3b4236fe54
Model: fpadovani/dan-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.25058469762779817,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.944228982925415,
|
|
"epoch": 0.000417641162712997,
|
|
"grad_norm": 14.75,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.2398,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 9371.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.94694414138794,
|
|
"epoch": 0.000835282325425994,
|
|
"grad_norm": 14.8125,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.1961,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 18155.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.961578607559204,
|
|
"epoch": 0.001252923488138991,
|
|
"grad_norm": 15.625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.1818,
|
|
"mean_token_accuracy": 9.380863048136234e-05,
|
|
"num_tokens": 27776.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.998337459564209,
|
|
"epoch": 0.001670564650851988,
|
|
"grad_norm": 17.5,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.9811,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 37166.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.118108034133911,
|
|
"epoch": 0.002088205813564985,
|
|
"grad_norm": 22.125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.6488,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 46667.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.413705348968506,
|
|
"epoch": 0.002505846976277982,
|
|
"grad_norm": 27.5,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.0874,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 55738.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.7129909038543705,
|
|
"epoch": 0.002923488138990979,
|
|
"grad_norm": 29.25,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 12.0634,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 65303.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 9.943841934204102,
|
|
"epoch": 0.003341129301703976,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.9276,
|
|
"mean_token_accuracy": 0.00012578616151586174,
|
|
"num_tokens": 74876.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.703345203399659,
|
|
"epoch": 0.003758770464416973,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.6802,
|
|
"mean_token_accuracy": 0.002392532047815621,
|
|
"num_tokens": 84683.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.740305995941162,
|
|
"epoch": 0.00417641162712997,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.5254,
|
|
"mean_token_accuracy": 0.013313664309680461,
|
|
"num_tokens": 94511.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.734064483642578,
|
|
"epoch": 0.004594052789842967,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.2867,
|
|
"mean_token_accuracy": 0.018075952026993036,
|
|
"num_tokens": 103820.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.681211948394775,
|
|
"epoch": 0.005011693952555964,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.1047,
|
|
"mean_token_accuracy": 0.019883409794420003,
|
|
"num_tokens": 112398.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.702549839019776,
|
|
"epoch": 0.005429335115268961,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.9646,
|
|
"mean_token_accuracy": 0.01945118773728609,
|
|
"num_tokens": 121167.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.730839729309082,
|
|
"epoch": 0.005846976277981958,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.8414,
|
|
"mean_token_accuracy": 0.025720258615911006,
|
|
"num_tokens": 129399.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.728861236572266,
|
|
"epoch": 0.006264617440694955,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.7822,
|
|
"mean_token_accuracy": 0.032033701054751874,
|
|
"num_tokens": 138512.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.722623062133788,
|
|
"epoch": 0.006682258603407952,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.7341,
|
|
"mean_token_accuracy": 0.032669741101562975,
|
|
"num_tokens": 147712.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.71749963760376,
|
|
"epoch": 0.007099899766120949,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.6255,
|
|
"mean_token_accuracy": 0.03035105634480715,
|
|
"num_tokens": 156759.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.71173620223999,
|
|
"epoch": 0.007517540928833946,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5187,
|
|
"mean_token_accuracy": 0.035255284421145915,
|
|
"num_tokens": 166395.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.703879737854004,
|
|
"epoch": 0.007935182091546943,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.3862,
|
|
"mean_token_accuracy": 0.044158879294991495,
|
|
"num_tokens": 174739.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.680936431884765,
|
|
"epoch": 0.00835282325425994,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.2512,
|
|
"mean_token_accuracy": 0.03875316996127367,
|
|
"num_tokens": 183010.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.65852222442627,
|
|
"epoch": 0.008770464416972937,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2045,
|
|
"mean_token_accuracy": 0.040588128939270975,
|
|
"num_tokens": 192589.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.639169883728027,
|
|
"epoch": 0.009188105579685933,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.0572,
|
|
"mean_token_accuracy": 0.0537865225225687,
|
|
"num_tokens": 201638.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.59452133178711,
|
|
"epoch": 0.00960574674239893,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9186,
|
|
"mean_token_accuracy": 0.05064392797648907,
|
|
"num_tokens": 209862.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.544370651245117,
|
|
"epoch": 0.010023387905111928,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8996,
|
|
"mean_token_accuracy": 0.043613025173544887,
|
|
"num_tokens": 218897.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.49176197052002,
|
|
"epoch": 0.010441029067824925,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7626,
|
|
"mean_token_accuracy": 0.05363074168562889,
|
|
"num_tokens": 227682.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.402692413330078,
|
|
"epoch": 0.010858670230537921,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.586,
|
|
"mean_token_accuracy": 0.053992220759391786,
|
|
"num_tokens": 236170.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.307563400268554,
|
|
"epoch": 0.011276311393250919,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5381,
|
|
"mean_token_accuracy": 0.0543564785271883,
|
|
"num_tokens": 245710.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.217035388946533,
|
|
"epoch": 0.011693952555963916,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.368,
|
|
"mean_token_accuracy": 0.05643460154533386,
|
|
"num_tokens": 254751.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.128512001037597,
|
|
"epoch": 0.012111593718676913,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.241,
|
|
"mean_token_accuracy": 0.05597202591598034,
|
|
"num_tokens": 264210.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.00536880493164,
|
|
"epoch": 0.01252923488138991,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1832,
|
|
"mean_token_accuracy": 0.0563384834676981,
|
|
"num_tokens": 272944.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.889774703979493,
|
|
"epoch": 0.012946876044102907,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.0239,
|
|
"mean_token_accuracy": 0.055541551858186725,
|
|
"num_tokens": 281311.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.758612728118896,
|
|
"epoch": 0.013364517206815904,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9127,
|
|
"mean_token_accuracy": 0.059244291856884956,
|
|
"num_tokens": 289701.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.522632217407226,
|
|
"epoch": 0.013782158369528901,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.9089,
|
|
"mean_token_accuracy": 0.05390802845358848,
|
|
"num_tokens": 299459.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.387851905822753,
|
|
"epoch": 0.014199799532241897,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.8314,
|
|
"mean_token_accuracy": 0.05658908933401108,
|
|
"num_tokens": 309343.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.159295749664306,
|
|
"epoch": 0.014617440694954895,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.7869,
|
|
"mean_token_accuracy": 0.0535435926169157,
|
|
"num_tokens": 318840.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.917513465881347,
|
|
"epoch": 0.015035081857667892,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.5732,
|
|
"mean_token_accuracy": 0.056347102671861646,
|
|
"num_tokens": 328689.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.685413837432861,
|
|
"epoch": 0.01545272302038089,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.658,
|
|
"mean_token_accuracy": 0.05352019853889942,
|
|
"num_tokens": 338209.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.488839721679687,
|
|
"epoch": 0.015870364183093885,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.4968,
|
|
"mean_token_accuracy": 0.056180522218346594,
|
|
"num_tokens": 347270.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.256251239776612,
|
|
"epoch": 0.016288005345806884,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.5217,
|
|
"mean_token_accuracy": 0.057517141476273535,
|
|
"num_tokens": 356366.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.176424980163574,
|
|
"epoch": 0.01670564650851988,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.4756,
|
|
"mean_token_accuracy": 0.059065777063369754,
|
|
"num_tokens": 365980.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.109168100357056,
|
|
"epoch": 0.017123287671232876,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4352,
|
|
"mean_token_accuracy": 0.06301593109965324,
|
|
"num_tokens": 374591.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.09407901763916,
|
|
"epoch": 0.017540928833945875,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4288,
|
|
"mean_token_accuracy": 0.06486969366669655,
|
|
"num_tokens": 383250.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.025069379806519,
|
|
"epoch": 0.01795856999665887,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.3621,
|
|
"mean_token_accuracy": 0.06629893258213997,
|
|
"num_tokens": 391502.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.9847424030303955,
|
|
"epoch": 0.018376211159371866,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.2782,
|
|
"mean_token_accuracy": 0.06931861937046051,
|
|
"num_tokens": 400225.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.029051160812378,
|
|
"epoch": 0.018793852322084866,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.4779,
|
|
"mean_token_accuracy": 0.060866087675094604,
|
|
"num_tokens": 410008.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.031083345413208,
|
|
"epoch": 0.01921149348479786,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.381,
|
|
"mean_token_accuracy": 0.0702624622732401,
|
|
"num_tokens": 418979.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.950044965744018,
|
|
"epoch": 0.01962913464751086,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.349,
|
|
"mean_token_accuracy": 0.06797430105507374,
|
|
"num_tokens": 428139.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.96306037902832,
|
|
"epoch": 0.020046775810223856,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.2651,
|
|
"mean_token_accuracy": 0.07591628283262253,
|
|
"num_tokens": 437113.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.929630136489868,
|
|
"epoch": 0.020464416972936852,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.4462,
|
|
"mean_token_accuracy": 0.06979386620223522,
|
|
"num_tokens": 446879.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.925119638442993,
|
|
"epoch": 0.02088205813564985,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.33,
|
|
"mean_token_accuracy": 0.07119030728936196,
|
|
"num_tokens": 456362.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.896007394790649,
|
|
"epoch": 0.021299699298362847,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.157,
|
|
"mean_token_accuracy": 0.07790606319904328,
|
|
"num_tokens": 464930.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.96244444847107,
|
|
"epoch": 0.021717340461075842,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.3203,
|
|
"mean_token_accuracy": 0.07410374954342842,
|
|
"num_tokens": 474303.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.917203140258789,
|
|
"epoch": 0.02213498162378884,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.2993,
|
|
"mean_token_accuracy": 0.0734116319566965,
|
|
"num_tokens": 483750.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.86039023399353,
|
|
"epoch": 0.022552622786501837,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.199,
|
|
"mean_token_accuracy": 0.07768494263291359,
|
|
"num_tokens": 493325.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.840238094329834,
|
|
"epoch": 0.022970263949214833,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.1762,
|
|
"mean_token_accuracy": 0.07519763223826885,
|
|
"num_tokens": 501907.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.810028219223023,
|
|
"epoch": 0.023387905111927832,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1942,
|
|
"mean_token_accuracy": 0.0795279961079359,
|
|
"num_tokens": 511522.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.749888896942139,
|
|
"epoch": 0.023805546274640828,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.1636,
|
|
"mean_token_accuracy": 0.07597449868917465,
|
|
"num_tokens": 521287.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.849759721755982,
|
|
"epoch": 0.024223187437353827,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.2325,
|
|
"mean_token_accuracy": 0.07516792006790637,
|
|
"num_tokens": 530631.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.650192070007324,
|
|
"epoch": 0.024640828600066823,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.1083,
|
|
"mean_token_accuracy": 0.08667415156960487,
|
|
"num_tokens": 540386.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.79657678604126,
|
|
"epoch": 0.02505846976277982,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.191,
|
|
"mean_token_accuracy": 0.07905804216861725,
|
|
"num_tokens": 550121.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.630661725997925,
|
|
"epoch": 0.025476110925492818,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.048,
|
|
"mean_token_accuracy": 0.08168927729129791,
|
|
"num_tokens": 559460.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.653521871566772,
|
|
"epoch": 0.025893752088205813,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0115,
|
|
"mean_token_accuracy": 0.08255561292171479,
|
|
"num_tokens": 568392.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.603034496307373,
|
|
"epoch": 0.02631139325091881,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.0908,
|
|
"mean_token_accuracy": 0.07983561903238297,
|
|
"num_tokens": 578248.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.682858037948608,
|
|
"epoch": 0.026729034413631808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.157,
|
|
"mean_token_accuracy": 0.07829831764101983,
|
|
"num_tokens": 588164.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.5797460079193115,
|
|
"epoch": 0.027146675576344804,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.0789,
|
|
"mean_token_accuracy": 0.08381804451346397,
|
|
"num_tokens": 598715.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.650176906585694,
|
|
"epoch": 0.027564316739057803,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.0161,
|
|
"mean_token_accuracy": 0.09236654937267304,
|
|
"num_tokens": 606939.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.4912495613098145,
|
|
"epoch": 0.0279819579017708,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.1029,
|
|
"mean_token_accuracy": 0.0873373556882143,
|
|
"num_tokens": 615803.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.667604541778564,
|
|
"epoch": 0.028399599064483794,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.9664,
|
|
"mean_token_accuracy": 0.08756924346089363,
|
|
"num_tokens": 624730.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.603380632400513,
|
|
"epoch": 0.028817240227196794,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.0542,
|
|
"mean_token_accuracy": 0.08866709396243096,
|
|
"num_tokens": 634082.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.52916407585144,
|
|
"epoch": 0.02923488138990979,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.0332,
|
|
"mean_token_accuracy": 0.08419890776276588,
|
|
"num_tokens": 643367.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.499692583084107,
|
|
"epoch": 0.029652522552622785,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.8535,
|
|
"mean_token_accuracy": 0.08740218952298165,
|
|
"num_tokens": 651861.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.492964124679565,
|
|
"epoch": 0.030070163715335784,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.9752,
|
|
"mean_token_accuracy": 0.08579764813184738,
|
|
"num_tokens": 661064.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.502609062194824,
|
|
"epoch": 0.03048780487804878,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.9488,
|
|
"mean_token_accuracy": 0.0932283952832222,
|
|
"num_tokens": 669299.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.401155567169189,
|
|
"epoch": 0.03090544604076178,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.0171,
|
|
"mean_token_accuracy": 0.08307098634541035,
|
|
"num_tokens": 678631.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.472736454010009,
|
|
"epoch": 0.03132308720347477,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.0131,
|
|
"mean_token_accuracy": 0.08543515279889106,
|
|
"num_tokens": 688511.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.527131605148315,
|
|
"epoch": 0.03174072836618777,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.9657,
|
|
"mean_token_accuracy": 0.08108578622341156,
|
|
"num_tokens": 697956.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.438411712646484,
|
|
"epoch": 0.03215836952890077,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8724,
|
|
"mean_token_accuracy": 0.08787695616483689,
|
|
"num_tokens": 706779.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.325165557861328,
|
|
"epoch": 0.03257601069161377,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.8617,
|
|
"mean_token_accuracy": 0.09062610566616058,
|
|
"num_tokens": 715749.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.425607204437256,
|
|
"epoch": 0.03299365185432676,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.8375,
|
|
"mean_token_accuracy": 0.0908269003033638,
|
|
"num_tokens": 724756.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.373869371414185,
|
|
"epoch": 0.03341129301703976,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8659,
|
|
"mean_token_accuracy": 0.09110177978873253,
|
|
"num_tokens": 733288.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.444917821884156,
|
|
"epoch": 0.03382893417975276,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.9685,
|
|
"mean_token_accuracy": 0.08536023795604705,
|
|
"num_tokens": 741629.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.3436695575714115,
|
|
"epoch": 0.03424657534246575,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9068,
|
|
"mean_token_accuracy": 0.08802182823419571,
|
|
"num_tokens": 751336.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.426488780975342,
|
|
"epoch": 0.03466421650517875,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.9733,
|
|
"mean_token_accuracy": 0.08576110526919364,
|
|
"num_tokens": 759725.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.417571353912353,
|
|
"epoch": 0.03508185766789175,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9582,
|
|
"mean_token_accuracy": 0.08887427300214767,
|
|
"num_tokens": 769752.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.324219417572022,
|
|
"epoch": 0.03549949883060474,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8629,
|
|
"mean_token_accuracy": 0.08838045299053192,
|
|
"num_tokens": 779124.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.344010305404663,
|
|
"epoch": 0.03591713999331774,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8149,
|
|
"mean_token_accuracy": 0.09638451412320137,
|
|
"num_tokens": 788892.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.214268350601197,
|
|
"epoch": 0.03633478115603074,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7784,
|
|
"mean_token_accuracy": 0.09481111764907837,
|
|
"num_tokens": 798265.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.317943811416626,
|
|
"epoch": 0.03675242231874373,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7438,
|
|
"mean_token_accuracy": 0.09948835447430611,
|
|
"num_tokens": 806896.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.3143962860107425,
|
|
"epoch": 0.03717006348145673,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.8058,
|
|
"mean_token_accuracy": 0.09371909499168396,
|
|
"num_tokens": 815540.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.221705627441406,
|
|
"epoch": 0.03758770464416973,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8558,
|
|
"mean_token_accuracy": 0.08694771379232406,
|
|
"num_tokens": 824555.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.346810579299927,
|
|
"epoch": 0.03800534580688272,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8838,
|
|
"mean_token_accuracy": 0.09503390341997146,
|
|
"num_tokens": 833414.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.228864622116089,
|
|
"epoch": 0.03842298696959572,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.745,
|
|
"mean_token_accuracy": 0.09891379103064538,
|
|
"num_tokens": 842644.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.261135673522949,
|
|
"epoch": 0.03884062813230872,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.7796,
|
|
"mean_token_accuracy": 0.09051957502961158,
|
|
"num_tokens": 851786.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.189091730117798,
|
|
"epoch": 0.03925826929502172,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8274,
|
|
"mean_token_accuracy": 0.09392543509602547,
|
|
"num_tokens": 861508.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.204404687881469,
|
|
"epoch": 0.03967591045773471,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.7046,
|
|
"mean_token_accuracy": 0.09566405564546585,
|
|
"num_tokens": 870433.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.245524454116821,
|
|
"epoch": 0.04009355162044771,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.8033,
|
|
"mean_token_accuracy": 0.09623450264334679,
|
|
"num_tokens": 879059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.304554224014282,
|
|
"epoch": 0.04051119278316071,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.8465,
|
|
"mean_token_accuracy": 0.09020947441458702,
|
|
"num_tokens": 888009.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.111552095413208,
|
|
"epoch": 0.040928833945873704,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7091,
|
|
"mean_token_accuracy": 0.09530647322535515,
|
|
"num_tokens": 897335.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.2552978515625,
|
|
"epoch": 0.0413464751085867,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.7299,
|
|
"mean_token_accuracy": 0.09859334379434585,
|
|
"num_tokens": 905802.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.216646766662597,
|
|
"epoch": 0.0417641162712997,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7167,
|
|
"mean_token_accuracy": 0.09858945608139039,
|
|
"num_tokens": 914836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.100709247589111,
|
|
"epoch": 0.042181757434012694,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6645,
|
|
"mean_token_accuracy": 0.09969677850604057,
|
|
"num_tokens": 924254.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.183725643157959,
|
|
"epoch": 0.04259939859672569,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.7576,
|
|
"mean_token_accuracy": 0.09866931736469269,
|
|
"num_tokens": 933841.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.210815715789795,
|
|
"epoch": 0.04301703975943869,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.8149,
|
|
"mean_token_accuracy": 0.0937366984784603,
|
|
"num_tokens": 943304.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.095678329467773,
|
|
"epoch": 0.043434680922151685,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6426,
|
|
"mean_token_accuracy": 0.09861454665660858,
|
|
"num_tokens": 952915.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.156992769241333,
|
|
"epoch": 0.043852322084864684,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6932,
|
|
"mean_token_accuracy": 0.09782055467367172,
|
|
"num_tokens": 962752.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.15832552909851,
|
|
"epoch": 0.04426996324757768,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7124,
|
|
"mean_token_accuracy": 0.09217726364731789,
|
|
"num_tokens": 971240.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.168659973144531,
|
|
"epoch": 0.044687604410290675,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.7519,
|
|
"mean_token_accuracy": 0.09481079205870628,
|
|
"num_tokens": 981391.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.195070505142212,
|
|
"epoch": 0.045105245573003674,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7498,
|
|
"mean_token_accuracy": 0.09649497717618942,
|
|
"num_tokens": 990551.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.086696815490723,
|
|
"epoch": 0.045522886735716674,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6753,
|
|
"mean_token_accuracy": 0.10147869288921356,
|
|
"num_tokens": 999593.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.119489288330078,
|
|
"epoch": 0.045940527898429666,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7394,
|
|
"mean_token_accuracy": 0.09457549154758453,
|
|
"num_tokens": 1008785.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.081824779510498,
|
|
"epoch": 0.046358169061142665,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.7256,
|
|
"mean_token_accuracy": 0.0977080836892128,
|
|
"num_tokens": 1016815.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.124262952804566,
|
|
"epoch": 0.046775810223855664,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6273,
|
|
"mean_token_accuracy": 0.09984842911362649,
|
|
"num_tokens": 1026182.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.061550188064575,
|
|
"epoch": 0.04719345138656866,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5498,
|
|
"mean_token_accuracy": 0.10488305762410163,
|
|
"num_tokens": 1034032.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.058889532089234,
|
|
"epoch": 0.047611092549281656,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7444,
|
|
"mean_token_accuracy": 0.09858610928058624,
|
|
"num_tokens": 1043493.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.081225299835205,
|
|
"epoch": 0.048028733711994655,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6467,
|
|
"mean_token_accuracy": 0.10488652363419533,
|
|
"num_tokens": 1052989.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.103153085708618,
|
|
"epoch": 0.048446374874707654,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6193,
|
|
"mean_token_accuracy": 0.100984375923872,
|
|
"num_tokens": 1061803.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.087803888320923,
|
|
"epoch": 0.048864016037420646,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7207,
|
|
"mean_token_accuracy": 0.09783147796988487,
|
|
"num_tokens": 1071227.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.093145227432251,
|
|
"epoch": 0.049281657200133645,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.7154,
|
|
"mean_token_accuracy": 0.10207850188016891,
|
|
"num_tokens": 1080082.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.990021800994873,
|
|
"epoch": 0.049699298362846644,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5626,
|
|
"mean_token_accuracy": 0.10718206688761711,
|
|
"num_tokens": 1089750.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.936739349365235,
|
|
"epoch": 0.05011693952555964,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.5546,
|
|
"mean_token_accuracy": 0.10501954108476638,
|
|
"num_tokens": 1098691.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.053757810592652,
|
|
"epoch": 0.050534580688272636,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.5961,
|
|
"mean_token_accuracy": 0.10269566178321839,
|
|
"num_tokens": 1107602.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.988081264495849,
|
|
"epoch": 0.050952221850985635,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5094,
|
|
"mean_token_accuracy": 0.10492742285132409,
|
|
"num_tokens": 1116426.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.099151086807251,
|
|
"epoch": 0.05136986301369863,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6837,
|
|
"mean_token_accuracy": 0.10082755610346794,
|
|
"num_tokens": 1126221.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.922530031204223,
|
|
"epoch": 0.051787504176411626,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.5676,
|
|
"mean_token_accuracy": 0.10399623438715935,
|
|
"num_tokens": 1135662.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.000867414474487,
|
|
"epoch": 0.052205145339124626,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6522,
|
|
"mean_token_accuracy": 0.10379877239465714,
|
|
"num_tokens": 1143963.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.910499048233032,
|
|
"epoch": 0.05262278650183762,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5471,
|
|
"mean_token_accuracy": 0.1115996465086937,
|
|
"num_tokens": 1152470.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.002635765075683,
|
|
"epoch": 0.05304042766455062,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5138,
|
|
"mean_token_accuracy": 0.10561447665095329,
|
|
"num_tokens": 1161257.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.011125802993774,
|
|
"epoch": 0.053458068827263616,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6179,
|
|
"mean_token_accuracy": 0.10046471804380416,
|
|
"num_tokens": 1170969.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 7.024777126312256,
|
|
"epoch": 0.053875709989976615,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.7546,
|
|
"mean_token_accuracy": 0.10059637054800988,
|
|
"num_tokens": 1181127.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.979152011871338,
|
|
"epoch": 0.05429335115268961,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.5445,
|
|
"mean_token_accuracy": 0.10627811849117279,
|
|
"num_tokens": 1190260.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.932449388504028,
|
|
"epoch": 0.05471099231540261,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.6163,
|
|
"mean_token_accuracy": 0.10629051998257637,
|
|
"num_tokens": 1200013.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.959189987182617,
|
|
"epoch": 0.055128633478115606,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5578,
|
|
"mean_token_accuracy": 0.1079456403851509,
|
|
"num_tokens": 1209239.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.908866500854492,
|
|
"epoch": 0.0555462746408286,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.4939,
|
|
"mean_token_accuracy": 0.10315626636147499,
|
|
"num_tokens": 1218552.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.846392631530762,
|
|
"epoch": 0.0559639158035416,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.557,
|
|
"mean_token_accuracy": 0.10559443160891532,
|
|
"num_tokens": 1227632.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.971360492706299,
|
|
"epoch": 0.056381556966254597,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.59,
|
|
"mean_token_accuracy": 0.10625778958201408,
|
|
"num_tokens": 1236433.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.848383378982544,
|
|
"epoch": 0.05679919812896759,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6224,
|
|
"mean_token_accuracy": 0.09530000388622284,
|
|
"num_tokens": 1245700.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.936568307876587,
|
|
"epoch": 0.05721683929168059,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.451,
|
|
"mean_token_accuracy": 0.10879322364926339,
|
|
"num_tokens": 1254206.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.84785647392273,
|
|
"epoch": 0.05763448045439359,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.5067,
|
|
"mean_token_accuracy": 0.11103252843022346,
|
|
"num_tokens": 1263302.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.9186759948730465,
|
|
"epoch": 0.05805212161710658,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.555,
|
|
"mean_token_accuracy": 0.11069672629237175,
|
|
"num_tokens": 1272998.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.80730710029602,
|
|
"epoch": 0.05846976277981958,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5205,
|
|
"mean_token_accuracy": 0.10760543420910836,
|
|
"num_tokens": 1281955.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.894368362426758,
|
|
"epoch": 0.05888740394253258,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.5413,
|
|
"mean_token_accuracy": 0.1049070693552494,
|
|
"num_tokens": 1291219.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.867767763137818,
|
|
"epoch": 0.05930504510524557,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5563,
|
|
"mean_token_accuracy": 0.10610216856002808,
|
|
"num_tokens": 1300963.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.923541641235351,
|
|
"epoch": 0.05972268626795857,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5669,
|
|
"mean_token_accuracy": 0.10349256247282028,
|
|
"num_tokens": 1310112.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.8491448879241945,
|
|
"epoch": 0.06014032743067157,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.501,
|
|
"mean_token_accuracy": 0.11320272982120513,
|
|
"num_tokens": 1319309.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.741468000411987,
|
|
"epoch": 0.06055796859338457,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4675,
|
|
"mean_token_accuracy": 0.10969400852918625,
|
|
"num_tokens": 1329049.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.756487131118774,
|
|
"epoch": 0.06097560975609756,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3257,
|
|
"mean_token_accuracy": 0.11157802790403366,
|
|
"num_tokens": 1337770.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.703513860702515,
|
|
"epoch": 0.06139325091881056,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.11474933475255966,
|
|
"num_tokens": 1346705.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.771881055831909,
|
|
"epoch": 0.06181089208152356,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4697,
|
|
"mean_token_accuracy": 0.106501704454422,
|
|
"num_tokens": 1354860.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.815874862670898,
|
|
"epoch": 0.06222853324423655,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.4437,
|
|
"mean_token_accuracy": 0.11245461031794549,
|
|
"num_tokens": 1364140.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.8553221225738525,
|
|
"epoch": 0.06264617440694954,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5912,
|
|
"mean_token_accuracy": 0.10352180451154709,
|
|
"num_tokens": 1373645.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.804048633575439,
|
|
"epoch": 0.06306381556966255,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.4578,
|
|
"mean_token_accuracy": 0.11486915424466133,
|
|
"num_tokens": 1383291.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.777978563308716,
|
|
"epoch": 0.06348145673237554,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4021,
|
|
"mean_token_accuracy": 0.11272331476211547,
|
|
"num_tokens": 1391172.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.718217420578003,
|
|
"epoch": 0.06389909789508853,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3903,
|
|
"mean_token_accuracy": 0.11387034431099892,
|
|
"num_tokens": 1400864.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.734544563293457,
|
|
"epoch": 0.06431673905780154,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4421,
|
|
"mean_token_accuracy": 0.11549821272492408,
|
|
"num_tokens": 1410570.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.7772174835205075,
|
|
"epoch": 0.06473438022051453,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.11346649378538132,
|
|
"num_tokens": 1419536.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.61550006866455,
|
|
"epoch": 0.06515202138322754,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.3284,
|
|
"mean_token_accuracy": 0.1189441479742527,
|
|
"num_tokens": 1428000.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.729035377502441,
|
|
"epoch": 0.06556966254594053,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.5179,
|
|
"mean_token_accuracy": 0.11673909649252892,
|
|
"num_tokens": 1437789.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.7100263118743895,
|
|
"epoch": 0.06598730370865352,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.3385,
|
|
"mean_token_accuracy": 0.11243527829647064,
|
|
"num_tokens": 1446848.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.658129739761352,
|
|
"epoch": 0.06640494487136653,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3964,
|
|
"mean_token_accuracy": 0.11076711565256118,
|
|
"num_tokens": 1455749.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.6773820400238035,
|
|
"epoch": 0.06682258603407952,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.318,
|
|
"mean_token_accuracy": 0.11754591464996338,
|
|
"num_tokens": 1464556.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.685335445404053,
|
|
"epoch": 0.06724022719679251,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4215,
|
|
"mean_token_accuracy": 0.11340176910161973,
|
|
"num_tokens": 1473617.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.737184619903564,
|
|
"epoch": 0.06765786835950552,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4597,
|
|
"mean_token_accuracy": 0.11323800832033157,
|
|
"num_tokens": 1483006.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.7530170440673825,
|
|
"epoch": 0.06807550952221851,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.4705,
|
|
"mean_token_accuracy": 0.10952020063996315,
|
|
"num_tokens": 1493009.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.672597074508667,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3574,
|
|
"mean_token_accuracy": 0.11739298403263092,
|
|
"num_tokens": 1501261.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.6765588283538815,
|
|
"epoch": 0.06891079184764451,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4492,
|
|
"mean_token_accuracy": 0.11198581531643867,
|
|
"num_tokens": 1511623.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.677420949935913,
|
|
"epoch": 0.0693284330103575,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4494,
|
|
"mean_token_accuracy": 0.10618537515401841,
|
|
"num_tokens": 1521741.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.656988143920898,
|
|
"epoch": 0.0697460741730705,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.3866,
|
|
"mean_token_accuracy": 0.11220621392130851,
|
|
"num_tokens": 1530988.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.581060457229614,
|
|
"epoch": 0.0701637153357835,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.2383,
|
|
"mean_token_accuracy": 0.1149817444384098,
|
|
"num_tokens": 1539415.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.736028957366943,
|
|
"epoch": 0.07058135649849649,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4412,
|
|
"mean_token_accuracy": 0.1137430302798748,
|
|
"num_tokens": 1547969.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.564602851867676,
|
|
"epoch": 0.07099899766120948,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.11980320662260055,
|
|
"num_tokens": 1557526.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.555064153671265,
|
|
"epoch": 0.07141663882392249,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.2604,
|
|
"mean_token_accuracy": 0.12150657400488854,
|
|
"num_tokens": 1565982.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.5531515121459964,
|
|
"epoch": 0.07183427998663548,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.12056252211332322,
|
|
"num_tokens": 1574492.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.53031177520752,
|
|
"epoch": 0.07225192114934847,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2788,
|
|
"mean_token_accuracy": 0.11661688834428788,
|
|
"num_tokens": 1583726.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.618681621551514,
|
|
"epoch": 0.07266956231206148,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3043,
|
|
"mean_token_accuracy": 0.11185830906033516,
|
|
"num_tokens": 1593780.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.555753469467163,
|
|
"epoch": 0.07308720347477447,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.11970926225185394,
|
|
"num_tokens": 1602746.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.615863084793091,
|
|
"epoch": 0.07350484463748747,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3353,
|
|
"mean_token_accuracy": 0.1214637279510498,
|
|
"num_tokens": 1611767.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.630537700653076,
|
|
"epoch": 0.07392248580020047,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.4031,
|
|
"mean_token_accuracy": 0.12145772501826287,
|
|
"num_tokens": 1621568.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.681979560852051,
|
|
"epoch": 0.07434012696291346,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.3366,
|
|
"mean_token_accuracy": 0.12460207119584084,
|
|
"num_tokens": 1630650.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.63215217590332,
|
|
"epoch": 0.07475776812562646,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3467,
|
|
"mean_token_accuracy": 0.11655501201748848,
|
|
"num_tokens": 1640482.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.57461371421814,
|
|
"epoch": 0.07517540928833946,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3777,
|
|
"mean_token_accuracy": 0.11941920891404152,
|
|
"num_tokens": 1649344.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.6421778202056885,
|
|
"epoch": 0.07559305045105245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3096,
|
|
"mean_token_accuracy": 0.12080781757831574,
|
|
"num_tokens": 1658962.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.565168476104736,
|
|
"epoch": 0.07601069161376545,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.3148,
|
|
"mean_token_accuracy": 0.12183948084712029,
|
|
"num_tokens": 1668615.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.573621845245361,
|
|
"epoch": 0.07642833277647845,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2734,
|
|
"mean_token_accuracy": 0.12021931409835815,
|
|
"num_tokens": 1679282.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.5133349895477295,
|
|
"epoch": 0.07684597393919144,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3597,
|
|
"mean_token_accuracy": 0.12050894126296044,
|
|
"num_tokens": 1688362.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.551096725463867,
|
|
"epoch": 0.07726361510190444,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2584,
|
|
"mean_token_accuracy": 0.11896604299545288,
|
|
"num_tokens": 1697593.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.589361953735351,
|
|
"epoch": 0.07768125626461744,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.3227,
|
|
"mean_token_accuracy": 0.12139411941170693,
|
|
"num_tokens": 1706961.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.611653614044189,
|
|
"epoch": 0.07809889742733044,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3515,
|
|
"mean_token_accuracy": 0.1260267861187458,
|
|
"num_tokens": 1716222.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.465685606002808,
|
|
"epoch": 0.07851653859004344,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.2154,
|
|
"mean_token_accuracy": 0.11723333075642586,
|
|
"num_tokens": 1726750.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.595513200759887,
|
|
"epoch": 0.07893417975275643,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3318,
|
|
"mean_token_accuracy": 0.11234179660677909,
|
|
"num_tokens": 1736262.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.523676586151123,
|
|
"epoch": 0.07935182091546943,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.342,
|
|
"mean_token_accuracy": 0.12143515646457673,
|
|
"num_tokens": 1745555.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.409244871139526,
|
|
"epoch": 0.07976946207818243,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2088,
|
|
"mean_token_accuracy": 0.1247611589729786,
|
|
"num_tokens": 1754107.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.638109350204468,
|
|
"epoch": 0.08018710324089542,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.389,
|
|
"mean_token_accuracy": 0.11902901157736778,
|
|
"num_tokens": 1762982.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.475300741195679,
|
|
"epoch": 0.08060474440360842,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.12456510663032531,
|
|
"num_tokens": 1772545.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.663013553619384,
|
|
"epoch": 0.08102238556632142,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.4068,
|
|
"mean_token_accuracy": 0.11605887189507484,
|
|
"num_tokens": 1782052.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.443525791168213,
|
|
"epoch": 0.08144002672903441,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2043,
|
|
"mean_token_accuracy": 0.12791636884212493,
|
|
"num_tokens": 1791682.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.452620172500611,
|
|
"epoch": 0.08185766789174741,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2055,
|
|
"mean_token_accuracy": 0.1278427518904209,
|
|
"num_tokens": 1800526.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.595154523849487,
|
|
"epoch": 0.08227530905446041,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3582,
|
|
"mean_token_accuracy": 0.12327518835663795,
|
|
"num_tokens": 1810062.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.507117128372192,
|
|
"epoch": 0.0826929502171734,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.3231,
|
|
"mean_token_accuracy": 0.1312553495168686,
|
|
"num_tokens": 1818909.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.483727598190308,
|
|
"epoch": 0.0831105913798864,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.282,
|
|
"mean_token_accuracy": 0.12424813508987427,
|
|
"num_tokens": 1827978.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.446569299697876,
|
|
"epoch": 0.0835282325425994,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2372,
|
|
"mean_token_accuracy": 0.12770728915929794,
|
|
"num_tokens": 1837955.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.493737745285034,
|
|
"epoch": 0.0839458737053124,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004999999987395534,
|
|
"loss": 6.3469,
|
|
"mean_token_accuracy": 0.11529407426714897,
|
|
"num_tokens": 1847699.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.606112098693847,
|
|
"epoch": 0.08436351486802539,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999936189888,
|
|
"loss": 6.2756,
|
|
"mean_token_accuracy": 0.12251131236553192,
|
|
"num_tokens": 1856490.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.418572616577149,
|
|
"epoch": 0.0847811560307384,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999999845595285,
|
|
"loss": 6.2846,
|
|
"mean_token_accuracy": 0.12404887601733208,
|
|
"num_tokens": 1865644.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.5010144233703615,
|
|
"epoch": 0.08519879719345139,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999999715611727,
|
|
"loss": 6.2203,
|
|
"mean_token_accuracy": 0.1302325703203678,
|
|
"num_tokens": 1874450.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.401221656799317,
|
|
"epoch": 0.08561643835616438,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999999546239215,
|
|
"loss": 6.2216,
|
|
"mean_token_accuracy": 0.1253162756562233,
|
|
"num_tokens": 1883259.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.503570652008056,
|
|
"epoch": 0.08603407951887738,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999999337477753,
|
|
"loss": 6.3041,
|
|
"mean_token_accuracy": 0.11902791410684585,
|
|
"num_tokens": 1891897.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.500441360473633,
|
|
"epoch": 0.08645172068159038,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999089327344,
|
|
"loss": 6.2862,
|
|
"mean_token_accuracy": 0.1212472915649414,
|
|
"num_tokens": 1901011.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.40726375579834,
|
|
"epoch": 0.08686936184430337,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999998801787993,
|
|
"loss": 6.1837,
|
|
"mean_token_accuracy": 0.13080133870244026,
|
|
"num_tokens": 1910132.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.537573909759521,
|
|
"epoch": 0.08728700300701638,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999998474859704,
|
|
"loss": 6.3178,
|
|
"mean_token_accuracy": 0.12691309154033661,
|
|
"num_tokens": 1919938.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.34345645904541,
|
|
"epoch": 0.08770464416972937,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999998108542483,
|
|
"loss": 6.1791,
|
|
"mean_token_accuracy": 0.12733794674277304,
|
|
"num_tokens": 1928199.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.4469976902008055,
|
|
"epoch": 0.08812228533244236,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999997702836339,
|
|
"loss": 6.1611,
|
|
"mean_token_accuracy": 0.12794166281819344,
|
|
"num_tokens": 1937133.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.510084438323974,
|
|
"epoch": 0.08853992649515537,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999997257741274,
|
|
"loss": 6.3356,
|
|
"mean_token_accuracy": 0.12451440691947938,
|
|
"num_tokens": 1946580.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.4161351203918455,
|
|
"epoch": 0.08895756765786836,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049999967732573,
|
|
"loss": 6.2346,
|
|
"mean_token_accuracy": 0.12813472747802734,
|
|
"num_tokens": 1955413.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.572496318817139,
|
|
"epoch": 0.08937520882058135,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999996249384425,
|
|
"loss": 6.3134,
|
|
"mean_token_accuracy": 0.12880465313792228,
|
|
"num_tokens": 1964716.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.361472511291504,
|
|
"epoch": 0.08979284998329436,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999995686122657,
|
|
"loss": 6.1731,
|
|
"mean_token_accuracy": 0.13375702425837516,
|
|
"num_tokens": 1974081.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.319162797927857,
|
|
"epoch": 0.09021049114600735,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004999995083472006,
|
|
"loss": 6.1591,
|
|
"mean_token_accuracy": 0.12707530632615088,
|
|
"num_tokens": 1983035.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.4332092761993405,
|
|
"epoch": 0.09062813230872034,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999994441432481,
|
|
"loss": 6.1721,
|
|
"mean_token_accuracy": 0.13475777059793473,
|
|
"num_tokens": 1992475.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.325397729873657,
|
|
"epoch": 0.09104577347143335,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999993760004097,
|
|
"loss": 6.2343,
|
|
"mean_token_accuracy": 0.12572435140609742,
|
|
"num_tokens": 2002729.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.269658946990967,
|
|
"epoch": 0.09146341463414634,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999993039186864,
|
|
"loss": 6.0865,
|
|
"mean_token_accuracy": 0.13097318336367608,
|
|
"num_tokens": 2011319.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.446812629699707,
|
|
"epoch": 0.09188105579685933,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999992278980794,
|
|
"loss": 6.13,
|
|
"mean_token_accuracy": 0.12895696312189103,
|
|
"num_tokens": 2020456.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.271724033355713,
|
|
"epoch": 0.09229869695957234,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999991479385901,
|
|
"loss": 6.2195,
|
|
"mean_token_accuracy": 0.1341036967933178,
|
|
"num_tokens": 2029417.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.4861917972564695,
|
|
"epoch": 0.09271633812228533,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999990640402198,
|
|
"loss": 6.2979,
|
|
"mean_token_accuracy": 0.12562437877058982,
|
|
"num_tokens": 2039290.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.4251697063446045,
|
|
"epoch": 0.09313397928499834,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999989762029701,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.13544357791543007,
|
|
"num_tokens": 2048485.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.2083420753479,
|
|
"epoch": 0.09355162044771133,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999988844268425,
|
|
"loss": 6.096,
|
|
"mean_token_accuracy": 0.13170384764671325,
|
|
"num_tokens": 2057131.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.312107372283935,
|
|
"epoch": 0.09396926161042432,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999987887118387,
|
|
"loss": 6.0797,
|
|
"mean_token_accuracy": 0.13444808647036552,
|
|
"num_tokens": 2066295.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.347876739501953,
|
|
"epoch": 0.09438690277313733,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999986890579602,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.1415345251560211,
|
|
"num_tokens": 2075656.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.335701656341553,
|
|
"epoch": 0.09480454393585032,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999985854652087,
|
|
"loss": 6.2225,
|
|
"mean_token_accuracy": 0.12682175189256667,
|
|
"num_tokens": 2086046.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.416574192047119,
|
|
"epoch": 0.09522218509856331,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999984779335862,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.12994211688637733,
|
|
"num_tokens": 2094808.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.290297937393189,
|
|
"epoch": 0.09563982626127632,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999983664630945,
|
|
"loss": 6.1605,
|
|
"mean_token_accuracy": 0.1330721542239189,
|
|
"num_tokens": 2104155.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.382285833358765,
|
|
"epoch": 0.09605746742398931,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999982510537357,
|
|
"loss": 6.0692,
|
|
"mean_token_accuracy": 0.12856426909565927,
|
|
"num_tokens": 2112517.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.208939743041992,
|
|
"epoch": 0.0964751085867023,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999981317055116,
|
|
"loss": 6.0236,
|
|
"mean_token_accuracy": 0.13144809231162072,
|
|
"num_tokens": 2121355.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.3527082920074465,
|
|
"epoch": 0.09689274974941531,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999980084184244,
|
|
"loss": 6.1534,
|
|
"mean_token_accuracy": 0.13644161820411682,
|
|
"num_tokens": 2129278.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.3879131317138675,
|
|
"epoch": 0.0973103909121283,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999978811924762,
|
|
"loss": 6.2951,
|
|
"mean_token_accuracy": 0.12582162991166115,
|
|
"num_tokens": 2139548.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.277176761627198,
|
|
"epoch": 0.09772803207484129,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999977500276693,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.12778721749782562,
|
|
"num_tokens": 2148765.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.430830717086792,
|
|
"epoch": 0.0981456732375543,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999976149240058,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.1366495445370674,
|
|
"num_tokens": 2157482.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.255828189849853,
|
|
"epoch": 0.09856331440026729,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999974758814884,
|
|
"loss": 6.2152,
|
|
"mean_token_accuracy": 0.1265973374247551,
|
|
"num_tokens": 2167320.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.394571590423584,
|
|
"epoch": 0.09898095556298028,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999973329001193,
|
|
"loss": 6.1659,
|
|
"mean_token_accuracy": 0.12668881118297576,
|
|
"num_tokens": 2175454.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.309787034988403,
|
|
"epoch": 0.09939859672569329,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999971859799009,
|
|
"loss": 6.1164,
|
|
"mean_token_accuracy": 0.12462705001235008,
|
|
"num_tokens": 2184391.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.220657396316528,
|
|
"epoch": 0.09981623788840628,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999970351208361,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.13656294345855713,
|
|
"num_tokens": 2193309.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.33141303062439,
|
|
"epoch": 0.10023387905111927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999968803229275,
|
|
"loss": 6.132,
|
|
"mean_token_accuracy": 0.12762896567583085,
|
|
"num_tokens": 2202057.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.345908117294312,
|
|
"epoch": 0.10065152021383228,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999967215861775,
|
|
"loss": 6.2193,
|
|
"mean_token_accuracy": 0.12862889021635054,
|
|
"num_tokens": 2212384.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.33440523147583,
|
|
"epoch": 0.10106916137654527,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499996558910589,
|
|
"loss": 6.129,
|
|
"mean_token_accuracy": 0.13246983289718628,
|
|
"num_tokens": 2221451.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.197815370559693,
|
|
"epoch": 0.10148680253925826,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499996392296165,
|
|
"loss": 6.033,
|
|
"mean_token_accuracy": 0.13185914009809493,
|
|
"num_tokens": 2230440.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.355322027206421,
|
|
"epoch": 0.10190444370197127,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999962217429083,
|
|
"loss": 6.214,
|
|
"mean_token_accuracy": 0.12665950432419776,
|
|
"num_tokens": 2239985.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.3212282180786135,
|
|
"epoch": 0.10232208486468426,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 6.0842,
|
|
"mean_token_accuracy": 0.13362730666995049,
|
|
"num_tokens": 2250391.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.305384016036987,
|
|
"epoch": 0.10273972602739725,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499995868819909,
|
|
"loss": 6.1996,
|
|
"mean_token_accuracy": 0.1324283190071583,
|
|
"num_tokens": 2260620.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.320593690872192,
|
|
"epoch": 0.10315736719011026,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999956864501725,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.12899876162409782,
|
|
"num_tokens": 2271176.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.355190849304199,
|
|
"epoch": 0.10357500835282325,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999955001416156,
|
|
"loss": 6.0567,
|
|
"mean_token_accuracy": 0.1392730712890625,
|
|
"num_tokens": 2280371.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.190901041030884,
|
|
"epoch": 0.10399264951553625,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999953098942417,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.13370997533202172,
|
|
"num_tokens": 2289015.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.2859964847564695,
|
|
"epoch": 0.10441029067824925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999951157080541,
|
|
"loss": 6.1068,
|
|
"mean_token_accuracy": 0.13385709300637244,
|
|
"num_tokens": 2297409.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.135534811019897,
|
|
"epoch": 0.10482793184096224,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999949175830561,
|
|
"loss": 6.1245,
|
|
"mean_token_accuracy": 0.12929951921105384,
|
|
"num_tokens": 2307017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.280382251739502,
|
|
"epoch": 0.10524557300367524,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999947155192514,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.1417563498020172,
|
|
"num_tokens": 2316014.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.253998756408691,
|
|
"epoch": 0.10566321416638824,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999945095166433,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.13147094696760178,
|
|
"num_tokens": 2326326.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.383511114120483,
|
|
"epoch": 0.10608085532910123,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999942995752354,
|
|
"loss": 6.1693,
|
|
"mean_token_accuracy": 0.1279841721057892,
|
|
"num_tokens": 2335108.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.264583396911621,
|
|
"epoch": 0.10649849649181423,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999940856950315,
|
|
"loss": 6.0791,
|
|
"mean_token_accuracy": 0.14134034141898155,
|
|
"num_tokens": 2343971.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.292309951782227,
|
|
"epoch": 0.10691613765452723,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999938678760354,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.13392335250973703,
|
|
"num_tokens": 2353742.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.289759016036987,
|
|
"epoch": 0.10733377881724022,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999936461182507,
|
|
"loss": 6.0966,
|
|
"mean_token_accuracy": 0.13741502091288565,
|
|
"num_tokens": 2363629.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.082193899154663,
|
|
"epoch": 0.10775141997995323,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999934204216814,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.1403780050575733,
|
|
"num_tokens": 2372705.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.2366783618927,
|
|
"epoch": 0.10816906114266622,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999931907863315,
|
|
"loss": 6.0658,
|
|
"mean_token_accuracy": 0.13578577116131782,
|
|
"num_tokens": 2382136.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.113440036773682,
|
|
"epoch": 0.10858670230537922,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499992957212205,
|
|
"loss": 6.0356,
|
|
"mean_token_accuracy": 0.1353696718811989,
|
|
"num_tokens": 2391060.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.3979072093963625,
|
|
"epoch": 0.10900434346809222,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999927196993059,
|
|
"loss": 6.1711,
|
|
"mean_token_accuracy": 0.13628476485610008,
|
|
"num_tokens": 2399885.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.263845205307007,
|
|
"epoch": 0.10942198463080521,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999924782476384,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.1464387968182564,
|
|
"num_tokens": 2409654.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.226789665222168,
|
|
"epoch": 0.1098396257935182,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999922328572068,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.13425977975130082,
|
|
"num_tokens": 2419342.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.150572347640991,
|
|
"epoch": 0.11025726695623121,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999919835280154,
|
|
"loss": 5.9804,
|
|
"mean_token_accuracy": 0.1443939872086048,
|
|
"num_tokens": 2428845.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.273833227157593,
|
|
"epoch": 0.1106749081189442,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999917302600684,
|
|
"loss": 5.9739,
|
|
"mean_token_accuracy": 0.14326085448265075,
|
|
"num_tokens": 2437134.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.0786871910095215,
|
|
"epoch": 0.1110925492816572,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999914730533704,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.14700671806931495,
|
|
"num_tokens": 2445438.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.22350287437439,
|
|
"epoch": 0.1115101904443702,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999912119079258,
|
|
"loss": 6.1506,
|
|
"mean_token_accuracy": 0.1359838679432869,
|
|
"num_tokens": 2455039.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.229891204833985,
|
|
"epoch": 0.1119278316070832,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999909468237393,
|
|
"loss": 6.0765,
|
|
"mean_token_accuracy": 0.13616930097341537,
|
|
"num_tokens": 2465170.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.1581672668457035,
|
|
"epoch": 0.11234547276979619,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999906778008153,
|
|
"loss": 5.8308,
|
|
"mean_token_accuracy": 0.14951538890600205,
|
|
"num_tokens": 2473688.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.1050516128540036,
|
|
"epoch": 0.11276311393250919,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999904048391588,
|
|
"loss": 6.0805,
|
|
"mean_token_accuracy": 0.13373313397169112,
|
|
"num_tokens": 2482335.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.243770885467529,
|
|
"epoch": 0.11318075509522219,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999901279387743,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.14334997087717055,
|
|
"num_tokens": 2491808.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.295271968841552,
|
|
"epoch": 0.11359839625793518,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999898470996669,
|
|
"loss": 6.1569,
|
|
"mean_token_accuracy": 0.12944946438074112,
|
|
"num_tokens": 2501422.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.184634590148926,
|
|
"epoch": 0.11401603742064818,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999895623218415,
|
|
"loss": 5.9515,
|
|
"mean_token_accuracy": 0.1408703289926052,
|
|
"num_tokens": 2511201.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.188165283203125,
|
|
"epoch": 0.11443367858336118,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999892736053027,
|
|
"loss": 5.9929,
|
|
"mean_token_accuracy": 0.13730614483356476,
|
|
"num_tokens": 2519798.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.183836936950684,
|
|
"epoch": 0.11485131974607417,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999889809500561,
|
|
"loss": 5.968,
|
|
"mean_token_accuracy": 0.14003934487700462,
|
|
"num_tokens": 2529177.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.234930992126465,
|
|
"epoch": 0.11526896090878717,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999886843561065,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.14338480234146117,
|
|
"num_tokens": 2537571.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.02715220451355,
|
|
"epoch": 0.11568660207150017,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999883838234592,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.14644728004932403,
|
|
"num_tokens": 2546258.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.149686002731324,
|
|
"epoch": 0.11610424323421316,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999880793521194,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.1373589113354683,
|
|
"num_tokens": 2555862.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.014897727966309,
|
|
"epoch": 0.11652188439692616,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999877709420924,
|
|
"loss": 5.9175,
|
|
"mean_token_accuracy": 0.14411035925149918,
|
|
"num_tokens": 2564583.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.16389479637146,
|
|
"epoch": 0.11693952555963916,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999874585933837,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.1459191247820854,
|
|
"num_tokens": 2574217.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.194282054901123,
|
|
"epoch": 0.11735716672235215,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999871423059987,
|
|
"loss": 5.9063,
|
|
"mean_token_accuracy": 0.1440393716096878,
|
|
"num_tokens": 2582821.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.116659116744995,
|
|
"epoch": 0.11777480788506516,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499986822079943,
|
|
"loss": 6.0746,
|
|
"mean_token_accuracy": 0.13738386183977128,
|
|
"num_tokens": 2592748.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.222877502441406,
|
|
"epoch": 0.11819244904777815,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999864979152221,
|
|
"loss": 5.9736,
|
|
"mean_token_accuracy": 0.1457105740904808,
|
|
"num_tokens": 2602053.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.020002746582032,
|
|
"epoch": 0.11861009021049114,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999861698118417,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.13822002336382866,
|
|
"num_tokens": 2610557.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.204063892364502,
|
|
"epoch": 0.11902773137320415,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999858377698076,
|
|
"loss": 5.9384,
|
|
"mean_token_accuracy": 0.13854485303163527,
|
|
"num_tokens": 2619628.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.294986391067505,
|
|
"epoch": 0.11944537253591714,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999855017891256,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.13476530238986015,
|
|
"num_tokens": 2629284.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.102528619766235,
|
|
"epoch": 0.11986301369863013,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999851618698017,
|
|
"loss": 6.0164,
|
|
"mean_token_accuracy": 0.14004518166184426,
|
|
"num_tokens": 2638001.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.149356412887573,
|
|
"epoch": 0.12028065486134314,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999848180118416,
|
|
"loss": 6.0075,
|
|
"mean_token_accuracy": 0.1504116952419281,
|
|
"num_tokens": 2647071.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.189749431610108,
|
|
"epoch": 0.12069829602405613,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999844702152516,
|
|
"loss": 5.9865,
|
|
"mean_token_accuracy": 0.14875612705945968,
|
|
"num_tokens": 2655826.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.086092138290406,
|
|
"epoch": 0.12111593718676913,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999841184800374,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.15078829377889633,
|
|
"num_tokens": 2664431.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.010515975952148,
|
|
"epoch": 0.12153357834948213,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999837628062055,
|
|
"loss": 5.7622,
|
|
"mean_token_accuracy": 0.15104235708713531,
|
|
"num_tokens": 2673631.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.052291202545166,
|
|
"epoch": 0.12195121951219512,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999834031937621,
|
|
"loss": 6.047,
|
|
"mean_token_accuracy": 0.14088533371686934,
|
|
"num_tokens": 2683363.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.159712791442871,
|
|
"epoch": 0.12236886067490813,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999830396427133,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.13705805838108062,
|
|
"num_tokens": 2692533.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.13315601348877,
|
|
"epoch": 0.12278650183762112,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999826721530657,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.14548553973436357,
|
|
"num_tokens": 2701211.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.203657341003418,
|
|
"epoch": 0.12320414300033411,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999823007248255,
|
|
"loss": 5.9974,
|
|
"mean_token_accuracy": 0.1427378311753273,
|
|
"num_tokens": 2709543.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.1870471954345705,
|
|
"epoch": 0.12362178416304712,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999819253579992,
|
|
"loss": 6.0064,
|
|
"mean_token_accuracy": 0.13959514498710632,
|
|
"num_tokens": 2718336.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.127546596527099,
|
|
"epoch": 0.12403942532576011,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999815460525938,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.14745968729257583,
|
|
"num_tokens": 2726504.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.105073881149292,
|
|
"epoch": 0.1244570664884731,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999811628086155,
|
|
"loss": 5.9567,
|
|
"mean_token_accuracy": 0.1415959879755974,
|
|
"num_tokens": 2736076.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.055798721313477,
|
|
"epoch": 0.1248747076511861,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499980775626071,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.14771346226334572,
|
|
"num_tokens": 2745497.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.116729402542115,
|
|
"epoch": 0.12529234881389908,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999803845049674,
|
|
"loss": 6.0194,
|
|
"mean_token_accuracy": 0.14392556473612786,
|
|
"num_tokens": 2754455.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.213052797317505,
|
|
"epoch": 0.1257099899766121,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999799894453112,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.14362442642450332,
|
|
"num_tokens": 2763603.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.095961046218872,
|
|
"epoch": 0.1261276311393251,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999795904471095,
|
|
"loss": 5.9026,
|
|
"mean_token_accuracy": 0.14689221382141113,
|
|
"num_tokens": 2772152.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.245121812820434,
|
|
"epoch": 0.12654527230203808,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999791875103694,
|
|
"loss": 6.0004,
|
|
"mean_token_accuracy": 0.1482790566980839,
|
|
"num_tokens": 2781459.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.167483615875244,
|
|
"epoch": 0.12696291346475108,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999787806350977,
|
|
"loss": 5.9445,
|
|
"mean_token_accuracy": 0.14450416788458825,
|
|
"num_tokens": 2791177.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.988239908218384,
|
|
"epoch": 0.1273805546274641,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999783698213016,
|
|
"loss": 5.9481,
|
|
"mean_token_accuracy": 0.15092730671167373,
|
|
"num_tokens": 2800543.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.051485967636109,
|
|
"epoch": 0.12779819579017707,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999779550689885,
|
|
"loss": 5.7947,
|
|
"mean_token_accuracy": 0.1509787768125534,
|
|
"num_tokens": 2809301.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.191277027130127,
|
|
"epoch": 0.12821583695289007,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999775363781654,
|
|
"loss": 5.9932,
|
|
"mean_token_accuracy": 0.14468340426683426,
|
|
"num_tokens": 2818269.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.0712157726287845,
|
|
"epoch": 0.12863347811560308,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999771137488395,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.14732339829206467,
|
|
"num_tokens": 2827170.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.983927059173584,
|
|
"epoch": 0.12905111927831608,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999766871810188,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.14839889854192734,
|
|
"num_tokens": 2835320.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.071327495574951,
|
|
"epoch": 0.12946876044102906,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999762566747101,
|
|
"loss": 5.9244,
|
|
"mean_token_accuracy": 0.14501172602176665,
|
|
"num_tokens": 2843755.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.151789903640747,
|
|
"epoch": 0.12988640160374207,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999758222299214,
|
|
"loss": 5.9715,
|
|
"mean_token_accuracy": 0.13980228453874588,
|
|
"num_tokens": 2853462.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.041283750534058,
|
|
"epoch": 0.13030404276645507,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999753838466601,
|
|
"loss": 5.8737,
|
|
"mean_token_accuracy": 0.1441491112112999,
|
|
"num_tokens": 2863041.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.223154211044312,
|
|
"epoch": 0.13072168392916805,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999749415249338,
|
|
"loss": 6.0883,
|
|
"mean_token_accuracy": 0.14627306610345842,
|
|
"num_tokens": 2873019.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.021166467666626,
|
|
"epoch": 0.13113932509188106,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999744952647505,
|
|
"loss": 5.8394,
|
|
"mean_token_accuracy": 0.14528503715991975,
|
|
"num_tokens": 2881467.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.078176975250244,
|
|
"epoch": 0.13155696625459407,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999740450661176,
|
|
"loss": 5.9283,
|
|
"mean_token_accuracy": 0.14148435667157172,
|
|
"num_tokens": 2890914.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.97394208908081,
|
|
"epoch": 0.13197460741730704,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999735909290436,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.15130585730075835,
|
|
"num_tokens": 2901164.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.17360486984253,
|
|
"epoch": 0.13239224858002005,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999731328535358,
|
|
"loss": 5.9837,
|
|
"mean_token_accuracy": 0.14389178678393363,
|
|
"num_tokens": 2910560.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.00739221572876,
|
|
"epoch": 0.13280988974273306,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999726708396026,
|
|
"loss": 5.8006,
|
|
"mean_token_accuracy": 0.15138354450464248,
|
|
"num_tokens": 2918980.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.089150905609131,
|
|
"epoch": 0.13322753090544603,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000499972204887252,
|
|
"loss": 5.9897,
|
|
"mean_token_accuracy": 0.13849136978387833,
|
|
"num_tokens": 2929516.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.0801748752594,
|
|
"epoch": 0.13364517206815904,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999717349964922,
|
|
"loss": 6.068,
|
|
"mean_token_accuracy": 0.13731011226773263,
|
|
"num_tokens": 2940603.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.169479703903198,
|
|
"epoch": 0.13406281323087205,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999712611673313,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.14724995344877242,
|
|
"num_tokens": 2950082.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.934827041625977,
|
|
"epoch": 0.13448045439358502,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999707833997777,
|
|
"loss": 5.7908,
|
|
"mean_token_accuracy": 0.1533707395195961,
|
|
"num_tokens": 2959098.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.161834812164306,
|
|
"epoch": 0.13489809555629803,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999703016938398,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.14561702385544778,
|
|
"num_tokens": 2968585.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.053872299194336,
|
|
"epoch": 0.13531573671901104,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499969816049526,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.14551280438899994,
|
|
"num_tokens": 2978430.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.212032508850098,
|
|
"epoch": 0.13573337788172402,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999693264668446,
|
|
"loss": 5.9962,
|
|
"mean_token_accuracy": 0.13857592716813089,
|
|
"num_tokens": 2988398.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.085241079330444,
|
|
"epoch": 0.13615101904443702,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999688329458045,
|
|
"loss": 6.0168,
|
|
"mean_token_accuracy": 0.14099103808403016,
|
|
"num_tokens": 2999255.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.169172143936157,
|
|
"epoch": 0.13656866020715003,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999683354864141,
|
|
"loss": 5.9099,
|
|
"mean_token_accuracy": 0.14426834136247635,
|
|
"num_tokens": 3008638.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.051702165603638,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999678340886823,
|
|
"loss": 5.9137,
|
|
"mean_token_accuracy": 0.14842754304409028,
|
|
"num_tokens": 3018070.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.950930213928222,
|
|
"epoch": 0.137403942532576,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999673287526176,
|
|
"loss": 5.8784,
|
|
"mean_token_accuracy": 0.15201137959957123,
|
|
"num_tokens": 3027878.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.174559926986694,
|
|
"epoch": 0.13782158369528902,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999668194782291,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.13952327594161035,
|
|
"num_tokens": 3037031.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.233021545410156,
|
|
"epoch": 0.138239224858002,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999663062655257,
|
|
"loss": 6.0016,
|
|
"mean_token_accuracy": 0.14014986380934716,
|
|
"num_tokens": 3046311.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.069745588302612,
|
|
"epoch": 0.138656866020715,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999657891145162,
|
|
"loss": 5.8249,
|
|
"mean_token_accuracy": 0.15104526281356812,
|
|
"num_tokens": 3055108.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.9705235958099365,
|
|
"epoch": 0.139074507183428,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999652680252099,
|
|
"loss": 5.8508,
|
|
"mean_token_accuracy": 0.14930724799633027,
|
|
"num_tokens": 3063492.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.149300765991211,
|
|
"epoch": 0.139492148346141,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999647429976157,
|
|
"loss": 5.9054,
|
|
"mean_token_accuracy": 0.15113156288862228,
|
|
"num_tokens": 3072572.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.122020435333252,
|
|
"epoch": 0.139909789508854,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999642140317429,
|
|
"loss": 5.9546,
|
|
"mean_token_accuracy": 0.14124443158507347,
|
|
"num_tokens": 3082942.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.042447471618653,
|
|
"epoch": 0.140327430671567,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999636811276007,
|
|
"loss": 5.919,
|
|
"mean_token_accuracy": 0.14785890504717827,
|
|
"num_tokens": 3091410.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.153117609024048,
|
|
"epoch": 0.14074507183427998,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999631442851986,
|
|
"loss": 5.9736,
|
|
"mean_token_accuracy": 0.1465502806007862,
|
|
"num_tokens": 3100626.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.026203060150147,
|
|
"epoch": 0.14116271299699298,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999626035045458,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.1571854069828987,
|
|
"num_tokens": 3109339.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.103426456451416,
|
|
"epoch": 0.141580354159706,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999620587856519,
|
|
"loss": 5.914,
|
|
"mean_token_accuracy": 0.14427188262343407,
|
|
"num_tokens": 3118636.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.9886900901794435,
|
|
"epoch": 0.14199799532241897,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999615101285262,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.14374638795852662,
|
|
"num_tokens": 3128162.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.051160144805908,
|
|
"epoch": 0.14241563648513197,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999609575331786,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.1519470438361168,
|
|
"num_tokens": 3136451.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.093698120117187,
|
|
"epoch": 0.14283327764784498,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999604009996186,
|
|
"loss": 5.8842,
|
|
"mean_token_accuracy": 0.1466047689318657,
|
|
"num_tokens": 3146599.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.099306440353393,
|
|
"epoch": 0.14325091881055796,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499959840527856,
|
|
"loss": 5.9379,
|
|
"mean_token_accuracy": 0.14325512945652008,
|
|
"num_tokens": 3155941.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.005642986297607,
|
|
"epoch": 0.14366855997327097,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999592761179007,
|
|
"loss": 5.8656,
|
|
"mean_token_accuracy": 0.15379103869199753,
|
|
"num_tokens": 3164641.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.069437789916992,
|
|
"epoch": 0.14408620113598397,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999587077697624,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.15470442548394203,
|
|
"num_tokens": 3173701.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.939715385437012,
|
|
"epoch": 0.14450384229869695,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999581354834512,
|
|
"loss": 5.7458,
|
|
"mean_token_accuracy": 0.14850927889347076,
|
|
"num_tokens": 3182268.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.929523706436157,
|
|
"epoch": 0.14492148346140996,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499957559258977,
|
|
"loss": 5.8259,
|
|
"mean_token_accuracy": 0.15093481987714769,
|
|
"num_tokens": 3191513.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.022497940063476,
|
|
"epoch": 0.14533912462412296,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049995697909635,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.14721936583518982,
|
|
"num_tokens": 3200580.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.952256393432617,
|
|
"epoch": 0.14575676578683594,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999563949955803,
|
|
"loss": 5.8709,
|
|
"mean_token_accuracy": 0.1540740728378296,
|
|
"num_tokens": 3209053.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.015556478500367,
|
|
"epoch": 0.14617440694954895,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499955806956678,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.14972457140684128,
|
|
"num_tokens": 3218241.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.084406089782715,
|
|
"epoch": 0.14659204811226195,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999552149796536,
|
|
"loss": 5.9255,
|
|
"mean_token_accuracy": 0.14822182059288025,
|
|
"num_tokens": 3227887.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.975216627120972,
|
|
"epoch": 0.14700968927497493,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999546190645175,
|
|
"loss": 5.7331,
|
|
"mean_token_accuracy": 0.15878990590572356,
|
|
"num_tokens": 3237281.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.977021408081055,
|
|
"epoch": 0.14742733043768794,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999540192112799,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.15504969358444215,
|
|
"num_tokens": 3246907.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.893853664398193,
|
|
"epoch": 0.14784497160040094,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999534154199514,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.14786117523908615,
|
|
"num_tokens": 3256312.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.171048641204834,
|
|
"epoch": 0.14826261276311392,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999528076905426,
|
|
"loss": 5.8781,
|
|
"mean_token_accuracy": 0.15021531730890275,
|
|
"num_tokens": 3265554.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.7882325649261475,
|
|
"epoch": 0.14868025392582693,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999521960230641,
|
|
"loss": 5.7149,
|
|
"mean_token_accuracy": 0.1591077446937561,
|
|
"num_tokens": 3274731.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.024976682662964,
|
|
"epoch": 0.14909789508853993,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 5.8542,
|
|
"mean_token_accuracy": 0.14886621683835982,
|
|
"num_tokens": 3283518.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.0305921077728275,
|
|
"epoch": 0.1495155362512529,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499950960873941,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.1539292372763157,
|
|
"num_tokens": 3292244.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.053695440292358,
|
|
"epoch": 0.14993317741396592,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999503373923182,
|
|
"loss": 5.8294,
|
|
"mean_token_accuracy": 0.15408268123865126,
|
|
"num_tokens": 3301198.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.911142015457154,
|
|
"epoch": 0.15035081857667892,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999497099726687,
|
|
"loss": 5.8257,
|
|
"mean_token_accuracy": 0.15286746770143508,
|
|
"num_tokens": 3309983.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.056093406677246,
|
|
"epoch": 0.1507684597393919,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999490786150039,
|
|
"loss": 5.8947,
|
|
"mean_token_accuracy": 0.14988958984613418,
|
|
"num_tokens": 3319313.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.970861577987671,
|
|
"epoch": 0.1511861009021049,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999484433193348,
|
|
"loss": 5.7466,
|
|
"mean_token_accuracy": 0.15159421861171724,
|
|
"num_tokens": 3327497.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.922145032882691,
|
|
"epoch": 0.15160374206481791,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999478040856722,
|
|
"loss": 5.7622,
|
|
"mean_token_accuracy": 0.15839407294988633,
|
|
"num_tokens": 3337029.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.838753938674927,
|
|
"epoch": 0.1520213832275309,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999471609140276,
|
|
"loss": 5.7499,
|
|
"mean_token_accuracy": 0.15191098004579545,
|
|
"num_tokens": 3346243.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.137970495223999,
|
|
"epoch": 0.1524390243902439,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999465138044122,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.14960521906614305,
|
|
"num_tokens": 3354846.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.996419382095337,
|
|
"epoch": 0.1528566655529569,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999458627568373,
|
|
"loss": 5.8623,
|
|
"mean_token_accuracy": 0.1439855642616749,
|
|
"num_tokens": 3364683.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.020885181427002,
|
|
"epoch": 0.15327430671566988,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999452077713144,
|
|
"loss": 5.7839,
|
|
"mean_token_accuracy": 0.15447492599487306,
|
|
"num_tokens": 3374652.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.986085510253906,
|
|
"epoch": 0.1536919478783829,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999445488478547,
|
|
"loss": 5.8018,
|
|
"mean_token_accuracy": 0.1501589760184288,
|
|
"num_tokens": 3384040.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.89569411277771,
|
|
"epoch": 0.1541095890410959,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049994388598647,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.15379735231399536,
|
|
"num_tokens": 3393185.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.9624189853668215,
|
|
"epoch": 0.15452723020380887,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999432191871719,
|
|
"loss": 5.8107,
|
|
"mean_token_accuracy": 0.15432377755641938,
|
|
"num_tokens": 3403077.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.947211456298828,
|
|
"epoch": 0.15494487136652188,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999425484499718,
|
|
"loss": 5.7819,
|
|
"mean_token_accuracy": 0.16086574792861938,
|
|
"num_tokens": 3412165.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.029496955871582,
|
|
"epoch": 0.1553625125292349,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999418737748817,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.14368949756026267,
|
|
"num_tokens": 3421162.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.066939353942871,
|
|
"epoch": 0.15578015369194786,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999411951619134,
|
|
"loss": 5.9092,
|
|
"mean_token_accuracy": 0.146198970079422,
|
|
"num_tokens": 3430363.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.006467866897583,
|
|
"epoch": 0.15619779485466087,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999405126110786,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.14844847470521927,
|
|
"num_tokens": 3439199.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.101349639892578,
|
|
"epoch": 0.15661543601737388,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999398261223895,
|
|
"loss": 5.9561,
|
|
"mean_token_accuracy": 0.1441134199500084,
|
|
"num_tokens": 3448720.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.027431869506836,
|
|
"epoch": 0.15703307718008688,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999391356958579,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.1493662789463997,
|
|
"num_tokens": 3458472.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.976059818267823,
|
|
"epoch": 0.15745071834279986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499938441331496,
|
|
"loss": 5.8454,
|
|
"mean_token_accuracy": 0.14676398932933807,
|
|
"num_tokens": 3467140.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.097150707244873,
|
|
"epoch": 0.15786835950551287,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999377430293159,
|
|
"loss": 5.8452,
|
|
"mean_token_accuracy": 0.15335095673799515,
|
|
"num_tokens": 3476431.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.8885892868042,
|
|
"epoch": 0.15828600066822587,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999370407893299,
|
|
"loss": 5.7525,
|
|
"mean_token_accuracy": 0.14893790632486342,
|
|
"num_tokens": 3485768.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.066452074050903,
|
|
"epoch": 0.15870364183093885,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999363346115501,
|
|
"loss": 5.9003,
|
|
"mean_token_accuracy": 0.14735231101512908,
|
|
"num_tokens": 3495678.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.97677001953125,
|
|
"epoch": 0.15912128299365186,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999356244959893,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.1467648006975651,
|
|
"num_tokens": 3505168.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.975177431106568,
|
|
"epoch": 0.15953892415636486,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999349104426594,
|
|
"loss": 5.8312,
|
|
"mean_token_accuracy": 0.1447260484099388,
|
|
"num_tokens": 3514498.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.0214598178863525,
|
|
"epoch": 0.15995656531907784,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999341924515732,
|
|
"loss": 5.7596,
|
|
"mean_token_accuracy": 0.1468587689101696,
|
|
"num_tokens": 3524617.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.928234100341797,
|
|
"epoch": 0.16037420648179085,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999334705227431,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.15519107580184938,
|
|
"num_tokens": 3533523.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.961508655548096,
|
|
"epoch": 0.16079184764450385,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499932744656182,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.15407586544752122,
|
|
"num_tokens": 3542922.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.024217510223389,
|
|
"epoch": 0.16120948880721683,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999320148519024,
|
|
"loss": 5.8079,
|
|
"mean_token_accuracy": 0.1524025820195675,
|
|
"num_tokens": 3551827.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.900309419631958,
|
|
"epoch": 0.16162712996992984,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999312811099171,
|
|
"loss": 5.7693,
|
|
"mean_token_accuracy": 0.1520832046866417,
|
|
"num_tokens": 3560911.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.964160490036011,
|
|
"epoch": 0.16204477113264285,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999305434302391,
|
|
"loss": 5.8033,
|
|
"mean_token_accuracy": 0.14884971603751182,
|
|
"num_tokens": 3569473.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.934193325042725,
|
|
"epoch": 0.16246241229535582,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499929801812881,
|
|
"loss": 5.7947,
|
|
"mean_token_accuracy": 0.15742168873548507,
|
|
"num_tokens": 3578843.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.9684545516967775,
|
|
"epoch": 0.16288005345806883,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999290562578561,
|
|
"loss": 5.8019,
|
|
"mean_token_accuracy": 0.15691341012716292,
|
|
"num_tokens": 3588304.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.96470685005188,
|
|
"epoch": 0.16329769462078184,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999283067651773,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.14991875737905502,
|
|
"num_tokens": 3598354.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.10321011543274,
|
|
"epoch": 0.16371533578349481,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999275533348577,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.14993757382035255,
|
|
"num_tokens": 3607503.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.818184232711792,
|
|
"epoch": 0.16413297694620782,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999267959669106,
|
|
"loss": 5.7108,
|
|
"mean_token_accuracy": 0.1614347442984581,
|
|
"num_tokens": 3617467.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.997748470306396,
|
|
"epoch": 0.16455061810892083,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999260346613491,
|
|
"loss": 5.7274,
|
|
"mean_token_accuracy": 0.1477570079267025,
|
|
"num_tokens": 3627048.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.856850242614746,
|
|
"epoch": 0.1649682592716338,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999252694181867,
|
|
"loss": 5.7536,
|
|
"mean_token_accuracy": 0.15221063643693925,
|
|
"num_tokens": 3636683.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.8793130874633786,
|
|
"epoch": 0.1653859004343468,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999245002374367,
|
|
"loss": 5.6541,
|
|
"mean_token_accuracy": 0.16297252625226974,
|
|
"num_tokens": 3645231.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.910471391677857,
|
|
"epoch": 0.16580354159705982,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999237271191125,
|
|
"loss": 5.7481,
|
|
"mean_token_accuracy": 0.1537959724664688,
|
|
"num_tokens": 3653851.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.851402044296265,
|
|
"epoch": 0.1662211827597728,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999229500632279,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.15754058510065078,
|
|
"num_tokens": 3662720.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.811029100418091,
|
|
"epoch": 0.1666388239224858,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999221690697961,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.15830501317977905,
|
|
"num_tokens": 3671777.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.900216579437256,
|
|
"epoch": 0.1670564650851988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999213841388312,
|
|
"loss": 5.7487,
|
|
"mean_token_accuracy": 0.16085124611854554,
|
|
"num_tokens": 3681390.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.014535903930664,
|
|
"epoch": 0.16747410624791179,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999205952703466,
|
|
"loss": 5.8095,
|
|
"mean_token_accuracy": 0.15208923071622849,
|
|
"num_tokens": 3690899.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.994240045547485,
|
|
"epoch": 0.1678917474106248,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999198024643563,
|
|
"loss": 5.9006,
|
|
"mean_token_accuracy": 0.14157435148954392,
|
|
"num_tokens": 3699891.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.851044797897339,
|
|
"epoch": 0.1683093885733378,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999190057208741,
|
|
"loss": 5.682,
|
|
"mean_token_accuracy": 0.1597720503807068,
|
|
"num_tokens": 3709860.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.947671413421631,
|
|
"epoch": 0.16872702973605078,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499918205039914,
|
|
"loss": 5.8256,
|
|
"mean_token_accuracy": 0.14998155385255812,
|
|
"num_tokens": 3718896.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.87712082862854,
|
|
"epoch": 0.16914467089876378,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999174004214899,
|
|
"loss": 5.6315,
|
|
"mean_token_accuracy": 0.157985882461071,
|
|
"num_tokens": 3727355.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.853571224212646,
|
|
"epoch": 0.1695623120614768,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999165918656161,
|
|
"loss": 5.7242,
|
|
"mean_token_accuracy": 0.1521446391940117,
|
|
"num_tokens": 3736191.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.971621370315551,
|
|
"epoch": 0.16997995322418977,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999157793723065,
|
|
"loss": 5.7667,
|
|
"mean_token_accuracy": 0.15560206323862075,
|
|
"num_tokens": 3744832.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.861223936080933,
|
|
"epoch": 0.17039759438690277,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999149629415755,
|
|
"loss": 5.7308,
|
|
"mean_token_accuracy": 0.152314256131649,
|
|
"num_tokens": 3753835.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.030371236801147,
|
|
"epoch": 0.17081523554961578,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999141425734374,
|
|
"loss": 5.8026,
|
|
"mean_token_accuracy": 0.15111032724380494,
|
|
"num_tokens": 3762816.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.8637120723724365,
|
|
"epoch": 0.17123287671232876,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999133182679064,
|
|
"loss": 5.8427,
|
|
"mean_token_accuracy": 0.14801040440797805,
|
|
"num_tokens": 3773244.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.971320104598999,
|
|
"epoch": 0.17165051787504176,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999124900249971,
|
|
"loss": 5.7059,
|
|
"mean_token_accuracy": 0.15795618146657944,
|
|
"num_tokens": 3782122.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.919811820983886,
|
|
"epoch": 0.17206815903775477,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999116578447239,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.16247085183858873,
|
|
"num_tokens": 3791303.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.881378173828125,
|
|
"epoch": 0.17248580020046775,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999108217271015,
|
|
"loss": 5.7661,
|
|
"mean_token_accuracy": 0.15498722046613694,
|
|
"num_tokens": 3800991.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.8623046875,
|
|
"epoch": 0.17290344136318075,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999099816721444,
|
|
"loss": 5.6712,
|
|
"mean_token_accuracy": 0.15415250658988952,
|
|
"num_tokens": 3811293.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.0197525978088375,
|
|
"epoch": 0.17332108252589376,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999091376798673,
|
|
"loss": 5.7834,
|
|
"mean_token_accuracy": 0.15429357066750526,
|
|
"num_tokens": 3820013.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.867264175415039,
|
|
"epoch": 0.17373872368860674,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999082897502849,
|
|
"loss": 5.6794,
|
|
"mean_token_accuracy": 0.15733524262905121,
|
|
"num_tokens": 3829099.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.878523349761963,
|
|
"epoch": 0.17415636485131974,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999074378834123,
|
|
"loss": 5.7719,
|
|
"mean_token_accuracy": 0.1538541316986084,
|
|
"num_tokens": 3838308.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.929077816009522,
|
|
"epoch": 0.17457400601403275,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999065820792644,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.16047724187374116,
|
|
"num_tokens": 3847650.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.942487955093384,
|
|
"epoch": 0.17499164717674573,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999057223378559,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.1422325260937214,
|
|
"num_tokens": 3857252.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.95904016494751,
|
|
"epoch": 0.17540928833945874,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499904858659202,
|
|
"loss": 5.7534,
|
|
"mean_token_accuracy": 0.1525118112564087,
|
|
"num_tokens": 3865747.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.90725622177124,
|
|
"epoch": 0.17582692950217174,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999039910433179,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.1620723456144333,
|
|
"num_tokens": 3874958.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.7633425235748295,
|
|
"epoch": 0.17624457066488472,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999031194902187,
|
|
"loss": 5.661,
|
|
"mean_token_accuracy": 0.16675298810005187,
|
|
"num_tokens": 3885216.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.845773363113404,
|
|
"epoch": 0.17666221182759773,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999022439999198,
|
|
"loss": 5.7095,
|
|
"mean_token_accuracy": 0.16534354239702226,
|
|
"num_tokens": 3893973.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.968949317932129,
|
|
"epoch": 0.17707985299031073,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999013645724362,
|
|
"loss": 5.7955,
|
|
"mean_token_accuracy": 0.15663563907146455,
|
|
"num_tokens": 3903532.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.935855197906494,
|
|
"epoch": 0.1774974941530237,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999004812077836,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.1600687876343727,
|
|
"num_tokens": 3913427.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.915048122406006,
|
|
"epoch": 0.17791513531573672,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998995939059773,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.14371922314167024,
|
|
"num_tokens": 3923870.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.892444753646851,
|
|
"epoch": 0.17833277647844972,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499898702667033,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.16210781186819076,
|
|
"num_tokens": 3933469.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.829478549957275,
|
|
"epoch": 0.1787504176411627,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998978074909661,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.16462984681129456,
|
|
"num_tokens": 3942427.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.888026475906372,
|
|
"epoch": 0.1791680588038757,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998969083777925,
|
|
"loss": 5.731,
|
|
"mean_token_accuracy": 0.16469569504261017,
|
|
"num_tokens": 3951250.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.877253484725952,
|
|
"epoch": 0.1795856999665887,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998960053275277,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.15940521210432052,
|
|
"num_tokens": 3959969.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.904099845886231,
|
|
"epoch": 0.1800033411293017,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998950983401875,
|
|
"loss": 5.7457,
|
|
"mean_token_accuracy": 0.15853157490491868,
|
|
"num_tokens": 3968171.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.909996271133423,
|
|
"epoch": 0.1804209822920147,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998941874157882,
|
|
"loss": 5.652,
|
|
"mean_token_accuracy": 0.16395194977521896,
|
|
"num_tokens": 3976686.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.807675743103028,
|
|
"epoch": 0.1808386234547277,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998932725543453,
|
|
"loss": 5.7738,
|
|
"mean_token_accuracy": 0.15376742482185363,
|
|
"num_tokens": 3986552.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.893441867828369,
|
|
"epoch": 0.18125626461744068,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998923537558749,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.15640538930892944,
|
|
"num_tokens": 3995501.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.737188863754272,
|
|
"epoch": 0.1816739057801537,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998914310203932,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.16420529335737227,
|
|
"num_tokens": 4004423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.930015420913696,
|
|
"epoch": 0.1820915469428667,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998905043479163,
|
|
"loss": 5.8099,
|
|
"mean_token_accuracy": 0.153107500821352,
|
|
"num_tokens": 4013324.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.915607213973999,
|
|
"epoch": 0.18250918810557967,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998895737384605,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.15703777819871903,
|
|
"num_tokens": 4021896.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.81768684387207,
|
|
"epoch": 0.18292682926829268,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998886391920418,
|
|
"loss": 5.6943,
|
|
"mean_token_accuracy": 0.1572074055671692,
|
|
"num_tokens": 4030590.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.833494710922241,
|
|
"epoch": 0.18334447043100568,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998877007086769,
|
|
"loss": 5.5793,
|
|
"mean_token_accuracy": 0.16950051933526994,
|
|
"num_tokens": 4040041.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.832726621627808,
|
|
"epoch": 0.18376211159371866,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998867582883821,
|
|
"loss": 5.7421,
|
|
"mean_token_accuracy": 0.15105979070067405,
|
|
"num_tokens": 4049119.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.889599370956421,
|
|
"epoch": 0.18417975275643167,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998858119311739,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.15757090598344803,
|
|
"num_tokens": 4059265.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.868921375274658,
|
|
"epoch": 0.18459739391914468,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998848616370689,
|
|
"loss": 5.7303,
|
|
"mean_token_accuracy": 0.15591793954372407,
|
|
"num_tokens": 4068363.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.834519529342652,
|
|
"epoch": 0.18501503508185768,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998839074060837,
|
|
"loss": 5.6149,
|
|
"mean_token_accuracy": 0.1670417383313179,
|
|
"num_tokens": 4077390.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.817612791061402,
|
|
"epoch": 0.18543267624457066,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499882949238235,
|
|
"loss": 5.6919,
|
|
"mean_token_accuracy": 0.15247385650873185,
|
|
"num_tokens": 4087331.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.97557053565979,
|
|
"epoch": 0.18585031740728367,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998819871335396,
|
|
"loss": 5.8788,
|
|
"mean_token_accuracy": 0.14540984779596328,
|
|
"num_tokens": 4096425.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.819278335571289,
|
|
"epoch": 0.18626795856999667,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998810210920142,
|
|
"loss": 5.6527,
|
|
"mean_token_accuracy": 0.157076658308506,
|
|
"num_tokens": 4106056.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.835240602493286,
|
|
"epoch": 0.18668559973270965,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998800511136759,
|
|
"loss": 5.7259,
|
|
"mean_token_accuracy": 0.15631824880838394,
|
|
"num_tokens": 4115133.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.864358139038086,
|
|
"epoch": 0.18710324089542266,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998790771985417,
|
|
"loss": 5.646,
|
|
"mean_token_accuracy": 0.15951664745807648,
|
|
"num_tokens": 4123630.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.7766501903533936,
|
|
"epoch": 0.18752088205813566,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998780993466284,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.15915831923484802,
|
|
"num_tokens": 4133337.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.940265655517578,
|
|
"epoch": 0.18793852322084864,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998771175579534,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.16006659865379333,
|
|
"num_tokens": 4142240.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.763757801055908,
|
|
"epoch": 0.18835616438356165,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998761318325337,
|
|
"loss": 5.6857,
|
|
"mean_token_accuracy": 0.15862759053707123,
|
|
"num_tokens": 4151297.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.8735432624816895,
|
|
"epoch": 0.18877380554627465,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998751421703868,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.16166311353445054,
|
|
"num_tokens": 4160193.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.8956348419189455,
|
|
"epoch": 0.18919144670898763,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998741485715297,
|
|
"loss": 5.7878,
|
|
"mean_token_accuracy": 0.15754115879535674,
|
|
"num_tokens": 4169948.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.02105131149292,
|
|
"epoch": 0.18960908787170064,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049987315103598,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.1528298608958721,
|
|
"num_tokens": 4179981.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.867388772964477,
|
|
"epoch": 0.19002672903441364,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998721495637551,
|
|
"loss": 5.8346,
|
|
"mean_token_accuracy": 0.1540336161851883,
|
|
"num_tokens": 4189172.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.91773419380188,
|
|
"epoch": 0.19044437019712662,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998711441548726,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.15736496299505234,
|
|
"num_tokens": 4197312.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.889427852630615,
|
|
"epoch": 0.19086201135983963,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998701348093499,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.16210058331489563,
|
|
"num_tokens": 4206828.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.964065837860107,
|
|
"epoch": 0.19127965252255263,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499869121527205,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.15945481210947038,
|
|
"num_tokens": 4214835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.850011205673217,
|
|
"epoch": 0.1916972936852656,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998681043084553,
|
|
"loss": 5.8345,
|
|
"mean_token_accuracy": 0.15231008231639862,
|
|
"num_tokens": 4225119.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.758636331558227,
|
|
"epoch": 0.19211493484797862,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998670831531188,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.1581309109926224,
|
|
"num_tokens": 4235257.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.886775064468384,
|
|
"epoch": 0.19253257601069163,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998660580612135,
|
|
"loss": 5.7484,
|
|
"mean_token_accuracy": 0.1589869663119316,
|
|
"num_tokens": 4244211.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.924040460586548,
|
|
"epoch": 0.1929502171734046,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998650290327569,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.1577833667397499,
|
|
"num_tokens": 4253149.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.840446710586548,
|
|
"epoch": 0.1933678583361176,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998639960677675,
|
|
"loss": 5.6477,
|
|
"mean_token_accuracy": 0.1637775108218193,
|
|
"num_tokens": 4262557.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.783983182907105,
|
|
"epoch": 0.19378549949883062,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998629591662631,
|
|
"loss": 5.6643,
|
|
"mean_token_accuracy": 0.16009251475334169,
|
|
"num_tokens": 4272881.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.816336631774902,
|
|
"epoch": 0.1942031406615436,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499861918328262,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.16216119825839997,
|
|
"num_tokens": 4281158.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.818071556091309,
|
|
"epoch": 0.1946207818242566,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998608735537822,
|
|
"loss": 5.6633,
|
|
"mean_token_accuracy": 0.15752760022878648,
|
|
"num_tokens": 4290319.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.862519454956055,
|
|
"epoch": 0.1950384229869696,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998598248428423,
|
|
"loss": 5.7436,
|
|
"mean_token_accuracy": 0.16369648277759552,
|
|
"num_tokens": 4299276.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.846491718292237,
|
|
"epoch": 0.19545606414968258,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998587721954604,
|
|
"loss": 5.7291,
|
|
"mean_token_accuracy": 0.15878876075148582,
|
|
"num_tokens": 4308291.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.825134420394898,
|
|
"epoch": 0.1958737053123956,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 5.6619,
|
|
"mean_token_accuracy": 0.1588639385998249,
|
|
"num_tokens": 4316654.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.863021326065064,
|
|
"epoch": 0.1962913464751086,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998566550914448,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.1598825752735138,
|
|
"num_tokens": 4325911.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.84814043045044,
|
|
"epoch": 0.19670898763782158,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998555906348481,
|
|
"loss": 5.8069,
|
|
"mean_token_accuracy": 0.1560124486684799,
|
|
"num_tokens": 4334846.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.906886148452759,
|
|
"epoch": 0.19712662880053458,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998545222418836,
|
|
"loss": 5.6736,
|
|
"mean_token_accuracy": 0.15957642048597337,
|
|
"num_tokens": 4343728.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.83021650314331,
|
|
"epoch": 0.1975442699632476,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998534499125701,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.1660468950867653,
|
|
"num_tokens": 4352774.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.949106073379516,
|
|
"epoch": 0.19796191112596057,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998523736469263,
|
|
"loss": 5.8009,
|
|
"mean_token_accuracy": 0.1570994645357132,
|
|
"num_tokens": 4361663.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.815302324295044,
|
|
"epoch": 0.19837955228867357,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499851293444971,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.16739457994699478,
|
|
"num_tokens": 4370278.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.9134697914123535,
|
|
"epoch": 0.19879719345138658,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998502093067231,
|
|
"loss": 5.6912,
|
|
"mean_token_accuracy": 0.16134303212165832,
|
|
"num_tokens": 4379010.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.838262128829956,
|
|
"epoch": 0.19921483461409956,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998491212322017,
|
|
"loss": 5.663,
|
|
"mean_token_accuracy": 0.16272303760051726,
|
|
"num_tokens": 4388145.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.780917119979859,
|
|
"epoch": 0.19963247577681256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998480292214258,
|
|
"loss": 5.806,
|
|
"mean_token_accuracy": 0.14910988062620162,
|
|
"num_tokens": 4396321.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.903149604797363,
|
|
"epoch": 0.20005011693952557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998469332744144,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.16502940952777861,
|
|
"num_tokens": 4404854.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.642773008346557,
|
|
"epoch": 0.20046775810223855,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998458333911869,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.1670069932937622,
|
|
"num_tokens": 4413890.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.862590408325195,
|
|
"epoch": 0.20088539926495155,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998447295717624,
|
|
"loss": 5.7323,
|
|
"mean_token_accuracy": 0.157737997174263,
|
|
"num_tokens": 4423019.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.81047739982605,
|
|
"epoch": 0.20130304042766456,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998436218161602,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.16053846180438996,
|
|
"num_tokens": 4432340.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.810161399841308,
|
|
"epoch": 0.20172068159037754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998425101243999,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.16139356642961503,
|
|
"num_tokens": 4441834.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.797228527069092,
|
|
"epoch": 0.20213832275309054,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998413944965007,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.1592136040329933,
|
|
"num_tokens": 4450864.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.749743509292602,
|
|
"epoch": 0.20255596391580355,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998402749324823,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.1552075505256653,
|
|
"num_tokens": 4460697.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.035622787475586,
|
|
"epoch": 0.20297360507851653,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998391514323642,
|
|
"loss": 5.7444,
|
|
"mean_token_accuracy": 0.16117378175258637,
|
|
"num_tokens": 4469926.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.734647989273071,
|
|
"epoch": 0.20339124624122953,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998380239961661,
|
|
"loss": 5.6838,
|
|
"mean_token_accuracy": 0.16252014935016632,
|
|
"num_tokens": 4478818.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.8350136280059814,
|
|
"epoch": 0.20380888740394254,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998368926239078,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.1623082473874092,
|
|
"num_tokens": 4487451.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.804310703277588,
|
|
"epoch": 0.20422652856665552,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499835757315609,
|
|
"loss": 5.6839,
|
|
"mean_token_accuracy": 0.15567411631345748,
|
|
"num_tokens": 4497674.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.778557586669922,
|
|
"epoch": 0.20464416972936852,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998346180712898,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.1650843396782875,
|
|
"num_tokens": 4507666.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.834744691848755,
|
|
"epoch": 0.20506181089208153,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998334748909698,
|
|
"loss": 5.743,
|
|
"mean_token_accuracy": 0.15409338921308519,
|
|
"num_tokens": 4517409.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.8095001697540285,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998323277746694,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.16385659277439119,
|
|
"num_tokens": 4526495.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.77939510345459,
|
|
"epoch": 0.20589709321750752,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998311767224081,
|
|
"loss": 5.6284,
|
|
"mean_token_accuracy": 0.16991629004478453,
|
|
"num_tokens": 4535240.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.838644981384277,
|
|
"epoch": 0.20631473438022052,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998300217342067,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.15681551843881608,
|
|
"num_tokens": 4544716.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.715267181396484,
|
|
"epoch": 0.2067323755429335,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998288628100851,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.162817020714283,
|
|
"num_tokens": 4553867.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.868233108520508,
|
|
"epoch": 0.2071500167056465,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998276999500636,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.15431201457977295,
|
|
"num_tokens": 4562529.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.715342092514038,
|
|
"epoch": 0.2075676578683595,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.17513344287872315,
|
|
"num_tokens": 4571041.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.711450433731079,
|
|
"epoch": 0.2079852990310725,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998253624224026,
|
|
"loss": 5.6309,
|
|
"mean_token_accuracy": 0.16020862385630608,
|
|
"num_tokens": 4579914.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.813286972045899,
|
|
"epoch": 0.2084029401937855,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000499824187754804,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.1612517148256302,
|
|
"num_tokens": 4590277.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.822319984436035,
|
|
"epoch": 0.2088205813564985,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998230091513872,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.1658724918961525,
|
|
"num_tokens": 4598719.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.7216949462890625,
|
|
"epoch": 0.20923822251921148,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998218266121731,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.16493814885616304,
|
|
"num_tokens": 4607804.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.74538516998291,
|
|
"epoch": 0.2096558636819245,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998206401371823,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.16702073365449904,
|
|
"num_tokens": 4616529.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.838421297073364,
|
|
"epoch": 0.2100735048446375,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998194497264357,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.15869868099689483,
|
|
"num_tokens": 4624545.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.782481956481933,
|
|
"epoch": 0.21049114600735047,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998182553799538,
|
|
"loss": 5.6006,
|
|
"mean_token_accuracy": 0.15949173867702485,
|
|
"num_tokens": 4633316.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.748195505142212,
|
|
"epoch": 0.21090878717006348,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998170570977579,
|
|
"loss": 5.5587,
|
|
"mean_token_accuracy": 0.1721911072731018,
|
|
"num_tokens": 4643353.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.747497320175171,
|
|
"epoch": 0.21132642833277648,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998158548798687,
|
|
"loss": 5.6494,
|
|
"mean_token_accuracy": 0.15524984747171403,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.837891101837158,
|
|
"epoch": 0.21174406949548946,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998146487263074,
|
|
"loss": 5.6515,
|
|
"mean_token_accuracy": 0.16123034954071044,
|
|
"num_tokens": 4659937.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.730093622207642,
|
|
"epoch": 0.21216171065820247,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998134386370951,
|
|
"loss": 5.6277,
|
|
"mean_token_accuracy": 0.16407201513648034,
|
|
"num_tokens": 4669396.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.881675386428833,
|
|
"epoch": 0.21257935182091547,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998122246122529,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.16837172955274582,
|
|
"num_tokens": 4679320.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.7952516078948975,
|
|
"epoch": 0.21299699298362845,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998110066518021,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.16251329183578492,
|
|
"num_tokens": 4688807.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.831697654724121,
|
|
"epoch": 0.21341463414634146,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499809784755764,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.17055489122867584,
|
|
"num_tokens": 4697819.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.700474548339844,
|
|
"epoch": 0.21383227530905446,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049980855892416,
|
|
"loss": 5.6051,
|
|
"mean_token_accuracy": 0.16278748512268065,
|
|
"num_tokens": 4706931.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.756153774261475,
|
|
"epoch": 0.21424991647176747,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998073291570116,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.16360058337450029,
|
|
"num_tokens": 4716262.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.81894998550415,
|
|
"epoch": 0.21466755763448045,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998060954543404,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.16175924837589264,
|
|
"num_tokens": 4725415.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.707076120376587,
|
|
"epoch": 0.21508519879719346,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998048578161678,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.16455809623003007,
|
|
"num_tokens": 4734580.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.7181299209594725,
|
|
"epoch": 0.21550283995990646,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998036162425155,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.1736983448266983,
|
|
"num_tokens": 4742966.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.801785516738891,
|
|
"epoch": 0.21592048112261944,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998023707334055,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.1645279809832573,
|
|
"num_tokens": 4751696.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.846903324127197,
|
|
"epoch": 0.21633812228533245,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998011212888592,
|
|
"loss": 5.6879,
|
|
"mean_token_accuracy": 0.16777165681123735,
|
|
"num_tokens": 4760460.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.780740785598755,
|
|
"epoch": 0.21675576344804545,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997998679088988,
|
|
"loss": 5.6102,
|
|
"mean_token_accuracy": 0.1645229384303093,
|
|
"num_tokens": 4769004.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.757664060592651,
|
|
"epoch": 0.21717340461075843,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997986105935461,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.16781664937734603,
|
|
"num_tokens": 4777204.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.864018487930298,
|
|
"epoch": 0.21759104577347144,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997973493428231,
|
|
"loss": 5.7145,
|
|
"mean_token_accuracy": 0.1602879449725151,
|
|
"num_tokens": 4786766.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.663840627670288,
|
|
"epoch": 0.21800868693618444,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997960841567519,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.16582195907831193,
|
|
"num_tokens": 4796676.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.9396082878112795,
|
|
"epoch": 0.21842632809889742,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997948150353548,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.16275097280740738,
|
|
"num_tokens": 4805514.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.718913602828979,
|
|
"epoch": 0.21884396926161043,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997935419786537,
|
|
"loss": 5.696,
|
|
"mean_token_accuracy": 0.16018566042184829,
|
|
"num_tokens": 4815487.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.88177261352539,
|
|
"epoch": 0.21926161042432343,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997922649866712,
|
|
"loss": 5.6489,
|
|
"mean_token_accuracy": 0.16259622126817702,
|
|
"num_tokens": 4825044.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.689206600189209,
|
|
"epoch": 0.2196792515870364,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997909840594294,
|
|
"loss": 5.4412,
|
|
"mean_token_accuracy": 0.17392415851354598,
|
|
"num_tokens": 4833875.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.6562834739685055,
|
|
"epoch": 0.22009689274974942,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997896991969509,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.15934335738420485,
|
|
"num_tokens": 4843317.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.805779695510864,
|
|
"epoch": 0.22051453391246242,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997884103992581,
|
|
"loss": 5.6515,
|
|
"mean_token_accuracy": 0.15986357778310775,
|
|
"num_tokens": 4852514.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.787460565567017,
|
|
"epoch": 0.2209321750751754,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997871176663736,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.16665420085191726,
|
|
"num_tokens": 4861260.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.70442008972168,
|
|
"epoch": 0.2213498162378884,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997858209983201,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.15970537588000297,
|
|
"num_tokens": 4869654.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.780343818664551,
|
|
"epoch": 0.22176745740060141,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997845203951202,
|
|
"loss": 5.6071,
|
|
"mean_token_accuracy": 0.15780386179685593,
|
|
"num_tokens": 4878311.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.839015626907349,
|
|
"epoch": 0.2221850985633144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997832158567967,
|
|
"loss": 5.6874,
|
|
"mean_token_accuracy": 0.1592348925769329,
|
|
"num_tokens": 4887251.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.693773031234741,
|
|
"epoch": 0.2226027397260274,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997819073833724,
|
|
"loss": 5.5377,
|
|
"mean_token_accuracy": 0.1633484482765198,
|
|
"num_tokens": 4896528.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.7157878398895265,
|
|
"epoch": 0.2230203808887404,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997805949748702,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.16120654642581939,
|
|
"num_tokens": 4904962.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.8058465957641605,
|
|
"epoch": 0.22343802205145338,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997792786313132,
|
|
"loss": 5.6042,
|
|
"mean_token_accuracy": 0.15915837287902831,
|
|
"num_tokens": 4914735.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.616079473495484,
|
|
"epoch": 0.2238556632141664,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997779583527243,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.16390765011310576,
|
|
"num_tokens": 4924271.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.869078683853149,
|
|
"epoch": 0.2242733043768794,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997766341391268,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.15845021605491638,
|
|
"num_tokens": 4933928.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.7307792663574215,
|
|
"epoch": 0.22469094553959237,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997753059905437,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.17364991903305055,
|
|
"num_tokens": 4942714.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.661212921142578,
|
|
"epoch": 0.22510858670230538,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997739739069981,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.16816597133874894,
|
|
"num_tokens": 4952297.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.714229440689087,
|
|
"epoch": 0.22552622786501839,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997726378885138,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.17623727917671203,
|
|
"num_tokens": 4960947.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.757331514358521,
|
|
"epoch": 0.22594386902773136,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997712979351137,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.161906411498785,
|
|
"num_tokens": 4969705.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.852696895599365,
|
|
"epoch": 0.22636151019044437,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997699540468216,
|
|
"loss": 5.6251,
|
|
"mean_token_accuracy": 0.16277607381343842,
|
|
"num_tokens": 4979112.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.718151617050171,
|
|
"epoch": 0.22677915135315738,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997686062236609,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.16444555073976516,
|
|
"num_tokens": 4987894.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.755270385742188,
|
|
"epoch": 0.22719679251587035,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997672544656553,
|
|
"loss": 5.6945,
|
|
"mean_token_accuracy": 0.15452539920806885,
|
|
"num_tokens": 4997774.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.837758636474609,
|
|
"epoch": 0.22761443367858336,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997658987728283,
|
|
"loss": 5.6182,
|
|
"mean_token_accuracy": 0.16429695934057237,
|
|
"num_tokens": 5006183.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.711544799804687,
|
|
"epoch": 0.22803207484129637,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997645391452035,
|
|
"loss": 5.5984,
|
|
"mean_token_accuracy": 0.1637036234140396,
|
|
"num_tokens": 5016909.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.844042348861694,
|
|
"epoch": 0.22844971600400935,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499763175582805,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.16498590111732483,
|
|
"num_tokens": 5027326.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.746332120895386,
|
|
"epoch": 0.22886735716672235,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997618080856566,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.1639745995402336,
|
|
"num_tokens": 5037043.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.687271451950073,
|
|
"epoch": 0.22928499832943536,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997604366537823,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.16922535002231598,
|
|
"num_tokens": 5045992.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.6921813011169435,
|
|
"epoch": 0.22970263949214834,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997590612872058,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.17040622532367705,
|
|
"num_tokens": 5055568.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.785310697555542,
|
|
"epoch": 0.23012028065486134,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997576819859515,
|
|
"loss": 5.634,
|
|
"mean_token_accuracy": 0.16597387343645095,
|
|
"num_tokens": 5065512.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.613603973388672,
|
|
"epoch": 0.23053792181757435,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997562987500434,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.17271397709846498,
|
|
"num_tokens": 5074776.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.682473802566529,
|
|
"epoch": 0.23095556298028733,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997549115795058,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.16364094167947768,
|
|
"num_tokens": 5084743.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.821541166305542,
|
|
"epoch": 0.23137320414300033,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499753520474363,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.16082392036914825,
|
|
"num_tokens": 5095387.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.723036479949951,
|
|
"epoch": 0.23179084530571334,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997521254346391,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.16801968365907669,
|
|
"num_tokens": 5104628.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.748641872406006,
|
|
"epoch": 0.23220848646842632,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997507264603589,
|
|
"loss": 5.5579,
|
|
"mean_token_accuracy": 0.16903598308563234,
|
|
"num_tokens": 5113169.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.735997152328491,
|
|
"epoch": 0.23262612763113932,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997493235515466,
|
|
"loss": 5.616,
|
|
"mean_token_accuracy": 0.1675027921795845,
|
|
"num_tokens": 5122294.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.68292818069458,
|
|
"epoch": 0.23304376879385233,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997479167082269,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.17553396224975587,
|
|
"num_tokens": 5131191.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.684044027328492,
|
|
"epoch": 0.2334614099565653,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997465059304243,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.1675591215491295,
|
|
"num_tokens": 5141974.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.787416267395019,
|
|
"epoch": 0.23387905111927831,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997450912181637,
|
|
"loss": 5.593,
|
|
"mean_token_accuracy": 0.16815385073423386,
|
|
"num_tokens": 5151412.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.694646167755127,
|
|
"epoch": 0.23429669228199132,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997436725714696,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.17085290551185608,
|
|
"num_tokens": 5160989.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.750547647476196,
|
|
"epoch": 0.2347143334447043,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997422499903671,
|
|
"loss": 5.5962,
|
|
"mean_token_accuracy": 0.16256070286035537,
|
|
"num_tokens": 5170241.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.86253604888916,
|
|
"epoch": 0.2351319746074173,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499740823474881,
|
|
"loss": 5.7114,
|
|
"mean_token_accuracy": 0.1583871603012085,
|
|
"num_tokens": 5180247.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.691003131866455,
|
|
"epoch": 0.2355496157701303,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997393930250363,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.16719801127910613,
|
|
"num_tokens": 5189144.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.7188694953918455,
|
|
"epoch": 0.2359672569328433,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499737958640858,
|
|
"loss": 5.6503,
|
|
"mean_token_accuracy": 0.163092702627182,
|
|
"num_tokens": 5199410.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.776434516906738,
|
|
"epoch": 0.2363848980955563,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997365203223711,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.1717270389199257,
|
|
"num_tokens": 5209032.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.60194149017334,
|
|
"epoch": 0.2368025392582693,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499735078069601,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.17052695155143738,
|
|
"num_tokens": 5217787.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.668485689163208,
|
|
"epoch": 0.23722018042098228,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997336318825728,
|
|
"loss": 5.5446,
|
|
"mean_token_accuracy": 0.17174894362688065,
|
|
"num_tokens": 5226962.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.678308296203613,
|
|
"epoch": 0.23763782158369529,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997321817613119,
|
|
"loss": 5.5173,
|
|
"mean_token_accuracy": 0.1678185984492302,
|
|
"num_tokens": 5236111.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.770784091949463,
|
|
"epoch": 0.2380554627464083,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997307277058436,
|
|
"loss": 5.6541,
|
|
"mean_token_accuracy": 0.16095943748950958,
|
|
"num_tokens": 5246628.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.723996591567993,
|
|
"epoch": 0.23847310390912127,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997292697161935,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.16508384943008422,
|
|
"num_tokens": 5255543.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.646565294265747,
|
|
"epoch": 0.23889074507183428,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499727807792387,
|
|
"loss": 5.4457,
|
|
"mean_token_accuracy": 0.17628723680973052,
|
|
"num_tokens": 5264559.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.608687114715576,
|
|
"epoch": 0.23930838623454728,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997263419344495,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.1655178412795067,
|
|
"num_tokens": 5274599.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.7203874588012695,
|
|
"epoch": 0.23972602739726026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997248721424071,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.17523384392261504,
|
|
"num_tokens": 5283495.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.695050477981567,
|
|
"epoch": 0.24014366855997327,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997233984162853,
|
|
"loss": 5.5477,
|
|
"mean_token_accuracy": 0.17063757181167602,
|
|
"num_tokens": 5292064.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.682350397109985,
|
|
"epoch": 0.24056130972268627,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997219207561099,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.16449775397777558,
|
|
"num_tokens": 5301696.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.779582738876343,
|
|
"epoch": 0.24097895088539925,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997204391619068,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.15998486280441285,
|
|
"num_tokens": 5311427.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.861279916763306,
|
|
"epoch": 0.24139659204811226,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997189536337018,
|
|
"loss": 5.5943,
|
|
"mean_token_accuracy": 0.165325590968132,
|
|
"num_tokens": 5321406.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.737252998352051,
|
|
"epoch": 0.24181423321082526,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997174641715211,
|
|
"loss": 5.6747,
|
|
"mean_token_accuracy": 0.16726240664720535,
|
|
"num_tokens": 5332257.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.6061920642852785,
|
|
"epoch": 0.24223187437353827,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997159707753906,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.17394435107707978,
|
|
"num_tokens": 5341857.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.674947690963745,
|
|
"epoch": 0.24264951553625125,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.1720260888338089,
|
|
"num_tokens": 5351367.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.615740251541138,
|
|
"epoch": 0.24306715669896425,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997129721813853,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.1757777988910675,
|
|
"num_tokens": 5360627.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.6760059833526615,
|
|
"epoch": 0.24348479786167726,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997114669835629,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.1785655990242958,
|
|
"num_tokens": 5369703.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.673794412612915,
|
|
"epoch": 0.24390243902439024,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997099578518959,
|
|
"loss": 5.562,
|
|
"mean_token_accuracy": 0.16899080127477645,
|
|
"num_tokens": 5378432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.56113076210022,
|
|
"epoch": 0.24432008018710324,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997084447864105,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.1710927039384842,
|
|
"num_tokens": 5386489.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.833731555938721,
|
|
"epoch": 0.24473772134981625,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997069277871333,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.16405942440032958,
|
|
"num_tokens": 5395908.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.775952911376953,
|
|
"epoch": 0.24515536251252923,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997054068540908,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.16982482224702836,
|
|
"num_tokens": 5404822.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.635651350021362,
|
|
"epoch": 0.24557300367524224,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997038819873098,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.17467086464166642,
|
|
"num_tokens": 5413980.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.684035778045654,
|
|
"epoch": 0.24599064483795524,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997023531868167,
|
|
"loss": 5.5357,
|
|
"mean_token_accuracy": 0.16595565229654313,
|
|
"num_tokens": 5423538.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.622634029388427,
|
|
"epoch": 0.24640828600066822,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997008204526386,
|
|
"loss": 5.4702,
|
|
"mean_token_accuracy": 0.1707819879055023,
|
|
"num_tokens": 5431930.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.666269826889038,
|
|
"epoch": 0.24682592716338123,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996992837848021,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.17090596705675126,
|
|
"num_tokens": 5440721.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.596457624435425,
|
|
"epoch": 0.24724356832609423,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996977431833342,
|
|
"loss": 5.5369,
|
|
"mean_token_accuracy": 0.16840151995420455,
|
|
"num_tokens": 5449617.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.668986415863037,
|
|
"epoch": 0.2476612094888072,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996961986482618,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.16662422716617584,
|
|
"num_tokens": 5458827.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.7311032772064205,
|
|
"epoch": 0.24807885065152022,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996946501796119,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.17484788447618485,
|
|
"num_tokens": 5467348.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.71124677658081,
|
|
"epoch": 0.24849649181423322,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996930977774118,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.15785626620054244,
|
|
"num_tokens": 5476645.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.715850973129273,
|
|
"epoch": 0.2489141329769462,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996915414416885,
|
|
"loss": 5.57,
|
|
"mean_token_accuracy": 0.16464744806289672,
|
|
"num_tokens": 5486120.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.771138858795166,
|
|
"epoch": 0.2493317741396592,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996899811724693,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.16355062425136566,
|
|
"num_tokens": 5495313.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.665059328079224,
|
|
"epoch": 0.2497494153023722,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996884169697816,
|
|
"loss": 5.5356,
|
|
"mean_token_accuracy": 0.17020975649356843,
|
|
"num_tokens": 5504587.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.6389179706573485,
|
|
"epoch": 0.2501670564650852,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996868488336526,
|
|
"loss": 5.5605,
|
|
"mean_token_accuracy": 0.16468265056610107,
|
|
"num_tokens": 5514188.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.653175640106201,
|
|
"epoch": 0.25058469762779817,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996852767641099,
|
|
"loss": 5.6088,
|
|
"mean_token_accuracy": 0.16206363141536712,
|
|
"num_tokens": 5524075.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.25058469762779817,
|
|
"eval_entropy": 5.512934588497156,
|
|
"eval_loss": 5.5222487449646,
|
|
"eval_mean_token_accuracy": 0.17784448021585295,
|
|
"eval_num_tokens": 5524075.0,
|
|
"eval_runtime": 21.1176,
|
|
"eval_samples_per_second": 1788.224,
|
|
"eval_steps_per_second": 223.558,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"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": 1208069049876480.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|