039,
|
|
"epoch": 2.932676244570665,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041440365557831693,
|
|
"loss": 4.7141,
|
|
"mean_token_accuracy": 0.23467947989702226,
|
|
"num_tokens": 64605555.0,
|
|
"step": 35110
|
|
},
|
|
{
|
|
"entropy": 5.465737581253052,
|
|
"epoch": 2.9330938857333777,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041438028671240875,
|
|
"loss": 4.7003,
|
|
"mean_token_accuracy": 0.23444557785987855,
|
|
"num_tokens": 64614610.0,
|
|
"step": 35115
|
|
},
|
|
{
|
|
"entropy": 5.367400169372559,
|
|
"epoch": 2.933511526896091,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041435691540648103,
|
|
"loss": 4.6435,
|
|
"mean_token_accuracy": 0.2356817752122879,
|
|
"num_tokens": 64623485.0,
|
|
"step": 35120
|
|
},
|
|
{
|
|
"entropy": 5.430563497543335,
|
|
"epoch": 2.9339291680588038,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004143335416609426,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.23931485712528228,
|
|
"num_tokens": 64632217.0,
|
|
"step": 35125
|
|
},
|
|
{
|
|
"entropy": 5.477476978302002,
|
|
"epoch": 2.934346809221517,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004143101654762029,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.22946077585220337,
|
|
"num_tokens": 64641347.0,
|
|
"step": 35130
|
|
},
|
|
{
|
|
"entropy": 5.451455163955688,
|
|
"epoch": 2.93476445038423,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041428678685267106,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.22983737736940385,
|
|
"num_tokens": 64651059.0,
|
|
"step": 35135
|
|
},
|
|
{
|
|
"entropy": 5.464876174926758,
|
|
"epoch": 2.9351820915469427,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041426340579075636,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.21796171367168427,
|
|
"num_tokens": 64661088.0,
|
|
"step": 35140
|
|
},
|
|
{
|
|
"entropy": 5.525548124313355,
|
|
"epoch": 2.935599732709656,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004142400222908681,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.2249241888523102,
|
|
"num_tokens": 64669952.0,
|
|
"step": 35145
|
|
},
|
|
{
|
|
"entropy": 5.460182523727417,
|
|
"epoch": 2.9360173738723687,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004142166363534156,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.2270788311958313,
|
|
"num_tokens": 64680337.0,
|
|
"step": 35150
|
|
},
|
|
{
|
|
"entropy": 5.378557586669922,
|
|
"epoch": 2.936435015035082,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004141932479788084,
|
|
"loss": 4.6396,
|
|
"mean_token_accuracy": 0.23787984549999236,
|
|
"num_tokens": 64688603.0,
|
|
"step": 35155
|
|
},
|
|
{
|
|
"entropy": 5.496641016006469,
|
|
"epoch": 2.936852656197795,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00041416985716745576,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.21957632452249526,
|
|
"num_tokens": 64697655.0,
|
|
"step": 35160
|
|
},
|
|
{
|
|
"entropy": 5.466786813735962,
|
|
"epoch": 2.9372702973605076,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004141464639197673,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.22867263108491898,
|
|
"num_tokens": 64706472.0,
|
|
"step": 35165
|
|
},
|
|
{
|
|
"entropy": 5.408323478698731,
|
|
"epoch": 2.937687938523221,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004141230682361525,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.24337709099054336,
|
|
"num_tokens": 64715625.0,
|
|
"step": 35170
|
|
},
|
|
{
|
|
"entropy": 5.375941038131714,
|
|
"epoch": 2.938105579685934,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041409967011702087,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.22858064174652098,
|
|
"num_tokens": 64724369.0,
|
|
"step": 35175
|
|
},
|
|
{
|
|
"entropy": 5.435696220397949,
|
|
"epoch": 2.938523220848647,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004140762695627822,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.23355981856584548,
|
|
"num_tokens": 64733016.0,
|
|
"step": 35180
|
|
},
|
|
{
|
|
"entropy": 5.469955825805664,
|
|
"epoch": 2.9389408620113597,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00041405286657384587,
|
|
"loss": 4.7161,
|
|
"mean_token_accuracy": 0.2289668008685112,
|
|
"num_tokens": 64741049.0,
|
|
"step": 35185
|
|
},
|
|
{
|
|
"entropy": 5.5399271011352536,
|
|
"epoch": 2.939358503174073,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00041402946115062187,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.23001357316970825,
|
|
"num_tokens": 64750042.0,
|
|
"step": 35190
|
|
},
|
|
{
|
|
"entropy": 5.390791559219361,
|
|
"epoch": 2.939776144336786,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004140060532935197,
|
|
"loss": 4.684,
|
|
"mean_token_accuracy": 0.2352052092552185,
|
|
"num_tokens": 64758467.0,
|
|
"step": 35195
|
|
},
|
|
{
|
|
"entropy": 5.415098381042481,
|
|
"epoch": 2.940193785499499,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004139826430029493,
|
|
"loss": 4.7075,
|
|
"mean_token_accuracy": 0.23691484481096267,
|
|
"num_tokens": 64767932.0,
|
|
"step": 35200
|
|
},
|
|
{
|
|
"entropy": 5.477224397659302,
|
|
"epoch": 2.940611426662212,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041395923027932045,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.2328386500477791,
|
|
"num_tokens": 64777500.0,
|
|
"step": 35205
|
|
},
|
|
{
|
|
"entropy": 5.4972008228302,
|
|
"epoch": 2.9410290678249247,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000413935815123043,
|
|
"loss": 4.7747,
|
|
"mean_token_accuracy": 0.2276524156332016,
|
|
"num_tokens": 64786901.0,
|
|
"step": 35210
|
|
},
|
|
{
|
|
"entropy": 5.449518775939941,
|
|
"epoch": 2.941446708987638,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041391239753452673,
|
|
"loss": 4.7847,
|
|
"mean_token_accuracy": 0.2264282539486885,
|
|
"num_tokens": 64796640.0,
|
|
"step": 35215
|
|
},
|
|
{
|
|
"entropy": 5.435948085784912,
|
|
"epoch": 2.9418643501503507,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004138889775141819,
|
|
"loss": 4.7178,
|
|
"mean_token_accuracy": 0.23463414162397384,
|
|
"num_tokens": 64805943.0,
|
|
"step": 35220
|
|
},
|
|
{
|
|
"entropy": 5.394881772994995,
|
|
"epoch": 2.942281991313064,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004138655550624183,
|
|
"loss": 4.5919,
|
|
"mean_token_accuracy": 0.23966405540704727,
|
|
"num_tokens": 64815308.0,
|
|
"step": 35225
|
|
},
|
|
{
|
|
"entropy": 5.464346981048584,
|
|
"epoch": 2.942699632475777,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004138421301796461,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.22509408742189407,
|
|
"num_tokens": 64823901.0,
|
|
"step": 35230
|
|
},
|
|
{
|
|
"entropy": 5.471676540374756,
|
|
"epoch": 2.9431172736384896,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00041381870286627515,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.2285889655351639,
|
|
"num_tokens": 64832878.0,
|
|
"step": 35235
|
|
},
|
|
{
|
|
"entropy": 5.455448913574219,
|
|
"epoch": 2.943534914801203,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041379527312271575,
|
|
"loss": 4.6724,
|
|
"mean_token_accuracy": 0.2341967299580574,
|
|
"num_tokens": 64842240.0,
|
|
"step": 35240
|
|
},
|
|
{
|
|
"entropy": 5.463013315200806,
|
|
"epoch": 2.9439525559639157,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041377184094937796,
|
|
"loss": 4.6911,
|
|
"mean_token_accuracy": 0.23382991403341294,
|
|
"num_tokens": 64852391.0,
|
|
"step": 35245
|
|
},
|
|
{
|
|
"entropy": 5.406412982940674,
|
|
"epoch": 2.944370197126629,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004137484063466722,
|
|
"loss": 4.6694,
|
|
"mean_token_accuracy": 0.2305466428399086,
|
|
"num_tokens": 64860622.0,
|
|
"step": 35250
|
|
},
|
|
{
|
|
"entropy": 5.364333248138427,
|
|
"epoch": 2.9447878382893418,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041372496931500855,
|
|
"loss": 4.6693,
|
|
"mean_token_accuracy": 0.23684307485818862,
|
|
"num_tokens": 64869448.0,
|
|
"step": 35255
|
|
},
|
|
{
|
|
"entropy": 5.384157657623291,
|
|
"epoch": 2.9452054794520546,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041370152985479723,
|
|
"loss": 4.7188,
|
|
"mean_token_accuracy": 0.23011721223592757,
|
|
"num_tokens": 64878247.0,
|
|
"step": 35260
|
|
},
|
|
{
|
|
"entropy": 5.488680076599121,
|
|
"epoch": 2.945623120614768,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004136780879664487,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.23374384939670562,
|
|
"num_tokens": 64887318.0,
|
|
"step": 35265
|
|
},
|
|
{
|
|
"entropy": 5.514237260818481,
|
|
"epoch": 2.9460407617774806,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004136546436503733,
|
|
"loss": 4.7914,
|
|
"mean_token_accuracy": 0.22896492034196853,
|
|
"num_tokens": 64896898.0,
|
|
"step": 35270
|
|
},
|
|
{
|
|
"entropy": 5.52361216545105,
|
|
"epoch": 2.946458402940194,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004136311969069815,
|
|
"loss": 4.8029,
|
|
"mean_token_accuracy": 0.23074470311403275,
|
|
"num_tokens": 64905457.0,
|
|
"step": 35275
|
|
},
|
|
{
|
|
"entropy": 5.449588775634766,
|
|
"epoch": 2.9468760441029067,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041360774773668374,
|
|
"loss": 4.7733,
|
|
"mean_token_accuracy": 0.23551763594150543,
|
|
"num_tokens": 64914337.0,
|
|
"step": 35280
|
|
},
|
|
{
|
|
"entropy": 5.4469739437103275,
|
|
"epoch": 2.9472936852656195,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00041358429613989054,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.23388056308031083,
|
|
"num_tokens": 64923206.0,
|
|
"step": 35285
|
|
},
|
|
{
|
|
"entropy": 5.418287038803101,
|
|
"epoch": 2.947711326428333,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004135608421170123,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.23152288496494294,
|
|
"num_tokens": 64931707.0,
|
|
"step": 35290
|
|
},
|
|
{
|
|
"entropy": 5.5042322158813475,
|
|
"epoch": 2.948128967591046,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004135373856684599,
|
|
"loss": 4.6939,
|
|
"mean_token_accuracy": 0.2389744833111763,
|
|
"num_tokens": 64940701.0,
|
|
"step": 35295
|
|
},
|
|
{
|
|
"entropy": 5.547838354110718,
|
|
"epoch": 2.948546608753759,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041351392679464364,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.2268144443631172,
|
|
"num_tokens": 64949284.0,
|
|
"step": 35300
|
|
},
|
|
{
|
|
"entropy": 5.451996898651123,
|
|
"epoch": 2.9489642499164717,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004134904654959745,
|
|
"loss": 4.7434,
|
|
"mean_token_accuracy": 0.2283647269010544,
|
|
"num_tokens": 64958607.0,
|
|
"step": 35305
|
|
},
|
|
{
|
|
"entropy": 5.458255290985107,
|
|
"epoch": 2.949381891079185,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000413467001772863,
|
|
"loss": 4.737,
|
|
"mean_token_accuracy": 0.23272535800933838,
|
|
"num_tokens": 64967064.0,
|
|
"step": 35310
|
|
},
|
|
{
|
|
"entropy": 5.477356052398681,
|
|
"epoch": 2.9497995322418977,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041344353562572,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.22496949136257172,
|
|
"num_tokens": 64976783.0,
|
|
"step": 35315
|
|
},
|
|
{
|
|
"entropy": 5.457982444763184,
|
|
"epoch": 2.950217173404611,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041342006705495616,
|
|
"loss": 4.6782,
|
|
"mean_token_accuracy": 0.23790150731801987,
|
|
"num_tokens": 64986010.0,
|
|
"step": 35320
|
|
},
|
|
{
|
|
"entropy": 5.447219514846802,
|
|
"epoch": 2.950634814567324,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004133965960609825,
|
|
"loss": 4.6828,
|
|
"mean_token_accuracy": 0.2412191092967987,
|
|
"num_tokens": 64995408.0,
|
|
"step": 35325
|
|
},
|
|
{
|
|
"entropy": 5.471050834655761,
|
|
"epoch": 2.9510524557300366,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004133731226442099,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.23089451044797898,
|
|
"num_tokens": 65004341.0,
|
|
"step": 35330
|
|
},
|
|
{
|
|
"entropy": 5.481589603424072,
|
|
"epoch": 2.95147009689275,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004133496468050491,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.22624641209840773,
|
|
"num_tokens": 65012310.0,
|
|
"step": 35335
|
|
},
|
|
{
|
|
"entropy": 5.501546382904053,
|
|
"epoch": 2.9518877380554627,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004133261685439113,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.2372394472360611,
|
|
"num_tokens": 65022401.0,
|
|
"step": 35340
|
|
},
|
|
{
|
|
"entropy": 5.44715256690979,
|
|
"epoch": 2.952305379218176,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004133026878612074,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.225180946290493,
|
|
"num_tokens": 65032248.0,
|
|
"step": 35345
|
|
},
|
|
{
|
|
"entropy": 5.453938627243042,
|
|
"epoch": 2.9527230203808887,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004132792047573484,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.22347974628210068,
|
|
"num_tokens": 65042357.0,
|
|
"step": 35350
|
|
},
|
|
{
|
|
"entropy": 5.557681226730347,
|
|
"epoch": 2.9531406615436016,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00041325571923274564,
|
|
"loss": 4.9092,
|
|
"mean_token_accuracy": 0.22116324603557586,
|
|
"num_tokens": 65051437.0,
|
|
"step": 35355
|
|
},
|
|
{
|
|
"entropy": 5.489989185333252,
|
|
"epoch": 2.953558302706315,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004132322312878099,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.2183988407254219,
|
|
"num_tokens": 65061618.0,
|
|
"step": 35360
|
|
},
|
|
{
|
|
"entropy": 5.472217321395874,
|
|
"epoch": 2.9539759438690276,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004132087409229527,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.2278141662478447,
|
|
"num_tokens": 65070958.0,
|
|
"step": 35365
|
|
},
|
|
{
|
|
"entropy": 5.429346513748169,
|
|
"epoch": 2.954393585031741,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041318524813858503,
|
|
"loss": 4.7018,
|
|
"mean_token_accuracy": 0.23413754105567933,
|
|
"num_tokens": 65079993.0,
|
|
"step": 35370
|
|
},
|
|
{
|
|
"entropy": 5.426882696151734,
|
|
"epoch": 2.9548112261944537,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00041316175293511833,
|
|
"loss": 4.731,
|
|
"mean_token_accuracy": 0.23649742603302001,
|
|
"num_tokens": 65089387.0,
|
|
"step": 35375
|
|
},
|
|
{
|
|
"entropy": 5.421173000335694,
|
|
"epoch": 2.9552288673571665,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041313825531296376,
|
|
"loss": 4.6611,
|
|
"mean_token_accuracy": 0.24048041999340058,
|
|
"num_tokens": 65098045.0,
|
|
"step": 35380
|
|
},
|
|
{
|
|
"entropy": 5.3984864234924315,
|
|
"epoch": 2.9556465085198798,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00041311475527253284,
|
|
"loss": 4.687,
|
|
"mean_token_accuracy": 0.23061685562133788,
|
|
"num_tokens": 65106954.0,
|
|
"step": 35385
|
|
},
|
|
{
|
|
"entropy": 5.42021861076355,
|
|
"epoch": 2.9560641496825926,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004130912528142368,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.23939092606306075,
|
|
"num_tokens": 65116004.0,
|
|
"step": 35390
|
|
},
|
|
{
|
|
"entropy": 5.436772966384888,
|
|
"epoch": 2.956481790845306,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004130677479384873,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.2320142164826393,
|
|
"num_tokens": 65125055.0,
|
|
"step": 35395
|
|
},
|
|
{
|
|
"entropy": 5.468134927749634,
|
|
"epoch": 2.9568994320080186,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004130442406456956,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.22511887550354004,
|
|
"num_tokens": 65134688.0,
|
|
"step": 35400
|
|
},
|
|
{
|
|
"entropy": 5.488264322280884,
|
|
"epoch": 2.9573170731707314,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041302073093627326,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.23036372363567353,
|
|
"num_tokens": 65143811.0,
|
|
"step": 35405
|
|
},
|
|
{
|
|
"entropy": 5.490865707397461,
|
|
"epoch": 2.9577347143334447,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041299721881063196,
|
|
"loss": 4.7905,
|
|
"mean_token_accuracy": 0.22432523369789123,
|
|
"num_tokens": 65152860.0,
|
|
"step": 35410
|
|
},
|
|
{
|
|
"entropy": 5.497634315490723,
|
|
"epoch": 2.958152355496158,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004129737042691832,
|
|
"loss": 4.7757,
|
|
"mean_token_accuracy": 0.22318572998046876,
|
|
"num_tokens": 65163043.0,
|
|
"step": 35415
|
|
},
|
|
{
|
|
"entropy": 5.422274589538574,
|
|
"epoch": 2.9585699966588708,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00041295018731233864,
|
|
"loss": 4.6673,
|
|
"mean_token_accuracy": 0.23807175159454347,
|
|
"num_tokens": 65171508.0,
|
|
"step": 35420
|
|
},
|
|
{
|
|
"entropy": 5.415389919281006,
|
|
"epoch": 2.9589876378215836,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041292666794051,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.2353188157081604,
|
|
"num_tokens": 65180956.0,
|
|
"step": 35425
|
|
},
|
|
{
|
|
"entropy": 5.413981580734253,
|
|
"epoch": 2.959405278984297,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041290314615410905,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.23106073290109636,
|
|
"num_tokens": 65189365.0,
|
|
"step": 35430
|
|
},
|
|
{
|
|
"entropy": 5.388423299789428,
|
|
"epoch": 2.9598229201470097,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041287962195354753,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.2378994941711426,
|
|
"num_tokens": 65198055.0,
|
|
"step": 35435
|
|
},
|
|
{
|
|
"entropy": 5.478050374984742,
|
|
"epoch": 2.960240561309723,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041285609533923723,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.22418209463357924,
|
|
"num_tokens": 65207963.0,
|
|
"step": 35440
|
|
},
|
|
{
|
|
"entropy": 5.42581090927124,
|
|
"epoch": 2.9606582024724357,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004128325663115901,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.23110701739788056,
|
|
"num_tokens": 65217444.0,
|
|
"step": 35445
|
|
},
|
|
{
|
|
"entropy": 5.414535760879517,
|
|
"epoch": 2.9610758436351485,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041280903487101795,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.2308998540043831,
|
|
"num_tokens": 65227379.0,
|
|
"step": 35450
|
|
},
|
|
{
|
|
"entropy": 5.432538223266602,
|
|
"epoch": 2.961493484797862,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041278550101793275,
|
|
"loss": 4.6756,
|
|
"mean_token_accuracy": 0.23566309958696366,
|
|
"num_tokens": 65237123.0,
|
|
"step": 35455
|
|
},
|
|
{
|
|
"entropy": 5.402748680114746,
|
|
"epoch": 2.9619111259605746,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004127619647527466,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.24034751951694489,
|
|
"num_tokens": 65245549.0,
|
|
"step": 35460
|
|
},
|
|
{
|
|
"entropy": 5.38619589805603,
|
|
"epoch": 2.962328767123288,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041273842607587137,
|
|
"loss": 4.6938,
|
|
"mean_token_accuracy": 0.23143359124660492,
|
|
"num_tokens": 65254936.0,
|
|
"step": 35465
|
|
},
|
|
{
|
|
"entropy": 5.432380437850952,
|
|
"epoch": 2.9627464082860007,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041271488498771913,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.23453331738710403,
|
|
"num_tokens": 65263402.0,
|
|
"step": 35470
|
|
},
|
|
{
|
|
"entropy": 5.49821662902832,
|
|
"epoch": 2.9631640494487135,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041269134148870214,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.2173226371407509,
|
|
"num_tokens": 65273079.0,
|
|
"step": 35475
|
|
},
|
|
{
|
|
"entropy": 5.455629587173462,
|
|
"epoch": 2.9635816906114267,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004126677955792324,
|
|
"loss": 4.6787,
|
|
"mean_token_accuracy": 0.2330406755208969,
|
|
"num_tokens": 65282196.0,
|
|
"step": 35480
|
|
},
|
|
{
|
|
"entropy": 5.449783658981323,
|
|
"epoch": 2.9639993317741395,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004126442472597223,
|
|
"loss": 4.7051,
|
|
"mean_token_accuracy": 0.2425326243042946,
|
|
"num_tokens": 65290633.0,
|
|
"step": 35485
|
|
},
|
|
{
|
|
"entropy": 5.404230213165283,
|
|
"epoch": 2.964416972936853,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041262069653058385,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.23424960523843766,
|
|
"num_tokens": 65300239.0,
|
|
"step": 35490
|
|
},
|
|
{
|
|
"entropy": 5.44136962890625,
|
|
"epoch": 2.9648346140995656,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004125971433922295,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.22508814334869384,
|
|
"num_tokens": 65310239.0,
|
|
"step": 35495
|
|
},
|
|
{
|
|
"entropy": 5.397144412994384,
|
|
"epoch": 2.9652522552622784,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041257358784507157,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.23522338420152664,
|
|
"num_tokens": 65319588.0,
|
|
"step": 35500
|
|
},
|
|
{
|
|
"entropy": 5.4157098770141605,
|
|
"epoch": 2.9656698964249917,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004125500298895224,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.23396226167678832,
|
|
"num_tokens": 65328922.0,
|
|
"step": 35505
|
|
},
|
|
{
|
|
"entropy": 5.5155322551727295,
|
|
"epoch": 2.9660875375877045,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004125264695259943,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.23208736926317214,
|
|
"num_tokens": 65338868.0,
|
|
"step": 35510
|
|
},
|
|
{
|
|
"entropy": 5.396420669555664,
|
|
"epoch": 2.9665051787504177,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004125029067548999,
|
|
"loss": 4.6787,
|
|
"mean_token_accuracy": 0.2303745985031128,
|
|
"num_tokens": 65348368.0,
|
|
"step": 35515
|
|
},
|
|
{
|
|
"entropy": 5.403063726425171,
|
|
"epoch": 2.9669228199131306,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00041247934157665156,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.22728042602539061,
|
|
"num_tokens": 65356780.0,
|
|
"step": 35520
|
|
},
|
|
{
|
|
"entropy": 5.434471654891968,
|
|
"epoch": 2.9673404610758434,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004124557739916618,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.23759374767541885,
|
|
"num_tokens": 65365423.0,
|
|
"step": 35525
|
|
},
|
|
{
|
|
"entropy": 5.349104976654052,
|
|
"epoch": 2.9677581022385566,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004124322040003434,
|
|
"loss": 4.6348,
|
|
"mean_token_accuracy": 0.24518750011920928,
|
|
"num_tokens": 65374186.0,
|
|
"step": 35530
|
|
},
|
|
{
|
|
"entropy": 5.442192697525025,
|
|
"epoch": 2.96817574340127,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004124086316031087,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.23424815535545349,
|
|
"num_tokens": 65383196.0,
|
|
"step": 35535
|
|
},
|
|
{
|
|
"entropy": 5.417137670516968,
|
|
"epoch": 2.9685933845639827,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041238505680037064,
|
|
"loss": 4.6695,
|
|
"mean_token_accuracy": 0.23509834706783295,
|
|
"num_tokens": 65391859.0,
|
|
"step": 35540
|
|
},
|
|
{
|
|
"entropy": 5.518378400802613,
|
|
"epoch": 2.9690110257266955,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041236147959254166,
|
|
"loss": 4.7379,
|
|
"mean_token_accuracy": 0.2308109551668167,
|
|
"num_tokens": 65402038.0,
|
|
"step": 35545
|
|
},
|
|
{
|
|
"entropy": 5.5231586456298825,
|
|
"epoch": 2.9694286668894088,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041233789998003476,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.2296963408589363,
|
|
"num_tokens": 65411269.0,
|
|
"step": 35550
|
|
},
|
|
{
|
|
"entropy": 5.48047456741333,
|
|
"epoch": 2.9698463080521216,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041231431796326254,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.22590091824531555,
|
|
"num_tokens": 65420581.0,
|
|
"step": 35555
|
|
},
|
|
{
|
|
"entropy": 5.465172815322876,
|
|
"epoch": 2.970263949214835,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00041229073354263787,
|
|
"loss": 4.7379,
|
|
"mean_token_accuracy": 0.22563184201717376,
|
|
"num_tokens": 65428891.0,
|
|
"step": 35560
|
|
},
|
|
{
|
|
"entropy": 5.578264141082764,
|
|
"epoch": 2.9706815903775476,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041226714671857367,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.2194327011704445,
|
|
"num_tokens": 65438783.0,
|
|
"step": 35565
|
|
},
|
|
{
|
|
"entropy": 5.41734766960144,
|
|
"epoch": 2.9710992315402605,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004122435574914829,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.2357519507408142,
|
|
"num_tokens": 65447493.0,
|
|
"step": 35570
|
|
},
|
|
{
|
|
"entropy": 5.523471546173096,
|
|
"epoch": 2.9715168727029737,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041221996586177843,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.2232340842485428,
|
|
"num_tokens": 65456974.0,
|
|
"step": 35575
|
|
},
|
|
{
|
|
"entropy": 5.4640946865081785,
|
|
"epoch": 2.9719345138656865,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041219637182987324,
|
|
"loss": 4.6948,
|
|
"mean_token_accuracy": 0.22556078135967256,
|
|
"num_tokens": 65465916.0,
|
|
"step": 35580
|
|
},
|
|
{
|
|
"entropy": 5.439486122131347,
|
|
"epoch": 2.9723521550284,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041217277539618046,
|
|
"loss": 4.6779,
|
|
"mean_token_accuracy": 0.23571026772260667,
|
|
"num_tokens": 65475363.0,
|
|
"step": 35585
|
|
},
|
|
{
|
|
"entropy": 5.385741090774536,
|
|
"epoch": 2.9727697961911126,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004121491765611131,
|
|
"loss": 4.6644,
|
|
"mean_token_accuracy": 0.2365900918841362,
|
|
"num_tokens": 65483774.0,
|
|
"step": 35590
|
|
},
|
|
{
|
|
"entropy": 5.3821797370910645,
|
|
"epoch": 2.9731874373538254,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041212557532508434,
|
|
"loss": 4.7219,
|
|
"mean_token_accuracy": 0.23045432269573213,
|
|
"num_tokens": 65493050.0,
|
|
"step": 35595
|
|
},
|
|
{
|
|
"entropy": 5.524290704727173,
|
|
"epoch": 2.9736050785165387,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004121019716885074,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.2271477609872818,
|
|
"num_tokens": 65501254.0,
|
|
"step": 35600
|
|
},
|
|
{
|
|
"entropy": 5.555329990386963,
|
|
"epoch": 2.9740227196792515,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004120783656517953,
|
|
"loss": 4.6876,
|
|
"mean_token_accuracy": 0.23637754321098328,
|
|
"num_tokens": 65509314.0,
|
|
"step": 35605
|
|
},
|
|
{
|
|
"entropy": 5.547512865066528,
|
|
"epoch": 2.9744403608419647,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004120547572153614,
|
|
"loss": 4.7916,
|
|
"mean_token_accuracy": 0.23107903003692626,
|
|
"num_tokens": 65518031.0,
|
|
"step": 35610
|
|
},
|
|
{
|
|
"entropy": 5.441957187652588,
|
|
"epoch": 2.9748580020046775,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004120311463796191,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.2274484857916832,
|
|
"num_tokens": 65527622.0,
|
|
"step": 35615
|
|
},
|
|
{
|
|
"entropy": 5.447047710418701,
|
|
"epoch": 2.9752756431673903,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041200753314498155,
|
|
"loss": 4.679,
|
|
"mean_token_accuracy": 0.22916072160005568,
|
|
"num_tokens": 65536940.0,
|
|
"step": 35620
|
|
},
|
|
{
|
|
"entropy": 5.594627857208252,
|
|
"epoch": 2.9756932843301036,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041198391751186227,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.21689824759960175,
|
|
"num_tokens": 65546087.0,
|
|
"step": 35625
|
|
},
|
|
{
|
|
"entropy": 5.42275824546814,
|
|
"epoch": 2.9761109254928164,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041196029948067464,
|
|
"loss": 4.7344,
|
|
"mean_token_accuracy": 0.2330067589879036,
|
|
"num_tokens": 65555652.0,
|
|
"step": 35630
|
|
},
|
|
{
|
|
"entropy": 5.454036808013916,
|
|
"epoch": 2.9765285666555297,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000411936679051832,
|
|
"loss": 4.7572,
|
|
"mean_token_accuracy": 0.2332295835018158,
|
|
"num_tokens": 65565082.0,
|
|
"step": 35635
|
|
},
|
|
{
|
|
"entropy": 5.505554819107056,
|
|
"epoch": 2.9769462078182425,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00041191305622574815,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.2314508631825447,
|
|
"num_tokens": 65574010.0,
|
|
"step": 35640
|
|
},
|
|
{
|
|
"entropy": 5.456867837905884,
|
|
"epoch": 2.9773638489809553,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004118894310028362,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.22673971951007843,
|
|
"num_tokens": 65582191.0,
|
|
"step": 35645
|
|
},
|
|
{
|
|
"entropy": 5.463497638702393,
|
|
"epoch": 2.9777814901436686,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041186580338351014,
|
|
"loss": 4.8377,
|
|
"mean_token_accuracy": 0.22572452574968338,
|
|
"num_tokens": 65591922.0,
|
|
"step": 35650
|
|
},
|
|
{
|
|
"entropy": 5.463946199417114,
|
|
"epoch": 2.978199131306382,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004118421733681835,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.23593817055225372,
|
|
"num_tokens": 65600904.0,
|
|
"step": 35655
|
|
},
|
|
{
|
|
"entropy": 5.479194116592407,
|
|
"epoch": 2.9786167724690946,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041181854095726986,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.23587285429239274,
|
|
"num_tokens": 65609773.0,
|
|
"step": 35660
|
|
},
|
|
{
|
|
"entropy": 5.416159439086914,
|
|
"epoch": 2.9790344136318074,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004117949061511829,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.23370835781097413,
|
|
"num_tokens": 65618054.0,
|
|
"step": 35665
|
|
},
|
|
{
|
|
"entropy": 5.391520166397095,
|
|
"epoch": 2.9794520547945207,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041177126895033646,
|
|
"loss": 4.6718,
|
|
"mean_token_accuracy": 0.23789255321025848,
|
|
"num_tokens": 65626387.0,
|
|
"step": 35670
|
|
},
|
|
{
|
|
"entropy": 5.443028402328491,
|
|
"epoch": 2.9798696959572335,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00041174762935514435,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.23936444371938706,
|
|
"num_tokens": 65634911.0,
|
|
"step": 35675
|
|
},
|
|
{
|
|
"entropy": 5.513776397705078,
|
|
"epoch": 2.9802873371199468,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004117239873660204,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.2178734600543976,
|
|
"num_tokens": 65645223.0,
|
|
"step": 35680
|
|
},
|
|
{
|
|
"entropy": 5.509975910186768,
|
|
"epoch": 2.9807049782826596,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004117003429833785,
|
|
"loss": 4.7669,
|
|
"mean_token_accuracy": 0.22980217039585113,
|
|
"num_tokens": 65653695.0,
|
|
"step": 35685
|
|
},
|
|
{
|
|
"entropy": 5.506290912628174,
|
|
"epoch": 2.9811226194453724,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004116766962076325,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.22395838648080826,
|
|
"num_tokens": 65663927.0,
|
|
"step": 35690
|
|
},
|
|
{
|
|
"entropy": 5.481973886489868,
|
|
"epoch": 2.9815402606080856,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041165304703919643,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.23639802932739257,
|
|
"num_tokens": 65673617.0,
|
|
"step": 35695
|
|
},
|
|
{
|
|
"entropy": 5.527976655960083,
|
|
"epoch": 2.9819579017707984,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00041162939547848427,
|
|
"loss": 4.7557,
|
|
"mean_token_accuracy": 0.23485021740198136,
|
|
"num_tokens": 65682506.0,
|
|
"step": 35700
|
|
},
|
|
{
|
|
"entropy": 5.466494798660278,
|
|
"epoch": 2.9823755429335117,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004116057415259101,
|
|
"loss": 4.7571,
|
|
"mean_token_accuracy": 0.23258000016212463,
|
|
"num_tokens": 65691228.0,
|
|
"step": 35705
|
|
},
|
|
{
|
|
"entropy": 5.44260082244873,
|
|
"epoch": 2.9827931840962245,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000411582085181888,
|
|
"loss": 4.7432,
|
|
"mean_token_accuracy": 0.22952873557806014,
|
|
"num_tokens": 65700772.0,
|
|
"step": 35710
|
|
},
|
|
{
|
|
"entropy": 5.3429240703582765,
|
|
"epoch": 2.9832108252589373,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041155842644683213,
|
|
"loss": 4.5912,
|
|
"mean_token_accuracy": 0.2451059564948082,
|
|
"num_tokens": 65709737.0,
|
|
"step": 35715
|
|
},
|
|
{
|
|
"entropy": 5.471945762634277,
|
|
"epoch": 2.9836284664216506,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004115347653211565,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.23486284613609315,
|
|
"num_tokens": 65718646.0,
|
|
"step": 35720
|
|
},
|
|
{
|
|
"entropy": 5.498866987228394,
|
|
"epoch": 2.9840461075843634,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00041151110180527557,
|
|
"loss": 4.7258,
|
|
"mean_token_accuracy": 0.2367549642920494,
|
|
"num_tokens": 65727070.0,
|
|
"step": 35725
|
|
},
|
|
{
|
|
"entropy": 5.350088262557984,
|
|
"epoch": 2.9844637487470767,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004114874358996034,
|
|
"loss": 4.6354,
|
|
"mean_token_accuracy": 0.2402138292789459,
|
|
"num_tokens": 65735792.0,
|
|
"step": 35730
|
|
},
|
|
{
|
|
"entropy": 5.4739179611206055,
|
|
"epoch": 2.9848813899097895,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004114637676045545,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.23026547729969024,
|
|
"num_tokens": 65744843.0,
|
|
"step": 35735
|
|
},
|
|
{
|
|
"entropy": 5.489833974838257,
|
|
"epoch": 2.9852990310725023,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041144009692054294,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.23052820414304734,
|
|
"num_tokens": 65754062.0,
|
|
"step": 35740
|
|
},
|
|
{
|
|
"entropy": 5.519318532943726,
|
|
"epoch": 2.9857166722352155,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004114164238479834,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.22975870370864868,
|
|
"num_tokens": 65763083.0,
|
|
"step": 35745
|
|
},
|
|
{
|
|
"entropy": 5.438665342330933,
|
|
"epoch": 2.9861343133979283,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004113927483872901,
|
|
"loss": 4.6167,
|
|
"mean_token_accuracy": 0.2495344564318657,
|
|
"num_tokens": 65772295.0,
|
|
"step": 35750
|
|
},
|
|
{
|
|
"entropy": 5.337552070617676,
|
|
"epoch": 2.9865519545606416,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004113690705388775,
|
|
"loss": 4.6392,
|
|
"mean_token_accuracy": 0.23610030859708786,
|
|
"num_tokens": 65781263.0,
|
|
"step": 35755
|
|
},
|
|
{
|
|
"entropy": 5.473101949691772,
|
|
"epoch": 2.9869695957233544,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00041134539030316026,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.23428836911916734,
|
|
"num_tokens": 65790167.0,
|
|
"step": 35760
|
|
},
|
|
{
|
|
"entropy": 5.435871839523315,
|
|
"epoch": 2.987387236886067,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041132170768055275,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.22514233440160752,
|
|
"num_tokens": 65799299.0,
|
|
"step": 35765
|
|
},
|
|
{
|
|
"entropy": 5.42843656539917,
|
|
"epoch": 2.9878048780487805,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004112980226714698,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.23874940127134323,
|
|
"num_tokens": 65808963.0,
|
|
"step": 35770
|
|
},
|
|
{
|
|
"entropy": 5.444188022613526,
|
|
"epoch": 2.9882225192114937,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041127433527632574,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.23665292859077453,
|
|
"num_tokens": 65818458.0,
|
|
"step": 35775
|
|
},
|
|
{
|
|
"entropy": 5.438649368286133,
|
|
"epoch": 2.9886401603742065,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041125064549553544,
|
|
"loss": 4.7347,
|
|
"mean_token_accuracy": 0.22849638760089874,
|
|
"num_tokens": 65827560.0,
|
|
"step": 35780
|
|
},
|
|
{
|
|
"entropy": 5.4202312469482425,
|
|
"epoch": 2.9890578015369194,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041122695332951363,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.23093999773263932,
|
|
"num_tokens": 65835870.0,
|
|
"step": 35785
|
|
},
|
|
{
|
|
"entropy": 5.50711612701416,
|
|
"epoch": 2.9894754426996326,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041120325877867504,
|
|
"loss": 4.766,
|
|
"mean_token_accuracy": 0.23326678574085236,
|
|
"num_tokens": 65844794.0,
|
|
"step": 35790
|
|
},
|
|
{
|
|
"entropy": 5.438318490982056,
|
|
"epoch": 2.9898930838623454,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004111795618434344,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.23290226906538009,
|
|
"num_tokens": 65853479.0,
|
|
"step": 35795
|
|
},
|
|
{
|
|
"entropy": 5.432145071029663,
|
|
"epoch": 2.9903107250250587,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004111558625242067,
|
|
"loss": 4.7381,
|
|
"mean_token_accuracy": 0.23381806910037994,
|
|
"num_tokens": 65862902.0,
|
|
"step": 35800
|
|
},
|
|
{
|
|
"entropy": 5.502327871322632,
|
|
"epoch": 2.9907283661877715,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004111321608214067,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.22779896557331086,
|
|
"num_tokens": 65871891.0,
|
|
"step": 35805
|
|
},
|
|
{
|
|
"entropy": 5.431931972503662,
|
|
"epoch": 2.9911460073504843,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004111084567354493,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.24549283534288407,
|
|
"num_tokens": 65879999.0,
|
|
"step": 35810
|
|
},
|
|
{
|
|
"entropy": 5.497239112854004,
|
|
"epoch": 2.9915636485131976,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041108475026674964,
|
|
"loss": 4.7924,
|
|
"mean_token_accuracy": 0.22989973723888396,
|
|
"num_tokens": 65890455.0,
|
|
"step": 35815
|
|
},
|
|
{
|
|
"entropy": 5.54177622795105,
|
|
"epoch": 2.9919812896759104,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041106104141572247,
|
|
"loss": 4.8353,
|
|
"mean_token_accuracy": 0.22406548112630845,
|
|
"num_tokens": 65899826.0,
|
|
"step": 35820
|
|
},
|
|
{
|
|
"entropy": 5.390251684188843,
|
|
"epoch": 2.9923989308386236,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004110373301827832,
|
|
"loss": 4.6596,
|
|
"mean_token_accuracy": 0.23504940420389175,
|
|
"num_tokens": 65908706.0,
|
|
"step": 35825
|
|
},
|
|
{
|
|
"entropy": 5.452787446975708,
|
|
"epoch": 2.9928165720013364,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004110136165683465,
|
|
"loss": 4.7606,
|
|
"mean_token_accuracy": 0.22452432513237,
|
|
"num_tokens": 65917334.0,
|
|
"step": 35830
|
|
},
|
|
{
|
|
"entropy": 5.327690458297729,
|
|
"epoch": 2.9932342131640493,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004109899005728278,
|
|
"loss": 4.6001,
|
|
"mean_token_accuracy": 0.23950163275003433,
|
|
"num_tokens": 65925449.0,
|
|
"step": 35835
|
|
},
|
|
{
|
|
"entropy": 5.413449811935425,
|
|
"epoch": 2.9936518543267625,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00041096618219664224,
|
|
"loss": 4.7322,
|
|
"mean_token_accuracy": 0.23052008748054503,
|
|
"num_tokens": 65934197.0,
|
|
"step": 35840
|
|
},
|
|
{
|
|
"entropy": 5.4038022518157955,
|
|
"epoch": 2.9940694954894753,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041094246144020497,
|
|
"loss": 4.6524,
|
|
"mean_token_accuracy": 0.23747200071811675,
|
|
"num_tokens": 65944067.0,
|
|
"step": 35845
|
|
},
|
|
{
|
|
"entropy": 5.517951774597168,
|
|
"epoch": 2.9944871366521886,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004109187383039313,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.21535656601190567,
|
|
"num_tokens": 65953027.0,
|
|
"step": 35850
|
|
},
|
|
{
|
|
"entropy": 5.5065912246704105,
|
|
"epoch": 2.9949047778149014,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004108950127882365,
|
|
"loss": 4.794,
|
|
"mean_token_accuracy": 0.22301361262798308,
|
|
"num_tokens": 65962311.0,
|
|
"step": 35855
|
|
},
|
|
{
|
|
"entropy": 5.470807266235352,
|
|
"epoch": 2.995322418977614,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041087128489353594,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.23375248312950134,
|
|
"num_tokens": 65970734.0,
|
|
"step": 35860
|
|
},
|
|
{
|
|
"entropy": 5.555424785614013,
|
|
"epoch": 2.9957400601403275,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004108475546202449,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.21639556735754012,
|
|
"num_tokens": 65979857.0,
|
|
"step": 35865
|
|
},
|
|
{
|
|
"entropy": 5.473004007339478,
|
|
"epoch": 2.9961577013030403,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000410823821968779,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.23172156363725663,
|
|
"num_tokens": 65989275.0,
|
|
"step": 35870
|
|
},
|
|
{
|
|
"entropy": 5.4813049793243405,
|
|
"epoch": 2.9965753424657535,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041080008693955355,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.22924539744853972,
|
|
"num_tokens": 65998521.0,
|
|
"step": 35875
|
|
},
|
|
{
|
|
"entropy": 5.490589189529419,
|
|
"epoch": 2.9969929836284663,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00041077634953298417,
|
|
"loss": 4.7948,
|
|
"mean_token_accuracy": 0.22558340132236482,
|
|
"num_tokens": 66007759.0,
|
|
"step": 35880
|
|
},
|
|
{
|
|
"entropy": 5.380006980895996,
|
|
"epoch": 2.997410624791179,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004107526097494864,
|
|
"loss": 4.5756,
|
|
"mean_token_accuracy": 0.23973129838705062,
|
|
"num_tokens": 66016275.0,
|
|
"step": 35885
|
|
},
|
|
{
|
|
"entropy": 5.495582580566406,
|
|
"epoch": 2.9978282659538924,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041072886758947565,
|
|
"loss": 4.8376,
|
|
"mean_token_accuracy": 0.22462779730558396,
|
|
"num_tokens": 66024897.0,
|
|
"step": 35890
|
|
},
|
|
{
|
|
"entropy": 5.535341596603393,
|
|
"epoch": 2.9982459071166057,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00041070512305336777,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.23404620885848998,
|
|
"num_tokens": 66034253.0,
|
|
"step": 35895
|
|
},
|
|
{
|
|
"entropy": 5.430576324462891,
|
|
"epoch": 2.9986635482793185,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004106813761415783,
|
|
"loss": 4.6598,
|
|
"mean_token_accuracy": 0.23547362834215163,
|
|
"num_tokens": 66043636.0,
|
|
"step": 35900
|
|
},
|
|
{
|
|
"entropy": 5.473587226867676,
|
|
"epoch": 2.9990811894420313,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00041065762685452313,
|
|
"loss": 4.7594,
|
|
"mean_token_accuracy": 0.22926213443279267,
|
|
"num_tokens": 66052560.0,
|
|
"step": 35905
|
|
},
|
|
{
|
|
"entropy": 5.404001951217651,
|
|
"epoch": 2.9994988306047445,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041063387519261785,
|
|
"loss": 4.6491,
|
|
"mean_token_accuracy": 0.2363146498799324,
|
|
"num_tokens": 66061221.0,
|
|
"step": 35910
|
|
},
|
|
{
|
|
"entropy": 5.498865365982056,
|
|
"epoch": 2.9999164717674573,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004106101211562783,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.2286740869283676,
|
|
"num_tokens": 66070665.0,
|
|
"step": 35915
|
|
},
|
|
{
|
|
"entropy": 5.463295221328735,
|
|
"epoch": 3.0003341129301706,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041058636474592037,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.2354022443294525,
|
|
"num_tokens": 66079592.0,
|
|
"step": 35920
|
|
},
|
|
{
|
|
"entropy": 5.475717306137085,
|
|
"epoch": 3.0007517540928834,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004105626059619599,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.2280087798833847,
|
|
"num_tokens": 66088357.0,
|
|
"step": 35925
|
|
},
|
|
{
|
|
"entropy": 5.410529661178589,
|
|
"epoch": 3.0011693952555962,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041053884480481286,
|
|
"loss": 4.6455,
|
|
"mean_token_accuracy": 0.23097782582044601,
|
|
"num_tokens": 66096974.0,
|
|
"step": 35930
|
|
},
|
|
{
|
|
"entropy": 5.402410459518433,
|
|
"epoch": 3.0015870364183095,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00041051508127489526,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.2353963926434517,
|
|
"num_tokens": 66106245.0,
|
|
"step": 35935
|
|
},
|
|
{
|
|
"entropy": 5.430347728729248,
|
|
"epoch": 3.0020046775810223,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041049131537262295,
|
|
"loss": 4.7035,
|
|
"mean_token_accuracy": 0.230260406434536,
|
|
"num_tokens": 66114773.0,
|
|
"step": 35940
|
|
},
|
|
{
|
|
"entropy": 5.439944076538086,
|
|
"epoch": 3.0024223187437356,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004104675470984121,
|
|
"loss": 4.6591,
|
|
"mean_token_accuracy": 0.23521311432123185,
|
|
"num_tokens": 66123616.0,
|
|
"step": 35945
|
|
},
|
|
{
|
|
"entropy": 5.505154943466186,
|
|
"epoch": 3.0028399599064484,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041044377645267876,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.23806936144828797,
|
|
"num_tokens": 66133384.0,
|
|
"step": 35950
|
|
},
|
|
{
|
|
"entropy": 5.427834558486938,
|
|
"epoch": 3.003257601069161,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00041042000343583906,
|
|
"loss": 4.6314,
|
|
"mean_token_accuracy": 0.2461082249879837,
|
|
"num_tokens": 66142998.0,
|
|
"step": 35955
|
|
},
|
|
{
|
|
"entropy": 5.4796778678894045,
|
|
"epoch": 3.0036752422318744,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004103962280483093,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.23254551887512206,
|
|
"num_tokens": 66152812.0,
|
|
"step": 35960
|
|
},
|
|
{
|
|
"entropy": 5.46138105392456,
|
|
"epoch": 3.0040928833945872,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004103724502905055,
|
|
"loss": 4.6665,
|
|
"mean_token_accuracy": 0.23193718045949935,
|
|
"num_tokens": 66161656.0,
|
|
"step": 35965
|
|
},
|
|
{
|
|
"entropy": 5.415531730651855,
|
|
"epoch": 3.0045105245573005,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041034867016284405,
|
|
"loss": 4.6561,
|
|
"mean_token_accuracy": 0.243423031270504,
|
|
"num_tokens": 66169845.0,
|
|
"step": 35970
|
|
},
|
|
{
|
|
"entropy": 5.423990058898926,
|
|
"epoch": 3.0049281657200133,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00041032488766574115,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.23842133581638336,
|
|
"num_tokens": 66178063.0,
|
|
"step": 35975
|
|
},
|
|
{
|
|
"entropy": 5.47512993812561,
|
|
"epoch": 3.0053458068827266,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00041030110279961324,
|
|
"loss": 4.8416,
|
|
"mean_token_accuracy": 0.22658978700637816,
|
|
"num_tokens": 66186886.0,
|
|
"step": 35980
|
|
},
|
|
{
|
|
"entropy": 5.328921985626221,
|
|
"epoch": 3.0057634480454394,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004102773155648767,
|
|
"loss": 4.5367,
|
|
"mean_token_accuracy": 0.2522203877568245,
|
|
"num_tokens": 66194938.0,
|
|
"step": 35985
|
|
},
|
|
{
|
|
"entropy": 5.496852540969849,
|
|
"epoch": 3.006181089208152,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004102535259619479,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.2418172240257263,
|
|
"num_tokens": 66205430.0,
|
|
"step": 35990
|
|
},
|
|
{
|
|
"entropy": 5.466831111907959,
|
|
"epoch": 3.0065987303708654,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041022973399124324,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.23702215105295182,
|
|
"num_tokens": 66214954.0,
|
|
"step": 35995
|
|
},
|
|
{
|
|
"entropy": 5.558287572860718,
|
|
"epoch": 3.0070163715335783,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041020593965317945,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.22980232685804367,
|
|
"num_tokens": 66224829.0,
|
|
"step": 36000
|
|
},
|
|
{
|
|
"epoch": 3.0070163715335783,
|
|
"eval_entropy": 5.13271983663199,
|
|
"eval_loss": 4.735513210296631,
|
|
"eval_mean_token_accuracy": 0.24329466039101416,
|
|
"eval_num_tokens": 66224829.0,
|
|
"eval_runtime": 20.8422,
|
|
"eval_samples_per_second": 1811.853,
|
|
"eval_steps_per_second": 226.512,
|
|
"step": 36000
|
|
},
|
|
{
|
|
"entropy": 5.525006723403931,
|
|
"epoch": 3.0074340126962915,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004101821429481728,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.23544392883777618,
|
|
"num_tokens": 66233632.0,
|
|
"step": 36005
|
|
},
|
|
{
|
|
"entropy": 5.449371957778931,
|
|
"epoch": 3.0078516538590043,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041015834387664015,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.23494164049625396,
|
|
"num_tokens": 66243703.0,
|
|
"step": 36010
|
|
},
|
|
{
|
|
"entropy": 5.426934909820557,
|
|
"epoch": 3.008269295021717,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004101345424389979,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.2290268212556839,
|
|
"num_tokens": 66252038.0,
|
|
"step": 36015
|
|
},
|
|
{
|
|
"entropy": 5.451875495910644,
|
|
"epoch": 3.0086869361844304,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004101107386356629,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.2382079303264618,
|
|
"num_tokens": 66262019.0,
|
|
"step": 36020
|
|
},
|
|
{
|
|
"entropy": 5.484067916870117,
|
|
"epoch": 3.009104577347143,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004100869324670517,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.23276441246271135,
|
|
"num_tokens": 66270770.0,
|
|
"step": 36025
|
|
},
|
|
{
|
|
"entropy": 5.395999383926392,
|
|
"epoch": 3.0095222185098565,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004100631239335812,
|
|
"loss": 4.5864,
|
|
"mean_token_accuracy": 0.24179165810346603,
|
|
"num_tokens": 66279391.0,
|
|
"step": 36030
|
|
},
|
|
{
|
|
"entropy": 5.426571178436279,
|
|
"epoch": 3.0099398596725693,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041003931303566814,
|
|
"loss": 4.6005,
|
|
"mean_token_accuracy": 0.24046102315187454,
|
|
"num_tokens": 66288132.0,
|
|
"step": 36035
|
|
},
|
|
{
|
|
"entropy": 5.438758659362793,
|
|
"epoch": 3.0103575008352825,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004100154997737293,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.2345198467373848,
|
|
"num_tokens": 66296823.0,
|
|
"step": 36040
|
|
},
|
|
{
|
|
"entropy": 5.406085014343262,
|
|
"epoch": 3.0107751419979953,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040999168414818164,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.24244986921548844,
|
|
"num_tokens": 66305919.0,
|
|
"step": 36045
|
|
},
|
|
{
|
|
"entropy": 5.408543062210083,
|
|
"epoch": 3.011192783160708,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040996786615944214,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.23319390714168547,
|
|
"num_tokens": 66314520.0,
|
|
"step": 36050
|
|
},
|
|
{
|
|
"entropy": 5.472885942459106,
|
|
"epoch": 3.0116104243234214,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004099440458079276,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.22290656566619874,
|
|
"num_tokens": 66323796.0,
|
|
"step": 36055
|
|
},
|
|
{
|
|
"entropy": 5.490655326843262,
|
|
"epoch": 3.012028065486134,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040992022309405514,
|
|
"loss": 4.6885,
|
|
"mean_token_accuracy": 0.23794779926538467,
|
|
"num_tokens": 66333927.0,
|
|
"step": 36060
|
|
},
|
|
{
|
|
"entropy": 5.466877174377442,
|
|
"epoch": 3.0124457066488475,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004098963980182418,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.23968101143836976,
|
|
"num_tokens": 66343299.0,
|
|
"step": 36065
|
|
},
|
|
{
|
|
"entropy": 5.427545404434204,
|
|
"epoch": 3.0128633478115603,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00040987257058090455,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.23561825156211852,
|
|
"num_tokens": 66352299.0,
|
|
"step": 36070
|
|
},
|
|
{
|
|
"entropy": 5.419460344314575,
|
|
"epoch": 3.013280988974273,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004098487407824607,
|
|
"loss": 4.6147,
|
|
"mean_token_accuracy": 0.23790289908647538,
|
|
"num_tokens": 66360903.0,
|
|
"step": 36075
|
|
},
|
|
{
|
|
"entropy": 5.411008214950561,
|
|
"epoch": 3.0136986301369864,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004098249086233273,
|
|
"loss": 4.7127,
|
|
"mean_token_accuracy": 0.2263518378138542,
|
|
"num_tokens": 66369997.0,
|
|
"step": 36080
|
|
},
|
|
{
|
|
"entropy": 5.422216606140137,
|
|
"epoch": 3.014116271299699,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004098010741039215,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.2254987969994545,
|
|
"num_tokens": 66379354.0,
|
|
"step": 36085
|
|
},
|
|
{
|
|
"entropy": 5.502219867706299,
|
|
"epoch": 3.0145339124624124,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00040977723722466076,
|
|
"loss": 4.6718,
|
|
"mean_token_accuracy": 0.23529857248067856,
|
|
"num_tokens": 66388640.0,
|
|
"step": 36090
|
|
},
|
|
{
|
|
"entropy": 5.427269077301025,
|
|
"epoch": 3.0149515536251252,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040975339798596217,
|
|
"loss": 4.6474,
|
|
"mean_token_accuracy": 0.24267688095569612,
|
|
"num_tokens": 66398329.0,
|
|
"step": 36095
|
|
},
|
|
{
|
|
"entropy": 5.459979009628296,
|
|
"epoch": 3.0153691947878385,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004097295563882432,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.22222572714090347,
|
|
"num_tokens": 66407600.0,
|
|
"step": 36100
|
|
},
|
|
{
|
|
"entropy": 5.4258904457092285,
|
|
"epoch": 3.0157868359505513,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004097057124319212,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.24604348987340927,
|
|
"num_tokens": 66416067.0,
|
|
"step": 36105
|
|
},
|
|
{
|
|
"entropy": 5.444742155075073,
|
|
"epoch": 3.016204477113264,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004096818661174134,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.23017148226499556,
|
|
"num_tokens": 66424376.0,
|
|
"step": 36110
|
|
},
|
|
{
|
|
"entropy": 5.46991491317749,
|
|
"epoch": 3.0166221182759774,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040965801744513754,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.229903507232666,
|
|
"num_tokens": 66433941.0,
|
|
"step": 36115
|
|
},
|
|
{
|
|
"entropy": 5.433261823654175,
|
|
"epoch": 3.01703975943869,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000409634166415511,
|
|
"loss": 4.6526,
|
|
"mean_token_accuracy": 0.23570844531059265,
|
|
"num_tokens": 66441930.0,
|
|
"step": 36120
|
|
},
|
|
{
|
|
"entropy": 5.46688551902771,
|
|
"epoch": 3.0174574006014034,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004096103130289513,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.2317436382174492,
|
|
"num_tokens": 66450632.0,
|
|
"step": 36125
|
|
},
|
|
{
|
|
"entropy": 5.41634955406189,
|
|
"epoch": 3.0178750417641163,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000409586457285876,
|
|
"loss": 4.5945,
|
|
"mean_token_accuracy": 0.2524599447846413,
|
|
"num_tokens": 66459435.0,
|
|
"step": 36130
|
|
},
|
|
{
|
|
"entropy": 5.376142978668213,
|
|
"epoch": 3.018292682926829,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004095625991867028,
|
|
"loss": 4.6488,
|
|
"mean_token_accuracy": 0.23745148181915282,
|
|
"num_tokens": 66468448.0,
|
|
"step": 36135
|
|
},
|
|
{
|
|
"entropy": 5.444307041168213,
|
|
"epoch": 3.0187103240895423,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040953873873184933,
|
|
"loss": 4.6794,
|
|
"mean_token_accuracy": 0.23650143295526505,
|
|
"num_tokens": 66477885.0,
|
|
"step": 36140
|
|
},
|
|
{
|
|
"entropy": 5.4743608951568605,
|
|
"epoch": 3.019127965252255,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004095148759217333,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.2379959762096405,
|
|
"num_tokens": 66487131.0,
|
|
"step": 36145
|
|
},
|
|
{
|
|
"entropy": 5.428804874420166,
|
|
"epoch": 3.0195456064149684,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004094910107567725,
|
|
"loss": 4.6188,
|
|
"mean_token_accuracy": 0.244517682492733,
|
|
"num_tokens": 66495129.0,
|
|
"step": 36150
|
|
},
|
|
{
|
|
"entropy": 5.435158824920654,
|
|
"epoch": 3.019963247577681,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004094671432373846,
|
|
"loss": 4.6935,
|
|
"mean_token_accuracy": 0.2354654774069786,
|
|
"num_tokens": 66503735.0,
|
|
"step": 36155
|
|
},
|
|
{
|
|
"entropy": 5.4621274948120115,
|
|
"epoch": 3.0203808887403945,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004094432733639875,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.22636020332574844,
|
|
"num_tokens": 66513740.0,
|
|
"step": 36160
|
|
},
|
|
{
|
|
"entropy": 5.427623653411866,
|
|
"epoch": 3.0207985299031073,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040941940113699906,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.23780016005039215,
|
|
"num_tokens": 66523812.0,
|
|
"step": 36165
|
|
},
|
|
{
|
|
"entropy": 5.434284973144531,
|
|
"epoch": 3.02121617106582,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004093955265568372,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.24239584654569626,
|
|
"num_tokens": 66533037.0,
|
|
"step": 36170
|
|
},
|
|
{
|
|
"entropy": 5.418207216262817,
|
|
"epoch": 3.0216338122285333,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040937164962392,
|
|
"loss": 4.6111,
|
|
"mean_token_accuracy": 0.24653150141239166,
|
|
"num_tokens": 66541609.0,
|
|
"step": 36175
|
|
},
|
|
{
|
|
"entropy": 5.371778774261474,
|
|
"epoch": 3.022051453391246,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004093477703386651,
|
|
"loss": 4.5861,
|
|
"mean_token_accuracy": 0.23460968732833862,
|
|
"num_tokens": 66550764.0,
|
|
"step": 36180
|
|
},
|
|
{
|
|
"entropy": 5.453441333770752,
|
|
"epoch": 3.0224690945539594,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000409323888701491,
|
|
"loss": 4.7784,
|
|
"mean_token_accuracy": 0.2266916587948799,
|
|
"num_tokens": 66559605.0,
|
|
"step": 36185
|
|
},
|
|
{
|
|
"entropy": 5.465487957000732,
|
|
"epoch": 3.022886735716672,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040930000471281534,
|
|
"loss": 4.6957,
|
|
"mean_token_accuracy": 0.24156027883291245,
|
|
"num_tokens": 66568754.0,
|
|
"step": 36190
|
|
},
|
|
{
|
|
"entropy": 5.5200892925262455,
|
|
"epoch": 3.023304376879385,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040927611837305656,
|
|
"loss": 4.7194,
|
|
"mean_token_accuracy": 0.23279963433742523,
|
|
"num_tokens": 66579044.0,
|
|
"step": 36195
|
|
},
|
|
{
|
|
"entropy": 5.5657734870910645,
|
|
"epoch": 3.0237220180420983,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040925222968263275,
|
|
"loss": 4.913,
|
|
"mean_token_accuracy": 0.21828391999006272,
|
|
"num_tokens": 66589036.0,
|
|
"step": 36200
|
|
},
|
|
{
|
|
"entropy": 5.487263441085815,
|
|
"epoch": 3.024139659204811,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040922833864196194,
|
|
"loss": 4.7129,
|
|
"mean_token_accuracy": 0.2329331949353218,
|
|
"num_tokens": 66597784.0,
|
|
"step": 36205
|
|
},
|
|
{
|
|
"entropy": 5.446956968307495,
|
|
"epoch": 3.0245573003675243,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004092044452514626,
|
|
"loss": 4.65,
|
|
"mean_token_accuracy": 0.24355246722698212,
|
|
"num_tokens": 66606936.0,
|
|
"step": 36210
|
|
},
|
|
{
|
|
"entropy": 5.375765609741211,
|
|
"epoch": 3.024974941530237,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040918054951155283,
|
|
"loss": 4.6572,
|
|
"mean_token_accuracy": 0.23902663588523865,
|
|
"num_tokens": 66615563.0,
|
|
"step": 36215
|
|
},
|
|
{
|
|
"entropy": 5.374551820755005,
|
|
"epoch": 3.0253925826929504,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000409156651422651,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.2353028252720833,
|
|
"num_tokens": 66624678.0,
|
|
"step": 36220
|
|
},
|
|
{
|
|
"entropy": 5.398965120315552,
|
|
"epoch": 3.0258102238556632,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040913275098517556,
|
|
"loss": 4.6299,
|
|
"mean_token_accuracy": 0.24258965700864793,
|
|
"num_tokens": 66633317.0,
|
|
"step": 36225
|
|
},
|
|
{
|
|
"entropy": 5.525543737411499,
|
|
"epoch": 3.026227865018376,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004091088481995448,
|
|
"loss": 4.7299,
|
|
"mean_token_accuracy": 0.23567213714122773,
|
|
"num_tokens": 66642252.0,
|
|
"step": 36230
|
|
},
|
|
{
|
|
"entropy": 5.538074636459351,
|
|
"epoch": 3.0266455061810893,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004090849430661773,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.22796778231859208,
|
|
"num_tokens": 66652131.0,
|
|
"step": 36235
|
|
},
|
|
{
|
|
"entropy": 5.462857723236084,
|
|
"epoch": 3.027063147343802,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040906103558549143,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.23392819613218307,
|
|
"num_tokens": 66661159.0,
|
|
"step": 36240
|
|
},
|
|
{
|
|
"entropy": 5.381189823150635,
|
|
"epoch": 3.0274807885065154,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004090371257579058,
|
|
"loss": 4.6791,
|
|
"mean_token_accuracy": 0.23689408600330353,
|
|
"num_tokens": 66669667.0,
|
|
"step": 36245
|
|
},
|
|
{
|
|
"entropy": 5.415284919738769,
|
|
"epoch": 3.027898429669228,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004090132135838389,
|
|
"loss": 4.6224,
|
|
"mean_token_accuracy": 0.23647918701171874,
|
|
"num_tokens": 66677933.0,
|
|
"step": 36250
|
|
},
|
|
{
|
|
"entropy": 5.41601448059082,
|
|
"epoch": 3.028316070831941,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004089892990637094,
|
|
"loss": 4.617,
|
|
"mean_token_accuracy": 0.2368388667702675,
|
|
"num_tokens": 66687134.0,
|
|
"step": 36255
|
|
},
|
|
{
|
|
"entropy": 5.4824971675872805,
|
|
"epoch": 3.0287337119946542,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040896538219793596,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.23204070180654526,
|
|
"num_tokens": 66696616.0,
|
|
"step": 36260
|
|
},
|
|
{
|
|
"entropy": 5.401013374328613,
|
|
"epoch": 3.029151353157367,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004089414629869373,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.23920750766992568,
|
|
"num_tokens": 66705425.0,
|
|
"step": 36265
|
|
},
|
|
{
|
|
"entropy": 5.383630800247192,
|
|
"epoch": 3.0295689943200803,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000408917541431132,
|
|
"loss": 4.702,
|
|
"mean_token_accuracy": 0.2316548779606819,
|
|
"num_tokens": 66714566.0,
|
|
"step": 36270
|
|
},
|
|
{
|
|
"entropy": 5.445295190811157,
|
|
"epoch": 3.029986635482793,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00040889361753093894,
|
|
"loss": 4.691,
|
|
"mean_token_accuracy": 0.23636971563100814,
|
|
"num_tokens": 66723579.0,
|
|
"step": 36275
|
|
},
|
|
{
|
|
"entropy": 5.475968980789185,
|
|
"epoch": 3.0304042766455064,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004088696912867769,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.2376476928591728,
|
|
"num_tokens": 66731714.0,
|
|
"step": 36280
|
|
},
|
|
{
|
|
"entropy": 5.3489417552948,
|
|
"epoch": 3.030821917808219,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000408845762699065,
|
|
"loss": 4.6376,
|
|
"mean_token_accuracy": 0.2413119286298752,
|
|
"num_tokens": 66740548.0,
|
|
"step": 36285
|
|
},
|
|
{
|
|
"entropy": 5.425238704681396,
|
|
"epoch": 3.031239558970932,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004088218317682217,
|
|
"loss": 4.7196,
|
|
"mean_token_accuracy": 0.2401143044233322,
|
|
"num_tokens": 66749709.0,
|
|
"step": 36290
|
|
},
|
|
{
|
|
"entropy": 5.4917889595031735,
|
|
"epoch": 3.0316572001336453,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004087978984946662,
|
|
"loss": 4.7519,
|
|
"mean_token_accuracy": 0.2340407997369766,
|
|
"num_tokens": 66759310.0,
|
|
"step": 36295
|
|
},
|
|
{
|
|
"entropy": 5.503571510314941,
|
|
"epoch": 3.032074841296358,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040877396287881745,
|
|
"loss": 4.7293,
|
|
"mean_token_accuracy": 0.2293096348643303,
|
|
"num_tokens": 66768711.0,
|
|
"step": 36300
|
|
},
|
|
{
|
|
"entropy": 5.397570943832397,
|
|
"epoch": 3.0324924824590713,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004087500249210944,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.236940498650074,
|
|
"num_tokens": 66778194.0,
|
|
"step": 36305
|
|
},
|
|
{
|
|
"entropy": 5.416211080551148,
|
|
"epoch": 3.032910123621784,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040872608462191623,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.22717481702566147,
|
|
"num_tokens": 66788030.0,
|
|
"step": 36310
|
|
},
|
|
{
|
|
"entropy": 5.450184297561646,
|
|
"epoch": 3.033327764784497,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040870214198170205,
|
|
"loss": 4.6612,
|
|
"mean_token_accuracy": 0.23719728291034697,
|
|
"num_tokens": 66797412.0,
|
|
"step": 36315
|
|
},
|
|
{
|
|
"entropy": 5.536885929107666,
|
|
"epoch": 3.03374540594721,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00040867819700087085,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.2234065130352974,
|
|
"num_tokens": 66807215.0,
|
|
"step": 36320
|
|
},
|
|
{
|
|
"entropy": 5.572017431259155,
|
|
"epoch": 3.034163047109923,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004086542496798419,
|
|
"loss": 4.8772,
|
|
"mean_token_accuracy": 0.2193937599658966,
|
|
"num_tokens": 66817381.0,
|
|
"step": 36325
|
|
},
|
|
{
|
|
"entropy": 5.484314632415772,
|
|
"epoch": 3.0345806882726363,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00040863030001903446,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.23361061066389083,
|
|
"num_tokens": 66826311.0,
|
|
"step": 36330
|
|
},
|
|
{
|
|
"entropy": 5.480105066299439,
|
|
"epoch": 3.034998329435349,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004086063480188677,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.23702383488416673,
|
|
"num_tokens": 66835318.0,
|
|
"step": 36335
|
|
},
|
|
{
|
|
"entropy": 5.414396190643311,
|
|
"epoch": 3.0354159705980623,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040858239367976115,
|
|
"loss": 4.6213,
|
|
"mean_token_accuracy": 0.2438257023692131,
|
|
"num_tokens": 66844493.0,
|
|
"step": 36340
|
|
},
|
|
{
|
|
"entropy": 5.41215763092041,
|
|
"epoch": 3.035833611760775,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040855843700213386,
|
|
"loss": 4.6393,
|
|
"mean_token_accuracy": 0.2438749924302101,
|
|
"num_tokens": 66853730.0,
|
|
"step": 36345
|
|
},
|
|
{
|
|
"entropy": 5.435747814178467,
|
|
"epoch": 3.036251252923488,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040853447798640534,
|
|
"loss": 4.6521,
|
|
"mean_token_accuracy": 0.23851799070835114,
|
|
"num_tokens": 66863291.0,
|
|
"step": 36350
|
|
},
|
|
{
|
|
"entropy": 5.438413000106811,
|
|
"epoch": 3.036668894086201,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004085105166329952,
|
|
"loss": 4.6394,
|
|
"mean_token_accuracy": 0.24516381770372392,
|
|
"num_tokens": 66872215.0,
|
|
"step": 36355
|
|
},
|
|
{
|
|
"entropy": 5.379040765762329,
|
|
"epoch": 3.037086535248914,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040848655294232263,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.24412162154912947,
|
|
"num_tokens": 66881446.0,
|
|
"step": 36360
|
|
},
|
|
{
|
|
"entropy": 5.4157147884368895,
|
|
"epoch": 3.0375041764116273,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004084625869148074,
|
|
"loss": 4.7105,
|
|
"mean_token_accuracy": 0.23084918707609176,
|
|
"num_tokens": 66890096.0,
|
|
"step": 36365
|
|
},
|
|
{
|
|
"entropy": 5.4422839164733885,
|
|
"epoch": 3.03792181757434,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040843861855086885,
|
|
"loss": 4.6936,
|
|
"mean_token_accuracy": 0.23718699365854262,
|
|
"num_tokens": 66899025.0,
|
|
"step": 36370
|
|
},
|
|
{
|
|
"entropy": 5.291573715209961,
|
|
"epoch": 3.038339458737053,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004084146478509266,
|
|
"loss": 4.5515,
|
|
"mean_token_accuracy": 0.24437081664800644,
|
|
"num_tokens": 66907708.0,
|
|
"step": 36375
|
|
},
|
|
{
|
|
"entropy": 5.484549570083618,
|
|
"epoch": 3.038757099899766,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040839067481540046,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.23010853976011275,
|
|
"num_tokens": 66918103.0,
|
|
"step": 36380
|
|
},
|
|
{
|
|
"entropy": 5.489122343063355,
|
|
"epoch": 3.039174741062479,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040836669944470995,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.23101591914892197,
|
|
"num_tokens": 66927992.0,
|
|
"step": 36385
|
|
},
|
|
{
|
|
"entropy": 5.483629322052002,
|
|
"epoch": 3.0395923822251922,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004083427217392748,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.22821035087108613,
|
|
"num_tokens": 66937949.0,
|
|
"step": 36390
|
|
},
|
|
{
|
|
"entropy": 5.465963745117188,
|
|
"epoch": 3.040010023387905,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040831874169951486,
|
|
"loss": 4.7538,
|
|
"mean_token_accuracy": 0.23520318418741226,
|
|
"num_tokens": 66946853.0,
|
|
"step": 36395
|
|
},
|
|
{
|
|
"entropy": 5.5758050918579105,
|
|
"epoch": 3.0404276645506183,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004082947593258499,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.2302064284682274,
|
|
"num_tokens": 66955978.0,
|
|
"step": 36400
|
|
},
|
|
{
|
|
"entropy": 5.454406595230102,
|
|
"epoch": 3.040845305713331,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040827077461869966,
|
|
"loss": 4.6794,
|
|
"mean_token_accuracy": 0.23817082196474076,
|
|
"num_tokens": 66965053.0,
|
|
"step": 36405
|
|
},
|
|
{
|
|
"entropy": 5.429448032379151,
|
|
"epoch": 3.041262946876044,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040824678757848406,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.22949883490800857,
|
|
"num_tokens": 66975354.0,
|
|
"step": 36410
|
|
},
|
|
{
|
|
"entropy": 5.482342100143432,
|
|
"epoch": 3.041680588038757,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004082227982056232,
|
|
"loss": 4.7169,
|
|
"mean_token_accuracy": 0.22841795086860656,
|
|
"num_tokens": 66984806.0,
|
|
"step": 36415
|
|
},
|
|
{
|
|
"entropy": 5.443726825714111,
|
|
"epoch": 3.04209822920147,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040819880650053673,
|
|
"loss": 4.6754,
|
|
"mean_token_accuracy": 0.2286151722073555,
|
|
"num_tokens": 66993273.0,
|
|
"step": 36420
|
|
},
|
|
{
|
|
"entropy": 5.3717693328857425,
|
|
"epoch": 3.0425158703641833,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004081748124636449,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.24105132520198821,
|
|
"num_tokens": 67003040.0,
|
|
"step": 36425
|
|
},
|
|
{
|
|
"entropy": 5.37707667350769,
|
|
"epoch": 3.042933511526896,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004081508160953677,
|
|
"loss": 4.499,
|
|
"mean_token_accuracy": 0.25909424424171446,
|
|
"num_tokens": 67012638.0,
|
|
"step": 36430
|
|
},
|
|
{
|
|
"entropy": 5.392331457138061,
|
|
"epoch": 3.043351152689609,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004081268173961251,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.2323453441262245,
|
|
"num_tokens": 67022298.0,
|
|
"step": 36435
|
|
},
|
|
{
|
|
"entropy": 5.4222673892974855,
|
|
"epoch": 3.043768793852322,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004081028163663374,
|
|
"loss": 4.6856,
|
|
"mean_token_accuracy": 0.23497749269008636,
|
|
"num_tokens": 67031142.0,
|
|
"step": 36440
|
|
},
|
|
{
|
|
"entropy": 5.464275455474853,
|
|
"epoch": 3.044186435015035,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004080788130064247,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.2321516528725624,
|
|
"num_tokens": 67039983.0,
|
|
"step": 36445
|
|
},
|
|
{
|
|
"entropy": 5.377463483810425,
|
|
"epoch": 3.044604076177748,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004080548073168072,
|
|
"loss": 4.6466,
|
|
"mean_token_accuracy": 0.23082605451345445,
|
|
"num_tokens": 67048773.0,
|
|
"step": 36450
|
|
},
|
|
{
|
|
"entropy": 5.46271915435791,
|
|
"epoch": 3.045021717340461,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000408030799297905,
|
|
"loss": 4.7015,
|
|
"mean_token_accuracy": 0.23408907055854797,
|
|
"num_tokens": 67057945.0,
|
|
"step": 36455
|
|
},
|
|
{
|
|
"entropy": 5.430496025085449,
|
|
"epoch": 3.0454393585031743,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040800678895013865,
|
|
"loss": 4.6971,
|
|
"mean_token_accuracy": 0.23534979522228242,
|
|
"num_tokens": 67067593.0,
|
|
"step": 36460
|
|
},
|
|
{
|
|
"entropy": 5.464330863952637,
|
|
"epoch": 3.045856999665887,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004079827762739283,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.2277171343564987,
|
|
"num_tokens": 67077105.0,
|
|
"step": 36465
|
|
},
|
|
{
|
|
"entropy": 5.453920459747314,
|
|
"epoch": 3.0462746408286,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00040795876126969446,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.2308749958872795,
|
|
"num_tokens": 67086287.0,
|
|
"step": 36470
|
|
},
|
|
{
|
|
"entropy": 5.502408456802368,
|
|
"epoch": 3.046692281991313,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004079347439378574,
|
|
"loss": 4.6935,
|
|
"mean_token_accuracy": 0.228306283056736,
|
|
"num_tokens": 67095716.0,
|
|
"step": 36475
|
|
},
|
|
{
|
|
"entropy": 5.4685948371887205,
|
|
"epoch": 3.047109923154026,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040791072427883763,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.23512453883886336,
|
|
"num_tokens": 67104486.0,
|
|
"step": 36480
|
|
},
|
|
{
|
|
"entropy": 5.437877178192139,
|
|
"epoch": 3.047527564316739,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004078867022930557,
|
|
"loss": 4.6432,
|
|
"mean_token_accuracy": 0.24583517014980316,
|
|
"num_tokens": 67113308.0,
|
|
"step": 36485
|
|
},
|
|
{
|
|
"entropy": 5.4672926902771,
|
|
"epoch": 3.047945205479452,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000407862677980932,
|
|
"loss": 4.7256,
|
|
"mean_token_accuracy": 0.2320086255669594,
|
|
"num_tokens": 67122288.0,
|
|
"step": 36490
|
|
},
|
|
{
|
|
"entropy": 5.4993256568908695,
|
|
"epoch": 3.048362846642165,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004078386513428873,
|
|
"loss": 4.6996,
|
|
"mean_token_accuracy": 0.24429633766412734,
|
|
"num_tokens": 67130689.0,
|
|
"step": 36495
|
|
},
|
|
{
|
|
"entropy": 5.494169664382935,
|
|
"epoch": 3.048780487804878,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040781462237934207,
|
|
"loss": 4.6965,
|
|
"mean_token_accuracy": 0.23226810544729232,
|
|
"num_tokens": 67139567.0,
|
|
"step": 36500
|
|
},
|
|
{
|
|
"entropy": 5.523294925689697,
|
|
"epoch": 3.049198128967591,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040779059109071706,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.22693851292133332,
|
|
"num_tokens": 67148860.0,
|
|
"step": 36505
|
|
},
|
|
{
|
|
"entropy": 5.405765104293823,
|
|
"epoch": 3.049615770130304,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004077665574774328,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.23702493607997893,
|
|
"num_tokens": 67157263.0,
|
|
"step": 36510
|
|
},
|
|
{
|
|
"entropy": 5.375216388702393,
|
|
"epoch": 3.050033411293017,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004077425215399102,
|
|
"loss": 4.6017,
|
|
"mean_token_accuracy": 0.24637120366096496,
|
|
"num_tokens": 67166222.0,
|
|
"step": 36515
|
|
},
|
|
{
|
|
"entropy": 5.354753112792968,
|
|
"epoch": 3.0504510524557302,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00040771848327856994,
|
|
"loss": 4.6474,
|
|
"mean_token_accuracy": 0.23891433626413344,
|
|
"num_tokens": 67174968.0,
|
|
"step": 36520
|
|
},
|
|
{
|
|
"entropy": 5.4694312572479244,
|
|
"epoch": 3.050868693618443,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004076944426938329,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.23086037039756774,
|
|
"num_tokens": 67183607.0,
|
|
"step": 36525
|
|
},
|
|
{
|
|
"entropy": 5.428463268280029,
|
|
"epoch": 3.051286334781156,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004076703997861199,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.23123235404491424,
|
|
"num_tokens": 67192521.0,
|
|
"step": 36530
|
|
},
|
|
{
|
|
"entropy": 5.506789112091065,
|
|
"epoch": 3.051703975943869,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040764635455585186,
|
|
"loss": 4.7889,
|
|
"mean_token_accuracy": 0.2251426547765732,
|
|
"num_tokens": 67201709.0,
|
|
"step": 36535
|
|
},
|
|
{
|
|
"entropy": 5.484769010543824,
|
|
"epoch": 3.052121617106582,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004076223070034498,
|
|
"loss": 4.7389,
|
|
"mean_token_accuracy": 0.23515902310609818,
|
|
"num_tokens": 67210107.0,
|
|
"step": 36540
|
|
},
|
|
{
|
|
"entropy": 5.433410787582398,
|
|
"epoch": 3.052539258269295,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004075982571293345,
|
|
"loss": 4.5971,
|
|
"mean_token_accuracy": 0.24004554897546768,
|
|
"num_tokens": 67218946.0,
|
|
"step": 36545
|
|
},
|
|
{
|
|
"entropy": 5.48600811958313,
|
|
"epoch": 3.052956899432008,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040757420493392715,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.23248131275177003,
|
|
"num_tokens": 67228672.0,
|
|
"step": 36550
|
|
},
|
|
{
|
|
"entropy": 5.56113715171814,
|
|
"epoch": 3.053374540594721,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040755015041764884,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.22184743285179137,
|
|
"num_tokens": 67238775.0,
|
|
"step": 36555
|
|
},
|
|
{
|
|
"entropy": 5.4966575622558596,
|
|
"epoch": 3.053792181757434,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004075260935809205,
|
|
"loss": 4.6439,
|
|
"mean_token_accuracy": 0.23882192075252534,
|
|
"num_tokens": 67248034.0,
|
|
"step": 36560
|
|
},
|
|
{
|
|
"entropy": 5.455309152603149,
|
|
"epoch": 3.054209822920147,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004075020344241634,
|
|
"loss": 4.712,
|
|
"mean_token_accuracy": 0.2344825327396393,
|
|
"num_tokens": 67257889.0,
|
|
"step": 36565
|
|
},
|
|
{
|
|
"entropy": 5.464329528808594,
|
|
"epoch": 3.05462746408286,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004074779729477986,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.22695842981338502,
|
|
"num_tokens": 67267276.0,
|
|
"step": 36570
|
|
},
|
|
{
|
|
"entropy": 5.448736619949341,
|
|
"epoch": 3.055045105245573,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004074539091522475,
|
|
"loss": 4.6634,
|
|
"mean_token_accuracy": 0.23487700670957565,
|
|
"num_tokens": 67275892.0,
|
|
"step": 36575
|
|
},
|
|
{
|
|
"entropy": 5.431583881378174,
|
|
"epoch": 3.055462746408286,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00040742984303793135,
|
|
"loss": 4.7017,
|
|
"mean_token_accuracy": 0.23008646667003632,
|
|
"num_tokens": 67284763.0,
|
|
"step": 36580
|
|
},
|
|
{
|
|
"entropy": 5.502442455291748,
|
|
"epoch": 3.055880387570999,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004074057746052713,
|
|
"loss": 4.7208,
|
|
"mean_token_accuracy": 0.23468555510044098,
|
|
"num_tokens": 67293812.0,
|
|
"step": 36585
|
|
},
|
|
{
|
|
"entropy": 5.405499887466431,
|
|
"epoch": 3.056298028733712,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004073817038546888,
|
|
"loss": 4.6229,
|
|
"mean_token_accuracy": 0.23934853971004486,
|
|
"num_tokens": 67303990.0,
|
|
"step": 36590
|
|
},
|
|
{
|
|
"entropy": 5.4926605224609375,
|
|
"epoch": 3.056715669896425,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040735763078660536,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.23184272646903992,
|
|
"num_tokens": 67313128.0,
|
|
"step": 36595
|
|
},
|
|
{
|
|
"entropy": 5.51036958694458,
|
|
"epoch": 3.057133311059138,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004073335554014421,
|
|
"loss": 4.7312,
|
|
"mean_token_accuracy": 0.22661150395870208,
|
|
"num_tokens": 67322008.0,
|
|
"step": 36600
|
|
},
|
|
{
|
|
"entropy": 5.503399085998535,
|
|
"epoch": 3.057550952221851,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040730947769962076,
|
|
"loss": 4.7812,
|
|
"mean_token_accuracy": 0.23452901989221572,
|
|
"num_tokens": 67331667.0,
|
|
"step": 36605
|
|
},
|
|
{
|
|
"entropy": 5.439412689208984,
|
|
"epoch": 3.057968593384564,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004072853976815627,
|
|
"loss": 4.6302,
|
|
"mean_token_accuracy": 0.2389998570084572,
|
|
"num_tokens": 67341330.0,
|
|
"step": 36610
|
|
},
|
|
{
|
|
"entropy": 5.452394151687622,
|
|
"epoch": 3.058386234547277,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004072613153476895,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.2336942344903946,
|
|
"num_tokens": 67350612.0,
|
|
"step": 36615
|
|
},
|
|
{
|
|
"entropy": 5.496504163742065,
|
|
"epoch": 3.05880387570999,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040723723069842284,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.23237505555152893,
|
|
"num_tokens": 67359956.0,
|
|
"step": 36620
|
|
},
|
|
{
|
|
"entropy": 5.522736883163452,
|
|
"epoch": 3.059221516872703,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004072131437341843,
|
|
"loss": 4.727,
|
|
"mean_token_accuracy": 0.2330721437931061,
|
|
"num_tokens": 67369716.0,
|
|
"step": 36625
|
|
},
|
|
{
|
|
"entropy": 5.443074655532837,
|
|
"epoch": 3.059639158035416,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004071890544553954,
|
|
"loss": 4.5979,
|
|
"mean_token_accuracy": 0.2443225458264351,
|
|
"num_tokens": 67378537.0,
|
|
"step": 36630
|
|
},
|
|
{
|
|
"entropy": 5.366362762451172,
|
|
"epoch": 3.060056799198129,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00040716496286247807,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.23506345748901367,
|
|
"num_tokens": 67387147.0,
|
|
"step": 36635
|
|
},
|
|
{
|
|
"entropy": 5.408819627761841,
|
|
"epoch": 3.060474440360842,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040714086895585406,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.24303647130727768,
|
|
"num_tokens": 67395573.0,
|
|
"step": 36640
|
|
},
|
|
{
|
|
"entropy": 5.513244581222534,
|
|
"epoch": 3.060892081523555,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00040711677273594496,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.2370111957192421,
|
|
"num_tokens": 67404546.0,
|
|
"step": 36645
|
|
},
|
|
{
|
|
"entropy": 5.48950834274292,
|
|
"epoch": 3.0613097226862678,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004070926742031728,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.23499978184700013,
|
|
"num_tokens": 67413324.0,
|
|
"step": 36650
|
|
},
|
|
{
|
|
"entropy": 5.425091934204102,
|
|
"epoch": 3.061727363848981,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004070685733579593,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.22986517548561097,
|
|
"num_tokens": 67422624.0,
|
|
"step": 36655
|
|
},
|
|
{
|
|
"entropy": 5.367113208770752,
|
|
"epoch": 3.062145005011694,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040704447020072657,
|
|
"loss": 4.559,
|
|
"mean_token_accuracy": 0.2410142183303833,
|
|
"num_tokens": 67431789.0,
|
|
"step": 36660
|
|
},
|
|
{
|
|
"entropy": 5.435756778717041,
|
|
"epoch": 3.062562646174407,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004070203647318963,
|
|
"loss": 4.6625,
|
|
"mean_token_accuracy": 0.23898268193006517,
|
|
"num_tokens": 67440810.0,
|
|
"step": 36665
|
|
},
|
|
{
|
|
"entropy": 5.416182327270508,
|
|
"epoch": 3.06298028733712,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004069962569518907,
|
|
"loss": 4.5995,
|
|
"mean_token_accuracy": 0.24000135511159898,
|
|
"num_tokens": 67449191.0,
|
|
"step": 36670
|
|
},
|
|
{
|
|
"entropy": 5.440860366821289,
|
|
"epoch": 3.0633979284998327,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004069721468611318,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.22679444551467895,
|
|
"num_tokens": 67458973.0,
|
|
"step": 36675
|
|
},
|
|
{
|
|
"entropy": 5.456608152389526,
|
|
"epoch": 3.063815569662546,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004069480344600415,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.23068586140871047,
|
|
"num_tokens": 67468292.0,
|
|
"step": 36680
|
|
},
|
|
{
|
|
"entropy": 5.495467567443848,
|
|
"epoch": 3.064233210825259,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004069239197490421,
|
|
"loss": 4.6999,
|
|
"mean_token_accuracy": 0.22862273901700975,
|
|
"num_tokens": 67477732.0,
|
|
"step": 36685
|
|
},
|
|
{
|
|
"entropy": 5.529880523681641,
|
|
"epoch": 3.064650851987972,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00040689980272855573,
|
|
"loss": 4.7679,
|
|
"mean_token_accuracy": 0.2250522643327713,
|
|
"num_tokens": 67487240.0,
|
|
"step": 36690
|
|
},
|
|
{
|
|
"entropy": 5.407333278656006,
|
|
"epoch": 3.065068493150685,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004068756833990045,
|
|
"loss": 4.6607,
|
|
"mean_token_accuracy": 0.2395135849714279,
|
|
"num_tokens": 67496479.0,
|
|
"step": 36695
|
|
},
|
|
{
|
|
"entropy": 5.411637306213379,
|
|
"epoch": 3.065486134313398,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004068515617608107,
|
|
"loss": 4.6331,
|
|
"mean_token_accuracy": 0.23727435022592544,
|
|
"num_tokens": 67505881.0,
|
|
"step": 36700
|
|
},
|
|
{
|
|
"entropy": 5.466477680206299,
|
|
"epoch": 3.065903775476111,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040682743781439657,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.2407156139612198,
|
|
"num_tokens": 67514493.0,
|
|
"step": 36705
|
|
},
|
|
{
|
|
"entropy": 5.473910760879517,
|
|
"epoch": 3.0663214166388237,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00040680331156018446,
|
|
"loss": 4.6833,
|
|
"mean_token_accuracy": 0.24037481099367142,
|
|
"num_tokens": 67523299.0,
|
|
"step": 36710
|
|
},
|
|
{
|
|
"entropy": 5.344918203353882,
|
|
"epoch": 3.066739057801537,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040677918299859676,
|
|
"loss": 4.5534,
|
|
"mean_token_accuracy": 0.2488158166408539,
|
|
"num_tokens": 67532774.0,
|
|
"step": 36715
|
|
},
|
|
{
|
|
"entropy": 5.532453727722168,
|
|
"epoch": 3.06715669896425,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004067550521300558,
|
|
"loss": 4.7711,
|
|
"mean_token_accuracy": 0.23230168521404265,
|
|
"num_tokens": 67542532.0,
|
|
"step": 36720
|
|
},
|
|
{
|
|
"entropy": 5.4288873195648195,
|
|
"epoch": 3.067574340126963,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004067309189549841,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.23083772957324983,
|
|
"num_tokens": 67551248.0,
|
|
"step": 36725
|
|
},
|
|
{
|
|
"entropy": 5.497347164154053,
|
|
"epoch": 3.067991981289676,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00040670678347380407,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.23524915277957917,
|
|
"num_tokens": 67560738.0,
|
|
"step": 36730
|
|
},
|
|
{
|
|
"entropy": 5.428768920898437,
|
|
"epoch": 3.068409622452389,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004066826456869383,
|
|
"loss": 4.7796,
|
|
"mean_token_accuracy": 0.22807466983795166,
|
|
"num_tokens": 67570654.0,
|
|
"step": 36735
|
|
},
|
|
{
|
|
"entropy": 5.402104282379151,
|
|
"epoch": 3.068827263615102,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040665850559480925,
|
|
"loss": 4.6442,
|
|
"mean_token_accuracy": 0.2318405583500862,
|
|
"num_tokens": 67579667.0,
|
|
"step": 36740
|
|
},
|
|
{
|
|
"entropy": 5.542652702331543,
|
|
"epoch": 3.0692449047778148,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00040663436319783965,
|
|
"loss": 4.8159,
|
|
"mean_token_accuracy": 0.2282823860645294,
|
|
"num_tokens": 67589386.0,
|
|
"step": 36745
|
|
},
|
|
{
|
|
"entropy": 5.500620698928833,
|
|
"epoch": 3.069662545940528,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000406610218496452,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.2332329899072647,
|
|
"num_tokens": 67598310.0,
|
|
"step": 36750
|
|
},
|
|
{
|
|
"entropy": 5.498677158355713,
|
|
"epoch": 3.070080187103241,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00040658607149106915,
|
|
"loss": 4.7771,
|
|
"mean_token_accuracy": 0.22986776977777482,
|
|
"num_tokens": 67607736.0,
|
|
"step": 36755
|
|
},
|
|
{
|
|
"entropy": 5.411969518661499,
|
|
"epoch": 3.070497828265954,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004065619221821137,
|
|
"loss": 4.6141,
|
|
"mean_token_accuracy": 0.24383839815855027,
|
|
"num_tokens": 67615787.0,
|
|
"step": 36760
|
|
},
|
|
{
|
|
"entropy": 5.372403144836426,
|
|
"epoch": 3.070915469428667,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004065377705700084,
|
|
"loss": 4.6165,
|
|
"mean_token_accuracy": 0.24246615469455718,
|
|
"num_tokens": 67625016.0,
|
|
"step": 36765
|
|
},
|
|
{
|
|
"entropy": 5.32119574546814,
|
|
"epoch": 3.0713331105913797,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004065136166551761,
|
|
"loss": 4.5504,
|
|
"mean_token_accuracy": 0.2456667646765709,
|
|
"num_tokens": 67633657.0,
|
|
"step": 36770
|
|
},
|
|
{
|
|
"entropy": 5.415801191329956,
|
|
"epoch": 3.071750751754093,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004064894604380397,
|
|
"loss": 4.6219,
|
|
"mean_token_accuracy": 0.24085965752601624,
|
|
"num_tokens": 67642603.0,
|
|
"step": 36775
|
|
},
|
|
{
|
|
"entropy": 5.485280275344849,
|
|
"epoch": 3.0721683929168058,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004064653019190219,
|
|
"loss": 4.688,
|
|
"mean_token_accuracy": 0.23381139934062958,
|
|
"num_tokens": 67652186.0,
|
|
"step": 36780
|
|
},
|
|
{
|
|
"entropy": 5.470937633514405,
|
|
"epoch": 3.072586034079519,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040644114109854583,
|
|
"loss": 4.6821,
|
|
"mean_token_accuracy": 0.244963575899601,
|
|
"num_tokens": 67660805.0,
|
|
"step": 36785
|
|
},
|
|
{
|
|
"entropy": 5.474461221694947,
|
|
"epoch": 3.073003675242232,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00040641697797703436,
|
|
"loss": 4.6891,
|
|
"mean_token_accuracy": 0.23448967784643174,
|
|
"num_tokens": 67669494.0,
|
|
"step": 36790
|
|
},
|
|
{
|
|
"entropy": 5.458641052246094,
|
|
"epoch": 3.0734213164049446,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004063928125549105,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.2361782357096672,
|
|
"num_tokens": 67678743.0,
|
|
"step": 36795
|
|
},
|
|
{
|
|
"entropy": 5.424978446960449,
|
|
"epoch": 3.073838957567658,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004063686448325973,
|
|
"loss": 4.6397,
|
|
"mean_token_accuracy": 0.24713850468397142,
|
|
"num_tokens": 67687319.0,
|
|
"step": 36800
|
|
},
|
|
{
|
|
"entropy": 5.465962934494018,
|
|
"epoch": 3.0742565987303707,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00040634447481051783,
|
|
"loss": 4.6571,
|
|
"mean_token_accuracy": 0.24252478182315826,
|
|
"num_tokens": 67696832.0,
|
|
"step": 36805
|
|
},
|
|
{
|
|
"entropy": 5.472791337966919,
|
|
"epoch": 3.074674239893084,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004063203024890953,
|
|
"loss": 4.6423,
|
|
"mean_token_accuracy": 0.2470078080892563,
|
|
"num_tokens": 67705453.0,
|
|
"step": 36810
|
|
},
|
|
{
|
|
"entropy": 5.462855482101441,
|
|
"epoch": 3.075091881055797,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040629612786875275,
|
|
"loss": 4.8083,
|
|
"mean_token_accuracy": 0.23392847180366516,
|
|
"num_tokens": 67714953.0,
|
|
"step": 36815
|
|
},
|
|
{
|
|
"entropy": 5.466335487365723,
|
|
"epoch": 3.07550952221851,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00040627195094991336,
|
|
"loss": 4.7447,
|
|
"mean_token_accuracy": 0.22520459741353988,
|
|
"num_tokens": 67724206.0,
|
|
"step": 36820
|
|
},
|
|
{
|
|
"entropy": 5.509447336196899,
|
|
"epoch": 3.075927163381223,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004062477717330006,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.23449441492557527,
|
|
"num_tokens": 67733542.0,
|
|
"step": 36825
|
|
},
|
|
{
|
|
"entropy": 5.471573257446289,
|
|
"epoch": 3.0763448045439357,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004062235902184375,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.23502935469150543,
|
|
"num_tokens": 67742654.0,
|
|
"step": 36830
|
|
},
|
|
{
|
|
"entropy": 5.455959177017212,
|
|
"epoch": 3.076762445706649,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004061994064066476,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.23572902530431747,
|
|
"num_tokens": 67751395.0,
|
|
"step": 36835
|
|
},
|
|
{
|
|
"entropy": 5.416534948348999,
|
|
"epoch": 3.0771800868693617,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040617522029805404,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.23302649706602097,
|
|
"num_tokens": 67760169.0,
|
|
"step": 36840
|
|
},
|
|
{
|
|
"entropy": 5.559570932388306,
|
|
"epoch": 3.077597728032075,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040615103189308046,
|
|
"loss": 4.8478,
|
|
"mean_token_accuracy": 0.22236376106739045,
|
|
"num_tokens": 67770643.0,
|
|
"step": 36845
|
|
},
|
|
{
|
|
"entropy": 5.514321899414062,
|
|
"epoch": 3.078015369194788,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00040612684119215015,
|
|
"loss": 4.7705,
|
|
"mean_token_accuracy": 0.228361676633358,
|
|
"num_tokens": 67779104.0,
|
|
"step": 36850
|
|
},
|
|
{
|
|
"entropy": 5.477244472503662,
|
|
"epoch": 3.078433010357501,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004061026481956867,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.22678946256637572,
|
|
"num_tokens": 67789074.0,
|
|
"step": 36855
|
|
},
|
|
{
|
|
"entropy": 5.444464063644409,
|
|
"epoch": 3.078850651520214,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040607845290411356,
|
|
"loss": 4.6997,
|
|
"mean_token_accuracy": 0.22959421277046205,
|
|
"num_tokens": 67798791.0,
|
|
"step": 36860
|
|
},
|
|
{
|
|
"entropy": 5.424159002304077,
|
|
"epoch": 3.0792682926829267,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040605425531785435,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.24215813726186752,
|
|
"num_tokens": 67808221.0,
|
|
"step": 36865
|
|
},
|
|
{
|
|
"entropy": 5.452654886245727,
|
|
"epoch": 3.07968593384564,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040603005543733255,
|
|
"loss": 4.6806,
|
|
"mean_token_accuracy": 0.2345212608575821,
|
|
"num_tokens": 67817255.0,
|
|
"step": 36870
|
|
},
|
|
{
|
|
"entropy": 5.4845061779022215,
|
|
"epoch": 3.0801035750083527,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040600585326297197,
|
|
"loss": 4.7519,
|
|
"mean_token_accuracy": 0.23282674998044967,
|
|
"num_tokens": 67826537.0,
|
|
"step": 36875
|
|
},
|
|
{
|
|
"entropy": 5.488985872268676,
|
|
"epoch": 3.080521216171066,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004059816487951962,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.23230149745941162,
|
|
"num_tokens": 67836149.0,
|
|
"step": 36880
|
|
},
|
|
{
|
|
"entropy": 5.475059127807617,
|
|
"epoch": 3.080938857333779,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040595744203442906,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.23282898366451263,
|
|
"num_tokens": 67845707.0,
|
|
"step": 36885
|
|
},
|
|
{
|
|
"entropy": 5.347981548309326,
|
|
"epoch": 3.0813564984964916,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004059332329810943,
|
|
"loss": 4.6066,
|
|
"mean_token_accuracy": 0.24395161867141724,
|
|
"num_tokens": 67854719.0,
|
|
"step": 36890
|
|
},
|
|
{
|
|
"entropy": 5.407469463348389,
|
|
"epoch": 3.081774139659205,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004059090216356156,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.23150062412023545,
|
|
"num_tokens": 67864247.0,
|
|
"step": 36895
|
|
},
|
|
{
|
|
"entropy": 5.48389196395874,
|
|
"epoch": 3.0821917808219177,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000405884807998417,
|
|
"loss": 4.7383,
|
|
"mean_token_accuracy": 0.2349725052714348,
|
|
"num_tokens": 67872957.0,
|
|
"step": 36900
|
|
},
|
|
{
|
|
"entropy": 5.422287511825561,
|
|
"epoch": 3.082609421984631,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040586059206992214,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.2416742756962776,
|
|
"num_tokens": 67881930.0,
|
|
"step": 36905
|
|
},
|
|
{
|
|
"entropy": 5.375266122817993,
|
|
"epoch": 3.0830270631473438,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040583637385055524,
|
|
"loss": 4.5158,
|
|
"mean_token_accuracy": 0.24954821914434433,
|
|
"num_tokens": 67889702.0,
|
|
"step": 36910
|
|
},
|
|
{
|
|
"entropy": 5.436109161376953,
|
|
"epoch": 3.0834447043100566,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004058121533407401,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.225142639875412,
|
|
"num_tokens": 67900306.0,
|
|
"step": 36915
|
|
},
|
|
{
|
|
"entropy": 5.412719058990478,
|
|
"epoch": 3.08386234547277,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040578793054090075,
|
|
"loss": 4.6059,
|
|
"mean_token_accuracy": 0.24075422883033754,
|
|
"num_tokens": 67909011.0,
|
|
"step": 36920
|
|
},
|
|
{
|
|
"entropy": 5.477752256393432,
|
|
"epoch": 3.0842799866354826,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004057637054514612,
|
|
"loss": 4.7645,
|
|
"mean_token_accuracy": 0.2338234841823578,
|
|
"num_tokens": 67918534.0,
|
|
"step": 36925
|
|
},
|
|
{
|
|
"entropy": 5.347119951248169,
|
|
"epoch": 3.084697627798196,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004057394780728456,
|
|
"loss": 4.5862,
|
|
"mean_token_accuracy": 0.24548629969358443,
|
|
"num_tokens": 67927475.0,
|
|
"step": 36930
|
|
},
|
|
{
|
|
"entropy": 5.428559875488281,
|
|
"epoch": 3.0851152689609087,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004057152484054781,
|
|
"loss": 4.7085,
|
|
"mean_token_accuracy": 0.23099443316459656,
|
|
"num_tokens": 67937153.0,
|
|
"step": 36935
|
|
},
|
|
{
|
|
"entropy": 5.433752536773682,
|
|
"epoch": 3.085532910123622,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004056910164497828,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.23183503448963166,
|
|
"num_tokens": 67946684.0,
|
|
"step": 36940
|
|
},
|
|
{
|
|
"entropy": 5.4570310592651365,
|
|
"epoch": 3.0859505512863348,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00040566678220618394,
|
|
"loss": 4.7874,
|
|
"mean_token_accuracy": 0.22985225468873977,
|
|
"num_tokens": 67955539.0,
|
|
"step": 36945
|
|
},
|
|
{
|
|
"entropy": 5.477051782608032,
|
|
"epoch": 3.0863681924490476,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004056425456751058,
|
|
"loss": 4.6659,
|
|
"mean_token_accuracy": 0.23629528433084487,
|
|
"num_tokens": 67964297.0,
|
|
"step": 36950
|
|
},
|
|
{
|
|
"entropy": 5.507762861251831,
|
|
"epoch": 3.086785833611761,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040561830685697267,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.24045555144548417,
|
|
"num_tokens": 67972857.0,
|
|
"step": 36955
|
|
},
|
|
{
|
|
"entropy": 5.532121753692627,
|
|
"epoch": 3.0872034747744737,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004055940657522088,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.22632549852132797,
|
|
"num_tokens": 67982372.0,
|
|
"step": 36960
|
|
},
|
|
{
|
|
"entropy": 5.4505589485168455,
|
|
"epoch": 3.087621115937187,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004055698223612386,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.22965007573366164,
|
|
"num_tokens": 67991864.0,
|
|
"step": 36965
|
|
},
|
|
{
|
|
"entropy": 5.427795314788819,
|
|
"epoch": 3.0880387570998997,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00040554557668448656,
|
|
"loss": 4.6721,
|
|
"mean_token_accuracy": 0.23265566527843476,
|
|
"num_tokens": 68000458.0,
|
|
"step": 36970
|
|
},
|
|
{
|
|
"entropy": 5.45047082901001,
|
|
"epoch": 3.088456398262613,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000405521328722377,
|
|
"loss": 4.624,
|
|
"mean_token_accuracy": 0.24248305559158326,
|
|
"num_tokens": 68009303.0,
|
|
"step": 36975
|
|
},
|
|
{
|
|
"entropy": 5.534605550765991,
|
|
"epoch": 3.088874039425326,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004054970784753345,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.22783998697996138,
|
|
"num_tokens": 68018969.0,
|
|
"step": 36980
|
|
},
|
|
{
|
|
"entropy": 5.462404489517212,
|
|
"epoch": 3.0892916805880386,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004054728259437836,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.23876805305480958,
|
|
"num_tokens": 68029248.0,
|
|
"step": 36985
|
|
},
|
|
{
|
|
"entropy": 5.4776238918304445,
|
|
"epoch": 3.089709321750752,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004054485711281488,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.2366965666413307,
|
|
"num_tokens": 68038128.0,
|
|
"step": 36990
|
|
},
|
|
{
|
|
"entropy": 5.3851134300231935,
|
|
"epoch": 3.0901269629134647,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00040542431402885477,
|
|
"loss": 4.6143,
|
|
"mean_token_accuracy": 0.24193591624498367,
|
|
"num_tokens": 68046617.0,
|
|
"step": 36995
|
|
},
|
|
{
|
|
"entropy": 5.462745666503906,
|
|
"epoch": 3.090544604076178,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000405400054646326,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.2274642750620842,
|
|
"num_tokens": 68056399.0,
|
|
"step": 37000
|
|
},
|
|
{
|
|
"entropy": 5.344463062286377,
|
|
"epoch": 3.0909622452388907,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004053757929809875,
|
|
"loss": 4.5691,
|
|
"mean_token_accuracy": 0.24064256250858307,
|
|
"num_tokens": 68065461.0,
|
|
"step": 37005
|
|
},
|
|
{
|
|
"entropy": 5.494500541687012,
|
|
"epoch": 3.0913798864016035,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004053515290332637,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.23655998557806016,
|
|
"num_tokens": 68075582.0,
|
|
"step": 37010
|
|
},
|
|
{
|
|
"entropy": 5.430802822113037,
|
|
"epoch": 3.091797527564317,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004053272628035795,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.23280769884586333,
|
|
"num_tokens": 68085682.0,
|
|
"step": 37015
|
|
},
|
|
{
|
|
"entropy": 5.3890444278717045,
|
|
"epoch": 3.0922151687270296,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040530299429235967,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.23136015236377716,
|
|
"num_tokens": 68094501.0,
|
|
"step": 37020
|
|
},
|
|
{
|
|
"entropy": 5.437977695465088,
|
|
"epoch": 3.092632809889743,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040527872350002906,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.2293248564004898,
|
|
"num_tokens": 68104193.0,
|
|
"step": 37025
|
|
},
|
|
{
|
|
"entropy": 5.5341956615448,
|
|
"epoch": 3.0930504510524557,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004052544504270126,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.23395647704601288,
|
|
"num_tokens": 68113023.0,
|
|
"step": 37030
|
|
},
|
|
{
|
|
"entropy": 5.5455810070037845,
|
|
"epoch": 3.093468092215169,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040523017507373526,
|
|
"loss": 4.7609,
|
|
"mean_token_accuracy": 0.22674371749162675,
|
|
"num_tokens": 68123260.0,
|
|
"step": 37035
|
|
},
|
|
{
|
|
"entropy": 5.451196193695068,
|
|
"epoch": 3.0938857333778818,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040520589744062193,
|
|
"loss": 4.6687,
|
|
"mean_token_accuracy": 0.23488442599773407,
|
|
"num_tokens": 68132211.0,
|
|
"step": 37040
|
|
},
|
|
{
|
|
"entropy": 5.447846269607544,
|
|
"epoch": 3.0943033745405946,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040518161752809757,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.23652299344539643,
|
|
"num_tokens": 68140539.0,
|
|
"step": 37045
|
|
},
|
|
{
|
|
"entropy": 5.419537448883057,
|
|
"epoch": 3.094721015703308,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040515733533658734,
|
|
"loss": 4.6443,
|
|
"mean_token_accuracy": 0.242759507894516,
|
|
"num_tokens": 68150417.0,
|
|
"step": 37050
|
|
},
|
|
{
|
|
"entropy": 5.514260578155517,
|
|
"epoch": 3.0951386568660206,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004051330508665163,
|
|
"loss": 4.7011,
|
|
"mean_token_accuracy": 0.23359924256801606,
|
|
"num_tokens": 68160276.0,
|
|
"step": 37055
|
|
},
|
|
{
|
|
"entropy": 5.424924087524414,
|
|
"epoch": 3.095556298028734,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004051087641183095,
|
|
"loss": 4.6446,
|
|
"mean_token_accuracy": 0.24552434384822847,
|
|
"num_tokens": 68168997.0,
|
|
"step": 37060
|
|
},
|
|
{
|
|
"entropy": 5.420285892486572,
|
|
"epoch": 3.0959739391914467,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040508447509239224,
|
|
"loss": 4.7225,
|
|
"mean_token_accuracy": 0.23606329262256623,
|
|
"num_tokens": 68178382.0,
|
|
"step": 37065
|
|
},
|
|
{
|
|
"entropy": 5.352189540863037,
|
|
"epoch": 3.0963915803541595,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040506018378918965,
|
|
"loss": 4.5993,
|
|
"mean_token_accuracy": 0.24606151431798934,
|
|
"num_tokens": 68187197.0,
|
|
"step": 37070
|
|
},
|
|
{
|
|
"entropy": 5.450923919677734,
|
|
"epoch": 3.0968092215168728,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00040503589020912694,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.23062543123960494,
|
|
"num_tokens": 68195938.0,
|
|
"step": 37075
|
|
},
|
|
{
|
|
"entropy": 5.558334875106811,
|
|
"epoch": 3.0972268626795856,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040501159435262944,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.23136974275112152,
|
|
"num_tokens": 68205062.0,
|
|
"step": 37080
|
|
},
|
|
{
|
|
"entropy": 5.4970526695251465,
|
|
"epoch": 3.097644503842299,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004049872962201226,
|
|
"loss": 4.7319,
|
|
"mean_token_accuracy": 0.2312728688120842,
|
|
"num_tokens": 68214298.0,
|
|
"step": 37085
|
|
},
|
|
{
|
|
"entropy": 5.494796562194824,
|
|
"epoch": 3.0980621450050116,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004049629958120316,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.23373400568962097,
|
|
"num_tokens": 68223830.0,
|
|
"step": 37090
|
|
},
|
|
{
|
|
"entropy": 5.520079278945923,
|
|
"epoch": 3.098479786167725,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004049386931287819,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.22782662659883499,
|
|
"num_tokens": 68233532.0,
|
|
"step": 37095
|
|
},
|
|
{
|
|
"entropy": 5.49935245513916,
|
|
"epoch": 3.0988974273304377,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040491438817079903,
|
|
"loss": 4.7172,
|
|
"mean_token_accuracy": 0.23704201430082322,
|
|
"num_tokens": 68242264.0,
|
|
"step": 37100
|
|
},
|
|
{
|
|
"entropy": 5.4194573879241945,
|
|
"epoch": 3.0993150684931505,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004048900809385083,
|
|
"loss": 4.6729,
|
|
"mean_token_accuracy": 0.2384951516985893,
|
|
"num_tokens": 68251564.0,
|
|
"step": 37105
|
|
},
|
|
{
|
|
"entropy": 5.536147165298462,
|
|
"epoch": 3.099732709655864,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004048657714323355,
|
|
"loss": 4.7395,
|
|
"mean_token_accuracy": 0.22930387854576112,
|
|
"num_tokens": 68260962.0,
|
|
"step": 37110
|
|
},
|
|
{
|
|
"entropy": 5.5233885765075685,
|
|
"epoch": 3.1001503508185766,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040484145965270595,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.2234163373708725,
|
|
"num_tokens": 68270230.0,
|
|
"step": 37115
|
|
},
|
|
{
|
|
"entropy": 5.547058916091919,
|
|
"epoch": 3.10056799198129,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004048171456000454,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.23047322332859038,
|
|
"num_tokens": 68281170.0,
|
|
"step": 37120
|
|
},
|
|
{
|
|
"entropy": 5.478194808959961,
|
|
"epoch": 3.1009856331440027,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00040479282927477944,
|
|
"loss": 4.7495,
|
|
"mean_token_accuracy": 0.22988191843032837,
|
|
"num_tokens": 68290504.0,
|
|
"step": 37125
|
|
},
|
|
{
|
|
"entropy": 5.4990581512451175,
|
|
"epoch": 3.1014032743067155,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004047685106773338,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.2369693011045456,
|
|
"num_tokens": 68300258.0,
|
|
"step": 37130
|
|
},
|
|
{
|
|
"entropy": 5.458049392700195,
|
|
"epoch": 3.1018209154694287,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004047441898081342,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.23169533908367157,
|
|
"num_tokens": 68309181.0,
|
|
"step": 37135
|
|
},
|
|
{
|
|
"entropy": 5.398447179794312,
|
|
"epoch": 3.1022385566321415,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004047198666676063,
|
|
"loss": 4.6847,
|
|
"mean_token_accuracy": 0.24325499385595323,
|
|
"num_tokens": 68318242.0,
|
|
"step": 37140
|
|
},
|
|
{
|
|
"entropy": 5.49981107711792,
|
|
"epoch": 3.102656197794855,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000404695541256176,
|
|
"loss": 4.7492,
|
|
"mean_token_accuracy": 0.23146932572126389,
|
|
"num_tokens": 68327588.0,
|
|
"step": 37145
|
|
},
|
|
{
|
|
"entropy": 5.4635967254638675,
|
|
"epoch": 3.1030738389575676,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004046712135742692,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.22193032503128052,
|
|
"num_tokens": 68337387.0,
|
|
"step": 37150
|
|
},
|
|
{
|
|
"entropy": 5.466848468780517,
|
|
"epoch": 3.103491480120281,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004046468836223117,
|
|
"loss": 4.6625,
|
|
"mean_token_accuracy": 0.24117540717124938,
|
|
"num_tokens": 68347153.0,
|
|
"step": 37155
|
|
},
|
|
{
|
|
"entropy": 5.617471551895141,
|
|
"epoch": 3.1039091212829937,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004046225514007295,
|
|
"loss": 4.8888,
|
|
"mean_token_accuracy": 0.22642464339733123,
|
|
"num_tokens": 68358374.0,
|
|
"step": 37160
|
|
},
|
|
{
|
|
"entropy": 5.447758722305298,
|
|
"epoch": 3.1043267624457065,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00040459821690994844,
|
|
"loss": 4.6688,
|
|
"mean_token_accuracy": 0.23861215859651566,
|
|
"num_tokens": 68366682.0,
|
|
"step": 37165
|
|
},
|
|
{
|
|
"entropy": 5.377468633651733,
|
|
"epoch": 3.1047444036084197,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040457388015039455,
|
|
"loss": 4.6447,
|
|
"mean_token_accuracy": 0.2372462660074234,
|
|
"num_tokens": 68377222.0,
|
|
"step": 37170
|
|
},
|
|
{
|
|
"entropy": 5.34436068534851,
|
|
"epoch": 3.1051620447711326,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00040454954112249396,
|
|
"loss": 4.6017,
|
|
"mean_token_accuracy": 0.23585770428180694,
|
|
"num_tokens": 68386333.0,
|
|
"step": 37175
|
|
},
|
|
{
|
|
"entropy": 5.463290977478027,
|
|
"epoch": 3.105579685933846,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040452519982667277,
|
|
"loss": 4.763,
|
|
"mean_token_accuracy": 0.2302576944231987,
|
|
"num_tokens": 68395655.0,
|
|
"step": 37180
|
|
},
|
|
{
|
|
"entropy": 5.5287433624267575,
|
|
"epoch": 3.1059973270965586,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040450085626335695,
|
|
"loss": 4.7447,
|
|
"mean_token_accuracy": 0.2282446429133415,
|
|
"num_tokens": 68404995.0,
|
|
"step": 37185
|
|
},
|
|
{
|
|
"entropy": 5.53636474609375,
|
|
"epoch": 3.1064149682592714,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004044765104329728,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.22628894448280334,
|
|
"num_tokens": 68414992.0,
|
|
"step": 37190
|
|
},
|
|
{
|
|
"entropy": 5.471245622634887,
|
|
"epoch": 3.1068326094219847,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004044521623359466,
|
|
"loss": 4.6566,
|
|
"mean_token_accuracy": 0.23497296273708343,
|
|
"num_tokens": 68423364.0,
|
|
"step": 37195
|
|
},
|
|
{
|
|
"entropy": 5.453661060333252,
|
|
"epoch": 3.1072502505846975,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004044278119727043,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.23518498092889786,
|
|
"num_tokens": 68432292.0,
|
|
"step": 37200
|
|
},
|
|
{
|
|
"entropy": 5.426059913635254,
|
|
"epoch": 3.1076678917474108,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040440345934367243,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.23695213496685028,
|
|
"num_tokens": 68441208.0,
|
|
"step": 37205
|
|
},
|
|
{
|
|
"entropy": 5.430023097991944,
|
|
"epoch": 3.1080855329101236,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00040437910444927726,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.23447970300912857,
|
|
"num_tokens": 68450502.0,
|
|
"step": 37210
|
|
},
|
|
{
|
|
"entropy": 5.506471157073975,
|
|
"epoch": 3.108503174072837,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040435474728994515,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.23655880093574524,
|
|
"num_tokens": 68459558.0,
|
|
"step": 37215
|
|
},
|
|
{
|
|
"entropy": 5.54132194519043,
|
|
"epoch": 3.1089208152355496,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040433038786610246,
|
|
"loss": 4.7908,
|
|
"mean_token_accuracy": 0.22584506273269653,
|
|
"num_tokens": 68469021.0,
|
|
"step": 37220
|
|
},
|
|
{
|
|
"entropy": 5.4705747127532955,
|
|
"epoch": 3.1093384563982625,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004043060261781756,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.2426955983042717,
|
|
"num_tokens": 68477613.0,
|
|
"step": 37225
|
|
},
|
|
{
|
|
"entropy": 5.391110897064209,
|
|
"epoch": 3.1097560975609757,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004042816622265912,
|
|
"loss": 4.695,
|
|
"mean_token_accuracy": 0.232827764749527,
|
|
"num_tokens": 68487603.0,
|
|
"step": 37230
|
|
},
|
|
{
|
|
"entropy": 5.449459886550903,
|
|
"epoch": 3.1101737387236885,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004042572960117756,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.23571681827306748,
|
|
"num_tokens": 68497218.0,
|
|
"step": 37235
|
|
},
|
|
{
|
|
"entropy": 5.485102605819702,
|
|
"epoch": 3.1105913798864018,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00040423292753415547,
|
|
"loss": 4.8023,
|
|
"mean_token_accuracy": 0.23168230950832366,
|
|
"num_tokens": 68505930.0,
|
|
"step": 37240
|
|
},
|
|
{
|
|
"entropy": 5.445746946334839,
|
|
"epoch": 3.1110090210491146,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004042085567941574,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.2339593544602394,
|
|
"num_tokens": 68514664.0,
|
|
"step": 37245
|
|
},
|
|
{
|
|
"entropy": 5.528309345245361,
|
|
"epoch": 3.1114266622118274,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040418418379220805,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.23252333104610443,
|
|
"num_tokens": 68523605.0,
|
|
"step": 37250
|
|
},
|
|
{
|
|
"entropy": 5.498921060562134,
|
|
"epoch": 3.1118443033745407,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000404159808528734,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.2381323218345642,
|
|
"num_tokens": 68531927.0,
|
|
"step": 37255
|
|
},
|
|
{
|
|
"entropy": 5.315600156784058,
|
|
"epoch": 3.1122619445372535,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004041354310041621,
|
|
"loss": 4.6217,
|
|
"mean_token_accuracy": 0.23503672033548356,
|
|
"num_tokens": 68541499.0,
|
|
"step": 37260
|
|
},
|
|
{
|
|
"entropy": 5.4859373569488525,
|
|
"epoch": 3.1126795856999667,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000404111051218919,
|
|
"loss": 4.7858,
|
|
"mean_token_accuracy": 0.22903112918138505,
|
|
"num_tokens": 68551639.0,
|
|
"step": 37265
|
|
},
|
|
{
|
|
"entropy": 5.489503192901611,
|
|
"epoch": 3.1130972268626795,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040408666917343157,
|
|
"loss": 4.6748,
|
|
"mean_token_accuracy": 0.23459618985652925,
|
|
"num_tokens": 68561725.0,
|
|
"step": 37270
|
|
},
|
|
{
|
|
"entropy": 5.460445499420166,
|
|
"epoch": 3.113514868025393,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040406228486812655,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.23414938300848007,
|
|
"num_tokens": 68572045.0,
|
|
"step": 37275
|
|
},
|
|
{
|
|
"entropy": 5.500040817260742,
|
|
"epoch": 3.1139325091881056,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000404037898303431,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.23670705705881118,
|
|
"num_tokens": 68581613.0,
|
|
"step": 37280
|
|
},
|
|
{
|
|
"entropy": 5.456297302246094,
|
|
"epoch": 3.1143501503508184,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004040135094797717,
|
|
"loss": 4.6542,
|
|
"mean_token_accuracy": 0.24479148536920547,
|
|
"num_tokens": 68590544.0,
|
|
"step": 37285
|
|
},
|
|
{
|
|
"entropy": 5.50582914352417,
|
|
"epoch": 3.1147677915135317,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004039891183975755,
|
|
"loss": 4.7372,
|
|
"mean_token_accuracy": 0.23544188290834428,
|
|
"num_tokens": 68599548.0,
|
|
"step": 37290
|
|
},
|
|
{
|
|
"entropy": 5.473063611984253,
|
|
"epoch": 3.1151854326762445,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004039647250572696,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.2330796867609024,
|
|
"num_tokens": 68609227.0,
|
|
"step": 37295
|
|
},
|
|
{
|
|
"entropy": 5.4837626934051515,
|
|
"epoch": 3.1156030738389577,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004039403294592808,
|
|
"loss": 4.7097,
|
|
"mean_token_accuracy": 0.23798453956842422,
|
|
"num_tokens": 68618378.0,
|
|
"step": 37300
|
|
},
|
|
{
|
|
"entropy": 5.4145369052886965,
|
|
"epoch": 3.1160207150016705,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040391593160403656,
|
|
"loss": 4.5739,
|
|
"mean_token_accuracy": 0.2487722784280777,
|
|
"num_tokens": 68627032.0,
|
|
"step": 37305
|
|
},
|
|
{
|
|
"entropy": 5.467124938964844,
|
|
"epoch": 3.1164383561643834,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040389153149196364,
|
|
"loss": 4.7538,
|
|
"mean_token_accuracy": 0.22816340923309325,
|
|
"num_tokens": 68636398.0,
|
|
"step": 37310
|
|
},
|
|
{
|
|
"entropy": 5.458902645111084,
|
|
"epoch": 3.1168559973270966,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004038671291234893,
|
|
"loss": 4.7217,
|
|
"mean_token_accuracy": 0.2298073559999466,
|
|
"num_tokens": 68645488.0,
|
|
"step": 37315
|
|
},
|
|
{
|
|
"entropy": 5.510628318786621,
|
|
"epoch": 3.1172736384898094,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004038427244990408,
|
|
"loss": 4.7104,
|
|
"mean_token_accuracy": 0.23675377368927003,
|
|
"num_tokens": 68654638.0,
|
|
"step": 37320
|
|
},
|
|
{
|
|
"entropy": 5.434515810012817,
|
|
"epoch": 3.1176912796525227,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004038183176190453,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.22794460207223893,
|
|
"num_tokens": 68664200.0,
|
|
"step": 37325
|
|
},
|
|
{
|
|
"entropy": 5.445707225799561,
|
|
"epoch": 3.1181089208152355,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004037939084839301,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.24023547172546386,
|
|
"num_tokens": 68673822.0,
|
|
"step": 37330
|
|
},
|
|
{
|
|
"entropy": 5.435659170150757,
|
|
"epoch": 3.1185265619779488,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004037694970941225,
|
|
"loss": 4.6704,
|
|
"mean_token_accuracy": 0.23066425174474717,
|
|
"num_tokens": 68682484.0,
|
|
"step": 37335
|
|
},
|
|
{
|
|
"entropy": 5.474404239654541,
|
|
"epoch": 3.1189442031406616,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004037450834500499,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.23181663304567338,
|
|
"num_tokens": 68691645.0,
|
|
"step": 37340
|
|
},
|
|
{
|
|
"entropy": 5.447802400588989,
|
|
"epoch": 3.1193618443033744,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00040372066755213953,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.24405466616153718,
|
|
"num_tokens": 68700433.0,
|
|
"step": 37345
|
|
},
|
|
{
|
|
"entropy": 5.50737943649292,
|
|
"epoch": 3.1197794854660876,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000403696249400819,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.22833795547485353,
|
|
"num_tokens": 68709121.0,
|
|
"step": 37350
|
|
},
|
|
{
|
|
"entropy": 5.4257917404174805,
|
|
"epoch": 3.1201971266288004,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00040367182899651567,
|
|
"loss": 4.6724,
|
|
"mean_token_accuracy": 0.2371869131922722,
|
|
"num_tokens": 68717999.0,
|
|
"step": 37355
|
|
},
|
|
{
|
|
"entropy": 5.4730137348175045,
|
|
"epoch": 3.1206147677915137,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00040364740633965716,
|
|
"loss": 4.6282,
|
|
"mean_token_accuracy": 0.23848477452993394,
|
|
"num_tokens": 68726439.0,
|
|
"step": 37360
|
|
},
|
|
{
|
|
"entropy": 5.433489179611206,
|
|
"epoch": 3.1210324089542265,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040362298143067096,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.2245798170566559,
|
|
"num_tokens": 68736551.0,
|
|
"step": 37365
|
|
},
|
|
{
|
|
"entropy": 5.471882343292236,
|
|
"epoch": 3.1214500501169393,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00040359855426998453,
|
|
"loss": 4.6894,
|
|
"mean_token_accuracy": 0.23200445622205734,
|
|
"num_tokens": 68745626.0,
|
|
"step": 37370
|
|
},
|
|
{
|
|
"entropy": 5.442837524414062,
|
|
"epoch": 3.1218676912796526,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040357412485802574,
|
|
"loss": 4.6236,
|
|
"mean_token_accuracy": 0.24023666828870774,
|
|
"num_tokens": 68754361.0,
|
|
"step": 37375
|
|
},
|
|
{
|
|
"entropy": 5.37610273361206,
|
|
"epoch": 3.1222853324423654,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040354969319522204,
|
|
"loss": 4.6433,
|
|
"mean_token_accuracy": 0.2390460804104805,
|
|
"num_tokens": 68763411.0,
|
|
"step": 37380
|
|
},
|
|
{
|
|
"entropy": 5.432001113891602,
|
|
"epoch": 3.1227029736050786,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040352525928200137,
|
|
"loss": 4.6946,
|
|
"mean_token_accuracy": 0.2414911687374115,
|
|
"num_tokens": 68773135.0,
|
|
"step": 37385
|
|
},
|
|
{
|
|
"entropy": 5.483861351013184,
|
|
"epoch": 3.1231206147677915,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040350082311879117,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.22806112468242645,
|
|
"num_tokens": 68783095.0,
|
|
"step": 37390
|
|
},
|
|
{
|
|
"entropy": 5.502149295806885,
|
|
"epoch": 3.1235382559305047,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004034763847060194,
|
|
"loss": 4.7941,
|
|
"mean_token_accuracy": 0.2261972740292549,
|
|
"num_tokens": 68792000.0,
|
|
"step": 37395
|
|
},
|
|
{
|
|
"entropy": 5.5278314590454105,
|
|
"epoch": 3.1239558970932175,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004034519440441139,
|
|
"loss": 4.7105,
|
|
"mean_token_accuracy": 0.23180729895830154,
|
|
"num_tokens": 68802042.0,
|
|
"step": 37400
|
|
},
|
|
{
|
|
"entropy": 5.529511547088623,
|
|
"epoch": 3.1243735382559303,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004034275011335025,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.24222576320171357,
|
|
"num_tokens": 68811336.0,
|
|
"step": 37405
|
|
},
|
|
{
|
|
"entropy": 5.406962966918945,
|
|
"epoch": 3.1247911794186436,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004034030559746131,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.24103626608848572,
|
|
"num_tokens": 68820661.0,
|
|
"step": 37410
|
|
},
|
|
{
|
|
"entropy": 5.616129064559937,
|
|
"epoch": 3.1252088205813564,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040337860856787375,
|
|
"loss": 4.9517,
|
|
"mean_token_accuracy": 0.2262560099363327,
|
|
"num_tokens": 68830719.0,
|
|
"step": 37415
|
|
},
|
|
{
|
|
"entropy": 5.5725902080535885,
|
|
"epoch": 3.1256264617440697,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004033541589137122,
|
|
"loss": 4.7779,
|
|
"mean_token_accuracy": 0.22607076466083526,
|
|
"num_tokens": 68839902.0,
|
|
"step": 37420
|
|
},
|
|
{
|
|
"entropy": 5.435116481781006,
|
|
"epoch": 3.1260441029067825,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004033297070125566,
|
|
"loss": 4.7094,
|
|
"mean_token_accuracy": 0.2332109346985817,
|
|
"num_tokens": 68850045.0,
|
|
"step": 37425
|
|
},
|
|
{
|
|
"entropy": 5.4501995086669925,
|
|
"epoch": 3.1264617440694953,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004033052528648351,
|
|
"loss": 4.6838,
|
|
"mean_token_accuracy": 0.23512523472309113,
|
|
"num_tokens": 68859346.0,
|
|
"step": 37430
|
|
},
|
|
{
|
|
"entropy": 5.4719523906707765,
|
|
"epoch": 3.1268793852322085,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00040328079647097565,
|
|
"loss": 4.6951,
|
|
"mean_token_accuracy": 0.23070220947265624,
|
|
"num_tokens": 68868365.0,
|
|
"step": 37435
|
|
},
|
|
{
|
|
"entropy": 5.494135427474975,
|
|
"epoch": 3.1272970263949214,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00040325633783140646,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.2323340430855751,
|
|
"num_tokens": 68876664.0,
|
|
"step": 37440
|
|
},
|
|
{
|
|
"entropy": 5.481481409072876,
|
|
"epoch": 3.1277146675576346,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004032318769465556,
|
|
"loss": 4.7238,
|
|
"mean_token_accuracy": 0.23338446170091628,
|
|
"num_tokens": 68886397.0,
|
|
"step": 37445
|
|
},
|
|
{
|
|
"entropy": 5.525004911422729,
|
|
"epoch": 3.1281323087203474,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004032074138168515,
|
|
"loss": 4.8357,
|
|
"mean_token_accuracy": 0.22322712540626527,
|
|
"num_tokens": 68895967.0,
|
|
"step": 37450
|
|
},
|
|
{
|
|
"entropy": 5.445894432067871,
|
|
"epoch": 3.1285499498830607,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004031829484427223,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.22993749380111694,
|
|
"num_tokens": 68905412.0,
|
|
"step": 37455
|
|
},
|
|
{
|
|
"entropy": 5.4834527492523195,
|
|
"epoch": 3.1289675910457735,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004031584808245962,
|
|
"loss": 4.6162,
|
|
"mean_token_accuracy": 0.2426136016845703,
|
|
"num_tokens": 68915469.0,
|
|
"step": 37460
|
|
},
|
|
{
|
|
"entropy": 5.46760926246643,
|
|
"epoch": 3.1293852322084863,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004031340109629017,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.24718316197395324,
|
|
"num_tokens": 68924672.0,
|
|
"step": 37465
|
|
},
|
|
{
|
|
"entropy": 5.432964038848877,
|
|
"epoch": 3.1298028733711996,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040310953885806713,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.23943762630224227,
|
|
"num_tokens": 68934796.0,
|
|
"step": 37470
|
|
},
|
|
{
|
|
"entropy": 5.502732515335083,
|
|
"epoch": 3.1302205145339124,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004030850645105208,
|
|
"loss": 4.785,
|
|
"mean_token_accuracy": 0.22707054018974304,
|
|
"num_tokens": 68944563.0,
|
|
"step": 37475
|
|
},
|
|
{
|
|
"entropy": 5.520724773406982,
|
|
"epoch": 3.1306381556966256,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004030605879206913,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.22737685292959214,
|
|
"num_tokens": 68953655.0,
|
|
"step": 37480
|
|
},
|
|
{
|
|
"entropy": 5.4291376113891605,
|
|
"epoch": 3.1310557968593384,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000403036109089007,
|
|
"loss": 4.6703,
|
|
"mean_token_accuracy": 0.23538817912340165,
|
|
"num_tokens": 68962923.0,
|
|
"step": 37485
|
|
},
|
|
{
|
|
"entropy": 5.37057466506958,
|
|
"epoch": 3.1314734380220512,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00040301162801589655,
|
|
"loss": 4.5938,
|
|
"mean_token_accuracy": 0.2509583309292793,
|
|
"num_tokens": 68971714.0,
|
|
"step": 37490
|
|
},
|
|
{
|
|
"entropy": 5.467027568817139,
|
|
"epoch": 3.1318910791847645,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004029871447017884,
|
|
"loss": 4.7194,
|
|
"mean_token_accuracy": 0.23927459865808487,
|
|
"num_tokens": 68981389.0,
|
|
"step": 37495
|
|
},
|
|
{
|
|
"entropy": 5.484847784042358,
|
|
"epoch": 3.1323087203474773,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004029626591471113,
|
|
"loss": 4.6637,
|
|
"mean_token_accuracy": 0.2308553710579872,
|
|
"num_tokens": 68990853.0,
|
|
"step": 37500
|
|
},
|
|
{
|
|
"entropy": 5.506516981124878,
|
|
"epoch": 3.1327263615101906,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004029381713522938,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.23488430231809615,
|
|
"num_tokens": 69001377.0,
|
|
"step": 37505
|
|
},
|
|
{
|
|
"entropy": 5.504785251617432,
|
|
"epoch": 3.1331440026729034,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040291368131776454,
|
|
"loss": 4.7557,
|
|
"mean_token_accuracy": 0.2300665020942688,
|
|
"num_tokens": 69011428.0,
|
|
"step": 37510
|
|
},
|
|
{
|
|
"entropy": 5.43711748123169,
|
|
"epoch": 3.1335616438356166,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040288918904395245,
|
|
"loss": 4.6513,
|
|
"mean_token_accuracy": 0.24287119805812835,
|
|
"num_tokens": 69020408.0,
|
|
"step": 37515
|
|
},
|
|
{
|
|
"entropy": 5.435584497451782,
|
|
"epoch": 3.1339792849983295,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00040286469453128606,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.24009974747896196,
|
|
"num_tokens": 69029678.0,
|
|
"step": 37520
|
|
},
|
|
{
|
|
"entropy": 5.486698293685913,
|
|
"epoch": 3.1343969261610423,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040284019778019436,
|
|
"loss": 4.6995,
|
|
"mean_token_accuracy": 0.2340577021241188,
|
|
"num_tokens": 69039670.0,
|
|
"step": 37525
|
|
},
|
|
{
|
|
"entropy": 5.477778577804566,
|
|
"epoch": 3.1348145673237555,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00040281569879110603,
|
|
"loss": 4.6998,
|
|
"mean_token_accuracy": 0.23711563497781754,
|
|
"num_tokens": 69048678.0,
|
|
"step": 37530
|
|
},
|
|
{
|
|
"entropy": 5.3603280544281,
|
|
"epoch": 3.1352322084864683,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004027911975644501,
|
|
"loss": 4.6508,
|
|
"mean_token_accuracy": 0.23659069389104842,
|
|
"num_tokens": 69057225.0,
|
|
"step": 37535
|
|
},
|
|
{
|
|
"entropy": 5.471566104888916,
|
|
"epoch": 3.1356498496491816,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040276669410065546,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.23736194670200347,
|
|
"num_tokens": 69066555.0,
|
|
"step": 37540
|
|
},
|
|
{
|
|
"entropy": 5.500835657119751,
|
|
"epoch": 3.1360674908118944,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000402742188400151,
|
|
"loss": 4.6895,
|
|
"mean_token_accuracy": 0.2339949905872345,
|
|
"num_tokens": 69075678.0,
|
|
"step": 37545
|
|
},
|
|
{
|
|
"entropy": 5.539352321624756,
|
|
"epoch": 3.136485131974607,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004027176804633657,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.2274962082505226,
|
|
"num_tokens": 69086026.0,
|
|
"step": 37550
|
|
},
|
|
{
|
|
"entropy": 5.448849678039551,
|
|
"epoch": 3.1369027731373205,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040269317029072876,
|
|
"loss": 4.6763,
|
|
"mean_token_accuracy": 0.23144367784261705,
|
|
"num_tokens": 69095621.0,
|
|
"step": 37555
|
|
},
|
|
{
|
|
"entropy": 5.465845394134521,
|
|
"epoch": 3.1373204143000333,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004026686578826692,
|
|
"loss": 4.671,
|
|
"mean_token_accuracy": 0.24400195479393005,
|
|
"num_tokens": 69104440.0,
|
|
"step": 37560
|
|
},
|
|
{
|
|
"entropy": 5.475568056106567,
|
|
"epoch": 3.1377380554627465,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004026441432396161,
|
|
"loss": 4.7262,
|
|
"mean_token_accuracy": 0.2346420928835869,
|
|
"num_tokens": 69113364.0,
|
|
"step": 37565
|
|
},
|
|
{
|
|
"entropy": 5.492106771469116,
|
|
"epoch": 3.1381556966254593,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040261962636199857,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.2308025225996971,
|
|
"num_tokens": 69122489.0,
|
|
"step": 37570
|
|
},
|
|
{
|
|
"entropy": 5.455265378952026,
|
|
"epoch": 3.1385733377881726,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00040259510725024585,
|
|
"loss": 4.7883,
|
|
"mean_token_accuracy": 0.22538121193647384,
|
|
"num_tokens": 69131403.0,
|
|
"step": 37575
|
|
},
|
|
{
|
|
"entropy": 5.567488145828247,
|
|
"epoch": 3.1389909789508854,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040257058590478724,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.2258647710084915,
|
|
"num_tokens": 69140246.0,
|
|
"step": 37580
|
|
},
|
|
{
|
|
"entropy": 5.442775726318359,
|
|
"epoch": 3.1394086201135982,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004025460623260519,
|
|
"loss": 4.7219,
|
|
"mean_token_accuracy": 0.23331345319747926,
|
|
"num_tokens": 69149939.0,
|
|
"step": 37585
|
|
},
|
|
{
|
|
"entropy": 5.427224588394165,
|
|
"epoch": 3.1398262612763115,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040252153651446933,
|
|
"loss": 4.6879,
|
|
"mean_token_accuracy": 0.2402009531855583,
|
|
"num_tokens": 69159913.0,
|
|
"step": 37590
|
|
},
|
|
{
|
|
"entropy": 5.486446952819824,
|
|
"epoch": 3.1402439024390243,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040249700847046866,
|
|
"loss": 4.6852,
|
|
"mean_token_accuracy": 0.23575425297021865,
|
|
"num_tokens": 69168377.0,
|
|
"step": 37595
|
|
},
|
|
{
|
|
"entropy": 5.497077369689942,
|
|
"epoch": 3.1406615436017375,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004024724781944795,
|
|
"loss": 4.7147,
|
|
"mean_token_accuracy": 0.23952065408229828,
|
|
"num_tokens": 69178133.0,
|
|
"step": 37600
|
|
},
|
|
{
|
|
"entropy": 5.457263946533203,
|
|
"epoch": 3.1410791847644504,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040244794568693106,
|
|
"loss": 4.7014,
|
|
"mean_token_accuracy": 0.23521890193223954,
|
|
"num_tokens": 69187358.0,
|
|
"step": 37605
|
|
},
|
|
{
|
|
"entropy": 5.373110675811768,
|
|
"epoch": 3.141496825927163,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040242341094825297,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.23677429407835007,
|
|
"num_tokens": 69197982.0,
|
|
"step": 37610
|
|
},
|
|
{
|
|
"entropy": 5.490724277496338,
|
|
"epoch": 3.1419144670898764,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00040239887397887467,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.23571473807096482,
|
|
"num_tokens": 69207610.0,
|
|
"step": 37615
|
|
},
|
|
{
|
|
"entropy": 5.433683109283447,
|
|
"epoch": 3.1423321082525892,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040237433477922576,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.23117552995681762,
|
|
"num_tokens": 69216258.0,
|
|
"step": 37620
|
|
},
|
|
{
|
|
"entropy": 5.458542394638061,
|
|
"epoch": 3.1427497494153025,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00040234979334973577,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.23591357767581939,
|
|
"num_tokens": 69225367.0,
|
|
"step": 37625
|
|
},
|
|
{
|
|
"entropy": 5.39434404373169,
|
|
"epoch": 3.1431673905780153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040232524969083434,
|
|
"loss": 4.6599,
|
|
"mean_token_accuracy": 0.24064715802669526,
|
|
"num_tokens": 69235392.0,
|
|
"step": 37630
|
|
},
|
|
{
|
|
"entropy": 5.4211994171142575,
|
|
"epoch": 3.1435850317407286,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004023007038029512,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.22960936427116393,
|
|
"num_tokens": 69244334.0,
|
|
"step": 37635
|
|
},
|
|
{
|
|
"entropy": 5.377403402328492,
|
|
"epoch": 3.1440026729034414,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000402276155686516,
|
|
"loss": 4.611,
|
|
"mean_token_accuracy": 0.24504305571317672,
|
|
"num_tokens": 69254225.0,
|
|
"step": 37640
|
|
},
|
|
{
|
|
"entropy": 5.43694281578064,
|
|
"epoch": 3.144420314066154,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004022516053419585,
|
|
"loss": 4.6232,
|
|
"mean_token_accuracy": 0.23648164570331573,
|
|
"num_tokens": 69262863.0,
|
|
"step": 37645
|
|
},
|
|
{
|
|
"entropy": 5.51648097038269,
|
|
"epoch": 3.1448379552288674,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004022270527697084,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.2340753197669983,
|
|
"num_tokens": 69273484.0,
|
|
"step": 37650
|
|
},
|
|
{
|
|
"entropy": 5.511625719070435,
|
|
"epoch": 3.1452555963915803,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00040220249797019573,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.2254835397005081,
|
|
"num_tokens": 69282358.0,
|
|
"step": 37655
|
|
},
|
|
{
|
|
"entropy": 5.50978274345398,
|
|
"epoch": 3.1456732375542935,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004021779409438501,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.23350476175546647,
|
|
"num_tokens": 69290973.0,
|
|
"step": 37660
|
|
},
|
|
{
|
|
"entropy": 5.472456073760986,
|
|
"epoch": 3.1460908787170063,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004021533816911016,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.23389424681663512,
|
|
"num_tokens": 69300036.0,
|
|
"step": 37665
|
|
},
|
|
{
|
|
"entropy": 5.469760465621948,
|
|
"epoch": 3.1465085198797196,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004021288202123801,
|
|
"loss": 4.724,
|
|
"mean_token_accuracy": 0.23372506648302077,
|
|
"num_tokens": 69309172.0,
|
|
"step": 37670
|
|
},
|
|
{
|
|
"entropy": 5.442247295379639,
|
|
"epoch": 3.1469261610424324,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004021042565081155,
|
|
"loss": 4.6545,
|
|
"mean_token_accuracy": 0.23910460621118546,
|
|
"num_tokens": 69318566.0,
|
|
"step": 37675
|
|
},
|
|
{
|
|
"entropy": 5.510095310211182,
|
|
"epoch": 3.147343802205145,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000402079690578738,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.23958567529916763,
|
|
"num_tokens": 69327917.0,
|
|
"step": 37680
|
|
},
|
|
{
|
|
"entropy": 5.5049598693847654,
|
|
"epoch": 3.1477614433678585,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040205512242467745,
|
|
"loss": 4.7302,
|
|
"mean_token_accuracy": 0.23143730014562608,
|
|
"num_tokens": 69336852.0,
|
|
"step": 37685
|
|
},
|
|
{
|
|
"entropy": 5.447366714477539,
|
|
"epoch": 3.1481790845305713,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004020305520463641,
|
|
"loss": 4.6782,
|
|
"mean_token_accuracy": 0.24315969944000243,
|
|
"num_tokens": 69345757.0,
|
|
"step": 37690
|
|
},
|
|
{
|
|
"entropy": 5.472762680053711,
|
|
"epoch": 3.1485967256932845,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000402005979444228,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.23364314138889314,
|
|
"num_tokens": 69354201.0,
|
|
"step": 37695
|
|
},
|
|
{
|
|
"entropy": 5.448192739486695,
|
|
"epoch": 3.1490143668559973,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004019814046186994,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.23768824338912964,
|
|
"num_tokens": 69363310.0,
|
|
"step": 37700
|
|
},
|
|
{
|
|
"entropy": 5.439552307128906,
|
|
"epoch": 3.14943200801871,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040195682757020846,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.23802968710660935,
|
|
"num_tokens": 69372629.0,
|
|
"step": 37705
|
|
},
|
|
{
|
|
"entropy": 5.460493707656861,
|
|
"epoch": 3.1498496491814234,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00040193224829918544,
|
|
"loss": 4.6643,
|
|
"mean_token_accuracy": 0.23691581189632416,
|
|
"num_tokens": 69381715.0,
|
|
"step": 37710
|
|
},
|
|
{
|
|
"entropy": 5.489569807052613,
|
|
"epoch": 3.150267290344136,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004019076668060606,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.2369035542011261,
|
|
"num_tokens": 69391063.0,
|
|
"step": 37715
|
|
},
|
|
{
|
|
"entropy": 5.477966165542602,
|
|
"epoch": 3.1506849315068495,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040188308309126424,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.24039193838834763,
|
|
"num_tokens": 69400146.0,
|
|
"step": 37720
|
|
},
|
|
{
|
|
"entropy": 5.486830997467041,
|
|
"epoch": 3.1511025726695623,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040185849715522687,
|
|
"loss": 4.7616,
|
|
"mean_token_accuracy": 0.2372738763689995,
|
|
"num_tokens": 69409430.0,
|
|
"step": 37725
|
|
},
|
|
{
|
|
"entropy": 5.501427364349365,
|
|
"epoch": 3.151520213832275,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004018339089983787,
|
|
"loss": 4.7479,
|
|
"mean_token_accuracy": 0.22653851211071013,
|
|
"num_tokens": 69418653.0,
|
|
"step": 37730
|
|
},
|
|
{
|
|
"entropy": 5.487090730667115,
|
|
"epoch": 3.1519378549949884,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040180931862115045,
|
|
"loss": 4.7245,
|
|
"mean_token_accuracy": 0.2324138328433037,
|
|
"num_tokens": 69427985.0,
|
|
"step": 37735
|
|
},
|
|
{
|
|
"entropy": 5.525233125686645,
|
|
"epoch": 3.152355496157701,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004017847260239723,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.23075856417417526,
|
|
"num_tokens": 69437694.0,
|
|
"step": 37740
|
|
},
|
|
{
|
|
"entropy": 5.498272371292114,
|
|
"epoch": 3.1527731373204144,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000401760131207275,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.22947024405002595,
|
|
"num_tokens": 69446523.0,
|
|
"step": 37745
|
|
},
|
|
{
|
|
"entropy": 5.487917137145996,
|
|
"epoch": 3.1531907784831272,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040173553417148896,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.23710785508155824,
|
|
"num_tokens": 69455664.0,
|
|
"step": 37750
|
|
},
|
|
{
|
|
"entropy": 5.3747481346130375,
|
|
"epoch": 3.1536084196458405,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004017109349170449,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.23954104632139206,
|
|
"num_tokens": 69465106.0,
|
|
"step": 37755
|
|
},
|
|
{
|
|
"entropy": 5.522165250778198,
|
|
"epoch": 3.1540260608085533,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040168633344437335,
|
|
"loss": 4.7045,
|
|
"mean_token_accuracy": 0.2258928745985031,
|
|
"num_tokens": 69473490.0,
|
|
"step": 37760
|
|
},
|
|
{
|
|
"entropy": 5.4973736763000485,
|
|
"epoch": 3.154443701971266,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004016617297539051,
|
|
"loss": 4.659,
|
|
"mean_token_accuracy": 0.2378014713525772,
|
|
"num_tokens": 69482749.0,
|
|
"step": 37765
|
|
},
|
|
{
|
|
"entropy": 5.450582981109619,
|
|
"epoch": 3.1548613431339794,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004016371238460707,
|
|
"loss": 4.6599,
|
|
"mean_token_accuracy": 0.23535437136888504,
|
|
"num_tokens": 69491076.0,
|
|
"step": 37770
|
|
},
|
|
{
|
|
"entropy": 5.48805456161499,
|
|
"epoch": 3.155278984296692,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040161251572130104,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.22750569581985475,
|
|
"num_tokens": 69500381.0,
|
|
"step": 37775
|
|
},
|
|
{
|
|
"entropy": 5.4475549221038815,
|
|
"epoch": 3.1556966254594054,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000401587905380027,
|
|
"loss": 4.6466,
|
|
"mean_token_accuracy": 0.24583836495876313,
|
|
"num_tokens": 69508469.0,
|
|
"step": 37780
|
|
},
|
|
{
|
|
"entropy": 5.5431407451629635,
|
|
"epoch": 3.1561142666221182,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00040156329282267915,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.22035261541604995,
|
|
"num_tokens": 69517359.0,
|
|
"step": 37785
|
|
},
|
|
{
|
|
"entropy": 5.44900803565979,
|
|
"epoch": 3.1565319077848315,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004015386780496886,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.24135020822286607,
|
|
"num_tokens": 69525784.0,
|
|
"step": 37790
|
|
},
|
|
{
|
|
"entropy": 5.4559831619262695,
|
|
"epoch": 3.1569495489475443,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004015140610614861,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.23226553648710252,
|
|
"num_tokens": 69534299.0,
|
|
"step": 37795
|
|
},
|
|
{
|
|
"entropy": 5.485021781921387,
|
|
"epoch": 3.157367190110257,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040148944185850285,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.2403562605381012,
|
|
"num_tokens": 69544561.0,
|
|
"step": 37800
|
|
},
|
|
{
|
|
"entropy": 5.461746740341186,
|
|
"epoch": 3.1577848312729704,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004014648204411695,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.23865733444690704,
|
|
"num_tokens": 69554271.0,
|
|
"step": 37805
|
|
},
|
|
{
|
|
"entropy": 5.422003221511841,
|
|
"epoch": 3.158202472435683,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004014401968099174,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.2337615132331848,
|
|
"num_tokens": 69563203.0,
|
|
"step": 37810
|
|
},
|
|
{
|
|
"entropy": 5.40008807182312,
|
|
"epoch": 3.1586201135983965,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004014155709651773,
|
|
"loss": 4.6878,
|
|
"mean_token_accuracy": 0.23470161557197572,
|
|
"num_tokens": 69571983.0,
|
|
"step": 37815
|
|
},
|
|
{
|
|
"entropy": 5.419113731384277,
|
|
"epoch": 3.1590377547611093,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004013909429073805,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.23085619360208512,
|
|
"num_tokens": 69582752.0,
|
|
"step": 37820
|
|
},
|
|
{
|
|
"entropy": 5.503307867050171,
|
|
"epoch": 3.159455395923822,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040136631263695816,
|
|
"loss": 4.6848,
|
|
"mean_token_accuracy": 0.23801662921905517,
|
|
"num_tokens": 69591271.0,
|
|
"step": 37825
|
|
},
|
|
{
|
|
"entropy": 5.46291766166687,
|
|
"epoch": 3.1598730370865353,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00040134168015434137,
|
|
"loss": 4.6544,
|
|
"mean_token_accuracy": 0.2343415215611458,
|
|
"num_tokens": 69600226.0,
|
|
"step": 37830
|
|
},
|
|
{
|
|
"entropy": 5.475314092636109,
|
|
"epoch": 3.160290678249248,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004013170454599614,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.2429775133728981,
|
|
"num_tokens": 69610112.0,
|
|
"step": 37835
|
|
},
|
|
{
|
|
"entropy": 5.5066437244415285,
|
|
"epoch": 3.1607083194119614,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004012924085542495,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.2248418927192688,
|
|
"num_tokens": 69618923.0,
|
|
"step": 37840
|
|
},
|
|
{
|
|
"entropy": 5.490180969238281,
|
|
"epoch": 3.161125960574674,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000401267769437637,
|
|
"loss": 4.7983,
|
|
"mean_token_accuracy": 0.2271543949842453,
|
|
"num_tokens": 69627985.0,
|
|
"step": 37845
|
|
},
|
|
{
|
|
"entropy": 5.411696720123291,
|
|
"epoch": 3.161543601737387,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040124312811055517,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.2349904865026474,
|
|
"num_tokens": 69637912.0,
|
|
"step": 37850
|
|
},
|
|
{
|
|
"entropy": 5.529902172088623,
|
|
"epoch": 3.1619612429001003,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004012184845734354,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.23552651554346085,
|
|
"num_tokens": 69647125.0,
|
|
"step": 37855
|
|
},
|
|
{
|
|
"entropy": 5.433447456359863,
|
|
"epoch": 3.162378884062813,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004011938388267092,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.23927512615919114,
|
|
"num_tokens": 69656580.0,
|
|
"step": 37860
|
|
},
|
|
{
|
|
"entropy": 5.479660415649414,
|
|
"epoch": 3.1627965252255263,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040116919087080787,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.22904921770095826,
|
|
"num_tokens": 69665869.0,
|
|
"step": 37865
|
|
},
|
|
{
|
|
"entropy": 5.426419401168824,
|
|
"epoch": 3.163214166388239,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00040114454070616304,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.23517018407583237,
|
|
"num_tokens": 69674962.0,
|
|
"step": 37870
|
|
},
|
|
{
|
|
"entropy": 5.407793951034546,
|
|
"epoch": 3.1636318075509524,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00040111988833320617,
|
|
"loss": 4.6046,
|
|
"mean_token_accuracy": 0.23950959295034407,
|
|
"num_tokens": 69684433.0,
|
|
"step": 37875
|
|
},
|
|
{
|
|
"entropy": 5.365702199935913,
|
|
"epoch": 3.1640494487136652,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004010952337523689,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.24389121681451797,
|
|
"num_tokens": 69693232.0,
|
|
"step": 37880
|
|
},
|
|
{
|
|
"entropy": 5.397351217269898,
|
|
"epoch": 3.164467089876378,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004010705769640827,
|
|
"loss": 4.7397,
|
|
"mean_token_accuracy": 0.23718980103731155,
|
|
"num_tokens": 69702420.0,
|
|
"step": 37885
|
|
},
|
|
{
|
|
"entropy": 5.488798570632935,
|
|
"epoch": 3.1648847310390913,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004010459179687793,
|
|
"loss": 4.6245,
|
|
"mean_token_accuracy": 0.2432667449116707,
|
|
"num_tokens": 69711096.0,
|
|
"step": 37890
|
|
},
|
|
{
|
|
"entropy": 5.460167026519775,
|
|
"epoch": 3.165302372201804,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004010212567668904,
|
|
"loss": 4.7083,
|
|
"mean_token_accuracy": 0.23166225254535674,
|
|
"num_tokens": 69721190.0,
|
|
"step": 37895
|
|
},
|
|
{
|
|
"entropy": 5.451013612747192,
|
|
"epoch": 3.1657200133645174,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040099659335884777,
|
|
"loss": 4.6931,
|
|
"mean_token_accuracy": 0.23314426690340043,
|
|
"num_tokens": 69730634.0,
|
|
"step": 37900
|
|
},
|
|
{
|
|
"entropy": 5.499860429763794,
|
|
"epoch": 3.16613765452723,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00040097192774508303,
|
|
"loss": 4.6862,
|
|
"mean_token_accuracy": 0.22569452375173568,
|
|
"num_tokens": 69739872.0,
|
|
"step": 37905
|
|
},
|
|
{
|
|
"entropy": 5.40257682800293,
|
|
"epoch": 3.1665552956899434,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004009472599260281,
|
|
"loss": 4.6214,
|
|
"mean_token_accuracy": 0.2394283264875412,
|
|
"num_tokens": 69748458.0,
|
|
"step": 37910
|
|
},
|
|
{
|
|
"entropy": 5.505212450027466,
|
|
"epoch": 3.1669729368526562,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004009225899021148,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.23155072331428528,
|
|
"num_tokens": 69757926.0,
|
|
"step": 37915
|
|
},
|
|
{
|
|
"entropy": 5.465575122833252,
|
|
"epoch": 3.167390578015369,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040089791767377496,
|
|
"loss": 4.6894,
|
|
"mean_token_accuracy": 0.22794608771800995,
|
|
"num_tokens": 69767754.0,
|
|
"step": 37920
|
|
},
|
|
{
|
|
"entropy": 5.480258274078369,
|
|
"epoch": 3.1678082191780823,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004008732432414405,
|
|
"loss": 4.7686,
|
|
"mean_token_accuracy": 0.23438155204057692,
|
|
"num_tokens": 69776900.0,
|
|
"step": 37925
|
|
},
|
|
{
|
|
"entropy": 5.398794412612915,
|
|
"epoch": 3.168225860340795,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040084856660554355,
|
|
"loss": 4.7025,
|
|
"mean_token_accuracy": 0.23384130001068115,
|
|
"num_tokens": 69786779.0,
|
|
"step": 37930
|
|
},
|
|
{
|
|
"entropy": 5.459599399566651,
|
|
"epoch": 3.1686435015035084,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040082388776651576,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.24230144470930098,
|
|
"num_tokens": 69796061.0,
|
|
"step": 37935
|
|
},
|
|
{
|
|
"entropy": 5.545666217803955,
|
|
"epoch": 3.169061142666221,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004007992067247895,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.22513525038957596,
|
|
"num_tokens": 69805820.0,
|
|
"step": 37940
|
|
},
|
|
{
|
|
"entropy": 5.4692628383636475,
|
|
"epoch": 3.169478783828934,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040077452348079664,
|
|
"loss": 4.6546,
|
|
"mean_token_accuracy": 0.2335287243127823,
|
|
"num_tokens": 69815166.0,
|
|
"step": 37945
|
|
},
|
|
{
|
|
"entropy": 5.466988611221313,
|
|
"epoch": 3.1698964249916473,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040074983803496927,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.22480077147483826,
|
|
"num_tokens": 69825260.0,
|
|
"step": 37950
|
|
},
|
|
{
|
|
"entropy": 5.530781555175781,
|
|
"epoch": 3.17031406615436,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040072515038773975,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.23682195395231248,
|
|
"num_tokens": 69834392.0,
|
|
"step": 37955
|
|
},
|
|
{
|
|
"entropy": 5.409859228134155,
|
|
"epoch": 3.1707317073170733,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040070046053954013,
|
|
"loss": 4.6589,
|
|
"mean_token_accuracy": 0.2377639517188072,
|
|
"num_tokens": 69843411.0,
|
|
"step": 37960
|
|
},
|
|
{
|
|
"entropy": 5.444904708862305,
|
|
"epoch": 3.171149348479786,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040067576849080254,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.23834120482206345,
|
|
"num_tokens": 69853484.0,
|
|
"step": 37965
|
|
},
|
|
{
|
|
"entropy": 5.484105443954467,
|
|
"epoch": 3.171566989642499,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00040065107424195945,
|
|
"loss": 4.628,
|
|
"mean_token_accuracy": 0.24375149607658386,
|
|
"num_tokens": 69862407.0,
|
|
"step": 37970
|
|
},
|
|
{
|
|
"entropy": 5.470456075668335,
|
|
"epoch": 3.171984630805212,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004006263777934431,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.2252430722117424,
|
|
"num_tokens": 69872608.0,
|
|
"step": 37975
|
|
},
|
|
{
|
|
"entropy": 5.418390560150146,
|
|
"epoch": 3.172402271967925,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004006016791456857,
|
|
"loss": 4.6945,
|
|
"mean_token_accuracy": 0.2309161201119423,
|
|
"num_tokens": 69882318.0,
|
|
"step": 37980
|
|
},
|
|
{
|
|
"entropy": 5.504142427444458,
|
|
"epoch": 3.1728199131306383,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040057697829911975,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.23975399881601334,
|
|
"num_tokens": 69891560.0,
|
|
"step": 37985
|
|
},
|
|
{
|
|
"entropy": 5.4037100315094,
|
|
"epoch": 3.173237554293351,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040055227525417767,
|
|
"loss": 4.6739,
|
|
"mean_token_accuracy": 0.24117313623428344,
|
|
"num_tokens": 69900538.0,
|
|
"step": 37990
|
|
},
|
|
{
|
|
"entropy": 5.4365945816040036,
|
|
"epoch": 3.1736551954560643,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004005275700112918,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.2344943568110466,
|
|
"num_tokens": 69909286.0,
|
|
"step": 37995
|
|
},
|
|
{
|
|
"entropy": 5.532680225372315,
|
|
"epoch": 3.174072836618777,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00040050286257089476,
|
|
"loss": 4.7836,
|
|
"mean_token_accuracy": 0.238289412856102,
|
|
"num_tokens": 69919054.0,
|
|
"step": 38000
|
|
},
|
|
{
|
|
"entropy": 5.511553478240967,
|
|
"epoch": 3.17449047778149,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00040047815293341903,
|
|
"loss": 4.8152,
|
|
"mean_token_accuracy": 0.23297070115804672,
|
|
"num_tokens": 69928526.0,
|
|
"step": 38005
|
|
},
|
|
{
|
|
"entropy": 5.496292638778686,
|
|
"epoch": 3.174908118944203,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004004534410992972,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.2306314915418625,
|
|
"num_tokens": 69938309.0,
|
|
"step": 38010
|
|
},
|
|
{
|
|
"entropy": 5.422701454162597,
|
|
"epoch": 3.175325760106916,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004004287270689618,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.23290462046861649,
|
|
"num_tokens": 69947726.0,
|
|
"step": 38015
|
|
},
|
|
{
|
|
"entropy": 5.396736669540405,
|
|
"epoch": 3.1757434012696293,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004004040108428457,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.23347420543432235,
|
|
"num_tokens": 69957562.0,
|
|
"step": 38020
|
|
},
|
|
{
|
|
"entropy": 5.56213345527649,
|
|
"epoch": 3.176161042432342,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004003792924213814,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.22591380625963212,
|
|
"num_tokens": 69967048.0,
|
|
"step": 38025
|
|
},
|
|
{
|
|
"entropy": 5.4772217750549315,
|
|
"epoch": 3.1765786835950554,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040035457180500163,
|
|
"loss": 4.7264,
|
|
"mean_token_accuracy": 0.22945616096258165,
|
|
"num_tokens": 69977053.0,
|
|
"step": 38030
|
|
},
|
|
{
|
|
"entropy": 5.486361885070801,
|
|
"epoch": 3.176996324757768,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004003298489941392,
|
|
"loss": 4.7555,
|
|
"mean_token_accuracy": 0.2277388319373131,
|
|
"num_tokens": 69986321.0,
|
|
"step": 38035
|
|
},
|
|
{
|
|
"entropy": 5.422566509246826,
|
|
"epoch": 3.177413965920481,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000400305123989227,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.23234157711267472,
|
|
"num_tokens": 69995644.0,
|
|
"step": 38040
|
|
},
|
|
{
|
|
"entropy": 5.490791320800781,
|
|
"epoch": 3.1778316070831942,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004002803967906976,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.23402324169874192,
|
|
"num_tokens": 70005186.0,
|
|
"step": 38045
|
|
},
|
|
{
|
|
"entropy": 5.4370420455932615,
|
|
"epoch": 3.178249248245907,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00040025566739898414,
|
|
"loss": 4.6445,
|
|
"mean_token_accuracy": 0.23365612477064132,
|
|
"num_tokens": 70014801.0,
|
|
"step": 38050
|
|
},
|
|
{
|
|
"entropy": 5.483906078338623,
|
|
"epoch": 3.1786668894086203,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00040023093581451947,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.23792748600244523,
|
|
"num_tokens": 70023760.0,
|
|
"step": 38055
|
|
},
|
|
{
|
|
"entropy": 5.502353811264038,
|
|
"epoch": 3.179084530571333,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00040020620203773643,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.2446754530072212,
|
|
"num_tokens": 70033743.0,
|
|
"step": 38060
|
|
},
|
|
{
|
|
"entropy": 5.567101764678955,
|
|
"epoch": 3.179502171734046,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040018146606906826,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.22055084705352784,
|
|
"num_tokens": 70042676.0,
|
|
"step": 38065
|
|
},
|
|
{
|
|
"entropy": 5.3893208503723145,
|
|
"epoch": 3.179919812896759,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004001567279089477,
|
|
"loss": 4.5509,
|
|
"mean_token_accuracy": 0.2495074599981308,
|
|
"num_tokens": 70051203.0,
|
|
"step": 38070
|
|
},
|
|
{
|
|
"entropy": 5.358687686920166,
|
|
"epoch": 3.180337454059472,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004001319875578081,
|
|
"loss": 4.6723,
|
|
"mean_token_accuracy": 0.23496306836605071,
|
|
"num_tokens": 70060583.0,
|
|
"step": 38075
|
|
},
|
|
{
|
|
"entropy": 5.424169969558716,
|
|
"epoch": 3.1807550952221852,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040010724501608237,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.241008922457695,
|
|
"num_tokens": 70070011.0,
|
|
"step": 38080
|
|
},
|
|
{
|
|
"entropy": 5.583847856521606,
|
|
"epoch": 3.181172736384898,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004000825002842038,
|
|
"loss": 4.8081,
|
|
"mean_token_accuracy": 0.22831428050994873,
|
|
"num_tokens": 70078916.0,
|
|
"step": 38085
|
|
},
|
|
{
|
|
"entropy": 5.550172758102417,
|
|
"epoch": 3.181590377547611,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00040005775336260537,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.22990727573633193,
|
|
"num_tokens": 70088611.0,
|
|
"step": 38090
|
|
},
|
|
{
|
|
"entropy": 5.436361598968506,
|
|
"epoch": 3.182008018710324,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004000330042517205,
|
|
"loss": 4.6855,
|
|
"mean_token_accuracy": 0.236760613322258,
|
|
"num_tokens": 70098090.0,
|
|
"step": 38095
|
|
},
|
|
{
|
|
"entropy": 5.524849462509155,
|
|
"epoch": 3.182425659873037,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004000082529519824,
|
|
"loss": 4.7819,
|
|
"mean_token_accuracy": 0.22972965240478516,
|
|
"num_tokens": 70107171.0,
|
|
"step": 38100
|
|
},
|
|
{
|
|
"entropy": 5.461524868011475,
|
|
"epoch": 3.18284330103575,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003999834994638243,
|
|
"loss": 4.6372,
|
|
"mean_token_accuracy": 0.24540886282920837,
|
|
"num_tokens": 70117359.0,
|
|
"step": 38105
|
|
},
|
|
{
|
|
"entropy": 5.535926008224488,
|
|
"epoch": 3.183260942198463,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039995874378767973,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.2214693084359169,
|
|
"num_tokens": 70127459.0,
|
|
"step": 38110
|
|
},
|
|
{
|
|
"entropy": 5.499474906921387,
|
|
"epoch": 3.1836785833611763,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039993398592398177,
|
|
"loss": 4.7289,
|
|
"mean_token_accuracy": 0.2293596714735031,
|
|
"num_tokens": 70136472.0,
|
|
"step": 38115
|
|
},
|
|
{
|
|
"entropy": 5.419035959243774,
|
|
"epoch": 3.184096224523889,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039990922587316414,
|
|
"loss": 4.6319,
|
|
"mean_token_accuracy": 0.23820656836032866,
|
|
"num_tokens": 70145296.0,
|
|
"step": 38120
|
|
},
|
|
{
|
|
"entropy": 5.454057264328003,
|
|
"epoch": 3.184513865686602,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039988446363566006,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.22795438319444655,
|
|
"num_tokens": 70154526.0,
|
|
"step": 38125
|
|
},
|
|
{
|
|
"entropy": 5.421109676361084,
|
|
"epoch": 3.184931506849315,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039985969921190324,
|
|
"loss": 4.5935,
|
|
"mean_token_accuracy": 0.2429218992590904,
|
|
"num_tokens": 70163901.0,
|
|
"step": 38130
|
|
},
|
|
{
|
|
"entropy": 5.456495332717895,
|
|
"epoch": 3.185349148012028,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039983493260232697,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.232017320394516,
|
|
"num_tokens": 70172820.0,
|
|
"step": 38135
|
|
},
|
|
{
|
|
"entropy": 5.4220499992370605,
|
|
"epoch": 3.185766789174741,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039981016380736503,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.23265514969825746,
|
|
"num_tokens": 70182083.0,
|
|
"step": 38140
|
|
},
|
|
{
|
|
"entropy": 5.440039110183716,
|
|
"epoch": 3.186184430337454,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003997853928274508,
|
|
"loss": 4.6406,
|
|
"mean_token_accuracy": 0.2318596988916397,
|
|
"num_tokens": 70191689.0,
|
|
"step": 38145
|
|
},
|
|
{
|
|
"entropy": 5.435216188430786,
|
|
"epoch": 3.1866020715001673,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039976061966301825,
|
|
"loss": 4.642,
|
|
"mean_token_accuracy": 0.23574358224868774,
|
|
"num_tokens": 70200555.0,
|
|
"step": 38150
|
|
},
|
|
{
|
|
"entropy": 5.406014823913575,
|
|
"epoch": 3.18701971266288,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003997358443145007,
|
|
"loss": 4.6899,
|
|
"mean_token_accuracy": 0.23627469837665557,
|
|
"num_tokens": 70209835.0,
|
|
"step": 38155
|
|
},
|
|
{
|
|
"entropy": 5.450238370895386,
|
|
"epoch": 3.187437353825593,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039971106678233224,
|
|
"loss": 4.6977,
|
|
"mean_token_accuracy": 0.23303807973861695,
|
|
"num_tokens": 70219352.0,
|
|
"step": 38160
|
|
},
|
|
{
|
|
"entropy": 5.356292200088501,
|
|
"epoch": 3.187854994988306,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00039968628706694634,
|
|
"loss": 4.6319,
|
|
"mean_token_accuracy": 0.2390556037425995,
|
|
"num_tokens": 70227827.0,
|
|
"step": 38165
|
|
},
|
|
{
|
|
"entropy": 5.434841680526733,
|
|
"epoch": 3.188272636151019,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00039966150516877687,
|
|
"loss": 4.7369,
|
|
"mean_token_accuracy": 0.23043746650218963,
|
|
"num_tokens": 70236932.0,
|
|
"step": 38170
|
|
},
|
|
{
|
|
"entropy": 5.436231470108032,
|
|
"epoch": 3.1886902773137322,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039963672108825777,
|
|
"loss": 4.657,
|
|
"mean_token_accuracy": 0.23512180298566818,
|
|
"num_tokens": 70245603.0,
|
|
"step": 38175
|
|
},
|
|
{
|
|
"entropy": 5.524595165252686,
|
|
"epoch": 3.189107918476445,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00039961193482582273,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.2286943569779396,
|
|
"num_tokens": 70253999.0,
|
|
"step": 38180
|
|
},
|
|
{
|
|
"entropy": 5.570957517623901,
|
|
"epoch": 3.189525559639158,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003995871463819059,
|
|
"loss": 4.798,
|
|
"mean_token_accuracy": 0.23164825290441513,
|
|
"num_tokens": 70263236.0,
|
|
"step": 38185
|
|
},
|
|
{
|
|
"entropy": 5.420429229736328,
|
|
"epoch": 3.189943200801871,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039956235575694106,
|
|
"loss": 4.6528,
|
|
"mean_token_accuracy": 0.24073877185583115,
|
|
"num_tokens": 70271722.0,
|
|
"step": 38190
|
|
},
|
|
{
|
|
"entropy": 5.393537187576294,
|
|
"epoch": 3.190360841964584,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003995375629513622,
|
|
"loss": 4.6429,
|
|
"mean_token_accuracy": 0.2465140551328659,
|
|
"num_tokens": 70280604.0,
|
|
"step": 38195
|
|
},
|
|
{
|
|
"entropy": 5.452754163742066,
|
|
"epoch": 3.190778483127297,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039951276796560347,
|
|
"loss": 4.6759,
|
|
"mean_token_accuracy": 0.2356075957417488,
|
|
"num_tokens": 70289367.0,
|
|
"step": 38200
|
|
},
|
|
{
|
|
"entropy": 5.46518988609314,
|
|
"epoch": 3.19119612429001,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003994879708000988,
|
|
"loss": 4.7004,
|
|
"mean_token_accuracy": 0.23334852755069732,
|
|
"num_tokens": 70298931.0,
|
|
"step": 38205
|
|
},
|
|
{
|
|
"entropy": 5.532020950317383,
|
|
"epoch": 3.191613765452723,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039946317145528245,
|
|
"loss": 4.7629,
|
|
"mean_token_accuracy": 0.2257665529847145,
|
|
"num_tokens": 70308055.0,
|
|
"step": 38210
|
|
},
|
|
{
|
|
"entropy": 5.448033714294434,
|
|
"epoch": 3.192031406615436,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039943836993158835,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.22728168964385986,
|
|
"num_tokens": 70318394.0,
|
|
"step": 38215
|
|
},
|
|
{
|
|
"entropy": 5.491350603103638,
|
|
"epoch": 3.192449047778149,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039941356622945085,
|
|
"loss": 4.7681,
|
|
"mean_token_accuracy": 0.2323670506477356,
|
|
"num_tokens": 70328247.0,
|
|
"step": 38220
|
|
},
|
|
{
|
|
"entropy": 5.558112144470215,
|
|
"epoch": 3.192866688940862,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003993887603493041,
|
|
"loss": 4.7814,
|
|
"mean_token_accuracy": 0.22796964049339294,
|
|
"num_tokens": 70336920.0,
|
|
"step": 38225
|
|
},
|
|
{
|
|
"entropy": 5.575571012496948,
|
|
"epoch": 3.193284330103575,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003993639522915824,
|
|
"loss": 4.7816,
|
|
"mean_token_accuracy": 0.2293030172586441,
|
|
"num_tokens": 70346547.0,
|
|
"step": 38230
|
|
},
|
|
{
|
|
"entropy": 5.5118492603302,
|
|
"epoch": 3.193701971266288,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00039933914205672003,
|
|
"loss": 4.7493,
|
|
"mean_token_accuracy": 0.2287028357386589,
|
|
"num_tokens": 70356390.0,
|
|
"step": 38235
|
|
},
|
|
{
|
|
"entropy": 5.518762826919556,
|
|
"epoch": 3.194119612429001,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003993143296451513,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.2278637781739235,
|
|
"num_tokens": 70366251.0,
|
|
"step": 38240
|
|
},
|
|
{
|
|
"entropy": 5.49468584060669,
|
|
"epoch": 3.194537253591714,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003992895150573105,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.24381839781999587,
|
|
"num_tokens": 70375713.0,
|
|
"step": 38245
|
|
},
|
|
{
|
|
"entropy": 5.474677181243896,
|
|
"epoch": 3.194954894754427,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039926469829363226,
|
|
"loss": 4.6769,
|
|
"mean_token_accuracy": 0.24250668436288833,
|
|
"num_tokens": 70385361.0,
|
|
"step": 38250
|
|
},
|
|
{
|
|
"entropy": 5.4135369777679445,
|
|
"epoch": 3.19537253591714,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00039923987935455084,
|
|
"loss": 4.6709,
|
|
"mean_token_accuracy": 0.23584434241056443,
|
|
"num_tokens": 70394707.0,
|
|
"step": 38255
|
|
},
|
|
{
|
|
"entropy": 5.4812358856201175,
|
|
"epoch": 3.195790177079853,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003992150582405009,
|
|
"loss": 4.6174,
|
|
"mean_token_accuracy": 0.24714207500219346,
|
|
"num_tokens": 70402741.0,
|
|
"step": 38260
|
|
},
|
|
{
|
|
"entropy": 5.467409086227417,
|
|
"epoch": 3.196207818242566,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039919023495191665,
|
|
"loss": 4.7077,
|
|
"mean_token_accuracy": 0.23563567996025087,
|
|
"num_tokens": 70412484.0,
|
|
"step": 38265
|
|
},
|
|
{
|
|
"entropy": 5.426644229888916,
|
|
"epoch": 3.196625459405279,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039916540948923293,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.24317322671413422,
|
|
"num_tokens": 70420818.0,
|
|
"step": 38270
|
|
},
|
|
{
|
|
"entropy": 5.425460720062256,
|
|
"epoch": 3.197043100567992,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003991405818528843,
|
|
"loss": 4.631,
|
|
"mean_token_accuracy": 0.24227819889783858,
|
|
"num_tokens": 70430759.0,
|
|
"step": 38275
|
|
},
|
|
{
|
|
"entropy": 5.4804009914398195,
|
|
"epoch": 3.197460741730705,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003991157520433053,
|
|
"loss": 4.6989,
|
|
"mean_token_accuracy": 0.2343025103211403,
|
|
"num_tokens": 70440199.0,
|
|
"step": 38280
|
|
},
|
|
{
|
|
"entropy": 5.575021457672119,
|
|
"epoch": 3.197878382893418,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039909092006093066,
|
|
"loss": 4.8997,
|
|
"mean_token_accuracy": 0.2154970109462738,
|
|
"num_tokens": 70450613.0,
|
|
"step": 38285
|
|
},
|
|
{
|
|
"entropy": 5.459196519851685,
|
|
"epoch": 3.198296024056131,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039906608590619514,
|
|
"loss": 4.645,
|
|
"mean_token_accuracy": 0.23213090002536774,
|
|
"num_tokens": 70460343.0,
|
|
"step": 38290
|
|
},
|
|
{
|
|
"entropy": 5.537581729888916,
|
|
"epoch": 3.198713665218844,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003990412495795334,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.23414257317781448,
|
|
"num_tokens": 70469483.0,
|
|
"step": 38295
|
|
},
|
|
{
|
|
"entropy": 5.47898497581482,
|
|
"epoch": 3.199131306381557,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003990164110813804,
|
|
"loss": 4.6926,
|
|
"mean_token_accuracy": 0.23009484261274338,
|
|
"num_tokens": 70478699.0,
|
|
"step": 38300
|
|
},
|
|
{
|
|
"entropy": 5.476954460144043,
|
|
"epoch": 3.1995489475442698,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003989915704121707,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.23898244202136992,
|
|
"num_tokens": 70487862.0,
|
|
"step": 38305
|
|
},
|
|
{
|
|
"entropy": 5.453524541854859,
|
|
"epoch": 3.199966588706983,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039896672757233935,
|
|
"loss": 4.6737,
|
|
"mean_token_accuracy": 0.2426017105579376,
|
|
"num_tokens": 70496345.0,
|
|
"step": 38310
|
|
},
|
|
{
|
|
"entropy": 5.44212532043457,
|
|
"epoch": 3.200384229869696,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003989418825623212,
|
|
"loss": 4.6873,
|
|
"mean_token_accuracy": 0.2376277595758438,
|
|
"num_tokens": 70504805.0,
|
|
"step": 38315
|
|
},
|
|
{
|
|
"entropy": 5.3929675102233885,
|
|
"epoch": 3.200801871032409,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003989170353825513,
|
|
"loss": 4.6257,
|
|
"mean_token_accuracy": 0.23637326806783676,
|
|
"num_tokens": 70514287.0,
|
|
"step": 38320
|
|
},
|
|
{
|
|
"entropy": 5.43485279083252,
|
|
"epoch": 3.201219512195122,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00039889218603346443,
|
|
"loss": 4.63,
|
|
"mean_token_accuracy": 0.23973023593425752,
|
|
"num_tokens": 70523311.0,
|
|
"step": 38325
|
|
},
|
|
{
|
|
"entropy": 5.391543865203857,
|
|
"epoch": 3.2016371533578347,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00039886733451549583,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.2452346622943878,
|
|
"num_tokens": 70532156.0,
|
|
"step": 38330
|
|
},
|
|
{
|
|
"entropy": 5.51947250366211,
|
|
"epoch": 3.202054794520548,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00039884248082908033,
|
|
"loss": 4.8113,
|
|
"mean_token_accuracy": 0.22942224144935608,
|
|
"num_tokens": 70540785.0,
|
|
"step": 38335
|
|
},
|
|
{
|
|
"entropy": 5.585970640182495,
|
|
"epoch": 3.202472435683261,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003988176249746532,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.23084289580583572,
|
|
"num_tokens": 70549768.0,
|
|
"step": 38340
|
|
},
|
|
{
|
|
"entropy": 5.397403430938721,
|
|
"epoch": 3.202890076845974,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003987927669526494,
|
|
"loss": 4.6211,
|
|
"mean_token_accuracy": 0.24327861219644548,
|
|
"num_tokens": 70559211.0,
|
|
"step": 38345
|
|
},
|
|
{
|
|
"entropy": 5.464969968795776,
|
|
"epoch": 3.203307718008687,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003987679067635044,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.23235799223184586,
|
|
"num_tokens": 70568242.0,
|
|
"step": 38350
|
|
},
|
|
{
|
|
"entropy": 5.53572039604187,
|
|
"epoch": 3.2037253591714,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000398743044407653,
|
|
"loss": 4.8199,
|
|
"mean_token_accuracy": 0.23249537497758865,
|
|
"num_tokens": 70577215.0,
|
|
"step": 38355
|
|
},
|
|
{
|
|
"entropy": 5.433585548400879,
|
|
"epoch": 3.204143000334113,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039871817988553084,
|
|
"loss": 4.6643,
|
|
"mean_token_accuracy": 0.23760422319173813,
|
|
"num_tokens": 70585569.0,
|
|
"step": 38360
|
|
},
|
|
{
|
|
"entropy": 5.478679847717285,
|
|
"epoch": 3.2045606414968257,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039869331319757284,
|
|
"loss": 4.7487,
|
|
"mean_token_accuracy": 0.23139978498220443,
|
|
"num_tokens": 70594055.0,
|
|
"step": 38365
|
|
},
|
|
{
|
|
"entropy": 5.458812665939331,
|
|
"epoch": 3.204978282659539,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039866844434421466,
|
|
"loss": 4.7647,
|
|
"mean_token_accuracy": 0.23139528483152388,
|
|
"num_tokens": 70603388.0,
|
|
"step": 38370
|
|
},
|
|
{
|
|
"entropy": 5.517465686798095,
|
|
"epoch": 3.205395923822252,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003986435733258914,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.23669153451919556,
|
|
"num_tokens": 70612902.0,
|
|
"step": 38375
|
|
},
|
|
{
|
|
"entropy": 5.537941980361938,
|
|
"epoch": 3.205813564984965,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00039861870014303865,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.23008915334939956,
|
|
"num_tokens": 70622041.0,
|
|
"step": 38380
|
|
},
|
|
{
|
|
"entropy": 5.512897062301636,
|
|
"epoch": 3.206231206147678,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003985938247960917,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.22567955106496812,
|
|
"num_tokens": 70630820.0,
|
|
"step": 38385
|
|
},
|
|
{
|
|
"entropy": 5.501311254501343,
|
|
"epoch": 3.206648847310391,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003985689472854861,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.23171856701374055,
|
|
"num_tokens": 70639940.0,
|
|
"step": 38390
|
|
},
|
|
{
|
|
"entropy": 5.471878099441528,
|
|
"epoch": 3.207066488473104,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003985440676116573,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.2357839122414589,
|
|
"num_tokens": 70648779.0,
|
|
"step": 38395
|
|
},
|
|
{
|
|
"entropy": 5.474267959594727,
|
|
"epoch": 3.2074841296358167,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003985191857750409,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.23402574509382248,
|
|
"num_tokens": 70657350.0,
|
|
"step": 38400
|
|
},
|
|
{
|
|
"entropy": 5.570529651641846,
|
|
"epoch": 3.20790177079853,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00039849430177607255,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.23451015204191208,
|
|
"num_tokens": 70666107.0,
|
|
"step": 38405
|
|
},
|
|
{
|
|
"entropy": 5.484596252441406,
|
|
"epoch": 3.208319411961243,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003984694156151877,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.23104026913642883,
|
|
"num_tokens": 70675562.0,
|
|
"step": 38410
|
|
},
|
|
{
|
|
"entropy": 5.555637216567993,
|
|
"epoch": 3.208737053123956,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003984445272928221,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.23321982473134995,
|
|
"num_tokens": 70685558.0,
|
|
"step": 38415
|
|
},
|
|
{
|
|
"entropy": 5.515390014648437,
|
|
"epoch": 3.209154694286669,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003984196368094115,
|
|
"loss": 4.787,
|
|
"mean_token_accuracy": 0.2276576802134514,
|
|
"num_tokens": 70694362.0,
|
|
"step": 38420
|
|
},
|
|
{
|
|
"entropy": 5.464664268493652,
|
|
"epoch": 3.2095723354493817,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039839474416539163,
|
|
"loss": 4.6602,
|
|
"mean_token_accuracy": 0.2431550830602646,
|
|
"num_tokens": 70703535.0,
|
|
"step": 38425
|
|
},
|
|
{
|
|
"entropy": 5.4544212341308596,
|
|
"epoch": 3.209989976612095,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003983698493611981,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.24404164850711824,
|
|
"num_tokens": 70711920.0,
|
|
"step": 38430
|
|
},
|
|
{
|
|
"entropy": 5.526822566986084,
|
|
"epoch": 3.2104076177748078,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039834495239726703,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.22554251551628113,
|
|
"num_tokens": 70720467.0,
|
|
"step": 38435
|
|
},
|
|
{
|
|
"entropy": 5.503491687774658,
|
|
"epoch": 3.210825258937521,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000398320053274034,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.23193253129720687,
|
|
"num_tokens": 70729743.0,
|
|
"step": 38440
|
|
},
|
|
{
|
|
"entropy": 5.5786644458770756,
|
|
"epoch": 3.211242900100234,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000398295151991935,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.22109154611825943,
|
|
"num_tokens": 70738361.0,
|
|
"step": 38445
|
|
},
|
|
{
|
|
"entropy": 5.42807970046997,
|
|
"epoch": 3.2116605412629466,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000398270248551406,
|
|
"loss": 4.5831,
|
|
"mean_token_accuracy": 0.24227734357118608,
|
|
"num_tokens": 70747235.0,
|
|
"step": 38450
|
|
},
|
|
{
|
|
"entropy": 5.37896499633789,
|
|
"epoch": 3.21207818242566,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039824534295288287,
|
|
"loss": 4.5967,
|
|
"mean_token_accuracy": 0.2472819447517395,
|
|
"num_tokens": 70756015.0,
|
|
"step": 38455
|
|
},
|
|
{
|
|
"entropy": 5.470439529418945,
|
|
"epoch": 3.2124958235883727,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003982204351968017,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.22666784673929213,
|
|
"num_tokens": 70765809.0,
|
|
"step": 38460
|
|
},
|
|
{
|
|
"entropy": 5.384084701538086,
|
|
"epoch": 3.212913464751086,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003981955252835984,
|
|
"loss": 4.674,
|
|
"mean_token_accuracy": 0.24174836575984954,
|
|
"num_tokens": 70774937.0,
|
|
"step": 38465
|
|
},
|
|
{
|
|
"entropy": 5.448692178726196,
|
|
"epoch": 3.213331105913799,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003981706132137093,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.23190146535634995,
|
|
"num_tokens": 70783884.0,
|
|
"step": 38470
|
|
},
|
|
{
|
|
"entropy": 5.541638422012329,
|
|
"epoch": 3.213748747076512,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003981456989875703,
|
|
"loss": 4.8288,
|
|
"mean_token_accuracy": 0.23009199351072313,
|
|
"num_tokens": 70793670.0,
|
|
"step": 38475
|
|
},
|
|
{
|
|
"entropy": 5.522085046768188,
|
|
"epoch": 3.214166388239225,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003981207826056176,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.22195955663919448,
|
|
"num_tokens": 70803792.0,
|
|
"step": 38480
|
|
},
|
|
{
|
|
"entropy": 5.508448362350464,
|
|
"epoch": 3.2145840294019377,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003980958640682873,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.23086402416229249,
|
|
"num_tokens": 70812482.0,
|
|
"step": 38485
|
|
},
|
|
{
|
|
"entropy": 5.500377750396728,
|
|
"epoch": 3.215001670564651,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003980709433760158,
|
|
"loss": 4.7559,
|
|
"mean_token_accuracy": 0.23211305290460588,
|
|
"num_tokens": 70821557.0,
|
|
"step": 38490
|
|
},
|
|
{
|
|
"entropy": 5.3660304069519045,
|
|
"epoch": 3.2154193117273637,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003980460205292394,
|
|
"loss": 4.5638,
|
|
"mean_token_accuracy": 0.23827093541622163,
|
|
"num_tokens": 70830364.0,
|
|
"step": 38495
|
|
},
|
|
{
|
|
"entropy": 5.480979681015015,
|
|
"epoch": 3.215836952890077,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003980210955283941,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.22731465697288514,
|
|
"num_tokens": 70838729.0,
|
|
"step": 38500
|
|
},
|
|
{
|
|
"entropy": 5.473546028137207,
|
|
"epoch": 3.21625459405279,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039799616837391655,
|
|
"loss": 4.654,
|
|
"mean_token_accuracy": 0.23619525283575057,
|
|
"num_tokens": 70848346.0,
|
|
"step": 38505
|
|
},
|
|
{
|
|
"entropy": 5.538142919540405,
|
|
"epoch": 3.216672235215503,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039797123906624304,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.22994642406702043,
|
|
"num_tokens": 70857342.0,
|
|
"step": 38510
|
|
},
|
|
{
|
|
"entropy": 5.5117024898529055,
|
|
"epoch": 3.217089876378216,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003979463076058099,
|
|
"loss": 4.7703,
|
|
"mean_token_accuracy": 0.23459856659173967,
|
|
"num_tokens": 70865928.0,
|
|
"step": 38515
|
|
},
|
|
{
|
|
"entropy": 5.4065470695495605,
|
|
"epoch": 3.2175075175409287,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003979213739930538,
|
|
"loss": 4.6337,
|
|
"mean_token_accuracy": 0.24381052255630492,
|
|
"num_tokens": 70874610.0,
|
|
"step": 38520
|
|
},
|
|
{
|
|
"entropy": 5.360015058517456,
|
|
"epoch": 3.217925158703642,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039789643822841093,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.23656888902187348,
|
|
"num_tokens": 70883466.0,
|
|
"step": 38525
|
|
},
|
|
{
|
|
"entropy": 5.434125471115112,
|
|
"epoch": 3.2183427998663547,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00039787150031231805,
|
|
"loss": 4.7173,
|
|
"mean_token_accuracy": 0.23280637860298156,
|
|
"num_tokens": 70891924.0,
|
|
"step": 38530
|
|
},
|
|
{
|
|
"entropy": 5.489321660995484,
|
|
"epoch": 3.218760441029068,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039784656024521164,
|
|
"loss": 4.7817,
|
|
"mean_token_accuracy": 0.22563424408435823,
|
|
"num_tokens": 70902058.0,
|
|
"step": 38535
|
|
},
|
|
{
|
|
"entropy": 5.46258134841919,
|
|
"epoch": 3.219178082191781,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003978216180275283,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.2323670729994774,
|
|
"num_tokens": 70911012.0,
|
|
"step": 38540
|
|
},
|
|
{
|
|
"entropy": 5.552223253250122,
|
|
"epoch": 3.2195957233544936,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039779667365970475,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.2322921186685562,
|
|
"num_tokens": 70920726.0,
|
|
"step": 38545
|
|
},
|
|
{
|
|
"entropy": 5.47733998298645,
|
|
"epoch": 3.220013364517207,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00039777172714217763,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.23820846080780028,
|
|
"num_tokens": 70929419.0,
|
|
"step": 38550
|
|
},
|
|
{
|
|
"entropy": 5.536647701263428,
|
|
"epoch": 3.2204310056799197,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039774677847538353,
|
|
"loss": 4.7835,
|
|
"mean_token_accuracy": 0.22954715490341188,
|
|
"num_tokens": 70939300.0,
|
|
"step": 38555
|
|
},
|
|
{
|
|
"entropy": 5.433778095245361,
|
|
"epoch": 3.220848646842633,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00039772182765975944,
|
|
"loss": 4.571,
|
|
"mean_token_accuracy": 0.2396490216255188,
|
|
"num_tokens": 70948047.0,
|
|
"step": 38560
|
|
},
|
|
{
|
|
"entropy": 5.4961014747619625,
|
|
"epoch": 3.2212662880053458,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000397696874695742,
|
|
"loss": 4.7755,
|
|
"mean_token_accuracy": 0.23620013296604156,
|
|
"num_tokens": 70957188.0,
|
|
"step": 38565
|
|
},
|
|
{
|
|
"entropy": 5.430529499053955,
|
|
"epoch": 3.2216839291680586,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039767191958376807,
|
|
"loss": 4.6182,
|
|
"mean_token_accuracy": 0.2416320651769638,
|
|
"num_tokens": 70965851.0,
|
|
"step": 38570
|
|
},
|
|
{
|
|
"entropy": 5.398926258087158,
|
|
"epoch": 3.222101570330772,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003976469623242745,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.24060935229063035,
|
|
"num_tokens": 70975312.0,
|
|
"step": 38575
|
|
},
|
|
{
|
|
"entropy": 5.472012042999268,
|
|
"epoch": 3.2225192114934846,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00039762200291769824,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.23604833334684372,
|
|
"num_tokens": 70984306.0,
|
|
"step": 38580
|
|
},
|
|
{
|
|
"entropy": 5.424241971969605,
|
|
"epoch": 3.222936852656198,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039759704136447627,
|
|
"loss": 4.6588,
|
|
"mean_token_accuracy": 0.2333239957690239,
|
|
"num_tokens": 70993452.0,
|
|
"step": 38585
|
|
},
|
|
{
|
|
"entropy": 5.583633184432983,
|
|
"epoch": 3.2233544938189107,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003975720776650455,
|
|
"loss": 4.7798,
|
|
"mean_token_accuracy": 0.22946053892374038,
|
|
"num_tokens": 71003046.0,
|
|
"step": 38590
|
|
},
|
|
{
|
|
"entropy": 5.513995265960693,
|
|
"epoch": 3.223772134981624,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039754711181984293,
|
|
"loss": 4.7415,
|
|
"mean_token_accuracy": 0.2283487156033516,
|
|
"num_tokens": 71012223.0,
|
|
"step": 38595
|
|
},
|
|
{
|
|
"entropy": 5.488707113265991,
|
|
"epoch": 3.2241897761443368,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003975221438293057,
|
|
"loss": 4.7393,
|
|
"mean_token_accuracy": 0.24221331030130386,
|
|
"num_tokens": 71021325.0,
|
|
"step": 38600
|
|
},
|
|
{
|
|
"entropy": 5.373833179473877,
|
|
"epoch": 3.2246074173070496,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039749717369387083,
|
|
"loss": 4.5865,
|
|
"mean_token_accuracy": 0.24071777611970901,
|
|
"num_tokens": 71030626.0,
|
|
"step": 38605
|
|
},
|
|
{
|
|
"entropy": 5.41771354675293,
|
|
"epoch": 3.225025058469763,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003974722014139755,
|
|
"loss": 4.6836,
|
|
"mean_token_accuracy": 0.23726135939359666,
|
|
"num_tokens": 71039701.0,
|
|
"step": 38610
|
|
},
|
|
{
|
|
"entropy": 5.40479097366333,
|
|
"epoch": 3.2254426996324757,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039744722699005684,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.2373274087905884,
|
|
"num_tokens": 71049692.0,
|
|
"step": 38615
|
|
},
|
|
{
|
|
"entropy": 5.475905227661133,
|
|
"epoch": 3.225860340795189,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039742225042255214,
|
|
"loss": 4.7325,
|
|
"mean_token_accuracy": 0.23101337850093842,
|
|
"num_tokens": 71059239.0,
|
|
"step": 38620
|
|
},
|
|
{
|
|
"entropy": 5.41409387588501,
|
|
"epoch": 3.2262779819579017,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003973972717118986,
|
|
"loss": 4.5893,
|
|
"mean_token_accuracy": 0.24714804738759993,
|
|
"num_tokens": 71068062.0,
|
|
"step": 38625
|
|
},
|
|
{
|
|
"entropy": 5.509158658981323,
|
|
"epoch": 3.226695623120615,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003973722908585334,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.2306770533323288,
|
|
"num_tokens": 71077243.0,
|
|
"step": 38630
|
|
},
|
|
{
|
|
"entropy": 5.464210033416748,
|
|
"epoch": 3.227113264283328,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039734730786289397,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.2312249705195427,
|
|
"num_tokens": 71086173.0,
|
|
"step": 38635
|
|
},
|
|
{
|
|
"entropy": 5.477403450012207,
|
|
"epoch": 3.2275309054460406,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003973223227254177,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.22471923977136612,
|
|
"num_tokens": 71095615.0,
|
|
"step": 38640
|
|
},
|
|
{
|
|
"entropy": 5.516548585891724,
|
|
"epoch": 3.227948546608754,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003972973354465419,
|
|
"loss": 4.7977,
|
|
"mean_token_accuracy": 0.231112302839756,
|
|
"num_tokens": 71105079.0,
|
|
"step": 38645
|
|
},
|
|
{
|
|
"entropy": 5.5095922470092775,
|
|
"epoch": 3.2283661877714667,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000397272346026704,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.24171301871538162,
|
|
"num_tokens": 71115349.0,
|
|
"step": 38650
|
|
},
|
|
{
|
|
"entropy": 5.495443439483642,
|
|
"epoch": 3.22878382893418,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003972473544663416,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.23655440360307695,
|
|
"num_tokens": 71123455.0,
|
|
"step": 38655
|
|
},
|
|
{
|
|
"entropy": 5.4013352394104,
|
|
"epoch": 3.2292014700968927,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000397222360765892,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.24896817207336425,
|
|
"num_tokens": 71132773.0,
|
|
"step": 38660
|
|
},
|
|
{
|
|
"entropy": 5.43551082611084,
|
|
"epoch": 3.2296191112596055,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003971973649257929,
|
|
"loss": 4.6987,
|
|
"mean_token_accuracy": 0.24088205993175507,
|
|
"num_tokens": 71142413.0,
|
|
"step": 38665
|
|
},
|
|
{
|
|
"entropy": 5.413772106170654,
|
|
"epoch": 3.230036752422319,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003971723669464818,
|
|
"loss": 4.6818,
|
|
"mean_token_accuracy": 0.23847725987434387,
|
|
"num_tokens": 71150921.0,
|
|
"step": 38670
|
|
},
|
|
{
|
|
"entropy": 5.433243131637573,
|
|
"epoch": 3.2304543935850316,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003971473668283964,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.23293462693691253,
|
|
"num_tokens": 71159853.0,
|
|
"step": 38675
|
|
},
|
|
{
|
|
"entropy": 5.536081790924072,
|
|
"epoch": 3.230872034747745,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003971223645719744,
|
|
"loss": 4.7828,
|
|
"mean_token_accuracy": 0.23284885585308074,
|
|
"num_tokens": 71169733.0,
|
|
"step": 38680
|
|
},
|
|
{
|
|
"entropy": 5.566795873641968,
|
|
"epoch": 3.2312896759104577,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003970973601776533,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.2208864137530327,
|
|
"num_tokens": 71178970.0,
|
|
"step": 38685
|
|
},
|
|
{
|
|
"entropy": 5.4808738231658936,
|
|
"epoch": 3.231707317073171,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039707235364587094,
|
|
"loss": 4.7385,
|
|
"mean_token_accuracy": 0.23086107224226,
|
|
"num_tokens": 71187921.0,
|
|
"step": 38690
|
|
},
|
|
{
|
|
"entropy": 5.446238946914673,
|
|
"epoch": 3.2321249582358837,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003970473449770651,
|
|
"loss": 4.6642,
|
|
"mean_token_accuracy": 0.23735762536525726,
|
|
"num_tokens": 71196810.0,
|
|
"step": 38695
|
|
},
|
|
{
|
|
"entropy": 5.466082000732422,
|
|
"epoch": 3.2325425993985966,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003970223341716736,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.23364899605512618,
|
|
"num_tokens": 71205642.0,
|
|
"step": 38700
|
|
},
|
|
{
|
|
"entropy": 5.484291028976441,
|
|
"epoch": 3.23296024056131,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00039699732123013424,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.22707933634519578,
|
|
"num_tokens": 71214618.0,
|
|
"step": 38705
|
|
},
|
|
{
|
|
"entropy": 5.493304014205933,
|
|
"epoch": 3.2333778817240226,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039697230615288494,
|
|
"loss": 4.6774,
|
|
"mean_token_accuracy": 0.2332194060087204,
|
|
"num_tokens": 71223880.0,
|
|
"step": 38710
|
|
},
|
|
{
|
|
"entropy": 5.423728513717651,
|
|
"epoch": 3.233795522886736,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003969472889403636,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.2342171087861061,
|
|
"num_tokens": 71233374.0,
|
|
"step": 38715
|
|
},
|
|
{
|
|
"entropy": 5.453279495239258,
|
|
"epoch": 3.2342131640494487,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003969222695930082,
|
|
"loss": 4.6757,
|
|
"mean_token_accuracy": 0.23944033980369567,
|
|
"num_tokens": 71242897.0,
|
|
"step": 38720
|
|
},
|
|
{
|
|
"entropy": 5.433281326293946,
|
|
"epoch": 3.2346308052121615,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0003968972481112567,
|
|
"loss": 4.7075,
|
|
"mean_token_accuracy": 0.2381577268242836,
|
|
"num_tokens": 71252111.0,
|
|
"step": 38725
|
|
},
|
|
{
|
|
"entropy": 5.49034104347229,
|
|
"epoch": 3.2350484463748748,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003968722244955471,
|
|
"loss": 4.7573,
|
|
"mean_token_accuracy": 0.230564746260643,
|
|
"num_tokens": 71261251.0,
|
|
"step": 38730
|
|
},
|
|
{
|
|
"entropy": 5.50482702255249,
|
|
"epoch": 3.2354660875375876,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039684719874631756,
|
|
"loss": 4.7194,
|
|
"mean_token_accuracy": 0.23595238476991653,
|
|
"num_tokens": 71270431.0,
|
|
"step": 38735
|
|
},
|
|
{
|
|
"entropy": 5.484179162979126,
|
|
"epoch": 3.235883728700301,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003968221708640062,
|
|
"loss": 4.728,
|
|
"mean_token_accuracy": 0.23527450263500213,
|
|
"num_tokens": 71278743.0,
|
|
"step": 38740
|
|
},
|
|
{
|
|
"entropy": 5.508648490905761,
|
|
"epoch": 3.2363013698630136,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000396797140849051,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.2299108922481537,
|
|
"num_tokens": 71287663.0,
|
|
"step": 38745
|
|
},
|
|
{
|
|
"entropy": 5.431722354888916,
|
|
"epoch": 3.236719011025727,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003967721087018903,
|
|
"loss": 4.6681,
|
|
"mean_token_accuracy": 0.24347987473011018,
|
|
"num_tokens": 71297469.0,
|
|
"step": 38750
|
|
},
|
|
{
|
|
"entropy": 5.432102632522583,
|
|
"epoch": 3.2371366521884397,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003967470744229621,
|
|
"loss": 4.7114,
|
|
"mean_token_accuracy": 0.23876271843910218,
|
|
"num_tokens": 71306705.0,
|
|
"step": 38755
|
|
},
|
|
{
|
|
"entropy": 5.456292915344238,
|
|
"epoch": 3.2375542933511525,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003967220380127051,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.23975301831960677,
|
|
"num_tokens": 71315808.0,
|
|
"step": 38760
|
|
},
|
|
{
|
|
"entropy": 5.4097092628479,
|
|
"epoch": 3.237971934513866,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00039669699947155715,
|
|
"loss": 4.6511,
|
|
"mean_token_accuracy": 0.2427757740020752,
|
|
"num_tokens": 71324065.0,
|
|
"step": 38765
|
|
},
|
|
{
|
|
"entropy": 5.500874996185303,
|
|
"epoch": 3.2383895756765786,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039667195879995666,
|
|
"loss": 4.7825,
|
|
"mean_token_accuracy": 0.23160797655582427,
|
|
"num_tokens": 71333958.0,
|
|
"step": 38770
|
|
},
|
|
{
|
|
"entropy": 5.456749725341797,
|
|
"epoch": 3.238807216839292,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039664691599834213,
|
|
"loss": 4.7147,
|
|
"mean_token_accuracy": 0.23288460224866867,
|
|
"num_tokens": 71344364.0,
|
|
"step": 38775
|
|
},
|
|
{
|
|
"entropy": 5.494898414611816,
|
|
"epoch": 3.2392248580020047,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039662187106715205,
|
|
"loss": 4.7086,
|
|
"mean_token_accuracy": 0.2345953866839409,
|
|
"num_tokens": 71352707.0,
|
|
"step": 38780
|
|
},
|
|
{
|
|
"entropy": 5.475239419937134,
|
|
"epoch": 3.2396424991647175,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003965968240068245,
|
|
"loss": 4.695,
|
|
"mean_token_accuracy": 0.23860125988721848,
|
|
"num_tokens": 71362012.0,
|
|
"step": 38785
|
|
},
|
|
{
|
|
"entropy": 5.456532573699951,
|
|
"epoch": 3.2400601403274307,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003965717748177983,
|
|
"loss": 4.647,
|
|
"mean_token_accuracy": 0.23500728309154512,
|
|
"num_tokens": 71369945.0,
|
|
"step": 38790
|
|
},
|
|
{
|
|
"entropy": 5.4113555431365965,
|
|
"epoch": 3.2404777814901435,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003965467235005119,
|
|
"loss": 4.6748,
|
|
"mean_token_accuracy": 0.23113551288843154,
|
|
"num_tokens": 71378678.0,
|
|
"step": 38795
|
|
},
|
|
{
|
|
"entropy": 5.482618713378907,
|
|
"epoch": 3.240895422652857,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039652167005540373,
|
|
"loss": 4.8097,
|
|
"mean_token_accuracy": 0.23376734256744386,
|
|
"num_tokens": 71388481.0,
|
|
"step": 38800
|
|
},
|
|
{
|
|
"entropy": 5.4287773132324215,
|
|
"epoch": 3.2413130638155696,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039649661448291245,
|
|
"loss": 4.6871,
|
|
"mean_token_accuracy": 0.2342815190553665,
|
|
"num_tokens": 71397848.0,
|
|
"step": 38805
|
|
},
|
|
{
|
|
"entropy": 5.508930253982544,
|
|
"epoch": 3.241730704978283,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003964715567834766,
|
|
"loss": 4.7723,
|
|
"mean_token_accuracy": 0.2250111609697342,
|
|
"num_tokens": 71407359.0,
|
|
"step": 38810
|
|
},
|
|
{
|
|
"entropy": 5.471129417419434,
|
|
"epoch": 3.2421483461409957,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003964464969575351,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.23294263780117036,
|
|
"num_tokens": 71416728.0,
|
|
"step": 38815
|
|
},
|
|
{
|
|
"entropy": 5.44734525680542,
|
|
"epoch": 3.2425659873037085,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003964214350055264,
|
|
"loss": 4.5704,
|
|
"mean_token_accuracy": 0.2479402869939804,
|
|
"num_tokens": 71425640.0,
|
|
"step": 38820
|
|
},
|
|
{
|
|
"entropy": 5.47574815750122,
|
|
"epoch": 3.2429836284664217,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039639637092788935,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.23722380250692368,
|
|
"num_tokens": 71434998.0,
|
|
"step": 38825
|
|
},
|
|
{
|
|
"entropy": 5.417229795455933,
|
|
"epoch": 3.2434012696291346,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003963713047250627,
|
|
"loss": 4.6038,
|
|
"mean_token_accuracy": 0.24804801344871522,
|
|
"num_tokens": 71444363.0,
|
|
"step": 38830
|
|
},
|
|
{
|
|
"entropy": 5.4371278285980225,
|
|
"epoch": 3.243818910791848,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003963462363974852,
|
|
"loss": 4.6809,
|
|
"mean_token_accuracy": 0.23900142014026643,
|
|
"num_tokens": 71452849.0,
|
|
"step": 38835
|
|
},
|
|
{
|
|
"entropy": 5.547451162338257,
|
|
"epoch": 3.2442365519545606,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003963211659455958,
|
|
"loss": 4.8959,
|
|
"mean_token_accuracy": 0.2259441301226616,
|
|
"num_tokens": 71462428.0,
|
|
"step": 38840
|
|
},
|
|
{
|
|
"entropy": 5.594169998168946,
|
|
"epoch": 3.2446541931172734,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003962960933698335,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.22498859763145446,
|
|
"num_tokens": 71471591.0,
|
|
"step": 38845
|
|
},
|
|
{
|
|
"entropy": 5.417900848388672,
|
|
"epoch": 3.2450718342799867,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003962710186706369,
|
|
"loss": 4.6323,
|
|
"mean_token_accuracy": 0.23904868066310883,
|
|
"num_tokens": 71480061.0,
|
|
"step": 38850
|
|
},
|
|
{
|
|
"entropy": 5.484611368179321,
|
|
"epoch": 3.2454894754426995,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003962459418484452,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.2245118275284767,
|
|
"num_tokens": 71488991.0,
|
|
"step": 38855
|
|
},
|
|
{
|
|
"entropy": 5.523462152481079,
|
|
"epoch": 3.2459071166054128,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003962208629036973,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.2334735721349716,
|
|
"num_tokens": 71498025.0,
|
|
"step": 38860
|
|
},
|
|
{
|
|
"entropy": 5.574482870101929,
|
|
"epoch": 3.2463247577681256,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003961957818368324,
|
|
"loss": 4.8259,
|
|
"mean_token_accuracy": 0.22322590351104737,
|
|
"num_tokens": 71508764.0,
|
|
"step": 38865
|
|
},
|
|
{
|
|
"entropy": 5.535842561721802,
|
|
"epoch": 3.246742398930839,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003961706986482893,
|
|
"loss": 4.7807,
|
|
"mean_token_accuracy": 0.23119719177484513,
|
|
"num_tokens": 71518510.0,
|
|
"step": 38870
|
|
},
|
|
{
|
|
"entropy": 5.478935623168946,
|
|
"epoch": 3.2471600400935516,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00039614561333850735,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.24778191596269608,
|
|
"num_tokens": 71526355.0,
|
|
"step": 38875
|
|
},
|
|
{
|
|
"entropy": 5.493571329116821,
|
|
"epoch": 3.2475776812562644,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039612052590792563,
|
|
"loss": 4.6584,
|
|
"mean_token_accuracy": 0.2346452385187149,
|
|
"num_tokens": 71534363.0,
|
|
"step": 38880
|
|
},
|
|
{
|
|
"entropy": 5.539427661895752,
|
|
"epoch": 3.2479953224189777,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003960954363569833,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.23508023768663405,
|
|
"num_tokens": 71542991.0,
|
|
"step": 38885
|
|
},
|
|
{
|
|
"entropy": 5.443092489242554,
|
|
"epoch": 3.2484129635816905,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039607034468611965,
|
|
"loss": 4.6447,
|
|
"mean_token_accuracy": 0.24274911731481552,
|
|
"num_tokens": 71551434.0,
|
|
"step": 38890
|
|
},
|
|
{
|
|
"entropy": 5.451053667068481,
|
|
"epoch": 3.2488306047444038,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003960452508957738,
|
|
"loss": 4.6323,
|
|
"mean_token_accuracy": 0.2494377613067627,
|
|
"num_tokens": 71561045.0,
|
|
"step": 38895
|
|
},
|
|
{
|
|
"entropy": 5.439359855651856,
|
|
"epoch": 3.2492482459071166,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039602015498638524,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.23761141151189805,
|
|
"num_tokens": 71570284.0,
|
|
"step": 38900
|
|
},
|
|
{
|
|
"entropy": 5.404349613189697,
|
|
"epoch": 3.2496658870698294,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000395995056958393,
|
|
"loss": 4.6297,
|
|
"mean_token_accuracy": 0.23601675927639007,
|
|
"num_tokens": 71578890.0,
|
|
"step": 38905
|
|
},
|
|
{
|
|
"entropy": 5.488093042373658,
|
|
"epoch": 3.2500835282325427,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003959699568122368,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.23643000423908234,
|
|
"num_tokens": 71587466.0,
|
|
"step": 38910
|
|
},
|
|
{
|
|
"entropy": 5.4816686630249025,
|
|
"epoch": 3.2505011693952555,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039594485454835576,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.22853345572948455,
|
|
"num_tokens": 71596989.0,
|
|
"step": 38915
|
|
},
|
|
{
|
|
"entropy": 5.472019338607788,
|
|
"epoch": 3.2509188105579687,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003959197501671896,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.2402356371283531,
|
|
"num_tokens": 71606168.0,
|
|
"step": 38920
|
|
},
|
|
{
|
|
"entropy": 5.482901477813721,
|
|
"epoch": 3.2513364517206815,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003958946436691776,
|
|
"loss": 4.7501,
|
|
"mean_token_accuracy": 0.2341736614704132,
|
|
"num_tokens": 71615592.0,
|
|
"step": 38925
|
|
},
|
|
{
|
|
"entropy": 5.4540050506591795,
|
|
"epoch": 3.2517540928833943,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039586953505475937,
|
|
"loss": 4.5968,
|
|
"mean_token_accuracy": 0.24578162431716918,
|
|
"num_tokens": 71624493.0,
|
|
"step": 38930
|
|
},
|
|
{
|
|
"entropy": 5.4684587001800535,
|
|
"epoch": 3.2521717340461076,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039584442432437437,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.23212318271398544,
|
|
"num_tokens": 71632886.0,
|
|
"step": 38935
|
|
},
|
|
{
|
|
"entropy": 5.4058633804321286,
|
|
"epoch": 3.2525893752088204,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003958193114784624,
|
|
"loss": 4.5602,
|
|
"mean_token_accuracy": 0.2481156826019287,
|
|
"num_tokens": 71641799.0,
|
|
"step": 38940
|
|
},
|
|
{
|
|
"entropy": 5.408043718338012,
|
|
"epoch": 3.2530070163715337,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003957941965174629,
|
|
"loss": 4.6476,
|
|
"mean_token_accuracy": 0.24451978802680968,
|
|
"num_tokens": 71650162.0,
|
|
"step": 38945
|
|
},
|
|
{
|
|
"entropy": 5.413664960861206,
|
|
"epoch": 3.2534246575342465,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039576907944181556,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.2294732227921486,
|
|
"num_tokens": 71659594.0,
|
|
"step": 38950
|
|
},
|
|
{
|
|
"entropy": 5.4758435726165775,
|
|
"epoch": 3.2538422986969597,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039574396025196003,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.229233618080616,
|
|
"num_tokens": 71667881.0,
|
|
"step": 38955
|
|
},
|
|
{
|
|
"entropy": 5.5076089859008786,
|
|
"epoch": 3.2542599398596725,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00039571883894833624,
|
|
"loss": 4.7628,
|
|
"mean_token_accuracy": 0.23329155892133713,
|
|
"num_tokens": 71676491.0,
|
|
"step": 38960
|
|
},
|
|
{
|
|
"entropy": 5.494276094436645,
|
|
"epoch": 3.254677581022386,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003956937155313839,
|
|
"loss": 4.6485,
|
|
"mean_token_accuracy": 0.23815446346998215,
|
|
"num_tokens": 71685455.0,
|
|
"step": 38965
|
|
},
|
|
{
|
|
"entropy": 5.430796909332275,
|
|
"epoch": 3.2550952221850986,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003956685900015427,
|
|
"loss": 4.5993,
|
|
"mean_token_accuracy": 0.2374693423509598,
|
|
"num_tokens": 71693722.0,
|
|
"step": 38970
|
|
},
|
|
{
|
|
"entropy": 5.526724052429199,
|
|
"epoch": 3.2555128633478114,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003956434623592526,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.21712073534727097,
|
|
"num_tokens": 71703689.0,
|
|
"step": 38975
|
|
},
|
|
{
|
|
"entropy": 5.533103322982788,
|
|
"epoch": 3.2559305045105247,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003956183326049535,
|
|
"loss": 4.8514,
|
|
"mean_token_accuracy": 0.2286326467990875,
|
|
"num_tokens": 71714575.0,
|
|
"step": 38980
|
|
},
|
|
{
|
|
"entropy": 5.528376770019531,
|
|
"epoch": 3.2563481456732375,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00039559320073908526,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.2289114147424698,
|
|
"num_tokens": 71723670.0,
|
|
"step": 38985
|
|
},
|
|
{
|
|
"entropy": 5.5007435321807865,
|
|
"epoch": 3.2567657868359507,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00039556806676208794,
|
|
"loss": 4.689,
|
|
"mean_token_accuracy": 0.24377793669700623,
|
|
"num_tokens": 71731359.0,
|
|
"step": 38990
|
|
},
|
|
{
|
|
"entropy": 5.5050383567810055,
|
|
"epoch": 3.2571834279986636,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039554293067440145,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.23098429143428803,
|
|
"num_tokens": 71741432.0,
|
|
"step": 38995
|
|
},
|
|
{
|
|
"entropy": 5.607757711410523,
|
|
"epoch": 3.2576010691613764,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003955177924764658,
|
|
"loss": 4.8358,
|
|
"mean_token_accuracy": 0.2213699921965599,
|
|
"num_tokens": 71750953.0,
|
|
"step": 39000
|
|
},
|
|
{
|
|
"epoch": 3.2576010691613764,
|
|
"eval_entropy": 5.1886335683308324,
|
|
"eval_loss": 4.739346504211426,
|
|
"eval_mean_token_accuracy": 0.2428381007351731,
|
|
"eval_num_tokens": 71750953.0,
|
|
"eval_runtime": 20.8672,
|
|
"eval_samples_per_second": 1809.686,
|
|
"eval_steps_per_second": 226.241,
|
|
"step": 39000
|
|
},
|
|
{
|
|
"entropy": 5.4935798168182375,
|
|
"epoch": 3.2580187103240896,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003954926521687212,
|
|
"loss": 4.6697,
|
|
"mean_token_accuracy": 0.23691818863153458,
|
|
"num_tokens": 71758940.0,
|
|
"step": 39005
|
|
},
|
|
{
|
|
"entropy": 5.529376554489136,
|
|
"epoch": 3.2584363514868024,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003954675097516078,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.23306349217891692,
|
|
"num_tokens": 71768801.0,
|
|
"step": 39010
|
|
},
|
|
{
|
|
"entropy": 5.483216142654419,
|
|
"epoch": 3.2588539926495157,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003954423652255655,
|
|
"loss": 4.749,
|
|
"mean_token_accuracy": 0.23023272007703782,
|
|
"num_tokens": 71777589.0,
|
|
"step": 39015
|
|
},
|
|
{
|
|
"entropy": 5.479443597793579,
|
|
"epoch": 3.2592716338122285,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039541721859103455,
|
|
"loss": 4.7227,
|
|
"mean_token_accuracy": 0.23022686839103698,
|
|
"num_tokens": 71787774.0,
|
|
"step": 39020
|
|
},
|
|
{
|
|
"entropy": 5.4772271633148195,
|
|
"epoch": 3.2596892749749413,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039539206984845536,
|
|
"loss": 4.7025,
|
|
"mean_token_accuracy": 0.23688935339450837,
|
|
"num_tokens": 71796007.0,
|
|
"step": 39025
|
|
},
|
|
{
|
|
"entropy": 5.551498031616211,
|
|
"epoch": 3.2601069161376546,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000395366918998268,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.22219979017972946,
|
|
"num_tokens": 71806712.0,
|
|
"step": 39030
|
|
},
|
|
{
|
|
"entropy": 5.588935279846192,
|
|
"epoch": 3.2605245573003674,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039534176604091295,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.23377977311611176,
|
|
"num_tokens": 71815719.0,
|
|
"step": 39035
|
|
},
|
|
{
|
|
"entropy": 5.481668949127197,
|
|
"epoch": 3.2609421984630806,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003953166109768303,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.22711749672889708,
|
|
"num_tokens": 71825007.0,
|
|
"step": 39040
|
|
},
|
|
{
|
|
"entropy": 5.514005899429321,
|
|
"epoch": 3.2613598396257935,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003952914538064606,
|
|
"loss": 4.7573,
|
|
"mean_token_accuracy": 0.23450998812913895,
|
|
"num_tokens": 71834510.0,
|
|
"step": 39045
|
|
},
|
|
{
|
|
"entropy": 5.5938252925872805,
|
|
"epoch": 3.2617774807885063,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003952662945302443,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.23020204156637192,
|
|
"num_tokens": 71843310.0,
|
|
"step": 39050
|
|
},
|
|
{
|
|
"entropy": 5.469381666183471,
|
|
"epoch": 3.2621951219512195,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003952411331486216,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.22992076426744462,
|
|
"num_tokens": 71852170.0,
|
|
"step": 39055
|
|
},
|
|
{
|
|
"entropy": 5.405617094039917,
|
|
"epoch": 3.2626127631139323,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003952159696620332,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.23600547164678573,
|
|
"num_tokens": 71862172.0,
|
|
"step": 39060
|
|
},
|
|
{
|
|
"entropy": 5.454971265792847,
|
|
"epoch": 3.2630304042766456,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039519080407091956,
|
|
"loss": 4.6397,
|
|
"mean_token_accuracy": 0.24346059560775757,
|
|
"num_tokens": 71871741.0,
|
|
"step": 39065
|
|
},
|
|
{
|
|
"entropy": 5.461433744430542,
|
|
"epoch": 3.2634480454393584,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039516563637572116,
|
|
"loss": 4.6353,
|
|
"mean_token_accuracy": 0.24101997911930084,
|
|
"num_tokens": 71880933.0,
|
|
"step": 39070
|
|
},
|
|
{
|
|
"entropy": 5.492981958389282,
|
|
"epoch": 3.2638656866020717,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039514046657687874,
|
|
"loss": 4.6774,
|
|
"mean_token_accuracy": 0.23980032056570053,
|
|
"num_tokens": 71890868.0,
|
|
"step": 39075
|
|
},
|
|
{
|
|
"entropy": 5.441141510009766,
|
|
"epoch": 3.2642833277647845,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039511529467483274,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.2418987661600113,
|
|
"num_tokens": 71900372.0,
|
|
"step": 39080
|
|
},
|
|
{
|
|
"entropy": 5.37748441696167,
|
|
"epoch": 3.2647009689274977,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00039509012067002395,
|
|
"loss": 4.6018,
|
|
"mean_token_accuracy": 0.24484313726425172,
|
|
"num_tokens": 71909184.0,
|
|
"step": 39085
|
|
},
|
|
{
|
|
"entropy": 5.526626777648926,
|
|
"epoch": 3.2651186100902105,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003950649445628931,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.22929926812648774,
|
|
"num_tokens": 71918122.0,
|
|
"step": 39090
|
|
},
|
|
{
|
|
"entropy": 5.426394748687744,
|
|
"epoch": 3.2655362512529233,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0003950397663538809,
|
|
"loss": 4.6725,
|
|
"mean_token_accuracy": 0.23763552755117417,
|
|
"num_tokens": 71925952.0,
|
|
"step": 39095
|
|
},
|
|
{
|
|
"entropy": 5.460411024093628,
|
|
"epoch": 3.2659538924156366,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039501458604342793,
|
|
"loss": 4.6915,
|
|
"mean_token_accuracy": 0.2402773380279541,
|
|
"num_tokens": 71934848.0,
|
|
"step": 39100
|
|
},
|
|
{
|
|
"entropy": 5.527141141891479,
|
|
"epoch": 3.2663715335783494,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039498940363197533,
|
|
"loss": 4.8576,
|
|
"mean_token_accuracy": 0.2184511810541153,
|
|
"num_tokens": 71945191.0,
|
|
"step": 39105
|
|
},
|
|
{
|
|
"entropy": 5.486374139785767,
|
|
"epoch": 3.2667891747410627,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039496421911996375,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.24011695981025696,
|
|
"num_tokens": 71954442.0,
|
|
"step": 39110
|
|
},
|
|
{
|
|
"entropy": 5.389338159561158,
|
|
"epoch": 3.2672068159037755,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039493903250783407,
|
|
"loss": 4.585,
|
|
"mean_token_accuracy": 0.2445114701986313,
|
|
"num_tokens": 71963327.0,
|
|
"step": 39115
|
|
},
|
|
{
|
|
"entropy": 5.503696393966675,
|
|
"epoch": 3.2676244570664883,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003949138437960273,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.23787904381752015,
|
|
"num_tokens": 71971906.0,
|
|
"step": 39120
|
|
},
|
|
{
|
|
"entropy": 5.5013665676116945,
|
|
"epoch": 3.2680420982292016,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003948886529849843,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.22988174110651016,
|
|
"num_tokens": 71981779.0,
|
|
"step": 39125
|
|
},
|
|
{
|
|
"entropy": 5.393016386032104,
|
|
"epoch": 3.2684597393919144,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039486346007514624,
|
|
"loss": 4.5787,
|
|
"mean_token_accuracy": 0.24900732934474945,
|
|
"num_tokens": 71990309.0,
|
|
"step": 39130
|
|
},
|
|
{
|
|
"entropy": 5.455674362182617,
|
|
"epoch": 3.2688773805546276,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003948382650669539,
|
|
"loss": 4.6999,
|
|
"mean_token_accuracy": 0.23455329835414887,
|
|
"num_tokens": 72001098.0,
|
|
"step": 39135
|
|
},
|
|
{
|
|
"entropy": 5.517623949050903,
|
|
"epoch": 3.2692950217173404,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003948130679608486,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.22798285633325577,
|
|
"num_tokens": 72010212.0,
|
|
"step": 39140
|
|
},
|
|
{
|
|
"entropy": 5.486274480819702,
|
|
"epoch": 3.2697126628800532,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039478786875727116,
|
|
"loss": 4.6938,
|
|
"mean_token_accuracy": 0.23567888736724854,
|
|
"num_tokens": 72019931.0,
|
|
"step": 39145
|
|
},
|
|
{
|
|
"entropy": 5.485649108886719,
|
|
"epoch": 3.2701303040427665,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039476266745666307,
|
|
"loss": 4.6318,
|
|
"mean_token_accuracy": 0.23905289620161058,
|
|
"num_tokens": 72028755.0,
|
|
"step": 39150
|
|
},
|
|
{
|
|
"entropy": 5.487727117538452,
|
|
"epoch": 3.2705479452054793,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003947374640594652,
|
|
"loss": 4.6894,
|
|
"mean_token_accuracy": 0.23717964738607406,
|
|
"num_tokens": 72037149.0,
|
|
"step": 39155
|
|
},
|
|
{
|
|
"entropy": 5.459629726409912,
|
|
"epoch": 3.2709655863681926,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039471225856611895,
|
|
"loss": 4.7392,
|
|
"mean_token_accuracy": 0.2310284212231636,
|
|
"num_tokens": 72047416.0,
|
|
"step": 39160
|
|
},
|
|
{
|
|
"entropy": 5.499148607254028,
|
|
"epoch": 3.2713832275309054,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039468705097706546,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.22843386679887773,
|
|
"num_tokens": 72056908.0,
|
|
"step": 39165
|
|
},
|
|
{
|
|
"entropy": 5.439537811279297,
|
|
"epoch": 3.2718008686936186,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039466184129274617,
|
|
"loss": 4.624,
|
|
"mean_token_accuracy": 0.24026171267032623,
|
|
"num_tokens": 72065697.0,
|
|
"step": 39170
|
|
},
|
|
{
|
|
"entropy": 5.5207987308502195,
|
|
"epoch": 3.2722185098563314,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039463662951360235,
|
|
"loss": 4.7184,
|
|
"mean_token_accuracy": 0.2309577628970146,
|
|
"num_tokens": 72075337.0,
|
|
"step": 39175
|
|
},
|
|
{
|
|
"entropy": 5.507364130020141,
|
|
"epoch": 3.2726361510190443,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003946114156400752,
|
|
"loss": 4.6517,
|
|
"mean_token_accuracy": 0.24368861466646194,
|
|
"num_tokens": 72085940.0,
|
|
"step": 39180
|
|
},
|
|
{
|
|
"entropy": 5.4748656272888185,
|
|
"epoch": 3.2730537921817575,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039458619967260635,
|
|
"loss": 4.738,
|
|
"mean_token_accuracy": 0.23223746418952942,
|
|
"num_tokens": 72095581.0,
|
|
"step": 39185
|
|
},
|
|
{
|
|
"entropy": 5.469815826416015,
|
|
"epoch": 3.2734714333444703,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039456098161163693,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.2263100653886795,
|
|
"num_tokens": 72105578.0,
|
|
"step": 39190
|
|
},
|
|
{
|
|
"entropy": 5.434775924682617,
|
|
"epoch": 3.2738890745071836,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003945357614576088,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.23817665576934816,
|
|
"num_tokens": 72114390.0,
|
|
"step": 39195
|
|
},
|
|
{
|
|
"entropy": 5.455474424362182,
|
|
"epoch": 3.2743067156698964,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039451053921096314,
|
|
"loss": 4.7558,
|
|
"mean_token_accuracy": 0.23762368708848952,
|
|
"num_tokens": 72124096.0,
|
|
"step": 39200
|
|
},
|
|
{
|
|
"entropy": 5.517141056060791,
|
|
"epoch": 3.2747243568326097,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003944853148721418,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.23409290313720704,
|
|
"num_tokens": 72132741.0,
|
|
"step": 39205
|
|
},
|
|
{
|
|
"entropy": 5.491848039627075,
|
|
"epoch": 3.2751419979953225,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003944600884415861,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.22919304221868514,
|
|
"num_tokens": 72141560.0,
|
|
"step": 39210
|
|
},
|
|
{
|
|
"entropy": 5.437547302246093,
|
|
"epoch": 3.2755596391580353,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003944348599197378,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.23325107097625733,
|
|
"num_tokens": 72150710.0,
|
|
"step": 39215
|
|
},
|
|
{
|
|
"entropy": 5.561106777191162,
|
|
"epoch": 3.2759772803207485,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00039440962930703836,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.22462357729673385,
|
|
"num_tokens": 72159929.0,
|
|
"step": 39220
|
|
},
|
|
{
|
|
"entropy": 5.50314154624939,
|
|
"epoch": 3.2763949214834613,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039438439660392983,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.22045254111289977,
|
|
"num_tokens": 72169514.0,
|
|
"step": 39225
|
|
},
|
|
{
|
|
"entropy": 5.472870349884033,
|
|
"epoch": 3.2768125626461746,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039435916181085367,
|
|
"loss": 4.6424,
|
|
"mean_token_accuracy": 0.24139289259910585,
|
|
"num_tokens": 72178885.0,
|
|
"step": 39230
|
|
},
|
|
{
|
|
"entropy": 5.503199481964112,
|
|
"epoch": 3.2772302038088874,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003943339249282517,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.23185722529888153,
|
|
"num_tokens": 72188000.0,
|
|
"step": 39235
|
|
},
|
|
{
|
|
"entropy": 5.511696243286133,
|
|
"epoch": 3.2776478449716,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003943086859565657,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.23524175733327865,
|
|
"num_tokens": 72197161.0,
|
|
"step": 39240
|
|
},
|
|
{
|
|
"entropy": 5.4995949268341064,
|
|
"epoch": 3.2780654861343135,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003942834448962376,
|
|
"loss": 4.6883,
|
|
"mean_token_accuracy": 0.2361661300063133,
|
|
"num_tokens": 72205847.0,
|
|
"step": 39245
|
|
},
|
|
{
|
|
"entropy": 5.467666816711426,
|
|
"epoch": 3.2784831272970263,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003942582017477092,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.23368200063705444,
|
|
"num_tokens": 72214760.0,
|
|
"step": 39250
|
|
},
|
|
{
|
|
"entropy": 5.504439353942871,
|
|
"epoch": 3.2789007684597395,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003942329565114224,
|
|
"loss": 4.8466,
|
|
"mean_token_accuracy": 0.2200402170419693,
|
|
"num_tokens": 72225611.0,
|
|
"step": 39255
|
|
},
|
|
{
|
|
"entropy": 5.5024168491363525,
|
|
"epoch": 3.2793184096224524,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003942077091878192,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.23854176551103592,
|
|
"num_tokens": 72235710.0,
|
|
"step": 39260
|
|
},
|
|
{
|
|
"entropy": 5.416419839859008,
|
|
"epoch": 3.279736050785165,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003941824597773415,
|
|
"loss": 4.5776,
|
|
"mean_token_accuracy": 0.24093631207942962,
|
|
"num_tokens": 72245093.0,
|
|
"step": 39265
|
|
},
|
|
{
|
|
"entropy": 5.450403308868408,
|
|
"epoch": 3.2801536919478784,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039415720828043144,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.22788792252540588,
|
|
"num_tokens": 72254503.0,
|
|
"step": 39270
|
|
},
|
|
{
|
|
"entropy": 5.48549599647522,
|
|
"epoch": 3.2805713331105912,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000394131954697531,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.2290765181183815,
|
|
"num_tokens": 72263351.0,
|
|
"step": 39275
|
|
},
|
|
{
|
|
"entropy": 5.4796887874603275,
|
|
"epoch": 3.2809889742733045,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039410669902908236,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.2296367198228836,
|
|
"num_tokens": 72272366.0,
|
|
"step": 39280
|
|
},
|
|
{
|
|
"entropy": 5.537285184860229,
|
|
"epoch": 3.2814066154360173,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039408144127552747,
|
|
"loss": 4.8582,
|
|
"mean_token_accuracy": 0.2238635927438736,
|
|
"num_tokens": 72282523.0,
|
|
"step": 39285
|
|
},
|
|
{
|
|
"entropy": 5.497168827056885,
|
|
"epoch": 3.2818242565987306,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039405618143730864,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.23494537621736528,
|
|
"num_tokens": 72292860.0,
|
|
"step": 39290
|
|
},
|
|
{
|
|
"entropy": 5.4389848709106445,
|
|
"epoch": 3.2822418977614434,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00039403091951486813,
|
|
"loss": 4.681,
|
|
"mean_token_accuracy": 0.2412266492843628,
|
|
"num_tokens": 72302190.0,
|
|
"step": 39295
|
|
},
|
|
{
|
|
"entropy": 5.4813282012939455,
|
|
"epoch": 3.282659538924156,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000394005655508648,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.2362568512558937,
|
|
"num_tokens": 72311598.0,
|
|
"step": 39300
|
|
},
|
|
{
|
|
"entropy": 5.480198621749878,
|
|
"epoch": 3.2830771800868694,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00039398038941909066,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.2356013312935829,
|
|
"num_tokens": 72321384.0,
|
|
"step": 39305
|
|
},
|
|
{
|
|
"entropy": 5.438240385055542,
|
|
"epoch": 3.2834948212495823,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039395512124663847,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.23994019329547883,
|
|
"num_tokens": 72330458.0,
|
|
"step": 39310
|
|
},
|
|
{
|
|
"entropy": 5.55207839012146,
|
|
"epoch": 3.2839124624122955,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00039392985099173357,
|
|
"loss": 4.9456,
|
|
"mean_token_accuracy": 0.214679816365242,
|
|
"num_tokens": 72340298.0,
|
|
"step": 39315
|
|
},
|
|
{
|
|
"entropy": 5.568695831298828,
|
|
"epoch": 3.2843301035750083,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00039390457865481855,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.24488799422979354,
|
|
"num_tokens": 72349766.0,
|
|
"step": 39320
|
|
},
|
|
{
|
|
"entropy": 5.508135652542114,
|
|
"epoch": 3.2847477447377216,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003938793042363357,
|
|
"loss": 4.7179,
|
|
"mean_token_accuracy": 0.2383580520749092,
|
|
"num_tokens": 72359548.0,
|
|
"step": 39325
|
|
},
|
|
{
|
|
"entropy": 5.385394525527954,
|
|
"epoch": 3.2851653859004344,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003938540277367276,
|
|
"loss": 4.5763,
|
|
"mean_token_accuracy": 0.24897077530622483,
|
|
"num_tokens": 72369068.0,
|
|
"step": 39330
|
|
},
|
|
{
|
|
"entropy": 5.4348626136779785,
|
|
"epoch": 3.285583027063147,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003938287491564366,
|
|
"loss": 4.6304,
|
|
"mean_token_accuracy": 0.2365218997001648,
|
|
"num_tokens": 72379303.0,
|
|
"step": 39335
|
|
},
|
|
{
|
|
"entropy": 5.498979949951172,
|
|
"epoch": 3.2860006682258605,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039380346849590545,
|
|
"loss": 4.7374,
|
|
"mean_token_accuracy": 0.23113379925489425,
|
|
"num_tokens": 72388999.0,
|
|
"step": 39340
|
|
},
|
|
{
|
|
"entropy": 5.445492458343506,
|
|
"epoch": 3.2864183093885733,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003937781857555764,
|
|
"loss": 4.6632,
|
|
"mean_token_accuracy": 0.23574821501970292,
|
|
"num_tokens": 72398102.0,
|
|
"step": 39345
|
|
},
|
|
{
|
|
"entropy": 5.541854476928711,
|
|
"epoch": 3.2868359505512865,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00039375290093589233,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.2296731099486351,
|
|
"num_tokens": 72407027.0,
|
|
"step": 39350
|
|
},
|
|
{
|
|
"entropy": 5.455264711380005,
|
|
"epoch": 3.2872535917139993,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00039372761403729575,
|
|
"loss": 4.7305,
|
|
"mean_token_accuracy": 0.2395598292350769,
|
|
"num_tokens": 72416266.0,
|
|
"step": 39355
|
|
},
|
|
{
|
|
"entropy": 5.543245124816894,
|
|
"epoch": 3.287671232876712,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003937023250602294,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.23339501470327378,
|
|
"num_tokens": 72426626.0,
|
|
"step": 39360
|
|
},
|
|
{
|
|
"entropy": 5.407711791992187,
|
|
"epoch": 3.2880888740394254,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039367703400513594,
|
|
"loss": 4.6169,
|
|
"mean_token_accuracy": 0.2386827513575554,
|
|
"num_tokens": 72435370.0,
|
|
"step": 39365
|
|
},
|
|
{
|
|
"entropy": 5.539994716644287,
|
|
"epoch": 3.288506515202138,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003936517408724582,
|
|
"loss": 4.78,
|
|
"mean_token_accuracy": 0.22761520743370056,
|
|
"num_tokens": 72443358.0,
|
|
"step": 39370
|
|
},
|
|
{
|
|
"entropy": 5.502148151397705,
|
|
"epoch": 3.2889241563648515,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003936264456626389,
|
|
"loss": 4.7732,
|
|
"mean_token_accuracy": 0.23541323244571685,
|
|
"num_tokens": 72452503.0,
|
|
"step": 39375
|
|
},
|
|
{
|
|
"entropy": 5.539281797409058,
|
|
"epoch": 3.2893417975275643,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003936011483761209,
|
|
"loss": 4.7414,
|
|
"mean_token_accuracy": 0.24155666083097457,
|
|
"num_tokens": 72462256.0,
|
|
"step": 39380
|
|
},
|
|
{
|
|
"entropy": 5.4913310527801515,
|
|
"epoch": 3.289759438690277,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000393575849013347,
|
|
"loss": 4.6345,
|
|
"mean_token_accuracy": 0.23834641873836518,
|
|
"num_tokens": 72471998.0,
|
|
"step": 39385
|
|
},
|
|
{
|
|
"entropy": 5.489602851867676,
|
|
"epoch": 3.2901770798529903,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003935505475747601,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.2335006132721901,
|
|
"num_tokens": 72480713.0,
|
|
"step": 39390
|
|
},
|
|
{
|
|
"entropy": 5.48021969795227,
|
|
"epoch": 3.290594721015703,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003935252440608032,
|
|
"loss": 4.6682,
|
|
"mean_token_accuracy": 0.24037785828113556,
|
|
"num_tokens": 72489600.0,
|
|
"step": 39395
|
|
},
|
|
{
|
|
"entropy": 5.4257526874542235,
|
|
"epoch": 3.2910123621784164,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003934999384719192,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.23650194555521012,
|
|
"num_tokens": 72498774.0,
|
|
"step": 39400
|
|
},
|
|
{
|
|
"entropy": 5.385075426101684,
|
|
"epoch": 3.2914300033411292,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003934746308085512,
|
|
"loss": 4.5575,
|
|
"mean_token_accuracy": 0.24989363104104995,
|
|
"num_tokens": 72506948.0,
|
|
"step": 39405
|
|
},
|
|
{
|
|
"entropy": 5.45247106552124,
|
|
"epoch": 3.2918476445038425,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003934493210711422,
|
|
"loss": 4.6774,
|
|
"mean_token_accuracy": 0.2337258294224739,
|
|
"num_tokens": 72516304.0,
|
|
"step": 39410
|
|
},
|
|
{
|
|
"entropy": 5.507095289230347,
|
|
"epoch": 3.2922652856665553,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003934240092601352,
|
|
"loss": 4.6695,
|
|
"mean_token_accuracy": 0.2365053653717041,
|
|
"num_tokens": 72524648.0,
|
|
"step": 39415
|
|
},
|
|
{
|
|
"entropy": 5.533347129821777,
|
|
"epoch": 3.292682926829268,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00039339869537597337,
|
|
"loss": 4.7054,
|
|
"mean_token_accuracy": 0.2340129390358925,
|
|
"num_tokens": 72533768.0,
|
|
"step": 39420
|
|
},
|
|
{
|
|
"entropy": 5.4520752906799315,
|
|
"epoch": 3.2931005679919814,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00039337337941909985,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.240905299782753,
|
|
"num_tokens": 72542279.0,
|
|
"step": 39425
|
|
},
|
|
{
|
|
"entropy": 5.460507726669311,
|
|
"epoch": 3.293518209154694,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00039334806138995786,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.2394696906208992,
|
|
"num_tokens": 72550975.0,
|
|
"step": 39430
|
|
},
|
|
{
|
|
"entropy": 5.456420469284057,
|
|
"epoch": 3.2939358503174074,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00039332274128899057,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.23614839762449263,
|
|
"num_tokens": 72560426.0,
|
|
"step": 39435
|
|
},
|
|
{
|
|
"entropy": 5.545349597930908,
|
|
"epoch": 3.2943534914801202,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003932974191166414,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.23235394656658173,
|
|
"num_tokens": 72569931.0,
|
|
"step": 39440
|
|
},
|
|
{
|
|
"entropy": 5.522860288619995,
|
|
"epoch": 3.2947711326428335,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003932720948733534,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.23002310395240783,
|
|
"num_tokens": 72579846.0,
|
|
"step": 39445
|
|
},
|
|
{
|
|
"entropy": 5.434385919570923,
|
|
"epoch": 3.2951887738055463,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00039324676855956997,
|
|
"loss": 4.6087,
|
|
"mean_token_accuracy": 0.25126818418502805,
|
|
"num_tokens": 72587579.0,
|
|
"step": 39450
|
|
},
|
|
{
|
|
"entropy": 5.460496997833252,
|
|
"epoch": 3.295606414968259,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003932214401757346,
|
|
"loss": 4.6197,
|
|
"mean_token_accuracy": 0.23988056927919388,
|
|
"num_tokens": 72596269.0,
|
|
"step": 39455
|
|
},
|
|
{
|
|
"entropy": 5.500318193435669,
|
|
"epoch": 3.2960240561309724,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039319610972229056,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.22695139050483704,
|
|
"num_tokens": 72604987.0,
|
|
"step": 39460
|
|
},
|
|
{
|
|
"entropy": 5.42841911315918,
|
|
"epoch": 3.296441697293685,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00039317077719968143,
|
|
"loss": 4.5855,
|
|
"mean_token_accuracy": 0.2396405190229416,
|
|
"num_tokens": 72613301.0,
|
|
"step": 39465
|
|
},
|
|
{
|
|
"entropy": 5.487714338302612,
|
|
"epoch": 3.2968593384563984,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039314544260835054,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.2311714693903923,
|
|
"num_tokens": 72621610.0,
|
|
"step": 39470
|
|
},
|
|
{
|
|
"entropy": 5.452829313278198,
|
|
"epoch": 3.2972769796191113,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003931201059487415,
|
|
"loss": 4.7218,
|
|
"mean_token_accuracy": 0.23166686594486235,
|
|
"num_tokens": 72631382.0,
|
|
"step": 39475
|
|
},
|
|
{
|
|
"entropy": 5.483666563034058,
|
|
"epoch": 3.297694620781824,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039309476722129775,
|
|
"loss": 4.6337,
|
|
"mean_token_accuracy": 0.23812745064496993,
|
|
"num_tokens": 72639883.0,
|
|
"step": 39480
|
|
},
|
|
{
|
|
"entropy": 5.504307603836059,
|
|
"epoch": 3.2981122619445373,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039306942642646306,
|
|
"loss": 4.7977,
|
|
"mean_token_accuracy": 0.2392913356423378,
|
|
"num_tokens": 72648869.0,
|
|
"step": 39485
|
|
},
|
|
{
|
|
"entropy": 5.460114765167236,
|
|
"epoch": 3.29852990310725,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00039304408356468084,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.2399190694093704,
|
|
"num_tokens": 72658550.0,
|
|
"step": 39490
|
|
},
|
|
{
|
|
"entropy": 5.473866701126099,
|
|
"epoch": 3.2989475442699634,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003930187386363949,
|
|
"loss": 4.657,
|
|
"mean_token_accuracy": 0.24196514636278152,
|
|
"num_tokens": 72666865.0,
|
|
"step": 39495
|
|
},
|
|
{
|
|
"entropy": 5.412607622146607,
|
|
"epoch": 3.299365185432676,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003929933916420489,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.23917466253042222,
|
|
"num_tokens": 72675816.0,
|
|
"step": 39500
|
|
},
|
|
{
|
|
"entropy": 5.467671680450439,
|
|
"epoch": 3.299782826595389,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003929680425820865,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.23169521391391754,
|
|
"num_tokens": 72684203.0,
|
|
"step": 39505
|
|
},
|
|
{
|
|
"entropy": 5.519072771072388,
|
|
"epoch": 3.3002004677581023,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003929426914569516,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.2269893318414688,
|
|
"num_tokens": 72693226.0,
|
|
"step": 39510
|
|
},
|
|
{
|
|
"entropy": 5.548756694793701,
|
|
"epoch": 3.300618108920815,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00039291733826708785,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.234760183095932,
|
|
"num_tokens": 72703258.0,
|
|
"step": 39515
|
|
},
|
|
{
|
|
"entropy": 5.4685688495635985,
|
|
"epoch": 3.3010357500835283,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039289198301293915,
|
|
"loss": 4.6485,
|
|
"mean_token_accuracy": 0.24292366951704025,
|
|
"num_tokens": 72711966.0,
|
|
"step": 39520
|
|
},
|
|
{
|
|
"entropy": 5.45336594581604,
|
|
"epoch": 3.301453391246241,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003928666256949495,
|
|
"loss": 4.6397,
|
|
"mean_token_accuracy": 0.24181191474199296,
|
|
"num_tokens": 72721246.0,
|
|
"step": 39525
|
|
},
|
|
{
|
|
"entropy": 5.46371603012085,
|
|
"epoch": 3.3018710324089544,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00039284126631356246,
|
|
"loss": 4.6868,
|
|
"mean_token_accuracy": 0.23697471022605895,
|
|
"num_tokens": 72730551.0,
|
|
"step": 39530
|
|
},
|
|
{
|
|
"entropy": 5.498901748657227,
|
|
"epoch": 3.302288673571667,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039281590486922244,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.23358695358037948,
|
|
"num_tokens": 72739689.0,
|
|
"step": 39535
|
|
},
|
|
{
|
|
"entropy": 5.490299081802368,
|
|
"epoch": 3.30270631473438,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000392790541362373,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.23815623074769973,
|
|
"num_tokens": 72748513.0,
|
|
"step": 39540
|
|
},
|
|
{
|
|
"entropy": 5.454039287567139,
|
|
"epoch": 3.3031239558970933,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00039276517579345846,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.23232949823141097,
|
|
"num_tokens": 72757730.0,
|
|
"step": 39545
|
|
},
|
|
{
|
|
"entropy": 5.543742561340332,
|
|
"epoch": 3.303541597059806,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003927398081629228,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.23352763801813126,
|
|
"num_tokens": 72766074.0,
|
|
"step": 39550
|
|
},
|
|
{
|
|
"entropy": 5.457540798187256,
|
|
"epoch": 3.3039592382225194,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003927144384712099,
|
|
"loss": 4.696,
|
|
"mean_token_accuracy": 0.23437751531600953,
|
|
"num_tokens": 72774889.0,
|
|
"step": 39555
|
|
},
|
|
{
|
|
"entropy": 5.503816318511963,
|
|
"epoch": 3.304376879385232,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003926890667187642,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.2316323846578598,
|
|
"num_tokens": 72784474.0,
|
|
"step": 39560
|
|
},
|
|
{
|
|
"entropy": 5.5130298137664795,
|
|
"epoch": 3.3047945205479454,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003926636929060297,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.22758439630270005,
|
|
"num_tokens": 72794057.0,
|
|
"step": 39565
|
|
},
|
|
{
|
|
"entropy": 5.462481355667114,
|
|
"epoch": 3.3052121617106582,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003926383170334507,
|
|
"loss": 4.7363,
|
|
"mean_token_accuracy": 0.22862779796123506,
|
|
"num_tokens": 72803644.0,
|
|
"step": 39570
|
|
},
|
|
{
|
|
"entropy": 5.59480299949646,
|
|
"epoch": 3.305629802873371,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003926129391014712,
|
|
"loss": 4.774,
|
|
"mean_token_accuracy": 0.23217330873012543,
|
|
"num_tokens": 72814036.0,
|
|
"step": 39575
|
|
},
|
|
{
|
|
"entropy": 5.5075352668762205,
|
|
"epoch": 3.3060474440360843,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003925875591105357,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.23921287953853607,
|
|
"num_tokens": 72824226.0,
|
|
"step": 39580
|
|
},
|
|
{
|
|
"entropy": 5.44498119354248,
|
|
"epoch": 3.306465085198797,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003925621770610885,
|
|
"loss": 4.6665,
|
|
"mean_token_accuracy": 0.23858524560928346,
|
|
"num_tokens": 72832624.0,
|
|
"step": 39585
|
|
},
|
|
{
|
|
"entropy": 5.436393594741821,
|
|
"epoch": 3.3068827263615104,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003925367929535738,
|
|
"loss": 4.731,
|
|
"mean_token_accuracy": 0.23296814262866974,
|
|
"num_tokens": 72842175.0,
|
|
"step": 39590
|
|
},
|
|
{
|
|
"entropy": 5.529116106033325,
|
|
"epoch": 3.307300367524223,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003925114067884361,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.22493177503347397,
|
|
"num_tokens": 72850273.0,
|
|
"step": 39595
|
|
},
|
|
{
|
|
"entropy": 5.632110500335694,
|
|
"epoch": 3.307718008686936,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003924860185661198,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.22164041548967361,
|
|
"num_tokens": 72859976.0,
|
|
"step": 39600
|
|
},
|
|
{
|
|
"entropy": 5.492954921722412,
|
|
"epoch": 3.3081356498496493,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003924606282870693,
|
|
"loss": 4.6948,
|
|
"mean_token_accuracy": 0.24245440661907197,
|
|
"num_tokens": 72868712.0,
|
|
"step": 39605
|
|
},
|
|
{
|
|
"entropy": 5.382717800140381,
|
|
"epoch": 3.308553291012362,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039243523595172914,
|
|
"loss": 4.655,
|
|
"mean_token_accuracy": 0.24240583032369614,
|
|
"num_tokens": 72878907.0,
|
|
"step": 39610
|
|
},
|
|
{
|
|
"entropy": 5.461828422546387,
|
|
"epoch": 3.3089709321750753,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003924098415605438,
|
|
"loss": 4.6677,
|
|
"mean_token_accuracy": 0.2347181558609009,
|
|
"num_tokens": 72888290.0,
|
|
"step": 39615
|
|
},
|
|
{
|
|
"entropy": 5.523006010055542,
|
|
"epoch": 3.309388573337788,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003923844451139578,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.23575352132320404,
|
|
"num_tokens": 72897579.0,
|
|
"step": 39620
|
|
},
|
|
{
|
|
"entropy": 5.392522096633911,
|
|
"epoch": 3.309806214500501,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003923590466124159,
|
|
"loss": 4.5703,
|
|
"mean_token_accuracy": 0.24990323334932327,
|
|
"num_tokens": 72906574.0,
|
|
"step": 39625
|
|
},
|
|
{
|
|
"entropy": 5.4380110740661625,
|
|
"epoch": 3.310223855663214,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003923336460563625,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.23212088495492936,
|
|
"num_tokens": 72915218.0,
|
|
"step": 39630
|
|
},
|
|
{
|
|
"entropy": 5.47448353767395,
|
|
"epoch": 3.310641496825927,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003923082434462425,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.2296352729201317,
|
|
"num_tokens": 72924524.0,
|
|
"step": 39635
|
|
},
|
|
{
|
|
"entropy": 5.462535715103149,
|
|
"epoch": 3.3110591379886403,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003922828387825004,
|
|
"loss": 4.6948,
|
|
"mean_token_accuracy": 0.23327670693397523,
|
|
"num_tokens": 72933806.0,
|
|
"step": 39640
|
|
},
|
|
{
|
|
"entropy": 5.485034036636352,
|
|
"epoch": 3.311476779151353,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039225743206558114,
|
|
"loss": 4.8223,
|
|
"mean_token_accuracy": 0.23140980303287506,
|
|
"num_tokens": 72943854.0,
|
|
"step": 39645
|
|
},
|
|
{
|
|
"entropy": 5.422298097610474,
|
|
"epoch": 3.3118944203140663,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039223202329592927,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.2407472997903824,
|
|
"num_tokens": 72952051.0,
|
|
"step": 39650
|
|
},
|
|
{
|
|
"entropy": 5.444650316238404,
|
|
"epoch": 3.312312061476779,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003922066124739898,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.2353852406144142,
|
|
"num_tokens": 72960818.0,
|
|
"step": 39655
|
|
},
|
|
{
|
|
"entropy": 5.593735885620117,
|
|
"epoch": 3.312729702639492,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003921811996002075,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.22597911953926086,
|
|
"num_tokens": 72970187.0,
|
|
"step": 39660
|
|
},
|
|
{
|
|
"entropy": 5.471797895431519,
|
|
"epoch": 3.313147343802205,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039215578467502715,
|
|
"loss": 4.6491,
|
|
"mean_token_accuracy": 0.2403001144528389,
|
|
"num_tokens": 72979356.0,
|
|
"step": 39665
|
|
},
|
|
{
|
|
"entropy": 5.423280048370361,
|
|
"epoch": 3.313564984964918,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003921303676988939,
|
|
"loss": 4.684,
|
|
"mean_token_accuracy": 0.23562027662992477,
|
|
"num_tokens": 72988918.0,
|
|
"step": 39670
|
|
},
|
|
{
|
|
"entropy": 5.466867971420288,
|
|
"epoch": 3.3139826261276313,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039210494867225257,
|
|
"loss": 4.7172,
|
|
"mean_token_accuracy": 0.23798151910305024,
|
|
"num_tokens": 72997843.0,
|
|
"step": 39675
|
|
},
|
|
{
|
|
"entropy": 5.514850521087647,
|
|
"epoch": 3.314400267290344,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003920795275955481,
|
|
"loss": 4.7755,
|
|
"mean_token_accuracy": 0.23537546396255493,
|
|
"num_tokens": 73006764.0,
|
|
"step": 39680
|
|
},
|
|
{
|
|
"entropy": 5.498249816894531,
|
|
"epoch": 3.3148179084530573,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003920541044692255,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.22925006002187728,
|
|
"num_tokens": 73014945.0,
|
|
"step": 39685
|
|
},
|
|
{
|
|
"entropy": 5.486873769760132,
|
|
"epoch": 3.31523554961577,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039202867929373,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.23291249126195906,
|
|
"num_tokens": 73023786.0,
|
|
"step": 39690
|
|
},
|
|
{
|
|
"entropy": 5.619822692871094,
|
|
"epoch": 3.315653190778483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003920032520695066,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.21892112791538237,
|
|
"num_tokens": 73036021.0,
|
|
"step": 39695
|
|
},
|
|
{
|
|
"entropy": 5.61577672958374,
|
|
"epoch": 3.3160708319411962,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003919778227970004,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.22448531091213225,
|
|
"num_tokens": 73045022.0,
|
|
"step": 39700
|
|
},
|
|
{
|
|
"entropy": 5.481187343597412,
|
|
"epoch": 3.316488473103909,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039195239147665664,
|
|
"loss": 4.7251,
|
|
"mean_token_accuracy": 0.22934475690126419,
|
|
"num_tokens": 73054435.0,
|
|
"step": 39705
|
|
},
|
|
{
|
|
"entropy": 5.5313794136047365,
|
|
"epoch": 3.3169061142666223,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039192695810892045,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.22671136409044265,
|
|
"num_tokens": 73063087.0,
|
|
"step": 39710
|
|
},
|
|
{
|
|
"entropy": 5.470163249969483,
|
|
"epoch": 3.317323755429335,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003919015226942372,
|
|
"loss": 4.7557,
|
|
"mean_token_accuracy": 0.23468304574489593,
|
|
"num_tokens": 73072685.0,
|
|
"step": 39715
|
|
},
|
|
{
|
|
"entropy": 5.4337574481964115,
|
|
"epoch": 3.317741396592048,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039187608523305194,
|
|
"loss": 4.7079,
|
|
"mean_token_accuracy": 0.233964404463768,
|
|
"num_tokens": 73082286.0,
|
|
"step": 39720
|
|
},
|
|
{
|
|
"entropy": 5.490478372573852,
|
|
"epoch": 3.318159037754761,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00039185064572581024,
|
|
"loss": 4.694,
|
|
"mean_token_accuracy": 0.2343605637550354,
|
|
"num_tokens": 73091791.0,
|
|
"step": 39725
|
|
},
|
|
{
|
|
"entropy": 5.498105525970459,
|
|
"epoch": 3.318576678917474,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003918252041729573,
|
|
"loss": 4.7075,
|
|
"mean_token_accuracy": 0.2328101858496666,
|
|
"num_tokens": 73100813.0,
|
|
"step": 39730
|
|
},
|
|
{
|
|
"entropy": 5.456619787216186,
|
|
"epoch": 3.3189943200801872,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039179976057493855,
|
|
"loss": 4.6413,
|
|
"mean_token_accuracy": 0.2427094340324402,
|
|
"num_tokens": 73109960.0,
|
|
"step": 39735
|
|
},
|
|
{
|
|
"entropy": 5.5080290794372555,
|
|
"epoch": 3.3194119612429,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00039177431493219936,
|
|
"loss": 4.6975,
|
|
"mean_token_accuracy": 0.23642903417348862,
|
|
"num_tokens": 73118729.0,
|
|
"step": 39740
|
|
},
|
|
{
|
|
"entropy": 5.437738943099975,
|
|
"epoch": 3.319829602405613,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003917488672451852,
|
|
"loss": 4.6515,
|
|
"mean_token_accuracy": 0.23859633058309554,
|
|
"num_tokens": 73128162.0,
|
|
"step": 39745
|
|
},
|
|
{
|
|
"entropy": 5.49291763305664,
|
|
"epoch": 3.320247243568326,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003917234175143417,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.24706286191940308,
|
|
"num_tokens": 73137565.0,
|
|
"step": 39750
|
|
},
|
|
{
|
|
"entropy": 5.546454048156738,
|
|
"epoch": 3.320664884731039,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039169796574011417,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.23133899569511412,
|
|
"num_tokens": 73146517.0,
|
|
"step": 39755
|
|
},
|
|
{
|
|
"entropy": 5.48645167350769,
|
|
"epoch": 3.321082525893752,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0003916725119229483,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.22565219402313233,
|
|
"num_tokens": 73156116.0,
|
|
"step": 39760
|
|
},
|
|
{
|
|
"entropy": 5.476029968261718,
|
|
"epoch": 3.321500167056465,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003916470560632897,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.2412663370370865,
|
|
"num_tokens": 73165088.0,
|
|
"step": 39765
|
|
},
|
|
{
|
|
"entropy": 5.514892625808716,
|
|
"epoch": 3.3219178082191783,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000391621598161584,
|
|
"loss": 4.7799,
|
|
"mean_token_accuracy": 0.2340825915336609,
|
|
"num_tokens": 73174935.0,
|
|
"step": 39770
|
|
},
|
|
{
|
|
"entropy": 5.499310302734375,
|
|
"epoch": 3.322335449381891,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003915961382182768,
|
|
"loss": 4.6591,
|
|
"mean_token_accuracy": 0.2398736983537674,
|
|
"num_tokens": 73184806.0,
|
|
"step": 39775
|
|
},
|
|
{
|
|
"entropy": 5.530655384063721,
|
|
"epoch": 3.322753090544604,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039157067623381384,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.2303949624300003,
|
|
"num_tokens": 73194147.0,
|
|
"step": 39780
|
|
},
|
|
{
|
|
"entropy": 5.552213859558106,
|
|
"epoch": 3.323170731707317,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039154521220864094,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.23711563050746917,
|
|
"num_tokens": 73204266.0,
|
|
"step": 39785
|
|
},
|
|
{
|
|
"entropy": 5.511066865921021,
|
|
"epoch": 3.32358837287003,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003915197461432038,
|
|
"loss": 4.7576,
|
|
"mean_token_accuracy": 0.23114053457975386,
|
|
"num_tokens": 73213555.0,
|
|
"step": 39790
|
|
},
|
|
{
|
|
"entropy": 5.487220811843872,
|
|
"epoch": 3.324006014032743,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003914942780379482,
|
|
"loss": 4.7525,
|
|
"mean_token_accuracy": 0.2423672318458557,
|
|
"num_tokens": 73222398.0,
|
|
"step": 39795
|
|
},
|
|
{
|
|
"entropy": 5.542016553878784,
|
|
"epoch": 3.324423655195456,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039146880789332013,
|
|
"loss": 4.8231,
|
|
"mean_token_accuracy": 0.23138800114393235,
|
|
"num_tokens": 73232233.0,
|
|
"step": 39800
|
|
},
|
|
{
|
|
"entropy": 5.550554275512695,
|
|
"epoch": 3.3248412963581693,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00039144333570976527,
|
|
"loss": 4.696,
|
|
"mean_token_accuracy": 0.23874846398830413,
|
|
"num_tokens": 73241832.0,
|
|
"step": 39805
|
|
},
|
|
{
|
|
"entropy": 5.465195846557617,
|
|
"epoch": 3.325258937520882,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039141786148772976,
|
|
"loss": 4.6361,
|
|
"mean_token_accuracy": 0.23884740024805068,
|
|
"num_tokens": 73251374.0,
|
|
"step": 39810
|
|
},
|
|
{
|
|
"entropy": 5.488207912445068,
|
|
"epoch": 3.325676578683595,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039139238522765935,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.23703658878803252,
|
|
"num_tokens": 73260364.0,
|
|
"step": 39815
|
|
},
|
|
{
|
|
"entropy": 5.491417026519775,
|
|
"epoch": 3.326094219846308,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003913669069300002,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.2261714220046997,
|
|
"num_tokens": 73270847.0,
|
|
"step": 39820
|
|
},
|
|
{
|
|
"entropy": 5.404034900665283,
|
|
"epoch": 3.326511861009021,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039134142659519826,
|
|
"loss": 4.6138,
|
|
"mean_token_accuracy": 0.23977175652980803,
|
|
"num_tokens": 73279869.0,
|
|
"step": 39825
|
|
},
|
|
{
|
|
"entropy": 5.469329690933227,
|
|
"epoch": 3.326929502171734,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039131594422369965,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.2320721670985222,
|
|
"num_tokens": 73289370.0,
|
|
"step": 39830
|
|
},
|
|
{
|
|
"entropy": 5.488998556137085,
|
|
"epoch": 3.327347143334447,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003912904598159503,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.22368264347314834,
|
|
"num_tokens": 73297992.0,
|
|
"step": 39835
|
|
},
|
|
{
|
|
"entropy": 5.425944185256958,
|
|
"epoch": 3.32776478449716,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003912649733723966,
|
|
"loss": 4.6613,
|
|
"mean_token_accuracy": 0.24004003256559373,
|
|
"num_tokens": 73306919.0,
|
|
"step": 39840
|
|
},
|
|
{
|
|
"entropy": 5.5809266567230225,
|
|
"epoch": 3.328182425659873,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003912394848934846,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.2222401514649391,
|
|
"num_tokens": 73315324.0,
|
|
"step": 39845
|
|
},
|
|
{
|
|
"entropy": 5.592060708999634,
|
|
"epoch": 3.328600066822586,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003912139943796604,
|
|
"loss": 4.8829,
|
|
"mean_token_accuracy": 0.21861876994371415,
|
|
"num_tokens": 73325393.0,
|
|
"step": 39850
|
|
},
|
|
{
|
|
"entropy": 5.466519546508789,
|
|
"epoch": 3.329017707985299,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003911885018313704,
|
|
"loss": 4.701,
|
|
"mean_token_accuracy": 0.23814935535192489,
|
|
"num_tokens": 73335060.0,
|
|
"step": 39855
|
|
},
|
|
{
|
|
"entropy": 5.511552524566651,
|
|
"epoch": 3.329435349148012,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00039116300724906076,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.24133951365947723,
|
|
"num_tokens": 73343690.0,
|
|
"step": 39860
|
|
},
|
|
{
|
|
"entropy": 5.368144941329956,
|
|
"epoch": 3.329852990310725,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039113751063317795,
|
|
"loss": 4.6219,
|
|
"mean_token_accuracy": 0.24393593072891234,
|
|
"num_tokens": 73352597.0,
|
|
"step": 39865
|
|
},
|
|
{
|
|
"entropy": 5.539807891845703,
|
|
"epoch": 3.330270631473438,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039111201198416815,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.2306361511349678,
|
|
"num_tokens": 73363085.0,
|
|
"step": 39870
|
|
},
|
|
{
|
|
"entropy": 5.546910810470581,
|
|
"epoch": 3.330688272636151,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00039108651130247786,
|
|
"loss": 4.7021,
|
|
"mean_token_accuracy": 0.23369822949171065,
|
|
"num_tokens": 73371702.0,
|
|
"step": 39875
|
|
},
|
|
{
|
|
"entropy": 5.466007471084595,
|
|
"epoch": 3.331105913798864,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00039106100858855343,
|
|
"loss": 4.6699,
|
|
"mean_token_accuracy": 0.24002014547586442,
|
|
"num_tokens": 73379798.0,
|
|
"step": 39880
|
|
},
|
|
{
|
|
"entropy": 5.457508754730225,
|
|
"epoch": 3.331523554961577,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039103550384284134,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.23328358083963394,
|
|
"num_tokens": 73389457.0,
|
|
"step": 39885
|
|
},
|
|
{
|
|
"entropy": 5.467107629776001,
|
|
"epoch": 3.33194119612429,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003910099970657881,
|
|
"loss": 4.6785,
|
|
"mean_token_accuracy": 0.24197497367858886,
|
|
"num_tokens": 73398486.0,
|
|
"step": 39890
|
|
},
|
|
{
|
|
"entropy": 5.466931533813477,
|
|
"epoch": 3.332358837287003,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039098448825784023,
|
|
"loss": 4.6816,
|
|
"mean_token_accuracy": 0.23677485436201096,
|
|
"num_tokens": 73407596.0,
|
|
"step": 39895
|
|
},
|
|
{
|
|
"entropy": 5.5205450534820555,
|
|
"epoch": 3.3327764784497163,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039095897741944427,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.22928640991449356,
|
|
"num_tokens": 73416509.0,
|
|
"step": 39900
|
|
},
|
|
{
|
|
"entropy": 5.441917371749878,
|
|
"epoch": 3.333194119612429,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003909334645510467,
|
|
"loss": 4.6441,
|
|
"mean_token_accuracy": 0.2341885671019554,
|
|
"num_tokens": 73425164.0,
|
|
"step": 39905
|
|
},
|
|
{
|
|
"entropy": 5.374098300933838,
|
|
"epoch": 3.333611760775142,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003909079496530945,
|
|
"loss": 4.569,
|
|
"mean_token_accuracy": 0.24843530356884003,
|
|
"num_tokens": 73434028.0,
|
|
"step": 39910
|
|
},
|
|
{
|
|
"entropy": 5.460231876373291,
|
|
"epoch": 3.334029401937855,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000390882432726034,
|
|
"loss": 4.6996,
|
|
"mean_token_accuracy": 0.22887105047702788,
|
|
"num_tokens": 73443407.0,
|
|
"step": 39915
|
|
},
|
|
{
|
|
"entropy": 5.533037233352661,
|
|
"epoch": 3.334447043100568,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039085691377031205,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.2340400531888008,
|
|
"num_tokens": 73452150.0,
|
|
"step": 39920
|
|
},
|
|
{
|
|
"entropy": 5.587658452987671,
|
|
"epoch": 3.334864684263281,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003908313927863754,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.23498584777116777,
|
|
"num_tokens": 73460948.0,
|
|
"step": 39925
|
|
},
|
|
{
|
|
"entropy": 5.378795099258423,
|
|
"epoch": 3.335282325425994,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003908058697746707,
|
|
"loss": 4.5709,
|
|
"mean_token_accuracy": 0.25181925892829893,
|
|
"num_tokens": 73470189.0,
|
|
"step": 39930
|
|
},
|
|
{
|
|
"entropy": 5.429438591003418,
|
|
"epoch": 3.335699966588707,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000390780344735645,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.23610174357891084,
|
|
"num_tokens": 73478671.0,
|
|
"step": 39935
|
|
},
|
|
{
|
|
"entropy": 5.50475697517395,
|
|
"epoch": 3.33611760775142,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003907548176697449,
|
|
"loss": 4.6579,
|
|
"mean_token_accuracy": 0.23589808195829393,
|
|
"num_tokens": 73487195.0,
|
|
"step": 39940
|
|
},
|
|
{
|
|
"entropy": 5.500997734069824,
|
|
"epoch": 3.336535248914133,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003907292885774175,
|
|
"loss": 4.7045,
|
|
"mean_token_accuracy": 0.23679010272026063,
|
|
"num_tokens": 73497044.0,
|
|
"step": 39945
|
|
},
|
|
{
|
|
"entropy": 5.4273459911346436,
|
|
"epoch": 3.336952890076846,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003907037574591095,
|
|
"loss": 4.6318,
|
|
"mean_token_accuracy": 0.24363055527210237,
|
|
"num_tokens": 73506467.0,
|
|
"step": 39950
|
|
},
|
|
{
|
|
"entropy": 5.501232719421386,
|
|
"epoch": 3.337370531239559,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003906782243152679,
|
|
"loss": 4.7548,
|
|
"mean_token_accuracy": 0.2356028825044632,
|
|
"num_tokens": 73515871.0,
|
|
"step": 39955
|
|
},
|
|
{
|
|
"entropy": 5.5560441493988035,
|
|
"epoch": 3.3377881724022718,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003906526891463398,
|
|
"loss": 4.818,
|
|
"mean_token_accuracy": 0.22597941607236863,
|
|
"num_tokens": 73525107.0,
|
|
"step": 39960
|
|
},
|
|
{
|
|
"entropy": 5.574735164642334,
|
|
"epoch": 3.338205813564985,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00039062715195277214,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.23033026307821275,
|
|
"num_tokens": 73534423.0,
|
|
"step": 39965
|
|
},
|
|
{
|
|
"entropy": 5.480434083938599,
|
|
"epoch": 3.338623454727698,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00039060161273501206,
|
|
"loss": 4.6997,
|
|
"mean_token_accuracy": 0.23431163281202316,
|
|
"num_tokens": 73543248.0,
|
|
"step": 39970
|
|
},
|
|
{
|
|
"entropy": 5.393492364883423,
|
|
"epoch": 3.339041095890411,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003905760714935066,
|
|
"loss": 4.6873,
|
|
"mean_token_accuracy": 0.23622130155563353,
|
|
"num_tokens": 73551915.0,
|
|
"step": 39975
|
|
},
|
|
{
|
|
"entropy": 5.451430416107177,
|
|
"epoch": 3.339458737053124,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003905505282287028,
|
|
"loss": 4.6392,
|
|
"mean_token_accuracy": 0.2388880580663681,
|
|
"num_tokens": 73560271.0,
|
|
"step": 39980
|
|
},
|
|
{
|
|
"entropy": 5.561818075180054,
|
|
"epoch": 3.3398763782158367,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000390524982941048,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.22160648107528685,
|
|
"num_tokens": 73569813.0,
|
|
"step": 39985
|
|
},
|
|
{
|
|
"entropy": 5.545888233184814,
|
|
"epoch": 3.34029401937855,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003904994356309893,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.24143754839897155,
|
|
"num_tokens": 73578311.0,
|
|
"step": 39990
|
|
},
|
|
{
|
|
"entropy": 5.469626188278198,
|
|
"epoch": 3.340711660541263,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039047388629897395,
|
|
"loss": 4.6539,
|
|
"mean_token_accuracy": 0.24060144871473313,
|
|
"num_tokens": 73586548.0,
|
|
"step": 39995
|
|
},
|
|
{
|
|
"entropy": 5.440975189208984,
|
|
"epoch": 3.341129301703976,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039044833494544925,
|
|
"loss": 4.6725,
|
|
"mean_token_accuracy": 0.24107526987791061,
|
|
"num_tokens": 73595859.0,
|
|
"step": 40000
|
|
},
|
|
{
|
|
"entropy": 5.428524589538574,
|
|
"epoch": 3.341546942866689,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003904227815708624,
|
|
"loss": 4.6775,
|
|
"mean_token_accuracy": 0.23592974692583085,
|
|
"num_tokens": 73605386.0,
|
|
"step": 40005
|
|
},
|
|
{
|
|
"entropy": 5.5405394554138185,
|
|
"epoch": 3.341964584029402,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003903972261756609,
|
|
"loss": 4.8422,
|
|
"mean_token_accuracy": 0.22350018918514253,
|
|
"num_tokens": 73615316.0,
|
|
"step": 40010
|
|
},
|
|
{
|
|
"entropy": 5.487039422988891,
|
|
"epoch": 3.342382225192115,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000390371668760292,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.23455095440149307,
|
|
"num_tokens": 73624891.0,
|
|
"step": 40015
|
|
},
|
|
{
|
|
"entropy": 5.502807998657227,
|
|
"epoch": 3.342799866354828,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003903461093252032,
|
|
"loss": 4.7293,
|
|
"mean_token_accuracy": 0.2313358947634697,
|
|
"num_tokens": 73634549.0,
|
|
"step": 40020
|
|
},
|
|
{
|
|
"entropy": 5.4154472827911375,
|
|
"epoch": 3.343217507517541,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003903205478708419,
|
|
"loss": 4.5874,
|
|
"mean_token_accuracy": 0.24324357360601426,
|
|
"num_tokens": 73642835.0,
|
|
"step": 40025
|
|
},
|
|
{
|
|
"entropy": 5.48284215927124,
|
|
"epoch": 3.343635148680254,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003902949843976556,
|
|
"loss": 4.7054,
|
|
"mean_token_accuracy": 0.23385453671216966,
|
|
"num_tokens": 73651835.0,
|
|
"step": 40030
|
|
},
|
|
{
|
|
"entropy": 5.458874940872192,
|
|
"epoch": 3.344052789842967,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039026941890609184,
|
|
"loss": 4.7013,
|
|
"mean_token_accuracy": 0.2306578651070595,
|
|
"num_tokens": 73660452.0,
|
|
"step": 40035
|
|
},
|
|
{
|
|
"entropy": 5.551187896728516,
|
|
"epoch": 3.34447043100568,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003902438513965981,
|
|
"loss": 4.758,
|
|
"mean_token_accuracy": 0.23284768164157868,
|
|
"num_tokens": 73669774.0,
|
|
"step": 40040
|
|
},
|
|
{
|
|
"entropy": 5.518681287765503,
|
|
"epoch": 3.344888072168393,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039021828186962205,
|
|
"loss": 4.7318,
|
|
"mean_token_accuracy": 0.23859765231609345,
|
|
"num_tokens": 73679100.0,
|
|
"step": 40045
|
|
},
|
|
{
|
|
"entropy": 5.429141855239868,
|
|
"epoch": 3.345305713331106,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003901927103256113,
|
|
"loss": 4.6948,
|
|
"mean_token_accuracy": 0.23460640162229537,
|
|
"num_tokens": 73688150.0,
|
|
"step": 40050
|
|
},
|
|
{
|
|
"entropy": 5.4686487197875975,
|
|
"epoch": 3.3457233544938187,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003901671367650135,
|
|
"loss": 4.7005,
|
|
"mean_token_accuracy": 0.23251091986894606,
|
|
"num_tokens": 73697780.0,
|
|
"step": 40055
|
|
},
|
|
{
|
|
"entropy": 5.479606294631958,
|
|
"epoch": 3.346140995656532,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003901415611882764,
|
|
"loss": 4.7123,
|
|
"mean_token_accuracy": 0.2396278664469719,
|
|
"num_tokens": 73707094.0,
|
|
"step": 40060
|
|
},
|
|
{
|
|
"entropy": 5.479920816421509,
|
|
"epoch": 3.346558636819245,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003901159835958475,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.23443174213171006,
|
|
"num_tokens": 73716051.0,
|
|
"step": 40065
|
|
},
|
|
{
|
|
"entropy": 5.441340065002441,
|
|
"epoch": 3.346976277981958,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003900904039881749,
|
|
"loss": 4.6949,
|
|
"mean_token_accuracy": 0.2321060225367546,
|
|
"num_tokens": 73724254.0,
|
|
"step": 40070
|
|
},
|
|
{
|
|
"entropy": 5.509946060180664,
|
|
"epoch": 3.347393919144671,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003900648223657062,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.23318209052085875,
|
|
"num_tokens": 73734174.0,
|
|
"step": 40075
|
|
},
|
|
{
|
|
"entropy": 5.499000167846679,
|
|
"epoch": 3.3478115603073837,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003900392387288893,
|
|
"loss": 4.7247,
|
|
"mean_token_accuracy": 0.23644638657569886,
|
|
"num_tokens": 73743086.0,
|
|
"step": 40080
|
|
},
|
|
{
|
|
"entropy": 5.356153440475464,
|
|
"epoch": 3.348229201470097,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00039001365307817203,
|
|
"loss": 4.6008,
|
|
"mean_token_accuracy": 0.23495132178068162,
|
|
"num_tokens": 73751791.0,
|
|
"step": 40085
|
|
},
|
|
{
|
|
"entropy": 5.47331280708313,
|
|
"epoch": 3.3486468426328098,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038998806541400236,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.23697649538517,
|
|
"num_tokens": 73761816.0,
|
|
"step": 40090
|
|
},
|
|
{
|
|
"entropy": 5.5357414245605465,
|
|
"epoch": 3.349064483795523,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003899624757368282,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.22892782986164092,
|
|
"num_tokens": 73770734.0,
|
|
"step": 40095
|
|
},
|
|
{
|
|
"entropy": 5.483790731430053,
|
|
"epoch": 3.349482124958236,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003899368840470974,
|
|
"loss": 4.6905,
|
|
"mean_token_accuracy": 0.22554484754800797,
|
|
"num_tokens": 73780595.0,
|
|
"step": 40100
|
|
},
|
|
{
|
|
"entropy": 5.479296445846558,
|
|
"epoch": 3.3498997661209486,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003899112903452582,
|
|
"loss": 4.6771,
|
|
"mean_token_accuracy": 0.23519657850265502,
|
|
"num_tokens": 73790542.0,
|
|
"step": 40105
|
|
},
|
|
{
|
|
"entropy": 5.508192300796509,
|
|
"epoch": 3.350317407283662,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038988569463175844,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.22703785300254822,
|
|
"num_tokens": 73800529.0,
|
|
"step": 40110
|
|
},
|
|
{
|
|
"entropy": 5.531595039367676,
|
|
"epoch": 3.3507350484463747,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00038986009690704647,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.2266052931547165,
|
|
"num_tokens": 73809962.0,
|
|
"step": 40115
|
|
},
|
|
{
|
|
"entropy": 5.499731826782226,
|
|
"epoch": 3.351152689609088,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003898344971715701,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.23771753460168837,
|
|
"num_tokens": 73819159.0,
|
|
"step": 40120
|
|
},
|
|
{
|
|
"entropy": 5.417827367782593,
|
|
"epoch": 3.3515703307718008,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038980889542577775,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.23888305723667144,
|
|
"num_tokens": 73827835.0,
|
|
"step": 40125
|
|
},
|
|
{
|
|
"entropy": 5.487789297103882,
|
|
"epoch": 3.351987971934514,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038978329167011747,
|
|
"loss": 4.7466,
|
|
"mean_token_accuracy": 0.23335584104061127,
|
|
"num_tokens": 73837075.0,
|
|
"step": 40130
|
|
},
|
|
{
|
|
"entropy": 5.479140996932983,
|
|
"epoch": 3.352405613097227,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038975768590503743,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.23057546317577363,
|
|
"num_tokens": 73846487.0,
|
|
"step": 40135
|
|
},
|
|
{
|
|
"entropy": 5.497602748870849,
|
|
"epoch": 3.35282325425994,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038973207813098606,
|
|
"loss": 4.8419,
|
|
"mean_token_accuracy": 0.22412729859352112,
|
|
"num_tokens": 73855660.0,
|
|
"step": 40140
|
|
},
|
|
{
|
|
"entropy": 5.517558956146241,
|
|
"epoch": 3.353240895422653,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00038970646834841146,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.23236361443996428,
|
|
"num_tokens": 73865479.0,
|
|
"step": 40145
|
|
},
|
|
{
|
|
"entropy": 5.505494451522827,
|
|
"epoch": 3.3536585365853657,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003896808565577621,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.23264161199331285,
|
|
"num_tokens": 73873715.0,
|
|
"step": 40150
|
|
},
|
|
{
|
|
"entropy": 5.444678592681885,
|
|
"epoch": 3.354076177748079,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038965524275948627,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.235948383808136,
|
|
"num_tokens": 73882285.0,
|
|
"step": 40155
|
|
},
|
|
{
|
|
"entropy": 5.480387115478516,
|
|
"epoch": 3.354493818910792,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003896296269540325,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.2280281215906143,
|
|
"num_tokens": 73891586.0,
|
|
"step": 40160
|
|
},
|
|
{
|
|
"entropy": 5.527423477172851,
|
|
"epoch": 3.354911460073505,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000389604009141849,
|
|
"loss": 4.791,
|
|
"mean_token_accuracy": 0.23543980121612548,
|
|
"num_tokens": 73901150.0,
|
|
"step": 40165
|
|
},
|
|
{
|
|
"entropy": 5.475039386749268,
|
|
"epoch": 3.355329101236218,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003895783893233845,
|
|
"loss": 4.6413,
|
|
"mean_token_accuracy": 0.2381816878914833,
|
|
"num_tokens": 73910060.0,
|
|
"step": 40170
|
|
},
|
|
{
|
|
"entropy": 5.437959289550781,
|
|
"epoch": 3.3557467423989307,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003895527674990872,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.2427053451538086,
|
|
"num_tokens": 73920084.0,
|
|
"step": 40175
|
|
},
|
|
{
|
|
"entropy": 5.5148200511932375,
|
|
"epoch": 3.356164383561644,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000389527143669406,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.2340444579720497,
|
|
"num_tokens": 73929950.0,
|
|
"step": 40180
|
|
},
|
|
{
|
|
"entropy": 5.525362873077393,
|
|
"epoch": 3.3565820247243567,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00038950151783478926,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.23609910607337953,
|
|
"num_tokens": 73938133.0,
|
|
"step": 40185
|
|
},
|
|
{
|
|
"entropy": 5.514832353591919,
|
|
"epoch": 3.35699966588707,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003894758899956856,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.23381970971822738,
|
|
"num_tokens": 73947321.0,
|
|
"step": 40190
|
|
},
|
|
{
|
|
"entropy": 5.450031566619873,
|
|
"epoch": 3.357417307049783,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003894502601525437,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.23125717639923096,
|
|
"num_tokens": 73956032.0,
|
|
"step": 40195
|
|
},
|
|
{
|
|
"entropy": 5.490027856826782,
|
|
"epoch": 3.3578349482124956,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003894246283058122,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.22760366201400756,
|
|
"num_tokens": 73964362.0,
|
|
"step": 40200
|
|
},
|
|
{
|
|
"entropy": 5.471793222427368,
|
|
"epoch": 3.358252589375209,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038939899445593985,
|
|
"loss": 4.6775,
|
|
"mean_token_accuracy": 0.2365680977702141,
|
|
"num_tokens": 73973925.0,
|
|
"step": 40205
|
|
},
|
|
{
|
|
"entropy": 5.472500419616699,
|
|
"epoch": 3.3586702305379217,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038937335860337533,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.2355281352996826,
|
|
"num_tokens": 73983061.0,
|
|
"step": 40210
|
|
},
|
|
{
|
|
"entropy": 5.501217365264893,
|
|
"epoch": 3.359087871700635,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038934772074856766,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.23537162095308303,
|
|
"num_tokens": 73992809.0,
|
|
"step": 40215
|
|
},
|
|
{
|
|
"entropy": 5.468585968017578,
|
|
"epoch": 3.3595055128633478,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038932208089196543,
|
|
"loss": 4.6602,
|
|
"mean_token_accuracy": 0.23596283346414565,
|
|
"num_tokens": 74001969.0,
|
|
"step": 40220
|
|
},
|
|
{
|
|
"entropy": 5.387649345397949,
|
|
"epoch": 3.3599231540260606,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003892964390340175,
|
|
"loss": 4.5635,
|
|
"mean_token_accuracy": 0.24843831807374955,
|
|
"num_tokens": 74010796.0,
|
|
"step": 40225
|
|
},
|
|
{
|
|
"entropy": 5.536927986145019,
|
|
"epoch": 3.360340795188774,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038927079517517293,
|
|
"loss": 4.7509,
|
|
"mean_token_accuracy": 0.2286088526248932,
|
|
"num_tokens": 74020392.0,
|
|
"step": 40230
|
|
},
|
|
{
|
|
"entropy": 5.487853002548218,
|
|
"epoch": 3.3607584363514866,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003892451493158805,
|
|
"loss": 4.7027,
|
|
"mean_token_accuracy": 0.23402426540851592,
|
|
"num_tokens": 74029268.0,
|
|
"step": 40235
|
|
},
|
|
{
|
|
"entropy": 5.457525968551636,
|
|
"epoch": 3.3611760775142,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038921950145658925,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.24128998070955276,
|
|
"num_tokens": 74039226.0,
|
|
"step": 40240
|
|
},
|
|
{
|
|
"entropy": 5.461601638793946,
|
|
"epoch": 3.3615937186769127,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000389193851597748,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.2357760861515999,
|
|
"num_tokens": 74048545.0,
|
|
"step": 40245
|
|
},
|
|
{
|
|
"entropy": 5.466654443740845,
|
|
"epoch": 3.362011359839626,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038916819973980614,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.24417046457529068,
|
|
"num_tokens": 74056799.0,
|
|
"step": 40250
|
|
},
|
|
{
|
|
"entropy": 5.510908079147339,
|
|
"epoch": 3.3624290010023388,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003891425458832123,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.2279062271118164,
|
|
"num_tokens": 74065465.0,
|
|
"step": 40255
|
|
},
|
|
{
|
|
"entropy": 5.452146387100219,
|
|
"epoch": 3.362846642165052,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000389116890028416,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.24212704002857208,
|
|
"num_tokens": 74075047.0,
|
|
"step": 40260
|
|
},
|
|
{
|
|
"entropy": 5.457481431961059,
|
|
"epoch": 3.363264283327765,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000389091232175866,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.23485575914382933,
|
|
"num_tokens": 74084578.0,
|
|
"step": 40265
|
|
},
|
|
{
|
|
"entropy": 5.428902101516724,
|
|
"epoch": 3.3636819244904776,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038906557232601174,
|
|
"loss": 4.7095,
|
|
"mean_token_accuracy": 0.2454381361603737,
|
|
"num_tokens": 74092674.0,
|
|
"step": 40270
|
|
},
|
|
{
|
|
"entropy": 5.529236888885498,
|
|
"epoch": 3.364099565653191,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003890399104793024,
|
|
"loss": 4.8445,
|
|
"mean_token_accuracy": 0.2228476658463478,
|
|
"num_tokens": 74101194.0,
|
|
"step": 40275
|
|
},
|
|
{
|
|
"entropy": 5.5626929759979244,
|
|
"epoch": 3.3645172068159037,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003890142466361871,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.2274393066763878,
|
|
"num_tokens": 74110737.0,
|
|
"step": 40280
|
|
},
|
|
{
|
|
"entropy": 5.456711530685425,
|
|
"epoch": 3.364934847978617,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003889885807971151,
|
|
"loss": 4.6487,
|
|
"mean_token_accuracy": 0.24841429889202118,
|
|
"num_tokens": 74121153.0,
|
|
"step": 40285
|
|
},
|
|
{
|
|
"entropy": 5.510691547393799,
|
|
"epoch": 3.36535248914133,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003889629129625359,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.22263247668743133,
|
|
"num_tokens": 74129978.0,
|
|
"step": 40290
|
|
},
|
|
{
|
|
"entropy": 5.477785921096801,
|
|
"epoch": 3.3657701303040426,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00038893724313289864,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.23804209530353546,
|
|
"num_tokens": 74138121.0,
|
|
"step": 40295
|
|
},
|
|
{
|
|
"entropy": 5.516468095779419,
|
|
"epoch": 3.366187771466756,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003889115713086528,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.23316097408533096,
|
|
"num_tokens": 74149117.0,
|
|
"step": 40300
|
|
},
|
|
{
|
|
"entropy": 5.470359373092651,
|
|
"epoch": 3.3666054126294687,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003888858974902478,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.23713216483592986,
|
|
"num_tokens": 74157531.0,
|
|
"step": 40305
|
|
},
|
|
{
|
|
"entropy": 5.538983106613159,
|
|
"epoch": 3.367023053792182,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003888602216781331,
|
|
"loss": 4.7018,
|
|
"mean_token_accuracy": 0.2347544327378273,
|
|
"num_tokens": 74166913.0,
|
|
"step": 40310
|
|
},
|
|
{
|
|
"entropy": 5.535469436645508,
|
|
"epoch": 3.3674406949548947,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003888345438727582,
|
|
"loss": 4.8298,
|
|
"mean_token_accuracy": 0.2305179551243782,
|
|
"num_tokens": 74176428.0,
|
|
"step": 40315
|
|
},
|
|
{
|
|
"entropy": 5.454302263259888,
|
|
"epoch": 3.3678583361176075,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003888088640745725,
|
|
"loss": 4.6547,
|
|
"mean_token_accuracy": 0.23933240175247192,
|
|
"num_tokens": 74185137.0,
|
|
"step": 40320
|
|
},
|
|
{
|
|
"entropy": 5.452274131774902,
|
|
"epoch": 3.368275977280321,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038878318228402573,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.22448290288448333,
|
|
"num_tokens": 74194717.0,
|
|
"step": 40325
|
|
},
|
|
{
|
|
"entropy": 5.467312288284302,
|
|
"epoch": 3.3686936184430336,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038875749850156733,
|
|
"loss": 4.7198,
|
|
"mean_token_accuracy": 0.2348976954817772,
|
|
"num_tokens": 74203000.0,
|
|
"step": 40330
|
|
},
|
|
{
|
|
"entropy": 5.482615566253662,
|
|
"epoch": 3.369111259605747,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000388731812727647,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.23464449793100356,
|
|
"num_tokens": 74212067.0,
|
|
"step": 40335
|
|
},
|
|
{
|
|
"entropy": 5.558980321884155,
|
|
"epoch": 3.3695289007684597,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003887061249627144,
|
|
"loss": 4.8886,
|
|
"mean_token_accuracy": 0.22549363374710082,
|
|
"num_tokens": 74221244.0,
|
|
"step": 40340
|
|
},
|
|
{
|
|
"entropy": 5.533004665374756,
|
|
"epoch": 3.3699465419311725,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003886804352072192,
|
|
"loss": 4.743,
|
|
"mean_token_accuracy": 0.23312871605157853,
|
|
"num_tokens": 74229786.0,
|
|
"step": 40345
|
|
},
|
|
{
|
|
"entropy": 5.50057463645935,
|
|
"epoch": 3.3703641830938857,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038865474346161117,
|
|
"loss": 4.7058,
|
|
"mean_token_accuracy": 0.24299941062927247,
|
|
"num_tokens": 74239455.0,
|
|
"step": 40350
|
|
},
|
|
{
|
|
"entropy": 5.6222466945648195,
|
|
"epoch": 3.3707818242565986,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038862904972634005,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.22619061768054963,
|
|
"num_tokens": 74247883.0,
|
|
"step": 40355
|
|
},
|
|
{
|
|
"entropy": 5.475457000732422,
|
|
"epoch": 3.371199465419312,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003886033540018556,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.24112705737352372,
|
|
"num_tokens": 74256881.0,
|
|
"step": 40360
|
|
},
|
|
{
|
|
"entropy": 5.3940825939178465,
|
|
"epoch": 3.3716171065820246,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038857765628860774,
|
|
"loss": 4.7129,
|
|
"mean_token_accuracy": 0.23685650825500487,
|
|
"num_tokens": 74266681.0,
|
|
"step": 40365
|
|
},
|
|
{
|
|
"entropy": 5.4960315227508545,
|
|
"epoch": 3.372034747744738,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003885519565870463,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.23636338710784913,
|
|
"num_tokens": 74275965.0,
|
|
"step": 40370
|
|
},
|
|
{
|
|
"entropy": 5.547529792785644,
|
|
"epoch": 3.3724523889074507,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038852625489762117,
|
|
"loss": 4.8285,
|
|
"mean_token_accuracy": 0.2217171832919121,
|
|
"num_tokens": 74285334.0,
|
|
"step": 40375
|
|
},
|
|
{
|
|
"entropy": 5.564292764663696,
|
|
"epoch": 3.372870030070164,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003885005512207822,
|
|
"loss": 4.7387,
|
|
"mean_token_accuracy": 0.23189263492822648,
|
|
"num_tokens": 74294697.0,
|
|
"step": 40380
|
|
},
|
|
{
|
|
"entropy": 5.520218992233277,
|
|
"epoch": 3.3732876712328768,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003884748455569796,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.228842531144619,
|
|
"num_tokens": 74303323.0,
|
|
"step": 40385
|
|
},
|
|
{
|
|
"entropy": 5.513851499557495,
|
|
"epoch": 3.3737053123955896,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038844913790666316,
|
|
"loss": 4.7044,
|
|
"mean_token_accuracy": 0.22967162430286409,
|
|
"num_tokens": 74312871.0,
|
|
"step": 40390
|
|
},
|
|
{
|
|
"entropy": 5.472086620330811,
|
|
"epoch": 3.374122953558303,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000388423428270283,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.23031648397445678,
|
|
"num_tokens": 74322352.0,
|
|
"step": 40395
|
|
},
|
|
{
|
|
"entropy": 5.50903582572937,
|
|
"epoch": 3.3745405947210156,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038839771664828923,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.23106449097394943,
|
|
"num_tokens": 74331225.0,
|
|
"step": 40400
|
|
},
|
|
{
|
|
"entropy": 5.467876529693603,
|
|
"epoch": 3.374958235883729,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003883720030411319,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.23418703377246858,
|
|
"num_tokens": 74340481.0,
|
|
"step": 40405
|
|
},
|
|
{
|
|
"entropy": 5.474708461761475,
|
|
"epoch": 3.3753758770464417,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038834628744926125,
|
|
"loss": 4.7481,
|
|
"mean_token_accuracy": 0.23331342339515687,
|
|
"num_tokens": 74350112.0,
|
|
"step": 40410
|
|
},
|
|
{
|
|
"entropy": 5.515647745132446,
|
|
"epoch": 3.3757935182091545,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038832056987312736,
|
|
"loss": 4.7481,
|
|
"mean_token_accuracy": 0.23053040206432343,
|
|
"num_tokens": 74359225.0,
|
|
"step": 40415
|
|
},
|
|
{
|
|
"entropy": 5.470760297775269,
|
|
"epoch": 3.3762111593718678,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038829485031318046,
|
|
"loss": 4.678,
|
|
"mean_token_accuracy": 0.23418441861867906,
|
|
"num_tokens": 74368274.0,
|
|
"step": 40420
|
|
},
|
|
{
|
|
"entropy": 5.498305177688598,
|
|
"epoch": 3.3766288005345806,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003882691287698709,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.237765534222126,
|
|
"num_tokens": 74377314.0,
|
|
"step": 40425
|
|
},
|
|
{
|
|
"entropy": 5.470293092727661,
|
|
"epoch": 3.377046441697294,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003882434052436489,
|
|
"loss": 4.6528,
|
|
"mean_token_accuracy": 0.2379698023200035,
|
|
"num_tokens": 74386504.0,
|
|
"step": 40430
|
|
},
|
|
{
|
|
"entropy": 5.475039434432984,
|
|
"epoch": 3.3774640828600067,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038821767973496477,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.2332513988018036,
|
|
"num_tokens": 74394678.0,
|
|
"step": 40435
|
|
},
|
|
{
|
|
"entropy": 5.467329263687134,
|
|
"epoch": 3.3778817240227195,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003881919522442688,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.22931118905544282,
|
|
"num_tokens": 74404566.0,
|
|
"step": 40440
|
|
},
|
|
{
|
|
"entropy": 5.461996269226074,
|
|
"epoch": 3.3782993651854327,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038816622277201157,
|
|
"loss": 4.6696,
|
|
"mean_token_accuracy": 0.23572738319635392,
|
|
"num_tokens": 74413155.0,
|
|
"step": 40445
|
|
},
|
|
{
|
|
"entropy": 5.4752223014831545,
|
|
"epoch": 3.3787170063481455,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038814049131864325,
|
|
"loss": 4.7406,
|
|
"mean_token_accuracy": 0.23828036040067674,
|
|
"num_tokens": 74422001.0,
|
|
"step": 40450
|
|
},
|
|
{
|
|
"entropy": 5.458369970321655,
|
|
"epoch": 3.379134647510859,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003881147578846146,
|
|
"loss": 4.6544,
|
|
"mean_token_accuracy": 0.24144160896539688,
|
|
"num_tokens": 74431418.0,
|
|
"step": 40455
|
|
},
|
|
{
|
|
"entropy": 5.4763490676879885,
|
|
"epoch": 3.3795522886735716,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003880890224703758,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.2392924517393112,
|
|
"num_tokens": 74441324.0,
|
|
"step": 40460
|
|
},
|
|
{
|
|
"entropy": 5.499477767944336,
|
|
"epoch": 3.3799699298362844,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003880632850763777,
|
|
"loss": 4.7559,
|
|
"mean_token_accuracy": 0.2280257135629654,
|
|
"num_tokens": 74450743.0,
|
|
"step": 40465
|
|
},
|
|
{
|
|
"entropy": 5.54218316078186,
|
|
"epoch": 3.3803875709989977,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038803754570307066,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.22082261890172958,
|
|
"num_tokens": 74459928.0,
|
|
"step": 40470
|
|
},
|
|
{
|
|
"entropy": 5.6167130947113035,
|
|
"epoch": 3.3808052121617105,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003880118043509052,
|
|
"loss": 4.8793,
|
|
"mean_token_accuracy": 0.21811956018209458,
|
|
"num_tokens": 74470263.0,
|
|
"step": 40475
|
|
},
|
|
{
|
|
"entropy": 5.593740701675415,
|
|
"epoch": 3.3812228533244237,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003879860610203322,
|
|
"loss": 4.862,
|
|
"mean_token_accuracy": 0.21715729534626008,
|
|
"num_tokens": 74480538.0,
|
|
"step": 40480
|
|
},
|
|
{
|
|
"entropy": 5.563553047180176,
|
|
"epoch": 3.3816404944871366,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038796031571180215,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.2346315711736679,
|
|
"num_tokens": 74490096.0,
|
|
"step": 40485
|
|
},
|
|
{
|
|
"entropy": 5.517136669158935,
|
|
"epoch": 3.38205813564985,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003879345684257658,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.23219744712114335,
|
|
"num_tokens": 74499803.0,
|
|
"step": 40490
|
|
},
|
|
{
|
|
"entropy": 5.424181127548218,
|
|
"epoch": 3.3824757768125626,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003879088191626739,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.23990704417228698,
|
|
"num_tokens": 74508512.0,
|
|
"step": 40495
|
|
},
|
|
{
|
|
"entropy": 5.425758028030396,
|
|
"epoch": 3.382893417975276,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038788306792297725,
|
|
"loss": 4.6584,
|
|
"mean_token_accuracy": 0.23951442539691925,
|
|
"num_tokens": 74517380.0,
|
|
"step": 40500
|
|
},
|
|
{
|
|
"entropy": 5.467477560043335,
|
|
"epoch": 3.3833110591379887,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003878573147071265,
|
|
"loss": 4.6507,
|
|
"mean_token_accuracy": 0.23319988399744035,
|
|
"num_tokens": 74525876.0,
|
|
"step": 40505
|
|
},
|
|
{
|
|
"entropy": 5.550462532043457,
|
|
"epoch": 3.3837287003007015,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00038783155951557276,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.2343900740146637,
|
|
"num_tokens": 74534741.0,
|
|
"step": 40510
|
|
},
|
|
{
|
|
"entropy": 5.506747150421143,
|
|
"epoch": 3.3841463414634148,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003878058023487666,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.23169123083353044,
|
|
"num_tokens": 74543983.0,
|
|
"step": 40515
|
|
},
|
|
{
|
|
"entropy": 5.518421840667725,
|
|
"epoch": 3.3845639826261276,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003877800432071592,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.22698109596967697,
|
|
"num_tokens": 74553715.0,
|
|
"step": 40520
|
|
},
|
|
{
|
|
"entropy": 5.57361159324646,
|
|
"epoch": 3.384981623788841,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003877542820912014,
|
|
"loss": 4.783,
|
|
"mean_token_accuracy": 0.2294487789273262,
|
|
"num_tokens": 74563012.0,
|
|
"step": 40525
|
|
},
|
|
{
|
|
"entropy": 5.5192540168762205,
|
|
"epoch": 3.3853992649515536,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038772851900134407,
|
|
"loss": 4.731,
|
|
"mean_token_accuracy": 0.23458915203809738,
|
|
"num_tokens": 74571724.0,
|
|
"step": 40530
|
|
},
|
|
{
|
|
"entropy": 5.420488262176514,
|
|
"epoch": 3.3858169061142664,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038770275393803843,
|
|
"loss": 4.6838,
|
|
"mean_token_accuracy": 0.23980321735143661,
|
|
"num_tokens": 74580817.0,
|
|
"step": 40535
|
|
},
|
|
{
|
|
"entropy": 5.559438753128052,
|
|
"epoch": 3.3862345472769797,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00038767698690173535,
|
|
"loss": 4.7665,
|
|
"mean_token_accuracy": 0.23445186018943787,
|
|
"num_tokens": 74590248.0,
|
|
"step": 40540
|
|
},
|
|
{
|
|
"entropy": 5.565570402145386,
|
|
"epoch": 3.3866521884396925,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00038765121789288606,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.23559913486242295,
|
|
"num_tokens": 74599313.0,
|
|
"step": 40545
|
|
},
|
|
{
|
|
"entropy": 5.5687566757202145,
|
|
"epoch": 3.3870698296024058,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003876254469119415,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.22413015216588975,
|
|
"num_tokens": 74609661.0,
|
|
"step": 40550
|
|
},
|
|
{
|
|
"entropy": 5.556348752975464,
|
|
"epoch": 3.3874874707651186,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038759967395935303,
|
|
"loss": 4.8541,
|
|
"mean_token_accuracy": 0.22286543846130372,
|
|
"num_tokens": 74618476.0,
|
|
"step": 40555
|
|
},
|
|
{
|
|
"entropy": 5.389889240264893,
|
|
"epoch": 3.3879051119278314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003875738990355716,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.2362556576728821,
|
|
"num_tokens": 74627586.0,
|
|
"step": 40560
|
|
},
|
|
{
|
|
"entropy": 5.436141872406006,
|
|
"epoch": 3.3883227530905446,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038754812214104867,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.23529633283615112,
|
|
"num_tokens": 74636758.0,
|
|
"step": 40565
|
|
},
|
|
{
|
|
"entropy": 5.4832549571990965,
|
|
"epoch": 3.3887403942532575,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038752234327623535,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.23246921449899674,
|
|
"num_tokens": 74646532.0,
|
|
"step": 40570
|
|
},
|
|
{
|
|
"entropy": 5.474044322967529,
|
|
"epoch": 3.3891580354159707,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038749656244158303,
|
|
"loss": 4.724,
|
|
"mean_token_accuracy": 0.23549934178590776,
|
|
"num_tokens": 74655886.0,
|
|
"step": 40575
|
|
},
|
|
{
|
|
"entropy": 5.459844923019409,
|
|
"epoch": 3.3895756765786835,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038747077963754295,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.23530826717615128,
|
|
"num_tokens": 74665502.0,
|
|
"step": 40580
|
|
},
|
|
{
|
|
"entropy": 5.475061464309692,
|
|
"epoch": 3.389993317741397,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003874449948645664,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.22834802269935608,
|
|
"num_tokens": 74674951.0,
|
|
"step": 40585
|
|
},
|
|
{
|
|
"entropy": 5.514863443374634,
|
|
"epoch": 3.3904109589041096,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003874192081231049,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.22831861227750777,
|
|
"num_tokens": 74684232.0,
|
|
"step": 40590
|
|
},
|
|
{
|
|
"entropy": 5.470242595672607,
|
|
"epoch": 3.3908286000668224,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003873934194136099,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.23677912801504136,
|
|
"num_tokens": 74693653.0,
|
|
"step": 40595
|
|
},
|
|
{
|
|
"entropy": 5.415358543395996,
|
|
"epoch": 3.3912462412295357,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038736762873653273,
|
|
"loss": 4.6767,
|
|
"mean_token_accuracy": 0.23799211531877518,
|
|
"num_tokens": 74702615.0,
|
|
"step": 40600
|
|
},
|
|
{
|
|
"entropy": 5.558140420913697,
|
|
"epoch": 3.3916638823922485,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000387341836092325,
|
|
"loss": 4.7924,
|
|
"mean_token_accuracy": 0.2259046658873558,
|
|
"num_tokens": 74712284.0,
|
|
"step": 40605
|
|
},
|
|
{
|
|
"entropy": 5.518823480606079,
|
|
"epoch": 3.3920815235549617,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00038731604148143826,
|
|
"loss": 4.8168,
|
|
"mean_token_accuracy": 0.2322822853922844,
|
|
"num_tokens": 74721020.0,
|
|
"step": 40610
|
|
},
|
|
{
|
|
"entropy": 5.525398683547974,
|
|
"epoch": 3.3924991647176745,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038729024490432397,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.237575463950634,
|
|
"num_tokens": 74729045.0,
|
|
"step": 40615
|
|
},
|
|
{
|
|
"entropy": 5.46510329246521,
|
|
"epoch": 3.392916805880388,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003872644463614338,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.22695446461439134,
|
|
"num_tokens": 74737576.0,
|
|
"step": 40620
|
|
},
|
|
{
|
|
"entropy": 5.5293010711669925,
|
|
"epoch": 3.3933344470431006,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038723864585321925,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.22807977348566055,
|
|
"num_tokens": 74746867.0,
|
|
"step": 40625
|
|
},
|
|
{
|
|
"entropy": 5.5148458003997805,
|
|
"epoch": 3.3937520882058134,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038721284338013223,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.23377033770084382,
|
|
"num_tokens": 74756979.0,
|
|
"step": 40630
|
|
},
|
|
{
|
|
"entropy": 5.4648768424987795,
|
|
"epoch": 3.3941697293685267,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003871870389426243,
|
|
"loss": 4.6269,
|
|
"mean_token_accuracy": 0.2460362508893013,
|
|
"num_tokens": 74765683.0,
|
|
"step": 40635
|
|
},
|
|
{
|
|
"entropy": 5.535600423812866,
|
|
"epoch": 3.3945873705312395,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038716123254114716,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.2376311868429184,
|
|
"num_tokens": 74774855.0,
|
|
"step": 40640
|
|
},
|
|
{
|
|
"entropy": 5.495233488082886,
|
|
"epoch": 3.3950050116939527,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003871354241761527,
|
|
"loss": 4.6518,
|
|
"mean_token_accuracy": 0.2433789074420929,
|
|
"num_tokens": 74783802.0,
|
|
"step": 40645
|
|
},
|
|
{
|
|
"entropy": 5.497309446334839,
|
|
"epoch": 3.3954226528566656,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038710961384809265,
|
|
"loss": 4.706,
|
|
"mean_token_accuracy": 0.23587658852338791,
|
|
"num_tokens": 74793013.0,
|
|
"step": 40650
|
|
},
|
|
{
|
|
"entropy": 5.452738428115845,
|
|
"epoch": 3.3958402940193784,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003870838015574188,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.23427268713712693,
|
|
"num_tokens": 74802327.0,
|
|
"step": 40655
|
|
},
|
|
{
|
|
"entropy": 5.406690645217895,
|
|
"epoch": 3.3962579351820916,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038705798730458315,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.2398082509636879,
|
|
"num_tokens": 74811485.0,
|
|
"step": 40660
|
|
},
|
|
{
|
|
"entropy": 5.539559984207154,
|
|
"epoch": 3.3966755763448044,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003870321710900375,
|
|
"loss": 4.7817,
|
|
"mean_token_accuracy": 0.22482725232839584,
|
|
"num_tokens": 74820723.0,
|
|
"step": 40665
|
|
},
|
|
{
|
|
"entropy": 5.549021434783936,
|
|
"epoch": 3.3970932175075177,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038700635291423393,
|
|
"loss": 4.7815,
|
|
"mean_token_accuracy": 0.23168458938598632,
|
|
"num_tokens": 74830196.0,
|
|
"step": 40670
|
|
},
|
|
{
|
|
"entropy": 5.45915961265564,
|
|
"epoch": 3.3975108586702305,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00038698053277762425,
|
|
"loss": 4.6653,
|
|
"mean_token_accuracy": 0.2353131353855133,
|
|
"num_tokens": 74839111.0,
|
|
"step": 40675
|
|
},
|
|
{
|
|
"entropy": 5.461059045791626,
|
|
"epoch": 3.3979284998329433,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003869547106806606,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.23340667188167571,
|
|
"num_tokens": 74847762.0,
|
|
"step": 40680
|
|
},
|
|
{
|
|
"entropy": 5.47518892288208,
|
|
"epoch": 3.3983461409956566,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038692888662379487,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.22965105324983598,
|
|
"num_tokens": 74857140.0,
|
|
"step": 40685
|
|
},
|
|
{
|
|
"entropy": 5.510094213485718,
|
|
"epoch": 3.3987637821583694,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038690306060747945,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.23373868316411972,
|
|
"num_tokens": 74866721.0,
|
|
"step": 40690
|
|
},
|
|
{
|
|
"entropy": 5.410952949523926,
|
|
"epoch": 3.3991814233210826,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038687723263216607,
|
|
"loss": 4.6426,
|
|
"mean_token_accuracy": 0.2400531604886055,
|
|
"num_tokens": 74875745.0,
|
|
"step": 40695
|
|
},
|
|
{
|
|
"entropy": 5.4749799251556395,
|
|
"epoch": 3.3995990644837955,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038685140269830717,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.23070984184741974,
|
|
"num_tokens": 74885812.0,
|
|
"step": 40700
|
|
},
|
|
{
|
|
"entropy": 5.565074777603149,
|
|
"epoch": 3.4000167056465087,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003868255708063548,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.23240478634834288,
|
|
"num_tokens": 74895253.0,
|
|
"step": 40705
|
|
},
|
|
{
|
|
"entropy": 5.5395622730255125,
|
|
"epoch": 3.4004343468092215,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038679973695676125,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.2363334208726883,
|
|
"num_tokens": 74904960.0,
|
|
"step": 40710
|
|
},
|
|
{
|
|
"entropy": 5.504366827011109,
|
|
"epoch": 3.4008519879719343,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00038677390114997856,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.23612705767154693,
|
|
"num_tokens": 74913479.0,
|
|
"step": 40715
|
|
},
|
|
{
|
|
"entropy": 5.492042922973633,
|
|
"epoch": 3.4012696291346476,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003867480633864594,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.2256777510046959,
|
|
"num_tokens": 74923209.0,
|
|
"step": 40720
|
|
},
|
|
{
|
|
"entropy": 5.420942211151123,
|
|
"epoch": 3.4016872702973604,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038672222366665577,
|
|
"loss": 4.6223,
|
|
"mean_token_accuracy": 0.24240497648715972,
|
|
"num_tokens": 74932146.0,
|
|
"step": 40725
|
|
},
|
|
{
|
|
"entropy": 5.493741130828857,
|
|
"epoch": 3.4021049114600737,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038669638199102015,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.24296902418136596,
|
|
"num_tokens": 74941011.0,
|
|
"step": 40730
|
|
},
|
|
{
|
|
"entropy": 5.471250724792481,
|
|
"epoch": 3.4025225526227865,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003866705383600049,
|
|
"loss": 4.7046,
|
|
"mean_token_accuracy": 0.23281697183847427,
|
|
"num_tokens": 74949672.0,
|
|
"step": 40735
|
|
},
|
|
{
|
|
"entropy": 5.473683500289917,
|
|
"epoch": 3.4029401937854997,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003866446927740625,
|
|
"loss": 4.7565,
|
|
"mean_token_accuracy": 0.2296840727329254,
|
|
"num_tokens": 74960177.0,
|
|
"step": 40740
|
|
},
|
|
{
|
|
"entropy": 5.495176887512207,
|
|
"epoch": 3.4033578349482125,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038661884523364537,
|
|
"loss": 4.7218,
|
|
"mean_token_accuracy": 0.23930169641971588,
|
|
"num_tokens": 74969667.0,
|
|
"step": 40745
|
|
},
|
|
{
|
|
"entropy": 5.470014333724976,
|
|
"epoch": 3.4037754761109253,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000386592995739206,
|
|
"loss": 4.7615,
|
|
"mean_token_accuracy": 0.2384796440601349,
|
|
"num_tokens": 74979045.0,
|
|
"step": 40750
|
|
},
|
|
{
|
|
"entropy": 5.5207281589508055,
|
|
"epoch": 3.4041931172736386,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038656714429119687,
|
|
"loss": 4.7429,
|
|
"mean_token_accuracy": 0.23578028827905656,
|
|
"num_tokens": 74988020.0,
|
|
"step": 40755
|
|
},
|
|
{
|
|
"entropy": 5.48030195236206,
|
|
"epoch": 3.4046107584363514,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003865412908900706,
|
|
"loss": 4.6632,
|
|
"mean_token_accuracy": 0.23815799057483672,
|
|
"num_tokens": 74997910.0,
|
|
"step": 40760
|
|
},
|
|
{
|
|
"entropy": 5.5095264434814455,
|
|
"epoch": 3.4050283995990647,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038651543553627977,
|
|
"loss": 4.7028,
|
|
"mean_token_accuracy": 0.23049238473176956,
|
|
"num_tokens": 75007866.0,
|
|
"step": 40765
|
|
},
|
|
{
|
|
"entropy": 5.46953821182251,
|
|
"epoch": 3.4054460407617775,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038648957823027703,
|
|
"loss": 4.7051,
|
|
"mean_token_accuracy": 0.2343638524413109,
|
|
"num_tokens": 75016640.0,
|
|
"step": 40770
|
|
},
|
|
{
|
|
"entropy": 5.492036151885986,
|
|
"epoch": 3.4058636819244903,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000386463718972515,
|
|
"loss": 4.7389,
|
|
"mean_token_accuracy": 0.23559556901454926,
|
|
"num_tokens": 75025191.0,
|
|
"step": 40775
|
|
},
|
|
{
|
|
"entropy": 5.486181116104126,
|
|
"epoch": 3.4062813230872035,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003864378577634464,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.23579590171575546,
|
|
"num_tokens": 75034294.0,
|
|
"step": 40780
|
|
},
|
|
{
|
|
"entropy": 5.535371160507202,
|
|
"epoch": 3.4066989642499164,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000386411994603524,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.23168788403272628,
|
|
"num_tokens": 75043124.0,
|
|
"step": 40785
|
|
},
|
|
{
|
|
"entropy": 5.51323938369751,
|
|
"epoch": 3.4071166054126296,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003863861294932005,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.23182280063629152,
|
|
"num_tokens": 75052068.0,
|
|
"step": 40790
|
|
},
|
|
{
|
|
"entropy": 5.448468971252441,
|
|
"epoch": 3.4075342465753424,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003863602624329287,
|
|
"loss": 4.6824,
|
|
"mean_token_accuracy": 0.23019384294748307,
|
|
"num_tokens": 75061349.0,
|
|
"step": 40795
|
|
},
|
|
{
|
|
"entropy": 5.552624893188477,
|
|
"epoch": 3.4079518877380552,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003863343934231615,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.21922612339258193,
|
|
"num_tokens": 75070721.0,
|
|
"step": 40800
|
|
},
|
|
{
|
|
"entropy": 5.54802680015564,
|
|
"epoch": 3.4083695289007685,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003863085224643517,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.23570127338171004,
|
|
"num_tokens": 75079499.0,
|
|
"step": 40805
|
|
},
|
|
{
|
|
"entropy": 5.489724493026733,
|
|
"epoch": 3.4087871700634813,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003862826495569523,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.23354000598192215,
|
|
"num_tokens": 75088815.0,
|
|
"step": 40810
|
|
},
|
|
{
|
|
"entropy": 5.508763599395752,
|
|
"epoch": 3.4092048112261946,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003862567747014161,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.22641623467206956,
|
|
"num_tokens": 75098154.0,
|
|
"step": 40815
|
|
},
|
|
{
|
|
"entropy": 5.4884374141693115,
|
|
"epoch": 3.4096224523889074,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038623089789819616,
|
|
"loss": 4.7261,
|
|
"mean_token_accuracy": 0.23511217385530472,
|
|
"num_tokens": 75108645.0,
|
|
"step": 40820
|
|
},
|
|
{
|
|
"entropy": 5.489882946014404,
|
|
"epoch": 3.4100400935516206,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00038620501914774554,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.231429722905159,
|
|
"num_tokens": 75117191.0,
|
|
"step": 40825
|
|
},
|
|
{
|
|
"entropy": 5.497748184204101,
|
|
"epoch": 3.4104577347143334,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00038617913845051706,
|
|
"loss": 4.6454,
|
|
"mean_token_accuracy": 0.2464768707752228,
|
|
"num_tokens": 75126238.0,
|
|
"step": 40830
|
|
},
|
|
{
|
|
"entropy": 5.548233890533448,
|
|
"epoch": 3.4108753758770463,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00038615325580696396,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.23238458335399628,
|
|
"num_tokens": 75135374.0,
|
|
"step": 40835
|
|
},
|
|
{
|
|
"entropy": 5.54870834350586,
|
|
"epoch": 3.4112930170397595,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00038612737121753945,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.2292412981390953,
|
|
"num_tokens": 75145183.0,
|
|
"step": 40840
|
|
},
|
|
{
|
|
"entropy": 5.417298364639282,
|
|
"epoch": 3.4117106582024723,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003861014846826964,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.23121481388807297,
|
|
"num_tokens": 75153731.0,
|
|
"step": 40845
|
|
},
|
|
{
|
|
"entropy": 5.548677396774292,
|
|
"epoch": 3.4121282993651856,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003860755962028882,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.24007472395896912,
|
|
"num_tokens": 75163028.0,
|
|
"step": 40850
|
|
},
|
|
{
|
|
"entropy": 5.4779078483581545,
|
|
"epoch": 3.4125459405278984,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000386049705778568,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.23448362052440644,
|
|
"num_tokens": 75172703.0,
|
|
"step": 40855
|
|
},
|
|
{
|
|
"entropy": 5.528500890731811,
|
|
"epoch": 3.4129635816906116,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000386023813410189,
|
|
"loss": 4.7641,
|
|
"mean_token_accuracy": 0.23191972374916076,
|
|
"num_tokens": 75182162.0,
|
|
"step": 40860
|
|
},
|
|
{
|
|
"entropy": 5.517830085754395,
|
|
"epoch": 3.4133812228533245,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038599791909820446,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.23934056460857392,
|
|
"num_tokens": 75191134.0,
|
|
"step": 40865
|
|
},
|
|
{
|
|
"entropy": 5.5138438701629635,
|
|
"epoch": 3.4137988640160373,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003859720228430678,
|
|
"loss": 4.7359,
|
|
"mean_token_accuracy": 0.23665618747472764,
|
|
"num_tokens": 75201005.0,
|
|
"step": 40870
|
|
},
|
|
{
|
|
"entropy": 5.477131128311157,
|
|
"epoch": 3.4142165051787505,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00038594612464523236,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.23355268836021423,
|
|
"num_tokens": 75210750.0,
|
|
"step": 40875
|
|
},
|
|
{
|
|
"entropy": 5.546055698394776,
|
|
"epoch": 3.4146341463414633,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003859202245051513,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.2315552592277527,
|
|
"num_tokens": 75219701.0,
|
|
"step": 40880
|
|
},
|
|
{
|
|
"entropy": 5.508479166030884,
|
|
"epoch": 3.4150517875041766,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038589432242327836,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.2335832729935646,
|
|
"num_tokens": 75229589.0,
|
|
"step": 40885
|
|
},
|
|
{
|
|
"entropy": 5.44821195602417,
|
|
"epoch": 3.4154694286668894,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003858684184000667,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.23187347650527954,
|
|
"num_tokens": 75239133.0,
|
|
"step": 40890
|
|
},
|
|
{
|
|
"entropy": 5.544028854370117,
|
|
"epoch": 3.415887069829602,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00038584251243597,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.22814267128705978,
|
|
"num_tokens": 75249208.0,
|
|
"step": 40895
|
|
},
|
|
{
|
|
"entropy": 5.5270764350891115,
|
|
"epoch": 3.4163047109923155,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003858166045314417,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.23375543504953383,
|
|
"num_tokens": 75258395.0,
|
|
"step": 40900
|
|
},
|
|
{
|
|
"entropy": 5.531583213806153,
|
|
"epoch": 3.4167223521550283,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038579069468693526,
|
|
"loss": 4.6808,
|
|
"mean_token_accuracy": 0.23268117010593414,
|
|
"num_tokens": 75267193.0,
|
|
"step": 40905
|
|
},
|
|
{
|
|
"entropy": 5.492617511749268,
|
|
"epoch": 3.4171399933177415,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003857647829029045,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.24423634260892868,
|
|
"num_tokens": 75275464.0,
|
|
"step": 40910
|
|
},
|
|
{
|
|
"entropy": 5.531509160995483,
|
|
"epoch": 3.4175576344804544,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00038573886917980273,
|
|
"loss": 4.701,
|
|
"mean_token_accuracy": 0.23929018676280975,
|
|
"num_tokens": 75284829.0,
|
|
"step": 40915
|
|
},
|
|
{
|
|
"entropy": 5.515756320953369,
|
|
"epoch": 3.417975275643167,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003857129535180839,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.22817417979240417,
|
|
"num_tokens": 75294667.0,
|
|
"step": 40920
|
|
},
|
|
{
|
|
"entropy": 5.486750173568725,
|
|
"epoch": 3.4183929168058804,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003856870359182014,
|
|
"loss": 4.6061,
|
|
"mean_token_accuracy": 0.24631508588790893,
|
|
"num_tokens": 75302587.0,
|
|
"step": 40925
|
|
},
|
|
{
|
|
"entropy": 5.4872194766998295,
|
|
"epoch": 3.4188105579685932,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003856611163806092,
|
|
"loss": 4.6804,
|
|
"mean_token_accuracy": 0.243350288271904,
|
|
"num_tokens": 75310665.0,
|
|
"step": 40930
|
|
},
|
|
{
|
|
"entropy": 5.438107204437256,
|
|
"epoch": 3.4192281991313065,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003856351949057609,
|
|
"loss": 4.6381,
|
|
"mean_token_accuracy": 0.2432625412940979,
|
|
"num_tokens": 75319516.0,
|
|
"step": 40935
|
|
},
|
|
{
|
|
"entropy": 5.465939998626709,
|
|
"epoch": 3.4196458402940193,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003856092714941104,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.23383298069238662,
|
|
"num_tokens": 75330336.0,
|
|
"step": 40940
|
|
},
|
|
{
|
|
"entropy": 5.498766613006592,
|
|
"epoch": 3.4200634814567326,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038558334614611145,
|
|
"loss": 4.7394,
|
|
"mean_token_accuracy": 0.24065001308918,
|
|
"num_tokens": 75340362.0,
|
|
"step": 40945
|
|
},
|
|
{
|
|
"entropy": 5.493540477752686,
|
|
"epoch": 3.4204811226194454,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003855574188622179,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.23763792365789413,
|
|
"num_tokens": 75348976.0,
|
|
"step": 40950
|
|
},
|
|
{
|
|
"entropy": 5.516672945022583,
|
|
"epoch": 3.420898763782158,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003855314896428837,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.22984783500432968,
|
|
"num_tokens": 75358241.0,
|
|
"step": 40955
|
|
},
|
|
{
|
|
"entropy": 5.48380560874939,
|
|
"epoch": 3.4213164049448714,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038550555848856265,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.23751698732376098,
|
|
"num_tokens": 75367395.0,
|
|
"step": 40960
|
|
},
|
|
{
|
|
"entropy": 5.464783763885498,
|
|
"epoch": 3.4217340461075842,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038547962539970884,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.24481746554374695,
|
|
"num_tokens": 75375947.0,
|
|
"step": 40965
|
|
},
|
|
{
|
|
"entropy": 5.542438173294068,
|
|
"epoch": 3.4221516872702975,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003854536903767762,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.23032618016004563,
|
|
"num_tokens": 75385024.0,
|
|
"step": 40970
|
|
},
|
|
{
|
|
"entropy": 5.592589712142944,
|
|
"epoch": 3.4225693284330103,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038542775342021877,
|
|
"loss": 4.8726,
|
|
"mean_token_accuracy": 0.22508650720119477,
|
|
"num_tokens": 75394789.0,
|
|
"step": 40975
|
|
},
|
|
{
|
|
"entropy": 5.531650972366333,
|
|
"epoch": 3.4229869695957236,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003854018145304905,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.23871761709451675,
|
|
"num_tokens": 75403900.0,
|
|
"step": 40980
|
|
},
|
|
{
|
|
"entropy": 5.388091516494751,
|
|
"epoch": 3.4234046107584364,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038537587370804567,
|
|
"loss": 4.6748,
|
|
"mean_token_accuracy": 0.23830363005399705,
|
|
"num_tokens": 75413837.0,
|
|
"step": 40985
|
|
},
|
|
{
|
|
"entropy": 5.478614616394043,
|
|
"epoch": 3.423822251921149,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038534993095333824,
|
|
"loss": 4.7022,
|
|
"mean_token_accuracy": 0.2376261442899704,
|
|
"num_tokens": 75422774.0,
|
|
"step": 40990
|
|
},
|
|
{
|
|
"entropy": 5.398179292678833,
|
|
"epoch": 3.4242398930838625,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003853239862668225,
|
|
"loss": 4.598,
|
|
"mean_token_accuracy": 0.24801224917173387,
|
|
"num_tokens": 75432328.0,
|
|
"step": 40995
|
|
},
|
|
{
|
|
"entropy": 5.4789710521698,
|
|
"epoch": 3.4246575342465753,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003852980396489526,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.231346495449543,
|
|
"num_tokens": 75441845.0,
|
|
"step": 41000
|
|
},
|
|
{
|
|
"entropy": 5.435598373413086,
|
|
"epoch": 3.4250751754092885,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003852720911001827,
|
|
"loss": 4.5622,
|
|
"mean_token_accuracy": 0.24679560363292694,
|
|
"num_tokens": 75450127.0,
|
|
"step": 41005
|
|
},
|
|
{
|
|
"entropy": 5.472331285476685,
|
|
"epoch": 3.4254928165720013,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038524614062096713,
|
|
"loss": 4.6561,
|
|
"mean_token_accuracy": 0.23946455717086793,
|
|
"num_tokens": 75458289.0,
|
|
"step": 41010
|
|
},
|
|
{
|
|
"entropy": 5.55925989151001,
|
|
"epoch": 3.425910457734714,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003852201882117602,
|
|
"loss": 4.7742,
|
|
"mean_token_accuracy": 0.23036331981420516,
|
|
"num_tokens": 75467414.0,
|
|
"step": 41015
|
|
},
|
|
{
|
|
"entropy": 5.489670515060425,
|
|
"epoch": 3.4263280988974274,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00038519423387301617,
|
|
"loss": 4.6767,
|
|
"mean_token_accuracy": 0.2469249188899994,
|
|
"num_tokens": 75476642.0,
|
|
"step": 41020
|
|
},
|
|
{
|
|
"entropy": 5.4786149024963375,
|
|
"epoch": 3.42674574006014,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038516827760518946,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.23094037771224976,
|
|
"num_tokens": 75485982.0,
|
|
"step": 41025
|
|
},
|
|
{
|
|
"entropy": 5.5822985649108885,
|
|
"epoch": 3.4271633812228535,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00038514231940873437,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.2246771991252899,
|
|
"num_tokens": 75494888.0,
|
|
"step": 41030
|
|
},
|
|
{
|
|
"entropy": 5.526914978027344,
|
|
"epoch": 3.4275810223855663,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003851163592841054,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.23411135375499725,
|
|
"num_tokens": 75504530.0,
|
|
"step": 41035
|
|
},
|
|
{
|
|
"entropy": 5.479455184936524,
|
|
"epoch": 3.427998663548279,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003850903972317571,
|
|
"loss": 4.6911,
|
|
"mean_token_accuracy": 0.24200329929590225,
|
|
"num_tokens": 75514302.0,
|
|
"step": 41040
|
|
},
|
|
{
|
|
"entropy": 5.463773727416992,
|
|
"epoch": 3.4284163047109923,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003850644332521438,
|
|
"loss": 4.6076,
|
|
"mean_token_accuracy": 0.24333970695734025,
|
|
"num_tokens": 75523228.0,
|
|
"step": 41045
|
|
},
|
|
{
|
|
"entropy": 5.501096916198731,
|
|
"epoch": 3.428833945873705,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00038503846734572016,
|
|
"loss": 4.7402,
|
|
"mean_token_accuracy": 0.2322509080171585,
|
|
"num_tokens": 75531970.0,
|
|
"step": 41050
|
|
},
|
|
{
|
|
"entropy": 5.488560438156128,
|
|
"epoch": 3.4292515870364184,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038501249951294073,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.23388865143060683,
|
|
"num_tokens": 75542474.0,
|
|
"step": 41055
|
|
},
|
|
{
|
|
"entropy": 5.463098669052124,
|
|
"epoch": 3.4296692281991312,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038498652975426,
|
|
"loss": 4.728,
|
|
"mean_token_accuracy": 0.23124055415391923,
|
|
"num_tokens": 75552627.0,
|
|
"step": 41060
|
|
},
|
|
{
|
|
"entropy": 5.58591103553772,
|
|
"epoch": 3.4300868693618445,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003849605580701327,
|
|
"loss": 4.788,
|
|
"mean_token_accuracy": 0.2353829026222229,
|
|
"num_tokens": 75562376.0,
|
|
"step": 41065
|
|
},
|
|
{
|
|
"entropy": 5.506361389160157,
|
|
"epoch": 3.4305045105245573,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003849345844610135,
|
|
"loss": 4.7186,
|
|
"mean_token_accuracy": 0.24282922744750976,
|
|
"num_tokens": 75570834.0,
|
|
"step": 41070
|
|
},
|
|
{
|
|
"entropy": 5.464494371414185,
|
|
"epoch": 3.43092215168727,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000384908608927357,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.2448809787631035,
|
|
"num_tokens": 75578732.0,
|
|
"step": 41075
|
|
},
|
|
{
|
|
"entropy": 5.469191455841065,
|
|
"epoch": 3.4313397928499834,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038488263146961815,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.22686725556850434,
|
|
"num_tokens": 75588670.0,
|
|
"step": 41080
|
|
},
|
|
{
|
|
"entropy": 5.536278343200683,
|
|
"epoch": 3.431757434012696,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038485665208825144,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.23078480511903762,
|
|
"num_tokens": 75598473.0,
|
|
"step": 41085
|
|
},
|
|
{
|
|
"entropy": 5.516586112976074,
|
|
"epoch": 3.4321750751754094,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003848306707837118,
|
|
"loss": 4.6926,
|
|
"mean_token_accuracy": 0.23754545748233796,
|
|
"num_tokens": 75607318.0,
|
|
"step": 41090
|
|
},
|
|
{
|
|
"entropy": 5.3928731918334964,
|
|
"epoch": 3.4325927163381222,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003848046875564541,
|
|
"loss": 4.6343,
|
|
"mean_token_accuracy": 0.2441328287124634,
|
|
"num_tokens": 75617042.0,
|
|
"step": 41095
|
|
},
|
|
{
|
|
"entropy": 5.3779058933258055,
|
|
"epoch": 3.4330103575008355,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003847787024069332,
|
|
"loss": 4.5645,
|
|
"mean_token_accuracy": 0.2370395392179489,
|
|
"num_tokens": 75625697.0,
|
|
"step": 41100
|
|
},
|
|
{
|
|
"entropy": 5.503213262557983,
|
|
"epoch": 3.4334279986635483,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000384752715335604,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.2328705981373787,
|
|
"num_tokens": 75634610.0,
|
|
"step": 41105
|
|
},
|
|
{
|
|
"entropy": 5.502335119247436,
|
|
"epoch": 3.433845639826261,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038472672634292125,
|
|
"loss": 4.6515,
|
|
"mean_token_accuracy": 0.23903235346078872,
|
|
"num_tokens": 75643719.0,
|
|
"step": 41110
|
|
},
|
|
{
|
|
"entropy": 5.483623790740967,
|
|
"epoch": 3.4342632809889744,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003847007354293402,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.23136792182922364,
|
|
"num_tokens": 75653149.0,
|
|
"step": 41115
|
|
},
|
|
{
|
|
"entropy": 5.471936559677124,
|
|
"epoch": 3.434680922151687,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003846747425953157,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.23359447568655015,
|
|
"num_tokens": 75662197.0,
|
|
"step": 41120
|
|
},
|
|
{
|
|
"entropy": 5.509777688980103,
|
|
"epoch": 3.4350985633144004,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038464874784130285,
|
|
"loss": 4.7824,
|
|
"mean_token_accuracy": 0.23091500103473664,
|
|
"num_tokens": 75672423.0,
|
|
"step": 41125
|
|
},
|
|
{
|
|
"entropy": 5.574248123168945,
|
|
"epoch": 3.4355162044771133,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003846227511677566,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.23326385617256165,
|
|
"num_tokens": 75681310.0,
|
|
"step": 41130
|
|
},
|
|
{
|
|
"entropy": 5.507971954345703,
|
|
"epoch": 3.435933845639826,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003845967525751323,
|
|
"loss": 4.7338,
|
|
"mean_token_accuracy": 0.23006715029478073,
|
|
"num_tokens": 75690902.0,
|
|
"step": 41135
|
|
},
|
|
{
|
|
"entropy": 5.503189992904663,
|
|
"epoch": 3.4363514868025393,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003845707520638848,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.23429436683654786,
|
|
"num_tokens": 75699305.0,
|
|
"step": 41140
|
|
},
|
|
{
|
|
"entropy": 5.5887122631073,
|
|
"epoch": 3.436769127965252,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003845447496344694,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.2236700549721718,
|
|
"num_tokens": 75708169.0,
|
|
"step": 41145
|
|
},
|
|
{
|
|
"entropy": 5.514392375946045,
|
|
"epoch": 3.4371867691279654,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003845187452873413,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.22577037215232848,
|
|
"num_tokens": 75717541.0,
|
|
"step": 41150
|
|
},
|
|
{
|
|
"entropy": 5.563769006729126,
|
|
"epoch": 3.437604410290678,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003844927390229558,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.23045652806758882,
|
|
"num_tokens": 75727702.0,
|
|
"step": 41155
|
|
},
|
|
{
|
|
"entropy": 5.459744262695312,
|
|
"epoch": 3.438022051453391,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003844667308417681,
|
|
"loss": 4.6548,
|
|
"mean_token_accuracy": 0.24337491095066072,
|
|
"num_tokens": 75736533.0,
|
|
"step": 41160
|
|
},
|
|
{
|
|
"entropy": 5.532071113586426,
|
|
"epoch": 3.4384396926161043,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038444072074423334,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.2214782014489174,
|
|
"num_tokens": 75746383.0,
|
|
"step": 41165
|
|
},
|
|
{
|
|
"entropy": 5.496194648742676,
|
|
"epoch": 3.438857333778817,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003844147087308072,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.23562049269676208,
|
|
"num_tokens": 75755307.0,
|
|
"step": 41170
|
|
},
|
|
{
|
|
"entropy": 5.425402975082397,
|
|
"epoch": 3.4392749749415303,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003843886948019448,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.23833466768264772,
|
|
"num_tokens": 75764153.0,
|
|
"step": 41175
|
|
},
|
|
{
|
|
"entropy": 5.487433290481567,
|
|
"epoch": 3.439692616104243,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003843626789581018,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.24518579840660096,
|
|
"num_tokens": 75772548.0,
|
|
"step": 41180
|
|
},
|
|
{
|
|
"entropy": 5.506293439865113,
|
|
"epoch": 3.4401102572669564,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003843366611997332,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.23763101398944855,
|
|
"num_tokens": 75782879.0,
|
|
"step": 41185
|
|
},
|
|
{
|
|
"entropy": 5.42366509437561,
|
|
"epoch": 3.440527898429669,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038431064152729495,
|
|
"loss": 4.6336,
|
|
"mean_token_accuracy": 0.24355852007865905,
|
|
"num_tokens": 75791938.0,
|
|
"step": 41190
|
|
},
|
|
{
|
|
"entropy": 5.528245162963867,
|
|
"epoch": 3.4409455395923825,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038428461994124226,
|
|
"loss": 4.7581,
|
|
"mean_token_accuracy": 0.23219497203826905,
|
|
"num_tokens": 75802533.0,
|
|
"step": 41195
|
|
},
|
|
{
|
|
"entropy": 5.543122911453247,
|
|
"epoch": 3.4413631807550953,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038425859644203075,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.24072193652391433,
|
|
"num_tokens": 75812267.0,
|
|
"step": 41200
|
|
},
|
|
{
|
|
"entropy": 5.451965808868408,
|
|
"epoch": 3.441780821917808,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000384232571030116,
|
|
"loss": 4.5545,
|
|
"mean_token_accuracy": 0.2468041479587555,
|
|
"num_tokens": 75821101.0,
|
|
"step": 41205
|
|
},
|
|
{
|
|
"entropy": 5.378243398666382,
|
|
"epoch": 3.4421984630805214,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003842065437059536,
|
|
"loss": 4.5932,
|
|
"mean_token_accuracy": 0.24591077864170074,
|
|
"num_tokens": 75829806.0,
|
|
"step": 41210
|
|
},
|
|
{
|
|
"entropy": 5.411700248718262,
|
|
"epoch": 3.442616104243234,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038418051446999923,
|
|
"loss": 4.6276,
|
|
"mean_token_accuracy": 0.24437972754240037,
|
|
"num_tokens": 75838121.0,
|
|
"step": 41215
|
|
},
|
|
{
|
|
"entropy": 5.459082078933716,
|
|
"epoch": 3.4430337454059474,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003841544833227085,
|
|
"loss": 4.6365,
|
|
"mean_token_accuracy": 0.23530281484127044,
|
|
"num_tokens": 75848026.0,
|
|
"step": 41220
|
|
},
|
|
{
|
|
"entropy": 5.472644424438476,
|
|
"epoch": 3.4434513865686602,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038412845026453715,
|
|
"loss": 4.6984,
|
|
"mean_token_accuracy": 0.2373946413397789,
|
|
"num_tokens": 75857194.0,
|
|
"step": 41225
|
|
},
|
|
{
|
|
"entropy": 5.432858562469482,
|
|
"epoch": 3.443869027731373,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00038410241529594096,
|
|
"loss": 4.7326,
|
|
"mean_token_accuracy": 0.23094257861375808,
|
|
"num_tokens": 75867037.0,
|
|
"step": 41230
|
|
},
|
|
{
|
|
"entropy": 5.483363342285156,
|
|
"epoch": 3.4442866688940863,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003840763784173756,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.23956186026334764,
|
|
"num_tokens": 75876380.0,
|
|
"step": 41235
|
|
},
|
|
{
|
|
"entropy": 5.579192876815796,
|
|
"epoch": 3.444704310056799,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000384050339629297,
|
|
"loss": 4.8346,
|
|
"mean_token_accuracy": 0.23289122581481933,
|
|
"num_tokens": 75885447.0,
|
|
"step": 41240
|
|
},
|
|
{
|
|
"entropy": 5.521999359130859,
|
|
"epoch": 3.4451219512195124,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038402429893216093,
|
|
"loss": 4.7649,
|
|
"mean_token_accuracy": 0.23947243243455887,
|
|
"num_tokens": 75894980.0,
|
|
"step": 41245
|
|
},
|
|
{
|
|
"entropy": 5.457805538177491,
|
|
"epoch": 3.445539592382225,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003839982563264232,
|
|
"loss": 4.5992,
|
|
"mean_token_accuracy": 0.24971261322498323,
|
|
"num_tokens": 75903842.0,
|
|
"step": 41250
|
|
},
|
|
{
|
|
"entropy": 5.427613210678101,
|
|
"epoch": 3.445957233544938,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003839722118125399,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.2374024361371994,
|
|
"num_tokens": 75913073.0,
|
|
"step": 41255
|
|
},
|
|
{
|
|
"entropy": 5.389065170288086,
|
|
"epoch": 3.4463748747076512,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00038394616539096685,
|
|
"loss": 4.6679,
|
|
"mean_token_accuracy": 0.23616757541894912,
|
|
"num_tokens": 75922369.0,
|
|
"step": 41260
|
|
},
|
|
{
|
|
"entropy": 5.482432508468628,
|
|
"epoch": 3.446792515870364,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038392011706216004,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.23359811455011367,
|
|
"num_tokens": 75932156.0,
|
|
"step": 41265
|
|
},
|
|
{
|
|
"entropy": 5.49433536529541,
|
|
"epoch": 3.4472101570330773,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003838940668265754,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.2375413656234741,
|
|
"num_tokens": 75940816.0,
|
|
"step": 41270
|
|
},
|
|
{
|
|
"entropy": 5.450987720489502,
|
|
"epoch": 3.44762779819579,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003838680146846691,
|
|
"loss": 4.6669,
|
|
"mean_token_accuracy": 0.23592179119586945,
|
|
"num_tokens": 75950205.0,
|
|
"step": 41275
|
|
},
|
|
{
|
|
"entropy": 5.493375968933106,
|
|
"epoch": 3.448045439358503,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038384196063689707,
|
|
"loss": 4.7354,
|
|
"mean_token_accuracy": 0.23387539833784105,
|
|
"num_tokens": 75959345.0,
|
|
"step": 41280
|
|
},
|
|
{
|
|
"entropy": 5.610829877853393,
|
|
"epoch": 3.448463080521216,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00038381590468371555,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.22181690335273743,
|
|
"num_tokens": 75968815.0,
|
|
"step": 41285
|
|
},
|
|
{
|
|
"entropy": 5.485015439987182,
|
|
"epoch": 3.448880721683929,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038378984682558074,
|
|
"loss": 4.6737,
|
|
"mean_token_accuracy": 0.24279014617204667,
|
|
"num_tokens": 75977123.0,
|
|
"step": 41290
|
|
},
|
|
{
|
|
"entropy": 5.489063549041748,
|
|
"epoch": 3.4492983628466423,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00038376378706294863,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.22217694371938707,
|
|
"num_tokens": 75985822.0,
|
|
"step": 41295
|
|
},
|
|
{
|
|
"entropy": 5.49456934928894,
|
|
"epoch": 3.449716004009355,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003837377253962755,
|
|
"loss": 4.6754,
|
|
"mean_token_accuracy": 0.24637919217348098,
|
|
"num_tokens": 75993910.0,
|
|
"step": 41300
|
|
},
|
|
{
|
|
"entropy": 5.472822904586792,
|
|
"epoch": 3.4501336451720683,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00038371166182601756,
|
|
"loss": 4.6087,
|
|
"mean_token_accuracy": 0.24557290375232696,
|
|
"num_tokens": 76003329.0,
|
|
"step": 41305
|
|
},
|
|
{
|
|
"entropy": 5.54954571723938,
|
|
"epoch": 3.450551286334781,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003836855963526312,
|
|
"loss": 4.8703,
|
|
"mean_token_accuracy": 0.2272808790206909,
|
|
"num_tokens": 76013352.0,
|
|
"step": 41310
|
|
},
|
|
{
|
|
"entropy": 5.476122665405273,
|
|
"epoch": 3.4509689274974944,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003836595289765727,
|
|
"loss": 4.6152,
|
|
"mean_token_accuracy": 0.2442689746618271,
|
|
"num_tokens": 76022278.0,
|
|
"step": 41315
|
|
},
|
|
{
|
|
"entropy": 5.555663347244263,
|
|
"epoch": 3.451386568660207,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00038363345969829823,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.2391239136457443,
|
|
"num_tokens": 76031374.0,
|
|
"step": 41320
|
|
},
|
|
{
|
|
"entropy": 5.523860597610474,
|
|
"epoch": 3.45180420982292,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038360738851826433,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.23507898449897766,
|
|
"num_tokens": 76041070.0,
|
|
"step": 41325
|
|
},
|
|
{
|
|
"entropy": 5.51886773109436,
|
|
"epoch": 3.4522218509856333,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003835813154369273,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.2294134318828583,
|
|
"num_tokens": 76050544.0,
|
|
"step": 41330
|
|
},
|
|
{
|
|
"entropy": 5.5786316871643065,
|
|
"epoch": 3.452639492148346,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038355524045474384,
|
|
"loss": 4.8088,
|
|
"mean_token_accuracy": 0.2295609101653099,
|
|
"num_tokens": 76060340.0,
|
|
"step": 41335
|
|
},
|
|
{
|
|
"entropy": 5.442196369171143,
|
|
"epoch": 3.4530571333110593,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038352916357217004,
|
|
"loss": 4.6784,
|
|
"mean_token_accuracy": 0.23846273124217987,
|
|
"num_tokens": 76068993.0,
|
|
"step": 41340
|
|
},
|
|
{
|
|
"entropy": 5.447846269607544,
|
|
"epoch": 3.453474774473772,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003835030847896627,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.23999261111021042,
|
|
"num_tokens": 76077675.0,
|
|
"step": 41345
|
|
},
|
|
{
|
|
"entropy": 5.479416465759277,
|
|
"epoch": 3.453892415636485,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003834770041076781,
|
|
"loss": 4.6763,
|
|
"mean_token_accuracy": 0.23729884028434753,
|
|
"num_tokens": 76086674.0,
|
|
"step": 41350
|
|
},
|
|
{
|
|
"entropy": 5.524237871170044,
|
|
"epoch": 3.4543100567991982,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038345092152667314,
|
|
"loss": 4.8275,
|
|
"mean_token_accuracy": 0.2264660805463791,
|
|
"num_tokens": 76095555.0,
|
|
"step": 41355
|
|
},
|
|
{
|
|
"entropy": 5.603994417190552,
|
|
"epoch": 3.454727697961911,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00038342483704710426,
|
|
"loss": 4.8514,
|
|
"mean_token_accuracy": 0.22591070532798768,
|
|
"num_tokens": 76105735.0,
|
|
"step": 41360
|
|
},
|
|
{
|
|
"entropy": 5.4325837135314945,
|
|
"epoch": 3.4551453391246243,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038339875066942806,
|
|
"loss": 4.5608,
|
|
"mean_token_accuracy": 0.2459150493144989,
|
|
"num_tokens": 76115256.0,
|
|
"step": 41365
|
|
},
|
|
{
|
|
"entropy": 5.529338550567627,
|
|
"epoch": 3.455562980287337,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003833726623941012,
|
|
"loss": 4.8148,
|
|
"mean_token_accuracy": 0.22728434056043625,
|
|
"num_tokens": 76123911.0,
|
|
"step": 41370
|
|
},
|
|
{
|
|
"entropy": 5.436409902572632,
|
|
"epoch": 3.45598062145005,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003833465722215804,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.2373150184750557,
|
|
"num_tokens": 76132473.0,
|
|
"step": 41375
|
|
},
|
|
{
|
|
"entropy": 5.520569849014282,
|
|
"epoch": 3.456398262612763,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003833204801523225,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.2335251048207283,
|
|
"num_tokens": 76141149.0,
|
|
"step": 41380
|
|
},
|
|
{
|
|
"entropy": 5.429464530944824,
|
|
"epoch": 3.456815903775476,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038329438618678427,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.23256393671035766,
|
|
"num_tokens": 76150464.0,
|
|
"step": 41385
|
|
},
|
|
{
|
|
"entropy": 5.477349710464478,
|
|
"epoch": 3.4572335449381892,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00038326829032542237,
|
|
"loss": 4.7241,
|
|
"mean_token_accuracy": 0.23944575041532518,
|
|
"num_tokens": 76159952.0,
|
|
"step": 41390
|
|
},
|
|
{
|
|
"entropy": 5.481595230102539,
|
|
"epoch": 3.457651186100902,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038324219256869374,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.24099773168563843,
|
|
"num_tokens": 76169090.0,
|
|
"step": 41395
|
|
},
|
|
{
|
|
"entropy": 5.5447728633880615,
|
|
"epoch": 3.458068827263615,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003832160929170552,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.22297970205545425,
|
|
"num_tokens": 76178825.0,
|
|
"step": 41400
|
|
},
|
|
{
|
|
"entropy": 5.596327066421509,
|
|
"epoch": 3.458486468426328,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038318999137096376,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.23442427366971968,
|
|
"num_tokens": 76188950.0,
|
|
"step": 41405
|
|
},
|
|
{
|
|
"entropy": 5.428937101364136,
|
|
"epoch": 3.458904109589041,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003831638879308763,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.2353324070572853,
|
|
"num_tokens": 76197951.0,
|
|
"step": 41410
|
|
},
|
|
{
|
|
"entropy": 5.491175031661987,
|
|
"epoch": 3.459321750751754,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003831377825972497,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.23583608418703078,
|
|
"num_tokens": 76207163.0,
|
|
"step": 41415
|
|
},
|
|
{
|
|
"entropy": 5.478526926040649,
|
|
"epoch": 3.459739391914467,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003831116753705411,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.24147702157497405,
|
|
"num_tokens": 76215764.0,
|
|
"step": 41420
|
|
},
|
|
{
|
|
"entropy": 5.497545289993286,
|
|
"epoch": 3.4601570330771803,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00038308556625120757,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.2414771318435669,
|
|
"num_tokens": 76224991.0,
|
|
"step": 41425
|
|
},
|
|
{
|
|
"entropy": 5.434880495071411,
|
|
"epoch": 3.460574674239893,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000383059455239706,
|
|
"loss": 4.6835,
|
|
"mean_token_accuracy": 0.24037034064531326,
|
|
"num_tokens": 76233653.0,
|
|
"step": 41430
|
|
},
|
|
{
|
|
"entropy": 5.4797896385192875,
|
|
"epoch": 3.4609923154026063,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003830333423364936,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.22729577869176865,
|
|
"num_tokens": 76243010.0,
|
|
"step": 41435
|
|
},
|
|
{
|
|
"entropy": 5.4950611114501955,
|
|
"epoch": 3.461409956565319,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038300722754202747,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.23901832550764085,
|
|
"num_tokens": 76252432.0,
|
|
"step": 41440
|
|
},
|
|
{
|
|
"entropy": 5.542450618743897,
|
|
"epoch": 3.461827597728032,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003829811108567649,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.2378338098526001,
|
|
"num_tokens": 76261441.0,
|
|
"step": 41445
|
|
},
|
|
{
|
|
"entropy": 5.544053649902343,
|
|
"epoch": 3.462245238890745,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00038295499228116296,
|
|
"loss": 4.7853,
|
|
"mean_token_accuracy": 0.22691685259342192,
|
|
"num_tokens": 76271658.0,
|
|
"step": 41450
|
|
},
|
|
{
|
|
"entropy": 5.4791669845581055,
|
|
"epoch": 3.462662880053458,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000382928871815679,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.2394760638475418,
|
|
"num_tokens": 76280399.0,
|
|
"step": 41455
|
|
},
|
|
{
|
|
"entropy": 5.4857102394104,
|
|
"epoch": 3.4630805212161713,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038290274946077015,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.23235855102539063,
|
|
"num_tokens": 76290321.0,
|
|
"step": 41460
|
|
},
|
|
{
|
|
"entropy": 5.449378442764282,
|
|
"epoch": 3.463498162378884,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003828766252168938,
|
|
"loss": 4.684,
|
|
"mean_token_accuracy": 0.23812728971242905,
|
|
"num_tokens": 76298689.0,
|
|
"step": 41465
|
|
},
|
|
{
|
|
"entropy": 5.456211757659912,
|
|
"epoch": 3.463915803541597,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003828504990845073,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.23687926381826402,
|
|
"num_tokens": 76307804.0,
|
|
"step": 41470
|
|
},
|
|
{
|
|
"entropy": 5.440231037139893,
|
|
"epoch": 3.46433344470431,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00038282437106406796,
|
|
"loss": 4.5993,
|
|
"mean_token_accuracy": 0.2466323509812355,
|
|
"num_tokens": 76316197.0,
|
|
"step": 41475
|
|
},
|
|
{
|
|
"entropy": 5.62781343460083,
|
|
"epoch": 3.464751085867023,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003827982411560333,
|
|
"loss": 4.8759,
|
|
"mean_token_accuracy": 0.22120773643255234,
|
|
"num_tokens": 76325891.0,
|
|
"step": 41480
|
|
},
|
|
{
|
|
"entropy": 5.602384471893311,
|
|
"epoch": 3.465168727029736,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003827721093608606,
|
|
"loss": 4.8113,
|
|
"mean_token_accuracy": 0.22633413076400757,
|
|
"num_tokens": 76335662.0,
|
|
"step": 41485
|
|
},
|
|
{
|
|
"entropy": 5.483353948593139,
|
|
"epoch": 3.465586368192449,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003827459756790074,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.23381748646497727,
|
|
"num_tokens": 76345870.0,
|
|
"step": 41490
|
|
},
|
|
{
|
|
"entropy": 5.516329622268676,
|
|
"epoch": 3.466004009355162,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003827198401109312,
|
|
"loss": 4.6507,
|
|
"mean_token_accuracy": 0.24353565275669098,
|
|
"num_tokens": 76353910.0,
|
|
"step": 41495
|
|
},
|
|
{
|
|
"entropy": 5.614112138748169,
|
|
"epoch": 3.466421650517875,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038269370265708955,
|
|
"loss": 4.8314,
|
|
"mean_token_accuracy": 0.21929553747177125,
|
|
"num_tokens": 76364362.0,
|
|
"step": 41500
|
|
},
|
|
{
|
|
"entropy": 5.51826581954956,
|
|
"epoch": 3.466839291680588,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038266756331793993,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.23939775824546813,
|
|
"num_tokens": 76374405.0,
|
|
"step": 41505
|
|
},
|
|
{
|
|
"entropy": 5.475690078735352,
|
|
"epoch": 3.467256932843301,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003826414220939402,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.23682988286018372,
|
|
"num_tokens": 76384022.0,
|
|
"step": 41510
|
|
},
|
|
{
|
|
"entropy": 5.4771484375,
|
|
"epoch": 3.467674574006014,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003826152789855476,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.22547206729650499,
|
|
"num_tokens": 76392887.0,
|
|
"step": 41515
|
|
},
|
|
{
|
|
"entropy": 5.442114782333374,
|
|
"epoch": 3.468092215168727,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00038258913399322013,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.24427563846111297,
|
|
"num_tokens": 76401572.0,
|
|
"step": 41520
|
|
},
|
|
{
|
|
"entropy": 5.502061271667481,
|
|
"epoch": 3.46850985633144,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00038256298711741534,
|
|
"loss": 4.6497,
|
|
"mean_token_accuracy": 0.24191124141216278,
|
|
"num_tokens": 76410014.0,
|
|
"step": 41525
|
|
},
|
|
{
|
|
"entropy": 5.450749015808105,
|
|
"epoch": 3.468927497494153,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000382536838358591,
|
|
"loss": 4.773,
|
|
"mean_token_accuracy": 0.2299786701798439,
|
|
"num_tokens": 76419481.0,
|
|
"step": 41530
|
|
},
|
|
{
|
|
"entropy": 5.379766988754272,
|
|
"epoch": 3.469345138656866,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003825106877172048,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.24282995909452437,
|
|
"num_tokens": 76428786.0,
|
|
"step": 41535
|
|
},
|
|
{
|
|
"entropy": 5.507233142852783,
|
|
"epoch": 3.469762779819579,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003824845351937147,
|
|
"loss": 4.753,
|
|
"mean_token_accuracy": 0.23609360456466674,
|
|
"num_tokens": 76438819.0,
|
|
"step": 41540
|
|
},
|
|
{
|
|
"entropy": 5.562642240524292,
|
|
"epoch": 3.470180420982292,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038245838078857837,
|
|
"loss": 4.8083,
|
|
"mean_token_accuracy": 0.23195146322250365,
|
|
"num_tokens": 76447344.0,
|
|
"step": 41545
|
|
},
|
|
{
|
|
"entropy": 5.442694616317749,
|
|
"epoch": 3.470598062145005,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038243222450225374,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.23669740706682205,
|
|
"num_tokens": 76455755.0,
|
|
"step": 41550
|
|
},
|
|
{
|
|
"entropy": 5.5686461448669435,
|
|
"epoch": 3.4710157033077182,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003824060663351987,
|
|
"loss": 4.781,
|
|
"mean_token_accuracy": 0.2316065862774849,
|
|
"num_tokens": 76465147.0,
|
|
"step": 41555
|
|
},
|
|
{
|
|
"entropy": 5.543758535385132,
|
|
"epoch": 3.471433344470431,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038237990628787116,
|
|
"loss": 4.7594,
|
|
"mean_token_accuracy": 0.227427139878273,
|
|
"num_tokens": 76474185.0,
|
|
"step": 41560
|
|
},
|
|
{
|
|
"entropy": 5.418018770217896,
|
|
"epoch": 3.471850985633144,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003823537443607292,
|
|
"loss": 4.5986,
|
|
"mean_token_accuracy": 0.24133920967578887,
|
|
"num_tokens": 76483027.0,
|
|
"step": 41565
|
|
},
|
|
{
|
|
"entropy": 5.487129211425781,
|
|
"epoch": 3.472268626795857,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003823275805542306,
|
|
"loss": 4.7238,
|
|
"mean_token_accuracy": 0.24254895448684693,
|
|
"num_tokens": 76492683.0,
|
|
"step": 41570
|
|
},
|
|
{
|
|
"entropy": 5.36345157623291,
|
|
"epoch": 3.47268626795857,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003823014148688336,
|
|
"loss": 4.5409,
|
|
"mean_token_accuracy": 0.24623004496097564,
|
|
"num_tokens": 76501704.0,
|
|
"step": 41575
|
|
},
|
|
{
|
|
"entropy": 5.5721001625061035,
|
|
"epoch": 3.473103909121283,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00038227524730499615,
|
|
"loss": 4.8279,
|
|
"mean_token_accuracy": 0.22590449899435044,
|
|
"num_tokens": 76510732.0,
|
|
"step": 41580
|
|
},
|
|
{
|
|
"entropy": 5.4656377792358395,
|
|
"epoch": 3.473521550283996,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038224907786317633,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.24060573130846025,
|
|
"num_tokens": 76520236.0,
|
|
"step": 41585
|
|
},
|
|
{
|
|
"entropy": 5.434107971191406,
|
|
"epoch": 3.473939191446709,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003822229065438324,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.23645218461751938,
|
|
"num_tokens": 76529348.0,
|
|
"step": 41590
|
|
},
|
|
{
|
|
"entropy": 5.49177131652832,
|
|
"epoch": 3.474356832609422,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038219673334742235,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.2294764444231987,
|
|
"num_tokens": 76538064.0,
|
|
"step": 41595
|
|
},
|
|
{
|
|
"entropy": 5.507020473480225,
|
|
"epoch": 3.474774473772135,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038217055827440444,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.2393334165215492,
|
|
"num_tokens": 76547135.0,
|
|
"step": 41600
|
|
},
|
|
{
|
|
"entropy": 5.512268590927124,
|
|
"epoch": 3.475192114934848,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003821443813252369,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.23075355142354964,
|
|
"num_tokens": 76555745.0,
|
|
"step": 41605
|
|
},
|
|
{
|
|
"entropy": 5.503771209716797,
|
|
"epoch": 3.475609756097561,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003821182025003781,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.2309575065970421,
|
|
"num_tokens": 76564809.0,
|
|
"step": 41610
|
|
},
|
|
{
|
|
"entropy": 5.4938880443573,
|
|
"epoch": 3.4760273972602738,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038209202180028613,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.24137884974479676,
|
|
"num_tokens": 76573521.0,
|
|
"step": 41615
|
|
},
|
|
{
|
|
"entropy": 5.591289138793945,
|
|
"epoch": 3.476445038422987,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038206583922541947,
|
|
"loss": 4.7772,
|
|
"mean_token_accuracy": 0.23162618577480315,
|
|
"num_tokens": 76582696.0,
|
|
"step": 41620
|
|
},
|
|
{
|
|
"entropy": 5.445023870468139,
|
|
"epoch": 3.4768626795857,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003820396547762363,
|
|
"loss": 4.6989,
|
|
"mean_token_accuracy": 0.23969256728887559,
|
|
"num_tokens": 76592296.0,
|
|
"step": 41625
|
|
},
|
|
{
|
|
"entropy": 5.471191930770874,
|
|
"epoch": 3.477280320748413,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003820134684531953,
|
|
"loss": 4.7778,
|
|
"mean_token_accuracy": 0.23225894719362258,
|
|
"num_tokens": 76601686.0,
|
|
"step": 41630
|
|
},
|
|
{
|
|
"entropy": 5.495032787322998,
|
|
"epoch": 3.477697961911126,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003819872802567546,
|
|
"loss": 4.6465,
|
|
"mean_token_accuracy": 0.24572548121213914,
|
|
"num_tokens": 76610243.0,
|
|
"step": 41635
|
|
},
|
|
{
|
|
"entropy": 5.509558534622192,
|
|
"epoch": 3.4781156030738387,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00038196109018737287,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.24035676419734955,
|
|
"num_tokens": 76619022.0,
|
|
"step": 41640
|
|
},
|
|
{
|
|
"entropy": 5.469649696350098,
|
|
"epoch": 3.478533244236552,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003819348982455084,
|
|
"loss": 4.6379,
|
|
"mean_token_accuracy": 0.24407748281955718,
|
|
"num_tokens": 76627315.0,
|
|
"step": 41645
|
|
},
|
|
{
|
|
"entropy": 5.4505335807800295,
|
|
"epoch": 3.478950885399265,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003819087044316199,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.23786082863807678,
|
|
"num_tokens": 76635770.0,
|
|
"step": 41650
|
|
},
|
|
{
|
|
"entropy": 5.572483110427856,
|
|
"epoch": 3.479368526561978,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00038188250874616586,
|
|
"loss": 4.7621,
|
|
"mean_token_accuracy": 0.23809850364923477,
|
|
"num_tokens": 76644663.0,
|
|
"step": 41655
|
|
},
|
|
{
|
|
"entropy": 5.469411849975586,
|
|
"epoch": 3.479786167724691,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038185631118960476,
|
|
"loss": 4.6513,
|
|
"mean_token_accuracy": 0.23818778097629548,
|
|
"num_tokens": 76652914.0,
|
|
"step": 41660
|
|
},
|
|
{
|
|
"entropy": 5.44502968788147,
|
|
"epoch": 3.480203808887404,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038183011176239534,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.23364022523164749,
|
|
"num_tokens": 76662327.0,
|
|
"step": 41665
|
|
},
|
|
{
|
|
"entropy": 5.502033424377442,
|
|
"epoch": 3.480621450050117,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038180391046499626,
|
|
"loss": 4.7695,
|
|
"mean_token_accuracy": 0.2360749661922455,
|
|
"num_tokens": 76672197.0,
|
|
"step": 41670
|
|
},
|
|
{
|
|
"entropy": 5.534741592407227,
|
|
"epoch": 3.48103909121283,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038177770729786614,
|
|
"loss": 4.7291,
|
|
"mean_token_accuracy": 0.2335955560207367,
|
|
"num_tokens": 76681532.0,
|
|
"step": 41675
|
|
},
|
|
{
|
|
"entropy": 5.521696615219116,
|
|
"epoch": 3.481456732375543,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003817515022614637,
|
|
"loss": 4.6275,
|
|
"mean_token_accuracy": 0.24797071814537047,
|
|
"num_tokens": 76690952.0,
|
|
"step": 41680
|
|
},
|
|
{
|
|
"entropy": 5.496840572357177,
|
|
"epoch": 3.481874373538256,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003817252953562478,
|
|
"loss": 4.7513,
|
|
"mean_token_accuracy": 0.22660870403051375,
|
|
"num_tokens": 76700399.0,
|
|
"step": 41685
|
|
},
|
|
{
|
|
"entropy": 5.50183367729187,
|
|
"epoch": 3.482292014700969,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003816990865826771,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.23395264148712158,
|
|
"num_tokens": 76709451.0,
|
|
"step": 41690
|
|
},
|
|
{
|
|
"entropy": 5.570618152618408,
|
|
"epoch": 3.482709655863682,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038167287594121046,
|
|
"loss": 4.7349,
|
|
"mean_token_accuracy": 0.2287239745259285,
|
|
"num_tokens": 76718884.0,
|
|
"step": 41695
|
|
},
|
|
{
|
|
"entropy": 5.500670528411865,
|
|
"epoch": 3.483127297026395,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003816466634323066,
|
|
"loss": 4.68,
|
|
"mean_token_accuracy": 0.23598238974809646,
|
|
"num_tokens": 76727857.0,
|
|
"step": 41700
|
|
},
|
|
{
|
|
"entropy": 5.445423221588134,
|
|
"epoch": 3.483544938189108,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003816204490564247,
|
|
"loss": 4.6767,
|
|
"mean_token_accuracy": 0.23424081802368163,
|
|
"num_tokens": 76737004.0,
|
|
"step": 41705
|
|
},
|
|
{
|
|
"entropy": 5.55386791229248,
|
|
"epoch": 3.4839625793518207,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038159423281402345,
|
|
"loss": 4.719,
|
|
"mean_token_accuracy": 0.22693240493535996,
|
|
"num_tokens": 76746757.0,
|
|
"step": 41710
|
|
},
|
|
{
|
|
"entropy": 5.584550905227661,
|
|
"epoch": 3.484380220514534,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038156801470556184,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.2377028912305832,
|
|
"num_tokens": 76755257.0,
|
|
"step": 41715
|
|
},
|
|
{
|
|
"entropy": 5.537898778915405,
|
|
"epoch": 3.484797861677247,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038154179473149887,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.23204632401466369,
|
|
"num_tokens": 76764193.0,
|
|
"step": 41720
|
|
},
|
|
{
|
|
"entropy": 5.465905714035034,
|
|
"epoch": 3.48521550283996,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00038151557289229347,
|
|
"loss": 4.7344,
|
|
"mean_token_accuracy": 0.24174537062644957,
|
|
"num_tokens": 76772631.0,
|
|
"step": 41725
|
|
},
|
|
{
|
|
"entropy": 5.44680438041687,
|
|
"epoch": 3.485633144002673,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003814893491884048,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.23724600672721863,
|
|
"num_tokens": 76781666.0,
|
|
"step": 41730
|
|
},
|
|
{
|
|
"entropy": 5.498601484298706,
|
|
"epoch": 3.4860507851653857,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00038146312362029197,
|
|
"loss": 4.7112,
|
|
"mean_token_accuracy": 0.2444688394665718,
|
|
"num_tokens": 76790167.0,
|
|
"step": 41735
|
|
},
|
|
{
|
|
"entropy": 5.500658941268921,
|
|
"epoch": 3.486468426328099,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038143689618841387,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.23747093677520753,
|
|
"num_tokens": 76799668.0,
|
|
"step": 41740
|
|
},
|
|
{
|
|
"entropy": 5.570445537567139,
|
|
"epoch": 3.4868860674908118,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003814106668932298,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.23210268765687941,
|
|
"num_tokens": 76808328.0,
|
|
"step": 41745
|
|
},
|
|
{
|
|
"entropy": 5.4641478061676025,
|
|
"epoch": 3.487303708653525,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00038138443573519903,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.23420288860797883,
|
|
"num_tokens": 76817098.0,
|
|
"step": 41750
|
|
},
|
|
{
|
|
"entropy": 5.399822330474853,
|
|
"epoch": 3.487721349816238,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003813582027147806,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.24808155000209808,
|
|
"num_tokens": 76825249.0,
|
|
"step": 41755
|
|
},
|
|
{
|
|
"entropy": 5.519019699096679,
|
|
"epoch": 3.4881389909789506,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003813319678324337,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.2287518635392189,
|
|
"num_tokens": 76834411.0,
|
|
"step": 41760
|
|
},
|
|
{
|
|
"entropy": 5.52844648361206,
|
|
"epoch": 3.488556632141664,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038130573108861794,
|
|
"loss": 4.7823,
|
|
"mean_token_accuracy": 0.23472086489200591,
|
|
"num_tokens": 76843558.0,
|
|
"step": 41765
|
|
},
|
|
{
|
|
"entropy": 5.448960685729981,
|
|
"epoch": 3.4889742733043767,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038127949248379224,
|
|
"loss": 4.7085,
|
|
"mean_token_accuracy": 0.23115434497594833,
|
|
"num_tokens": 76852848.0,
|
|
"step": 41770
|
|
},
|
|
{
|
|
"entropy": 5.441161203384399,
|
|
"epoch": 3.48939191446709,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038125325201841614,
|
|
"loss": 4.6316,
|
|
"mean_token_accuracy": 0.24061616659164428,
|
|
"num_tokens": 76862157.0,
|
|
"step": 41775
|
|
},
|
|
{
|
|
"entropy": 5.456728887557984,
|
|
"epoch": 3.4898095556298028,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038122700969294896,
|
|
"loss": 4.7536,
|
|
"mean_token_accuracy": 0.23654797077178955,
|
|
"num_tokens": 76872389.0,
|
|
"step": 41780
|
|
},
|
|
{
|
|
"entropy": 5.458653497695923,
|
|
"epoch": 3.490227196792516,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003812007655078501,
|
|
"loss": 4.6549,
|
|
"mean_token_accuracy": 0.24979830533266068,
|
|
"num_tokens": 76881308.0,
|
|
"step": 41785
|
|
},
|
|
{
|
|
"entropy": 5.479446697235107,
|
|
"epoch": 3.490644837955229,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000381174519463579,
|
|
"loss": 4.6791,
|
|
"mean_token_accuracy": 0.23024048358201982,
|
|
"num_tokens": 76890341.0,
|
|
"step": 41790
|
|
},
|
|
{
|
|
"entropy": 5.499466180801392,
|
|
"epoch": 3.491062479117942,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003811482715605952,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.2365912601351738,
|
|
"num_tokens": 76900183.0,
|
|
"step": 41795
|
|
},
|
|
{
|
|
"entropy": 5.499964046478271,
|
|
"epoch": 3.491480120280655,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000381122021799358,
|
|
"loss": 4.7679,
|
|
"mean_token_accuracy": 0.2360074371099472,
|
|
"num_tokens": 76909452.0,
|
|
"step": 41800
|
|
},
|
|
{
|
|
"entropy": 5.521483612060547,
|
|
"epoch": 3.4918977614433677,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038109577018032714,
|
|
"loss": 4.7726,
|
|
"mean_token_accuracy": 0.23055112808942796,
|
|
"num_tokens": 76919643.0,
|
|
"step": 41805
|
|
},
|
|
{
|
|
"entropy": 5.558682823181153,
|
|
"epoch": 3.492315402606081,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003810695167039621,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.2325510114431381,
|
|
"num_tokens": 76928225.0,
|
|
"step": 41810
|
|
},
|
|
{
|
|
"entropy": 5.5238025188446045,
|
|
"epoch": 3.492733043768794,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003810432613707226,
|
|
"loss": 4.7434,
|
|
"mean_token_accuracy": 0.2320171818137169,
|
|
"num_tokens": 76938287.0,
|
|
"step": 41815
|
|
},
|
|
{
|
|
"entropy": 5.482160425186157,
|
|
"epoch": 3.493150684931507,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000381017004181068,
|
|
"loss": 4.6716,
|
|
"mean_token_accuracy": 0.23833810836076735,
|
|
"num_tokens": 76947977.0,
|
|
"step": 41820
|
|
},
|
|
{
|
|
"entropy": 5.411458253860474,
|
|
"epoch": 3.49356832609422,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038099074513545827,
|
|
"loss": 4.6185,
|
|
"mean_token_accuracy": 0.24496936351060866,
|
|
"num_tokens": 76957305.0,
|
|
"step": 41825
|
|
},
|
|
{
|
|
"entropy": 5.370176553726196,
|
|
"epoch": 3.4939859672569327,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038096448423435294,
|
|
"loss": 4.6371,
|
|
"mean_token_accuracy": 0.23797955513000488,
|
|
"num_tokens": 76966156.0,
|
|
"step": 41830
|
|
},
|
|
{
|
|
"entropy": 5.520292949676514,
|
|
"epoch": 3.494403608419646,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038093822147821174,
|
|
"loss": 4.827,
|
|
"mean_token_accuracy": 0.23093652874231338,
|
|
"num_tokens": 76975742.0,
|
|
"step": 41835
|
|
},
|
|
{
|
|
"entropy": 5.510467147827148,
|
|
"epoch": 3.4948212495823587,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003809119568674944,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.24814170002937316,
|
|
"num_tokens": 76984526.0,
|
|
"step": 41840
|
|
},
|
|
{
|
|
"entropy": 5.438447046279907,
|
|
"epoch": 3.495238890745072,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003808856904026608,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.24578913152217866,
|
|
"num_tokens": 76993732.0,
|
|
"step": 41845
|
|
},
|
|
{
|
|
"entropy": 5.409902620315552,
|
|
"epoch": 3.495656531907785,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003808594220841708,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.25639564692974093,
|
|
"num_tokens": 77003255.0,
|
|
"step": 41850
|
|
},
|
|
{
|
|
"entropy": 5.547910499572754,
|
|
"epoch": 3.4960741730704976,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003808331519124841,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.2267228290438652,
|
|
"num_tokens": 77012386.0,
|
|
"step": 41855
|
|
},
|
|
{
|
|
"entropy": 5.463247966766358,
|
|
"epoch": 3.496491814233211,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003808068798880607,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.23500287383794785,
|
|
"num_tokens": 77021586.0,
|
|
"step": 41860
|
|
},
|
|
{
|
|
"entropy": 5.563172483444214,
|
|
"epoch": 3.4969094553959237,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003807806060113606,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.23003037869930268,
|
|
"num_tokens": 77031099.0,
|
|
"step": 41865
|
|
},
|
|
{
|
|
"entropy": 5.436523962020874,
|
|
"epoch": 3.497327096558637,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003807543302828436,
|
|
"loss": 4.6737,
|
|
"mean_token_accuracy": 0.2336517885327339,
|
|
"num_tokens": 77040145.0,
|
|
"step": 41870
|
|
},
|
|
{
|
|
"entropy": 5.53824896812439,
|
|
"epoch": 3.4977447377213498,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003807280527029697,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.23470280915498734,
|
|
"num_tokens": 77051003.0,
|
|
"step": 41875
|
|
},
|
|
{
|
|
"entropy": 5.501592588424683,
|
|
"epoch": 3.498162378884063,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003807017732721991,
|
|
"loss": 4.6765,
|
|
"mean_token_accuracy": 0.24400595128536223,
|
|
"num_tokens": 77060679.0,
|
|
"step": 41880
|
|
},
|
|
{
|
|
"entropy": 5.49657130241394,
|
|
"epoch": 3.498580020046776,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003806754919909916,
|
|
"loss": 4.718,
|
|
"mean_token_accuracy": 0.23598039895296097,
|
|
"num_tokens": 77068958.0,
|
|
"step": 41885
|
|
},
|
|
{
|
|
"entropy": 5.465581798553467,
|
|
"epoch": 3.4989976612094886,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003806492088598074,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.24451305270195006,
|
|
"num_tokens": 77077669.0,
|
|
"step": 41890
|
|
},
|
|
{
|
|
"entropy": 5.551588535308838,
|
|
"epoch": 3.499415302372202,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00038062292387910674,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.23042616993188858,
|
|
"num_tokens": 77086492.0,
|
|
"step": 41895
|
|
},
|
|
{
|
|
"entropy": 5.441059494018555,
|
|
"epoch": 3.4998329435349147,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003805966370493496,
|
|
"loss": 4.6499,
|
|
"mean_token_accuracy": 0.2458325669169426,
|
|
"num_tokens": 77095524.0,
|
|
"step": 41900
|
|
},
|
|
{
|
|
"entropy": 5.516724920272827,
|
|
"epoch": 3.500250584697628,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003805703483709962,
|
|
"loss": 4.7319,
|
|
"mean_token_accuracy": 0.23129148334264754,
|
|
"num_tokens": 77103857.0,
|
|
"step": 41905
|
|
},
|
|
{
|
|
"entropy": 5.55022292137146,
|
|
"epoch": 3.5006682258603408,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003805440578445069,
|
|
"loss": 4.7077,
|
|
"mean_token_accuracy": 0.23666443973779677,
|
|
"num_tokens": 77112143.0,
|
|
"step": 41910
|
|
},
|
|
{
|
|
"entropy": 5.583875417709351,
|
|
"epoch": 3.501085867023054,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038051776547034166,
|
|
"loss": 4.8465,
|
|
"mean_token_accuracy": 0.22222262620925903,
|
|
"num_tokens": 77121303.0,
|
|
"step": 41915
|
|
},
|
|
{
|
|
"entropy": 5.526349258422852,
|
|
"epoch": 3.501503508185767,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000380491471248961,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.2316657304763794,
|
|
"num_tokens": 77130875.0,
|
|
"step": 41920
|
|
},
|
|
{
|
|
"entropy": 5.5443755149841305,
|
|
"epoch": 3.5019211493484796,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038046517518082517,
|
|
"loss": 4.7725,
|
|
"mean_token_accuracy": 0.22817436456680298,
|
|
"num_tokens": 77140126.0,
|
|
"step": 41925
|
|
},
|
|
{
|
|
"entropy": 5.5003032207489015,
|
|
"epoch": 3.502338790511193,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038043887726639454,
|
|
"loss": 4.7016,
|
|
"mean_token_accuracy": 0.2345299944281578,
|
|
"num_tokens": 77150717.0,
|
|
"step": 41930
|
|
},
|
|
{
|
|
"entropy": 5.5371034145355225,
|
|
"epoch": 3.5027564316739057,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00038041257750612935,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.23048830032348633,
|
|
"num_tokens": 77158632.0,
|
|
"step": 41935
|
|
},
|
|
{
|
|
"entropy": 5.561793947219849,
|
|
"epoch": 3.503174072836619,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003803862759004902,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.23885809183120726,
|
|
"num_tokens": 77167178.0,
|
|
"step": 41940
|
|
},
|
|
{
|
|
"entropy": 5.458743715286255,
|
|
"epoch": 3.503591713999332,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003803599724499373,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.25097216218709945,
|
|
"num_tokens": 77175696.0,
|
|
"step": 41945
|
|
},
|
|
{
|
|
"entropy": 5.486455774307251,
|
|
"epoch": 3.5040093551620446,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00038033366715493135,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.22754087597131728,
|
|
"num_tokens": 77184651.0,
|
|
"step": 41950
|
|
},
|
|
{
|
|
"entropy": 5.496494483947754,
|
|
"epoch": 3.504426996324758,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038030736001593273,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.2262279972434044,
|
|
"num_tokens": 77194132.0,
|
|
"step": 41955
|
|
},
|
|
{
|
|
"entropy": 5.521204090118408,
|
|
"epoch": 3.5048446374874707,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0003802810510334021,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.23449646234512328,
|
|
"num_tokens": 77202982.0,
|
|
"step": 41960
|
|
},
|
|
{
|
|
"entropy": 5.448659420013428,
|
|
"epoch": 3.505262278650184,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003802547402077999,
|
|
"loss": 4.6654,
|
|
"mean_token_accuracy": 0.23376724123954773,
|
|
"num_tokens": 77211396.0,
|
|
"step": 41965
|
|
},
|
|
{
|
|
"entropy": 5.516894769668579,
|
|
"epoch": 3.5056799198128967,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003802284275395868,
|
|
"loss": 4.7457,
|
|
"mean_token_accuracy": 0.235855071246624,
|
|
"num_tokens": 77222458.0,
|
|
"step": 41970
|
|
},
|
|
{
|
|
"entropy": 5.455773639678955,
|
|
"epoch": 3.5060975609756095,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003802021130292233,
|
|
"loss": 4.6372,
|
|
"mean_token_accuracy": 0.24232524484395981,
|
|
"num_tokens": 77231238.0,
|
|
"step": 41975
|
|
},
|
|
{
|
|
"entropy": 5.475769567489624,
|
|
"epoch": 3.506515202138323,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00038017579667717026,
|
|
"loss": 4.6849,
|
|
"mean_token_accuracy": 0.2408837467432022,
|
|
"num_tokens": 77239849.0,
|
|
"step": 41980
|
|
},
|
|
{
|
|
"entropy": 5.560935115814209,
|
|
"epoch": 3.5069328433010356,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003801494784838883,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.2251012533903122,
|
|
"num_tokens": 77249230.0,
|
|
"step": 41985
|
|
},
|
|
{
|
|
"entropy": 5.492318534851075,
|
|
"epoch": 3.507350484463749,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003801231584498382,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.24190906286239625,
|
|
"num_tokens": 77258142.0,
|
|
"step": 41990
|
|
},
|
|
{
|
|
"entropy": 5.530475378036499,
|
|
"epoch": 3.5077681256264617,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00038009683657548056,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.22503135800361634,
|
|
"num_tokens": 77267694.0,
|
|
"step": 41995
|
|
},
|
|
{
|
|
"entropy": 5.375532054901123,
|
|
"epoch": 3.5081857667891745,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003800705128612764,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.24885481595993042,
|
|
"num_tokens": 77277474.0,
|
|
"step": 42000
|
|
},
|
|
{
|
|
"epoch": 3.5081857667891745,
|
|
"eval_entropy": 5.1394877276716535,
|
|
"eval_loss": 4.7374396324157715,
|
|
"eval_mean_token_accuracy": 0.24540338379281024,
|
|
"eval_num_tokens": 77277474.0,
|
|
"eval_runtime": 21.3668,
|
|
"eval_samples_per_second": 1767.371,
|
|
"eval_steps_per_second": 220.951,
|
|
"step": 42000
|
|
},
|
|
{
|
|
"entropy": 5.468257236480713,
|
|
"epoch": 3.5086034079518877,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00038004418730768635,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.23783960640430452,
|
|
"num_tokens": 77286893.0,
|
|
"step": 42005
|
|
},
|
|
{
|
|
"entropy": 5.484739112854004,
|
|
"epoch": 3.509021049114601,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003800178599151714,
|
|
"loss": 4.6871,
|
|
"mean_token_accuracy": 0.23770143538713456,
|
|
"num_tokens": 77295190.0,
|
|
"step": 42010
|
|
},
|
|
{
|
|
"entropy": 5.520151996612549,
|
|
"epoch": 3.509438690277314,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003799915306841924,
|
|
"loss": 4.7054,
|
|
"mean_token_accuracy": 0.24133603572845458,
|
|
"num_tokens": 77304201.0,
|
|
"step": 42015
|
|
},
|
|
{
|
|
"entropy": 5.475706148147583,
|
|
"epoch": 3.5098563314400266,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003799651996152103,
|
|
"loss": 4.6605,
|
|
"mean_token_accuracy": 0.2441791206598282,
|
|
"num_tokens": 77313448.0,
|
|
"step": 42020
|
|
},
|
|
{
|
|
"entropy": 5.474782848358155,
|
|
"epoch": 3.51027397260274,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000379938866708686,
|
|
"loss": 4.7009,
|
|
"mean_token_accuracy": 0.23430500328540801,
|
|
"num_tokens": 77322420.0,
|
|
"step": 42025
|
|
},
|
|
{
|
|
"entropy": 5.506433296203613,
|
|
"epoch": 3.5106916137654527,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00037991253196508054,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.23729273974895476,
|
|
"num_tokens": 77332163.0,
|
|
"step": 42030
|
|
},
|
|
{
|
|
"entropy": 5.490984582901001,
|
|
"epoch": 3.511109254928166,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003798861953848549,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.24138692319393157,
|
|
"num_tokens": 77341626.0,
|
|
"step": 42035
|
|
},
|
|
{
|
|
"entropy": 5.481207227706909,
|
|
"epoch": 3.5115268960908788,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003798598569684703,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.2367397129535675,
|
|
"num_tokens": 77350632.0,
|
|
"step": 42040
|
|
},
|
|
{
|
|
"entropy": 5.418524599075317,
|
|
"epoch": 3.5119445372535916,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00037983351671638744,
|
|
"loss": 4.6492,
|
|
"mean_token_accuracy": 0.2342156618833542,
|
|
"num_tokens": 77359216.0,
|
|
"step": 42045
|
|
},
|
|
{
|
|
"entropy": 5.424506902694702,
|
|
"epoch": 3.512362178416305,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003798071746290679,
|
|
"loss": 4.648,
|
|
"mean_token_accuracy": 0.24422649145126343,
|
|
"num_tokens": 77368964.0,
|
|
"step": 42050
|
|
},
|
|
{
|
|
"entropy": 5.548094654083252,
|
|
"epoch": 3.5127798195790176,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003797808307069724,
|
|
"loss": 4.7697,
|
|
"mean_token_accuracy": 0.22916440665721893,
|
|
"num_tokens": 77377937.0,
|
|
"step": 42055
|
|
},
|
|
{
|
|
"entropy": 5.5657206058502195,
|
|
"epoch": 3.513197460741731,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003797544849505625,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.2353840470314026,
|
|
"num_tokens": 77387816.0,
|
|
"step": 42060
|
|
},
|
|
{
|
|
"entropy": 5.570456171035767,
|
|
"epoch": 3.5136151019044437,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003797281373602992,
|
|
"loss": 4.7838,
|
|
"mean_token_accuracy": 0.2286805748939514,
|
|
"num_tokens": 77397077.0,
|
|
"step": 42065
|
|
},
|
|
{
|
|
"entropy": 5.500549697875977,
|
|
"epoch": 3.5140327430671565,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003797017879366438,
|
|
"loss": 4.8357,
|
|
"mean_token_accuracy": 0.22547757774591445,
|
|
"num_tokens": 77406465.0,
|
|
"step": 42070
|
|
},
|
|
{
|
|
"entropy": 5.47152943611145,
|
|
"epoch": 3.5144503842298698,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003796754366800575,
|
|
"loss": 4.6851,
|
|
"mean_token_accuracy": 0.23534787446260452,
|
|
"num_tokens": 77416423.0,
|
|
"step": 42075
|
|
},
|
|
{
|
|
"entropy": 5.43708987236023,
|
|
"epoch": 3.5148680253925826,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003796490835910019,
|
|
"loss": 4.6475,
|
|
"mean_token_accuracy": 0.23912130445241928,
|
|
"num_tokens": 77425284.0,
|
|
"step": 42080
|
|
},
|
|
{
|
|
"entropy": 5.513519191741944,
|
|
"epoch": 3.515285666555296,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00037962272866993784,
|
|
"loss": 4.6502,
|
|
"mean_token_accuracy": 0.2471026673913002,
|
|
"num_tokens": 77434294.0,
|
|
"step": 42085
|
|
},
|
|
{
|
|
"entropy": 5.528328704833984,
|
|
"epoch": 3.5157033077180087,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003795963719173272,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.23297779858112336,
|
|
"num_tokens": 77443440.0,
|
|
"step": 42090
|
|
},
|
|
{
|
|
"entropy": 5.443888711929321,
|
|
"epoch": 3.5161209488807215,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037957001333363105,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.23775425553321838,
|
|
"num_tokens": 77452147.0,
|
|
"step": 42095
|
|
},
|
|
{
|
|
"entropy": 5.481340456008911,
|
|
"epoch": 3.5165385900434347,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000379543652919311,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.23387625217437744,
|
|
"num_tokens": 77460336.0,
|
|
"step": 42100
|
|
},
|
|
{
|
|
"entropy": 5.609807872772217,
|
|
"epoch": 3.5169562312061475,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00037951729067482845,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.22765665799379348,
|
|
"num_tokens": 77469804.0,
|
|
"step": 42105
|
|
},
|
|
{
|
|
"entropy": 5.570615005493164,
|
|
"epoch": 3.517373872368861,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00037949092660064486,
|
|
"loss": 4.7854,
|
|
"mean_token_accuracy": 0.23243146687746047,
|
|
"num_tokens": 77479609.0,
|
|
"step": 42110
|
|
},
|
|
{
|
|
"entropy": 5.487475204467773,
|
|
"epoch": 3.5177915135315736,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003794645606972219,
|
|
"loss": 4.7011,
|
|
"mean_token_accuracy": 0.23591201454401017,
|
|
"num_tokens": 77489545.0,
|
|
"step": 42115
|
|
},
|
|
{
|
|
"entropy": 5.449814081192017,
|
|
"epoch": 3.5182091546942864,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003794381929650211,
|
|
"loss": 4.6712,
|
|
"mean_token_accuracy": 0.23722182512283324,
|
|
"num_tokens": 77498757.0,
|
|
"step": 42120
|
|
},
|
|
{
|
|
"entropy": 5.495807743072509,
|
|
"epoch": 3.5186267958569997,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00037941182340450394,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.23311039954423904,
|
|
"num_tokens": 77508352.0,
|
|
"step": 42125
|
|
},
|
|
{
|
|
"entropy": 5.498372507095337,
|
|
"epoch": 3.519044437019713,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00037938545201613214,
|
|
"loss": 4.7614,
|
|
"mean_token_accuracy": 0.2307121992111206,
|
|
"num_tokens": 77517196.0,
|
|
"step": 42130
|
|
},
|
|
{
|
|
"entropy": 5.494615936279297,
|
|
"epoch": 3.5194620781824257,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00037935907880036734,
|
|
"loss": 4.7086,
|
|
"mean_token_accuracy": 0.23821998983621598,
|
|
"num_tokens": 77526284.0,
|
|
"step": 42135
|
|
},
|
|
{
|
|
"entropy": 5.415980386734009,
|
|
"epoch": 3.5198797193451385,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003793327037576713,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.23769886791706085,
|
|
"num_tokens": 77535949.0,
|
|
"step": 42140
|
|
},
|
|
{
|
|
"entropy": 5.560196256637573,
|
|
"epoch": 3.520297360507852,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003793063268885056,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.2249351531267166,
|
|
"num_tokens": 77546499.0,
|
|
"step": 42145
|
|
},
|
|
{
|
|
"entropy": 5.555160140991211,
|
|
"epoch": 3.5207150016705646,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003792799481933322,
|
|
"loss": 4.6833,
|
|
"mean_token_accuracy": 0.24214307367801666,
|
|
"num_tokens": 77556178.0,
|
|
"step": 42150
|
|
},
|
|
{
|
|
"entropy": 5.499641942977905,
|
|
"epoch": 3.521132642833278,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00037925356767261277,
|
|
"loss": 4.5876,
|
|
"mean_token_accuracy": 0.24525108188390732,
|
|
"num_tokens": 77564168.0,
|
|
"step": 42155
|
|
},
|
|
{
|
|
"entropy": 5.53930811882019,
|
|
"epoch": 3.5215502839959907,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00037922718532680907,
|
|
"loss": 4.8035,
|
|
"mean_token_accuracy": 0.22544972002506256,
|
|
"num_tokens": 77573949.0,
|
|
"step": 42160
|
|
},
|
|
{
|
|
"entropy": 5.419779253005982,
|
|
"epoch": 3.5219679251587035,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003792008011563831,
|
|
"loss": 4.5918,
|
|
"mean_token_accuracy": 0.24251904785633088,
|
|
"num_tokens": 77583087.0,
|
|
"step": 42165
|
|
},
|
|
{
|
|
"entropy": 5.497745990753174,
|
|
"epoch": 3.5223855663214167,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003791744151617967,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.23150957226753235,
|
|
"num_tokens": 77593462.0,
|
|
"step": 42170
|
|
},
|
|
{
|
|
"entropy": 5.483358144760132,
|
|
"epoch": 3.5228032074841296,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00037914802734351173,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.2461556911468506,
|
|
"num_tokens": 77602672.0,
|
|
"step": 42175
|
|
},
|
|
{
|
|
"entropy": 5.513628768920898,
|
|
"epoch": 3.523220848646843,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00037912163770199023,
|
|
"loss": 4.7889,
|
|
"mean_token_accuracy": 0.2285699501633644,
|
|
"num_tokens": 77611571.0,
|
|
"step": 42180
|
|
},
|
|
{
|
|
"entropy": 5.524336862564087,
|
|
"epoch": 3.5236384898095556,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00037909524623769405,
|
|
"loss": 4.7496,
|
|
"mean_token_accuracy": 0.23081481009721755,
|
|
"num_tokens": 77620346.0,
|
|
"step": 42185
|
|
},
|
|
{
|
|
"entropy": 5.531304979324341,
|
|
"epoch": 3.5240561309722684,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003790688529510853,
|
|
"loss": 4.7418,
|
|
"mean_token_accuracy": 0.23579512685537338,
|
|
"num_tokens": 77629228.0,
|
|
"step": 42190
|
|
},
|
|
{
|
|
"entropy": 5.398615980148316,
|
|
"epoch": 3.5244737721349817,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000379042457842626,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.23722854852676392,
|
|
"num_tokens": 77638198.0,
|
|
"step": 42195
|
|
},
|
|
{
|
|
"entropy": 5.453156185150147,
|
|
"epoch": 3.5248914132976945,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003790160609127782,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.23203717917203903,
|
|
"num_tokens": 77646723.0,
|
|
"step": 42200
|
|
},
|
|
{
|
|
"entropy": 5.5253337860107425,
|
|
"epoch": 3.5253090544604078,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037898966216200425,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.23069117963314056,
|
|
"num_tokens": 77656419.0,
|
|
"step": 42205
|
|
},
|
|
{
|
|
"entropy": 5.55533242225647,
|
|
"epoch": 3.5257266956231206,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003789632615907659,
|
|
"loss": 4.8102,
|
|
"mean_token_accuracy": 0.22565218657255173,
|
|
"num_tokens": 77665890.0,
|
|
"step": 42210
|
|
},
|
|
{
|
|
"entropy": 5.557700967788696,
|
|
"epoch": 3.5261443367858334,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003789368591995256,
|
|
"loss": 4.7626,
|
|
"mean_token_accuracy": 0.23405779898166656,
|
|
"num_tokens": 77675420.0,
|
|
"step": 42215
|
|
},
|
|
{
|
|
"entropy": 5.543746042251587,
|
|
"epoch": 3.5265619779485466,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037891045498874545,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.2385910928249359,
|
|
"num_tokens": 77683828.0,
|
|
"step": 42220
|
|
},
|
|
{
|
|
"entropy": 5.46619758605957,
|
|
"epoch": 3.5269796191112595,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00037888404895888774,
|
|
"loss": 4.7237,
|
|
"mean_token_accuracy": 0.23812531381845475,
|
|
"num_tokens": 77693133.0,
|
|
"step": 42225
|
|
},
|
|
{
|
|
"entropy": 5.41554627418518,
|
|
"epoch": 3.5273972602739727,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0003788576411104146,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.2366867780685425,
|
|
"num_tokens": 77702351.0,
|
|
"step": 42230
|
|
},
|
|
{
|
|
"entropy": 5.51976432800293,
|
|
"epoch": 3.5278149014366855,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037883123144378855,
|
|
"loss": 4.783,
|
|
"mean_token_accuracy": 0.23215994983911514,
|
|
"num_tokens": 77711284.0,
|
|
"step": 42235
|
|
},
|
|
{
|
|
"entropy": 5.4649487972259525,
|
|
"epoch": 3.5282325425993983,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003788048199594717,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.22861746549606324,
|
|
"num_tokens": 77721384.0,
|
|
"step": 42240
|
|
},
|
|
{
|
|
"entropy": 5.520964574813843,
|
|
"epoch": 3.5286501837621116,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003787784066579267,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.23177067786455155,
|
|
"num_tokens": 77730557.0,
|
|
"step": 42245
|
|
},
|
|
{
|
|
"entropy": 5.575629615783692,
|
|
"epoch": 3.529067824924825,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003787519915396156,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.23153882175683976,
|
|
"num_tokens": 77739752.0,
|
|
"step": 42250
|
|
},
|
|
{
|
|
"entropy": 5.4627354621887205,
|
|
"epoch": 3.5294854660875377,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00037872557460500117,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.24063339233398437,
|
|
"num_tokens": 77748369.0,
|
|
"step": 42255
|
|
},
|
|
{
|
|
"entropy": 5.518820190429688,
|
|
"epoch": 3.5299031072502505,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003786991558545455,
|
|
"loss": 4.7807,
|
|
"mean_token_accuracy": 0.229964716732502,
|
|
"num_tokens": 77758764.0,
|
|
"step": 42260
|
|
},
|
|
{
|
|
"entropy": 5.455734777450561,
|
|
"epoch": 3.5303207484129637,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003786727352887114,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.23991037011146546,
|
|
"num_tokens": 77767402.0,
|
|
"step": 42265
|
|
},
|
|
{
|
|
"entropy": 5.409914350509643,
|
|
"epoch": 3.5307383895756765,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003786463129079613,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.24182528257369995,
|
|
"num_tokens": 77775936.0,
|
|
"step": 42270
|
|
},
|
|
{
|
|
"entropy": 5.514236211776733,
|
|
"epoch": 3.53115603073839,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003786198887127577,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.22452379912137985,
|
|
"num_tokens": 77785305.0,
|
|
"step": 42275
|
|
},
|
|
{
|
|
"entropy": 5.60918779373169,
|
|
"epoch": 3.5315736719011026,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003785934627035633,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.23228769749403,
|
|
"num_tokens": 77794909.0,
|
|
"step": 42280
|
|
},
|
|
{
|
|
"entropy": 5.5718286514282225,
|
|
"epoch": 3.5319913130638154,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00037856703488084047,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.23293420374393464,
|
|
"num_tokens": 77804191.0,
|
|
"step": 42285
|
|
},
|
|
{
|
|
"entropy": 5.515264225006104,
|
|
"epoch": 3.5324089542265287,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003785406052450521,
|
|
"loss": 4.7203,
|
|
"mean_token_accuracy": 0.22987646460533143,
|
|
"num_tokens": 77813592.0,
|
|
"step": 42290
|
|
},
|
|
{
|
|
"entropy": 5.530541944503784,
|
|
"epoch": 3.5328265953892415,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003785141737966609,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.23782183676958085,
|
|
"num_tokens": 77822469.0,
|
|
"step": 42295
|
|
},
|
|
{
|
|
"entropy": 5.567737150192261,
|
|
"epoch": 3.5332442365519547,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00037848774053612943,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.23323213309049606,
|
|
"num_tokens": 77831495.0,
|
|
"step": 42300
|
|
},
|
|
{
|
|
"entropy": 5.542321014404297,
|
|
"epoch": 3.5336618777146676,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037846130546392046,
|
|
"loss": 4.8383,
|
|
"mean_token_accuracy": 0.22687692642211915,
|
|
"num_tokens": 77840919.0,
|
|
"step": 42305
|
|
},
|
|
{
|
|
"entropy": 5.488032579421997,
|
|
"epoch": 3.5340795188773804,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003784348685804968,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.23843568414449692,
|
|
"num_tokens": 77850978.0,
|
|
"step": 42310
|
|
},
|
|
{
|
|
"entropy": 5.521772813796997,
|
|
"epoch": 3.5344971600400936,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003784084298863213,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.23895975947380066,
|
|
"num_tokens": 77859000.0,
|
|
"step": 42315
|
|
},
|
|
{
|
|
"entropy": 5.526720952987671,
|
|
"epoch": 3.5349148012028064,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003783819893818567,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.23338210135698317,
|
|
"num_tokens": 77868589.0,
|
|
"step": 42320
|
|
},
|
|
{
|
|
"entropy": 5.5658361434936525,
|
|
"epoch": 3.5353324423655197,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000378355547067566,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.23629042655229568,
|
|
"num_tokens": 77878107.0,
|
|
"step": 42325
|
|
},
|
|
{
|
|
"entropy": 5.42278642654419,
|
|
"epoch": 3.5357500835282325,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000378329102943912,
|
|
"loss": 4.6302,
|
|
"mean_token_accuracy": 0.24093419760465623,
|
|
"num_tokens": 77887280.0,
|
|
"step": 42330
|
|
},
|
|
{
|
|
"entropy": 5.522685098648071,
|
|
"epoch": 3.5361677246909453,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00037830265701135776,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.23533333241939544,
|
|
"num_tokens": 77896332.0,
|
|
"step": 42335
|
|
},
|
|
{
|
|
"entropy": 5.542786741256714,
|
|
"epoch": 3.5365853658536586,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037827620927036605,
|
|
"loss": 4.8339,
|
|
"mean_token_accuracy": 0.21861645579338074,
|
|
"num_tokens": 77905818.0,
|
|
"step": 42340
|
|
},
|
|
{
|
|
"entropy": 5.476704120635986,
|
|
"epoch": 3.5370030070163714,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00037824975972140004,
|
|
"loss": 4.6925,
|
|
"mean_token_accuracy": 0.23906111866235732,
|
|
"num_tokens": 77915018.0,
|
|
"step": 42345
|
|
},
|
|
{
|
|
"entropy": 5.597965574264526,
|
|
"epoch": 3.5374206481790846,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003782233083649227,
|
|
"loss": 4.8588,
|
|
"mean_token_accuracy": 0.2249211236834526,
|
|
"num_tokens": 77924178.0,
|
|
"step": 42350
|
|
},
|
|
{
|
|
"entropy": 5.572213172912598,
|
|
"epoch": 3.5378382893417974,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00037819685520139713,
|
|
"loss": 4.8068,
|
|
"mean_token_accuracy": 0.22706106156110764,
|
|
"num_tokens": 77933053.0,
|
|
"step": 42355
|
|
},
|
|
{
|
|
"entropy": 5.509532833099366,
|
|
"epoch": 3.5382559305045103,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003781704002312863,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.2357272431254387,
|
|
"num_tokens": 77941539.0,
|
|
"step": 42360
|
|
},
|
|
{
|
|
"entropy": 5.464159917831421,
|
|
"epoch": 3.5386735716672235,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003781439434550535,
|
|
"loss": 4.6923,
|
|
"mean_token_accuracy": 0.2448832243680954,
|
|
"num_tokens": 77950620.0,
|
|
"step": 42365
|
|
},
|
|
{
|
|
"entropy": 5.554717206954956,
|
|
"epoch": 3.5390912128299368,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037811748487316183,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.23035427033901215,
|
|
"num_tokens": 77959759.0,
|
|
"step": 42370
|
|
},
|
|
{
|
|
"entropy": 5.5385507106781,
|
|
"epoch": 3.5395088539926496,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003780910244860744,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.24105008095502853,
|
|
"num_tokens": 77968515.0,
|
|
"step": 42375
|
|
},
|
|
{
|
|
"entropy": 5.58759651184082,
|
|
"epoch": 3.5399264951553624,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00037806456229425457,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.2306630030274391,
|
|
"num_tokens": 77977394.0,
|
|
"step": 42380
|
|
},
|
|
{
|
|
"entropy": 5.477088737487793,
|
|
"epoch": 3.5403441363180757,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003780380982981654,
|
|
"loss": 4.6667,
|
|
"mean_token_accuracy": 0.24323755502700806,
|
|
"num_tokens": 77986446.0,
|
|
"step": 42385
|
|
},
|
|
{
|
|
"entropy": 5.527640676498413,
|
|
"epoch": 3.5407617774807885,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003780116324982705,
|
|
"loss": 4.7594,
|
|
"mean_token_accuracy": 0.22690898925065994,
|
|
"num_tokens": 77995674.0,
|
|
"step": 42390
|
|
},
|
|
{
|
|
"entropy": 5.457267332077026,
|
|
"epoch": 3.5411794186435017,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00037798516489503275,
|
|
"loss": 4.6621,
|
|
"mean_token_accuracy": 0.23524832129478454,
|
|
"num_tokens": 78004284.0,
|
|
"step": 42395
|
|
},
|
|
{
|
|
"entropy": 5.464914321899414,
|
|
"epoch": 3.5415970598062145,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003779586954889159,
|
|
"loss": 4.6716,
|
|
"mean_token_accuracy": 0.24240820705890656,
|
|
"num_tokens": 78014535.0,
|
|
"step": 42400
|
|
},
|
|
{
|
|
"entropy": 5.525079822540283,
|
|
"epoch": 3.5420147009689273,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00037793222428038293,
|
|
"loss": 4.7203,
|
|
"mean_token_accuracy": 0.23922569900751114,
|
|
"num_tokens": 78023830.0,
|
|
"step": 42405
|
|
},
|
|
{
|
|
"entropy": 5.531609010696411,
|
|
"epoch": 3.5424323421316406,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003779057512698977,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.2329781174659729,
|
|
"num_tokens": 78032740.0,
|
|
"step": 42410
|
|
},
|
|
{
|
|
"entropy": 5.427816486358642,
|
|
"epoch": 3.5428499832943534,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003778792764579233,
|
|
"loss": 4.5468,
|
|
"mean_token_accuracy": 0.24941013902425765,
|
|
"num_tokens": 78040990.0,
|
|
"step": 42415
|
|
},
|
|
{
|
|
"entropy": 5.567343664169312,
|
|
"epoch": 3.5432676244570667,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00037785279984492345,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.22314438223838806,
|
|
"num_tokens": 78050723.0,
|
|
"step": 42420
|
|
},
|
|
{
|
|
"entropy": 5.535945653915405,
|
|
"epoch": 3.5436852656197795,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003778263214313614,
|
|
"loss": 4.7384,
|
|
"mean_token_accuracy": 0.23471756875514985,
|
|
"num_tokens": 78059925.0,
|
|
"step": 42425
|
|
},
|
|
{
|
|
"entropy": 5.6078417778015135,
|
|
"epoch": 3.5441029067824923,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037779984121770086,
|
|
"loss": 4.8406,
|
|
"mean_token_accuracy": 0.22037224620580673,
|
|
"num_tokens": 78069263.0,
|
|
"step": 42430
|
|
},
|
|
{
|
|
"entropy": 5.558064937591553,
|
|
"epoch": 3.5445205479452055,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037777335920440545,
|
|
"loss": 4.7899,
|
|
"mean_token_accuracy": 0.22625440806150438,
|
|
"num_tokens": 78079050.0,
|
|
"step": 42435
|
|
},
|
|
{
|
|
"entropy": 5.538376331329346,
|
|
"epoch": 3.5449381891079184,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003777468753919386,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.22839747071266175,
|
|
"num_tokens": 78089430.0,
|
|
"step": 42440
|
|
},
|
|
{
|
|
"entropy": 5.556681823730469,
|
|
"epoch": 3.5453558302706316,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00037772038978076404,
|
|
"loss": 4.7766,
|
|
"mean_token_accuracy": 0.23079847246408464,
|
|
"num_tokens": 78098094.0,
|
|
"step": 42445
|
|
},
|
|
{
|
|
"entropy": 5.49946608543396,
|
|
"epoch": 3.5457734714333444,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037769390237134536,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.23199748396873474,
|
|
"num_tokens": 78106707.0,
|
|
"step": 42450
|
|
},
|
|
{
|
|
"entropy": 5.435490608215332,
|
|
"epoch": 3.5461911125960572,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003776674131641464,
|
|
"loss": 4.6119,
|
|
"mean_token_accuracy": 0.24823305010795593,
|
|
"num_tokens": 78115492.0,
|
|
"step": 42455
|
|
},
|
|
{
|
|
"entropy": 5.415101099014282,
|
|
"epoch": 3.5466087537587705,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003776409221596307,
|
|
"loss": 4.7042,
|
|
"mean_token_accuracy": 0.24087062776088713,
|
|
"num_tokens": 78124516.0,
|
|
"step": 42460
|
|
},
|
|
{
|
|
"entropy": 5.4168466091156,
|
|
"epoch": 3.5470263949214833,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003776144293582621,
|
|
"loss": 4.6199,
|
|
"mean_token_accuracy": 0.24276404082775116,
|
|
"num_tokens": 78133061.0,
|
|
"step": 42465
|
|
},
|
|
{
|
|
"entropy": 5.471998691558838,
|
|
"epoch": 3.5474440360841966,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0003775879347605045,
|
|
"loss": 4.7369,
|
|
"mean_token_accuracy": 0.2351287543773651,
|
|
"num_tokens": 78140982.0,
|
|
"step": 42470
|
|
},
|
|
{
|
|
"entropy": 5.469826507568359,
|
|
"epoch": 3.5478616772469094,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00037756143836682163,
|
|
"loss": 4.7045,
|
|
"mean_token_accuracy": 0.23510983884334563,
|
|
"num_tokens": 78150615.0,
|
|
"step": 42475
|
|
},
|
|
{
|
|
"entropy": 5.524050188064575,
|
|
"epoch": 3.548279318409622,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003775349401776772,
|
|
"loss": 4.6971,
|
|
"mean_token_accuracy": 0.23687895238399506,
|
|
"num_tokens": 78159387.0,
|
|
"step": 42480
|
|
},
|
|
{
|
|
"entropy": 5.527919006347656,
|
|
"epoch": 3.5486969595723354,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00037750844019353525,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.23282529711723327,
|
|
"num_tokens": 78168991.0,
|
|
"step": 42485
|
|
},
|
|
{
|
|
"entropy": 5.525769758224487,
|
|
"epoch": 3.5491146007350487,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003774819384148598,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.23317942172288894,
|
|
"num_tokens": 78178714.0,
|
|
"step": 42490
|
|
},
|
|
{
|
|
"entropy": 5.4449450969696045,
|
|
"epoch": 3.5495322418977615,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003774554348421145,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.23334405124187468,
|
|
"num_tokens": 78187171.0,
|
|
"step": 42495
|
|
},
|
|
{
|
|
"entropy": 5.5454775333404545,
|
|
"epoch": 3.5499498830604743,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003774289294757636,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.2306920126080513,
|
|
"num_tokens": 78196381.0,
|
|
"step": 42500
|
|
},
|
|
{
|
|
"entropy": 5.517455434799194,
|
|
"epoch": 3.5503675242231876,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00037740242231627086,
|
|
"loss": 4.6714,
|
|
"mean_token_accuracy": 0.23215475529432297,
|
|
"num_tokens": 78204703.0,
|
|
"step": 42505
|
|
},
|
|
{
|
|
"entropy": 5.488183450698853,
|
|
"epoch": 3.5507851653859004,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003773759133641006,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.23512462079524993,
|
|
"num_tokens": 78214087.0,
|
|
"step": 42510
|
|
},
|
|
{
|
|
"entropy": 5.560493755340576,
|
|
"epoch": 3.5512028065486136,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003773494026197166,
|
|
"loss": 4.7964,
|
|
"mean_token_accuracy": 0.2379402458667755,
|
|
"num_tokens": 78223235.0,
|
|
"step": 42515
|
|
},
|
|
{
|
|
"entropy": 5.574945163726807,
|
|
"epoch": 3.5516204477113265,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00037732289008358326,
|
|
"loss": 4.7806,
|
|
"mean_token_accuracy": 0.23147086799144745,
|
|
"num_tokens": 78232097.0,
|
|
"step": 42520
|
|
},
|
|
{
|
|
"entropy": 5.539983510971069,
|
|
"epoch": 3.5520380888740393,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003772963757561644,
|
|
"loss": 4.6862,
|
|
"mean_token_accuracy": 0.23179802894592286,
|
|
"num_tokens": 78241346.0,
|
|
"step": 42525
|
|
},
|
|
{
|
|
"entropy": 5.533029222488404,
|
|
"epoch": 3.5524557300367525,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037726985963792455,
|
|
"loss": 4.7345,
|
|
"mean_token_accuracy": 0.23868580162525177,
|
|
"num_tokens": 78250680.0,
|
|
"step": 42530
|
|
},
|
|
{
|
|
"entropy": 5.558607769012451,
|
|
"epoch": 3.5528733711994653,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00037724334172932754,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.22874140739440918,
|
|
"num_tokens": 78259447.0,
|
|
"step": 42535
|
|
},
|
|
{
|
|
"entropy": 5.5148662567138675,
|
|
"epoch": 3.5532910123621786,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003772168220308379,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.23613128811120987,
|
|
"num_tokens": 78269144.0,
|
|
"step": 42540
|
|
},
|
|
{
|
|
"entropy": 5.454099178314209,
|
|
"epoch": 3.5537086535248914,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00037719030054291967,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.2414055123925209,
|
|
"num_tokens": 78277386.0,
|
|
"step": 42545
|
|
},
|
|
{
|
|
"entropy": 5.48111891746521,
|
|
"epoch": 3.554126294687604,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003771637772660372,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.23627922534942628,
|
|
"num_tokens": 78287478.0,
|
|
"step": 42550
|
|
},
|
|
{
|
|
"entropy": 5.5636128902435305,
|
|
"epoch": 3.5545439358503175,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003771372522006549,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.23785865008831025,
|
|
"num_tokens": 78296304.0,
|
|
"step": 42555
|
|
},
|
|
{
|
|
"entropy": 5.5179259300231935,
|
|
"epoch": 3.5549615770130303,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00037711072534723697,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.23651142418384552,
|
|
"num_tokens": 78305248.0,
|
|
"step": 42560
|
|
},
|
|
{
|
|
"entropy": 5.497928047180176,
|
|
"epoch": 3.5553792181757435,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003770841967062479,
|
|
"loss": 4.6483,
|
|
"mean_token_accuracy": 0.23857744187116622,
|
|
"num_tokens": 78314754.0,
|
|
"step": 42565
|
|
},
|
|
{
|
|
"entropy": 5.506681728363037,
|
|
"epoch": 3.5557968593384564,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00037705766627815215,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.2363617703318596,
|
|
"num_tokens": 78324477.0,
|
|
"step": 42570
|
|
},
|
|
{
|
|
"entropy": 5.485788249969483,
|
|
"epoch": 3.556214500501169,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003770311340634141,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.23033256828784943,
|
|
"num_tokens": 78333104.0,
|
|
"step": 42575
|
|
},
|
|
{
|
|
"entropy": 5.48140811920166,
|
|
"epoch": 3.5566321416638824,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003770046000624982,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.2412683770060539,
|
|
"num_tokens": 78341609.0,
|
|
"step": 42580
|
|
},
|
|
{
|
|
"entropy": 5.5523967266082765,
|
|
"epoch": 3.5570497828265952,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00037697806427586895,
|
|
"loss": 4.8586,
|
|
"mean_token_accuracy": 0.230201555788517,
|
|
"num_tokens": 78350880.0,
|
|
"step": 42585
|
|
},
|
|
{
|
|
"entropy": 5.534128904342651,
|
|
"epoch": 3.5574674239893085,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000376951526703991,
|
|
"loss": 4.8099,
|
|
"mean_token_accuracy": 0.2299109384417534,
|
|
"num_tokens": 78360492.0,
|
|
"step": 42590
|
|
},
|
|
{
|
|
"entropy": 5.509263229370117,
|
|
"epoch": 3.5578850651520213,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003769249873473289,
|
|
"loss": 4.6244,
|
|
"mean_token_accuracy": 0.2448982462286949,
|
|
"num_tokens": 78369821.0,
|
|
"step": 42595
|
|
},
|
|
{
|
|
"entropy": 5.482546424865722,
|
|
"epoch": 3.558302706314734,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00037689844620634707,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.23549297899007798,
|
|
"num_tokens": 78378663.0,
|
|
"step": 42600
|
|
},
|
|
{
|
|
"entropy": 5.503321933746338,
|
|
"epoch": 3.5587203474774474,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003768719032815104,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.23163139820098877,
|
|
"num_tokens": 78387499.0,
|
|
"step": 42605
|
|
},
|
|
{
|
|
"entropy": 5.488944149017334,
|
|
"epoch": 3.5591379886401606,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037684535857328337,
|
|
"loss": 4.6746,
|
|
"mean_token_accuracy": 0.23784682750701905,
|
|
"num_tokens": 78396952.0,
|
|
"step": 42610
|
|
},
|
|
{
|
|
"entropy": 5.494962596893311,
|
|
"epoch": 3.5595556298028734,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003768188120821308,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.24502334594726563,
|
|
"num_tokens": 78406245.0,
|
|
"step": 42615
|
|
},
|
|
{
|
|
"entropy": 5.559338808059692,
|
|
"epoch": 3.5599732709655862,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00037679226380851733,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.23719029724597931,
|
|
"num_tokens": 78416546.0,
|
|
"step": 42620
|
|
},
|
|
{
|
|
"entropy": 5.4638769149780275,
|
|
"epoch": 3.5603909121282995,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003767657137529078,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.23298730403184892,
|
|
"num_tokens": 78425799.0,
|
|
"step": 42625
|
|
},
|
|
{
|
|
"entropy": 5.5397954940795895,
|
|
"epoch": 3.5608085532910123,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003767391619157669,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.23767286241054536,
|
|
"num_tokens": 78434494.0,
|
|
"step": 42630
|
|
},
|
|
{
|
|
"entropy": 5.523517274856568,
|
|
"epoch": 3.5612261944537256,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003767126082975595,
|
|
"loss": 4.7203,
|
|
"mean_token_accuracy": 0.23614254742860794,
|
|
"num_tokens": 78444779.0,
|
|
"step": 42635
|
|
},
|
|
{
|
|
"entropy": 5.5083592414855955,
|
|
"epoch": 3.5616438356164384,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037668605289875053,
|
|
"loss": 4.7201,
|
|
"mean_token_accuracy": 0.23240746110677718,
|
|
"num_tokens": 78453143.0,
|
|
"step": 42640
|
|
},
|
|
{
|
|
"entropy": 5.546871614456177,
|
|
"epoch": 3.562061476779151,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003766594957198047,
|
|
"loss": 4.7695,
|
|
"mean_token_accuracy": 0.22893851697444917,
|
|
"num_tokens": 78462445.0,
|
|
"step": 42645
|
|
},
|
|
{
|
|
"entropy": 5.516882514953613,
|
|
"epoch": 3.5624791179418644,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00037663293676118713,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.23018304258584976,
|
|
"num_tokens": 78471813.0,
|
|
"step": 42650
|
|
},
|
|
{
|
|
"entropy": 5.522656106948853,
|
|
"epoch": 3.5628967591045773,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003766063760233627,
|
|
"loss": 4.754,
|
|
"mean_token_accuracy": 0.2375282272696495,
|
|
"num_tokens": 78480303.0,
|
|
"step": 42655
|
|
},
|
|
{
|
|
"entropy": 5.577239179611206,
|
|
"epoch": 3.5633144002672905,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003765798135067962,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.2295868068933487,
|
|
"num_tokens": 78489321.0,
|
|
"step": 42660
|
|
},
|
|
{
|
|
"entropy": 5.455659341812134,
|
|
"epoch": 3.5637320414300033,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037655324921195295,
|
|
"loss": 4.6612,
|
|
"mean_token_accuracy": 0.23881842494010924,
|
|
"num_tokens": 78498516.0,
|
|
"step": 42665
|
|
},
|
|
{
|
|
"entropy": 5.5072120189666744,
|
|
"epoch": 3.564149682592716,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003765266831392977,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.23354752212762833,
|
|
"num_tokens": 78508150.0,
|
|
"step": 42670
|
|
},
|
|
{
|
|
"entropy": 5.534505462646484,
|
|
"epoch": 3.5645673237554294,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003765001152892958,
|
|
"loss": 4.6685,
|
|
"mean_token_accuracy": 0.24083679765462876,
|
|
"num_tokens": 78517102.0,
|
|
"step": 42675
|
|
},
|
|
{
|
|
"entropy": 5.500838327407837,
|
|
"epoch": 3.564984964918142,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00037647354566241206,
|
|
"loss": 4.6331,
|
|
"mean_token_accuracy": 0.25111185759305954,
|
|
"num_tokens": 78525643.0,
|
|
"step": 42680
|
|
},
|
|
{
|
|
"entropy": 5.492708396911621,
|
|
"epoch": 3.5654026060808555,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003764469742591118,
|
|
"loss": 4.7984,
|
|
"mean_token_accuracy": 0.23208640813827514,
|
|
"num_tokens": 78535876.0,
|
|
"step": 42685
|
|
},
|
|
{
|
|
"entropy": 5.527159023284912,
|
|
"epoch": 3.5658202472435683,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003764204010798602,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.23493921756744385,
|
|
"num_tokens": 78544717.0,
|
|
"step": 42690
|
|
},
|
|
{
|
|
"entropy": 5.534270238876343,
|
|
"epoch": 3.566237888406281,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003763938261251224,
|
|
"loss": 4.6459,
|
|
"mean_token_accuracy": 0.24046459943056106,
|
|
"num_tokens": 78553787.0,
|
|
"step": 42695
|
|
},
|
|
{
|
|
"entropy": 5.553187704086303,
|
|
"epoch": 3.5666555295689943,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003763672493953636,
|
|
"loss": 4.7655,
|
|
"mean_token_accuracy": 0.2273678734898567,
|
|
"num_tokens": 78562721.0,
|
|
"step": 42700
|
|
},
|
|
{
|
|
"entropy": 5.527552509307862,
|
|
"epoch": 3.567073170731707,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00037634067089104906,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.23580588549375534,
|
|
"num_tokens": 78572690.0,
|
|
"step": 42705
|
|
},
|
|
{
|
|
"entropy": 5.518928527832031,
|
|
"epoch": 3.5674908118944204,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037631409061264406,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.2358771488070488,
|
|
"num_tokens": 78581729.0,
|
|
"step": 42710
|
|
},
|
|
{
|
|
"entropy": 5.480405282974243,
|
|
"epoch": 3.5679084530571332,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003762875085606141,
|
|
"loss": 4.6083,
|
|
"mean_token_accuracy": 0.24458657205104828,
|
|
"num_tokens": 78589766.0,
|
|
"step": 42715
|
|
},
|
|
{
|
|
"entropy": 5.528640031814575,
|
|
"epoch": 3.568326094219846,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003762609247354242,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.22654480040073394,
|
|
"num_tokens": 78600131.0,
|
|
"step": 42720
|
|
},
|
|
{
|
|
"entropy": 5.549263572692871,
|
|
"epoch": 3.5687437353825593,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00037623433913754,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.23648113161325454,
|
|
"num_tokens": 78609742.0,
|
|
"step": 42725
|
|
},
|
|
{
|
|
"entropy": 5.544564867019654,
|
|
"epoch": 3.5691613765452725,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003762077517674269,
|
|
"loss": 4.6858,
|
|
"mean_token_accuracy": 0.23753711581230164,
|
|
"num_tokens": 78619417.0,
|
|
"step": 42730
|
|
},
|
|
{
|
|
"entropy": 5.518265724182129,
|
|
"epoch": 3.5695790177079854,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00037618116262555024,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.23143401443958284,
|
|
"num_tokens": 78628230.0,
|
|
"step": 42735
|
|
},
|
|
{
|
|
"entropy": 5.4617753505706785,
|
|
"epoch": 3.569996658870698,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003761545717123755,
|
|
"loss": 4.6237,
|
|
"mean_token_accuracy": 0.24070731699466705,
|
|
"num_tokens": 78636654.0,
|
|
"step": 42740
|
|
},
|
|
{
|
|
"entropy": 5.53738694190979,
|
|
"epoch": 3.5704143000334114,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003761279790283682,
|
|
"loss": 4.7724,
|
|
"mean_token_accuracy": 0.22755504995584488,
|
|
"num_tokens": 78646150.0,
|
|
"step": 42745
|
|
},
|
|
{
|
|
"entropy": 5.419343280792236,
|
|
"epoch": 3.5708319411961242,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00037610138457399396,
|
|
"loss": 4.6036,
|
|
"mean_token_accuracy": 0.25275774151086805,
|
|
"num_tokens": 78654399.0,
|
|
"step": 42750
|
|
},
|
|
{
|
|
"entropy": 5.505546379089355,
|
|
"epoch": 3.5712495823588375,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003760747883497183,
|
|
"loss": 4.7205,
|
|
"mean_token_accuracy": 0.23279182463884354,
|
|
"num_tokens": 78663372.0,
|
|
"step": 42755
|
|
},
|
|
{
|
|
"entropy": 5.490848875045776,
|
|
"epoch": 3.5716672235215503,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003760481903560068,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.23277588188648224,
|
|
"num_tokens": 78672278.0,
|
|
"step": 42760
|
|
},
|
|
{
|
|
"entropy": 5.572363758087159,
|
|
"epoch": 3.572084864684263,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00037602159059332504,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.22840598225593567,
|
|
"num_tokens": 78682706.0,
|
|
"step": 42765
|
|
},
|
|
{
|
|
"entropy": 5.522179508209229,
|
|
"epoch": 3.5725025058469764,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037599498906213877,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.23821091651916504,
|
|
"num_tokens": 78692347.0,
|
|
"step": 42770
|
|
},
|
|
{
|
|
"entropy": 5.5012139797210695,
|
|
"epoch": 3.572920147009689,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00037596838576291365,
|
|
"loss": 4.6838,
|
|
"mean_token_accuracy": 0.24481706619262694,
|
|
"num_tokens": 78702018.0,
|
|
"step": 42775
|
|
},
|
|
{
|
|
"entropy": 5.519258880615235,
|
|
"epoch": 3.5733377881724024,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003759417806961154,
|
|
"loss": 4.7236,
|
|
"mean_token_accuracy": 0.24026810377836227,
|
|
"num_tokens": 78710519.0,
|
|
"step": 42780
|
|
},
|
|
{
|
|
"entropy": 5.593927812576294,
|
|
"epoch": 3.5737554293351153,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0003759151738622098,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.22250587046146392,
|
|
"num_tokens": 78720179.0,
|
|
"step": 42785
|
|
},
|
|
{
|
|
"entropy": 5.5743865966796875,
|
|
"epoch": 3.574173070497828,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037588856526166257,
|
|
"loss": 4.7649,
|
|
"mean_token_accuracy": 0.23235969990491867,
|
|
"num_tokens": 78729693.0,
|
|
"step": 42790
|
|
},
|
|
{
|
|
"entropy": 5.590786743164062,
|
|
"epoch": 3.5745907116605413,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00037586195489493955,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.2336878925561905,
|
|
"num_tokens": 78738632.0,
|
|
"step": 42795
|
|
},
|
|
{
|
|
"entropy": 5.569298505783081,
|
|
"epoch": 3.575008352823254,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003758353427625066,
|
|
"loss": 4.7207,
|
|
"mean_token_accuracy": 0.2376238077878952,
|
|
"num_tokens": 78747737.0,
|
|
"step": 42800
|
|
},
|
|
{
|
|
"entropy": 5.56203293800354,
|
|
"epoch": 3.5754259939859674,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003758087288648297,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.23337833285331727,
|
|
"num_tokens": 78758062.0,
|
|
"step": 42805
|
|
},
|
|
{
|
|
"entropy": 5.575504541397095,
|
|
"epoch": 3.57584363514868,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00037578211320237457,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.23701179027557373,
|
|
"num_tokens": 78766265.0,
|
|
"step": 42810
|
|
},
|
|
{
|
|
"entropy": 5.5089398384094235,
|
|
"epoch": 3.576261276311393,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003757554957756072,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.23539893925189972,
|
|
"num_tokens": 78775873.0,
|
|
"step": 42815
|
|
},
|
|
{
|
|
"entropy": 5.457468795776367,
|
|
"epoch": 3.5766789174741063,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003757288765849937,
|
|
"loss": 4.6294,
|
|
"mean_token_accuracy": 0.2490455761551857,
|
|
"num_tokens": 78783738.0,
|
|
"step": 42820
|
|
},
|
|
{
|
|
"entropy": 5.465191459655761,
|
|
"epoch": 3.577096558636819,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00037570225563099993,
|
|
"loss": 4.6962,
|
|
"mean_token_accuracy": 0.23798711895942687,
|
|
"num_tokens": 78792570.0,
|
|
"step": 42825
|
|
},
|
|
{
|
|
"entropy": 5.4901210308074955,
|
|
"epoch": 3.5775141997995323,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000375675632914092,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.24258116036653518,
|
|
"num_tokens": 78802239.0,
|
|
"step": 42830
|
|
},
|
|
{
|
|
"entropy": 5.614226770401001,
|
|
"epoch": 3.577931840962245,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00037564900843473585,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.23523856997489928,
|
|
"num_tokens": 78811738.0,
|
|
"step": 42835
|
|
},
|
|
{
|
|
"entropy": 5.397103500366211,
|
|
"epoch": 3.578349482124958,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003756223821933978,
|
|
"loss": 4.5285,
|
|
"mean_token_accuracy": 0.25658755749464035,
|
|
"num_tokens": 78820499.0,
|
|
"step": 42840
|
|
},
|
|
{
|
|
"entropy": 5.490719985961914,
|
|
"epoch": 3.578767123287671,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003755957541905436,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.23081300556659698,
|
|
"num_tokens": 78830139.0,
|
|
"step": 42845
|
|
},
|
|
{
|
|
"entropy": 5.526059103012085,
|
|
"epoch": 3.5791847644503845,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003755691244266398,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.2336640700697899,
|
|
"num_tokens": 78839407.0,
|
|
"step": 42850
|
|
},
|
|
{
|
|
"entropy": 5.578751945495606,
|
|
"epoch": 3.5796024056130973,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003755424929021524,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.23718461394309998,
|
|
"num_tokens": 78848572.0,
|
|
"step": 42855
|
|
},
|
|
{
|
|
"entropy": 5.545911169052124,
|
|
"epoch": 3.58002004677581,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037551585961754765,
|
|
"loss": 4.7064,
|
|
"mean_token_accuracy": 0.23684405237436296,
|
|
"num_tokens": 78857116.0,
|
|
"step": 42860
|
|
},
|
|
{
|
|
"entropy": 5.493846035003662,
|
|
"epoch": 3.5804376879385234,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00037548922457329167,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.2304847478866577,
|
|
"num_tokens": 78866173.0,
|
|
"step": 42865
|
|
},
|
|
{
|
|
"entropy": 5.505682849884034,
|
|
"epoch": 3.580855329101236,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000375462587769851,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.23601986169815065,
|
|
"num_tokens": 78875020.0,
|
|
"step": 42870
|
|
},
|
|
{
|
|
"entropy": 5.426651048660278,
|
|
"epoch": 3.5812729702639494,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003754359492076917,
|
|
"loss": 4.7123,
|
|
"mean_token_accuracy": 0.23252568542957305,
|
|
"num_tokens": 78885537.0,
|
|
"step": 42875
|
|
},
|
|
{
|
|
"entropy": 5.6464207649230955,
|
|
"epoch": 3.5816906114266622,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037540930888728033,
|
|
"loss": 4.7647,
|
|
"mean_token_accuracy": 0.2347438007593155,
|
|
"num_tokens": 78894387.0,
|
|
"step": 42880
|
|
},
|
|
{
|
|
"entropy": 5.490080213546753,
|
|
"epoch": 3.582108252589375,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00037538266680908305,
|
|
"loss": 4.6578,
|
|
"mean_token_accuracy": 0.24387031942605972,
|
|
"num_tokens": 78902948.0,
|
|
"step": 42885
|
|
},
|
|
{
|
|
"entropy": 5.483932209014893,
|
|
"epoch": 3.5825258937520883,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0003753560229735664,
|
|
"loss": 4.6566,
|
|
"mean_token_accuracy": 0.24319751262664796,
|
|
"num_tokens": 78911334.0,
|
|
"step": 42890
|
|
},
|
|
{
|
|
"entropy": 5.557563066482544,
|
|
"epoch": 3.582943534914801,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003753293773811967,
|
|
"loss": 4.8623,
|
|
"mean_token_accuracy": 0.22526898980140686,
|
|
"num_tokens": 78920449.0,
|
|
"step": 42895
|
|
},
|
|
{
|
|
"entropy": 5.480230760574341,
|
|
"epoch": 3.5833611760775144,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003753027300324405,
|
|
"loss": 4.6532,
|
|
"mean_token_accuracy": 0.2370762676000595,
|
|
"num_tokens": 78929128.0,
|
|
"step": 42900
|
|
},
|
|
{
|
|
"entropy": 5.469385814666748,
|
|
"epoch": 3.583778817240227,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00037527608092776434,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.24486369788646697,
|
|
"num_tokens": 78937751.0,
|
|
"step": 42905
|
|
},
|
|
{
|
|
"entropy": 5.504137420654297,
|
|
"epoch": 3.58419645840294,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003752494300676347,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.22627494037151336,
|
|
"num_tokens": 78948507.0,
|
|
"step": 42910
|
|
},
|
|
{
|
|
"entropy": 5.58908863067627,
|
|
"epoch": 3.5846140995656532,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037522277745251803,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.22681906521320344,
|
|
"num_tokens": 78957768.0,
|
|
"step": 42915
|
|
},
|
|
{
|
|
"entropy": 5.595856714248657,
|
|
"epoch": 3.585031740728366,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000375196123082881,
|
|
"loss": 4.7301,
|
|
"mean_token_accuracy": 0.23206952810287476,
|
|
"num_tokens": 78967503.0,
|
|
"step": 42920
|
|
},
|
|
{
|
|
"entropy": 5.626986122131347,
|
|
"epoch": 3.5854493818910793,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003751694669591903,
|
|
"loss": 4.8651,
|
|
"mean_token_accuracy": 0.22341950386762618,
|
|
"num_tokens": 78976393.0,
|
|
"step": 42925
|
|
},
|
|
{
|
|
"entropy": 5.550383996963501,
|
|
"epoch": 3.585867023053792,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003751428090819125,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.2367844268679619,
|
|
"num_tokens": 78984659.0,
|
|
"step": 42930
|
|
},
|
|
{
|
|
"entropy": 5.573420238494873,
|
|
"epoch": 3.586284664216505,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003751161494515143,
|
|
"loss": 4.7395,
|
|
"mean_token_accuracy": 0.2388855442404747,
|
|
"num_tokens": 78993942.0,
|
|
"step": 42935
|
|
},
|
|
{
|
|
"entropy": 5.501931238174438,
|
|
"epoch": 3.586702305379218,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003750894880684623,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.24155893325805664,
|
|
"num_tokens": 79002842.0,
|
|
"step": 42940
|
|
},
|
|
{
|
|
"entropy": 5.5207664489746096,
|
|
"epoch": 3.5871199465419314,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003750628249332234,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.23347517102956772,
|
|
"num_tokens": 79011516.0,
|
|
"step": 42945
|
|
},
|
|
{
|
|
"entropy": 5.527609205245971,
|
|
"epoch": 3.5875375877046443,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00037503616004626436,
|
|
"loss": 4.6548,
|
|
"mean_token_accuracy": 0.24396401792764663,
|
|
"num_tokens": 79019585.0,
|
|
"step": 42950
|
|
},
|
|
{
|
|
"entropy": 5.548814725875855,
|
|
"epoch": 3.587955228867357,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003750094934080518,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.23050334453582763,
|
|
"num_tokens": 79029513.0,
|
|
"step": 42955
|
|
},
|
|
{
|
|
"entropy": 5.514334392547608,
|
|
"epoch": 3.5883728700300703,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00037498282501905274,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.2293678417801857,
|
|
"num_tokens": 79039605.0,
|
|
"step": 42960
|
|
},
|
|
{
|
|
"entropy": 5.520034885406494,
|
|
"epoch": 3.588790511192783,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00037495615487973395,
|
|
"loss": 4.7586,
|
|
"mean_token_accuracy": 0.23169469833374023,
|
|
"num_tokens": 79049861.0,
|
|
"step": 42965
|
|
},
|
|
{
|
|
"entropy": 5.536627388000488,
|
|
"epoch": 3.5892081523554964,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00037492948299056245,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.22453655898571015,
|
|
"num_tokens": 79059151.0,
|
|
"step": 42970
|
|
},
|
|
{
|
|
"entropy": 5.539570760726929,
|
|
"epoch": 3.589625793518209,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037490280935200494,
|
|
"loss": 4.6579,
|
|
"mean_token_accuracy": 0.23267740458250047,
|
|
"num_tokens": 79068036.0,
|
|
"step": 42975
|
|
},
|
|
{
|
|
"entropy": 5.544914674758911,
|
|
"epoch": 3.590043434680922,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003748761339645285,
|
|
"loss": 4.7905,
|
|
"mean_token_accuracy": 0.22403693646192552,
|
|
"num_tokens": 79077184.0,
|
|
"step": 42980
|
|
},
|
|
{
|
|
"entropy": 5.6146105289459225,
|
|
"epoch": 3.5904610758436353,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003748494568286002,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.22643817067146302,
|
|
"num_tokens": 79087270.0,
|
|
"step": 42985
|
|
},
|
|
{
|
|
"entropy": 5.500226402282715,
|
|
"epoch": 3.590878717006348,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003748227779446869,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.23659496903419494,
|
|
"num_tokens": 79095880.0,
|
|
"step": 42990
|
|
},
|
|
{
|
|
"entropy": 5.484222078323365,
|
|
"epoch": 3.5912963581690613,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00037479609731325576,
|
|
"loss": 4.6772,
|
|
"mean_token_accuracy": 0.2361557275056839,
|
|
"num_tokens": 79105426.0,
|
|
"step": 42995
|
|
},
|
|
{
|
|
"entropy": 5.492887735366821,
|
|
"epoch": 3.591713999331774,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00037476941493477377,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.22453104555606843,
|
|
"num_tokens": 79114448.0,
|
|
"step": 43000
|
|
},
|
|
{
|
|
"entropy": 5.55279541015625,
|
|
"epoch": 3.592131640494487,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00037474273080970817,
|
|
"loss": 4.7287,
|
|
"mean_token_accuracy": 0.23657046258449554,
|
|
"num_tokens": 79123289.0,
|
|
"step": 43005
|
|
},
|
|
{
|
|
"entropy": 5.495260524749756,
|
|
"epoch": 3.5925492816572,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003747160449385259,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.22435907125473023,
|
|
"num_tokens": 79132371.0,
|
|
"step": 43010
|
|
},
|
|
{
|
|
"entropy": 5.4383015632629395,
|
|
"epoch": 3.592966922819913,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037468935732169436,
|
|
"loss": 4.6158,
|
|
"mean_token_accuracy": 0.2358902543783188,
|
|
"num_tokens": 79141085.0,
|
|
"step": 43015
|
|
},
|
|
{
|
|
"entropy": 5.529827499389649,
|
|
"epoch": 3.5933845639826263,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037466266795968046,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.23539526611566544,
|
|
"num_tokens": 79150100.0,
|
|
"step": 43020
|
|
},
|
|
{
|
|
"entropy": 5.5541181564331055,
|
|
"epoch": 3.593802205145339,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003746359768529518,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.23504653871059417,
|
|
"num_tokens": 79159025.0,
|
|
"step": 43025
|
|
},
|
|
{
|
|
"entropy": 5.456237268447876,
|
|
"epoch": 3.594219846308052,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00037460928400197523,
|
|
"loss": 4.719,
|
|
"mean_token_accuracy": 0.23504422158002852,
|
|
"num_tokens": 79168427.0,
|
|
"step": 43030
|
|
},
|
|
{
|
|
"entropy": 5.485702896118164,
|
|
"epoch": 3.594637487470765,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037458258940721833,
|
|
"loss": 4.6586,
|
|
"mean_token_accuracy": 0.24317186325788498,
|
|
"num_tokens": 79177591.0,
|
|
"step": 43035
|
|
},
|
|
{
|
|
"entropy": 5.539004468917847,
|
|
"epoch": 3.595055128633478,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003745558930691483,
|
|
"loss": 4.6594,
|
|
"mean_token_accuracy": 0.23768825978040695,
|
|
"num_tokens": 79187575.0,
|
|
"step": 43040
|
|
},
|
|
{
|
|
"entropy": 5.475757598876953,
|
|
"epoch": 3.5954727697961912,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00037452919498823256,
|
|
"loss": 4.748,
|
|
"mean_token_accuracy": 0.23186832070350646,
|
|
"num_tokens": 79197136.0,
|
|
"step": 43045
|
|
},
|
|
{
|
|
"entropy": 5.42528805732727,
|
|
"epoch": 3.595890410958904,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003745024951649385,
|
|
"loss": 4.6403,
|
|
"mean_token_accuracy": 0.24277279824018477,
|
|
"num_tokens": 79206383.0,
|
|
"step": 43050
|
|
},
|
|
{
|
|
"entropy": 5.54544997215271,
|
|
"epoch": 3.596308052121617,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037447579359973344,
|
|
"loss": 4.777,
|
|
"mean_token_accuracy": 0.2292303904891014,
|
|
"num_tokens": 79215566.0,
|
|
"step": 43055
|
|
},
|
|
{
|
|
"entropy": 5.593872928619385,
|
|
"epoch": 3.59672569328433,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003744490902930848,
|
|
"loss": 4.7644,
|
|
"mean_token_accuracy": 0.22966626584529876,
|
|
"num_tokens": 79225119.0,
|
|
"step": 43060
|
|
},
|
|
{
|
|
"entropy": 5.589255857467651,
|
|
"epoch": 3.5971433344470434,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003744223852454603,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.2215807095170021,
|
|
"num_tokens": 79235972.0,
|
|
"step": 43065
|
|
},
|
|
{
|
|
"entropy": 5.642422771453857,
|
|
"epoch": 3.597560975609756,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003743956784573271,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.2180449903011322,
|
|
"num_tokens": 79245037.0,
|
|
"step": 43070
|
|
},
|
|
{
|
|
"entropy": 5.559177732467651,
|
|
"epoch": 3.597978616772469,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00037436896992915303,
|
|
"loss": 4.7417,
|
|
"mean_token_accuracy": 0.23371059745550155,
|
|
"num_tokens": 79254409.0,
|
|
"step": 43075
|
|
},
|
|
{
|
|
"entropy": 5.48680477142334,
|
|
"epoch": 3.5983962579351823,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003743422596614055,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.24231091737747193,
|
|
"num_tokens": 79262980.0,
|
|
"step": 43080
|
|
},
|
|
{
|
|
"entropy": 5.487056016921997,
|
|
"epoch": 3.598813899097895,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003743155476545521,
|
|
"loss": 4.6526,
|
|
"mean_token_accuracy": 0.24803757518529893,
|
|
"num_tokens": 79272575.0,
|
|
"step": 43085
|
|
},
|
|
{
|
|
"entropy": 5.514851093292236,
|
|
"epoch": 3.5992315402606083,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00037428883390906053,
|
|
"loss": 4.7188,
|
|
"mean_token_accuracy": 0.23115543276071548,
|
|
"num_tokens": 79282423.0,
|
|
"step": 43090
|
|
},
|
|
{
|
|
"entropy": 5.571680164337158,
|
|
"epoch": 3.599649181423321,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00037426211842539844,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.22595798075199128,
|
|
"num_tokens": 79292297.0,
|
|
"step": 43095
|
|
},
|
|
{
|
|
"entropy": 5.525275993347168,
|
|
"epoch": 3.600066822586034,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037423540120403337,
|
|
"loss": 4.7035,
|
|
"mean_token_accuracy": 0.23711466640233994,
|
|
"num_tokens": 79301733.0,
|
|
"step": 43100
|
|
},
|
|
{
|
|
"entropy": 5.493422937393189,
|
|
"epoch": 3.600484463748747,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00037420868224543333,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.23112149387598038,
|
|
"num_tokens": 79310549.0,
|
|
"step": 43105
|
|
},
|
|
{
|
|
"entropy": 5.422953081130982,
|
|
"epoch": 3.60090210491146,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037418196155006566,
|
|
"loss": 4.6451,
|
|
"mean_token_accuracy": 0.23772785067558289,
|
|
"num_tokens": 79319267.0,
|
|
"step": 43110
|
|
},
|
|
{
|
|
"entropy": 5.570660972595215,
|
|
"epoch": 3.6013197460741733,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00037415523911839857,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.2251600742340088,
|
|
"num_tokens": 79328833.0,
|
|
"step": 43115
|
|
},
|
|
{
|
|
"entropy": 5.491389226913452,
|
|
"epoch": 3.601737387236886,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003741285149508995,
|
|
"loss": 4.625,
|
|
"mean_token_accuracy": 0.2445344179868698,
|
|
"num_tokens": 79338125.0,
|
|
"step": 43120
|
|
},
|
|
{
|
|
"entropy": 5.540163183212281,
|
|
"epoch": 3.602155028399599,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003741017890480366,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.22616127282381057,
|
|
"num_tokens": 79347537.0,
|
|
"step": 43125
|
|
},
|
|
{
|
|
"entropy": 5.471503734588623,
|
|
"epoch": 3.602572669562312,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003740750614102775,
|
|
"loss": 4.7444,
|
|
"mean_token_accuracy": 0.2414116755127907,
|
|
"num_tokens": 79356663.0,
|
|
"step": 43130
|
|
},
|
|
{
|
|
"entropy": 5.452750253677368,
|
|
"epoch": 3.602990310725025,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003740483320380903,
|
|
"loss": 4.5985,
|
|
"mean_token_accuracy": 0.2343614161014557,
|
|
"num_tokens": 79365777.0,
|
|
"step": 43135
|
|
},
|
|
{
|
|
"entropy": 5.47932767868042,
|
|
"epoch": 3.603407951887738,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00037402160093194265,
|
|
"loss": 4.7816,
|
|
"mean_token_accuracy": 0.2238544851541519,
|
|
"num_tokens": 79374685.0,
|
|
"step": 43140
|
|
},
|
|
{
|
|
"entropy": 5.449624538421631,
|
|
"epoch": 3.603825593050451,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00037399486809230285,
|
|
"loss": 4.7123,
|
|
"mean_token_accuracy": 0.2416532814502716,
|
|
"num_tokens": 79383927.0,
|
|
"step": 43145
|
|
},
|
|
{
|
|
"entropy": 5.556480503082275,
|
|
"epoch": 3.604243234213164,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037396813351963867,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.23612768650054933,
|
|
"num_tokens": 79393444.0,
|
|
"step": 43150
|
|
},
|
|
{
|
|
"entropy": 5.495502376556397,
|
|
"epoch": 3.604660875375877,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003739413972144182,
|
|
"loss": 4.6937,
|
|
"mean_token_accuracy": 0.23356471359729766,
|
|
"num_tokens": 79402681.0,
|
|
"step": 43155
|
|
},
|
|
{
|
|
"entropy": 5.511634778976441,
|
|
"epoch": 3.60507851653859,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003739146591771093,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.23254636377096177,
|
|
"num_tokens": 79412184.0,
|
|
"step": 43160
|
|
},
|
|
{
|
|
"entropy": 5.5719719409942625,
|
|
"epoch": 3.605496157701303,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00037388791940818044,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.23209361732006073,
|
|
"num_tokens": 79421312.0,
|
|
"step": 43165
|
|
},
|
|
{
|
|
"entropy": 5.553555107116699,
|
|
"epoch": 3.605913798864016,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00037386117790809946,
|
|
"loss": 4.6586,
|
|
"mean_token_accuracy": 0.2349897339940071,
|
|
"num_tokens": 79430060.0,
|
|
"step": 43170
|
|
},
|
|
{
|
|
"entropy": 5.483087158203125,
|
|
"epoch": 3.606331440026729,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00037383443467733457,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.23268236666917802,
|
|
"num_tokens": 79438822.0,
|
|
"step": 43175
|
|
},
|
|
{
|
|
"entropy": 5.484364175796509,
|
|
"epoch": 3.606749081189442,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037380768971635394,
|
|
"loss": 4.6981,
|
|
"mean_token_accuracy": 0.24942520558834075,
|
|
"num_tokens": 79447332.0,
|
|
"step": 43180
|
|
},
|
|
{
|
|
"entropy": 5.539530515670776,
|
|
"epoch": 3.6071667223521553,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003737809430256258,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.2383786678314209,
|
|
"num_tokens": 79456806.0,
|
|
"step": 43185
|
|
},
|
|
{
|
|
"entropy": 5.461817646026612,
|
|
"epoch": 3.607584363514868,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003737541946056182,
|
|
"loss": 4.6086,
|
|
"mean_token_accuracy": 0.2431545674800873,
|
|
"num_tokens": 79465678.0,
|
|
"step": 43190
|
|
},
|
|
{
|
|
"entropy": 5.520843839645385,
|
|
"epoch": 3.608002004677581,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003737274444567997,
|
|
"loss": 4.761,
|
|
"mean_token_accuracy": 0.2232660561800003,
|
|
"num_tokens": 79475323.0,
|
|
"step": 43195
|
|
},
|
|
{
|
|
"entropy": 5.444611263275147,
|
|
"epoch": 3.608419645840294,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00037370069257963836,
|
|
"loss": 4.6035,
|
|
"mean_token_accuracy": 0.2427162453532219,
|
|
"num_tokens": 79483620.0,
|
|
"step": 43200
|
|
},
|
|
{
|
|
"entropy": 5.390864896774292,
|
|
"epoch": 3.608837287003007,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003736739389746026,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.2396346300840378,
|
|
"num_tokens": 79493527.0,
|
|
"step": 43205
|
|
},
|
|
{
|
|
"entropy": 5.477487373352051,
|
|
"epoch": 3.6092549281657202,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037364718364216084,
|
|
"loss": 4.6486,
|
|
"mean_token_accuracy": 0.24056199043989182,
|
|
"num_tokens": 79502087.0,
|
|
"step": 43210
|
|
},
|
|
{
|
|
"entropy": 5.507494592666626,
|
|
"epoch": 3.609672569328433,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00037362042658278127,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.2328477457165718,
|
|
"num_tokens": 79511411.0,
|
|
"step": 43215
|
|
},
|
|
{
|
|
"entropy": 5.49079213142395,
|
|
"epoch": 3.610090210491146,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003735936677969325,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.23580240756273269,
|
|
"num_tokens": 79520414.0,
|
|
"step": 43220
|
|
},
|
|
{
|
|
"entropy": 5.464365530014038,
|
|
"epoch": 3.610507851653859,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003735669072850829,
|
|
"loss": 4.6677,
|
|
"mean_token_accuracy": 0.2379867121577263,
|
|
"num_tokens": 79528747.0,
|
|
"step": 43225
|
|
},
|
|
{
|
|
"entropy": 5.550963020324707,
|
|
"epoch": 3.610925492816572,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00037354014504770096,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.2299461543560028,
|
|
"num_tokens": 79538013.0,
|
|
"step": 43230
|
|
},
|
|
{
|
|
"entropy": 5.515107011795044,
|
|
"epoch": 3.611343133979285,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00037351338108525516,
|
|
"loss": 4.6606,
|
|
"mean_token_accuracy": 0.2402304530143738,
|
|
"num_tokens": 79546203.0,
|
|
"step": 43235
|
|
},
|
|
{
|
|
"entropy": 5.471327495574951,
|
|
"epoch": 3.611760775141998,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000373486615398214,
|
|
"loss": 4.713,
|
|
"mean_token_accuracy": 0.2334604188799858,
|
|
"num_tokens": 79554537.0,
|
|
"step": 43240
|
|
},
|
|
{
|
|
"entropy": 5.4563640594482425,
|
|
"epoch": 3.612178416304711,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003734598479870461,
|
|
"loss": 4.6847,
|
|
"mean_token_accuracy": 0.24679764360189438,
|
|
"num_tokens": 79564120.0,
|
|
"step": 43245
|
|
},
|
|
{
|
|
"entropy": 5.4502723693847654,
|
|
"epoch": 3.612596057467424,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037343307885222006,
|
|
"loss": 4.6649,
|
|
"mean_token_accuracy": 0.23589873313903809,
|
|
"num_tokens": 79573700.0,
|
|
"step": 43250
|
|
},
|
|
{
|
|
"entropy": 5.461469554901123,
|
|
"epoch": 3.613013698630137,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00037340630799420453,
|
|
"loss": 4.6329,
|
|
"mean_token_accuracy": 0.23742199689149857,
|
|
"num_tokens": 79582762.0,
|
|
"step": 43255
|
|
},
|
|
{
|
|
"entropy": 5.519874238967896,
|
|
"epoch": 3.61343133979285,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003733795354134681,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.22866492122411727,
|
|
"num_tokens": 79592138.0,
|
|
"step": 43260
|
|
},
|
|
{
|
|
"entropy": 5.407412385940551,
|
|
"epoch": 3.613848980955563,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00037335276111047946,
|
|
"loss": 4.6257,
|
|
"mean_token_accuracy": 0.243783538043499,
|
|
"num_tokens": 79601873.0,
|
|
"step": 43265
|
|
},
|
|
{
|
|
"entropy": 5.457404947280883,
|
|
"epoch": 3.6142666221182758,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003733259850857073,
|
|
"loss": 4.6873,
|
|
"mean_token_accuracy": 0.23429345935583115,
|
|
"num_tokens": 79611428.0,
|
|
"step": 43270
|
|
},
|
|
{
|
|
"entropy": 5.467794752120971,
|
|
"epoch": 3.614684263280989,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003732992073396205,
|
|
"loss": 4.6497,
|
|
"mean_token_accuracy": 0.2385060966014862,
|
|
"num_tokens": 79620972.0,
|
|
"step": 43275
|
|
},
|
|
{
|
|
"entropy": 5.467842531204224,
|
|
"epoch": 3.615101904443702,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00037327242787268776,
|
|
"loss": 4.6845,
|
|
"mean_token_accuracy": 0.24204539656639099,
|
|
"num_tokens": 79630459.0,
|
|
"step": 43280
|
|
},
|
|
{
|
|
"entropy": 5.539509630203247,
|
|
"epoch": 3.615519545606415,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00037324564668537785,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.22961021363735198,
|
|
"num_tokens": 79639620.0,
|
|
"step": 43285
|
|
},
|
|
{
|
|
"entropy": 5.478599166870117,
|
|
"epoch": 3.615937186769128,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00037321886377815965,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.2321598619222641,
|
|
"num_tokens": 79649531.0,
|
|
"step": 43290
|
|
},
|
|
{
|
|
"entropy": 5.412855958938598,
|
|
"epoch": 3.6163548279318407,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003731920791515019,
|
|
"loss": 4.5677,
|
|
"mean_token_accuracy": 0.24530048072338104,
|
|
"num_tokens": 79658248.0,
|
|
"step": 43295
|
|
},
|
|
{
|
|
"entropy": 5.486384105682373,
|
|
"epoch": 3.616772469094554,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003731652928058738,
|
|
"loss": 4.7486,
|
|
"mean_token_accuracy": 0.23571303188800813,
|
|
"num_tokens": 79666859.0,
|
|
"step": 43300
|
|
},
|
|
{
|
|
"entropy": 5.606728219985962,
|
|
"epoch": 3.617190110257267,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003731385047417439,
|
|
"loss": 4.8301,
|
|
"mean_token_accuracy": 0.22666991502046585,
|
|
"num_tokens": 79676377.0,
|
|
"step": 43305
|
|
},
|
|
{
|
|
"entropy": 5.519172239303589,
|
|
"epoch": 3.61760775141998,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003731117149595816,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.23271194994449615,
|
|
"num_tokens": 79685929.0,
|
|
"step": 43310
|
|
},
|
|
{
|
|
"entropy": 5.545610570907593,
|
|
"epoch": 3.618025392582693,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003730849234598554,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.2283010959625244,
|
|
"num_tokens": 79696119.0,
|
|
"step": 43315
|
|
},
|
|
{
|
|
"entropy": 5.419298982620239,
|
|
"epoch": 3.618443033745406,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003730581302430347,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.23137322515249253,
|
|
"num_tokens": 79704858.0,
|
|
"step": 43320
|
|
},
|
|
{
|
|
"entropy": 5.524803209304809,
|
|
"epoch": 3.618860674908119,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003730313353095882,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.23532620817422867,
|
|
"num_tokens": 79713813.0,
|
|
"step": 43325
|
|
},
|
|
{
|
|
"entropy": 5.561033821105957,
|
|
"epoch": 3.619278316070832,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003730045386599854,
|
|
"loss": 4.7929,
|
|
"mean_token_accuracy": 0.23418665081262588,
|
|
"num_tokens": 79723036.0,
|
|
"step": 43330
|
|
},
|
|
{
|
|
"entropy": 5.481854391098023,
|
|
"epoch": 3.619695957233545,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037297774029469504,
|
|
"loss": 4.6772,
|
|
"mean_token_accuracy": 0.23513068556785582,
|
|
"num_tokens": 79732079.0,
|
|
"step": 43335
|
|
},
|
|
{
|
|
"entropy": 5.5630964756011965,
|
|
"epoch": 3.620113598396258,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003729509402141864,
|
|
"loss": 4.7594,
|
|
"mean_token_accuracy": 0.2362355351448059,
|
|
"num_tokens": 79740815.0,
|
|
"step": 43340
|
|
},
|
|
{
|
|
"entropy": 5.472973394393921,
|
|
"epoch": 3.620531239558971,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003729241384189287,
|
|
"loss": 4.5962,
|
|
"mean_token_accuracy": 0.2506358206272125,
|
|
"num_tokens": 79749467.0,
|
|
"step": 43345
|
|
},
|
|
{
|
|
"entropy": 5.422174882888794,
|
|
"epoch": 3.620948880721684,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003728973349093911,
|
|
"loss": 4.6384,
|
|
"mean_token_accuracy": 0.2433561623096466,
|
|
"num_tokens": 79758480.0,
|
|
"step": 43350
|
|
},
|
|
{
|
|
"entropy": 5.501566934585571,
|
|
"epoch": 3.621366521884397,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003728705296860428,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.23878284692764282,
|
|
"num_tokens": 79767070.0,
|
|
"step": 43355
|
|
},
|
|
{
|
|
"entropy": 5.53386549949646,
|
|
"epoch": 3.62178416304711,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003728437227493531,
|
|
"loss": 4.8093,
|
|
"mean_token_accuracy": 0.22937512993812562,
|
|
"num_tokens": 79776291.0,
|
|
"step": 43360
|
|
},
|
|
{
|
|
"entropy": 5.563601064682007,
|
|
"epoch": 3.6222018042098227,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037281691409979113,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.23944152146577835,
|
|
"num_tokens": 79784655.0,
|
|
"step": 43365
|
|
},
|
|
{
|
|
"entropy": 5.479742765426636,
|
|
"epoch": 3.622619445372536,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00037279010373782645,
|
|
"loss": 4.6794,
|
|
"mean_token_accuracy": 0.24006625562906264,
|
|
"num_tokens": 79793316.0,
|
|
"step": 43370
|
|
},
|
|
{
|
|
"entropy": 5.4543036937713625,
|
|
"epoch": 3.623037086535249,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00037276329166392833,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.23387744277715683,
|
|
"num_tokens": 79801775.0,
|
|
"step": 43375
|
|
},
|
|
{
|
|
"entropy": 5.5597631454467775,
|
|
"epoch": 3.623454727697962,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00037273647787856596,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.22764378190040588,
|
|
"num_tokens": 79810730.0,
|
|
"step": 43380
|
|
},
|
|
{
|
|
"entropy": 5.450375318527222,
|
|
"epoch": 3.623872368860675,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000372709662382209,
|
|
"loss": 4.7016,
|
|
"mean_token_accuracy": 0.24191157519817352,
|
|
"num_tokens": 79819954.0,
|
|
"step": 43385
|
|
},
|
|
{
|
|
"entropy": 5.5096673488616945,
|
|
"epoch": 3.6242900100233877,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003726828451753268,
|
|
"loss": 4.801,
|
|
"mean_token_accuracy": 0.22547558546066285,
|
|
"num_tokens": 79829249.0,
|
|
"step": 43390
|
|
},
|
|
{
|
|
"entropy": 5.5569757461547855,
|
|
"epoch": 3.624707651186101,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00037265602625838876,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.22911641597747803,
|
|
"num_tokens": 79838559.0,
|
|
"step": 43395
|
|
},
|
|
{
|
|
"entropy": 5.618495273590088,
|
|
"epoch": 3.6251252923488138,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003726292056318645,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.22352229356765746,
|
|
"num_tokens": 79848981.0,
|
|
"step": 43400
|
|
},
|
|
{
|
|
"entropy": 5.538275098800659,
|
|
"epoch": 3.625542933511527,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00037260238329622335,
|
|
"loss": 4.6868,
|
|
"mean_token_accuracy": 0.2428866669535637,
|
|
"num_tokens": 79857895.0,
|
|
"step": 43405
|
|
},
|
|
{
|
|
"entropy": 5.539729404449463,
|
|
"epoch": 3.62596057467424,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00037257555925193517,
|
|
"loss": 4.6939,
|
|
"mean_token_accuracy": 0.23528572916984558,
|
|
"num_tokens": 79866690.0,
|
|
"step": 43410
|
|
},
|
|
{
|
|
"entropy": 5.569047212600708,
|
|
"epoch": 3.6263782158369526,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003725487334994693,
|
|
"loss": 4.8254,
|
|
"mean_token_accuracy": 0.22339565604925155,
|
|
"num_tokens": 79876600.0,
|
|
"step": 43415
|
|
},
|
|
{
|
|
"entropy": 5.48784065246582,
|
|
"epoch": 3.626795856999666,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037252190603929535,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.23310830742120742,
|
|
"num_tokens": 79884972.0,
|
|
"step": 43420
|
|
},
|
|
{
|
|
"entropy": 5.466331815719604,
|
|
"epoch": 3.627213498162379,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003724950768718832,
|
|
"loss": 4.7318,
|
|
"mean_token_accuracy": 0.2328207090497017,
|
|
"num_tokens": 79894441.0,
|
|
"step": 43425
|
|
},
|
|
{
|
|
"entropy": 5.4977405071258545,
|
|
"epoch": 3.627631139325092,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00037246824599770223,
|
|
"loss": 4.68,
|
|
"mean_token_accuracy": 0.24248118102550506,
|
|
"num_tokens": 79903508.0,
|
|
"step": 43430
|
|
},
|
|
{
|
|
"entropy": 5.636818885803223,
|
|
"epoch": 3.6280487804878048,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003724414134172224,
|
|
"loss": 4.8231,
|
|
"mean_token_accuracy": 0.22871311008930206,
|
|
"num_tokens": 79912566.0,
|
|
"step": 43435
|
|
},
|
|
{
|
|
"entropy": 5.480125379562378,
|
|
"epoch": 3.628466421650518,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00037241457913091326,
|
|
"loss": 4.6659,
|
|
"mean_token_accuracy": 0.2428330212831497,
|
|
"num_tokens": 79921305.0,
|
|
"step": 43440
|
|
},
|
|
{
|
|
"entropy": 5.515282154083252,
|
|
"epoch": 3.628884062813231,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037238774313924476,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.2374053865671158,
|
|
"num_tokens": 79930746.0,
|
|
"step": 43445
|
|
},
|
|
{
|
|
"entropy": 5.507979249954223,
|
|
"epoch": 3.629301703975944,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037236090544268645,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.23609574288129806,
|
|
"num_tokens": 79939924.0,
|
|
"step": 43450
|
|
},
|
|
{
|
|
"entropy": 5.515767240524292,
|
|
"epoch": 3.629719345138657,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00037233406604170844,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.23749666064977645,
|
|
"num_tokens": 79949600.0,
|
|
"step": 43455
|
|
},
|
|
{
|
|
"entropy": 5.473403882980347,
|
|
"epoch": 3.6301369863013697,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003723072249367803,
|
|
"loss": 4.6457,
|
|
"mean_token_accuracy": 0.24257651716470718,
|
|
"num_tokens": 79958564.0,
|
|
"step": 43460
|
|
},
|
|
{
|
|
"entropy": 5.543472957611084,
|
|
"epoch": 3.630554627464083,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003722803821283722,
|
|
"loss": 4.6765,
|
|
"mean_token_accuracy": 0.23614041805267333,
|
|
"num_tokens": 79967380.0,
|
|
"step": 43465
|
|
},
|
|
{
|
|
"entropy": 5.489306259155273,
|
|
"epoch": 3.630972268626796,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003722535376169538,
|
|
"loss": 4.7225,
|
|
"mean_token_accuracy": 0.2314086452126503,
|
|
"num_tokens": 79977383.0,
|
|
"step": 43470
|
|
},
|
|
{
|
|
"entropy": 5.561637687683105,
|
|
"epoch": 3.631389909789509,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003722266914029952,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.22528633773326873,
|
|
"num_tokens": 79986778.0,
|
|
"step": 43475
|
|
},
|
|
{
|
|
"entropy": 5.470512056350708,
|
|
"epoch": 3.631807550952222,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003721998434869663,
|
|
"loss": 4.6116,
|
|
"mean_token_accuracy": 0.23524964600801468,
|
|
"num_tokens": 79995702.0,
|
|
"step": 43480
|
|
},
|
|
{
|
|
"entropy": 5.528408861160278,
|
|
"epoch": 3.6322251921149347,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00037217299386933724,
|
|
"loss": 4.7363,
|
|
"mean_token_accuracy": 0.22891219556331635,
|
|
"num_tokens": 80005395.0,
|
|
"step": 43485
|
|
},
|
|
{
|
|
"entropy": 5.47758674621582,
|
|
"epoch": 3.632642833277648,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037214614255057785,
|
|
"loss": 4.648,
|
|
"mean_token_accuracy": 0.2397409439086914,
|
|
"num_tokens": 80015553.0,
|
|
"step": 43490
|
|
},
|
|
{
|
|
"entropy": 5.497433376312256,
|
|
"epoch": 3.6330604744403607,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00037211928953115835,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.23742664605379105,
|
|
"num_tokens": 80025754.0,
|
|
"step": 43495
|
|
},
|
|
{
|
|
"entropy": 5.469954299926758,
|
|
"epoch": 3.633478115603074,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037209243481154883,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.2363774523139,
|
|
"num_tokens": 80035228.0,
|
|
"step": 43500
|
|
},
|
|
{
|
|
"entropy": 5.471620893478393,
|
|
"epoch": 3.633895756765787,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037206557839221925,
|
|
"loss": 4.6279,
|
|
"mean_token_accuracy": 0.2402377024292946,
|
|
"num_tokens": 80043688.0,
|
|
"step": 43505
|
|
},
|
|
{
|
|
"entropy": 5.597074222564697,
|
|
"epoch": 3.6343133979284996,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00037203872027363993,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.22646818459033966,
|
|
"num_tokens": 80054121.0,
|
|
"step": 43510
|
|
},
|
|
{
|
|
"entropy": 5.539524412155151,
|
|
"epoch": 3.634731039091213,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003720118604562811,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.2248527929186821,
|
|
"num_tokens": 80062709.0,
|
|
"step": 43515
|
|
},
|
|
{
|
|
"entropy": 5.493987226486206,
|
|
"epoch": 3.6351486802539257,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003719849989406128,
|
|
"loss": 4.7064,
|
|
"mean_token_accuracy": 0.24628937989473343,
|
|
"num_tokens": 80072002.0,
|
|
"step": 43520
|
|
},
|
|
{
|
|
"entropy": 5.510867500305176,
|
|
"epoch": 3.635566321416639,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003719581357271053,
|
|
"loss": 4.7726,
|
|
"mean_token_accuracy": 0.22891463935375214,
|
|
"num_tokens": 80081911.0,
|
|
"step": 43525
|
|
},
|
|
{
|
|
"entropy": 5.5865847110748295,
|
|
"epoch": 3.6359839625793517,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00037193127081622897,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.23009200543165206,
|
|
"num_tokens": 80091825.0,
|
|
"step": 43530
|
|
},
|
|
{
|
|
"entropy": 5.516590118408203,
|
|
"epoch": 3.6364016037420646,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037190440420845414,
|
|
"loss": 4.7058,
|
|
"mean_token_accuracy": 0.23682351857423783,
|
|
"num_tokens": 80101037.0,
|
|
"step": 43535
|
|
},
|
|
{
|
|
"entropy": 5.569750022888184,
|
|
"epoch": 3.636819244904778,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037187753590425094,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.23354137241840361,
|
|
"num_tokens": 80110143.0,
|
|
"step": 43540
|
|
},
|
|
{
|
|
"entropy": 5.530135631561279,
|
|
"epoch": 3.637236886067491,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037185066590408997,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.22608047872781753,
|
|
"num_tokens": 80119580.0,
|
|
"step": 43545
|
|
},
|
|
{
|
|
"entropy": 5.518070554733276,
|
|
"epoch": 3.637654527230204,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003718237942084415,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.23058551996946336,
|
|
"num_tokens": 80128650.0,
|
|
"step": 43550
|
|
},
|
|
{
|
|
"entropy": 5.48200044631958,
|
|
"epoch": 3.6380721683929167,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000371796920817776,
|
|
"loss": 4.6678,
|
|
"mean_token_accuracy": 0.24255056232213973,
|
|
"num_tokens": 80137551.0,
|
|
"step": 43555
|
|
},
|
|
{
|
|
"entropy": 5.451232290267944,
|
|
"epoch": 3.63848980955563,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037177004573256373,
|
|
"loss": 4.6689,
|
|
"mean_token_accuracy": 0.23651565462350846,
|
|
"num_tokens": 80146354.0,
|
|
"step": 43560
|
|
},
|
|
{
|
|
"entropy": 5.501338815689087,
|
|
"epoch": 3.6389074507183428,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003717431689532755,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.2294752612709999,
|
|
"num_tokens": 80155061.0,
|
|
"step": 43565
|
|
},
|
|
{
|
|
"entropy": 5.54663233757019,
|
|
"epoch": 3.639325091881056,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003717162904803815,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.23114318400621414,
|
|
"num_tokens": 80163636.0,
|
|
"step": 43570
|
|
},
|
|
{
|
|
"entropy": 5.47115044593811,
|
|
"epoch": 3.639742733043769,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037168941031435256,
|
|
"loss": 4.6508,
|
|
"mean_token_accuracy": 0.2354681447148323,
|
|
"num_tokens": 80172487.0,
|
|
"step": 43575
|
|
},
|
|
{
|
|
"entropy": 5.465145492553711,
|
|
"epoch": 3.6401603742064816,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000371662528455659,
|
|
"loss": 4.6955,
|
|
"mean_token_accuracy": 0.239812970161438,
|
|
"num_tokens": 80181006.0,
|
|
"step": 43580
|
|
},
|
|
{
|
|
"entropy": 5.5349297523498535,
|
|
"epoch": 3.640578015369195,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003716356449047716,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.2339680388569832,
|
|
"num_tokens": 80190180.0,
|
|
"step": 43585
|
|
},
|
|
{
|
|
"entropy": 5.396636581420898,
|
|
"epoch": 3.6409956565319077,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003716087596621608,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.24166938662528992,
|
|
"num_tokens": 80198712.0,
|
|
"step": 43590
|
|
},
|
|
{
|
|
"entropy": 5.49037766456604,
|
|
"epoch": 3.641413297694621,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003715818727282975,
|
|
"loss": 4.7316,
|
|
"mean_token_accuracy": 0.24132487624883653,
|
|
"num_tokens": 80207544.0,
|
|
"step": 43595
|
|
},
|
|
{
|
|
"entropy": 5.495170068740845,
|
|
"epoch": 3.6418309388573338,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003715549841036522,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.23069394379854202,
|
|
"num_tokens": 80216824.0,
|
|
"step": 43600
|
|
},
|
|
{
|
|
"entropy": 5.566744422912597,
|
|
"epoch": 3.6422485800200466,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037152809378869565,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.22622065246105194,
|
|
"num_tokens": 80226110.0,
|
|
"step": 43605
|
|
},
|
|
{
|
|
"entropy": 5.470860528945923,
|
|
"epoch": 3.64266622118276,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003715012017838987,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.23587134033441542,
|
|
"num_tokens": 80234289.0,
|
|
"step": 43610
|
|
},
|
|
{
|
|
"entropy": 5.492706394195556,
|
|
"epoch": 3.6430838623454727,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00037147430808973206,
|
|
"loss": 4.6688,
|
|
"mean_token_accuracy": 0.23839928656816484,
|
|
"num_tokens": 80242295.0,
|
|
"step": 43615
|
|
},
|
|
{
|
|
"entropy": 5.521779775619507,
|
|
"epoch": 3.643501503508186,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003714474127066665,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.23572672307491302,
|
|
"num_tokens": 80251068.0,
|
|
"step": 43620
|
|
},
|
|
{
|
|
"entropy": 5.512071895599365,
|
|
"epoch": 3.6439191446708987,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00037142051563517287,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.2447863206267357,
|
|
"num_tokens": 80260455.0,
|
|
"step": 43625
|
|
},
|
|
{
|
|
"entropy": 5.5533562183380125,
|
|
"epoch": 3.6443367858336115,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003713936168757221,
|
|
"loss": 4.7842,
|
|
"mean_token_accuracy": 0.23494451344013215,
|
|
"num_tokens": 80269856.0,
|
|
"step": 43630
|
|
},
|
|
{
|
|
"entropy": 5.5708832263946535,
|
|
"epoch": 3.644754426996325,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000371366716428785,
|
|
"loss": 4.7724,
|
|
"mean_token_accuracy": 0.23331970274448394,
|
|
"num_tokens": 80279430.0,
|
|
"step": 43635
|
|
},
|
|
{
|
|
"entropy": 5.487669658660889,
|
|
"epoch": 3.6451720681590376,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00037133981429483256,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.23592142760753632,
|
|
"num_tokens": 80287756.0,
|
|
"step": 43640
|
|
},
|
|
{
|
|
"entropy": 5.5773694038391115,
|
|
"epoch": 3.645589709321751,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003713129104743357,
|
|
"loss": 4.7933,
|
|
"mean_token_accuracy": 0.23544540107250214,
|
|
"num_tokens": 80297257.0,
|
|
"step": 43645
|
|
},
|
|
{
|
|
"entropy": 5.599317598342895,
|
|
"epoch": 3.6460073504844637,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003712860049677653,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.2332851320505142,
|
|
"num_tokens": 80307127.0,
|
|
"step": 43650
|
|
},
|
|
{
|
|
"entropy": 5.611062908172608,
|
|
"epoch": 3.6464249916471765,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003712590977755926,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.22756579667329788,
|
|
"num_tokens": 80317549.0,
|
|
"step": 43655
|
|
},
|
|
{
|
|
"entropy": 5.438782978057861,
|
|
"epoch": 3.6468426328098897,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003712321888982886,
|
|
"loss": 4.6008,
|
|
"mean_token_accuracy": 0.25008121877908707,
|
|
"num_tokens": 80326688.0,
|
|
"step": 43660
|
|
},
|
|
{
|
|
"entropy": 5.556015205383301,
|
|
"epoch": 3.647260273972603,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037120527833632414,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.22309095412492752,
|
|
"num_tokens": 80336067.0,
|
|
"step": 43665
|
|
},
|
|
{
|
|
"entropy": 5.483217382431031,
|
|
"epoch": 3.647677915135316,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003711783660901706,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.2405477598309517,
|
|
"num_tokens": 80344445.0,
|
|
"step": 43670
|
|
},
|
|
{
|
|
"entropy": 5.525457668304443,
|
|
"epoch": 3.6480955562980286,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00037115145216029896,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.2410571590065956,
|
|
"num_tokens": 80353880.0,
|
|
"step": 43675
|
|
},
|
|
{
|
|
"entropy": 5.484686470031738,
|
|
"epoch": 3.648513197460742,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003711245365471803,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.23105966299772263,
|
|
"num_tokens": 80362332.0,
|
|
"step": 43680
|
|
},
|
|
{
|
|
"entropy": 5.55340051651001,
|
|
"epoch": 3.6489308386234547,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00037109761925128597,
|
|
"loss": 4.7322,
|
|
"mean_token_accuracy": 0.23943498581647873,
|
|
"num_tokens": 80371668.0,
|
|
"step": 43685
|
|
},
|
|
{
|
|
"entropy": 5.538856840133667,
|
|
"epoch": 3.649348479786168,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003710707002730873,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.24334985315799712,
|
|
"num_tokens": 80381658.0,
|
|
"step": 43690
|
|
},
|
|
{
|
|
"entropy": 5.525318622589111,
|
|
"epoch": 3.6497661209488808,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00037104377961305526,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.2291511595249176,
|
|
"num_tokens": 80391472.0,
|
|
"step": 43695
|
|
},
|
|
{
|
|
"entropy": 5.4974365234375,
|
|
"epoch": 3.6501837621115936,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00037101685727166116,
|
|
"loss": 4.6818,
|
|
"mean_token_accuracy": 0.23407785445451737,
|
|
"num_tokens": 80400374.0,
|
|
"step": 43700
|
|
},
|
|
{
|
|
"entropy": 5.518725967407226,
|
|
"epoch": 3.650601403274307,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003709899332493765,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.23638743609189988,
|
|
"num_tokens": 80409818.0,
|
|
"step": 43705
|
|
},
|
|
{
|
|
"entropy": 5.557151651382446,
|
|
"epoch": 3.6510190444370196,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003709630075466725,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.22745810598134994,
|
|
"num_tokens": 80419606.0,
|
|
"step": 43710
|
|
},
|
|
{
|
|
"entropy": 5.453407049179077,
|
|
"epoch": 3.651436685599733,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003709360801640206,
|
|
"loss": 4.6419,
|
|
"mean_token_accuracy": 0.23730225265026092,
|
|
"num_tokens": 80428838.0,
|
|
"step": 43715
|
|
},
|
|
{
|
|
"entropy": 5.496217107772827,
|
|
"epoch": 3.6518543267624457,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00037090915110189206,
|
|
"loss": 4.6963,
|
|
"mean_token_accuracy": 0.23448657095432282,
|
|
"num_tokens": 80437617.0,
|
|
"step": 43720
|
|
},
|
|
{
|
|
"entropy": 5.478821563720703,
|
|
"epoch": 3.6522719679251585,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003708822203607584,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.24094246476888656,
|
|
"num_tokens": 80446715.0,
|
|
"step": 43725
|
|
},
|
|
{
|
|
"entropy": 5.599976396560669,
|
|
"epoch": 3.6526896090878718,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003708552879410911,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.22165931314229964,
|
|
"num_tokens": 80456656.0,
|
|
"step": 43730
|
|
},
|
|
{
|
|
"entropy": 5.503836345672608,
|
|
"epoch": 3.6531072502505846,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00037082835384336153,
|
|
"loss": 4.6506,
|
|
"mean_token_accuracy": 0.2491927534341812,
|
|
"num_tokens": 80465283.0,
|
|
"step": 43735
|
|
},
|
|
{
|
|
"entropy": 5.4551619529724125,
|
|
"epoch": 3.653524891413298,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003708014180680414,
|
|
"loss": 4.7254,
|
|
"mean_token_accuracy": 0.2310619682073593,
|
|
"num_tokens": 80474011.0,
|
|
"step": 43740
|
|
},
|
|
{
|
|
"entropy": 5.469313383102417,
|
|
"epoch": 3.6539425325760106,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000370774480615602,
|
|
"loss": 4.7359,
|
|
"mean_token_accuracy": 0.23125943541526794,
|
|
"num_tokens": 80483795.0,
|
|
"step": 43745
|
|
},
|
|
{
|
|
"entropy": 5.531169128417969,
|
|
"epoch": 3.6543601737387235,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003707475414865151,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.23064298033714295,
|
|
"num_tokens": 80494153.0,
|
|
"step": 43750
|
|
},
|
|
{
|
|
"entropy": 5.49195671081543,
|
|
"epoch": 3.6547778149014367,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00037072060068125224,
|
|
"loss": 4.5607,
|
|
"mean_token_accuracy": 0.24760081768035888,
|
|
"num_tokens": 80503316.0,
|
|
"step": 43755
|
|
},
|
|
{
|
|
"entropy": 5.5247832298278805,
|
|
"epoch": 3.6551954560641495,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00037069365820028514,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.23119752258062362,
|
|
"num_tokens": 80512695.0,
|
|
"step": 43760
|
|
},
|
|
{
|
|
"entropy": 5.416129159927368,
|
|
"epoch": 3.655613097226863,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00037066671404408516,
|
|
"loss": 4.5896,
|
|
"mean_token_accuracy": 0.2463192641735077,
|
|
"num_tokens": 80521576.0,
|
|
"step": 43765
|
|
},
|
|
{
|
|
"entropy": 5.532720613479614,
|
|
"epoch": 3.6560307383895756,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003706397682131243,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.23557335436344146,
|
|
"num_tokens": 80530706.0,
|
|
"step": 43770
|
|
},
|
|
{
|
|
"entropy": 5.4574596881866455,
|
|
"epoch": 3.6564483795522884,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037061282070787415,
|
|
"loss": 4.7078,
|
|
"mean_token_accuracy": 0.24186795502901076,
|
|
"num_tokens": 80539623.0,
|
|
"step": 43775
|
|
},
|
|
{
|
|
"entropy": 5.553741407394409,
|
|
"epoch": 3.6568660207150017,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003705858715288065,
|
|
"loss": 4.7075,
|
|
"mean_token_accuracy": 0.23427455127239227,
|
|
"num_tokens": 80549139.0,
|
|
"step": 43780
|
|
},
|
|
{
|
|
"entropy": 5.508835697174073,
|
|
"epoch": 3.657283661877715,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00037055892067639314,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.24326126128435135,
|
|
"num_tokens": 80559184.0,
|
|
"step": 43785
|
|
},
|
|
{
|
|
"entropy": 5.489293813705444,
|
|
"epoch": 3.6577013030404277,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00037053196815110584,
|
|
"loss": 4.6455,
|
|
"mean_token_accuracy": 0.24601176232099534,
|
|
"num_tokens": 80567898.0,
|
|
"step": 43790
|
|
},
|
|
{
|
|
"entropy": 5.479529571533203,
|
|
"epoch": 3.6581189442031405,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003705050139534164,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.23897129893302918,
|
|
"num_tokens": 80576283.0,
|
|
"step": 43795
|
|
},
|
|
{
|
|
"entropy": 5.501029825210571,
|
|
"epoch": 3.658536585365854,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037047805808379676,
|
|
"loss": 4.7687,
|
|
"mean_token_accuracy": 0.23518039733171464,
|
|
"num_tokens": 80586676.0,
|
|
"step": 43800
|
|
},
|
|
{
|
|
"entropy": 5.561445856094361,
|
|
"epoch": 3.6589542265285666,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003704511005427188,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.22825277894735335,
|
|
"num_tokens": 80596008.0,
|
|
"step": 43805
|
|
},
|
|
{
|
|
"entropy": 5.566840028762817,
|
|
"epoch": 3.65937186769128,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00037042414133065443,
|
|
"loss": 4.7246,
|
|
"mean_token_accuracy": 0.23094309121370316,
|
|
"num_tokens": 80604953.0,
|
|
"step": 43810
|
|
},
|
|
{
|
|
"entropy": 5.557020044326782,
|
|
"epoch": 3.6597895088539927,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003703971804480756,
|
|
"loss": 4.7453,
|
|
"mean_token_accuracy": 0.23366168439388274,
|
|
"num_tokens": 80614374.0,
|
|
"step": 43815
|
|
},
|
|
{
|
|
"entropy": 5.497534275054932,
|
|
"epoch": 3.6602071500167055,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00037037021789545425,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.23739757686853408,
|
|
"num_tokens": 80623981.0,
|
|
"step": 43820
|
|
},
|
|
{
|
|
"entropy": 5.4587562561035154,
|
|
"epoch": 3.6606247911794187,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037034325367326244,
|
|
"loss": 4.5825,
|
|
"mean_token_accuracy": 0.2429608702659607,
|
|
"num_tokens": 80633177.0,
|
|
"step": 43825
|
|
},
|
|
{
|
|
"entropy": 5.543049001693726,
|
|
"epoch": 3.6610424323421316,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003703162877819723,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.2327614426612854,
|
|
"num_tokens": 80642275.0,
|
|
"step": 43830
|
|
},
|
|
{
|
|
"entropy": 5.511010456085205,
|
|
"epoch": 3.661460073504845,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00037028932022205573,
|
|
"loss": 4.6988,
|
|
"mean_token_accuracy": 0.23242576271295548,
|
|
"num_tokens": 80651582.0,
|
|
"step": 43835
|
|
},
|
|
{
|
|
"entropy": 5.528081846237183,
|
|
"epoch": 3.6618777146675576,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037026235099398496,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.23230278939008714,
|
|
"num_tokens": 80661616.0,
|
|
"step": 43840
|
|
},
|
|
{
|
|
"entropy": 5.448705720901489,
|
|
"epoch": 3.6622953558302704,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000370235380098232,
|
|
"loss": 4.5954,
|
|
"mean_token_accuracy": 0.24827731251716614,
|
|
"num_tokens": 80670019.0,
|
|
"step": 43845
|
|
},
|
|
{
|
|
"entropy": 5.478925561904907,
|
|
"epoch": 3.6627129969929837,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037020840753526917,
|
|
"loss": 4.7874,
|
|
"mean_token_accuracy": 0.22225189954042435,
|
|
"num_tokens": 80679690.0,
|
|
"step": 43850
|
|
},
|
|
{
|
|
"entropy": 5.5290467739105225,
|
|
"epoch": 3.6631306381556965,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003701814333055685,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.23487139344215394,
|
|
"num_tokens": 80688007.0,
|
|
"step": 43855
|
|
},
|
|
{
|
|
"entropy": 5.610186338424683,
|
|
"epoch": 3.6635482793184098,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003701544574096023,
|
|
"loss": 4.8631,
|
|
"mean_token_accuracy": 0.21735815554857255,
|
|
"num_tokens": 80697792.0,
|
|
"step": 43860
|
|
},
|
|
{
|
|
"entropy": 5.557620286941528,
|
|
"epoch": 3.6639659204811226,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00037012747984784276,
|
|
"loss": 4.7169,
|
|
"mean_token_accuracy": 0.22641980797052383,
|
|
"num_tokens": 80706521.0,
|
|
"step": 43865
|
|
},
|
|
{
|
|
"entropy": 5.572325944900513,
|
|
"epoch": 3.6643835616438354,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003701005006207622,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.23410710096359252,
|
|
"num_tokens": 80716396.0,
|
|
"step": 43870
|
|
},
|
|
{
|
|
"entropy": 5.420670223236084,
|
|
"epoch": 3.6648012028065486,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037007351972883284,
|
|
"loss": 4.6606,
|
|
"mean_token_accuracy": 0.24097769558429719,
|
|
"num_tokens": 80725995.0,
|
|
"step": 43875
|
|
},
|
|
{
|
|
"entropy": 5.440156078338623,
|
|
"epoch": 3.6652188439692615,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003700465371725272,
|
|
"loss": 4.6876,
|
|
"mean_token_accuracy": 0.2358415111899376,
|
|
"num_tokens": 80735083.0,
|
|
"step": 43880
|
|
},
|
|
{
|
|
"entropy": 5.510271644592285,
|
|
"epoch": 3.6656364851319747,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003700195529523174,
|
|
"loss": 4.7235,
|
|
"mean_token_accuracy": 0.23375418931245803,
|
|
"num_tokens": 80743919.0,
|
|
"step": 43885
|
|
},
|
|
{
|
|
"entropy": 5.507398414611816,
|
|
"epoch": 3.6660541262946875,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000369992567068676,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.23663873970508575,
|
|
"num_tokens": 80753495.0,
|
|
"step": 43890
|
|
},
|
|
{
|
|
"entropy": 5.456907844543457,
|
|
"epoch": 3.6664717674574003,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00036996557952207544,
|
|
"loss": 4.6609,
|
|
"mean_token_accuracy": 0.2413388192653656,
|
|
"num_tokens": 80762218.0,
|
|
"step": 43895
|
|
},
|
|
{
|
|
"entropy": 5.422036075592041,
|
|
"epoch": 3.6668894086201136,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00036993859031298794,
|
|
"loss": 4.6557,
|
|
"mean_token_accuracy": 0.24415556192398072,
|
|
"num_tokens": 80771677.0,
|
|
"step": 43900
|
|
},
|
|
{
|
|
"entropy": 5.492752885818481,
|
|
"epoch": 3.667307049782827,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00036991159944188627,
|
|
"loss": 4.6767,
|
|
"mean_token_accuracy": 0.2435940057039261,
|
|
"num_tokens": 80780841.0,
|
|
"step": 43905
|
|
},
|
|
{
|
|
"entropy": 5.449494075775147,
|
|
"epoch": 3.6677246909455397,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00036988460690924276,
|
|
"loss": 4.6525,
|
|
"mean_token_accuracy": 0.23276914656162262,
|
|
"num_tokens": 80789421.0,
|
|
"step": 43910
|
|
},
|
|
{
|
|
"entropy": 5.5358367443084715,
|
|
"epoch": 3.6681423321082525,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00036985761271553,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.2336870923638344,
|
|
"num_tokens": 80799795.0,
|
|
"step": 43915
|
|
},
|
|
{
|
|
"entropy": 5.525849723815918,
|
|
"epoch": 3.6685599732709657,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00036983061686122055,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.2441274806857109,
|
|
"num_tokens": 80808422.0,
|
|
"step": 43920
|
|
},
|
|
{
|
|
"entropy": 5.541812133789063,
|
|
"epoch": 3.6689776144336785,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000369803619346787,
|
|
"loss": 4.7176,
|
|
"mean_token_accuracy": 0.24021971076726914,
|
|
"num_tokens": 80817529.0,
|
|
"step": 43925
|
|
},
|
|
{
|
|
"entropy": 5.506343984603882,
|
|
"epoch": 3.669395255596392,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000369776620172702,
|
|
"loss": 4.7856,
|
|
"mean_token_accuracy": 0.23011110574007035,
|
|
"num_tokens": 80826626.0,
|
|
"step": 43930
|
|
},
|
|
{
|
|
"entropy": 5.421022510528564,
|
|
"epoch": 3.6698128967591046,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003697496193394382,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.2421489953994751,
|
|
"num_tokens": 80836442.0,
|
|
"step": 43935
|
|
},
|
|
{
|
|
"entropy": 5.503792428970337,
|
|
"epoch": 3.6702305379218174,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00036972261684746824,
|
|
"loss": 4.7173,
|
|
"mean_token_accuracy": 0.23252101838588715,
|
|
"num_tokens": 80845291.0,
|
|
"step": 43940
|
|
},
|
|
{
|
|
"entropy": 5.4654860496521,
|
|
"epoch": 3.6706481790845307,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003696956126972648,
|
|
"loss": 4.6231,
|
|
"mean_token_accuracy": 0.24719603210687638,
|
|
"num_tokens": 80853828.0,
|
|
"step": 43945
|
|
},
|
|
{
|
|
"entropy": 5.511477947235107,
|
|
"epoch": 3.6710658202472435,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003696686068893008,
|
|
"loss": 4.6738,
|
|
"mean_token_accuracy": 0.23830721974372865,
|
|
"num_tokens": 80863208.0,
|
|
"step": 43950
|
|
},
|
|
{
|
|
"entropy": 5.443703985214233,
|
|
"epoch": 3.6714834614099567,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036964159942404873,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.24085647314786912,
|
|
"num_tokens": 80872239.0,
|
|
"step": 43955
|
|
},
|
|
{
|
|
"entropy": 5.61325044631958,
|
|
"epoch": 3.6719011025726696,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00036961459030198165,
|
|
"loss": 4.8029,
|
|
"mean_token_accuracy": 0.22366809844970703,
|
|
"num_tokens": 80881147.0,
|
|
"step": 43960
|
|
},
|
|
{
|
|
"entropy": 5.50967435836792,
|
|
"epoch": 3.6723187437353824,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00036958757952357225,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.23585849553346633,
|
|
"num_tokens": 80890327.0,
|
|
"step": 43965
|
|
},
|
|
{
|
|
"entropy": 5.513330078125,
|
|
"epoch": 3.6727363848980956,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00036956056708929344,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.23923267871141435,
|
|
"num_tokens": 80899813.0,
|
|
"step": 43970
|
|
},
|
|
{
|
|
"entropy": 5.458929634094238,
|
|
"epoch": 3.6731540260608084,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000369533552999618,
|
|
"loss": 4.5819,
|
|
"mean_token_accuracy": 0.24185139089822769,
|
|
"num_tokens": 80909069.0,
|
|
"step": 43975
|
|
},
|
|
{
|
|
"entropy": 5.4423752784729,
|
|
"epoch": 3.6735716672235217,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000369506537255019,
|
|
"loss": 4.6462,
|
|
"mean_token_accuracy": 0.2448044702410698,
|
|
"num_tokens": 80917974.0,
|
|
"step": 43980
|
|
},
|
|
{
|
|
"entropy": 5.515643882751465,
|
|
"epoch": 3.6739893083862345,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00036947951985596923,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.23648570030927657,
|
|
"num_tokens": 80927888.0,
|
|
"step": 43985
|
|
},
|
|
{
|
|
"entropy": 5.55880823135376,
|
|
"epoch": 3.6744069495489473,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003694525008029418,
|
|
"loss": 4.766,
|
|
"mean_token_accuracy": 0.22778704017400742,
|
|
"num_tokens": 80936392.0,
|
|
"step": 43990
|
|
},
|
|
{
|
|
"entropy": 5.51116418838501,
|
|
"epoch": 3.6748245907116606,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003694254800964096,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.2335377022624016,
|
|
"num_tokens": 80946428.0,
|
|
"step": 43995
|
|
},
|
|
{
|
|
"entropy": 5.54226598739624,
|
|
"epoch": 3.6752422318743734,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00036939845773684577,
|
|
"loss": 4.696,
|
|
"mean_token_accuracy": 0.24039339870214463,
|
|
"num_tokens": 80957150.0,
|
|
"step": 44000
|
|
},
|
|
{
|
|
"entropy": 5.529142189025879,
|
|
"epoch": 3.6756598730370866,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00036937143372472336,
|
|
"loss": 4.7557,
|
|
"mean_token_accuracy": 0.23182910978794097,
|
|
"num_tokens": 80965659.0,
|
|
"step": 44005
|
|
},
|
|
{
|
|
"entropy": 5.507371044158935,
|
|
"epoch": 3.6760775141997994,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003693444080605153,
|
|
"loss": 4.6953,
|
|
"mean_token_accuracy": 0.23430904000997543,
|
|
"num_tokens": 80974657.0,
|
|
"step": 44010
|
|
},
|
|
{
|
|
"entropy": 5.466658353805542,
|
|
"epoch": 3.6764951553625123,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003693173807446949,
|
|
"loss": 4.6193,
|
|
"mean_token_accuracy": 0.2491207867860794,
|
|
"num_tokens": 80983732.0,
|
|
"step": 44015
|
|
},
|
|
{
|
|
"entropy": 5.512035322189331,
|
|
"epoch": 3.6769127965252255,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003692903517777352,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.2295667439699173,
|
|
"num_tokens": 80992924.0,
|
|
"step": 44020
|
|
},
|
|
{
|
|
"entropy": 5.626643133163452,
|
|
"epoch": 3.6773304376879388,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036926332116010935,
|
|
"loss": 4.8755,
|
|
"mean_token_accuracy": 0.21766155064105988,
|
|
"num_tokens": 81002162.0,
|
|
"step": 44025
|
|
},
|
|
{
|
|
"entropy": 5.459915637969971,
|
|
"epoch": 3.6777480788506516,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00036923628889229057,
|
|
"loss": 4.6106,
|
|
"mean_token_accuracy": 0.24382637888193132,
|
|
"num_tokens": 81010628.0,
|
|
"step": 44030
|
|
},
|
|
{
|
|
"entropy": 5.492580461502075,
|
|
"epoch": 3.6781657200133644,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003692092549747522,
|
|
"loss": 4.6652,
|
|
"mean_token_accuracy": 0.24316290766000748,
|
|
"num_tokens": 81018933.0,
|
|
"step": 44035
|
|
},
|
|
{
|
|
"entropy": 5.479295921325684,
|
|
"epoch": 3.6785833611760776,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00036918221940796734,
|
|
"loss": 4.6411,
|
|
"mean_token_accuracy": 0.2476104512810707,
|
|
"num_tokens": 81027735.0,
|
|
"step": 44040
|
|
},
|
|
{
|
|
"entropy": 5.560761404037476,
|
|
"epoch": 3.6790010023387905,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003691551821924095,
|
|
"loss": 4.8142,
|
|
"mean_token_accuracy": 0.22240122705698012,
|
|
"num_tokens": 81037516.0,
|
|
"step": 44045
|
|
},
|
|
{
|
|
"entropy": 5.452908086776733,
|
|
"epoch": 3.6794186435015037,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003691281433285517,
|
|
"loss": 4.6648,
|
|
"mean_token_accuracy": 0.24295573830604553,
|
|
"num_tokens": 81046077.0,
|
|
"step": 44050
|
|
},
|
|
{
|
|
"entropy": 5.475706386566162,
|
|
"epoch": 3.6798362846642165,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003691011028168676,
|
|
"loss": 4.6753,
|
|
"mean_token_accuracy": 0.24355804324150085,
|
|
"num_tokens": 81055256.0,
|
|
"step": 44055
|
|
},
|
|
{
|
|
"entropy": 5.518105602264404,
|
|
"epoch": 3.6802539258269293,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003690740606578303,
|
|
"loss": 4.7198,
|
|
"mean_token_accuracy": 0.2350729614496231,
|
|
"num_tokens": 81063897.0,
|
|
"step": 44060
|
|
},
|
|
{
|
|
"entropy": 5.536624765396118,
|
|
"epoch": 3.6806715669896426,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036904701685191337,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.23441398441791533,
|
|
"num_tokens": 81072847.0,
|
|
"step": 44065
|
|
},
|
|
{
|
|
"entropy": 5.564200782775879,
|
|
"epoch": 3.6810892081523554,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00036901997139959027,
|
|
"loss": 4.7387,
|
|
"mean_token_accuracy": 0.2322879984974861,
|
|
"num_tokens": 81082572.0,
|
|
"step": 44070
|
|
},
|
|
{
|
|
"entropy": 5.426740598678589,
|
|
"epoch": 3.6815068493150687,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00036899292430133437,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.24030492603778839,
|
|
"num_tokens": 81091147.0,
|
|
"step": 44075
|
|
},
|
|
{
|
|
"entropy": 5.505947113037109,
|
|
"epoch": 3.6819244904777815,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003689658755576191,
|
|
"loss": 4.6668,
|
|
"mean_token_accuracy": 0.23856448382139206,
|
|
"num_tokens": 81099755.0,
|
|
"step": 44080
|
|
},
|
|
{
|
|
"entropy": 5.496039533615113,
|
|
"epoch": 3.6823421316404943,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00036893882516891814,
|
|
"loss": 4.7422,
|
|
"mean_token_accuracy": 0.23215045630931855,
|
|
"num_tokens": 81109377.0,
|
|
"step": 44085
|
|
},
|
|
{
|
|
"entropy": 5.582548666000366,
|
|
"epoch": 3.6827597728032075,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000368911773135705,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.23540398180484773,
|
|
"num_tokens": 81118203.0,
|
|
"step": 44090
|
|
},
|
|
{
|
|
"entropy": 5.5294468879699705,
|
|
"epoch": 3.6831774139659204,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00036888471945845314,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.23246604800224305,
|
|
"num_tokens": 81127057.0,
|
|
"step": 44095
|
|
},
|
|
{
|
|
"entropy": 5.577957582473755,
|
|
"epoch": 3.6835950551286336,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003688576641376364,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.2212183505296707,
|
|
"num_tokens": 81136556.0,
|
|
"step": 44100
|
|
},
|
|
{
|
|
"entropy": 5.56360650062561,
|
|
"epoch": 3.6840126962913464,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00036883060717372813,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.2361912250518799,
|
|
"num_tokens": 81145773.0,
|
|
"step": 44105
|
|
},
|
|
{
|
|
"entropy": 5.558720922470092,
|
|
"epoch": 3.6844303374540592,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00036880354856720215,
|
|
"loss": 4.6441,
|
|
"mean_token_accuracy": 0.2389923259615898,
|
|
"num_tokens": 81154412.0,
|
|
"step": 44110
|
|
},
|
|
{
|
|
"entropy": 5.472861433029175,
|
|
"epoch": 3.6848479786167725,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003687764883185323,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.24042371809482574,
|
|
"num_tokens": 81163780.0,
|
|
"step": 44115
|
|
},
|
|
{
|
|
"entropy": 5.473172616958618,
|
|
"epoch": 3.6852656197794853,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000368749426428192,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.23427930027246474,
|
|
"num_tokens": 81173010.0,
|
|
"step": 44120
|
|
},
|
|
{
|
|
"entropy": 5.495724868774414,
|
|
"epoch": 3.6856832609421986,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00036872236289665515,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.2401750609278679,
|
|
"num_tokens": 81181545.0,
|
|
"step": 44125
|
|
},
|
|
{
|
|
"entropy": 5.5515398502349855,
|
|
"epoch": 3.6861009021049114,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00036869529772439553,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.2252385750412941,
|
|
"num_tokens": 81191683.0,
|
|
"step": 44130
|
|
},
|
|
{
|
|
"entropy": 5.506829309463501,
|
|
"epoch": 3.686518543267624,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000368668230911887,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.2294238582253456,
|
|
"num_tokens": 81200698.0,
|
|
"step": 44135
|
|
},
|
|
{
|
|
"entropy": 5.513737583160401,
|
|
"epoch": 3.6869361844303374,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003686411624596033,
|
|
"loss": 4.7344,
|
|
"mean_token_accuracy": 0.2343125119805336,
|
|
"num_tokens": 81209915.0,
|
|
"step": 44140
|
|
},
|
|
{
|
|
"entropy": 5.614862012863159,
|
|
"epoch": 3.6873538255930507,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003686140923680183,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.23555634915828705,
|
|
"num_tokens": 81219213.0,
|
|
"step": 44145
|
|
},
|
|
{
|
|
"entropy": 5.519661235809326,
|
|
"epoch": 3.6877714667557635,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036858702063760596,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.23325746655464172,
|
|
"num_tokens": 81228178.0,
|
|
"step": 44150
|
|
},
|
|
{
|
|
"entropy": 5.582950925827026,
|
|
"epoch": 3.6881891079184763,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036855994726884016,
|
|
"loss": 4.82,
|
|
"mean_token_accuracy": 0.22655332386493682,
|
|
"num_tokens": 81237151.0,
|
|
"step": 44155
|
|
},
|
|
{
|
|
"entropy": 5.574304533004761,
|
|
"epoch": 3.6886067490811896,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003685328722621949,
|
|
"loss": 4.7958,
|
|
"mean_token_accuracy": 0.22822062224149703,
|
|
"num_tokens": 81245895.0,
|
|
"step": 44160
|
|
},
|
|
{
|
|
"entropy": 5.6032679080963135,
|
|
"epoch": 3.6890243902439024,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003685057956181441,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.22664524018764495,
|
|
"num_tokens": 81255782.0,
|
|
"step": 44165
|
|
},
|
|
{
|
|
"entropy": 5.5676047801971436,
|
|
"epoch": 3.6894420314066156,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00036847871733716183,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.22864029705524444,
|
|
"num_tokens": 81265924.0,
|
|
"step": 44170
|
|
},
|
|
{
|
|
"entropy": 5.6520191669464115,
|
|
"epoch": 3.6898596725693285,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00036845163741972204,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.22385077625513078,
|
|
"num_tokens": 81275965.0,
|
|
"step": 44175
|
|
},
|
|
{
|
|
"entropy": 5.5092448711395265,
|
|
"epoch": 3.6902773137320413,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003684245558662989,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.22914617955684663,
|
|
"num_tokens": 81284879.0,
|
|
"step": 44180
|
|
},
|
|
{
|
|
"entropy": 5.478329372406006,
|
|
"epoch": 3.6906949548947545,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003683974726773664,
|
|
"loss": 4.7103,
|
|
"mean_token_accuracy": 0.23658363074064254,
|
|
"num_tokens": 81295549.0,
|
|
"step": 44185
|
|
},
|
|
{
|
|
"entropy": 5.477806282043457,
|
|
"epoch": 3.6911125960574673,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00036837038785339884,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.23435474783182145,
|
|
"num_tokens": 81304823.0,
|
|
"step": 44190
|
|
},
|
|
{
|
|
"entropy": 5.60757966041565,
|
|
"epoch": 3.6915302372201806,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00036834330139487003,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.23001102358102798,
|
|
"num_tokens": 81314958.0,
|
|
"step": 44195
|
|
},
|
|
{
|
|
"entropy": 5.519655752182007,
|
|
"epoch": 3.6919478783828934,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003683162133022546,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.23507245033979415,
|
|
"num_tokens": 81323361.0,
|
|
"step": 44200
|
|
},
|
|
{
|
|
"entropy": 5.401905918121338,
|
|
"epoch": 3.692365519545606,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00036828912357602636,
|
|
"loss": 4.6672,
|
|
"mean_token_accuracy": 0.24607810974121094,
|
|
"num_tokens": 81331741.0,
|
|
"step": 44205
|
|
},
|
|
{
|
|
"entropy": 5.506462097167969,
|
|
"epoch": 3.6927831607083195,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003682620322166599,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.23294952660799026,
|
|
"num_tokens": 81340593.0,
|
|
"step": 44210
|
|
},
|
|
{
|
|
"entropy": 5.572560834884643,
|
|
"epoch": 3.6932008018710323,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00036823493922462906,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.23380743712186813,
|
|
"num_tokens": 81349262.0,
|
|
"step": 44215
|
|
},
|
|
{
|
|
"entropy": 5.504022073745728,
|
|
"epoch": 3.6936184430337455,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003682078446004086,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.2367755353450775,
|
|
"num_tokens": 81358021.0,
|
|
"step": 44220
|
|
},
|
|
{
|
|
"entropy": 5.424993991851807,
|
|
"epoch": 3.6940360841964583,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003681807483444725,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.24353711903095246,
|
|
"num_tokens": 81366700.0,
|
|
"step": 44225
|
|
},
|
|
{
|
|
"entropy": 5.496493864059448,
|
|
"epoch": 3.694453725359171,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003681536504572953,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.23249525725841522,
|
|
"num_tokens": 81375873.0,
|
|
"step": 44230
|
|
},
|
|
{
|
|
"entropy": 5.546519994735718,
|
|
"epoch": 3.6948713665218844,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003681265509393513,
|
|
"loss": 4.7687,
|
|
"mean_token_accuracy": 0.2267373099923134,
|
|
"num_tokens": 81385002.0,
|
|
"step": 44235
|
|
},
|
|
{
|
|
"entropy": 5.471128511428833,
|
|
"epoch": 3.6952890076845977,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000368099449791115,
|
|
"loss": 4.6288,
|
|
"mean_token_accuracy": 0.23650448620319367,
|
|
"num_tokens": 81393980.0,
|
|
"step": 44240
|
|
},
|
|
{
|
|
"entropy": 5.629210472106934,
|
|
"epoch": 3.6957066488473105,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003680723470130607,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.22390744388103484,
|
|
"num_tokens": 81403492.0,
|
|
"step": 44245
|
|
},
|
|
{
|
|
"entropy": 5.505894708633423,
|
|
"epoch": 3.6961242900100233,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003680452426056629,
|
|
"loss": 4.6517,
|
|
"mean_token_accuracy": 0.24156333059072493,
|
|
"num_tokens": 81412736.0,
|
|
"step": 44250
|
|
},
|
|
{
|
|
"entropy": 5.546643257141113,
|
|
"epoch": 3.6965419311727366,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036801813656939616,
|
|
"loss": 4.7536,
|
|
"mean_token_accuracy": 0.23594294339418412,
|
|
"num_tokens": 81421021.0,
|
|
"step": 44255
|
|
},
|
|
{
|
|
"entropy": 5.476142263412475,
|
|
"epoch": 3.6969595723354494,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000367991028904735,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.23762670606374742,
|
|
"num_tokens": 81429395.0,
|
|
"step": 44260
|
|
},
|
|
{
|
|
"entropy": 5.489383220672607,
|
|
"epoch": 3.6973772134981626,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003679639196121539,
|
|
"loss": 4.7002,
|
|
"mean_token_accuracy": 0.2388654127717018,
|
|
"num_tokens": 81438583.0,
|
|
"step": 44265
|
|
},
|
|
{
|
|
"entropy": 5.495226240158081,
|
|
"epoch": 3.6977948546608754,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00036793680869212755,
|
|
"loss": 4.6768,
|
|
"mean_token_accuracy": 0.2438378944993019,
|
|
"num_tokens": 81446862.0,
|
|
"step": 44270
|
|
},
|
|
{
|
|
"entropy": 5.528409004211426,
|
|
"epoch": 3.6982124958235882,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00036790969614513045,
|
|
"loss": 4.7263,
|
|
"mean_token_accuracy": 0.23625391125679016,
|
|
"num_tokens": 81456295.0,
|
|
"step": 44275
|
|
},
|
|
{
|
|
"entropy": 5.5081559181213375,
|
|
"epoch": 3.6986301369863015,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00036788258197163726,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.23568521291017533,
|
|
"num_tokens": 81465767.0,
|
|
"step": 44280
|
|
},
|
|
{
|
|
"entropy": 5.4999524593353275,
|
|
"epoch": 3.6990477781490143,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003678554661721227,
|
|
"loss": 4.8039,
|
|
"mean_token_accuracy": 0.23643751740455626,
|
|
"num_tokens": 81474973.0,
|
|
"step": 44285
|
|
},
|
|
{
|
|
"entropy": 5.438244342803955,
|
|
"epoch": 3.6994654193117276,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036782834874706145,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.23935803771018982,
|
|
"num_tokens": 81483413.0,
|
|
"step": 44290
|
|
},
|
|
{
|
|
"entropy": 5.51196608543396,
|
|
"epoch": 3.6998830604744404,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00036780122969692826,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.23120494037866593,
|
|
"num_tokens": 81493531.0,
|
|
"step": 44295
|
|
},
|
|
{
|
|
"entropy": 5.482605361938477,
|
|
"epoch": 3.700300701637153,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00036777410902219776,
|
|
"loss": 4.6258,
|
|
"mean_token_accuracy": 0.2442095085978508,
|
|
"num_tokens": 81502439.0,
|
|
"step": 44300
|
|
},
|
|
{
|
|
"entropy": 5.545269393920899,
|
|
"epoch": 3.7007183427998664,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003677469867233448,
|
|
"loss": 4.7007,
|
|
"mean_token_accuracy": 0.23213475793600083,
|
|
"num_tokens": 81511810.0,
|
|
"step": 44305
|
|
},
|
|
{
|
|
"entropy": 5.503064203262329,
|
|
"epoch": 3.7011359839625793,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00036771986280084425,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.23801777213811875,
|
|
"num_tokens": 81521214.0,
|
|
"step": 44310
|
|
},
|
|
{
|
|
"entropy": 5.500187110900879,
|
|
"epoch": 3.7015536251252925,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036769273725517084,
|
|
"loss": 4.6519,
|
|
"mean_token_accuracy": 0.24322436302900313,
|
|
"num_tokens": 81530106.0,
|
|
"step": 44315
|
|
},
|
|
{
|
|
"entropy": 5.472137880325318,
|
|
"epoch": 3.7019712662880053,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00036766561008679953,
|
|
"loss": 4.6337,
|
|
"mean_token_accuracy": 0.24946540892124175,
|
|
"num_tokens": 81538871.0,
|
|
"step": 44320
|
|
},
|
|
{
|
|
"entropy": 5.440700054168701,
|
|
"epoch": 3.702388907450718,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003676384812962052,
|
|
"loss": 4.6057,
|
|
"mean_token_accuracy": 0.24794264137744904,
|
|
"num_tokens": 81547209.0,
|
|
"step": 44325
|
|
},
|
|
{
|
|
"entropy": 5.480128765106201,
|
|
"epoch": 3.7028065486134314,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00036761135088386266,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.23405387699604036,
|
|
"num_tokens": 81556650.0,
|
|
"step": 44330
|
|
},
|
|
{
|
|
"entropy": 5.53820309638977,
|
|
"epoch": 3.703224189776144,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000367584218850247,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.2402962103486061,
|
|
"num_tokens": 81565608.0,
|
|
"step": 44335
|
|
},
|
|
{
|
|
"entropy": 5.52466893196106,
|
|
"epoch": 3.7036418309388575,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036755708519583315,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.23806242942810057,
|
|
"num_tokens": 81574646.0,
|
|
"step": 44340
|
|
},
|
|
{
|
|
"entropy": 5.563236713409424,
|
|
"epoch": 3.7040594721015703,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00036752994992109617,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.232167986035347,
|
|
"num_tokens": 81584201.0,
|
|
"step": 44345
|
|
},
|
|
{
|
|
"entropy": 5.545426368713379,
|
|
"epoch": 3.704477113264283,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003675028130265109,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.2288798362016678,
|
|
"num_tokens": 81592914.0,
|
|
"step": 44350
|
|
},
|
|
{
|
|
"entropy": 5.637786149978638,
|
|
"epoch": 3.7048947544269963,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00036747567451255267,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.22403813749551774,
|
|
"num_tokens": 81602788.0,
|
|
"step": 44355
|
|
},
|
|
{
|
|
"entropy": 5.585795831680298,
|
|
"epoch": 3.7053123955897096,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003674485343796964,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.23638207465410233,
|
|
"num_tokens": 81611826.0,
|
|
"step": 44360
|
|
},
|
|
{
|
|
"entropy": 5.502894544601441,
|
|
"epoch": 3.7057300367524224,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036742139262841724,
|
|
"loss": 4.6859,
|
|
"mean_token_accuracy": 0.2356644868850708,
|
|
"num_tokens": 81620654.0,
|
|
"step": 44365
|
|
},
|
|
{
|
|
"entropy": 5.436010217666626,
|
|
"epoch": 3.706147677915135,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003673942492591903,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.24479431807994842,
|
|
"num_tokens": 81629297.0,
|
|
"step": 44370
|
|
},
|
|
{
|
|
"entropy": 5.527501249313355,
|
|
"epoch": 3.7065653190778485,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00036736710427249093,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.23832852393388748,
|
|
"num_tokens": 81638281.0,
|
|
"step": 44375
|
|
},
|
|
{
|
|
"entropy": 5.523658752441406,
|
|
"epoch": 3.7069829602405613,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00036733995766879415,
|
|
"loss": 4.7439,
|
|
"mean_token_accuracy": 0.23779701441526413,
|
|
"num_tokens": 81648219.0,
|
|
"step": 44380
|
|
},
|
|
{
|
|
"entropy": 5.484855985641479,
|
|
"epoch": 3.7074006014032745,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003673128094485753,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.2362858235836029,
|
|
"num_tokens": 81657421.0,
|
|
"step": 44385
|
|
},
|
|
{
|
|
"entropy": 5.436875295639038,
|
|
"epoch": 3.7078182425659874,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003672856596123095,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.24093721508979798,
|
|
"num_tokens": 81666320.0,
|
|
"step": 44390
|
|
},
|
|
{
|
|
"entropy": 5.501998472213745,
|
|
"epoch": 3.7082358837287,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003672585081604723,
|
|
"loss": 4.6933,
|
|
"mean_token_accuracy": 0.2308544099330902,
|
|
"num_tokens": 81674853.0,
|
|
"step": 44395
|
|
},
|
|
{
|
|
"entropy": 5.613758993148804,
|
|
"epoch": 3.7086535248914134,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00036723135509353876,
|
|
"loss": 4.8223,
|
|
"mean_token_accuracy": 0.22664850652217866,
|
|
"num_tokens": 81684147.0,
|
|
"step": 44400
|
|
},
|
|
{
|
|
"entropy": 5.518708896636963,
|
|
"epoch": 3.7090711660541262,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00036720420041198436,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.23381417542695998,
|
|
"num_tokens": 81693888.0,
|
|
"step": 44405
|
|
},
|
|
{
|
|
"entropy": 5.522154331207275,
|
|
"epoch": 3.7094888072168395,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0003671770441162845,
|
|
"loss": 4.7733,
|
|
"mean_token_accuracy": 0.23603528439998628,
|
|
"num_tokens": 81702864.0,
|
|
"step": 44410
|
|
},
|
|
{
|
|
"entropy": 5.498442697525024,
|
|
"epoch": 3.7099064483795523,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00036714988620691443,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.2386158972978592,
|
|
"num_tokens": 81712078.0,
|
|
"step": 44415
|
|
},
|
|
{
|
|
"entropy": 5.578491258621216,
|
|
"epoch": 3.710324089542265,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003671227266843497,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.22845801413059236,
|
|
"num_tokens": 81720948.0,
|
|
"step": 44420
|
|
},
|
|
{
|
|
"entropy": 5.568884325027466,
|
|
"epoch": 3.7107417307049784,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003670955655490658,
|
|
"loss": 4.7658,
|
|
"mean_token_accuracy": 0.22555574476718904,
|
|
"num_tokens": 81730846.0,
|
|
"step": 44425
|
|
},
|
|
{
|
|
"entropy": 5.4719456195831295,
|
|
"epoch": 3.711159371867691,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003670684028015381,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.24043883085250856,
|
|
"num_tokens": 81739430.0,
|
|
"step": 44430
|
|
},
|
|
{
|
|
"entropy": 5.551512813568115,
|
|
"epoch": 3.7115770130304044,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00036704123844224227,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.23763709515333176,
|
|
"num_tokens": 81748210.0,
|
|
"step": 44435
|
|
},
|
|
{
|
|
"entropy": 5.56681752204895,
|
|
"epoch": 3.7119946541931172,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003670140724716537,
|
|
"loss": 4.7712,
|
|
"mean_token_accuracy": 0.22790361791849137,
|
|
"num_tokens": 81757247.0,
|
|
"step": 44440
|
|
},
|
|
{
|
|
"entropy": 5.5410243511199955,
|
|
"epoch": 3.71241229535583,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003669869048902481,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.2325351506471634,
|
|
"num_tokens": 81767479.0,
|
|
"step": 44445
|
|
},
|
|
{
|
|
"entropy": 5.510640859603882,
|
|
"epoch": 3.7128299365185433,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00036695973569850096,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.24454938024282455,
|
|
"num_tokens": 81776899.0,
|
|
"step": 44450
|
|
},
|
|
{
|
|
"entropy": 5.60943832397461,
|
|
"epoch": 3.713247577681256,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00036693256489688805,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.22833261489868165,
|
|
"num_tokens": 81786864.0,
|
|
"step": 44455
|
|
},
|
|
{
|
|
"entropy": 5.460263919830322,
|
|
"epoch": 3.7136652188439694,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003669053924858848,
|
|
"loss": 4.658,
|
|
"mean_token_accuracy": 0.246959288418293,
|
|
"num_tokens": 81796206.0,
|
|
"step": 44460
|
|
},
|
|
{
|
|
"entropy": 5.4918553829193115,
|
|
"epoch": 3.714082860006682,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036687821846596706,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.23249355852603912,
|
|
"num_tokens": 81805935.0,
|
|
"step": 44465
|
|
},
|
|
{
|
|
"entropy": 5.4804035186767575,
|
|
"epoch": 3.714500501169395,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003668510428376105,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.2309458777308464,
|
|
"num_tokens": 81816615.0,
|
|
"step": 44470
|
|
},
|
|
{
|
|
"entropy": 5.458696556091309,
|
|
"epoch": 3.7149181423321083,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00036682386560129096,
|
|
"loss": 4.5721,
|
|
"mean_token_accuracy": 0.2390047714114189,
|
|
"num_tokens": 81825641.0,
|
|
"step": 44475
|
|
},
|
|
{
|
|
"entropy": 5.564533138275147,
|
|
"epoch": 3.7153357834948215,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000366796686757484,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.23501984179019927,
|
|
"num_tokens": 81836144.0,
|
|
"step": 44480
|
|
},
|
|
{
|
|
"entropy": 5.591765308380127,
|
|
"epoch": 3.7157534246575343,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003667695063066656,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.2339429035782814,
|
|
"num_tokens": 81846317.0,
|
|
"step": 44485
|
|
},
|
|
{
|
|
"entropy": 5.547014474868774,
|
|
"epoch": 3.716171065820247,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003667423242493115,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.232750828564167,
|
|
"num_tokens": 81857050.0,
|
|
"step": 44490
|
|
},
|
|
{
|
|
"entropy": 5.496233606338501,
|
|
"epoch": 3.7165887069829604,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003667151405858977,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.2468668058514595,
|
|
"num_tokens": 81865721.0,
|
|
"step": 44495
|
|
},
|
|
{
|
|
"entropy": 5.504447031021118,
|
|
"epoch": 3.717006348145673,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00036668795531689984,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.23224829733371735,
|
|
"num_tokens": 81875036.0,
|
|
"step": 44500
|
|
},
|
|
{
|
|
"entropy": 5.56182017326355,
|
|
"epoch": 3.7174239893083865,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000366660768442794,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.23628711253404616,
|
|
"num_tokens": 81885223.0,
|
|
"step": 44505
|
|
},
|
|
{
|
|
"entropy": 5.439665651321411,
|
|
"epoch": 3.7178416304710993,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003666335799640561,
|
|
"loss": 4.6803,
|
|
"mean_token_accuracy": 0.24218775629997252,
|
|
"num_tokens": 81894944.0,
|
|
"step": 44510
|
|
},
|
|
{
|
|
"entropy": 5.449333810806275,
|
|
"epoch": 3.718259271633812,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003666063898811621,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.23384150266647338,
|
|
"num_tokens": 81904718.0,
|
|
"step": 44515
|
|
},
|
|
{
|
|
"entropy": 5.516015100479126,
|
|
"epoch": 3.7186769127965253,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003665791981945879,
|
|
"loss": 4.7198,
|
|
"mean_token_accuracy": 0.2376022681593895,
|
|
"num_tokens": 81913472.0,
|
|
"step": 44520
|
|
},
|
|
{
|
|
"entropy": 5.512146806716919,
|
|
"epoch": 3.719094553959238,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00036655200490480966,
|
|
"loss": 4.7396,
|
|
"mean_token_accuracy": 0.23494144827127456,
|
|
"num_tokens": 81922620.0,
|
|
"step": 44525
|
|
},
|
|
{
|
|
"entropy": 5.555755615234375,
|
|
"epoch": 3.7195121951219514,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00036652481001230334,
|
|
"loss": 4.8016,
|
|
"mean_token_accuracy": 0.2323693573474884,
|
|
"num_tokens": 81932856.0,
|
|
"step": 44530
|
|
},
|
|
{
|
|
"entropy": 5.4941075325012205,
|
|
"epoch": 3.7199298362846642,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00036649761351754506,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.23336874842643737,
|
|
"num_tokens": 81942924.0,
|
|
"step": 44535
|
|
},
|
|
{
|
|
"entropy": 5.5316061019897464,
|
|
"epoch": 3.720347477447377,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003664704154210109,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.2413002520799637,
|
|
"num_tokens": 81952488.0,
|
|
"step": 44540
|
|
},
|
|
{
|
|
"entropy": 5.565605020523071,
|
|
"epoch": 3.7207651186100903,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036644321572317705,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.2359418511390686,
|
|
"num_tokens": 81960910.0,
|
|
"step": 44545
|
|
},
|
|
{
|
|
"entropy": 5.642821455001831,
|
|
"epoch": 3.721182759772803,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003664160144245197,
|
|
"loss": 4.8631,
|
|
"mean_token_accuracy": 0.2292309209704399,
|
|
"num_tokens": 81971213.0,
|
|
"step": 44550
|
|
},
|
|
{
|
|
"entropy": 5.592997217178345,
|
|
"epoch": 3.7216004009355164,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003663888115255149,
|
|
"loss": 4.6868,
|
|
"mean_token_accuracy": 0.23722064048051833,
|
|
"num_tokens": 81980647.0,
|
|
"step": 44555
|
|
},
|
|
{
|
|
"entropy": 5.448457813262939,
|
|
"epoch": 3.722018042098229,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00036636160702663897,
|
|
"loss": 4.6627,
|
|
"mean_token_accuracy": 0.24468652307987213,
|
|
"num_tokens": 81989001.0,
|
|
"step": 44560
|
|
},
|
|
{
|
|
"entropy": 5.503444337844849,
|
|
"epoch": 3.722435683260942,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00036633440092836804,
|
|
"loss": 4.7333,
|
|
"mean_token_accuracy": 0.24300962835550308,
|
|
"num_tokens": 81998503.0,
|
|
"step": 44565
|
|
},
|
|
{
|
|
"entropy": 5.493700647354126,
|
|
"epoch": 3.7228533244236552,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00036630719323117863,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.23047855794429778,
|
|
"num_tokens": 82007688.0,
|
|
"step": 44570
|
|
},
|
|
{
|
|
"entropy": 5.545819568634033,
|
|
"epoch": 3.723270965586368,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003662799839355468,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.24621793776750564,
|
|
"num_tokens": 82015679.0,
|
|
"step": 44575
|
|
},
|
|
{
|
|
"entropy": 5.560583829879761,
|
|
"epoch": 3.7236886067490813,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00036625277304194905,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.22789598852396012,
|
|
"num_tokens": 82026211.0,
|
|
"step": 44580
|
|
},
|
|
{
|
|
"entropy": 5.587258911132812,
|
|
"epoch": 3.724106247911794,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00036622556055086167,
|
|
"loss": 4.7422,
|
|
"mean_token_accuracy": 0.23586678206920625,
|
|
"num_tokens": 82035133.0,
|
|
"step": 44585
|
|
},
|
|
{
|
|
"entropy": 5.5738019943237305,
|
|
"epoch": 3.724523889074507,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00036619834646276097,
|
|
"loss": 4.7383,
|
|
"mean_token_accuracy": 0.23219930827617646,
|
|
"num_tokens": 82044367.0,
|
|
"step": 44590
|
|
},
|
|
{
|
|
"entropy": 5.535124158859253,
|
|
"epoch": 3.72494153023722,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036617113077812345,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.23235561996698378,
|
|
"num_tokens": 82052908.0,
|
|
"step": 44595
|
|
},
|
|
{
|
|
"entropy": 5.542281436920166,
|
|
"epoch": 3.7253591713999334,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003661439134974256,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.22350175827741622,
|
|
"num_tokens": 82062372.0,
|
|
"step": 44600
|
|
},
|
|
{
|
|
"entropy": 5.483644199371338,
|
|
"epoch": 3.7257768125626463,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036611669462114385,
|
|
"loss": 4.6692,
|
|
"mean_token_accuracy": 0.2377756729722023,
|
|
"num_tokens": 82071516.0,
|
|
"step": 44605
|
|
},
|
|
{
|
|
"entropy": 5.575030040740967,
|
|
"epoch": 3.726194453725359,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00036608947414975456,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.23264214098453523,
|
|
"num_tokens": 82080412.0,
|
|
"step": 44610
|
|
},
|
|
{
|
|
"entropy": 5.477637720108032,
|
|
"epoch": 3.7266120948880723,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003660622520837344,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.23209567070007325,
|
|
"num_tokens": 82090024.0,
|
|
"step": 44615
|
|
},
|
|
{
|
|
"entropy": 5.541945075988769,
|
|
"epoch": 3.727029736050785,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036603502842356,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.22232370227575302,
|
|
"num_tokens": 82099580.0,
|
|
"step": 44620
|
|
},
|
|
{
|
|
"entropy": 5.529086971282959,
|
|
"epoch": 3.7274473772134984,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00036600780316970783,
|
|
"loss": 4.6807,
|
|
"mean_token_accuracy": 0.24252257794141768,
|
|
"num_tokens": 82109326.0,
|
|
"step": 44625
|
|
},
|
|
{
|
|
"entropy": 5.5871340274810795,
|
|
"epoch": 3.727865018376211,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003659805763226546,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.2241418480873108,
|
|
"num_tokens": 82119340.0,
|
|
"step": 44630
|
|
},
|
|
{
|
|
"entropy": 5.507447957992554,
|
|
"epoch": 3.728282659538924,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003659533478828767,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.23800986558198928,
|
|
"num_tokens": 82127856.0,
|
|
"step": 44635
|
|
},
|
|
{
|
|
"entropy": 5.43976240158081,
|
|
"epoch": 3.7287003007016373,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003659261178508511,
|
|
"loss": 4.655,
|
|
"mean_token_accuracy": 0.24877277612686158,
|
|
"num_tokens": 82136691.0,
|
|
"step": 44640
|
|
},
|
|
{
|
|
"entropy": 5.528837823867798,
|
|
"epoch": 3.72911794186435,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00036589888622705417,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.2357616037130356,
|
|
"num_tokens": 82146506.0,
|
|
"step": 44645
|
|
},
|
|
{
|
|
"entropy": 5.526108026504517,
|
|
"epoch": 3.7295355830270633,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000365871653011963,
|
|
"loss": 4.758,
|
|
"mean_token_accuracy": 0.23077753484249114,
|
|
"num_tokens": 82155873.0,
|
|
"step": 44650
|
|
},
|
|
{
|
|
"entropy": 5.439948415756225,
|
|
"epoch": 3.729953224189776,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00036584441820605414,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.2367565304040909,
|
|
"num_tokens": 82165236.0,
|
|
"step": 44655
|
|
},
|
|
{
|
|
"entropy": 5.51937198638916,
|
|
"epoch": 3.730370865352489,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00036581718180980435,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.23534021973609925,
|
|
"num_tokens": 82174018.0,
|
|
"step": 44660
|
|
},
|
|
{
|
|
"entropy": 5.517339897155762,
|
|
"epoch": 3.730788506515202,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003657899438236904,
|
|
"loss": 4.748,
|
|
"mean_token_accuracy": 0.23576910942792892,
|
|
"num_tokens": 82183489.0,
|
|
"step": 44665
|
|
},
|
|
{
|
|
"entropy": 5.497208881378174,
|
|
"epoch": 3.731206147677915,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003657627042481894,
|
|
"loss": 4.6856,
|
|
"mean_token_accuracy": 0.2406648725271225,
|
|
"num_tokens": 82192385.0,
|
|
"step": 44670
|
|
},
|
|
{
|
|
"entropy": 5.513544416427612,
|
|
"epoch": 3.7316237888406283,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00036573546308377777,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.23107003271579743,
|
|
"num_tokens": 82201418.0,
|
|
"step": 44675
|
|
},
|
|
{
|
|
"entropy": 5.515609836578369,
|
|
"epoch": 3.732041430003341,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003657082203309328,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.23520599752664567,
|
|
"num_tokens": 82210165.0,
|
|
"step": 44680
|
|
},
|
|
{
|
|
"entropy": 5.4900956630706785,
|
|
"epoch": 3.732459071166054,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003656809759901313,
|
|
"loss": 4.6963,
|
|
"mean_token_accuracy": 0.22946908324956894,
|
|
"num_tokens": 82220160.0,
|
|
"step": 44685
|
|
},
|
|
{
|
|
"entropy": 5.508650445938111,
|
|
"epoch": 3.732876712328767,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036565373006185,
|
|
"loss": 4.7807,
|
|
"mean_token_accuracy": 0.22536781132221223,
|
|
"num_tokens": 82229251.0,
|
|
"step": 44690
|
|
},
|
|
{
|
|
"entropy": 5.591408681869507,
|
|
"epoch": 3.73329435349148,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003656264825465661,
|
|
"loss": 4.8067,
|
|
"mean_token_accuracy": 0.22724124640226365,
|
|
"num_tokens": 82238638.0,
|
|
"step": 44695
|
|
},
|
|
{
|
|
"entropy": 5.619318628311158,
|
|
"epoch": 3.7337119946541932,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00036559923344475656,
|
|
"loss": 4.7567,
|
|
"mean_token_accuracy": 0.23131374418735504,
|
|
"num_tokens": 82246620.0,
|
|
"step": 44700
|
|
},
|
|
{
|
|
"entropy": 5.534566879272461,
|
|
"epoch": 3.734129635816906,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003655719827568984,
|
|
"loss": 4.7378,
|
|
"mean_token_accuracy": 0.23118302524089812,
|
|
"num_tokens": 82256845.0,
|
|
"step": 44705
|
|
},
|
|
{
|
|
"entropy": 5.556736946105957,
|
|
"epoch": 3.734547276979619,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003655447304834686,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.24151815921068193,
|
|
"num_tokens": 82266214.0,
|
|
"step": 44710
|
|
},
|
|
{
|
|
"entropy": 5.4993894577026365,
|
|
"epoch": 3.734964918142332,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003655174766249443,
|
|
"loss": 4.67,
|
|
"mean_token_accuracy": 0.23877599090337753,
|
|
"num_tokens": 82274929.0,
|
|
"step": 44715
|
|
},
|
|
{
|
|
"entropy": 5.525778675079346,
|
|
"epoch": 3.7353825593050454,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0003654902211818027,
|
|
"loss": 4.6613,
|
|
"mean_token_accuracy": 0.24491645395755768,
|
|
"num_tokens": 82283144.0,
|
|
"step": 44720
|
|
},
|
|
{
|
|
"entropy": 5.5237830638885494,
|
|
"epoch": 3.735800200467758,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003654629641545208,
|
|
"loss": 4.6903,
|
|
"mean_token_accuracy": 0.24136805087327956,
|
|
"num_tokens": 82292241.0,
|
|
"step": 44725
|
|
},
|
|
{
|
|
"entropy": 5.5036492347717285,
|
|
"epoch": 3.736217841630471,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003654357055435758,
|
|
"loss": 4.6686,
|
|
"mean_token_accuracy": 0.24099466651678086,
|
|
"num_tokens": 82301307.0,
|
|
"step": 44730
|
|
},
|
|
{
|
|
"entropy": 5.510721921920776,
|
|
"epoch": 3.7366354827931842,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000365408445349445,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.2371396690607071,
|
|
"num_tokens": 82309693.0,
|
|
"step": 44735
|
|
},
|
|
{
|
|
"entropy": 5.562246179580688,
|
|
"epoch": 3.737053123955897,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003653811835726055,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.23309363573789596,
|
|
"num_tokens": 82319026.0,
|
|
"step": 44740
|
|
},
|
|
{
|
|
"entropy": 5.535211133956909,
|
|
"epoch": 3.7374707651186103,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003653539202135345,
|
|
"loss": 4.773,
|
|
"mean_token_accuracy": 0.23237081617116928,
|
|
"num_tokens": 82328051.0,
|
|
"step": 44745
|
|
},
|
|
{
|
|
"entropy": 5.579678201675415,
|
|
"epoch": 3.737888406281323,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036532665527270943,
|
|
"loss": 4.7806,
|
|
"mean_token_accuracy": 0.2310769736766815,
|
|
"num_tokens": 82336261.0,
|
|
"step": 44750
|
|
},
|
|
{
|
|
"entropy": 5.490066623687744,
|
|
"epoch": 3.738306047444036,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003652993887506075,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.23677541613578795,
|
|
"num_tokens": 82345246.0,
|
|
"step": 44755
|
|
},
|
|
{
|
|
"entropy": 5.589498996734619,
|
|
"epoch": 3.738723688606749,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003652721206477062,
|
|
"loss": 4.896,
|
|
"mean_token_accuracy": 0.21848268210887908,
|
|
"num_tokens": 82355737.0,
|
|
"step": 44760
|
|
},
|
|
{
|
|
"entropy": 5.596019077301025,
|
|
"epoch": 3.739141329769462,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00036524485096448266,
|
|
"loss": 4.7776,
|
|
"mean_token_accuracy": 0.23257021903991698,
|
|
"num_tokens": 82365480.0,
|
|
"step": 44765
|
|
},
|
|
{
|
|
"entropy": 5.546948051452636,
|
|
"epoch": 3.7395589709321753,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003652175797014144,
|
|
"loss": 4.6665,
|
|
"mean_token_accuracy": 0.23956629186868666,
|
|
"num_tokens": 82373415.0,
|
|
"step": 44770
|
|
},
|
|
{
|
|
"entropy": 5.506046533584595,
|
|
"epoch": 3.739976612094888,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003651903068589788,
|
|
"loss": 4.7738,
|
|
"mean_token_accuracy": 0.23352903723716736,
|
|
"num_tokens": 82382123.0,
|
|
"step": 44775
|
|
},
|
|
{
|
|
"entropy": 5.558873224258423,
|
|
"epoch": 3.740394253257601,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00036516303243765337,
|
|
"loss": 4.7679,
|
|
"mean_token_accuracy": 0.23445713371038437,
|
|
"num_tokens": 82391218.0,
|
|
"step": 44780
|
|
},
|
|
{
|
|
"entropy": 5.506086015701294,
|
|
"epoch": 3.740811894420314,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00036513575643791545,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.2312003940343857,
|
|
"num_tokens": 82400166.0,
|
|
"step": 44785
|
|
},
|
|
{
|
|
"entropy": 5.500543117523193,
|
|
"epoch": 3.741229535583027,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003651084788602427,
|
|
"loss": 4.7228,
|
|
"mean_token_accuracy": 0.2339269623160362,
|
|
"num_tokens": 82409828.0,
|
|
"step": 44790
|
|
},
|
|
{
|
|
"entropy": 5.5110057353973385,
|
|
"epoch": 3.74164717674574,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00036508119970511254,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.23469994068145753,
|
|
"num_tokens": 82419350.0,
|
|
"step": 44795
|
|
},
|
|
{
|
|
"entropy": 5.59022159576416,
|
|
"epoch": 3.742064817908453,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003650539189730025,
|
|
"loss": 4.7832,
|
|
"mean_token_accuracy": 0.23456877171993257,
|
|
"num_tokens": 82429644.0,
|
|
"step": 44800
|
|
},
|
|
{
|
|
"entropy": 5.650617027282715,
|
|
"epoch": 3.742482459071166,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003650266366643903,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.22381250858306884,
|
|
"num_tokens": 82439218.0,
|
|
"step": 44805
|
|
},
|
|
{
|
|
"entropy": 5.489584112167359,
|
|
"epoch": 3.742900100233879,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036499935277975335,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.23727409839630126,
|
|
"num_tokens": 82448105.0,
|
|
"step": 44810
|
|
},
|
|
{
|
|
"entropy": 5.525198554992675,
|
|
"epoch": 3.743317741396592,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00036497206731956944,
|
|
"loss": 4.7032,
|
|
"mean_token_accuracy": 0.24146949350833893,
|
|
"num_tokens": 82457323.0,
|
|
"step": 44815
|
|
},
|
|
{
|
|
"entropy": 5.571387434005738,
|
|
"epoch": 3.743735382559305,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003649447802843162,
|
|
"loss": 4.8202,
|
|
"mean_token_accuracy": 0.22696258574724198,
|
|
"num_tokens": 82465765.0,
|
|
"step": 44820
|
|
},
|
|
{
|
|
"entropy": 5.556689643859864,
|
|
"epoch": 3.744153023722018,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0003649174916744713,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.23608231246471406,
|
|
"num_tokens": 82475412.0,
|
|
"step": 44825
|
|
},
|
|
{
|
|
"entropy": 5.514794111251831,
|
|
"epoch": 3.744570664884731,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003648902014905125,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.23788469284772873,
|
|
"num_tokens": 82484658.0,
|
|
"step": 44830
|
|
},
|
|
{
|
|
"entropy": 5.479098701477051,
|
|
"epoch": 3.744988306047444,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003648629097329175,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.23394242972135543,
|
|
"num_tokens": 82493289.0,
|
|
"step": 44835
|
|
},
|
|
{
|
|
"entropy": 5.513842391967773,
|
|
"epoch": 3.7454059472101573,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0003648356164021641,
|
|
"loss": 4.687,
|
|
"mean_token_accuracy": 0.2347453474998474,
|
|
"num_tokens": 82502396.0,
|
|
"step": 44840
|
|
},
|
|
{
|
|
"entropy": 5.472558307647705,
|
|
"epoch": 3.74582358837287,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003648083214987302,
|
|
"loss": 4.67,
|
|
"mean_token_accuracy": 0.24356057047843932,
|
|
"num_tokens": 82512591.0,
|
|
"step": 44845
|
|
},
|
|
{
|
|
"entropy": 5.544458436965942,
|
|
"epoch": 3.746241229535583,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003647810250230934,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.23490780889987944,
|
|
"num_tokens": 82522057.0,
|
|
"step": 44850
|
|
},
|
|
{
|
|
"entropy": 5.464649820327759,
|
|
"epoch": 3.746658870698296,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003647537269757317,
|
|
"loss": 4.6486,
|
|
"mean_token_accuracy": 0.24590084403753282,
|
|
"num_tokens": 82530490.0,
|
|
"step": 44855
|
|
},
|
|
{
|
|
"entropy": 5.464461755752564,
|
|
"epoch": 3.747076511861009,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000364726427357123,
|
|
"loss": 4.6181,
|
|
"mean_token_accuracy": 0.2450473949313164,
|
|
"num_tokens": 82540035.0,
|
|
"step": 44860
|
|
},
|
|
{
|
|
"entropy": 5.544702053070068,
|
|
"epoch": 3.7474941530237222,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003646991261677452,
|
|
"loss": 4.7127,
|
|
"mean_token_accuracy": 0.2316498875617981,
|
|
"num_tokens": 82548990.0,
|
|
"step": 44865
|
|
},
|
|
{
|
|
"entropy": 5.4742506980896,
|
|
"epoch": 3.747911794186435,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003646718234080762,
|
|
"loss": 4.644,
|
|
"mean_token_accuracy": 0.24175891429185867,
|
|
"num_tokens": 82557246.0,
|
|
"step": 44870
|
|
},
|
|
{
|
|
"entropy": 5.509496021270752,
|
|
"epoch": 3.748329435349148,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036464451907859403,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.2345365732908249,
|
|
"num_tokens": 82567283.0,
|
|
"step": 44875
|
|
},
|
|
{
|
|
"entropy": 5.596725702285767,
|
|
"epoch": 3.748747076511861,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003646172131797766,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.23768280297517777,
|
|
"num_tokens": 82575857.0,
|
|
"step": 44880
|
|
},
|
|
{
|
|
"entropy": 5.603432893753052,
|
|
"epoch": 3.749164717674574,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000364589905712102,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.22895153015851974,
|
|
"num_tokens": 82584712.0,
|
|
"step": 44885
|
|
},
|
|
{
|
|
"entropy": 5.527665376663208,
|
|
"epoch": 3.749582358837287,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003645625966760483,
|
|
"loss": 4.6885,
|
|
"mean_token_accuracy": 0.2420301467180252,
|
|
"num_tokens": 82593871.0,
|
|
"step": 44890
|
|
},
|
|
{
|
|
"entropy": 5.512714052200318,
|
|
"epoch": 3.75,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00036453528607209346,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.23617140501737593,
|
|
"num_tokens": 82602851.0,
|
|
"step": 44895
|
|
},
|
|
{
|
|
"entropy": 5.44058666229248,
|
|
"epoch": 3.750417641162713,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00036450797390071574,
|
|
"loss": 4.6059,
|
|
"mean_token_accuracy": 0.2465214639902115,
|
|
"num_tokens": 82612015.0,
|
|
"step": 44900
|
|
},
|
|
{
|
|
"entropy": 5.570470094680786,
|
|
"epoch": 3.750835282325426,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00036448066016239316,
|
|
"loss": 4.7187,
|
|
"mean_token_accuracy": 0.23871274441480636,
|
|
"num_tokens": 82620765.0,
|
|
"step": 44905
|
|
},
|
|
{
|
|
"entropy": 5.463856840133667,
|
|
"epoch": 3.751252923488139,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003644533448576039,
|
|
"loss": 4.6849,
|
|
"mean_token_accuracy": 0.23735546469688415,
|
|
"num_tokens": 82628977.0,
|
|
"step": 44910
|
|
},
|
|
{
|
|
"entropy": 5.500213479995727,
|
|
"epoch": 3.751670564650852,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036442602798682623,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.23119355589151383,
|
|
"num_tokens": 82638254.0,
|
|
"step": 44915
|
|
},
|
|
{
|
|
"entropy": 5.541119813919067,
|
|
"epoch": 3.752088205813565,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00036439870955053816,
|
|
"loss": 4.6519,
|
|
"mean_token_accuracy": 0.23916148990392685,
|
|
"num_tokens": 82647762.0,
|
|
"step": 44920
|
|
},
|
|
{
|
|
"entropy": 5.542876577377319,
|
|
"epoch": 3.7525058469762778,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036437138954921824,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.23913525491952897,
|
|
"num_tokens": 82656728.0,
|
|
"step": 44925
|
|
},
|
|
{
|
|
"entropy": 5.584588146209716,
|
|
"epoch": 3.752923488138991,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00036434406798334444,
|
|
"loss": 4.8114,
|
|
"mean_token_accuracy": 0.22667419016361237,
|
|
"num_tokens": 82665831.0,
|
|
"step": 44930
|
|
},
|
|
{
|
|
"entropy": 5.6017303466796875,
|
|
"epoch": 3.753341129301704,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003643167448533952,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.23752089589834213,
|
|
"num_tokens": 82675121.0,
|
|
"step": 44935
|
|
},
|
|
{
|
|
"entropy": 5.515863084793091,
|
|
"epoch": 3.753758770464417,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00036428942015984887,
|
|
"loss": 4.7254,
|
|
"mean_token_accuracy": 0.23593973070383073,
|
|
"num_tokens": 82683802.0,
|
|
"step": 44940
|
|
},
|
|
{
|
|
"entropy": 5.484610176086425,
|
|
"epoch": 3.75417641162713,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00036426209390318375,
|
|
"loss": 4.6913,
|
|
"mean_token_accuracy": 0.23858440816402435,
|
|
"num_tokens": 82693230.0,
|
|
"step": 44945
|
|
},
|
|
{
|
|
"entropy": 5.474486207962036,
|
|
"epoch": 3.7545940527898427,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00036423476608387826,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.24050431847572326,
|
|
"num_tokens": 82701298.0,
|
|
"step": 44950
|
|
},
|
|
{
|
|
"entropy": 5.52359185218811,
|
|
"epoch": 3.755011693952556,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00036420743670241074,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.2345745474100113,
|
|
"num_tokens": 82710413.0,
|
|
"step": 44955
|
|
},
|
|
{
|
|
"entropy": 5.542008876800537,
|
|
"epoch": 3.755429335115269,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003641801057592598,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.2333453819155693,
|
|
"num_tokens": 82719005.0,
|
|
"step": 44960
|
|
},
|
|
{
|
|
"entropy": 5.473966598510742,
|
|
"epoch": 3.755846976277982,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036415277325490354,
|
|
"loss": 4.7338,
|
|
"mean_token_accuracy": 0.23963321894407272,
|
|
"num_tokens": 82728361.0,
|
|
"step": 44965
|
|
},
|
|
{
|
|
"entropy": 5.519105863571167,
|
|
"epoch": 3.756264617440695,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003641254391898208,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.2338176593184471,
|
|
"num_tokens": 82737409.0,
|
|
"step": 44970
|
|
},
|
|
{
|
|
"entropy": 5.591152906417847,
|
|
"epoch": 3.756682258603408,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003640981035644899,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.23190400749444962,
|
|
"num_tokens": 82746036.0,
|
|
"step": 44975
|
|
},
|
|
{
|
|
"entropy": 5.550479602813721,
|
|
"epoch": 3.757099899766121,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003640707663793895,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.23350929021835326,
|
|
"num_tokens": 82755615.0,
|
|
"step": 44980
|
|
},
|
|
{
|
|
"entropy": 5.508299207687378,
|
|
"epoch": 3.757517540928834,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00036404342763499814,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.22549997568130492,
|
|
"num_tokens": 82764257.0,
|
|
"step": 44985
|
|
},
|
|
{
|
|
"entropy": 5.503856039047241,
|
|
"epoch": 3.757935182091547,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00036401608733179435,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.2340971753001213,
|
|
"num_tokens": 82773635.0,
|
|
"step": 44990
|
|
},
|
|
{
|
|
"entropy": 5.618563032150268,
|
|
"epoch": 3.75835282325426,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003639887454702568,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.22834839820861816,
|
|
"num_tokens": 82783637.0,
|
|
"step": 44995
|
|
},
|
|
{
|
|
"entropy": 5.550993251800537,
|
|
"epoch": 3.758770464416973,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003639614020508642,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.22942253202199936,
|
|
"num_tokens": 82793081.0,
|
|
"step": 45000
|
|
},
|
|
{
|
|
"epoch": 3.758770464416973,
|
|
"eval_entropy": 5.201569376898832,
|
|
"eval_loss": 4.7305474281311035,
|
|
"eval_mean_token_accuracy": 0.2466688454577262,
|
|
"eval_num_tokens": 82793081.0,
|
|
"eval_runtime": 20.8917,
|
|
"eval_samples_per_second": 1807.563,
|
|
"eval_steps_per_second": 225.975,
|
|
"step": 45000
|
|
},
|
|
{
|
|
"entropy": 5.623502969741821,
|
|
"epoch": 3.759188105579686,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003639340570740951,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.22789347618818284,
|
|
"num_tokens": 82802506.0,
|
|
"step": 45005
|
|
},
|
|
{
|
|
"entropy": 5.573910045623779,
|
|
"epoch": 3.759605746742399,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00036390671054042836,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.22869905978441238,
|
|
"num_tokens": 82811499.0,
|
|
"step": 45010
|
|
},
|
|
{
|
|
"entropy": 5.521754503250122,
|
|
"epoch": 3.760023387905112,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003638793624503426,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.23280212581157683,
|
|
"num_tokens": 82820289.0,
|
|
"step": 45015
|
|
},
|
|
{
|
|
"entropy": 5.488431596755982,
|
|
"epoch": 3.7604410290678247,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036385201280431665,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.24080578237771988,
|
|
"num_tokens": 82829978.0,
|
|
"step": 45020
|
|
},
|
|
{
|
|
"entropy": 5.451123762130737,
|
|
"epoch": 3.760858670230538,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036382466160282917,
|
|
"loss": 4.6565,
|
|
"mean_token_accuracy": 0.2364413857460022,
|
|
"num_tokens": 82839523.0,
|
|
"step": 45025
|
|
},
|
|
{
|
|
"entropy": 5.469245100021363,
|
|
"epoch": 3.761276311393251,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00036379730884635915,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.23980328142642976,
|
|
"num_tokens": 82848023.0,
|
|
"step": 45030
|
|
},
|
|
{
|
|
"entropy": 5.51934118270874,
|
|
"epoch": 3.761693952555964,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00036376995453538536,
|
|
"loss": 4.7227,
|
|
"mean_token_accuracy": 0.23366792649030685,
|
|
"num_tokens": 82857405.0,
|
|
"step": 45035
|
|
},
|
|
{
|
|
"entropy": 5.558668613433838,
|
|
"epoch": 3.762111593718677,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003637425986703866,
|
|
"loss": 4.7382,
|
|
"mean_token_accuracy": 0.22874933779239653,
|
|
"num_tokens": 82866725.0,
|
|
"step": 45040
|
|
},
|
|
{
|
|
"entropy": 5.475603342056274,
|
|
"epoch": 3.7625292348813897,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003637152412518419,
|
|
"loss": 4.6217,
|
|
"mean_token_accuracy": 0.24491806030273439,
|
|
"num_tokens": 82875560.0,
|
|
"step": 45045
|
|
},
|
|
{
|
|
"entropy": 5.551198148727417,
|
|
"epoch": 3.762946876044103,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00036368788228023,
|
|
"loss": 4.6722,
|
|
"mean_token_accuracy": 0.23866381347179413,
|
|
"num_tokens": 82884587.0,
|
|
"step": 45050
|
|
},
|
|
{
|
|
"entropy": 5.48816704750061,
|
|
"epoch": 3.7633645172068158,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003636605217560301,
|
|
"loss": 4.599,
|
|
"mean_token_accuracy": 0.2418915256857872,
|
|
"num_tokens": 82892961.0,
|
|
"step": 45055
|
|
},
|
|
{
|
|
"entropy": 5.451658487319946,
|
|
"epoch": 3.763782158369529,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000363633159679721,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.24468945562839509,
|
|
"num_tokens": 82901899.0,
|
|
"step": 45060
|
|
},
|
|
{
|
|
"entropy": 5.44382529258728,
|
|
"epoch": 3.764199799532242,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036360579605178176,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.23433370143175125,
|
|
"num_tokens": 82910732.0,
|
|
"step": 45065
|
|
},
|
|
{
|
|
"entropy": 5.60315465927124,
|
|
"epoch": 3.7646174406949546,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00036357843087269135,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.24619931429624559,
|
|
"num_tokens": 82919410.0,
|
|
"step": 45070
|
|
},
|
|
{
|
|
"entropy": 5.545728254318237,
|
|
"epoch": 3.765035081857668,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00036355106414292886,
|
|
"loss": 4.6632,
|
|
"mean_token_accuracy": 0.23647484481334685,
|
|
"num_tokens": 82927950.0,
|
|
"step": 45075
|
|
},
|
|
{
|
|
"entropy": 5.58041672706604,
|
|
"epoch": 3.765452723020381,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00036352369586297356,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.23594011813402177,
|
|
"num_tokens": 82938335.0,
|
|
"step": 45080
|
|
},
|
|
{
|
|
"entropy": 5.485473394393921,
|
|
"epoch": 3.765870364183094,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003634963260333043,
|
|
"loss": 4.6811,
|
|
"mean_token_accuracy": 0.23143312633037566,
|
|
"num_tokens": 82946523.0,
|
|
"step": 45085
|
|
},
|
|
{
|
|
"entropy": 5.578622579574585,
|
|
"epoch": 3.7662880053458068,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003634689546544004,
|
|
"loss": 4.8128,
|
|
"mean_token_accuracy": 0.22796353697776794,
|
|
"num_tokens": 82956544.0,
|
|
"step": 45090
|
|
},
|
|
{
|
|
"entropy": 5.611462831497192,
|
|
"epoch": 3.76670564650852,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003634415817267409,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.23715664446353912,
|
|
"num_tokens": 82966958.0,
|
|
"step": 45095
|
|
},
|
|
{
|
|
"entropy": 5.497906589508057,
|
|
"epoch": 3.767123287671233,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000363414207250805,
|
|
"loss": 4.5854,
|
|
"mean_token_accuracy": 0.2488846004009247,
|
|
"num_tokens": 82975910.0,
|
|
"step": 45100
|
|
},
|
|
{
|
|
"entropy": 5.473430919647217,
|
|
"epoch": 3.767540928833946,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000363386831227072,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.24737917482852936,
|
|
"num_tokens": 82984525.0,
|
|
"step": 45105
|
|
},
|
|
{
|
|
"entropy": 5.550875425338745,
|
|
"epoch": 3.767958569996659,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003633594536560212,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.23317354321479797,
|
|
"num_tokens": 82994066.0,
|
|
"step": 45110
|
|
},
|
|
{
|
|
"entropy": 5.608313369750976,
|
|
"epoch": 3.7683762111593717,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00036333207453813175,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.23230454176664353,
|
|
"num_tokens": 83003508.0,
|
|
"step": 45115
|
|
},
|
|
{
|
|
"entropy": 5.553019046783447,
|
|
"epoch": 3.768793852322085,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00036330469387388305,
|
|
"loss": 4.6552,
|
|
"mean_token_accuracy": 0.23337970227003096,
|
|
"num_tokens": 83012149.0,
|
|
"step": 45120
|
|
},
|
|
{
|
|
"entropy": 5.4392077922821045,
|
|
"epoch": 3.769211493484798,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00036327731166375433,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.24722542762756347,
|
|
"num_tokens": 83022485.0,
|
|
"step": 45125
|
|
},
|
|
{
|
|
"entropy": 5.562763452529907,
|
|
"epoch": 3.769629134647511,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003632499279082251,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.23320927023887633,
|
|
"num_tokens": 83032132.0,
|
|
"step": 45130
|
|
},
|
|
{
|
|
"entropy": 5.564849901199341,
|
|
"epoch": 3.770046775810224,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00036322254260777464,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.23705652207136155,
|
|
"num_tokens": 83042528.0,
|
|
"step": 45135
|
|
},
|
|
{
|
|
"entropy": 5.540700674057007,
|
|
"epoch": 3.7704644169729367,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003631951557628824,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.2421823501586914,
|
|
"num_tokens": 83050942.0,
|
|
"step": 45140
|
|
},
|
|
{
|
|
"entropy": 5.598360586166382,
|
|
"epoch": 3.77088205813565,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00036316776737402767,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.22018641084432602,
|
|
"num_tokens": 83059785.0,
|
|
"step": 45145
|
|
},
|
|
{
|
|
"entropy": 5.61317811012268,
|
|
"epoch": 3.7712996992983627,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003631403774416901,
|
|
"loss": 4.8357,
|
|
"mean_token_accuracy": 0.23268781006336212,
|
|
"num_tokens": 83068742.0,
|
|
"step": 45150
|
|
},
|
|
{
|
|
"entropy": 5.548153924942016,
|
|
"epoch": 3.771717340461076,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036311298596634916,
|
|
"loss": 4.761,
|
|
"mean_token_accuracy": 0.23268944025039673,
|
|
"num_tokens": 83078515.0,
|
|
"step": 45155
|
|
},
|
|
{
|
|
"entropy": 5.58009705543518,
|
|
"epoch": 3.772134981623789,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003630855929484844,
|
|
"loss": 4.8548,
|
|
"mean_token_accuracy": 0.2259267032146454,
|
|
"num_tokens": 83088095.0,
|
|
"step": 45160
|
|
},
|
|
{
|
|
"entropy": 5.531277227401733,
|
|
"epoch": 3.7725526227865016,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0003630581983885752,
|
|
"loss": 4.6687,
|
|
"mean_token_accuracy": 0.242325559258461,
|
|
"num_tokens": 83096780.0,
|
|
"step": 45165
|
|
},
|
|
{
|
|
"entropy": 5.502858448028564,
|
|
"epoch": 3.772970263949215,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003630308022871012,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.23387494385242463,
|
|
"num_tokens": 83106152.0,
|
|
"step": 45170
|
|
},
|
|
{
|
|
"entropy": 5.494756698608398,
|
|
"epoch": 3.7733879051119277,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003630034046445422,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.23508464992046357,
|
|
"num_tokens": 83115179.0,
|
|
"step": 45175
|
|
},
|
|
{
|
|
"entropy": 5.476974773406982,
|
|
"epoch": 3.773805546274641,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00036297600546137754,
|
|
"loss": 4.6641,
|
|
"mean_token_accuracy": 0.23910945951938628,
|
|
"num_tokens": 83124667.0,
|
|
"step": 45180
|
|
},
|
|
{
|
|
"entropy": 5.580229568481445,
|
|
"epoch": 3.7742231874373537,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036294860473808706,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.22735133320093154,
|
|
"num_tokens": 83134676.0,
|
|
"step": 45185
|
|
},
|
|
{
|
|
"entropy": 5.560912322998047,
|
|
"epoch": 3.7746408286000666,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003629212024751504,
|
|
"loss": 4.7397,
|
|
"mean_token_accuracy": 0.23614225834608077,
|
|
"num_tokens": 83143880.0,
|
|
"step": 45190
|
|
},
|
|
{
|
|
"entropy": 5.510400009155274,
|
|
"epoch": 3.77505846976278,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003628937986730472,
|
|
"loss": 4.7119,
|
|
"mean_token_accuracy": 0.23316264152526855,
|
|
"num_tokens": 83152772.0,
|
|
"step": 45195
|
|
},
|
|
{
|
|
"entropy": 5.48987832069397,
|
|
"epoch": 3.775476110925493,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003628663933322573,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.23595667630434036,
|
|
"num_tokens": 83161662.0,
|
|
"step": 45200
|
|
},
|
|
{
|
|
"entropy": 5.544788026809693,
|
|
"epoch": 3.775893752088206,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003628389864532604,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.23521346151828765,
|
|
"num_tokens": 83171521.0,
|
|
"step": 45205
|
|
},
|
|
{
|
|
"entropy": 5.502546882629394,
|
|
"epoch": 3.7763113932509187,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003628115780365364,
|
|
"loss": 4.5743,
|
|
"mean_token_accuracy": 0.2466645747423172,
|
|
"num_tokens": 83180080.0,
|
|
"step": 45210
|
|
},
|
|
{
|
|
"entropy": 5.523397636413574,
|
|
"epoch": 3.776729034413632,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003627841680825649,
|
|
"loss": 4.7334,
|
|
"mean_token_accuracy": 0.235109406709671,
|
|
"num_tokens": 83189234.0,
|
|
"step": 45215
|
|
},
|
|
{
|
|
"entropy": 5.473035621643066,
|
|
"epoch": 3.7771466755763448,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00036275675659182597,
|
|
"loss": 4.6721,
|
|
"mean_token_accuracy": 0.24628809988498687,
|
|
"num_tokens": 83198092.0,
|
|
"step": 45220
|
|
},
|
|
{
|
|
"entropy": 5.546364593505859,
|
|
"epoch": 3.777564316739058,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003627293435647994,
|
|
"loss": 4.7779,
|
|
"mean_token_accuracy": 0.2375581219792366,
|
|
"num_tokens": 83207125.0,
|
|
"step": 45225
|
|
},
|
|
{
|
|
"entropy": 5.419360589981079,
|
|
"epoch": 3.777981957901771,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000362701929001965,
|
|
"loss": 4.5973,
|
|
"mean_token_accuracy": 0.24800885319709778,
|
|
"num_tokens": 83216401.0,
|
|
"step": 45230
|
|
},
|
|
{
|
|
"entropy": 5.50538477897644,
|
|
"epoch": 3.7783995990644836,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00036267451290380277,
|
|
"loss": 4.7046,
|
|
"mean_token_accuracy": 0.2399088978767395,
|
|
"num_tokens": 83225227.0,
|
|
"step": 45235
|
|
},
|
|
{
|
|
"entropy": 5.546785354614258,
|
|
"epoch": 3.778817240227197,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003626470952707926,
|
|
"loss": 4.7334,
|
|
"mean_token_accuracy": 0.23002631962299347,
|
|
"num_tokens": 83233659.0,
|
|
"step": 45240
|
|
},
|
|
{
|
|
"entropy": 5.467376852035523,
|
|
"epoch": 3.7792348813899097,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00036261967610341474,
|
|
"loss": 4.7033,
|
|
"mean_token_accuracy": 0.23769991099834442,
|
|
"num_tokens": 83242220.0,
|
|
"step": 45245
|
|
},
|
|
{
|
|
"entropy": 5.551866769790649,
|
|
"epoch": 3.779652522552623,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003625922554021487,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.2415313959121704,
|
|
"num_tokens": 83251113.0,
|
|
"step": 45250
|
|
},
|
|
{
|
|
"entropy": 5.549315786361694,
|
|
"epoch": 3.7800701637153358,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000362564833167475,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.23585430383682252,
|
|
"num_tokens": 83260961.0,
|
|
"step": 45255
|
|
},
|
|
{
|
|
"entropy": 5.527195453643799,
|
|
"epoch": 3.7804878048780486,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00036253740939987345,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.2401803508400917,
|
|
"num_tokens": 83269588.0,
|
|
"step": 45260
|
|
},
|
|
{
|
|
"entropy": 5.588402223587036,
|
|
"epoch": 3.780905446040762,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00036250998409982415,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.22529308050870894,
|
|
"num_tokens": 83278382.0,
|
|
"step": 45265
|
|
},
|
|
{
|
|
"entropy": 5.510383033752442,
|
|
"epoch": 3.7813230872034747,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003624825572678072,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.2340321347117424,
|
|
"num_tokens": 83287764.0,
|
|
"step": 45270
|
|
},
|
|
{
|
|
"entropy": 5.503233337402344,
|
|
"epoch": 3.781740728366188,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003624551289043029,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.22853677421808244,
|
|
"num_tokens": 83297624.0,
|
|
"step": 45275
|
|
},
|
|
{
|
|
"entropy": 5.531577491760254,
|
|
"epoch": 3.7821583695289007,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00036242769900979115,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.23502849340438842,
|
|
"num_tokens": 83306667.0,
|
|
"step": 45280
|
|
},
|
|
{
|
|
"entropy": 5.5546262741088865,
|
|
"epoch": 3.7825760106916135,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003624002675847524,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.23995426893234253,
|
|
"num_tokens": 83315828.0,
|
|
"step": 45285
|
|
},
|
|
{
|
|
"entropy": 5.642804145812988,
|
|
"epoch": 3.782993651854327,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003623728346296667,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.22929445803165435,
|
|
"num_tokens": 83325638.0,
|
|
"step": 45290
|
|
},
|
|
{
|
|
"entropy": 5.5792337417602536,
|
|
"epoch": 3.7834112930170396,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003623454001450145,
|
|
"loss": 4.759,
|
|
"mean_token_accuracy": 0.2341863766312599,
|
|
"num_tokens": 83333883.0,
|
|
"step": 45295
|
|
},
|
|
{
|
|
"entropy": 5.51385383605957,
|
|
"epoch": 3.783828934179753,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003623179641312758,
|
|
"loss": 4.7078,
|
|
"mean_token_accuracy": 0.24163075685501098,
|
|
"num_tokens": 83343013.0,
|
|
"step": 45300
|
|
},
|
|
{
|
|
"entropy": 5.480474758148193,
|
|
"epoch": 3.7842465753424657,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00036229052658893107,
|
|
"loss": 4.6925,
|
|
"mean_token_accuracy": 0.24369724541902543,
|
|
"num_tokens": 83352385.0,
|
|
"step": 45305
|
|
},
|
|
{
|
|
"entropy": 5.498808670043945,
|
|
"epoch": 3.7846642165051785,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00036226308751846056,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.23288727998733522,
|
|
"num_tokens": 83360728.0,
|
|
"step": 45310
|
|
},
|
|
{
|
|
"entropy": 5.4434699535369875,
|
|
"epoch": 3.7850818576678917,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003622356469203448,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.24668026864528655,
|
|
"num_tokens": 83369172.0,
|
|
"step": 45315
|
|
},
|
|
{
|
|
"entropy": 5.478279972076416,
|
|
"epoch": 3.785499498830605,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003622082047950638,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.2414736568927765,
|
|
"num_tokens": 83379032.0,
|
|
"step": 45320
|
|
},
|
|
{
|
|
"entropy": 5.532209968566894,
|
|
"epoch": 3.785917139993318,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003621807611430984,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.23519837707281113,
|
|
"num_tokens": 83387636.0,
|
|
"step": 45325
|
|
},
|
|
{
|
|
"entropy": 5.534775304794311,
|
|
"epoch": 3.7863347811560306,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00036215331596492874,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.2462551400065422,
|
|
"num_tokens": 83397242.0,
|
|
"step": 45330
|
|
},
|
|
{
|
|
"entropy": 5.5092095851898195,
|
|
"epoch": 3.786752422318744,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003621258692610354,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.23542040288448335,
|
|
"num_tokens": 83406164.0,
|
|
"step": 45335
|
|
},
|
|
{
|
|
"entropy": 5.517458963394165,
|
|
"epoch": 3.7871700634814567,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036209842103189884,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.2358263060450554,
|
|
"num_tokens": 83416109.0,
|
|
"step": 45340
|
|
},
|
|
{
|
|
"entropy": 5.504894781112671,
|
|
"epoch": 3.78758770464417,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003620709712779996,
|
|
"loss": 4.7506,
|
|
"mean_token_accuracy": 0.2343595877289772,
|
|
"num_tokens": 83424661.0,
|
|
"step": 45345
|
|
},
|
|
{
|
|
"entropy": 5.520014667510987,
|
|
"epoch": 3.7880053458068828,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003620435199998182,
|
|
"loss": 4.658,
|
|
"mean_token_accuracy": 0.24657574892044068,
|
|
"num_tokens": 83433749.0,
|
|
"step": 45350
|
|
},
|
|
{
|
|
"entropy": 5.462750959396362,
|
|
"epoch": 3.7884229869695956,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003620160671978352,
|
|
"loss": 4.6578,
|
|
"mean_token_accuracy": 0.24269452095031738,
|
|
"num_tokens": 83442965.0,
|
|
"step": 45355
|
|
},
|
|
{
|
|
"entropy": 5.575595855712891,
|
|
"epoch": 3.788840628132309,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003619886128725312,
|
|
"loss": 4.8438,
|
|
"mean_token_accuracy": 0.22593883872032167,
|
|
"num_tokens": 83453414.0,
|
|
"step": 45360
|
|
},
|
|
{
|
|
"entropy": 5.580135440826416,
|
|
"epoch": 3.7892582692950216,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003619611570243869,
|
|
"loss": 4.7486,
|
|
"mean_token_accuracy": 0.24099447280168534,
|
|
"num_tokens": 83462273.0,
|
|
"step": 45365
|
|
},
|
|
{
|
|
"entropy": 5.486278247833252,
|
|
"epoch": 3.789675910457735,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00036193369965388273,
|
|
"loss": 4.6216,
|
|
"mean_token_accuracy": 0.24264529645442962,
|
|
"num_tokens": 83470574.0,
|
|
"step": 45370
|
|
},
|
|
{
|
|
"entropy": 5.50294132232666,
|
|
"epoch": 3.7900935516204477,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003619062407614996,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.23999677002429962,
|
|
"num_tokens": 83479390.0,
|
|
"step": 45375
|
|
},
|
|
{
|
|
"entropy": 5.521975660324097,
|
|
"epoch": 3.7905111927831605,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000361878780347718,
|
|
"loss": 4.7094,
|
|
"mean_token_accuracy": 0.23547471314668655,
|
|
"num_tokens": 83487287.0,
|
|
"step": 45380
|
|
},
|
|
{
|
|
"entropy": 5.531964540481567,
|
|
"epoch": 3.7909288339458738,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00036185131841301894,
|
|
"loss": 4.6613,
|
|
"mean_token_accuracy": 0.24047111719846725,
|
|
"num_tokens": 83495919.0,
|
|
"step": 45385
|
|
},
|
|
{
|
|
"entropy": 5.4280924797058105,
|
|
"epoch": 3.7913464751085866,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00036182385495788297,
|
|
"loss": 4.6298,
|
|
"mean_token_accuracy": 0.24113101810216903,
|
|
"num_tokens": 83505415.0,
|
|
"step": 45390
|
|
},
|
|
{
|
|
"entropy": 5.5737292766571045,
|
|
"epoch": 3.7917641162713,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036179638998279086,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.23027083277702332,
|
|
"num_tokens": 83514376.0,
|
|
"step": 45395
|
|
},
|
|
{
|
|
"entropy": 5.514999437332153,
|
|
"epoch": 3.7921817574340126,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036176892348822344,
|
|
"loss": 4.6782,
|
|
"mean_token_accuracy": 0.24026232957839966,
|
|
"num_tokens": 83523388.0,
|
|
"step": 45400
|
|
},
|
|
{
|
|
"entropy": 5.552879714965821,
|
|
"epoch": 3.7925993985967255,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00036174145547466157,
|
|
"loss": 4.7652,
|
|
"mean_token_accuracy": 0.23441405296325685,
|
|
"num_tokens": 83532778.0,
|
|
"step": 45405
|
|
},
|
|
{
|
|
"entropy": 5.448457193374634,
|
|
"epoch": 3.7930170397594387,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003617139859425862,
|
|
"loss": 4.5989,
|
|
"mean_token_accuracy": 0.24301307499408722,
|
|
"num_tokens": 83541397.0,
|
|
"step": 45410
|
|
},
|
|
{
|
|
"entropy": 5.580133724212646,
|
|
"epoch": 3.7934346809221515,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00036168651489247805,
|
|
"loss": 4.8219,
|
|
"mean_token_accuracy": 0.23543778359889983,
|
|
"num_tokens": 83550204.0,
|
|
"step": 45415
|
|
},
|
|
{
|
|
"entropy": 5.577205562591553,
|
|
"epoch": 3.793852322084865,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00036165904232481814,
|
|
"loss": 4.8336,
|
|
"mean_token_accuracy": 0.23047491312026977,
|
|
"num_tokens": 83559974.0,
|
|
"step": 45420
|
|
},
|
|
{
|
|
"entropy": 5.531986427307129,
|
|
"epoch": 3.7942699632475776,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00036163156824008737,
|
|
"loss": 4.639,
|
|
"mean_token_accuracy": 0.25099724531173706,
|
|
"num_tokens": 83568718.0,
|
|
"step": 45425
|
|
},
|
|
{
|
|
"entropy": 5.573459100723267,
|
|
"epoch": 3.7946876044102904,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00036160409263876674,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.23752111047506333,
|
|
"num_tokens": 83577992.0,
|
|
"step": 45430
|
|
},
|
|
{
|
|
"entropy": 5.528012037277222,
|
|
"epoch": 3.7951052455730037,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00036157661552133725,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.2376672625541687,
|
|
"num_tokens": 83587350.0,
|
|
"step": 45435
|
|
},
|
|
{
|
|
"entropy": 5.617683982849121,
|
|
"epoch": 3.795522886735717,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003615491368882799,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.23501401990652085,
|
|
"num_tokens": 83596988.0,
|
|
"step": 45440
|
|
},
|
|
{
|
|
"entropy": 5.5429943084716795,
|
|
"epoch": 3.7959405278984297,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003615216567400756,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.24568211138248444,
|
|
"num_tokens": 83606074.0,
|
|
"step": 45445
|
|
},
|
|
{
|
|
"entropy": 5.521905899047852,
|
|
"epoch": 3.7963581690611425,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036149417507720574,
|
|
"loss": 4.7466,
|
|
"mean_token_accuracy": 0.24055775701999665,
|
|
"num_tokens": 83615680.0,
|
|
"step": 45450
|
|
},
|
|
{
|
|
"entropy": 5.5782829284667965,
|
|
"epoch": 3.796775810223856,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00036146669190015106,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.22721738815307618,
|
|
"num_tokens": 83624983.0,
|
|
"step": 45455
|
|
},
|
|
{
|
|
"entropy": 5.604032802581787,
|
|
"epoch": 3.7971934513865686,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000361439207209393,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.23345448672771454,
|
|
"num_tokens": 83634069.0,
|
|
"step": 45460
|
|
},
|
|
{
|
|
"entropy": 5.581895446777343,
|
|
"epoch": 3.797611092549282,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00036141172100541245,
|
|
"loss": 4.6911,
|
|
"mean_token_accuracy": 0.23822253495454787,
|
|
"num_tokens": 83642717.0,
|
|
"step": 45465
|
|
},
|
|
{
|
|
"entropy": 5.588774156570435,
|
|
"epoch": 3.7980287337119947,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003613842332886908,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.23182161152362823,
|
|
"num_tokens": 83652107.0,
|
|
"step": 45470
|
|
},
|
|
{
|
|
"entropy": 5.500451755523682,
|
|
"epoch": 3.7984463748747075,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036135674405970915,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.2371516168117523,
|
|
"num_tokens": 83660897.0,
|
|
"step": 45475
|
|
},
|
|
{
|
|
"entropy": 5.509371376037597,
|
|
"epoch": 3.7988640160374207,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003613292533189487,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.2361539602279663,
|
|
"num_tokens": 83670374.0,
|
|
"step": 45480
|
|
},
|
|
{
|
|
"entropy": 5.464409971237183,
|
|
"epoch": 3.7992816572001336,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00036130176106689073,
|
|
"loss": 4.5916,
|
|
"mean_token_accuracy": 0.24404052793979644,
|
|
"num_tokens": 83679367.0,
|
|
"step": 45485
|
|
},
|
|
{
|
|
"entropy": 5.493268728256226,
|
|
"epoch": 3.799699298362847,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003612742673040166,
|
|
"loss": 4.6977,
|
|
"mean_token_accuracy": 0.24343386739492417,
|
|
"num_tokens": 83689176.0,
|
|
"step": 45490
|
|
},
|
|
{
|
|
"entropy": 5.5893717288970945,
|
|
"epoch": 3.8001169395255596,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003612467720308076,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.23058274239301682,
|
|
"num_tokens": 83698737.0,
|
|
"step": 45495
|
|
},
|
|
{
|
|
"entropy": 5.532027053833008,
|
|
"epoch": 3.8005345806882724,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003612192752477451,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.24496012181043625,
|
|
"num_tokens": 83708021.0,
|
|
"step": 45500
|
|
},
|
|
{
|
|
"entropy": 5.467962837219238,
|
|
"epoch": 3.8009522218509857,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003611917769553102,
|
|
"loss": 4.6573,
|
|
"mean_token_accuracy": 0.24328152537345887,
|
|
"num_tokens": 83717409.0,
|
|
"step": 45505
|
|
},
|
|
{
|
|
"entropy": 5.497871398925781,
|
|
"epoch": 3.8013698630136985,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036116427715398463,
|
|
"loss": 4.7017,
|
|
"mean_token_accuracy": 0.23378650099039078,
|
|
"num_tokens": 83727228.0,
|
|
"step": 45510
|
|
},
|
|
{
|
|
"entropy": 5.495327997207641,
|
|
"epoch": 3.8017875041764118,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003611367758442497,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.23950005620718,
|
|
"num_tokens": 83735889.0,
|
|
"step": 45515
|
|
},
|
|
{
|
|
"entropy": 5.551213598251342,
|
|
"epoch": 3.8022051453391246,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003611092730265868,
|
|
"loss": 4.7054,
|
|
"mean_token_accuracy": 0.24061038494110107,
|
|
"num_tokens": 83744744.0,
|
|
"step": 45520
|
|
},
|
|
{
|
|
"entropy": 5.4969817161560055,
|
|
"epoch": 3.8026227865018374,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00036108176870147733,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.24941399842500686,
|
|
"num_tokens": 83752747.0,
|
|
"step": 45525
|
|
},
|
|
{
|
|
"entropy": 5.532688236236572,
|
|
"epoch": 3.8030404276645506,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003610542628694031,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.23936179280281067,
|
|
"num_tokens": 83761911.0,
|
|
"step": 45530
|
|
},
|
|
{
|
|
"entropy": 5.551308727264404,
|
|
"epoch": 3.8034580688272634,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00036102675553084527,
|
|
"loss": 4.7394,
|
|
"mean_token_accuracy": 0.23676313906908036,
|
|
"num_tokens": 83771786.0,
|
|
"step": 45535
|
|
},
|
|
{
|
|
"entropy": 5.455118036270141,
|
|
"epoch": 3.8038757099899767,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00036099924668628547,
|
|
"loss": 4.7029,
|
|
"mean_token_accuracy": 0.23381335735321046,
|
|
"num_tokens": 83781342.0,
|
|
"step": 45540
|
|
},
|
|
{
|
|
"entropy": 5.546266222000122,
|
|
"epoch": 3.8042933511526895,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003609717363362054,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.23163641840219498,
|
|
"num_tokens": 83790638.0,
|
|
"step": 45545
|
|
},
|
|
{
|
|
"entropy": 5.472108459472656,
|
|
"epoch": 3.8047109923154023,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00036094422448108664,
|
|
"loss": 4.6716,
|
|
"mean_token_accuracy": 0.24314507395029067,
|
|
"num_tokens": 83800646.0,
|
|
"step": 45550
|
|
},
|
|
{
|
|
"entropy": 5.5390078067779545,
|
|
"epoch": 3.8051286334781156,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003609167111214107,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.2396747425198555,
|
|
"num_tokens": 83809316.0,
|
|
"step": 45555
|
|
},
|
|
{
|
|
"entropy": 5.551476955413818,
|
|
"epoch": 3.805546274640829,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036088919625765946,
|
|
"loss": 4.7102,
|
|
"mean_token_accuracy": 0.23721508383750917,
|
|
"num_tokens": 83818741.0,
|
|
"step": 45560
|
|
},
|
|
{
|
|
"entropy": 5.547499322891236,
|
|
"epoch": 3.8059639158035417,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003608616798903143,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.2353008881211281,
|
|
"num_tokens": 83827837.0,
|
|
"step": 45565
|
|
},
|
|
{
|
|
"entropy": 5.438137102127075,
|
|
"epoch": 3.8063815569662545,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00036083416201985715,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.24021310210227967,
|
|
"num_tokens": 83837405.0,
|
|
"step": 45570
|
|
},
|
|
{
|
|
"entropy": 5.495055723190307,
|
|
"epoch": 3.8067991981289677,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00036080664264676965,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.23516703844070436,
|
|
"num_tokens": 83846919.0,
|
|
"step": 45575
|
|
},
|
|
{
|
|
"entropy": 5.583482503890991,
|
|
"epoch": 3.8072168392916805,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00036077912177153365,
|
|
"loss": 4.7826,
|
|
"mean_token_accuracy": 0.23935043960809707,
|
|
"num_tokens": 83855550.0,
|
|
"step": 45580
|
|
},
|
|
{
|
|
"entropy": 5.579738569259644,
|
|
"epoch": 3.807634480454394,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003607515993946308,
|
|
"loss": 4.6529,
|
|
"mean_token_accuracy": 0.24196667671203614,
|
|
"num_tokens": 83863661.0,
|
|
"step": 45585
|
|
},
|
|
{
|
|
"entropy": 5.5607726097106935,
|
|
"epoch": 3.8080521216171066,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00036072407551654304,
|
|
"loss": 4.6852,
|
|
"mean_token_accuracy": 0.2419355109333992,
|
|
"num_tokens": 83872321.0,
|
|
"step": 45590
|
|
},
|
|
{
|
|
"entropy": 5.538907480239868,
|
|
"epoch": 3.8084697627798194,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003606965501377521,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.2346881240606308,
|
|
"num_tokens": 83882124.0,
|
|
"step": 45595
|
|
},
|
|
{
|
|
"entropy": 5.5919781684875485,
|
|
"epoch": 3.8088874039425327,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003606690232587399,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.23729752898216247,
|
|
"num_tokens": 83891415.0,
|
|
"step": 45600
|
|
},
|
|
{
|
|
"entropy": 5.57724895477295,
|
|
"epoch": 3.8093050451052455,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003606414948799883,
|
|
"loss": 4.7141,
|
|
"mean_token_accuracy": 0.2360953986644745,
|
|
"num_tokens": 83900871.0,
|
|
"step": 45605
|
|
},
|
|
{
|
|
"entropy": 5.525465965270996,
|
|
"epoch": 3.8097226862679587,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00036061396500197934,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.23946485221385955,
|
|
"num_tokens": 83911018.0,
|
|
"step": 45610
|
|
},
|
|
{
|
|
"entropy": 5.580501413345337,
|
|
"epoch": 3.8101403274306715,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00036058643362519476,
|
|
"loss": 4.8489,
|
|
"mean_token_accuracy": 0.22329202592372893,
|
|
"num_tokens": 83920342.0,
|
|
"step": 45615
|
|
},
|
|
{
|
|
"entropy": 5.587893342971801,
|
|
"epoch": 3.8105579685933844,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003605589007501168,
|
|
"loss": 4.8129,
|
|
"mean_token_accuracy": 0.23162037432193755,
|
|
"num_tokens": 83930114.0,
|
|
"step": 45620
|
|
},
|
|
{
|
|
"entropy": 5.550488519668579,
|
|
"epoch": 3.8109756097560976,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00036053136637722715,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.23805056065320968,
|
|
"num_tokens": 83938899.0,
|
|
"step": 45625
|
|
},
|
|
{
|
|
"entropy": 5.4884254932403564,
|
|
"epoch": 3.8113932509188104,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00036050383050700803,
|
|
"loss": 4.605,
|
|
"mean_token_accuracy": 0.24499861150979996,
|
|
"num_tokens": 83948072.0,
|
|
"step": 45630
|
|
},
|
|
{
|
|
"entropy": 5.47142481803894,
|
|
"epoch": 3.8118108920815237,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003604762931399414,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.22743732035160064,
|
|
"num_tokens": 83956230.0,
|
|
"step": 45635
|
|
},
|
|
{
|
|
"entropy": 5.621842575073242,
|
|
"epoch": 3.8122285332442365,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003604487542765094,
|
|
"loss": 4.8625,
|
|
"mean_token_accuracy": 0.22137068808078766,
|
|
"num_tokens": 83965724.0,
|
|
"step": 45640
|
|
},
|
|
{
|
|
"entropy": 5.540132665634156,
|
|
"epoch": 3.8126461744069493,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003604212139171941,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.23678663969039918,
|
|
"num_tokens": 83975538.0,
|
|
"step": 45645
|
|
},
|
|
{
|
|
"entropy": 5.564886283874512,
|
|
"epoch": 3.8130638155696626,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00036039367206247764,
|
|
"loss": 4.7687,
|
|
"mean_token_accuracy": 0.23173719346523286,
|
|
"num_tokens": 83984714.0,
|
|
"step": 45650
|
|
},
|
|
{
|
|
"entropy": 5.569357061386109,
|
|
"epoch": 3.813481456732376,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036036612871284213,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.23402346521615983,
|
|
"num_tokens": 83994450.0,
|
|
"step": 45655
|
|
},
|
|
{
|
|
"entropy": 5.539822912216186,
|
|
"epoch": 3.8138990978950886,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00036033858386876977,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.2380744621157646,
|
|
"num_tokens": 84001941.0,
|
|
"step": 45660
|
|
},
|
|
{
|
|
"entropy": 5.395155715942383,
|
|
"epoch": 3.8143167390578014,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003603110375307428,
|
|
"loss": 4.6096,
|
|
"mean_token_accuracy": 0.24327335208654405,
|
|
"num_tokens": 84010338.0,
|
|
"step": 45665
|
|
},
|
|
{
|
|
"entropy": 5.46311731338501,
|
|
"epoch": 3.8147343802205147,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003602834896992435,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.23866163790225983,
|
|
"num_tokens": 84018980.0,
|
|
"step": 45670
|
|
},
|
|
{
|
|
"entropy": 5.5056328773498535,
|
|
"epoch": 3.8151520213832275,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00036025594037475395,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.2386146754026413,
|
|
"num_tokens": 84028613.0,
|
|
"step": 45675
|
|
},
|
|
{
|
|
"entropy": 5.55119571685791,
|
|
"epoch": 3.8155696625459408,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003602283895577566,
|
|
"loss": 4.6344,
|
|
"mean_token_accuracy": 0.23890257030725479,
|
|
"num_tokens": 84037391.0,
|
|
"step": 45680
|
|
},
|
|
{
|
|
"entropy": 5.4959320545196535,
|
|
"epoch": 3.8159873037086536,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00036020083724873364,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.2392505392432213,
|
|
"num_tokens": 84046473.0,
|
|
"step": 45685
|
|
},
|
|
{
|
|
"entropy": 5.560874509811401,
|
|
"epoch": 3.8164049448713664,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003601732834481676,
|
|
"loss": 4.7749,
|
|
"mean_token_accuracy": 0.23339032828807832,
|
|
"num_tokens": 84055688.0,
|
|
"step": 45690
|
|
},
|
|
{
|
|
"entropy": 5.624143075942993,
|
|
"epoch": 3.8168225860340796,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003601457281565406,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.23527720719575881,
|
|
"num_tokens": 84064894.0,
|
|
"step": 45695
|
|
},
|
|
{
|
|
"entropy": 5.590462064743042,
|
|
"epoch": 3.8172402271967925,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00036011817137433517,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.2364281013607979,
|
|
"num_tokens": 84073634.0,
|
|
"step": 45700
|
|
},
|
|
{
|
|
"entropy": 5.583645629882812,
|
|
"epoch": 3.8176578683595057,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00036009061310203374,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.23391493707895278,
|
|
"num_tokens": 84083777.0,
|
|
"step": 45705
|
|
},
|
|
{
|
|
"entropy": 5.594710922241211,
|
|
"epoch": 3.8180755095222185,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00036006305334011855,
|
|
"loss": 4.7833,
|
|
"mean_token_accuracy": 0.23142954111099243,
|
|
"num_tokens": 84093109.0,
|
|
"step": 45710
|
|
},
|
|
{
|
|
"entropy": 5.491960048675537,
|
|
"epoch": 3.8184931506849313,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003600354920890724,
|
|
"loss": 4.6073,
|
|
"mean_token_accuracy": 0.24270529747009278,
|
|
"num_tokens": 84101534.0,
|
|
"step": 45715
|
|
},
|
|
{
|
|
"entropy": 5.5808494091033936,
|
|
"epoch": 3.8189107918476446,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003600079293493774,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.24024153798818587,
|
|
"num_tokens": 84110644.0,
|
|
"step": 45720
|
|
},
|
|
{
|
|
"entropy": 5.643151760101318,
|
|
"epoch": 3.8193284330103574,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003599803651215165,
|
|
"loss": 4.7756,
|
|
"mean_token_accuracy": 0.23022057563066484,
|
|
"num_tokens": 84120075.0,
|
|
"step": 45725
|
|
},
|
|
{
|
|
"entropy": 5.418589878082275,
|
|
"epoch": 3.8197460741730707,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00035995279940597195,
|
|
"loss": 4.6394,
|
|
"mean_token_accuracy": 0.23924131989479064,
|
|
"num_tokens": 84128989.0,
|
|
"step": 45730
|
|
},
|
|
{
|
|
"entropy": 5.403506278991699,
|
|
"epoch": 3.8201637153357835,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00035992523220322635,
|
|
"loss": 4.5649,
|
|
"mean_token_accuracy": 0.25098954886198044,
|
|
"num_tokens": 84137199.0,
|
|
"step": 45735
|
|
},
|
|
{
|
|
"entropy": 5.560086584091186,
|
|
"epoch": 3.8205813564984963,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00035989766351376224,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.2266460657119751,
|
|
"num_tokens": 84147036.0,
|
|
"step": 45740
|
|
},
|
|
{
|
|
"entropy": 5.491089677810669,
|
|
"epoch": 3.8209989976612095,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003598700933380625,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.24162087738513946,
|
|
"num_tokens": 84156279.0,
|
|
"step": 45745
|
|
},
|
|
{
|
|
"entropy": 5.530419826507568,
|
|
"epoch": 3.8214166388239224,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003598425216766096,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.2367066666483879,
|
|
"num_tokens": 84166338.0,
|
|
"step": 45750
|
|
},
|
|
{
|
|
"entropy": 5.536042499542236,
|
|
"epoch": 3.8218342799866356,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00035981494852988617,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.24108806252479553,
|
|
"num_tokens": 84175863.0,
|
|
"step": 45755
|
|
},
|
|
{
|
|
"entropy": 5.5032915592193605,
|
|
"epoch": 3.8222519211493484,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00035978737389837496,
|
|
"loss": 4.684,
|
|
"mean_token_accuracy": 0.23337249755859374,
|
|
"num_tokens": 84184017.0,
|
|
"step": 45760
|
|
},
|
|
{
|
|
"entropy": 5.5139344215393065,
|
|
"epoch": 3.8226695623120612,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003597597977825588,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.24207680374383928,
|
|
"num_tokens": 84192723.0,
|
|
"step": 45765
|
|
},
|
|
{
|
|
"entropy": 5.5738873958587645,
|
|
"epoch": 3.8230872034747745,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003597322201829202,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.23369597345590593,
|
|
"num_tokens": 84202854.0,
|
|
"step": 45770
|
|
},
|
|
{
|
|
"entropy": 5.524417161941528,
|
|
"epoch": 3.8235048446374877,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035970464109994225,
|
|
"loss": 4.6484,
|
|
"mean_token_accuracy": 0.24150142669677735,
|
|
"num_tokens": 84211791.0,
|
|
"step": 45775
|
|
},
|
|
{
|
|
"entropy": 5.582277774810791,
|
|
"epoch": 3.8239224858002006,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00035967706053410754,
|
|
"loss": 4.8778,
|
|
"mean_token_accuracy": 0.22745362669229507,
|
|
"num_tokens": 84221910.0,
|
|
"step": 45780
|
|
},
|
|
{
|
|
"entropy": 5.534582710266113,
|
|
"epoch": 3.8243401269629134,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00035964947848589904,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.24038849472999574,
|
|
"num_tokens": 84231526.0,
|
|
"step": 45785
|
|
},
|
|
{
|
|
"entropy": 5.579152345657349,
|
|
"epoch": 3.8247577681256266,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003596218949557994,
|
|
"loss": 4.8236,
|
|
"mean_token_accuracy": 0.22370034605264663,
|
|
"num_tokens": 84240566.0,
|
|
"step": 45790
|
|
},
|
|
{
|
|
"entropy": 5.423266315460205,
|
|
"epoch": 3.8251754092883394,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00035959430994429167,
|
|
"loss": 4.577,
|
|
"mean_token_accuracy": 0.24275469928979873,
|
|
"num_tokens": 84248964.0,
|
|
"step": 45795
|
|
},
|
|
{
|
|
"entropy": 5.412312030792236,
|
|
"epoch": 3.8255930504510527,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003595667234518587,
|
|
"loss": 4.5984,
|
|
"mean_token_accuracy": 0.2536677852272987,
|
|
"num_tokens": 84257938.0,
|
|
"step": 45800
|
|
},
|
|
{
|
|
"entropy": 5.434482002258301,
|
|
"epoch": 3.8260106916137655,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00035953913547898353,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.2432529255747795,
|
|
"num_tokens": 84267393.0,
|
|
"step": 45805
|
|
},
|
|
{
|
|
"entropy": 5.541393518447876,
|
|
"epoch": 3.8264283327764783,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00035951154602614896,
|
|
"loss": 4.7511,
|
|
"mean_token_accuracy": 0.2359766960144043,
|
|
"num_tokens": 84275405.0,
|
|
"step": 45810
|
|
},
|
|
{
|
|
"entropy": 5.6021524429321286,
|
|
"epoch": 3.8268459739391916,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000359483955093838,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.2362723469734192,
|
|
"num_tokens": 84284758.0,
|
|
"step": 45815
|
|
},
|
|
{
|
|
"entropy": 5.521134519577027,
|
|
"epoch": 3.8272636151019044,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00035945636268253377,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.232537080347538,
|
|
"num_tokens": 84294437.0,
|
|
"step": 45820
|
|
},
|
|
{
|
|
"entropy": 5.5260735034942625,
|
|
"epoch": 3.8276812562646176,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003594287687927193,
|
|
"loss": 4.7334,
|
|
"mean_token_accuracy": 0.23365607410669326,
|
|
"num_tokens": 84304046.0,
|
|
"step": 45825
|
|
},
|
|
{
|
|
"entropy": 5.52610445022583,
|
|
"epoch": 3.8280988974273304,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00035940117342487756,
|
|
"loss": 4.7616,
|
|
"mean_token_accuracy": 0.23297390192747117,
|
|
"num_tokens": 84313066.0,
|
|
"step": 45830
|
|
},
|
|
{
|
|
"entropy": 5.544469213485717,
|
|
"epoch": 3.8285165385900433,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003593735765794917,
|
|
"loss": 4.8382,
|
|
"mean_token_accuracy": 0.22839849293231965,
|
|
"num_tokens": 84322938.0,
|
|
"step": 45835
|
|
},
|
|
{
|
|
"entropy": 5.543358421325683,
|
|
"epoch": 3.8289341797527565,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00035934597825704477,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.23329276442527772,
|
|
"num_tokens": 84332364.0,
|
|
"step": 45840
|
|
},
|
|
{
|
|
"entropy": 5.495223760604858,
|
|
"epoch": 3.8293518209154693,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00035931837845802,
|
|
"loss": 4.6835,
|
|
"mean_token_accuracy": 0.2483588933944702,
|
|
"num_tokens": 84340980.0,
|
|
"step": 45845
|
|
},
|
|
{
|
|
"entropy": 5.583977127075196,
|
|
"epoch": 3.8297694620781826,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00035929077718290057,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.23068434596061707,
|
|
"num_tokens": 84349886.0,
|
|
"step": 45850
|
|
},
|
|
{
|
|
"entropy": 5.497687578201294,
|
|
"epoch": 3.8301871032408954,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00035926317443216963,
|
|
"loss": 4.7016,
|
|
"mean_token_accuracy": 0.2339853048324585,
|
|
"num_tokens": 84359146.0,
|
|
"step": 45855
|
|
},
|
|
{
|
|
"entropy": 5.504536056518555,
|
|
"epoch": 3.830604744403608,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003592355702063103,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.23620689362287522,
|
|
"num_tokens": 84368537.0,
|
|
"step": 45860
|
|
},
|
|
{
|
|
"entropy": 5.440707492828369,
|
|
"epoch": 3.8310223855663215,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00035920796450580596,
|
|
"loss": 4.5925,
|
|
"mean_token_accuracy": 0.2507565885782242,
|
|
"num_tokens": 84377384.0,
|
|
"step": 45865
|
|
},
|
|
{
|
|
"entropy": 5.533617401123047,
|
|
"epoch": 3.8314400267290343,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00035918035733113984,
|
|
"loss": 4.7537,
|
|
"mean_token_accuracy": 0.23314979672431946,
|
|
"num_tokens": 84386792.0,
|
|
"step": 45870
|
|
},
|
|
{
|
|
"entropy": 5.543411493301392,
|
|
"epoch": 3.8318576678917475,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003591527486827952,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.2342608243227005,
|
|
"num_tokens": 84396601.0,
|
|
"step": 45875
|
|
},
|
|
{
|
|
"entropy": 5.511045122146607,
|
|
"epoch": 3.8322753090544603,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00035912513856125553,
|
|
"loss": 4.6356,
|
|
"mean_token_accuracy": 0.23907188922166825,
|
|
"num_tokens": 84405121.0,
|
|
"step": 45880
|
|
},
|
|
{
|
|
"entropy": 5.376368045806885,
|
|
"epoch": 3.832692950217173,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003590975269670039,
|
|
"loss": 4.5492,
|
|
"mean_token_accuracy": 0.25294901579618456,
|
|
"num_tokens": 84413324.0,
|
|
"step": 45885
|
|
},
|
|
{
|
|
"entropy": 5.500775098800659,
|
|
"epoch": 3.8331105913798864,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003590699139005239,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.23324853628873826,
|
|
"num_tokens": 84422305.0,
|
|
"step": 45890
|
|
},
|
|
{
|
|
"entropy": 5.550690460205078,
|
|
"epoch": 3.8335282325425997,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003590422993622988,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.23012906908988953,
|
|
"num_tokens": 84432794.0,
|
|
"step": 45895
|
|
},
|
|
{
|
|
"entropy": 5.499777507781983,
|
|
"epoch": 3.8339458737053125,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00035901468335281216,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.2308662101626396,
|
|
"num_tokens": 84442018.0,
|
|
"step": 45900
|
|
},
|
|
{
|
|
"entropy": 5.511480188369751,
|
|
"epoch": 3.8343635148680253,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00035898706587254734,
|
|
"loss": 4.7422,
|
|
"mean_token_accuracy": 0.23979561775922775,
|
|
"num_tokens": 84451535.0,
|
|
"step": 45905
|
|
},
|
|
{
|
|
"entropy": 5.592295360565186,
|
|
"epoch": 3.8347811560307385,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00035895944692198787,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.23164437264204024,
|
|
"num_tokens": 84460399.0,
|
|
"step": 45910
|
|
},
|
|
{
|
|
"entropy": 5.5121465682983395,
|
|
"epoch": 3.8351987971934514,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003589318265016172,
|
|
"loss": 4.6499,
|
|
"mean_token_accuracy": 0.24295644015073775,
|
|
"num_tokens": 84469398.0,
|
|
"step": 45915
|
|
},
|
|
{
|
|
"entropy": 5.482578945159912,
|
|
"epoch": 3.8356164383561646,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035890420461191883,
|
|
"loss": 4.6813,
|
|
"mean_token_accuracy": 0.23773396760225296,
|
|
"num_tokens": 84477713.0,
|
|
"step": 45920
|
|
},
|
|
{
|
|
"entropy": 5.532626724243164,
|
|
"epoch": 3.8360340795188774,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035887658125337643,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.23657969385385513,
|
|
"num_tokens": 84486622.0,
|
|
"step": 45925
|
|
},
|
|
{
|
|
"entropy": 5.4695906162261965,
|
|
"epoch": 3.8364517206815902,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003588489564264735,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.24437393993139267,
|
|
"num_tokens": 84495407.0,
|
|
"step": 45930
|
|
},
|
|
{
|
|
"entropy": 5.458735227584839,
|
|
"epoch": 3.8368693618443035,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003588213301316935,
|
|
"loss": 4.6506,
|
|
"mean_token_accuracy": 0.23838618844747544,
|
|
"num_tokens": 84505308.0,
|
|
"step": 45935
|
|
},
|
|
{
|
|
"entropy": 5.503606653213501,
|
|
"epoch": 3.8372870030070163,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003587937023695204,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.23423411846160888,
|
|
"num_tokens": 84514263.0,
|
|
"step": 45940
|
|
},
|
|
{
|
|
"entropy": 5.527830457687378,
|
|
"epoch": 3.8377046441697296,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00035876607314043766,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.24036844223737716,
|
|
"num_tokens": 84522569.0,
|
|
"step": 45945
|
|
},
|
|
{
|
|
"entropy": 5.629659032821655,
|
|
"epoch": 3.8381222853324424,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000358738442444929,
|
|
"loss": 4.7914,
|
|
"mean_token_accuracy": 0.2318315848708153,
|
|
"num_tokens": 84531494.0,
|
|
"step": 45950
|
|
},
|
|
{
|
|
"entropy": 5.530865287780761,
|
|
"epoch": 3.838539926495155,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00035871081028347805,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.233994023501873,
|
|
"num_tokens": 84540533.0,
|
|
"step": 45955
|
|
},
|
|
{
|
|
"entropy": 5.577289628982544,
|
|
"epoch": 3.8389575676578684,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003586831766565686,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.23255635797977448,
|
|
"num_tokens": 84549550.0,
|
|
"step": 45960
|
|
},
|
|
{
|
|
"entropy": 5.550979661941528,
|
|
"epoch": 3.8393752088205813,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003586555415646844,
|
|
"loss": 4.8029,
|
|
"mean_token_accuracy": 0.22932392805814744,
|
|
"num_tokens": 84559053.0,
|
|
"step": 45965
|
|
},
|
|
{
|
|
"entropy": 5.627507257461548,
|
|
"epoch": 3.8397928499832945,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00035862790500830927,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.21882617473602295,
|
|
"num_tokens": 84569759.0,
|
|
"step": 45970
|
|
},
|
|
{
|
|
"entropy": 5.595982885360717,
|
|
"epoch": 3.8402104911460073,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00035860026698792704,
|
|
"loss": 4.7247,
|
|
"mean_token_accuracy": 0.23831735104322432,
|
|
"num_tokens": 84579764.0,
|
|
"step": 45975
|
|
},
|
|
{
|
|
"entropy": 5.499651288986206,
|
|
"epoch": 3.84062813230872,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00035857262750402154,
|
|
"loss": 4.6209,
|
|
"mean_token_accuracy": 0.24149637371301652,
|
|
"num_tokens": 84588619.0,
|
|
"step": 45980
|
|
},
|
|
{
|
|
"entropy": 5.5276813983917235,
|
|
"epoch": 3.8410457734714334,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003585449865570765,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.23307400494813918,
|
|
"num_tokens": 84597836.0,
|
|
"step": 45985
|
|
},
|
|
{
|
|
"entropy": 5.5218523979187015,
|
|
"epoch": 3.841463414634146,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000358517344147576,
|
|
"loss": 4.7083,
|
|
"mean_token_accuracy": 0.24585671424865724,
|
|
"num_tokens": 84606152.0,
|
|
"step": 45990
|
|
},
|
|
{
|
|
"entropy": 5.695101737976074,
|
|
"epoch": 3.8418810557968595,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035848970027600377,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.22801008820533752,
|
|
"num_tokens": 84615471.0,
|
|
"step": 45995
|
|
},
|
|
{
|
|
"entropy": 5.526871919631958,
|
|
"epoch": 3.8422986969595723,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003584620549428439,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.24041083008050917,
|
|
"num_tokens": 84624625.0,
|
|
"step": 46000
|
|
},
|
|
{
|
|
"entropy": 5.463473129272461,
|
|
"epoch": 3.842716338122285,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003584344081485802,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.23728069216012954,
|
|
"num_tokens": 84633828.0,
|
|
"step": 46005
|
|
},
|
|
{
|
|
"entropy": 5.521689081192017,
|
|
"epoch": 3.8431339792849983,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0003584067598936969,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.23964605033397673,
|
|
"num_tokens": 84644081.0,
|
|
"step": 46010
|
|
},
|
|
{
|
|
"entropy": 5.449009418487549,
|
|
"epoch": 3.8435516204477116,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003583791101786777,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.242995548248291,
|
|
"num_tokens": 84653148.0,
|
|
"step": 46015
|
|
},
|
|
{
|
|
"entropy": 5.590973997116089,
|
|
"epoch": 3.8439692616104244,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00035835145900400703,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.23959741592407227,
|
|
"num_tokens": 84661660.0,
|
|
"step": 46020
|
|
},
|
|
{
|
|
"entropy": 5.564209938049316,
|
|
"epoch": 3.844386902773137,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00035832380637016846,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.23155531138181687,
|
|
"num_tokens": 84671271.0,
|
|
"step": 46025
|
|
},
|
|
{
|
|
"entropy": 5.589544439315796,
|
|
"epoch": 3.8448045439358505,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00035829615227764663,
|
|
"loss": 4.7481,
|
|
"mean_token_accuracy": 0.2343520000576973,
|
|
"num_tokens": 84680609.0,
|
|
"step": 46030
|
|
},
|
|
{
|
|
"entropy": 5.600975561141968,
|
|
"epoch": 3.8452221850985633,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003582684967269253,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.23138566464185714,
|
|
"num_tokens": 84690303.0,
|
|
"step": 46035
|
|
},
|
|
{
|
|
"entropy": 5.618086862564087,
|
|
"epoch": 3.8456398262612765,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035824083971848866,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.2317299112677574,
|
|
"num_tokens": 84699640.0,
|
|
"step": 46040
|
|
},
|
|
{
|
|
"entropy": 5.4904303550720215,
|
|
"epoch": 3.8460574674239894,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00035821318125282093,
|
|
"loss": 4.6757,
|
|
"mean_token_accuracy": 0.2372489869594574,
|
|
"num_tokens": 84708942.0,
|
|
"step": 46045
|
|
},
|
|
{
|
|
"entropy": 5.411724805831909,
|
|
"epoch": 3.846475108586702,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003581855213304063,
|
|
"loss": 4.6314,
|
|
"mean_token_accuracy": 0.24225908666849136,
|
|
"num_tokens": 84717978.0,
|
|
"step": 46050
|
|
},
|
|
{
|
|
"entropy": 5.565785217285156,
|
|
"epoch": 3.8468927497494154,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003581578599517291,
|
|
"loss": 4.7221,
|
|
"mean_token_accuracy": 0.23386341482400894,
|
|
"num_tokens": 84727332.0,
|
|
"step": 46055
|
|
},
|
|
{
|
|
"entropy": 5.626423406600952,
|
|
"epoch": 3.8473103909121282,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003581301971172733,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.22768125534057618,
|
|
"num_tokens": 84736968.0,
|
|
"step": 46060
|
|
},
|
|
{
|
|
"entropy": 5.586788988113403,
|
|
"epoch": 3.8477280320748415,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035810253282752343,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.2270767644047737,
|
|
"num_tokens": 84745675.0,
|
|
"step": 46065
|
|
},
|
|
{
|
|
"entropy": 5.612220525741577,
|
|
"epoch": 3.8481456732375543,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00035807486708296364,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.23044155687093734,
|
|
"num_tokens": 84755829.0,
|
|
"step": 46070
|
|
},
|
|
{
|
|
"entropy": 5.661207628250122,
|
|
"epoch": 3.848563314400267,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003580471998840784,
|
|
"loss": 4.7986,
|
|
"mean_token_accuracy": 0.23044467270374297,
|
|
"num_tokens": 84765087.0,
|
|
"step": 46075
|
|
},
|
|
{
|
|
"entropy": 5.589801168441772,
|
|
"epoch": 3.8489809555629804,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003580195312313518,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.2384961098432541,
|
|
"num_tokens": 84773759.0,
|
|
"step": 46080
|
|
},
|
|
{
|
|
"entropy": 5.4695028305053714,
|
|
"epoch": 3.849398596725693,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003579918611252685,
|
|
"loss": 4.6406,
|
|
"mean_token_accuracy": 0.24317134022712708,
|
|
"num_tokens": 84782742.0,
|
|
"step": 46085
|
|
},
|
|
{
|
|
"entropy": 5.542109441757202,
|
|
"epoch": 3.8498162378884064,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003579641895663128,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.2397627890110016,
|
|
"num_tokens": 84792435.0,
|
|
"step": 46090
|
|
},
|
|
{
|
|
"entropy": 5.498846530914307,
|
|
"epoch": 3.8502338790511192,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000357936516554969,
|
|
"loss": 4.6519,
|
|
"mean_token_accuracy": 0.2414947122335434,
|
|
"num_tokens": 84801447.0,
|
|
"step": 46095
|
|
},
|
|
{
|
|
"entropy": 5.514047002792358,
|
|
"epoch": 3.850651520213832,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003579088420917217,
|
|
"loss": 4.5875,
|
|
"mean_token_accuracy": 0.254986834526062,
|
|
"num_tokens": 84809631.0,
|
|
"step": 46100
|
|
},
|
|
{
|
|
"entropy": 5.426632881164551,
|
|
"epoch": 3.8510691613765453,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035788116617705535,
|
|
"loss": 4.6069,
|
|
"mean_token_accuracy": 0.24339876174926758,
|
|
"num_tokens": 84818559.0,
|
|
"step": 46105
|
|
},
|
|
{
|
|
"entropy": 5.522418451309204,
|
|
"epoch": 3.851486802539258,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035785348881145436,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.23275549113750457,
|
|
"num_tokens": 84829163.0,
|
|
"step": 46110
|
|
},
|
|
{
|
|
"entropy": 5.50182843208313,
|
|
"epoch": 3.8519044437019714,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003578258099954033,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.24323985427618028,
|
|
"num_tokens": 84838508.0,
|
|
"step": 46115
|
|
},
|
|
{
|
|
"entropy": 5.550084590911865,
|
|
"epoch": 3.852322084864684,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003577981297293868,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.2384474277496338,
|
|
"num_tokens": 84847826.0,
|
|
"step": 46120
|
|
},
|
|
{
|
|
"entropy": 5.486474084854126,
|
|
"epoch": 3.852739726027397,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00035777044801388937,
|
|
"loss": 4.6444,
|
|
"mean_token_accuracy": 0.2405282273888588,
|
|
"num_tokens": 84857457.0,
|
|
"step": 46125
|
|
},
|
|
{
|
|
"entropy": 5.515016794204712,
|
|
"epoch": 3.8531573671901103,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035774276484939555,
|
|
"loss": 4.7739,
|
|
"mean_token_accuracy": 0.22980808317661286,
|
|
"num_tokens": 84866871.0,
|
|
"step": 46130
|
|
},
|
|
{
|
|
"entropy": 5.530343246459961,
|
|
"epoch": 3.8535750083528235,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003577150802363901,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.22988587170839309,
|
|
"num_tokens": 84876054.0,
|
|
"step": 46135
|
|
},
|
|
{
|
|
"entropy": 5.6251606941223145,
|
|
"epoch": 3.8539926495155363,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00035768739417535764,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.23188173472881318,
|
|
"num_tokens": 84885307.0,
|
|
"step": 46140
|
|
},
|
|
{
|
|
"entropy": 5.623350143432617,
|
|
"epoch": 3.854410290678249,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003576597066667828,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.229319329559803,
|
|
"num_tokens": 84895473.0,
|
|
"step": 46145
|
|
},
|
|
{
|
|
"entropy": 5.5394610404968265,
|
|
"epoch": 3.8548279318409624,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035763201771115024,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.23148610889911653,
|
|
"num_tokens": 84904703.0,
|
|
"step": 46150
|
|
},
|
|
{
|
|
"entropy": 5.497081851959228,
|
|
"epoch": 3.855245573003675,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003576043273089448,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.23575856387615204,
|
|
"num_tokens": 84913962.0,
|
|
"step": 46155
|
|
},
|
|
{
|
|
"entropy": 5.616424179077148,
|
|
"epoch": 3.8556632141663885,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003575766354606511,
|
|
"loss": 4.8648,
|
|
"mean_token_accuracy": 0.22525113672018052,
|
|
"num_tokens": 84923672.0,
|
|
"step": 46160
|
|
},
|
|
{
|
|
"entropy": 5.505469179153442,
|
|
"epoch": 3.8560808553291013,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000357548942166754,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.24633390307426453,
|
|
"num_tokens": 84931694.0,
|
|
"step": 46165
|
|
},
|
|
{
|
|
"entropy": 5.496804857254029,
|
|
"epoch": 3.856498496491814,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003575212474277383,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.25001520067453387,
|
|
"num_tokens": 84941182.0,
|
|
"step": 46170
|
|
},
|
|
{
|
|
"entropy": 5.558137083053589,
|
|
"epoch": 3.8569161376545273,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000357493551244089,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.2331108570098877,
|
|
"num_tokens": 84950929.0,
|
|
"step": 46175
|
|
},
|
|
{
|
|
"entropy": 5.582821226119995,
|
|
"epoch": 3.85733377881724,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003574658536162906,
|
|
"loss": 4.7618,
|
|
"mean_token_accuracy": 0.23730627149343492,
|
|
"num_tokens": 84961275.0,
|
|
"step": 46180
|
|
},
|
|
{
|
|
"entropy": 5.5328452587127686,
|
|
"epoch": 3.8577514199799534,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035743815454482834,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.23137227892875672,
|
|
"num_tokens": 84970843.0,
|
|
"step": 46185
|
|
},
|
|
{
|
|
"entropy": 5.4634325981140135,
|
|
"epoch": 3.8581690611426662,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003574104540301868,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.23588598370552064,
|
|
"num_tokens": 84979864.0,
|
|
"step": 46190
|
|
},
|
|
{
|
|
"entropy": 5.538519287109375,
|
|
"epoch": 3.858586702305379,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00035738275207285115,
|
|
"loss": 4.674,
|
|
"mean_token_accuracy": 0.24031104892492294,
|
|
"num_tokens": 84989343.0,
|
|
"step": 46195
|
|
},
|
|
{
|
|
"entropy": 5.590385675430298,
|
|
"epoch": 3.8590043434680923,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003573550486733063,
|
|
"loss": 4.7971,
|
|
"mean_token_accuracy": 0.2313387557864189,
|
|
"num_tokens": 84998467.0,
|
|
"step": 46200
|
|
},
|
|
{
|
|
"entropy": 5.516520547866821,
|
|
"epoch": 3.859421984630805,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000357327343832037,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.23501773774623871,
|
|
"num_tokens": 85008011.0,
|
|
"step": 46205
|
|
},
|
|
{
|
|
"entropy": 5.49738507270813,
|
|
"epoch": 3.8598396257935184,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003572996375495286,
|
|
"loss": 4.5831,
|
|
"mean_token_accuracy": 0.24785620272159575,
|
|
"num_tokens": 85016810.0,
|
|
"step": 46210
|
|
},
|
|
{
|
|
"entropy": 5.454894876480102,
|
|
"epoch": 3.860257266956231,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00035727192982626594,
|
|
"loss": 4.6218,
|
|
"mean_token_accuracy": 0.24892512410879136,
|
|
"num_tokens": 85025467.0,
|
|
"step": 46215
|
|
},
|
|
{
|
|
"entropy": 5.414939069747925,
|
|
"epoch": 3.860674908118944,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003572442206627341,
|
|
"loss": 4.5622,
|
|
"mean_token_accuracy": 0.24293409883975983,
|
|
"num_tokens": 85034065.0,
|
|
"step": 46220
|
|
},
|
|
{
|
|
"entropy": 5.503379774093628,
|
|
"epoch": 3.8610925492816572,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035721651005941825,
|
|
"loss": 4.7173,
|
|
"mean_token_accuracy": 0.2421512708067894,
|
|
"num_tokens": 85043045.0,
|
|
"step": 46225
|
|
},
|
|
{
|
|
"entropy": 5.463645887374878,
|
|
"epoch": 3.86151019044437,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035718879801680345,
|
|
"loss": 4.6144,
|
|
"mean_token_accuracy": 0.24544162750244142,
|
|
"num_tokens": 85051263.0,
|
|
"step": 46230
|
|
},
|
|
{
|
|
"entropy": 5.5578173160552975,
|
|
"epoch": 3.8619278316070833,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00035716108453537473,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.24000659883022307,
|
|
"num_tokens": 85059955.0,
|
|
"step": 46235
|
|
},
|
|
{
|
|
"entropy": 5.473360586166382,
|
|
"epoch": 3.862345472769796,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00035713336961561734,
|
|
"loss": 4.6822,
|
|
"mean_token_accuracy": 0.2492339551448822,
|
|
"num_tokens": 85069306.0,
|
|
"step": 46240
|
|
},
|
|
{
|
|
"entropy": 5.579052925109863,
|
|
"epoch": 3.862763113932509,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003571056532580164,
|
|
"loss": 4.8405,
|
|
"mean_token_accuracy": 0.22681177854537965,
|
|
"num_tokens": 85079626.0,
|
|
"step": 46245
|
|
},
|
|
{
|
|
"entropy": 5.624509048461914,
|
|
"epoch": 3.863180755095222,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003570779354630573,
|
|
"loss": 4.7628,
|
|
"mean_token_accuracy": 0.22994986027479172,
|
|
"num_tokens": 85088804.0,
|
|
"step": 46250
|
|
},
|
|
{
|
|
"entropy": 5.638586091995239,
|
|
"epoch": 3.8635983962579354,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00035705021623122496,
|
|
"loss": 4.8119,
|
|
"mean_token_accuracy": 0.22709068208932875,
|
|
"num_tokens": 85098399.0,
|
|
"step": 46255
|
|
},
|
|
{
|
|
"entropy": 5.5747076034545895,
|
|
"epoch": 3.8640160374206483,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000357022495563005,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.23369486778974533,
|
|
"num_tokens": 85108332.0,
|
|
"step": 46260
|
|
},
|
|
{
|
|
"entropy": 5.606834602355957,
|
|
"epoch": 3.864433678583361,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003569947734588824,
|
|
"loss": 4.757,
|
|
"mean_token_accuracy": 0.2351796180009842,
|
|
"num_tokens": 85117271.0,
|
|
"step": 46265
|
|
},
|
|
{
|
|
"entropy": 5.598040342330933,
|
|
"epoch": 3.8648513197460743,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003569670499193427,
|
|
"loss": 4.7652,
|
|
"mean_token_accuracy": 0.22677855789661408,
|
|
"num_tokens": 85127065.0,
|
|
"step": 46270
|
|
},
|
|
{
|
|
"entropy": 5.659729671478272,
|
|
"epoch": 3.865268960908787,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000356939324944871,
|
|
"loss": 4.7739,
|
|
"mean_token_accuracy": 0.23374402821063994,
|
|
"num_tokens": 85136807.0,
|
|
"step": 46275
|
|
},
|
|
{
|
|
"entropy": 5.628087854385376,
|
|
"epoch": 3.8656866020715004,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003569115985359529,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.23118350207805632,
|
|
"num_tokens": 85146583.0,
|
|
"step": 46280
|
|
},
|
|
{
|
|
"entropy": 5.53328948020935,
|
|
"epoch": 3.866104243234213,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003568838706930736,
|
|
"loss": 4.7004,
|
|
"mean_token_accuracy": 0.24024278819561004,
|
|
"num_tokens": 85156473.0,
|
|
"step": 46285
|
|
},
|
|
{
|
|
"entropy": 5.524112701416016,
|
|
"epoch": 3.866521884396926,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003568561414167186,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.2296355053782463,
|
|
"num_tokens": 85166010.0,
|
|
"step": 46290
|
|
},
|
|
{
|
|
"entropy": 5.639388227462769,
|
|
"epoch": 3.8669395255596393,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003568284107073734,
|
|
"loss": 4.8698,
|
|
"mean_token_accuracy": 0.22480330765247344,
|
|
"num_tokens": 85175804.0,
|
|
"step": 46295
|
|
},
|
|
{
|
|
"entropy": 5.61294469833374,
|
|
"epoch": 3.867357166722352,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003568006785655232,
|
|
"loss": 4.7264,
|
|
"mean_token_accuracy": 0.2339075744152069,
|
|
"num_tokens": 85184324.0,
|
|
"step": 46300
|
|
},
|
|
{
|
|
"entropy": 5.533587455749512,
|
|
"epoch": 3.8677748078850653,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0003567729449916538,
|
|
"loss": 4.7537,
|
|
"mean_token_accuracy": 0.2342140331864357,
|
|
"num_tokens": 85192776.0,
|
|
"step": 46305
|
|
},
|
|
{
|
|
"entropy": 5.5374959945678714,
|
|
"epoch": 3.868192449047778,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003567452099862506,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.2373979240655899,
|
|
"num_tokens": 85201219.0,
|
|
"step": 46310
|
|
},
|
|
{
|
|
"entropy": 5.6021771907806395,
|
|
"epoch": 3.868610090210491,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003567174735497989,
|
|
"loss": 4.8259,
|
|
"mean_token_accuracy": 0.22673544883728028,
|
|
"num_tokens": 85210867.0,
|
|
"step": 46315
|
|
},
|
|
{
|
|
"entropy": 5.560267782211303,
|
|
"epoch": 3.869027731373204,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003566897356827847,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.23853760510683059,
|
|
"num_tokens": 85219612.0,
|
|
"step": 46320
|
|
},
|
|
{
|
|
"entropy": 5.462199735641479,
|
|
"epoch": 3.869445372535917,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00035666199638569317,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.2471551552414894,
|
|
"num_tokens": 85228200.0,
|
|
"step": 46325
|
|
},
|
|
{
|
|
"entropy": 5.537395668029785,
|
|
"epoch": 3.8698630136986303,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00035663425565901017,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.23644858002662658,
|
|
"num_tokens": 85237265.0,
|
|
"step": 46330
|
|
},
|
|
{
|
|
"entropy": 5.525734233856201,
|
|
"epoch": 3.870280654861343,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00035660651350322126,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.23675299435853958,
|
|
"num_tokens": 85245986.0,
|
|
"step": 46335
|
|
},
|
|
{
|
|
"entropy": 5.578542947769165,
|
|
"epoch": 3.870698296024056,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00035657876991881216,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.23321041017770766,
|
|
"num_tokens": 85255629.0,
|
|
"step": 46340
|
|
},
|
|
{
|
|
"entropy": 5.5704676628112795,
|
|
"epoch": 3.871115937186769,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003565510249062684,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.23384522944688796,
|
|
"num_tokens": 85264908.0,
|
|
"step": 46345
|
|
},
|
|
{
|
|
"entropy": 5.479027271270752,
|
|
"epoch": 3.871533578349482,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003565232784660758,
|
|
"loss": 4.6209,
|
|
"mean_token_accuracy": 0.23988097459077834,
|
|
"num_tokens": 85274166.0,
|
|
"step": 46350
|
|
},
|
|
{
|
|
"entropy": 5.542986917495727,
|
|
"epoch": 3.8719512195121952,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003564955305987201,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.23494426906108856,
|
|
"num_tokens": 85284381.0,
|
|
"step": 46355
|
|
},
|
|
{
|
|
"entropy": 5.528064823150634,
|
|
"epoch": 3.872368860674908,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003564677813046871,
|
|
"loss": 4.8128,
|
|
"mean_token_accuracy": 0.22938136309385299,
|
|
"num_tokens": 85293940.0,
|
|
"step": 46360
|
|
},
|
|
{
|
|
"entropy": 5.5340904712677,
|
|
"epoch": 3.872786501837621,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035644003058446245,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.23806452453136445,
|
|
"num_tokens": 85302460.0,
|
|
"step": 46365
|
|
},
|
|
{
|
|
"entropy": 5.483931207656861,
|
|
"epoch": 3.873204143000334,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000356412278438532,
|
|
"loss": 4.6664,
|
|
"mean_token_accuracy": 0.24092508405447005,
|
|
"num_tokens": 85311928.0,
|
|
"step": 46370
|
|
},
|
|
{
|
|
"entropy": 5.525841283798218,
|
|
"epoch": 3.8736217841630474,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003563845248673817,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.23354773074388505,
|
|
"num_tokens": 85321449.0,
|
|
"step": 46375
|
|
},
|
|
{
|
|
"entropy": 5.5978004932403564,
|
|
"epoch": 3.87403942532576,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0003563567698714973,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.2191024273633957,
|
|
"num_tokens": 85330975.0,
|
|
"step": 46380
|
|
},
|
|
{
|
|
"entropy": 5.571883869171143,
|
|
"epoch": 3.874457066488473,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003563290134513647,
|
|
"loss": 4.7526,
|
|
"mean_token_accuracy": 0.23664903044700622,
|
|
"num_tokens": 85340138.0,
|
|
"step": 46385
|
|
},
|
|
{
|
|
"entropy": 5.569075059890747,
|
|
"epoch": 3.8748747076511862,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003563012556074698,
|
|
"loss": 4.7703,
|
|
"mean_token_accuracy": 0.23576623499393462,
|
|
"num_tokens": 85349455.0,
|
|
"step": 46390
|
|
},
|
|
{
|
|
"entropy": 5.492731142044067,
|
|
"epoch": 3.875292348813899,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035627349634029866,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.24925188720226288,
|
|
"num_tokens": 85359426.0,
|
|
"step": 46395
|
|
},
|
|
{
|
|
"entropy": 5.542258024215698,
|
|
"epoch": 3.8757099899766123,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000356245735650337,
|
|
"loss": 4.726,
|
|
"mean_token_accuracy": 0.23218564689159393,
|
|
"num_tokens": 85368521.0,
|
|
"step": 46400
|
|
},
|
|
{
|
|
"entropy": 5.5660080909729,
|
|
"epoch": 3.876127631139325,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035621797353807105,
|
|
"loss": 4.7549,
|
|
"mean_token_accuracy": 0.22744911164045334,
|
|
"num_tokens": 85378018.0,
|
|
"step": 46405
|
|
},
|
|
{
|
|
"entropy": 5.55253643989563,
|
|
"epoch": 3.876545272302038,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00035619021000398674,
|
|
"loss": 4.7649,
|
|
"mean_token_accuracy": 0.23318575620651244,
|
|
"num_tokens": 85386982.0,
|
|
"step": 46410
|
|
},
|
|
{
|
|
"entropy": 5.583052015304565,
|
|
"epoch": 3.876962913464751,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00035616244504857,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.23087771236896515,
|
|
"num_tokens": 85397266.0,
|
|
"step": 46415
|
|
},
|
|
{
|
|
"entropy": 5.578813600540161,
|
|
"epoch": 3.877380554627464,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00035613467867230697,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.23659515231847764,
|
|
"num_tokens": 85406012.0,
|
|
"step": 46420
|
|
},
|
|
{
|
|
"entropy": 5.446198320388794,
|
|
"epoch": 3.8777981957901773,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003561069108756837,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.23588904440402986,
|
|
"num_tokens": 85415445.0,
|
|
"step": 46425
|
|
},
|
|
{
|
|
"entropy": 5.458747339248657,
|
|
"epoch": 3.87821583695289,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003560791416591864,
|
|
"loss": 4.7035,
|
|
"mean_token_accuracy": 0.2367113247513771,
|
|
"num_tokens": 85423897.0,
|
|
"step": 46430
|
|
},
|
|
{
|
|
"entropy": 5.3675642013549805,
|
|
"epoch": 3.878633478115603,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035605137102330103,
|
|
"loss": 4.551,
|
|
"mean_token_accuracy": 0.24900902807712555,
|
|
"num_tokens": 85433349.0,
|
|
"step": 46435
|
|
},
|
|
{
|
|
"entropy": 5.498460721969605,
|
|
"epoch": 3.879051119278316,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000356023598968514,
|
|
"loss": 4.6402,
|
|
"mean_token_accuracy": 0.2457049772143364,
|
|
"num_tokens": 85442035.0,
|
|
"step": 46440
|
|
},
|
|
{
|
|
"entropy": 5.584218502044678,
|
|
"epoch": 3.879468760441029,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00035599582549531117,
|
|
"loss": 4.8437,
|
|
"mean_token_accuracy": 0.22581852078437806,
|
|
"num_tokens": 85451742.0,
|
|
"step": 46445
|
|
},
|
|
{
|
|
"entropy": 5.595189094543457,
|
|
"epoch": 3.879886401603742,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00035596805060417907,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.23376432806253433,
|
|
"num_tokens": 85461270.0,
|
|
"step": 46450
|
|
},
|
|
{
|
|
"entropy": 5.486299705505371,
|
|
"epoch": 3.880304042766455,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00035594027429560366,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.23865359872579575,
|
|
"num_tokens": 85469857.0,
|
|
"step": 46455
|
|
},
|
|
{
|
|
"entropy": 5.49990758895874,
|
|
"epoch": 3.880721683929168,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003559124965700714,
|
|
"loss": 4.6777,
|
|
"mean_token_accuracy": 0.23707105368375778,
|
|
"num_tokens": 85478304.0,
|
|
"step": 46460
|
|
},
|
|
{
|
|
"entropy": 5.44964566230774,
|
|
"epoch": 3.881139325091881,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003558847174280685,
|
|
"loss": 4.6063,
|
|
"mean_token_accuracy": 0.23986269682645797,
|
|
"num_tokens": 85486812.0,
|
|
"step": 46465
|
|
},
|
|
{
|
|
"entropy": 5.589939928054809,
|
|
"epoch": 3.881556966254594,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00035585693687008123,
|
|
"loss": 4.7724,
|
|
"mean_token_accuracy": 0.23374752849340438,
|
|
"num_tokens": 85495940.0,
|
|
"step": 46470
|
|
},
|
|
{
|
|
"entropy": 5.603474760055542,
|
|
"epoch": 3.881974607417307,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003558291548965959,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.23667549192905427,
|
|
"num_tokens": 85505083.0,
|
|
"step": 46475
|
|
},
|
|
{
|
|
"entropy": 5.595305871963501,
|
|
"epoch": 3.88239224858002,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000355801371508099,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.22327050119638442,
|
|
"num_tokens": 85514288.0,
|
|
"step": 46480
|
|
},
|
|
{
|
|
"entropy": 5.505272960662841,
|
|
"epoch": 3.882809889742733,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003557735867050768,
|
|
"loss": 4.6902,
|
|
"mean_token_accuracy": 0.23596445769071578,
|
|
"num_tokens": 85522441.0,
|
|
"step": 46485
|
|
},
|
|
{
|
|
"entropy": 5.508129644393921,
|
|
"epoch": 3.883227530905446,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003557458004880158,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.23866236507892608,
|
|
"num_tokens": 85533079.0,
|
|
"step": 46490
|
|
},
|
|
{
|
|
"entropy": 5.559938716888428,
|
|
"epoch": 3.8836451720681593,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0003557180128574023,
|
|
"loss": 4.7686,
|
|
"mean_token_accuracy": 0.23331046402454375,
|
|
"num_tokens": 85542631.0,
|
|
"step": 46495
|
|
},
|
|
{
|
|
"entropy": 5.581385135650635,
|
|
"epoch": 3.884062813230872,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003556902238137228,
|
|
"loss": 4.7018,
|
|
"mean_token_accuracy": 0.23695667386054992,
|
|
"num_tokens": 85551328.0,
|
|
"step": 46500
|
|
},
|
|
{
|
|
"entropy": 5.572434377670288,
|
|
"epoch": 3.884480454393585,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00035566243335746387,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.23974156230688096,
|
|
"num_tokens": 85560610.0,
|
|
"step": 46505
|
|
},
|
|
{
|
|
"entropy": 5.583793687820434,
|
|
"epoch": 3.884898095556298,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00035563464148911185,
|
|
"loss": 4.7902,
|
|
"mean_token_accuracy": 0.23212921023368835,
|
|
"num_tokens": 85570688.0,
|
|
"step": 46510
|
|
},
|
|
{
|
|
"entropy": 5.519680833816528,
|
|
"epoch": 3.885315736719011,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003556068482091535,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.23666683137416838,
|
|
"num_tokens": 85579621.0,
|
|
"step": 46515
|
|
},
|
|
{
|
|
"entropy": 5.542465543746948,
|
|
"epoch": 3.8857333778817242,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003555790535180751,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.23835369795560837,
|
|
"num_tokens": 85587917.0,
|
|
"step": 46520
|
|
},
|
|
{
|
|
"entropy": 5.568226718902588,
|
|
"epoch": 3.886151019044437,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003555512574163635,
|
|
"loss": 4.7025,
|
|
"mean_token_accuracy": 0.2327412560582161,
|
|
"num_tokens": 85597301.0,
|
|
"step": 46525
|
|
},
|
|
{
|
|
"entropy": 5.523008012771607,
|
|
"epoch": 3.88656866020715,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003555234599045051,
|
|
"loss": 4.6905,
|
|
"mean_token_accuracy": 0.2368847668170929,
|
|
"num_tokens": 85607307.0,
|
|
"step": 46530
|
|
},
|
|
{
|
|
"entropy": 5.5933184146881105,
|
|
"epoch": 3.886986301369863,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003554956609829867,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.23105148375034332,
|
|
"num_tokens": 85616774.0,
|
|
"step": 46535
|
|
},
|
|
{
|
|
"entropy": 5.545119190216065,
|
|
"epoch": 3.887403942532576,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003554678606522948,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.2397838294506073,
|
|
"num_tokens": 85626160.0,
|
|
"step": 46540
|
|
},
|
|
{
|
|
"entropy": 5.416906309127808,
|
|
"epoch": 3.887821583695289,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00035544005891291616,
|
|
"loss": 4.6185,
|
|
"mean_token_accuracy": 0.24745352268218995,
|
|
"num_tokens": 85634802.0,
|
|
"step": 46545
|
|
},
|
|
{
|
|
"entropy": 5.485342121124267,
|
|
"epoch": 3.888239224858002,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00035541225576533745,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.2373752161860466,
|
|
"num_tokens": 85644797.0,
|
|
"step": 46550
|
|
},
|
|
{
|
|
"entropy": 5.508967638015747,
|
|
"epoch": 3.888656866020715,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00035538445121004544,
|
|
"loss": 4.6039,
|
|
"mean_token_accuracy": 0.24503855109214784,
|
|
"num_tokens": 85653394.0,
|
|
"step": 46555
|
|
},
|
|
{
|
|
"entropy": 5.492342281341553,
|
|
"epoch": 3.889074507183428,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00035535664524752683,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.23990513533353805,
|
|
"num_tokens": 85662066.0,
|
|
"step": 46560
|
|
},
|
|
{
|
|
"entropy": 5.491177034378052,
|
|
"epoch": 3.889492148346141,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00035532883787826836,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.23761370480060579,
|
|
"num_tokens": 85670832.0,
|
|
"step": 46565
|
|
},
|
|
{
|
|
"entropy": 5.62455382347107,
|
|
"epoch": 3.889909789508854,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000355301029102757,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.23785263448953628,
|
|
"num_tokens": 85680561.0,
|
|
"step": 46570
|
|
},
|
|
{
|
|
"entropy": 5.578082180023193,
|
|
"epoch": 3.890327430671567,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003552732189214794,
|
|
"loss": 4.7097,
|
|
"mean_token_accuracy": 0.23575564324855805,
|
|
"num_tokens": 85688999.0,
|
|
"step": 46575
|
|
},
|
|
{
|
|
"entropy": 5.592158079147339,
|
|
"epoch": 3.8907450718342798,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003552454073349225,
|
|
"loss": 4.7785,
|
|
"mean_token_accuracy": 0.23242584615945816,
|
|
"num_tokens": 85698689.0,
|
|
"step": 46580
|
|
},
|
|
{
|
|
"entropy": 5.508882331848144,
|
|
"epoch": 3.891162712996993,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003552175943435731,
|
|
"loss": 4.7247,
|
|
"mean_token_accuracy": 0.23702205419540406,
|
|
"num_tokens": 85708146.0,
|
|
"step": 46585
|
|
},
|
|
{
|
|
"entropy": 5.501959753036499,
|
|
"epoch": 3.891580354159706,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003551897799479182,
|
|
"loss": 4.6212,
|
|
"mean_token_accuracy": 0.24134600758552552,
|
|
"num_tokens": 85716775.0,
|
|
"step": 46590
|
|
},
|
|
{
|
|
"entropy": 5.516603612899781,
|
|
"epoch": 3.891997995322419,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003551619641484448,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.23578357249498366,
|
|
"num_tokens": 85726909.0,
|
|
"step": 46595
|
|
},
|
|
{
|
|
"entropy": 5.54495267868042,
|
|
"epoch": 3.892415636485132,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003551341469456395,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.23428293764591218,
|
|
"num_tokens": 85735810.0,
|
|
"step": 46600
|
|
},
|
|
{
|
|
"entropy": 5.57296051979065,
|
|
"epoch": 3.8928332776478447,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003551063283399897,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.23440107703208923,
|
|
"num_tokens": 85744980.0,
|
|
"step": 46605
|
|
},
|
|
{
|
|
"entropy": 5.573150587081909,
|
|
"epoch": 3.893250918810558,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000355078508331982,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.2354225382208824,
|
|
"num_tokens": 85754314.0,
|
|
"step": 46610
|
|
},
|
|
{
|
|
"entropy": 5.541909694671631,
|
|
"epoch": 3.893668559973271,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003550506869221038,
|
|
"loss": 4.7631,
|
|
"mean_token_accuracy": 0.23844429552555085,
|
|
"num_tokens": 85764537.0,
|
|
"step": 46615
|
|
},
|
|
{
|
|
"entropy": 5.581519603729248,
|
|
"epoch": 3.894086201135984,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00035502286411084183,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.22959689795970917,
|
|
"num_tokens": 85773944.0,
|
|
"step": 46620
|
|
},
|
|
{
|
|
"entropy": 5.543196058273315,
|
|
"epoch": 3.894503842298697,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00035499503989868335,
|
|
"loss": 4.6662,
|
|
"mean_token_accuracy": 0.23909128904342652,
|
|
"num_tokens": 85782638.0,
|
|
"step": 46625
|
|
},
|
|
{
|
|
"entropy": 5.601529455184936,
|
|
"epoch": 3.89492148346141,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00035496721428611547,
|
|
"loss": 4.7937,
|
|
"mean_token_accuracy": 0.234799724817276,
|
|
"num_tokens": 85792185.0,
|
|
"step": 46630
|
|
},
|
|
{
|
|
"entropy": 5.52690863609314,
|
|
"epoch": 3.895339124624123,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003549393872736252,
|
|
"loss": 4.6984,
|
|
"mean_token_accuracy": 0.2440956100821495,
|
|
"num_tokens": 85800836.0,
|
|
"step": 46635
|
|
},
|
|
{
|
|
"entropy": 5.608210897445678,
|
|
"epoch": 3.895756765786836,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00035491155886169967,
|
|
"loss": 4.8548,
|
|
"mean_token_accuracy": 0.22777196913957595,
|
|
"num_tokens": 85809278.0,
|
|
"step": 46640
|
|
},
|
|
{
|
|
"entropy": 5.4945878982543945,
|
|
"epoch": 3.896174406949549,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003548837290508263,
|
|
"loss": 4.6472,
|
|
"mean_token_accuracy": 0.2363378956913948,
|
|
"num_tokens": 85817733.0,
|
|
"step": 46645
|
|
},
|
|
{
|
|
"entropy": 5.505469512939453,
|
|
"epoch": 3.896592048112262,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003548558978414919,
|
|
"loss": 4.7419,
|
|
"mean_token_accuracy": 0.2373747855424881,
|
|
"num_tokens": 85827894.0,
|
|
"step": 46650
|
|
},
|
|
{
|
|
"entropy": 5.545105457305908,
|
|
"epoch": 3.897009689274975,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00035482806523418395,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.23612676560878754,
|
|
"num_tokens": 85836615.0,
|
|
"step": 46655
|
|
},
|
|
{
|
|
"entropy": 5.598236465454102,
|
|
"epoch": 3.897427330437688,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035480023122938964,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.23702077716588973,
|
|
"num_tokens": 85845019.0,
|
|
"step": 46660
|
|
},
|
|
{
|
|
"entropy": 5.539129257202148,
|
|
"epoch": 3.897844971600401,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00035477239582759623,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.23767739683389663,
|
|
"num_tokens": 85853734.0,
|
|
"step": 46665
|
|
},
|
|
{
|
|
"entropy": 5.655519294738769,
|
|
"epoch": 3.898262612763114,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000354744559029291,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.22395082265138627,
|
|
"num_tokens": 85863719.0,
|
|
"step": 46670
|
|
},
|
|
{
|
|
"entropy": 5.48380970954895,
|
|
"epoch": 3.8986802539258267,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00035471672083496126,
|
|
"loss": 4.651,
|
|
"mean_token_accuracy": 0.24338337630033494,
|
|
"num_tokens": 85872968.0,
|
|
"step": 46675
|
|
},
|
|
{
|
|
"entropy": 5.547085952758789,
|
|
"epoch": 3.89909789508854,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00035468888124509434,
|
|
"loss": 4.6977,
|
|
"mean_token_accuracy": 0.23467477411031723,
|
|
"num_tokens": 85881220.0,
|
|
"step": 46680
|
|
},
|
|
{
|
|
"entropy": 5.550334739685058,
|
|
"epoch": 3.899515536251253,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003546610402601777,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.2339962601661682,
|
|
"num_tokens": 85889690.0,
|
|
"step": 46685
|
|
},
|
|
{
|
|
"entropy": 5.584229373931885,
|
|
"epoch": 3.899933177413966,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003546331978806986,
|
|
"loss": 4.7434,
|
|
"mean_token_accuracy": 0.23202457875013352,
|
|
"num_tokens": 85898723.0,
|
|
"step": 46690
|
|
},
|
|
{
|
|
"entropy": 5.5395787239074705,
|
|
"epoch": 3.900350818576679,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035460535410714456,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.2283043846487999,
|
|
"num_tokens": 85907757.0,
|
|
"step": 46695
|
|
},
|
|
{
|
|
"entropy": 5.492800378799439,
|
|
"epoch": 3.9007684597393917,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000354577508940003,
|
|
"loss": 4.6502,
|
|
"mean_token_accuracy": 0.24632046669721602,
|
|
"num_tokens": 85916361.0,
|
|
"step": 46700
|
|
},
|
|
{
|
|
"entropy": 5.605850791931152,
|
|
"epoch": 3.901186100902105,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00035454966237976135,
|
|
"loss": 4.7779,
|
|
"mean_token_accuracy": 0.2338111847639084,
|
|
"num_tokens": 85925521.0,
|
|
"step": 46705
|
|
},
|
|
{
|
|
"entropy": 5.4711480140686035,
|
|
"epoch": 3.9016037420648177,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00035452181442690705,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.24315786063671113,
|
|
"num_tokens": 85934229.0,
|
|
"step": 46710
|
|
},
|
|
{
|
|
"entropy": 5.531940984725952,
|
|
"epoch": 3.902021383227531,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003544939650819277,
|
|
"loss": 4.6249,
|
|
"mean_token_accuracy": 0.24081665128469468,
|
|
"num_tokens": 85942914.0,
|
|
"step": 46715
|
|
},
|
|
{
|
|
"entropy": 5.599124622344971,
|
|
"epoch": 3.902439024390244,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035446611434531084,
|
|
"loss": 4.6763,
|
|
"mean_token_accuracy": 0.2369694232940674,
|
|
"num_tokens": 85951214.0,
|
|
"step": 46720
|
|
},
|
|
{
|
|
"entropy": 5.581721305847168,
|
|
"epoch": 3.9028566655529566,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00035443826221754395,
|
|
"loss": 4.7821,
|
|
"mean_token_accuracy": 0.22819352447986602,
|
|
"num_tokens": 85960204.0,
|
|
"step": 46725
|
|
},
|
|
{
|
|
"entropy": 5.407811403274536,
|
|
"epoch": 3.90327430671567,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003544104086991147,
|
|
"loss": 4.6115,
|
|
"mean_token_accuracy": 0.24559245109558106,
|
|
"num_tokens": 85969044.0,
|
|
"step": 46730
|
|
},
|
|
{
|
|
"entropy": 5.559079599380493,
|
|
"epoch": 3.903691947878383,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00035438255379051056,
|
|
"loss": 4.7938,
|
|
"mean_token_accuracy": 0.23347121626138687,
|
|
"num_tokens": 85978669.0,
|
|
"step": 46735
|
|
},
|
|
{
|
|
"entropy": 5.627266073226929,
|
|
"epoch": 3.904109589041096,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003543546974922194,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.22834884822368623,
|
|
"num_tokens": 85987197.0,
|
|
"step": 46740
|
|
},
|
|
{
|
|
"entropy": 5.489485597610473,
|
|
"epoch": 3.9045272302038088,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003543268398047286,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.2524771347641945,
|
|
"num_tokens": 85996010.0,
|
|
"step": 46745
|
|
},
|
|
{
|
|
"entropy": 5.47868013381958,
|
|
"epoch": 3.904944871366522,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00035429898072852613,
|
|
"loss": 4.6291,
|
|
"mean_token_accuracy": 0.2471115455031395,
|
|
"num_tokens": 86005140.0,
|
|
"step": 46750
|
|
},
|
|
{
|
|
"entropy": 5.543755340576172,
|
|
"epoch": 3.905362512529235,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00035427112026409943,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.23465979248285293,
|
|
"num_tokens": 86013885.0,
|
|
"step": 46755
|
|
},
|
|
{
|
|
"entropy": 5.567109870910644,
|
|
"epoch": 3.905780153691948,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00035424325841193645,
|
|
"loss": 4.8043,
|
|
"mean_token_accuracy": 0.23115324079990388,
|
|
"num_tokens": 86023112.0,
|
|
"step": 46760
|
|
},
|
|
{
|
|
"entropy": 5.4618443012237545,
|
|
"epoch": 3.906197794854661,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003542153951725247,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.24587926268577576,
|
|
"num_tokens": 86033046.0,
|
|
"step": 46765
|
|
},
|
|
{
|
|
"entropy": 5.648593759536743,
|
|
"epoch": 3.9066154360173737,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003541875305463523,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.2339570239186287,
|
|
"num_tokens": 86043194.0,
|
|
"step": 46770
|
|
},
|
|
{
|
|
"entropy": 5.55463171005249,
|
|
"epoch": 3.907033077180087,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0003541596645339067,
|
|
"loss": 4.6769,
|
|
"mean_token_accuracy": 0.24666234254837036,
|
|
"num_tokens": 86051666.0,
|
|
"step": 46775
|
|
},
|
|
{
|
|
"entropy": 5.601631212234497,
|
|
"epoch": 3.9074507183428,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000354131797135676,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.23497726619243622,
|
|
"num_tokens": 86060215.0,
|
|
"step": 46780
|
|
},
|
|
{
|
|
"entropy": 5.565232610702514,
|
|
"epoch": 3.907868359505513,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00035410392835214785,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.22945082634687425,
|
|
"num_tokens": 86069562.0,
|
|
"step": 46785
|
|
},
|
|
{
|
|
"entropy": 5.540882301330567,
|
|
"epoch": 3.908286000668226,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003540760581838103,
|
|
"loss": 4.6457,
|
|
"mean_token_accuracy": 0.24490879625082015,
|
|
"num_tokens": 86078835.0,
|
|
"step": 46790
|
|
},
|
|
{
|
|
"entropy": 5.610836362838745,
|
|
"epoch": 3.9087036418309387,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00035404818663115105,
|
|
"loss": 4.7658,
|
|
"mean_token_accuracy": 0.23481726497411728,
|
|
"num_tokens": 86087648.0,
|
|
"step": 46795
|
|
},
|
|
{
|
|
"entropy": 5.499196863174438,
|
|
"epoch": 3.909121282993652,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003540203136946583,
|
|
"loss": 4.6831,
|
|
"mean_token_accuracy": 0.23156411796808243,
|
|
"num_tokens": 86096879.0,
|
|
"step": 46800
|
|
},
|
|
{
|
|
"entropy": 5.453122758865357,
|
|
"epoch": 3.9095389241563647,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003539924393748197,
|
|
"loss": 4.6498,
|
|
"mean_token_accuracy": 0.24599926471710204,
|
|
"num_tokens": 86105647.0,
|
|
"step": 46805
|
|
},
|
|
{
|
|
"entropy": 5.555804300308227,
|
|
"epoch": 3.909956565319078,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003539645636721234,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.23196214735507964,
|
|
"num_tokens": 86115176.0,
|
|
"step": 46810
|
|
},
|
|
{
|
|
"entropy": 5.52052059173584,
|
|
"epoch": 3.910374206481791,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00035393668658705745,
|
|
"loss": 4.6786,
|
|
"mean_token_accuracy": 0.23596799820661546,
|
|
"num_tokens": 86123327.0,
|
|
"step": 46815
|
|
},
|
|
{
|
|
"entropy": 5.631770181655884,
|
|
"epoch": 3.9107918476445036,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003539088081201097,
|
|
"loss": 4.8043,
|
|
"mean_token_accuracy": 0.23256283402442932,
|
|
"num_tokens": 86133271.0,
|
|
"step": 46820
|
|
},
|
|
{
|
|
"entropy": 5.618548822402954,
|
|
"epoch": 3.911209488807217,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003538809282717683,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.23346610069274903,
|
|
"num_tokens": 86143586.0,
|
|
"step": 46825
|
|
},
|
|
{
|
|
"entropy": 5.57576813697815,
|
|
"epoch": 3.9116271299699297,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003538530470425213,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.2331594631075859,
|
|
"num_tokens": 86152165.0,
|
|
"step": 46830
|
|
},
|
|
{
|
|
"entropy": 5.4365404605865475,
|
|
"epoch": 3.912044771132643,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00035382516443285676,
|
|
"loss": 4.6882,
|
|
"mean_token_accuracy": 0.23475642502307892,
|
|
"num_tokens": 86160963.0,
|
|
"step": 46835
|
|
},
|
|
{
|
|
"entropy": 5.4812836170196535,
|
|
"epoch": 3.9124624122953557,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00035379728044326295,
|
|
"loss": 4.6135,
|
|
"mean_token_accuracy": 0.24145179837942124,
|
|
"num_tokens": 86170132.0,
|
|
"step": 46840
|
|
},
|
|
{
|
|
"entropy": 5.617294883728027,
|
|
"epoch": 3.9128800534580686,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00035376939507422776,
|
|
"loss": 4.7968,
|
|
"mean_token_accuracy": 0.23528962284326554,
|
|
"num_tokens": 86179291.0,
|
|
"step": 46845
|
|
},
|
|
{
|
|
"entropy": 5.489105844497681,
|
|
"epoch": 3.913297694620782,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00035374150832623964,
|
|
"loss": 4.6833,
|
|
"mean_token_accuracy": 0.24235389828681947,
|
|
"num_tokens": 86188425.0,
|
|
"step": 46850
|
|
},
|
|
{
|
|
"entropy": 5.5549663543701175,
|
|
"epoch": 3.913715335783495,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003537136201997865,
|
|
"loss": 4.7537,
|
|
"mean_token_accuracy": 0.24055844992399217,
|
|
"num_tokens": 86197961.0,
|
|
"step": 46855
|
|
},
|
|
{
|
|
"entropy": 5.532603549957275,
|
|
"epoch": 3.914132976946208,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035368573069535677,
|
|
"loss": 4.7161,
|
|
"mean_token_accuracy": 0.23635452687740327,
|
|
"num_tokens": 86206708.0,
|
|
"step": 46860
|
|
},
|
|
{
|
|
"entropy": 5.573917198181152,
|
|
"epoch": 3.9145506181089207,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003536578398134386,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.23398934602737426,
|
|
"num_tokens": 86215750.0,
|
|
"step": 46865
|
|
},
|
|
{
|
|
"entropy": 5.510099458694458,
|
|
"epoch": 3.914968259271634,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003536299475545202,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.2403499275445938,
|
|
"num_tokens": 86224913.0,
|
|
"step": 46870
|
|
},
|
|
{
|
|
"entropy": 5.601492834091187,
|
|
"epoch": 3.9153859004343468,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00035360205391909,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.22569599598646164,
|
|
"num_tokens": 86236130.0,
|
|
"step": 46875
|
|
},
|
|
{
|
|
"entropy": 5.535977935791015,
|
|
"epoch": 3.91580354159706,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003535741589076362,
|
|
"loss": 4.7449,
|
|
"mean_token_accuracy": 0.23964085280895234,
|
|
"num_tokens": 86245698.0,
|
|
"step": 46880
|
|
},
|
|
{
|
|
"entropy": 5.579282474517822,
|
|
"epoch": 3.916221182759773,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035354626252064714,
|
|
"loss": 4.7956,
|
|
"mean_token_accuracy": 0.23644204139709474,
|
|
"num_tokens": 86255376.0,
|
|
"step": 46885
|
|
},
|
|
{
|
|
"entropy": 5.519890880584716,
|
|
"epoch": 3.9166388239224856,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00035351836475861127,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.2329130157828331,
|
|
"num_tokens": 86264245.0,
|
|
"step": 46890
|
|
},
|
|
{
|
|
"entropy": 5.480968427658081,
|
|
"epoch": 3.917056465085199,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003534904656220169,
|
|
"loss": 4.6484,
|
|
"mean_token_accuracy": 0.24698469638824463,
|
|
"num_tokens": 86273114.0,
|
|
"step": 46895
|
|
},
|
|
{
|
|
"entropy": 5.566500663757324,
|
|
"epoch": 3.9174741062479117,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003534625651113524,
|
|
"loss": 4.6767,
|
|
"mean_token_accuracy": 0.2411716565489769,
|
|
"num_tokens": 86282539.0,
|
|
"step": 46900
|
|
},
|
|
{
|
|
"entropy": 5.591454124450683,
|
|
"epoch": 3.917891747410625,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003534346632271063,
|
|
"loss": 4.751,
|
|
"mean_token_accuracy": 0.22750697880983353,
|
|
"num_tokens": 86293755.0,
|
|
"step": 46905
|
|
},
|
|
{
|
|
"entropy": 5.551562404632568,
|
|
"epoch": 3.9183093885733378,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00035340675996976703,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.22928112447261811,
|
|
"num_tokens": 86302736.0,
|
|
"step": 46910
|
|
},
|
|
{
|
|
"entropy": 5.535208797454834,
|
|
"epoch": 3.9187270297360506,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00035337885533982295,
|
|
"loss": 4.6267,
|
|
"mean_token_accuracy": 0.2424985274672508,
|
|
"num_tokens": 86312357.0,
|
|
"step": 46915
|
|
},
|
|
{
|
|
"entropy": 5.526575040817261,
|
|
"epoch": 3.919144670898764,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003533509493377627,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.23394553363323212,
|
|
"num_tokens": 86322218.0,
|
|
"step": 46920
|
|
},
|
|
{
|
|
"entropy": 5.547411251068115,
|
|
"epoch": 3.9195623120614766,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00035332304196407485,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.23284535259008407,
|
|
"num_tokens": 86332020.0,
|
|
"step": 46925
|
|
},
|
|
{
|
|
"entropy": 5.610790681838989,
|
|
"epoch": 3.91997995322419,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00035329513321924775,
|
|
"loss": 4.7371,
|
|
"mean_token_accuracy": 0.23213099241256713,
|
|
"num_tokens": 86341387.0,
|
|
"step": 46930
|
|
},
|
|
{
|
|
"entropy": 5.534732246398926,
|
|
"epoch": 3.9203975943869027,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00035326722310377026,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.24130623936653137,
|
|
"num_tokens": 86350137.0,
|
|
"step": 46935
|
|
},
|
|
{
|
|
"entropy": 5.520279502868652,
|
|
"epoch": 3.9208152355496155,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035323931161813064,
|
|
"loss": 4.6999,
|
|
"mean_token_accuracy": 0.2416228696703911,
|
|
"num_tokens": 86359176.0,
|
|
"step": 46940
|
|
},
|
|
{
|
|
"entropy": 5.515482330322266,
|
|
"epoch": 3.921232876712329,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003532113987628179,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.24229057133197784,
|
|
"num_tokens": 86367621.0,
|
|
"step": 46945
|
|
},
|
|
{
|
|
"entropy": 5.547414255142212,
|
|
"epoch": 3.921650517875042,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003531834845383203,
|
|
"loss": 4.7786,
|
|
"mean_token_accuracy": 0.23062806725502014,
|
|
"num_tokens": 86376102.0,
|
|
"step": 46950
|
|
},
|
|
{
|
|
"entropy": 5.611300086975097,
|
|
"epoch": 3.922068159037755,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00035315556894512676,
|
|
"loss": 4.7594,
|
|
"mean_token_accuracy": 0.23044796288013458,
|
|
"num_tokens": 86384950.0,
|
|
"step": 46955
|
|
},
|
|
{
|
|
"entropy": 5.546203899383545,
|
|
"epoch": 3.9224858002004677,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00035312765198372586,
|
|
"loss": 4.697,
|
|
"mean_token_accuracy": 0.24266188442707062,
|
|
"num_tokens": 86393370.0,
|
|
"step": 46960
|
|
},
|
|
{
|
|
"entropy": 5.598986291885376,
|
|
"epoch": 3.922903441363181,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035309973365460647,
|
|
"loss": 4.8855,
|
|
"mean_token_accuracy": 0.2164828822016716,
|
|
"num_tokens": 86402545.0,
|
|
"step": 46965
|
|
},
|
|
{
|
|
"entropy": 5.582671880722046,
|
|
"epoch": 3.9233210825258937,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003530718139582571,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.2295933723449707,
|
|
"num_tokens": 86411906.0,
|
|
"step": 46970
|
|
},
|
|
{
|
|
"entropy": 5.598493814468384,
|
|
"epoch": 3.923738723688607,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003530438928951668,
|
|
"loss": 4.688,
|
|
"mean_token_accuracy": 0.2349045157432556,
|
|
"num_tokens": 86420776.0,
|
|
"step": 46975
|
|
},
|
|
{
|
|
"entropy": 5.583315134048462,
|
|
"epoch": 3.92415636485132,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003530159704658241,
|
|
"loss": 4.7493,
|
|
"mean_token_accuracy": 0.23057095855474471,
|
|
"num_tokens": 86429490.0,
|
|
"step": 46980
|
|
},
|
|
{
|
|
"entropy": 5.496988677978516,
|
|
"epoch": 3.9245740060140326,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035298804667071806,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.24471722841262816,
|
|
"num_tokens": 86438142.0,
|
|
"step": 46985
|
|
},
|
|
{
|
|
"entropy": 5.596951150894165,
|
|
"epoch": 3.924991647176746,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00035296012151033726,
|
|
"loss": 4.7945,
|
|
"mean_token_accuracy": 0.22527830451726913,
|
|
"num_tokens": 86447840.0,
|
|
"step": 46990
|
|
},
|
|
{
|
|
"entropy": 5.589200401306153,
|
|
"epoch": 3.9254092883394587,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003529321949851707,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.23745177686214447,
|
|
"num_tokens": 86456382.0,
|
|
"step": 46995
|
|
},
|
|
{
|
|
"entropy": 5.523239326477051,
|
|
"epoch": 3.925826929502172,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035290426709570734,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.24228459000587463,
|
|
"num_tokens": 86465324.0,
|
|
"step": 47000
|
|
},
|
|
{
|
|
"entropy": 5.539932203292847,
|
|
"epoch": 3.9262445706648847,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00035287633784243595,
|
|
"loss": 4.6577,
|
|
"mean_token_accuracy": 0.2354825794696808,
|
|
"num_tokens": 86474040.0,
|
|
"step": 47005
|
|
},
|
|
{
|
|
"entropy": 5.584628057479859,
|
|
"epoch": 3.9266622118275976,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003528484072258455,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.23113533854484558,
|
|
"num_tokens": 86484330.0,
|
|
"step": 47010
|
|
},
|
|
{
|
|
"entropy": 5.594127511978149,
|
|
"epoch": 3.927079852990311,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000352820475246425,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.2309749573469162,
|
|
"num_tokens": 86493756.0,
|
|
"step": 47015
|
|
},
|
|
{
|
|
"entropy": 5.5780902862548825,
|
|
"epoch": 3.9274974941530236,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003527925419046635,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.229957714676857,
|
|
"num_tokens": 86503267.0,
|
|
"step": 47020
|
|
},
|
|
{
|
|
"entropy": 5.5472283363342285,
|
|
"epoch": 3.927915135315737,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003527646072010498,
|
|
"loss": 4.6609,
|
|
"mean_token_accuracy": 0.2458649381995201,
|
|
"num_tokens": 86512140.0,
|
|
"step": 47025
|
|
},
|
|
{
|
|
"entropy": 5.517658329010009,
|
|
"epoch": 3.9283327764784497,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003527366711360731,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.23792146742343903,
|
|
"num_tokens": 86521168.0,
|
|
"step": 47030
|
|
},
|
|
{
|
|
"entropy": 5.499385929107666,
|
|
"epoch": 3.9287504176411625,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003527087337102224,
|
|
"loss": 4.6965,
|
|
"mean_token_accuracy": 0.23626900911331178,
|
|
"num_tokens": 86529823.0,
|
|
"step": 47035
|
|
},
|
|
{
|
|
"entropy": 5.495591354370117,
|
|
"epoch": 3.9291680588038758,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00035268079492398673,
|
|
"loss": 4.6738,
|
|
"mean_token_accuracy": 0.23408445417881013,
|
|
"num_tokens": 86540597.0,
|
|
"step": 47040
|
|
},
|
|
{
|
|
"entropy": 5.475944900512696,
|
|
"epoch": 3.9295856999665886,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003526528547778553,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.2427869752049446,
|
|
"num_tokens": 86548621.0,
|
|
"step": 47045
|
|
},
|
|
{
|
|
"entropy": 5.5139891624450685,
|
|
"epoch": 3.930003341129302,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003526249132723171,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.23606230169534684,
|
|
"num_tokens": 86558315.0,
|
|
"step": 47050
|
|
},
|
|
{
|
|
"entropy": 5.556406402587891,
|
|
"epoch": 3.9304209822920146,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003525969704078615,
|
|
"loss": 4.8285,
|
|
"mean_token_accuracy": 0.22342851161956787,
|
|
"num_tokens": 86568925.0,
|
|
"step": 47055
|
|
},
|
|
{
|
|
"entropy": 5.5080180168151855,
|
|
"epoch": 3.9308386234547275,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00035256902618497737,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.24615367799997329,
|
|
"num_tokens": 86578188.0,
|
|
"step": 47060
|
|
},
|
|
{
|
|
"entropy": 5.480410575866699,
|
|
"epoch": 3.9312562646174407,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00035254108060415415,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.2347061440348625,
|
|
"num_tokens": 86588333.0,
|
|
"step": 47065
|
|
},
|
|
{
|
|
"entropy": 5.518491888046265,
|
|
"epoch": 3.931673905780154,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003525131336658809,
|
|
"loss": 4.7382,
|
|
"mean_token_accuracy": 0.23675262778997422,
|
|
"num_tokens": 86597148.0,
|
|
"step": 47070
|
|
},
|
|
{
|
|
"entropy": 5.5071063995361325,
|
|
"epoch": 3.9320915469428668,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00035248518537064704,
|
|
"loss": 4.6546,
|
|
"mean_token_accuracy": 0.24495479315519333,
|
|
"num_tokens": 86606497.0,
|
|
"step": 47075
|
|
},
|
|
{
|
|
"entropy": 5.436457347869873,
|
|
"epoch": 3.9325091881055796,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00035245723571894174,
|
|
"loss": 4.6327,
|
|
"mean_token_accuracy": 0.23730078488588333,
|
|
"num_tokens": 86616416.0,
|
|
"step": 47080
|
|
},
|
|
{
|
|
"entropy": 5.5056390285491945,
|
|
"epoch": 3.932926829268293,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003524292847112542,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.2410174161195755,
|
|
"num_tokens": 86625264.0,
|
|
"step": 47085
|
|
},
|
|
{
|
|
"entropy": 5.5802295207977295,
|
|
"epoch": 3.9333444704310057,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003524013323480739,
|
|
"loss": 4.7772,
|
|
"mean_token_accuracy": 0.22595678716897966,
|
|
"num_tokens": 86635020.0,
|
|
"step": 47090
|
|
},
|
|
{
|
|
"entropy": 5.526920509338379,
|
|
"epoch": 3.933762111593719,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035237337862989015,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.23846310675144194,
|
|
"num_tokens": 86644770.0,
|
|
"step": 47095
|
|
},
|
|
{
|
|
"entropy": 5.51028618812561,
|
|
"epoch": 3.9341797527564317,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00035234542355719225,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.23102570623159407,
|
|
"num_tokens": 86654488.0,
|
|
"step": 47100
|
|
},
|
|
{
|
|
"entropy": 5.487319660186768,
|
|
"epoch": 3.9345973939191445,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003523174671304695,
|
|
"loss": 4.6124,
|
|
"mean_token_accuracy": 0.24595567882061004,
|
|
"num_tokens": 86663432.0,
|
|
"step": 47105
|
|
},
|
|
{
|
|
"entropy": 5.4754664421081545,
|
|
"epoch": 3.935015035081858,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003522895093502115,
|
|
"loss": 4.6846,
|
|
"mean_token_accuracy": 0.23753005564212798,
|
|
"num_tokens": 86672184.0,
|
|
"step": 47110
|
|
},
|
|
{
|
|
"entropy": 5.529477167129516,
|
|
"epoch": 3.9354326762445706,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00035226155021690766,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.23177751749753953,
|
|
"num_tokens": 86681652.0,
|
|
"step": 47115
|
|
},
|
|
{
|
|
"entropy": 5.584132051467895,
|
|
"epoch": 3.935850317407284,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003522335897310473,
|
|
"loss": 4.774,
|
|
"mean_token_accuracy": 0.24311165511608124,
|
|
"num_tokens": 86690291.0,
|
|
"step": 47120
|
|
},
|
|
{
|
|
"entropy": 5.523287010192871,
|
|
"epoch": 3.9362679585699967,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00035220562789312006,
|
|
"loss": 4.7014,
|
|
"mean_token_accuracy": 0.24181242436170577,
|
|
"num_tokens": 86698928.0,
|
|
"step": 47125
|
|
},
|
|
{
|
|
"entropy": 5.49147777557373,
|
|
"epoch": 3.9366855997327095,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003521776647036153,
|
|
"loss": 4.7526,
|
|
"mean_token_accuracy": 0.23791593611240386,
|
|
"num_tokens": 86708249.0,
|
|
"step": 47130
|
|
},
|
|
{
|
|
"entropy": 5.449348640441895,
|
|
"epoch": 3.9371032408954227,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003521497001630226,
|
|
"loss": 4.648,
|
|
"mean_token_accuracy": 0.24661166220903397,
|
|
"num_tokens": 86717273.0,
|
|
"step": 47135
|
|
},
|
|
{
|
|
"entropy": 5.580180549621582,
|
|
"epoch": 3.9375208820581356,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00035212173427183165,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.22436976283788682,
|
|
"num_tokens": 86726444.0,
|
|
"step": 47140
|
|
},
|
|
{
|
|
"entropy": 5.619295406341553,
|
|
"epoch": 3.937938523220849,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003520937670305318,
|
|
"loss": 4.7651,
|
|
"mean_token_accuracy": 0.23088956773281097,
|
|
"num_tokens": 86735889.0,
|
|
"step": 47145
|
|
},
|
|
{
|
|
"entropy": 5.594905233383178,
|
|
"epoch": 3.9383561643835616,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003520657984396128,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.24120336025953293,
|
|
"num_tokens": 86745393.0,
|
|
"step": 47150
|
|
},
|
|
{
|
|
"entropy": 5.526306962966919,
|
|
"epoch": 3.9387738055462744,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00035203782849956423,
|
|
"loss": 4.7502,
|
|
"mean_token_accuracy": 0.2413395270705223,
|
|
"num_tokens": 86754785.0,
|
|
"step": 47155
|
|
},
|
|
{
|
|
"entropy": 5.5416234016418455,
|
|
"epoch": 3.9391914467089877,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003520098572108758,
|
|
"loss": 4.722,
|
|
"mean_token_accuracy": 0.23443542867898942,
|
|
"num_tokens": 86764181.0,
|
|
"step": 47160
|
|
},
|
|
{
|
|
"entropy": 5.591191530227661,
|
|
"epoch": 3.9396090878717005,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003519818845740371,
|
|
"loss": 4.7782,
|
|
"mean_token_accuracy": 0.23290175944566727,
|
|
"num_tokens": 86773718.0,
|
|
"step": 47165
|
|
},
|
|
{
|
|
"entropy": 5.603180360794068,
|
|
"epoch": 3.9400267290344138,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035195391058953776,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.23070333898067474,
|
|
"num_tokens": 86782135.0,
|
|
"step": 47170
|
|
},
|
|
{
|
|
"entropy": 5.583168649673462,
|
|
"epoch": 3.9404443701971266,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003519259352578676,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.2413901388645172,
|
|
"num_tokens": 86791001.0,
|
|
"step": 47175
|
|
},
|
|
{
|
|
"entropy": 5.495897054672241,
|
|
"epoch": 3.9408620113598394,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00035189795857951643,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.23598811775445938,
|
|
"num_tokens": 86799757.0,
|
|
"step": 47180
|
|
},
|
|
{
|
|
"entropy": 5.582860231399536,
|
|
"epoch": 3.9412796525225526,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00035186998055497396,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.23141134828329085,
|
|
"num_tokens": 86808441.0,
|
|
"step": 47185
|
|
},
|
|
{
|
|
"entropy": 5.5407843589782715,
|
|
"epoch": 3.941697293685266,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035184200118472983,
|
|
"loss": 4.7123,
|
|
"mean_token_accuracy": 0.23628369867801666,
|
|
"num_tokens": 86817712.0,
|
|
"step": 47190
|
|
},
|
|
{
|
|
"entropy": 5.54845175743103,
|
|
"epoch": 3.9421149348479787,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000351814020469274,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.23246257454156877,
|
|
"num_tokens": 86826756.0,
|
|
"step": 47195
|
|
},
|
|
{
|
|
"entropy": 5.502262163162231,
|
|
"epoch": 3.9425325760106915,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003517860384090963,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.2444980949163437,
|
|
"num_tokens": 86835349.0,
|
|
"step": 47200
|
|
},
|
|
{
|
|
"entropy": 5.463473844528198,
|
|
"epoch": 3.9429502171734048,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00035175805500468654,
|
|
"loss": 4.6544,
|
|
"mean_token_accuracy": 0.23865987062454225,
|
|
"num_tokens": 86845147.0,
|
|
"step": 47205
|
|
},
|
|
{
|
|
"entropy": 5.493406581878662,
|
|
"epoch": 3.9433678583361176,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035173007025653477,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.23913231939077378,
|
|
"num_tokens": 86853474.0,
|
|
"step": 47210
|
|
},
|
|
{
|
|
"entropy": 5.511127996444702,
|
|
"epoch": 3.943785499498831,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003517020841651306,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.23389613032341003,
|
|
"num_tokens": 86862459.0,
|
|
"step": 47215
|
|
},
|
|
{
|
|
"entropy": 5.637110233306885,
|
|
"epoch": 3.9442031406615436,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035167409673096423,
|
|
"loss": 4.8573,
|
|
"mean_token_accuracy": 0.22544210255146027,
|
|
"num_tokens": 86871978.0,
|
|
"step": 47220
|
|
},
|
|
{
|
|
"entropy": 5.615022230148315,
|
|
"epoch": 3.9446207818242565,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0003516461079545255,
|
|
"loss": 4.8154,
|
|
"mean_token_accuracy": 0.2272478699684143,
|
|
"num_tokens": 86880620.0,
|
|
"step": 47225
|
|
},
|
|
{
|
|
"entropy": 5.5440467357635494,
|
|
"epoch": 3.9450384229869697,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003516181178363044,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.23570678681135177,
|
|
"num_tokens": 86889456.0,
|
|
"step": 47230
|
|
},
|
|
{
|
|
"entropy": 5.571424055099487,
|
|
"epoch": 3.9454560641496825,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00035159012637679075,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.24135814905166625,
|
|
"num_tokens": 86898138.0,
|
|
"step": 47235
|
|
},
|
|
{
|
|
"entropy": 5.628052616119385,
|
|
"epoch": 3.945873705312396,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035156213357647495,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.22905114889144898,
|
|
"num_tokens": 86907563.0,
|
|
"step": 47240
|
|
},
|
|
{
|
|
"entropy": 5.538450479507446,
|
|
"epoch": 3.9462913464751086,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003515341394358467,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.23888293355703355,
|
|
"num_tokens": 86916830.0,
|
|
"step": 47245
|
|
},
|
|
{
|
|
"entropy": 5.5620002269744875,
|
|
"epoch": 3.9467089876378214,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035150614395539634,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.2261285737156868,
|
|
"num_tokens": 86926734.0,
|
|
"step": 47250
|
|
},
|
|
{
|
|
"entropy": 5.512236881256103,
|
|
"epoch": 3.9471266288005347,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003514781471356137,
|
|
"loss": 4.6864,
|
|
"mean_token_accuracy": 0.2411051645874977,
|
|
"num_tokens": 86936009.0,
|
|
"step": 47255
|
|
},
|
|
{
|
|
"entropy": 5.567965793609619,
|
|
"epoch": 3.9475442699632475,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00035145014897698917,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.23588284701108933,
|
|
"num_tokens": 86946047.0,
|
|
"step": 47260
|
|
},
|
|
{
|
|
"entropy": 5.576629018783569,
|
|
"epoch": 3.9479619111259607,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003514221494800127,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.22704101949930192,
|
|
"num_tokens": 86955589.0,
|
|
"step": 47265
|
|
},
|
|
{
|
|
"entropy": 5.6101402759552,
|
|
"epoch": 3.9483795522886735,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003513941486451745,
|
|
"loss": 4.7815,
|
|
"mean_token_accuracy": 0.22646634429693221,
|
|
"num_tokens": 86964560.0,
|
|
"step": 47270
|
|
},
|
|
{
|
|
"entropy": 5.515402603149414,
|
|
"epoch": 3.9487971934513864,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00035136614647296476,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.24147249460220338,
|
|
"num_tokens": 86973225.0,
|
|
"step": 47275
|
|
},
|
|
{
|
|
"entropy": 5.492625379562378,
|
|
"epoch": 3.9492148346140996,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00035133814296387373,
|
|
"loss": 4.6627,
|
|
"mean_token_accuracy": 0.24184924662113189,
|
|
"num_tokens": 86981420.0,
|
|
"step": 47280
|
|
},
|
|
{
|
|
"entropy": 5.5981302738189695,
|
|
"epoch": 3.9496324757768124,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00035131013811839164,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.23399025499820708,
|
|
"num_tokens": 86990980.0,
|
|
"step": 47285
|
|
},
|
|
{
|
|
"entropy": 5.486300039291382,
|
|
"epoch": 3.9500501169395257,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00035128213193700875,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.2357518494129181,
|
|
"num_tokens": 86999836.0,
|
|
"step": 47290
|
|
},
|
|
{
|
|
"entropy": 5.473841857910156,
|
|
"epoch": 3.9504677581022385,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003512541244202153,
|
|
"loss": 4.6653,
|
|
"mean_token_accuracy": 0.2369916170835495,
|
|
"num_tokens": 87008753.0,
|
|
"step": 47295
|
|
},
|
|
{
|
|
"entropy": 5.592573404312134,
|
|
"epoch": 3.9508853992649513,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035122611556850155,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.2335047110915184,
|
|
"num_tokens": 87017821.0,
|
|
"step": 47300
|
|
},
|
|
{
|
|
"entropy": 5.544531583786011,
|
|
"epoch": 3.9513030404276646,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003511981053823579,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.23560407310724257,
|
|
"num_tokens": 87026967.0,
|
|
"step": 47305
|
|
},
|
|
{
|
|
"entropy": 5.54852261543274,
|
|
"epoch": 3.951720681590378,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00035117009386227476,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.2351600408554077,
|
|
"num_tokens": 87035995.0,
|
|
"step": 47310
|
|
},
|
|
{
|
|
"entropy": 5.593348169326783,
|
|
"epoch": 3.9521383227530906,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00035114208100874245,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.230753031373024,
|
|
"num_tokens": 87044414.0,
|
|
"step": 47315
|
|
},
|
|
{
|
|
"entropy": 5.549188423156738,
|
|
"epoch": 3.9525559639158034,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003511140668222513,
|
|
"loss": 4.6751,
|
|
"mean_token_accuracy": 0.24313662946224213,
|
|
"num_tokens": 87052829.0,
|
|
"step": 47320
|
|
},
|
|
{
|
|
"entropy": 5.511822986602783,
|
|
"epoch": 3.9529736050785167,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003510860513032918,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.24372579753398896,
|
|
"num_tokens": 87061849.0,
|
|
"step": 47325
|
|
},
|
|
{
|
|
"entropy": 5.4666746139526365,
|
|
"epoch": 3.9533912462412295,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035105803445235445,
|
|
"loss": 4.6055,
|
|
"mean_token_accuracy": 0.2508858308196068,
|
|
"num_tokens": 87070636.0,
|
|
"step": 47330
|
|
},
|
|
{
|
|
"entropy": 5.5045938968658445,
|
|
"epoch": 3.9538088874039428,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003510300162699296,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.24057670384645463,
|
|
"num_tokens": 87080133.0,
|
|
"step": 47335
|
|
},
|
|
{
|
|
"entropy": 5.502153444290161,
|
|
"epoch": 3.9542265285666556,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00035100199675650777,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.24129685014486313,
|
|
"num_tokens": 87089538.0,
|
|
"step": 47340
|
|
},
|
|
{
|
|
"entropy": 5.557987451553345,
|
|
"epoch": 3.9546441697293684,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00035097397591257956,
|
|
"loss": 4.7354,
|
|
"mean_token_accuracy": 0.23183225393295287,
|
|
"num_tokens": 87099182.0,
|
|
"step": 47345
|
|
},
|
|
{
|
|
"entropy": 5.587280988693237,
|
|
"epoch": 3.9550618108920816,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00035094595373863545,
|
|
"loss": 4.7853,
|
|
"mean_token_accuracy": 0.23274798989295958,
|
|
"num_tokens": 87108215.0,
|
|
"step": 47350
|
|
},
|
|
{
|
|
"entropy": 5.517260646820068,
|
|
"epoch": 3.9554794520547945,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000350917930235166,
|
|
"loss": 4.6704,
|
|
"mean_token_accuracy": 0.24244106113910674,
|
|
"num_tokens": 87118044.0,
|
|
"step": 47355
|
|
},
|
|
{
|
|
"entropy": 5.469539642333984,
|
|
"epoch": 3.9558970932175077,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00035088990540266176,
|
|
"loss": 4.6605,
|
|
"mean_token_accuracy": 0.24708300083875656,
|
|
"num_tokens": 87126584.0,
|
|
"step": 47360
|
|
},
|
|
{
|
|
"entropy": 5.5244639873504635,
|
|
"epoch": 3.9563147343802205,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003508618792416134,
|
|
"loss": 4.7278,
|
|
"mean_token_accuracy": 0.22664646208286285,
|
|
"num_tokens": 87134733.0,
|
|
"step": 47365
|
|
},
|
|
{
|
|
"entropy": 5.491649055480957,
|
|
"epoch": 3.9567323755429333,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00035083385175251156,
|
|
"loss": 4.6514,
|
|
"mean_token_accuracy": 0.2413337990641594,
|
|
"num_tokens": 87143283.0,
|
|
"step": 47370
|
|
},
|
|
{
|
|
"entropy": 5.621381616592407,
|
|
"epoch": 3.9571500167056466,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003508058229358468,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.22808565497398375,
|
|
"num_tokens": 87152321.0,
|
|
"step": 47375
|
|
},
|
|
{
|
|
"entropy": 5.516356992721557,
|
|
"epoch": 3.9575676578683594,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00035077779279210993,
|
|
"loss": 4.7071,
|
|
"mean_token_accuracy": 0.23842989206314086,
|
|
"num_tokens": 87161157.0,
|
|
"step": 47380
|
|
},
|
|
{
|
|
"entropy": 5.589976072311401,
|
|
"epoch": 3.9579852990310727,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035074976132179155,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.23434981107711791,
|
|
"num_tokens": 87170648.0,
|
|
"step": 47385
|
|
},
|
|
{
|
|
"entropy": 5.5809448719024655,
|
|
"epoch": 3.9584029401937855,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035072172852538235,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.22729135304689407,
|
|
"num_tokens": 87180008.0,
|
|
"step": 47390
|
|
},
|
|
{
|
|
"entropy": 5.516877746582031,
|
|
"epoch": 3.9588205813564983,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003506936944033733,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.238174469769001,
|
|
"num_tokens": 87188411.0,
|
|
"step": 47395
|
|
},
|
|
{
|
|
"entropy": 5.440889835357666,
|
|
"epoch": 3.9592382225192115,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003506656589562549,
|
|
"loss": 4.6024,
|
|
"mean_token_accuracy": 0.24754989743232728,
|
|
"num_tokens": 87197967.0,
|
|
"step": 47400
|
|
},
|
|
{
|
|
"entropy": 5.543473100662231,
|
|
"epoch": 3.9596558636819243,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003506376221845181,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.23648055493831635,
|
|
"num_tokens": 87207698.0,
|
|
"step": 47405
|
|
},
|
|
{
|
|
"entropy": 5.5029356479644775,
|
|
"epoch": 3.9600735048446376,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003506095840886537,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.23482417166233063,
|
|
"num_tokens": 87216049.0,
|
|
"step": 47410
|
|
},
|
|
{
|
|
"entropy": 5.521345806121826,
|
|
"epoch": 3.9604911460073504,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00035058154466915254,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.23215212672948837,
|
|
"num_tokens": 87225911.0,
|
|
"step": 47415
|
|
},
|
|
{
|
|
"entropy": 5.650609159469605,
|
|
"epoch": 3.9609087871700632,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003505535039265053,
|
|
"loss": 4.8968,
|
|
"mean_token_accuracy": 0.22570435255765914,
|
|
"num_tokens": 87234921.0,
|
|
"step": 47420
|
|
},
|
|
{
|
|
"entropy": 5.613753032684326,
|
|
"epoch": 3.9613264283327765,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0003505254618612032,
|
|
"loss": 4.7716,
|
|
"mean_token_accuracy": 0.23483940213918686,
|
|
"num_tokens": 87243565.0,
|
|
"step": 47425
|
|
},
|
|
{
|
|
"entropy": 5.5751629829406735,
|
|
"epoch": 3.9617440694954897,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003504974184737369,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.23713416010141372,
|
|
"num_tokens": 87253054.0,
|
|
"step": 47430
|
|
},
|
|
{
|
|
"entropy": 5.539108610153198,
|
|
"epoch": 3.9621617106582026,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00035046937376459746,
|
|
"loss": 4.6818,
|
|
"mean_token_accuracy": 0.24044266641139983,
|
|
"num_tokens": 87263217.0,
|
|
"step": 47435
|
|
},
|
|
{
|
|
"entropy": 5.491819143295288,
|
|
"epoch": 3.9625793518209154,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003504413277342758,
|
|
"loss": 4.6982,
|
|
"mean_token_accuracy": 0.23514188081026077,
|
|
"num_tokens": 87271952.0,
|
|
"step": 47440
|
|
},
|
|
{
|
|
"entropy": 5.530351877212524,
|
|
"epoch": 3.9629969929836286,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003504132803832629,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.22822979539632798,
|
|
"num_tokens": 87281075.0,
|
|
"step": 47445
|
|
},
|
|
{
|
|
"entropy": 5.511572980880738,
|
|
"epoch": 3.9634146341463414,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00035038523171204965,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.2363622397184372,
|
|
"num_tokens": 87290144.0,
|
|
"step": 47450
|
|
},
|
|
{
|
|
"entropy": 5.490617132186889,
|
|
"epoch": 3.9638322753090547,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003503571817211272,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.2400125190615654,
|
|
"num_tokens": 87299854.0,
|
|
"step": 47455
|
|
},
|
|
{
|
|
"entropy": 5.526895141601562,
|
|
"epoch": 3.9642499164717675,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003503291304109866,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.2290707215666771,
|
|
"num_tokens": 87308969.0,
|
|
"step": 47460
|
|
},
|
|
{
|
|
"entropy": 5.5223651885986325,
|
|
"epoch": 3.9646675576344803,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035030107778211893,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.24858309030532838,
|
|
"num_tokens": 87317851.0,
|
|
"step": 47465
|
|
},
|
|
{
|
|
"entropy": 5.542439222335815,
|
|
"epoch": 3.9650851987971936,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003502730238350153,
|
|
"loss": 4.7964,
|
|
"mean_token_accuracy": 0.2271001785993576,
|
|
"num_tokens": 87327326.0,
|
|
"step": 47470
|
|
},
|
|
{
|
|
"entropy": 5.4897449016571045,
|
|
"epoch": 3.9655028399599064,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035024496857016666,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.24341727793216705,
|
|
"num_tokens": 87335929.0,
|
|
"step": 47475
|
|
},
|
|
{
|
|
"entropy": 5.577138185501099,
|
|
"epoch": 3.9659204811226196,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003502169119880643,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.2397911936044693,
|
|
"num_tokens": 87345052.0,
|
|
"step": 47480
|
|
},
|
|
{
|
|
"entropy": 5.545518398284912,
|
|
"epoch": 3.9663381222853324,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003501888540891994,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.23721176385879517,
|
|
"num_tokens": 87354042.0,
|
|
"step": 47485
|
|
},
|
|
{
|
|
"entropy": 5.467542505264282,
|
|
"epoch": 3.9667557634480453,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00035016079487406313,
|
|
"loss": 4.6116,
|
|
"mean_token_accuracy": 0.24245160669088364,
|
|
"num_tokens": 87362826.0,
|
|
"step": 47490
|
|
},
|
|
{
|
|
"entropy": 5.521589851379394,
|
|
"epoch": 3.9671734046107585,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003501327343431467,
|
|
"loss": 4.7572,
|
|
"mean_token_accuracy": 0.2375553473830223,
|
|
"num_tokens": 87371944.0,
|
|
"step": 47495
|
|
},
|
|
{
|
|
"entropy": 5.488776111602784,
|
|
"epoch": 3.9675910457734713,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00035010467249694117,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.2401389494538307,
|
|
"num_tokens": 87380953.0,
|
|
"step": 47500
|
|
},
|
|
{
|
|
"entropy": 5.488856935501099,
|
|
"epoch": 3.9680086869361846,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003500766093359381,
|
|
"loss": 4.6751,
|
|
"mean_token_accuracy": 0.24231395423412322,
|
|
"num_tokens": 87390641.0,
|
|
"step": 47505
|
|
},
|
|
{
|
|
"entropy": 5.57805609703064,
|
|
"epoch": 3.9684263280988974,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003500485448606285,
|
|
"loss": 4.8076,
|
|
"mean_token_accuracy": 0.22489850521087645,
|
|
"num_tokens": 87400702.0,
|
|
"step": 47510
|
|
},
|
|
{
|
|
"entropy": 5.6067389965057375,
|
|
"epoch": 3.96884396926161,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035002047907150386,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.22639195919036864,
|
|
"num_tokens": 87410284.0,
|
|
"step": 47515
|
|
},
|
|
{
|
|
"entropy": 5.542735528945923,
|
|
"epoch": 3.9692616104243235,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00034999241196905537,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.2348056584596634,
|
|
"num_tokens": 87419381.0,
|
|
"step": 47520
|
|
},
|
|
{
|
|
"entropy": 5.553313827514648,
|
|
"epoch": 3.9696792515870363,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003499643435537745,
|
|
"loss": 4.7278,
|
|
"mean_token_accuracy": 0.23862732201814651,
|
|
"num_tokens": 87428064.0,
|
|
"step": 47525
|
|
},
|
|
{
|
|
"entropy": 5.47311372756958,
|
|
"epoch": 3.9700968927497495,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00034993627382615247,
|
|
"loss": 4.6152,
|
|
"mean_token_accuracy": 0.23967579901218414,
|
|
"num_tokens": 87436743.0,
|
|
"step": 47530
|
|
},
|
|
{
|
|
"entropy": 5.591102981567383,
|
|
"epoch": 3.9705145339124623,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003499082027866809,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.22684895396232604,
|
|
"num_tokens": 87446542.0,
|
|
"step": 47535
|
|
},
|
|
{
|
|
"entropy": 5.534079313278198,
|
|
"epoch": 3.970932175075175,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003498801304358509,
|
|
"loss": 4.6466,
|
|
"mean_token_accuracy": 0.24702494591474533,
|
|
"num_tokens": 87455477.0,
|
|
"step": 47540
|
|
},
|
|
{
|
|
"entropy": 5.55239520072937,
|
|
"epoch": 3.9713498162378884,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003498520567741543,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.24018536508083344,
|
|
"num_tokens": 87463740.0,
|
|
"step": 47545
|
|
},
|
|
{
|
|
"entropy": 5.486389827728272,
|
|
"epoch": 3.9717674574006017,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003498239818020822,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.23854980170726775,
|
|
"num_tokens": 87474057.0,
|
|
"step": 47550
|
|
},
|
|
{
|
|
"entropy": 5.538063287734985,
|
|
"epoch": 3.9721850985633145,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003497959055201263,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.234189735352993,
|
|
"num_tokens": 87483530.0,
|
|
"step": 47555
|
|
},
|
|
{
|
|
"entropy": 5.64644227027893,
|
|
"epoch": 3.9726027397260273,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003497678279287779,
|
|
"loss": 4.8331,
|
|
"mean_token_accuracy": 0.2245311975479126,
|
|
"num_tokens": 87492636.0,
|
|
"step": 47560
|
|
},
|
|
{
|
|
"entropy": 5.64250636100769,
|
|
"epoch": 3.9730203808887405,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003497397490285288,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.24663293063640596,
|
|
"num_tokens": 87501682.0,
|
|
"step": 47565
|
|
},
|
|
{
|
|
"entropy": 5.576906061172485,
|
|
"epoch": 3.9734380220514534,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003497116688198704,
|
|
"loss": 4.793,
|
|
"mean_token_accuracy": 0.2273445963859558,
|
|
"num_tokens": 87511110.0,
|
|
"step": 47570
|
|
},
|
|
{
|
|
"entropy": 5.461032342910767,
|
|
"epoch": 3.9738556632141666,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00034968358730329437,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.2454881936311722,
|
|
"num_tokens": 87521111.0,
|
|
"step": 47575
|
|
},
|
|
{
|
|
"entropy": 5.458936405181885,
|
|
"epoch": 3.9742733043768794,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00034965550447929226,
|
|
"loss": 4.7142,
|
|
"mean_token_accuracy": 0.2408081218600273,
|
|
"num_tokens": 87529192.0,
|
|
"step": 47580
|
|
},
|
|
{
|
|
"entropy": 5.509632682800293,
|
|
"epoch": 3.9746909455395922,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00034962742034835555,
|
|
"loss": 4.7661,
|
|
"mean_token_accuracy": 0.23196028918027878,
|
|
"num_tokens": 87538647.0,
|
|
"step": 47585
|
|
},
|
|
{
|
|
"entropy": 5.646673059463501,
|
|
"epoch": 3.9751085867023055,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00034959933491097604,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.2253822863101959,
|
|
"num_tokens": 87548388.0,
|
|
"step": 47590
|
|
},
|
|
{
|
|
"entropy": 5.582321739196777,
|
|
"epoch": 3.9755262278650183,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00034957124816764547,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.2384186714887619,
|
|
"num_tokens": 87557420.0,
|
|
"step": 47595
|
|
},
|
|
{
|
|
"entropy": 5.490015029907227,
|
|
"epoch": 3.9759438690277316,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034954316011885536,
|
|
"loss": 4.6776,
|
|
"mean_token_accuracy": 0.23883649706840515,
|
|
"num_tokens": 87567106.0,
|
|
"step": 47600
|
|
},
|
|
{
|
|
"entropy": 5.588913488388061,
|
|
"epoch": 3.9763615101904444,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003495150707650975,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.23880086243152618,
|
|
"num_tokens": 87575554.0,
|
|
"step": 47605
|
|
},
|
|
{
|
|
"entropy": 5.602553415298462,
|
|
"epoch": 3.976779151353157,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00034948698010686376,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.22950246334075927,
|
|
"num_tokens": 87584271.0,
|
|
"step": 47610
|
|
},
|
|
{
|
|
"entropy": 5.516066265106201,
|
|
"epoch": 3.9771967925158704,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003494588881446456,
|
|
"loss": 4.6588,
|
|
"mean_token_accuracy": 0.24252056926488877,
|
|
"num_tokens": 87593381.0,
|
|
"step": 47615
|
|
},
|
|
{
|
|
"entropy": 5.490424728393554,
|
|
"epoch": 3.9776144336785833,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003494307948789351,
|
|
"loss": 4.6828,
|
|
"mean_token_accuracy": 0.2394156575202942,
|
|
"num_tokens": 87601963.0,
|
|
"step": 47620
|
|
},
|
|
{
|
|
"entropy": 5.572941160202026,
|
|
"epoch": 3.9780320748412965,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003494027003102239,
|
|
"loss": 4.7464,
|
|
"mean_token_accuracy": 0.23831535279750823,
|
|
"num_tokens": 87611757.0,
|
|
"step": 47625
|
|
},
|
|
{
|
|
"entropy": 5.586921548843383,
|
|
"epoch": 3.9784497160040093,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0003493746044390039,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.23274154514074324,
|
|
"num_tokens": 87620437.0,
|
|
"step": 47630
|
|
},
|
|
{
|
|
"entropy": 5.5089129447937015,
|
|
"epoch": 3.978867357166722,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003493465072657668,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.23538764119148253,
|
|
"num_tokens": 87630052.0,
|
|
"step": 47635
|
|
},
|
|
{
|
|
"entropy": 5.5060100078582765,
|
|
"epoch": 3.9792849983294354,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00034931840879100473,
|
|
"loss": 4.6477,
|
|
"mean_token_accuracy": 0.23916171193122865,
|
|
"num_tokens": 87638918.0,
|
|
"step": 47640
|
|
},
|
|
{
|
|
"entropy": 5.477821254730225,
|
|
"epoch": 3.979702639492148,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00034929030901520946,
|
|
"loss": 4.6391,
|
|
"mean_token_accuracy": 0.245033860206604,
|
|
"num_tokens": 87647434.0,
|
|
"step": 47645
|
|
},
|
|
{
|
|
"entropy": 5.559617567062378,
|
|
"epoch": 3.9801202806548615,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003492622079388728,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.23581964373588563,
|
|
"num_tokens": 87656621.0,
|
|
"step": 47650
|
|
},
|
|
{
|
|
"entropy": 5.459442377090454,
|
|
"epoch": 3.9805379218175743,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003492341055624869,
|
|
"loss": 4.6717,
|
|
"mean_token_accuracy": 0.24059924036264418,
|
|
"num_tokens": 87665385.0,
|
|
"step": 47655
|
|
},
|
|
{
|
|
"entropy": 5.4759820938110355,
|
|
"epoch": 3.980955562980287,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003492060018865437,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.23627015501260756,
|
|
"num_tokens": 87674631.0,
|
|
"step": 47660
|
|
},
|
|
{
|
|
"entropy": 5.502330636978149,
|
|
"epoch": 3.9813732041430003,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00034917789691153495,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.2383585348725319,
|
|
"num_tokens": 87683894.0,
|
|
"step": 47665
|
|
},
|
|
{
|
|
"entropy": 5.529679870605468,
|
|
"epoch": 3.9817908453057136,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00034914979063795294,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.24394585341215133,
|
|
"num_tokens": 87693016.0,
|
|
"step": 47670
|
|
},
|
|
{
|
|
"entropy": 5.544891786575318,
|
|
"epoch": 3.9822084864684264,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00034912168306628944,
|
|
"loss": 4.7391,
|
|
"mean_token_accuracy": 0.22845658659934998,
|
|
"num_tokens": 87701572.0,
|
|
"step": 47675
|
|
},
|
|
{
|
|
"entropy": 5.554018354415893,
|
|
"epoch": 3.982626127631139,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0003490935741970368,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.2294766500592232,
|
|
"num_tokens": 87711558.0,
|
|
"step": 47680
|
|
},
|
|
{
|
|
"entropy": 5.541130685806275,
|
|
"epoch": 3.9830437687938525,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003490654640306869,
|
|
"loss": 4.6346,
|
|
"mean_token_accuracy": 0.2482346549630165,
|
|
"num_tokens": 87720455.0,
|
|
"step": 47685
|
|
},
|
|
{
|
|
"entropy": 5.614235496520996,
|
|
"epoch": 3.9834614099565653,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00034903735256773197,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.2356983467936516,
|
|
"num_tokens": 87730451.0,
|
|
"step": 47690
|
|
},
|
|
{
|
|
"entropy": 5.512338781356812,
|
|
"epoch": 3.9838790511192785,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0003490092398086639,
|
|
"loss": 4.6621,
|
|
"mean_token_accuracy": 0.24940031617879868,
|
|
"num_tokens": 87739061.0,
|
|
"step": 47695
|
|
},
|
|
{
|
|
"entropy": 5.53852858543396,
|
|
"epoch": 3.9842966922819913,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00034898112575397516,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.23216709345579148,
|
|
"num_tokens": 87748616.0,
|
|
"step": 47700
|
|
},
|
|
{
|
|
"entropy": 5.6014539241790775,
|
|
"epoch": 3.984714333444704,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003489530104041577,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.23466943204402924,
|
|
"num_tokens": 87758661.0,
|
|
"step": 47705
|
|
},
|
|
{
|
|
"entropy": 5.542220687866211,
|
|
"epoch": 3.9851319746074174,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003489248937597038,
|
|
"loss": 4.6749,
|
|
"mean_token_accuracy": 0.2482052654027939,
|
|
"num_tokens": 87769183.0,
|
|
"step": 47710
|
|
},
|
|
{
|
|
"entropy": 5.568816184997559,
|
|
"epoch": 3.9855496157701302,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00034889677582110567,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.23168636858463287,
|
|
"num_tokens": 87778493.0,
|
|
"step": 47715
|
|
},
|
|
{
|
|
"entropy": 5.534080171585083,
|
|
"epoch": 3.9859672569328435,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003488686565888555,
|
|
"loss": 4.7225,
|
|
"mean_token_accuracy": 0.24067620038986207,
|
|
"num_tokens": 87787841.0,
|
|
"step": 47720
|
|
},
|
|
{
|
|
"entropy": 5.546721935272217,
|
|
"epoch": 3.9863848980955563,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00034884053606344564,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.23886690586805343,
|
|
"num_tokens": 87796365.0,
|
|
"step": 47725
|
|
},
|
|
{
|
|
"entropy": 5.480382108688355,
|
|
"epoch": 3.986802539258269,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003488124142453682,
|
|
"loss": 4.7301,
|
|
"mean_token_accuracy": 0.23419813066720963,
|
|
"num_tokens": 87805427.0,
|
|
"step": 47730
|
|
},
|
|
{
|
|
"entropy": 5.516640567779541,
|
|
"epoch": 3.9872201804209824,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003487842911351157,
|
|
"loss": 4.6847,
|
|
"mean_token_accuracy": 0.24263983368873596,
|
|
"num_tokens": 87814789.0,
|
|
"step": 47735
|
|
},
|
|
{
|
|
"entropy": 5.591907119750976,
|
|
"epoch": 3.987637821583695,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0003487561667331803,
|
|
"loss": 4.8306,
|
|
"mean_token_accuracy": 0.23188247084617614,
|
|
"num_tokens": 87823710.0,
|
|
"step": 47740
|
|
},
|
|
{
|
|
"entropy": 5.584666395187378,
|
|
"epoch": 3.9880554627464084,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00034872804104005446,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.22838693708181382,
|
|
"num_tokens": 87832796.0,
|
|
"step": 47745
|
|
},
|
|
{
|
|
"entropy": 5.498362827301025,
|
|
"epoch": 3.9884731039091212,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003486999140562305,
|
|
"loss": 4.6556,
|
|
"mean_token_accuracy": 0.23751979917287827,
|
|
"num_tokens": 87842254.0,
|
|
"step": 47750
|
|
},
|
|
{
|
|
"entropy": 5.556963634490967,
|
|
"epoch": 3.988890745071834,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0003486717857822008,
|
|
"loss": 4.7847,
|
|
"mean_token_accuracy": 0.22932332009077072,
|
|
"num_tokens": 87851332.0,
|
|
"step": 47755
|
|
},
|
|
{
|
|
"entropy": 5.5882621765136715,
|
|
"epoch": 3.9893083862345473,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003486436562184578,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.23517911285161971,
|
|
"num_tokens": 87859903.0,
|
|
"step": 47760
|
|
},
|
|
{
|
|
"entropy": 5.593580102920532,
|
|
"epoch": 3.98972602739726,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003486155253654941,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.225529545545578,
|
|
"num_tokens": 87869160.0,
|
|
"step": 47765
|
|
},
|
|
{
|
|
"entropy": 5.569207382202149,
|
|
"epoch": 3.9901436685599734,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003485873932238019,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.23020206540822982,
|
|
"num_tokens": 87877778.0,
|
|
"step": 47770
|
|
},
|
|
{
|
|
"entropy": 5.440618515014648,
|
|
"epoch": 3.990561309722686,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003485592597938738,
|
|
"loss": 4.6018,
|
|
"mean_token_accuracy": 0.24029066264629365,
|
|
"num_tokens": 87886095.0,
|
|
"step": 47775
|
|
},
|
|
{
|
|
"entropy": 5.55976505279541,
|
|
"epoch": 3.990978950885399,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00034853112507620234,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.23034798204898835,
|
|
"num_tokens": 87895661.0,
|
|
"step": 47780
|
|
},
|
|
{
|
|
"entropy": 5.570153760910034,
|
|
"epoch": 3.9913965920481123,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00034850298907128,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.23798589408397675,
|
|
"num_tokens": 87904878.0,
|
|
"step": 47785
|
|
},
|
|
{
|
|
"entropy": 5.556536626815796,
|
|
"epoch": 3.9918142332108255,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00034847485177959937,
|
|
"loss": 4.7208,
|
|
"mean_token_accuracy": 0.2331921637058258,
|
|
"num_tokens": 87913848.0,
|
|
"step": 47790
|
|
},
|
|
{
|
|
"entropy": 5.5273419380187985,
|
|
"epoch": 3.9922318743735383,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034844671320165304,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.23188022077083587,
|
|
"num_tokens": 87923043.0,
|
|
"step": 47795
|
|
},
|
|
{
|
|
"entropy": 5.567064189910889,
|
|
"epoch": 3.992649515536251,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0003484185733379336,
|
|
"loss": 4.7357,
|
|
"mean_token_accuracy": 0.2390316531062126,
|
|
"num_tokens": 87930936.0,
|
|
"step": 47800
|
|
},
|
|
{
|
|
"entropy": 5.582302284240723,
|
|
"epoch": 3.9930671566989644,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00034839043218893364,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.23880552798509597,
|
|
"num_tokens": 87940214.0,
|
|
"step": 47805
|
|
},
|
|
{
|
|
"entropy": 5.538021183013916,
|
|
"epoch": 3.993484797861677,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003483622897551458,
|
|
"loss": 4.7447,
|
|
"mean_token_accuracy": 0.23661387264728545,
|
|
"num_tokens": 87949375.0,
|
|
"step": 47810
|
|
},
|
|
{
|
|
"entropy": 5.552877950668335,
|
|
"epoch": 3.9939024390243905,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003483341460370628,
|
|
"loss": 4.7854,
|
|
"mean_token_accuracy": 0.2385580509901047,
|
|
"num_tokens": 87958785.0,
|
|
"step": 47815
|
|
},
|
|
{
|
|
"entropy": 5.67240948677063,
|
|
"epoch": 3.9943200801871033,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003483060010351773,
|
|
"loss": 4.8539,
|
|
"mean_token_accuracy": 0.22880679965019227,
|
|
"num_tokens": 87968751.0,
|
|
"step": 47820
|
|
},
|
|
{
|
|
"entropy": 5.519354772567749,
|
|
"epoch": 3.994737721349816,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000348277854749982,
|
|
"loss": 4.7256,
|
|
"mean_token_accuracy": 0.2366989314556122,
|
|
"num_tokens": 87977998.0,
|
|
"step": 47825
|
|
},
|
|
{
|
|
"entropy": 5.704370832443237,
|
|
"epoch": 3.9951553625125293,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00034824970718196963,
|
|
"loss": 4.876,
|
|
"mean_token_accuracy": 0.23126902878284455,
|
|
"num_tokens": 87987964.0,
|
|
"step": 47830
|
|
},
|
|
{
|
|
"entropy": 5.608047342300415,
|
|
"epoch": 3.995573003675242,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00034822155833163306,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.23738162219524384,
|
|
"num_tokens": 87997602.0,
|
|
"step": 47835
|
|
},
|
|
{
|
|
"entropy": 5.509395599365234,
|
|
"epoch": 3.9959906448379554,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003481934081994649,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.24507094770669938,
|
|
"num_tokens": 88007107.0,
|
|
"step": 47840
|
|
},
|
|
{
|
|
"entropy": 5.456695604324341,
|
|
"epoch": 3.996408286000668,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000348165256785958,
|
|
"loss": 4.6453,
|
|
"mean_token_accuracy": 0.2458566591143608,
|
|
"num_tokens": 88015223.0,
|
|
"step": 47845
|
|
},
|
|
{
|
|
"entropy": 5.53548493385315,
|
|
"epoch": 3.996825927163381,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003481371040916052,
|
|
"loss": 4.7798,
|
|
"mean_token_accuracy": 0.2350003108382225,
|
|
"num_tokens": 88025854.0,
|
|
"step": 47850
|
|
},
|
|
{
|
|
"entropy": 5.566725158691407,
|
|
"epoch": 3.9972435683260943,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00034810895011689946,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.23675099462270738,
|
|
"num_tokens": 88035814.0,
|
|
"step": 47855
|
|
},
|
|
{
|
|
"entropy": 5.4970110893249515,
|
|
"epoch": 3.997661209488807,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00034808079486233347,
|
|
"loss": 4.6753,
|
|
"mean_token_accuracy": 0.2385697066783905,
|
|
"num_tokens": 88044048.0,
|
|
"step": 47860
|
|
},
|
|
{
|
|
"entropy": 5.602322435379028,
|
|
"epoch": 3.9980788506515204,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00034805263832840024,
|
|
"loss": 4.8121,
|
|
"mean_token_accuracy": 0.23117864429950713,
|
|
"num_tokens": 88053713.0,
|
|
"step": 47865
|
|
},
|
|
{
|
|
"entropy": 5.565943670272827,
|
|
"epoch": 3.998496491814233,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003480244805155926,
|
|
"loss": 4.7018,
|
|
"mean_token_accuracy": 0.24320391863584517,
|
|
"num_tokens": 88063888.0,
|
|
"step": 47870
|
|
},
|
|
{
|
|
"entropy": 5.567736434936523,
|
|
"epoch": 3.998914132976946,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003479963214244036,
|
|
"loss": 4.6669,
|
|
"mean_token_accuracy": 0.24611337333917618,
|
|
"num_tokens": 88073428.0,
|
|
"step": 47875
|
|
},
|
|
{
|
|
"entropy": 5.568379878997803,
|
|
"epoch": 3.9993317741396592,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00034796816105532596,
|
|
"loss": 4.695,
|
|
"mean_token_accuracy": 0.23608846217393875,
|
|
"num_tokens": 88082781.0,
|
|
"step": 47880
|
|
},
|
|
{
|
|
"entropy": 5.531634187698364,
|
|
"epoch": 3.999749415302372,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000347939999408853,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.23806748539209366,
|
|
"num_tokens": 88091401.0,
|
|
"step": 47885
|
|
},
|
|
{
|
|
"entropy": 5.488448238372802,
|
|
"epoch": 4.000167056465085,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003479118364854775,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.23720854818820952,
|
|
"num_tokens": 88100570.0,
|
|
"step": 47890
|
|
},
|
|
{
|
|
"entropy": 5.441144227981567,
|
|
"epoch": 4.000584697627798,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00034788367228569256,
|
|
"loss": 4.6037,
|
|
"mean_token_accuracy": 0.23930398225784302,
|
|
"num_tokens": 88109200.0,
|
|
"step": 47895
|
|
},
|
|
{
|
|
"entropy": 5.450000667572022,
|
|
"epoch": 4.001002338790511,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00034785550680999116,
|
|
"loss": 4.5744,
|
|
"mean_token_accuracy": 0.25295130759477613,
|
|
"num_tokens": 88118244.0,
|
|
"step": 47900
|
|
},
|
|
{
|
|
"entropy": 5.53546633720398,
|
|
"epoch": 4.001419979953225,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00034782734005886647,
|
|
"loss": 4.6583,
|
|
"mean_token_accuracy": 0.2452067881822586,
|
|
"num_tokens": 88127088.0,
|
|
"step": 47905
|
|
},
|
|
{
|
|
"entropy": 5.533985900878906,
|
|
"epoch": 4.001837621115937,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00034779917203281153,
|
|
"loss": 4.6588,
|
|
"mean_token_accuracy": 0.23822623491287231,
|
|
"num_tokens": 88137169.0,
|
|
"step": 47910
|
|
},
|
|
{
|
|
"entropy": 5.533377695083618,
|
|
"epoch": 4.00225526227865,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003477710027323194,
|
|
"loss": 4.7392,
|
|
"mean_token_accuracy": 0.23900602012872696,
|
|
"num_tokens": 88147387.0,
|
|
"step": 47915
|
|
},
|
|
{
|
|
"entropy": 5.5037713050842285,
|
|
"epoch": 4.002672903441363,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003477428321578833,
|
|
"loss": 4.6434,
|
|
"mean_token_accuracy": 0.24965789914131165,
|
|
"num_tokens": 88155930.0,
|
|
"step": 47920
|
|
},
|
|
{
|
|
"entropy": 5.536483907699585,
|
|
"epoch": 4.003090544604076,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00034771466030999635,
|
|
"loss": 4.7178,
|
|
"mean_token_accuracy": 0.24734434634447097,
|
|
"num_tokens": 88165990.0,
|
|
"step": 47925
|
|
},
|
|
{
|
|
"entropy": 5.49782075881958,
|
|
"epoch": 4.00350818576679,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00034768648718915175,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.24265822619199753,
|
|
"num_tokens": 88175912.0,
|
|
"step": 47930
|
|
},
|
|
{
|
|
"entropy": 5.595229959487915,
|
|
"epoch": 4.003925826929502,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003476583127958427,
|
|
"loss": 4.766,
|
|
"mean_token_accuracy": 0.2288928359746933,
|
|
"num_tokens": 88186903.0,
|
|
"step": 47935
|
|
},
|
|
{
|
|
"entropy": 5.646474361419678,
|
|
"epoch": 4.004343468092215,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003476301371305624,
|
|
"loss": 4.7172,
|
|
"mean_token_accuracy": 0.23538950383663176,
|
|
"num_tokens": 88195514.0,
|
|
"step": 47940
|
|
},
|
|
{
|
|
"entropy": 5.581231021881104,
|
|
"epoch": 4.004761109254928,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00034760196019380425,
|
|
"loss": 4.7406,
|
|
"mean_token_accuracy": 0.2376437559723854,
|
|
"num_tokens": 88205099.0,
|
|
"step": 47945
|
|
},
|
|
{
|
|
"entropy": 5.439288091659546,
|
|
"epoch": 4.005178750417641,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003475737819860612,
|
|
"loss": 4.5656,
|
|
"mean_token_accuracy": 0.25154976844787597,
|
|
"num_tokens": 88214065.0,
|
|
"step": 47950
|
|
},
|
|
{
|
|
"entropy": 5.518996620178223,
|
|
"epoch": 4.0055963915803545,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0003475456025078268,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.24623543322086333,
|
|
"num_tokens": 88222471.0,
|
|
"step": 47955
|
|
},
|
|
{
|
|
"entropy": 5.579275131225586,
|
|
"epoch": 4.006014032743067,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003475174217595944,
|
|
"loss": 4.7749,
|
|
"mean_token_accuracy": 0.24314985126256944,
|
|
"num_tokens": 88231190.0,
|
|
"step": 47960
|
|
},
|
|
{
|
|
"entropy": 5.5225239276885985,
|
|
"epoch": 4.00643167390578,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00034748923974185726,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.23900082409381868,
|
|
"num_tokens": 88240738.0,
|
|
"step": 47965
|
|
},
|
|
{
|
|
"entropy": 5.502362012863159,
|
|
"epoch": 4.006849315068493,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00034746105645510857,
|
|
"loss": 4.6616,
|
|
"mean_token_accuracy": 0.24247646778821946,
|
|
"num_tokens": 88250379.0,
|
|
"step": 47970
|
|
},
|
|
{
|
|
"entropy": 5.561009931564331,
|
|
"epoch": 4.007266956231206,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000347432871899842,
|
|
"loss": 4.6971,
|
|
"mean_token_accuracy": 0.23346493691205977,
|
|
"num_tokens": 88260036.0,
|
|
"step": 47975
|
|
},
|
|
{
|
|
"entropy": 5.562392330169677,
|
|
"epoch": 4.0076845973939195,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00034740468607655066,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.2363104060292244,
|
|
"num_tokens": 88268705.0,
|
|
"step": 47980
|
|
},
|
|
{
|
|
"entropy": 5.575228929519653,
|
|
"epoch": 4.008102238556632,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003473764989857283,
|
|
"loss": 4.7381,
|
|
"mean_token_accuracy": 0.23867758065462114,
|
|
"num_tokens": 88278408.0,
|
|
"step": 47985
|
|
},
|
|
{
|
|
"entropy": 5.479887580871582,
|
|
"epoch": 4.008519879719345,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00034734831062786814,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.2478870928287506,
|
|
"num_tokens": 88286348.0,
|
|
"step": 47990
|
|
},
|
|
{
|
|
"entropy": 5.501867580413818,
|
|
"epoch": 4.008937520882058,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003473201210034638,
|
|
"loss": 4.6434,
|
|
"mean_token_accuracy": 0.23702267706394195,
|
|
"num_tokens": 88295769.0,
|
|
"step": 47995
|
|
},
|
|
{
|
|
"entropy": 5.51459493637085,
|
|
"epoch": 4.009355162044771,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003472919301130086,
|
|
"loss": 4.621,
|
|
"mean_token_accuracy": 0.24833889901638032,
|
|
"num_tokens": 88304846.0,
|
|
"step": 48000
|
|
},
|
|
{
|
|
"epoch": 4.009355162044771,
|
|
"eval_entropy": 5.137793726548379,
|
|
"eval_loss": 4.73213529586792,
|
|
"eval_mean_token_accuracy": 0.24812487815048098,
|
|
"eval_num_tokens": 88304846.0,
|
|
"eval_runtime": 20.8403,
|
|
"eval_samples_per_second": 1812.022,
|
|
"eval_steps_per_second": 226.533,
|
|
"step": 48000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119720,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.937553909940224e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|