ffa3d0ff90
Model: fpadovani/dan-latn-100mb-after-ppt-Dp-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": 6.7180821895599365,
|
|
"epoch": 0.000417641162712997,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.5123,
|
|
"mean_token_accuracy": 0.10666800066828727,
|
|
"num_tokens": 9371.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 6.808059024810791,
|
|
"epoch": 0.000835282325425994,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.5956,
|
|
"mean_token_accuracy": 0.10533942952752114,
|
|
"num_tokens": 18155.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 6.759247636795044,
|
|
"epoch": 0.001252923488138991,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.5801,
|
|
"mean_token_accuracy": 0.10018297508358956,
|
|
"num_tokens": 27776.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 6.797110748291016,
|
|
"epoch": 0.001670564650851988,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.5797,
|
|
"mean_token_accuracy": 0.10600945577025414,
|
|
"num_tokens": 37166.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.759796857833862,
|
|
"epoch": 0.002088205813564985,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 6.5305,
|
|
"mean_token_accuracy": 0.11286764591932297,
|
|
"num_tokens": 46667.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 6.808503246307373,
|
|
"epoch": 0.002505846976277982,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.5297,
|
|
"mean_token_accuracy": 0.10954836457967758,
|
|
"num_tokens": 55738.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.905849361419678,
|
|
"epoch": 0.002923488138990979,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.6363,
|
|
"mean_token_accuracy": 0.10485906973481178,
|
|
"num_tokens": 65303.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 6.810987138748169,
|
|
"epoch": 0.003341129301703976,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.4128,
|
|
"mean_token_accuracy": 0.11579142212867737,
|
|
"num_tokens": 74876.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 6.819403839111328,
|
|
"epoch": 0.003758770464416973,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 6.5539,
|
|
"mean_token_accuracy": 0.11837585121393204,
|
|
"num_tokens": 84683.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 6.842317581176758,
|
|
"epoch": 0.00417641162712997,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.5476,
|
|
"mean_token_accuracy": 0.1076658695936203,
|
|
"num_tokens": 94511.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 6.806653213500977,
|
|
"epoch": 0.004594052789842967,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 6.529,
|
|
"mean_token_accuracy": 0.12048889845609664,
|
|
"num_tokens": 103820.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 6.758758592605591,
|
|
"epoch": 0.005011693952555964,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.5035,
|
|
"mean_token_accuracy": 0.1163383036851883,
|
|
"num_tokens": 112398.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 6.7997699737548825,
|
|
"epoch": 0.005429335115268961,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.4622,
|
|
"mean_token_accuracy": 0.119983372092247,
|
|
"num_tokens": 121167.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 6.826302528381348,
|
|
"epoch": 0.005846976277981958,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.4857,
|
|
"mean_token_accuracy": 0.11032287627458573,
|
|
"num_tokens": 129399.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 6.845746660232544,
|
|
"epoch": 0.006264617440694955,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.4687,
|
|
"mean_token_accuracy": 0.1163133703172207,
|
|
"num_tokens": 138512.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 6.800804281234742,
|
|
"epoch": 0.006682258603407952,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.5206,
|
|
"mean_token_accuracy": 0.10875637605786323,
|
|
"num_tokens": 147712.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 6.811766719818115,
|
|
"epoch": 0.007099899766120949,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.4852,
|
|
"mean_token_accuracy": 0.1177453450858593,
|
|
"num_tokens": 156759.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 6.773466730117798,
|
|
"epoch": 0.007517540928833946,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.533,
|
|
"mean_token_accuracy": 0.11238256990909576,
|
|
"num_tokens": 166395.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 6.842059373855591,
|
|
"epoch": 0.007935182091546943,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.4534,
|
|
"mean_token_accuracy": 0.11896919012069702,
|
|
"num_tokens": 174739.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 6.710035228729248,
|
|
"epoch": 0.00835282325425994,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.3439,
|
|
"mean_token_accuracy": 0.12140651717782021,
|
|
"num_tokens": 183010.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 6.729191780090332,
|
|
"epoch": 0.008770464416972937,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.5163,
|
|
"mean_token_accuracy": 0.11011387556791305,
|
|
"num_tokens": 192589.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 6.83894910812378,
|
|
"epoch": 0.009188105579685933,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 6.45,
|
|
"mean_token_accuracy": 0.11901598572731018,
|
|
"num_tokens": 201638.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 6.744243049621582,
|
|
"epoch": 0.00960574674239893,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.12338117063045502,
|
|
"num_tokens": 209862.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 6.756110143661499,
|
|
"epoch": 0.010023387905111928,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.5095,
|
|
"mean_token_accuracy": 0.11191049665212631,
|
|
"num_tokens": 218897.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 6.908449125289917,
|
|
"epoch": 0.010441029067824925,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.5859,
|
|
"mean_token_accuracy": 0.11279568374156952,
|
|
"num_tokens": 227682.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 6.8623613834381105,
|
|
"epoch": 0.010858670230537921,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.4542,
|
|
"mean_token_accuracy": 0.11863475143909455,
|
|
"num_tokens": 236170.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 6.790626573562622,
|
|
"epoch": 0.011276311393250919,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.5522,
|
|
"mean_token_accuracy": 0.11070087552070618,
|
|
"num_tokens": 245710.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 6.78648738861084,
|
|
"epoch": 0.011693952555963916,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.5029,
|
|
"mean_token_accuracy": 0.11403205692768097,
|
|
"num_tokens": 254751.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 6.7859738826751705,
|
|
"epoch": 0.012111593718676913,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.433,
|
|
"mean_token_accuracy": 0.1188641369342804,
|
|
"num_tokens": 264210.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 6.8096400737762455,
|
|
"epoch": 0.01252923488138991,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.4861,
|
|
"mean_token_accuracy": 0.12114087268710136,
|
|
"num_tokens": 272944.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 6.791913175582886,
|
|
"epoch": 0.012946876044102907,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.12244183719158172,
|
|
"num_tokens": 281311.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 6.694759273529053,
|
|
"epoch": 0.013364517206815904,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.3769,
|
|
"mean_token_accuracy": 0.12260683327913284,
|
|
"num_tokens": 289701.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 6.748257827758789,
|
|
"epoch": 0.013782158369528901,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.5215,
|
|
"mean_token_accuracy": 0.1143926203250885,
|
|
"num_tokens": 299459.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 6.883009147644043,
|
|
"epoch": 0.014199799532241897,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.5421,
|
|
"mean_token_accuracy": 0.11752694174647331,
|
|
"num_tokens": 309343.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 6.830853223800659,
|
|
"epoch": 0.014617440694954895,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.5302,
|
|
"mean_token_accuracy": 0.11090763658285141,
|
|
"num_tokens": 318840.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 6.675867223739624,
|
|
"epoch": 0.015035081857667892,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.3784,
|
|
"mean_token_accuracy": 0.11448234245181084,
|
|
"num_tokens": 328689.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 6.797796392440796,
|
|
"epoch": 0.01545272302038089,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.4889,
|
|
"mean_token_accuracy": 0.11072958707809448,
|
|
"num_tokens": 338209.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 6.7780595302581785,
|
|
"epoch": 0.015870364183093885,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.417,
|
|
"mean_token_accuracy": 0.11931143030524254,
|
|
"num_tokens": 347270.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 6.799556255340576,
|
|
"epoch": 0.016288005345806884,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.4735,
|
|
"mean_token_accuracy": 0.11163464188575745,
|
|
"num_tokens": 356366.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 6.763126516342163,
|
|
"epoch": 0.01670564650851988,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.4167,
|
|
"mean_token_accuracy": 0.11596830189228058,
|
|
"num_tokens": 365980.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 6.702800369262695,
|
|
"epoch": 0.017123287671232876,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.3882,
|
|
"mean_token_accuracy": 0.11993374973535538,
|
|
"num_tokens": 374591.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 6.849011707305908,
|
|
"epoch": 0.017540928833945875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.4294,
|
|
"mean_token_accuracy": 0.11508302688598633,
|
|
"num_tokens": 383250.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 6.693080568313599,
|
|
"epoch": 0.01795856999665887,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.3306,
|
|
"mean_token_accuracy": 0.11563051715493203,
|
|
"num_tokens": 391502.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 6.630117034912109,
|
|
"epoch": 0.018376211159371866,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.2712,
|
|
"mean_token_accuracy": 0.11645801290869713,
|
|
"num_tokens": 400225.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 6.8181227684021,
|
|
"epoch": 0.018793852322084866,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.4937,
|
|
"mean_token_accuracy": 0.1128729097545147,
|
|
"num_tokens": 410008.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 6.736743688583374,
|
|
"epoch": 0.01921149348479786,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.4332,
|
|
"mean_token_accuracy": 0.11869536191225052,
|
|
"num_tokens": 418979.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 6.718912887573242,
|
|
"epoch": 0.01962913464751086,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.4259,
|
|
"mean_token_accuracy": 0.11591459438204765,
|
|
"num_tokens": 428139.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 6.7471612930297855,
|
|
"epoch": 0.020046775810223856,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.3418,
|
|
"mean_token_accuracy": 0.12110752388834953,
|
|
"num_tokens": 437113.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 6.818037843704223,
|
|
"epoch": 0.020464416972936852,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.6019,
|
|
"mean_token_accuracy": 0.11445037350058555,
|
|
"num_tokens": 446879.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 6.695638751983642,
|
|
"epoch": 0.02088205813564985,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.5041,
|
|
"mean_token_accuracy": 0.11364466175436974,
|
|
"num_tokens": 456362.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 6.799724435806274,
|
|
"epoch": 0.021299699298362847,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.2963,
|
|
"mean_token_accuracy": 0.12356706708669662,
|
|
"num_tokens": 464930.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 6.682189035415649,
|
|
"epoch": 0.021717340461075842,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.469,
|
|
"mean_token_accuracy": 0.11262325197458267,
|
|
"num_tokens": 474303.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 6.784652948379517,
|
|
"epoch": 0.02213498162378884,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.4998,
|
|
"mean_token_accuracy": 0.11313469260931015,
|
|
"num_tokens": 483750.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 6.743142223358154,
|
|
"epoch": 0.022552622786501837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.3944,
|
|
"mean_token_accuracy": 0.1151240773499012,
|
|
"num_tokens": 493325.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 6.729674768447876,
|
|
"epoch": 0.022970263949214833,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.4083,
|
|
"mean_token_accuracy": 0.11122140809893608,
|
|
"num_tokens": 501907.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 6.695761060714721,
|
|
"epoch": 0.023387905111927832,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.4871,
|
|
"mean_token_accuracy": 0.11502960547804833,
|
|
"num_tokens": 511522.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 6.770887994766236,
|
|
"epoch": 0.023805546274640828,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.4136,
|
|
"mean_token_accuracy": 0.1140117235481739,
|
|
"num_tokens": 521287.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 6.772694158554077,
|
|
"epoch": 0.024223187437353827,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.5268,
|
|
"mean_token_accuracy": 0.10702815651893616,
|
|
"num_tokens": 530631.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 6.726316118240357,
|
|
"epoch": 0.024640828600066823,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.12561146542429924,
|
|
"num_tokens": 540386.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 6.716358995437622,
|
|
"epoch": 0.02505846976277982,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.11597420573234558,
|
|
"num_tokens": 550121.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 6.649577903747558,
|
|
"epoch": 0.025476110925492818,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.3557,
|
|
"mean_token_accuracy": 0.11343038976192474,
|
|
"num_tokens": 559460.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 6.724728441238403,
|
|
"epoch": 0.025893752088205813,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.12006132379174232,
|
|
"num_tokens": 568392.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 6.653720140457153,
|
|
"epoch": 0.02631139325091881,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.11691968142986298,
|
|
"num_tokens": 578248.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 6.7646496295928955,
|
|
"epoch": 0.026729034413631808,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.4952,
|
|
"mean_token_accuracy": 0.11188015565276146,
|
|
"num_tokens": 588164.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 6.729947662353515,
|
|
"epoch": 0.027146675576344804,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.4382,
|
|
"mean_token_accuracy": 0.11248505786061287,
|
|
"num_tokens": 598715.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 6.6656099319458,
|
|
"epoch": 0.027564316739057803,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.3299,
|
|
"mean_token_accuracy": 0.11870421469211578,
|
|
"num_tokens": 606939.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 6.688929510116577,
|
|
"epoch": 0.0279819579017708,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.4408,
|
|
"mean_token_accuracy": 0.12059589847922325,
|
|
"num_tokens": 615803.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 6.677912378311158,
|
|
"epoch": 0.028399599064483794,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.3016,
|
|
"mean_token_accuracy": 0.1152017168700695,
|
|
"num_tokens": 624730.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 6.668429660797119,
|
|
"epoch": 0.028817240227196794,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.11559123620390892,
|
|
"num_tokens": 634082.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 6.710170698165894,
|
|
"epoch": 0.02923488138990979,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.11764291599392891,
|
|
"num_tokens": 643367.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 6.57072377204895,
|
|
"epoch": 0.029652522552622785,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.2433,
|
|
"mean_token_accuracy": 0.12115906029939652,
|
|
"num_tokens": 651861.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 6.699751520156861,
|
|
"epoch": 0.030070163715335784,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.383,
|
|
"mean_token_accuracy": 0.11497076004743575,
|
|
"num_tokens": 661064.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 6.6671435832977295,
|
|
"epoch": 0.03048780487804878,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.3574,
|
|
"mean_token_accuracy": 0.12420301362872124,
|
|
"num_tokens": 669299.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 6.628156757354736,
|
|
"epoch": 0.03090544604076178,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.4516,
|
|
"mean_token_accuracy": 0.11220049262046813,
|
|
"num_tokens": 678631.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.7193104267120365,
|
|
"epoch": 0.03132308720347477,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.4496,
|
|
"mean_token_accuracy": 0.1158321812748909,
|
|
"num_tokens": 688511.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 6.703116130828858,
|
|
"epoch": 0.03174072836618777,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.3797,
|
|
"mean_token_accuracy": 0.11359225586056709,
|
|
"num_tokens": 697956.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 6.668367481231689,
|
|
"epoch": 0.03215836952890077,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.2828,
|
|
"mean_token_accuracy": 0.12736818715929984,
|
|
"num_tokens": 706779.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 6.554675436019897,
|
|
"epoch": 0.03257601069161377,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.3132,
|
|
"mean_token_accuracy": 0.11831648498773575,
|
|
"num_tokens": 715749.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.59646201133728,
|
|
"epoch": 0.03299365185432676,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.2781,
|
|
"mean_token_accuracy": 0.11623693332076072,
|
|
"num_tokens": 724756.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.562495231628418,
|
|
"epoch": 0.03341129301703976,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.3001,
|
|
"mean_token_accuracy": 0.1243792787194252,
|
|
"num_tokens": 733288.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.739299392700195,
|
|
"epoch": 0.03382893417975276,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.4209,
|
|
"mean_token_accuracy": 0.1129365734755993,
|
|
"num_tokens": 741629.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 6.62856707572937,
|
|
"epoch": 0.03424657534246575,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.3605,
|
|
"mean_token_accuracy": 0.12043223157525063,
|
|
"num_tokens": 751336.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.780359745025635,
|
|
"epoch": 0.03466421650517875,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.4408,
|
|
"mean_token_accuracy": 0.11233260035514832,
|
|
"num_tokens": 759725.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.7300169467926025,
|
|
"epoch": 0.03508185766789175,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.4676,
|
|
"mean_token_accuracy": 0.11555668562650681,
|
|
"num_tokens": 769752.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.61152400970459,
|
|
"epoch": 0.03549949883060474,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.3419,
|
|
"mean_token_accuracy": 0.12118100821971893,
|
|
"num_tokens": 779124.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.572236108779907,
|
|
"epoch": 0.03591713999331774,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.3142,
|
|
"mean_token_accuracy": 0.11852151229977607,
|
|
"num_tokens": 788892.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.499159049987793,
|
|
"epoch": 0.03633478115603074,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.2789,
|
|
"mean_token_accuracy": 0.12280359491705894,
|
|
"num_tokens": 798265.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.5266131401062015,
|
|
"epoch": 0.03675242231874373,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.12434489950537682,
|
|
"num_tokens": 806896.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.646367168426513,
|
|
"epoch": 0.03717006348145673,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.1231755070388317,
|
|
"num_tokens": 815540.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.595507431030273,
|
|
"epoch": 0.03758770464416973,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.3785,
|
|
"mean_token_accuracy": 0.11604066267609596,
|
|
"num_tokens": 824555.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.659368467330933,
|
|
"epoch": 0.03800534580688272,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.429,
|
|
"mean_token_accuracy": 0.11681790426373481,
|
|
"num_tokens": 833414.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.521911573410034,
|
|
"epoch": 0.03842298696959572,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.2667,
|
|
"mean_token_accuracy": 0.1260523058474064,
|
|
"num_tokens": 842644.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.635482358932495,
|
|
"epoch": 0.03884062813230872,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.3016,
|
|
"mean_token_accuracy": 0.11958117336034775,
|
|
"num_tokens": 851786.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.533578109741211,
|
|
"epoch": 0.03925826929502172,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.378,
|
|
"mean_token_accuracy": 0.11788101494312286,
|
|
"num_tokens": 861508.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.512241077423096,
|
|
"epoch": 0.03967591045773471,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.24,
|
|
"mean_token_accuracy": 0.1280357524752617,
|
|
"num_tokens": 870433.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.659976148605347,
|
|
"epoch": 0.04009355162044771,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.3483,
|
|
"mean_token_accuracy": 0.12422682046890259,
|
|
"num_tokens": 879059.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.637609958648682,
|
|
"epoch": 0.04051119278316071,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.3906,
|
|
"mean_token_accuracy": 0.11781356558203697,
|
|
"num_tokens": 888009.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.5305976390838625,
|
|
"epoch": 0.040928833945873704,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.11897468864917755,
|
|
"num_tokens": 897335.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.650092506408692,
|
|
"epoch": 0.0413464751085867,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.12942158281803132,
|
|
"num_tokens": 905802.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.505962324142456,
|
|
"epoch": 0.0417641162712997,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.2894,
|
|
"mean_token_accuracy": 0.1238292008638382,
|
|
"num_tokens": 914836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.481074333190918,
|
|
"epoch": 0.042181757434012694,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.2294,
|
|
"mean_token_accuracy": 0.12505172789096833,
|
|
"num_tokens": 924254.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.538729810714722,
|
|
"epoch": 0.04259939859672569,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.343,
|
|
"mean_token_accuracy": 0.12079363018274307,
|
|
"num_tokens": 933841.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.602547264099121,
|
|
"epoch": 0.04301703975943869,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.3927,
|
|
"mean_token_accuracy": 0.11534046903252601,
|
|
"num_tokens": 943304.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.526961374282837,
|
|
"epoch": 0.043434680922151685,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.2249,
|
|
"mean_token_accuracy": 0.12119961977005005,
|
|
"num_tokens": 952915.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.538762998580933,
|
|
"epoch": 0.043852322084864684,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.2935,
|
|
"mean_token_accuracy": 0.12450704649090767,
|
|
"num_tokens": 962752.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.56287579536438,
|
|
"epoch": 0.04426996324757768,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.309,
|
|
"mean_token_accuracy": 0.1171677753329277,
|
|
"num_tokens": 971240.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.575090742111206,
|
|
"epoch": 0.044687604410290675,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.3548,
|
|
"mean_token_accuracy": 0.11371841728687286,
|
|
"num_tokens": 981391.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.543639373779297,
|
|
"epoch": 0.045105245573003674,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.12311091870069504,
|
|
"num_tokens": 990551.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.53157148361206,
|
|
"epoch": 0.045522886735716674,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.2798,
|
|
"mean_token_accuracy": 0.12509959563612938,
|
|
"num_tokens": 999593.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.54977445602417,
|
|
"epoch": 0.045940527898429666,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.3563,
|
|
"mean_token_accuracy": 0.11864383593201637,
|
|
"num_tokens": 1008785.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.53155255317688,
|
|
"epoch": 0.046358169061142665,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.3408,
|
|
"mean_token_accuracy": 0.12224255055189133,
|
|
"num_tokens": 1016815.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.564304971694947,
|
|
"epoch": 0.046775810223855664,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.2135,
|
|
"mean_token_accuracy": 0.13047643452882768,
|
|
"num_tokens": 1026182.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.417008876800537,
|
|
"epoch": 0.04719345138656866,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.1538,
|
|
"mean_token_accuracy": 0.1273562304675579,
|
|
"num_tokens": 1034032.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.540080308914185,
|
|
"epoch": 0.047611092549281656,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.3695,
|
|
"mean_token_accuracy": 0.12380489185452462,
|
|
"num_tokens": 1043493.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.542786312103272,
|
|
"epoch": 0.048028733711994655,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.12197929993271828,
|
|
"num_tokens": 1052989.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.446332406997681,
|
|
"epoch": 0.048446374874707654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.2418,
|
|
"mean_token_accuracy": 0.12374974638223649,
|
|
"num_tokens": 1061803.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.586713171005249,
|
|
"epoch": 0.048864016037420646,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.3667,
|
|
"mean_token_accuracy": 0.12280836850404739,
|
|
"num_tokens": 1071227.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.523447036743164,
|
|
"epoch": 0.049281657200133645,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.3889,
|
|
"mean_token_accuracy": 0.12325869053602219,
|
|
"num_tokens": 1080082.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.480297422409057,
|
|
"epoch": 0.049699298362846644,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.2021,
|
|
"mean_token_accuracy": 0.12905326038599013,
|
|
"num_tokens": 1089750.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.378500175476074,
|
|
"epoch": 0.05011693952555964,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.2089,
|
|
"mean_token_accuracy": 0.12159204185009002,
|
|
"num_tokens": 1098691.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.468329238891601,
|
|
"epoch": 0.050534580688272636,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.2107,
|
|
"mean_token_accuracy": 0.1222094714641571,
|
|
"num_tokens": 1107602.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.37498927116394,
|
|
"epoch": 0.050952221850985635,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.1582,
|
|
"mean_token_accuracy": 0.12626441866159438,
|
|
"num_tokens": 1116426.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.563107347488403,
|
|
"epoch": 0.05136986301369863,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.3579,
|
|
"mean_token_accuracy": 0.12089578509330749,
|
|
"num_tokens": 1126221.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.436634206771851,
|
|
"epoch": 0.051787504176411626,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.2162,
|
|
"mean_token_accuracy": 0.13165414333343506,
|
|
"num_tokens": 1135662.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.47764105796814,
|
|
"epoch": 0.052205145339124626,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.1241353303194046,
|
|
"num_tokens": 1143963.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.503053283691406,
|
|
"epoch": 0.05262278650183762,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.2121,
|
|
"mean_token_accuracy": 0.12860342785716056,
|
|
"num_tokens": 1152470.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.398306846618652,
|
|
"epoch": 0.05304042766455062,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.1715,
|
|
"mean_token_accuracy": 0.12845860794186592,
|
|
"num_tokens": 1161257.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.530808067321777,
|
|
"epoch": 0.053458068827263616,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.3039,
|
|
"mean_token_accuracy": 0.12109335586428642,
|
|
"num_tokens": 1170969.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.558892440795899,
|
|
"epoch": 0.053875709989976615,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4402,
|
|
"mean_token_accuracy": 0.12084705233573914,
|
|
"num_tokens": 1181127.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.407193994522094,
|
|
"epoch": 0.05429335115268961,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.2425,
|
|
"mean_token_accuracy": 0.12455282807350158,
|
|
"num_tokens": 1190260.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.455674695968628,
|
|
"epoch": 0.05471099231540261,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.316,
|
|
"mean_token_accuracy": 0.12325879707932472,
|
|
"num_tokens": 1200013.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.5374016761779785,
|
|
"epoch": 0.055128633478115606,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.2256,
|
|
"mean_token_accuracy": 0.13025743141770363,
|
|
"num_tokens": 1209239.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.347896671295166,
|
|
"epoch": 0.0555462746408286,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.1814,
|
|
"mean_token_accuracy": 0.12614438980817794,
|
|
"num_tokens": 1218552.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.401571559906006,
|
|
"epoch": 0.0559639158035416,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.2656,
|
|
"mean_token_accuracy": 0.12373785302042961,
|
|
"num_tokens": 1227632.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.45081524848938,
|
|
"epoch": 0.056381556966254597,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.2906,
|
|
"mean_token_accuracy": 0.12531701177358628,
|
|
"num_tokens": 1236433.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.433235931396484,
|
|
"epoch": 0.05679919812896759,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.3248,
|
|
"mean_token_accuracy": 0.11682864874601365,
|
|
"num_tokens": 1245700.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.424199199676513,
|
|
"epoch": 0.05721683929168059,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.1626,
|
|
"mean_token_accuracy": 0.12845946177840234,
|
|
"num_tokens": 1254206.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.392566871643067,
|
|
"epoch": 0.05763448045439359,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.2238,
|
|
"mean_token_accuracy": 0.12663000896573068,
|
|
"num_tokens": 1263302.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.433683109283447,
|
|
"epoch": 0.05805212161710658,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.261,
|
|
"mean_token_accuracy": 0.12566009759902955,
|
|
"num_tokens": 1272998.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.42986831665039,
|
|
"epoch": 0.05846976277981958,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.2316,
|
|
"mean_token_accuracy": 0.12945592105388642,
|
|
"num_tokens": 1281955.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.384770917892456,
|
|
"epoch": 0.05888740394253258,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2693,
|
|
"mean_token_accuracy": 0.1220188558101654,
|
|
"num_tokens": 1291219.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.439512538909912,
|
|
"epoch": 0.05930504510524557,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.11803281754255295,
|
|
"num_tokens": 1300963.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.434574270248413,
|
|
"epoch": 0.05972268626795857,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.315,
|
|
"mean_token_accuracy": 0.11672014072537422,
|
|
"num_tokens": 1310112.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.382553958892823,
|
|
"epoch": 0.06014032743067157,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.2513,
|
|
"mean_token_accuracy": 0.12916786298155786,
|
|
"num_tokens": 1319309.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.326040887832642,
|
|
"epoch": 0.06055796859338457,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.12591121718287468,
|
|
"num_tokens": 1329049.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.351260471343994,
|
|
"epoch": 0.06097560975609756,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.0671,
|
|
"mean_token_accuracy": 0.12919704169034957,
|
|
"num_tokens": 1337770.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.254184007644653,
|
|
"epoch": 0.06139325091881056,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.1822,
|
|
"mean_token_accuracy": 0.1272610329091549,
|
|
"num_tokens": 1346705.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.3455441951751705,
|
|
"epoch": 0.06181089208152356,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.2394,
|
|
"mean_token_accuracy": 0.12634490579366683,
|
|
"num_tokens": 1354860.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.381866407394409,
|
|
"epoch": 0.06222853324423655,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.12138592973351478,
|
|
"num_tokens": 1364140.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.432730674743652,
|
|
"epoch": 0.06264617440694954,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3331,
|
|
"mean_token_accuracy": 0.11733241975307465,
|
|
"num_tokens": 1373645.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.377966737747192,
|
|
"epoch": 0.06306381556966255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2159,
|
|
"mean_token_accuracy": 0.13121263906359673,
|
|
"num_tokens": 1383291.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.239141368865967,
|
|
"epoch": 0.06348145673237554,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.1152,
|
|
"mean_token_accuracy": 0.1310908943414688,
|
|
"num_tokens": 1391172.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.377418088912964,
|
|
"epoch": 0.06389909789508853,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.1472,
|
|
"mean_token_accuracy": 0.12764590457081795,
|
|
"num_tokens": 1400864.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.295232057571411,
|
|
"epoch": 0.06431673905780154,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.2001,
|
|
"mean_token_accuracy": 0.12997447326779366,
|
|
"num_tokens": 1410570.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.313883256912232,
|
|
"epoch": 0.06473438022051453,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.1744,
|
|
"mean_token_accuracy": 0.1313069112598896,
|
|
"num_tokens": 1419536.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.338523483276367,
|
|
"epoch": 0.06515202138322754,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.091,
|
|
"mean_token_accuracy": 0.13004501089453696,
|
|
"num_tokens": 1428000.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.260497093200684,
|
|
"epoch": 0.06556966254594053,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2992,
|
|
"mean_token_accuracy": 0.12507489323616028,
|
|
"num_tokens": 1437789.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.270367765426636,
|
|
"epoch": 0.06598730370865352,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.1214,
|
|
"mean_token_accuracy": 0.1259957693517208,
|
|
"num_tokens": 1446848.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.279500675201416,
|
|
"epoch": 0.06640494487136653,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.1257844291627407,
|
|
"num_tokens": 1455749.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.253476810455322,
|
|
"epoch": 0.06682258603407952,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.0701,
|
|
"mean_token_accuracy": 0.1354301691055298,
|
|
"num_tokens": 1464556.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.333716917037964,
|
|
"epoch": 0.06724022719679251,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.2213,
|
|
"mean_token_accuracy": 0.12829236462712287,
|
|
"num_tokens": 1473617.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.306687116622925,
|
|
"epoch": 0.06765786835950552,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.2385,
|
|
"mean_token_accuracy": 0.12713917568325997,
|
|
"num_tokens": 1483006.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.430218935012817,
|
|
"epoch": 0.06807550952221851,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2582,
|
|
"mean_token_accuracy": 0.1252996154129505,
|
|
"num_tokens": 1493009.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.253592920303345,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.1341,
|
|
"mean_token_accuracy": 0.1317764475941658,
|
|
"num_tokens": 1501261.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.3305917263031,
|
|
"epoch": 0.06891079184764451,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.2536,
|
|
"mean_token_accuracy": 0.12618372738361358,
|
|
"num_tokens": 1511623.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.283257102966308,
|
|
"epoch": 0.0693284330103575,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2422,
|
|
"mean_token_accuracy": 0.12288018986582756,
|
|
"num_tokens": 1521741.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.252234697341919,
|
|
"epoch": 0.0697460741730705,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.1818,
|
|
"mean_token_accuracy": 0.12901844680309296,
|
|
"num_tokens": 1530988.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.257218217849731,
|
|
"epoch": 0.0701637153357835,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.13119714483618736,
|
|
"num_tokens": 1539415.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.338153076171875,
|
|
"epoch": 0.07058135649849649,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.12688441276550294,
|
|
"num_tokens": 1547969.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.164967966079712,
|
|
"epoch": 0.07099899766120948,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.08,
|
|
"mean_token_accuracy": 0.1340305209159851,
|
|
"num_tokens": 1557526.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.167168045043946,
|
|
"epoch": 0.07141663882392249,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.13036102801561356,
|
|
"num_tokens": 1565982.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.178088760375976,
|
|
"epoch": 0.07183427998663548,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.13804332464933394,
|
|
"num_tokens": 1574492.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.236712503433227,
|
|
"epoch": 0.07225192114934847,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.12888288199901582,
|
|
"num_tokens": 1583726.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.159904909133911,
|
|
"epoch": 0.07266956231206148,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1032,
|
|
"mean_token_accuracy": 0.12467294186353683,
|
|
"num_tokens": 1593780.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.252811336517334,
|
|
"epoch": 0.07308720347477447,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.1079,
|
|
"mean_token_accuracy": 0.1311504900455475,
|
|
"num_tokens": 1602746.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.235387468338013,
|
|
"epoch": 0.07350484463748747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.1317,
|
|
"mean_token_accuracy": 0.13153513595461847,
|
|
"num_tokens": 1611767.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.322087335586548,
|
|
"epoch": 0.07392248580020047,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.223,
|
|
"mean_token_accuracy": 0.13359929099678994,
|
|
"num_tokens": 1621568.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.234439277648926,
|
|
"epoch": 0.07434012696291346,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.1574,
|
|
"mean_token_accuracy": 0.1362864576280117,
|
|
"num_tokens": 1630650.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.207277011871338,
|
|
"epoch": 0.07475776812562646,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.1565,
|
|
"mean_token_accuracy": 0.1267276994884014,
|
|
"num_tokens": 1640482.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.311604309082031,
|
|
"epoch": 0.07517540928833946,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2126,
|
|
"mean_token_accuracy": 0.1277651831507683,
|
|
"num_tokens": 1649344.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.199459648132324,
|
|
"epoch": 0.07559305045105245,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.1479,
|
|
"mean_token_accuracy": 0.13086290359497071,
|
|
"num_tokens": 1658962.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.197014045715332,
|
|
"epoch": 0.07601069161376545,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.16,
|
|
"mean_token_accuracy": 0.12403983399271964,
|
|
"num_tokens": 1668615.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.247787952423096,
|
|
"epoch": 0.07642833277647845,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.1306306391954422,
|
|
"num_tokens": 1679282.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.110937595367432,
|
|
"epoch": 0.07684597393919144,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.1861,
|
|
"mean_token_accuracy": 0.13143347576260567,
|
|
"num_tokens": 1688362.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.203617334365845,
|
|
"epoch": 0.07726361510190444,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.0853,
|
|
"mean_token_accuracy": 0.12813379019498825,
|
|
"num_tokens": 1697593.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.284222555160523,
|
|
"epoch": 0.07768125626461744,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.1326735071837902,
|
|
"num_tokens": 1706961.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.214397430419922,
|
|
"epoch": 0.07809889742733044,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.1837,
|
|
"mean_token_accuracy": 0.13653906658291817,
|
|
"num_tokens": 1716222.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.132423162460327,
|
|
"epoch": 0.07851653859004344,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.0741,
|
|
"mean_token_accuracy": 0.12650192454457282,
|
|
"num_tokens": 1726750.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.258601665496826,
|
|
"epoch": 0.07893417975275643,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.12657316625118256,
|
|
"num_tokens": 1736262.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.192229986190796,
|
|
"epoch": 0.07935182091546943,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1729,
|
|
"mean_token_accuracy": 0.13067680075764657,
|
|
"num_tokens": 1745555.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.050552940368652,
|
|
"epoch": 0.07976946207818243,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.0643,
|
|
"mean_token_accuracy": 0.12940090522170067,
|
|
"num_tokens": 1754107.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.305977058410645,
|
|
"epoch": 0.08018710324089542,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.12384195700287819,
|
|
"num_tokens": 1762982.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.171813297271728,
|
|
"epoch": 0.08060474440360842,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.1338811330497265,
|
|
"num_tokens": 1772545.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.244448280334472,
|
|
"epoch": 0.08102238556632142,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2549,
|
|
"mean_token_accuracy": 0.12475204095244408,
|
|
"num_tokens": 1782052.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.1756124019622805,
|
|
"epoch": 0.08144002672903441,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.1337449759244919,
|
|
"num_tokens": 1791682.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.1777324199676515,
|
|
"epoch": 0.08185766789174741,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.0759,
|
|
"mean_token_accuracy": 0.13526007980108262,
|
|
"num_tokens": 1800526.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.219584560394287,
|
|
"epoch": 0.08227530905446041,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2113,
|
|
"mean_token_accuracy": 0.1325635403394699,
|
|
"num_tokens": 1810062.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.163633823394775,
|
|
"epoch": 0.0826929502171734,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.1872,
|
|
"mean_token_accuracy": 0.13362277597188948,
|
|
"num_tokens": 1818909.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.275831508636474,
|
|
"epoch": 0.0831105913798864,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.13871751874685287,
|
|
"num_tokens": 1827978.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.068942451477051,
|
|
"epoch": 0.0835282325425994,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.1366957776248455,
|
|
"num_tokens": 1837955.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.199518489837646,
|
|
"epoch": 0.0839458737053124,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999999987395534,
|
|
"loss": 6.1966,
|
|
"mean_token_accuracy": 0.12947369664907454,
|
|
"num_tokens": 1847699.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.2342846393585205,
|
|
"epoch": 0.08436351486802539,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999936189888,
|
|
"loss": 6.135,
|
|
"mean_token_accuracy": 0.1308988593518734,
|
|
"num_tokens": 1856490.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.187710952758789,
|
|
"epoch": 0.0847811560307384,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999845595285,
|
|
"loss": 6.1336,
|
|
"mean_token_accuracy": 0.1302417054772377,
|
|
"num_tokens": 1865644.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.139751815795899,
|
|
"epoch": 0.08519879719345139,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004999999715611727,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.13923914581537247,
|
|
"num_tokens": 1874450.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.1254647731781,
|
|
"epoch": 0.08561643835616438,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999999546239215,
|
|
"loss": 6.0891,
|
|
"mean_token_accuracy": 0.13145651072263717,
|
|
"num_tokens": 1883259.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.193487119674683,
|
|
"epoch": 0.08603407951887738,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999337477753,
|
|
"loss": 6.1689,
|
|
"mean_token_accuracy": 0.12691283002495765,
|
|
"num_tokens": 1891897.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.166404056549072,
|
|
"epoch": 0.08645172068159038,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999999089327344,
|
|
"loss": 6.1476,
|
|
"mean_token_accuracy": 0.12759166434407235,
|
|
"num_tokens": 1901011.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.058528995513916,
|
|
"epoch": 0.08686936184430337,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999998801787993,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.13580385074019433,
|
|
"num_tokens": 1910132.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.21063199043274,
|
|
"epoch": 0.08728700300701638,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999998474859704,
|
|
"loss": 6.1796,
|
|
"mean_token_accuracy": 0.13001134023070335,
|
|
"num_tokens": 1919938.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.021421146392822,
|
|
"epoch": 0.08770464416972937,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999998108542483,
|
|
"loss": 6.0474,
|
|
"mean_token_accuracy": 0.1303606778383255,
|
|
"num_tokens": 1928199.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.149118709564209,
|
|
"epoch": 0.08812228533244236,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999997702836339,
|
|
"loss": 6.0384,
|
|
"mean_token_accuracy": 0.1368630550801754,
|
|
"num_tokens": 1937133.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.19862322807312,
|
|
"epoch": 0.08853992649515537,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999997257741274,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.13205777183175088,
|
|
"num_tokens": 1946580.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.109546327590943,
|
|
"epoch": 0.08895756765786836,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049999967732573,
|
|
"loss": 6.1303,
|
|
"mean_token_accuracy": 0.1276082694530487,
|
|
"num_tokens": 1955413.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.293388748168946,
|
|
"epoch": 0.08937520882058135,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999996249384425,
|
|
"loss": 6.1897,
|
|
"mean_token_accuracy": 0.1298133671283722,
|
|
"num_tokens": 1964716.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.0309676170349125,
|
|
"epoch": 0.08979284998329436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999995686122657,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.13794475570321083,
|
|
"num_tokens": 1974081.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.057157135009765,
|
|
"epoch": 0.09021049114600735,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999995083472006,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.13763214722275735,
|
|
"num_tokens": 1983035.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.133276653289795,
|
|
"epoch": 0.09062813230872034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999994441432481,
|
|
"loss": 6.0401,
|
|
"mean_token_accuracy": 0.1399047665297985,
|
|
"num_tokens": 1992475.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.012667560577393,
|
|
"epoch": 0.09104577347143335,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999993760004097,
|
|
"loss": 6.1266,
|
|
"mean_token_accuracy": 0.12739486023783683,
|
|
"num_tokens": 2002729.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.0253236293792725,
|
|
"epoch": 0.09146341463414634,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999993039186864,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.13841661661863328,
|
|
"num_tokens": 2011319.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.083655738830567,
|
|
"epoch": 0.09188105579685933,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999992278980794,
|
|
"loss": 5.9924,
|
|
"mean_token_accuracy": 0.1362566351890564,
|
|
"num_tokens": 2020456.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.034357261657715,
|
|
"epoch": 0.09229869695957234,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999991479385901,
|
|
"loss": 6.0927,
|
|
"mean_token_accuracy": 0.13392627835273743,
|
|
"num_tokens": 2029417.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.154821872711182,
|
|
"epoch": 0.09271633812228533,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999990640402198,
|
|
"loss": 6.1738,
|
|
"mean_token_accuracy": 0.1311173379421234,
|
|
"num_tokens": 2039290.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.101737451553345,
|
|
"epoch": 0.09313397928499834,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999989762029701,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.13381630852818488,
|
|
"num_tokens": 2048485.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 5.9683490753173825,
|
|
"epoch": 0.09355162044771133,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999988844268425,
|
|
"loss": 5.9595,
|
|
"mean_token_accuracy": 0.14155827090144157,
|
|
"num_tokens": 2057131.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.020996618270874,
|
|
"epoch": 0.09396926161042432,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999987887118387,
|
|
"loss": 5.9606,
|
|
"mean_token_accuracy": 0.1338317573070526,
|
|
"num_tokens": 2066295.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.021601724624634,
|
|
"epoch": 0.09438690277313733,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999986890579602,
|
|
"loss": 5.9637,
|
|
"mean_token_accuracy": 0.1408805377781391,
|
|
"num_tokens": 2075656.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.0348409652709964,
|
|
"epoch": 0.09480454393585032,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999985854652087,
|
|
"loss": 6.1381,
|
|
"mean_token_accuracy": 0.129783895611763,
|
|
"num_tokens": 2086046.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.1812419414520265,
|
|
"epoch": 0.09522218509856331,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999984779335862,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.13610694855451583,
|
|
"num_tokens": 2094808.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 5.959377193450928,
|
|
"epoch": 0.09563982626127632,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999983664630945,
|
|
"loss": 6.0585,
|
|
"mean_token_accuracy": 0.1390154741704464,
|
|
"num_tokens": 2104155.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.033576393127442,
|
|
"epoch": 0.09605746742398931,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999982510537357,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.1419323816895485,
|
|
"num_tokens": 2112517.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 5.961051750183105,
|
|
"epoch": 0.0964751085867023,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999981317055116,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.1370644360780716,
|
|
"num_tokens": 2121355.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.07532811164856,
|
|
"epoch": 0.09689274974941531,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999980084184244,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.14000216126441956,
|
|
"num_tokens": 2129278.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.112037467956543,
|
|
"epoch": 0.0973103909121283,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999978811924762,
|
|
"loss": 6.209,
|
|
"mean_token_accuracy": 0.13468564450740814,
|
|
"num_tokens": 2139548.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.011156606674194,
|
|
"epoch": 0.09772803207484129,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999977500276693,
|
|
"loss": 6.1051,
|
|
"mean_token_accuracy": 0.13282948657870292,
|
|
"num_tokens": 2148765.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.156813764572144,
|
|
"epoch": 0.0981456732375543,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999976149240058,
|
|
"loss": 5.9998,
|
|
"mean_token_accuracy": 0.14147626087069512,
|
|
"num_tokens": 2157482.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.06043438911438,
|
|
"epoch": 0.09856331440026729,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999974758814884,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.12927817851305007,
|
|
"num_tokens": 2167320.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.090041780471802,
|
|
"epoch": 0.09898095556298028,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999973329001193,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.13234857842326164,
|
|
"num_tokens": 2175454.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.048929071426391,
|
|
"epoch": 0.09939859672569329,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999971859799009,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.137349022179842,
|
|
"num_tokens": 2184391.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 5.9458996772766115,
|
|
"epoch": 0.09981623788840628,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999970351208361,
|
|
"loss": 5.8738,
|
|
"mean_token_accuracy": 0.1423418328166008,
|
|
"num_tokens": 2193309.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.062114095687866,
|
|
"epoch": 0.10023387905111927,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999968803229275,
|
|
"loss": 6.0268,
|
|
"mean_token_accuracy": 0.13685409501194953,
|
|
"num_tokens": 2202057.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.010811853408813,
|
|
"epoch": 0.10065152021383228,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999967215861775,
|
|
"loss": 6.1207,
|
|
"mean_token_accuracy": 0.13319561630487442,
|
|
"num_tokens": 2212384.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.149314880371094,
|
|
"epoch": 0.10106916137654527,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499996558910589,
|
|
"loss": 6.0364,
|
|
"mean_token_accuracy": 0.13858548328280448,
|
|
"num_tokens": 2221451.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 5.897707605361939,
|
|
"epoch": 0.10148680253925826,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000499996392296165,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.1363538235425949,
|
|
"num_tokens": 2230440.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.108274269104004,
|
|
"epoch": 0.10190444370197127,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999962217429083,
|
|
"loss": 6.1278,
|
|
"mean_token_accuracy": 0.1263136975467205,
|
|
"num_tokens": 2239985.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.034344911575317,
|
|
"epoch": 0.10232208486468426,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 5.9906,
|
|
"mean_token_accuracy": 0.13609189465641974,
|
|
"num_tokens": 2250391.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.079465055465699,
|
|
"epoch": 0.10273972602739725,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499995868819909,
|
|
"loss": 6.0937,
|
|
"mean_token_accuracy": 0.12762524262070657,
|
|
"num_tokens": 2260620.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.125043344497681,
|
|
"epoch": 0.10315736719011026,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999956864501725,
|
|
"loss": 6.0771,
|
|
"mean_token_accuracy": 0.13054439499974252,
|
|
"num_tokens": 2271176.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.024161291122437,
|
|
"epoch": 0.10357500835282325,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999955001416156,
|
|
"loss": 5.9637,
|
|
"mean_token_accuracy": 0.1394001565873623,
|
|
"num_tokens": 2280371.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 5.873808765411377,
|
|
"epoch": 0.10399264951553625,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999953098942417,
|
|
"loss": 5.9383,
|
|
"mean_token_accuracy": 0.13987089917063714,
|
|
"num_tokens": 2289015.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 5.993573093414307,
|
|
"epoch": 0.10441029067824925,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999951157080541,
|
|
"loss": 6.011,
|
|
"mean_token_accuracy": 0.14008186012506485,
|
|
"num_tokens": 2297409.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.020661783218384,
|
|
"epoch": 0.10482793184096224,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999949175830561,
|
|
"loss": 6.0346,
|
|
"mean_token_accuracy": 0.137710864841938,
|
|
"num_tokens": 2307017.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 5.966087722778321,
|
|
"epoch": 0.10524557300367524,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999947155192514,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.14721441268920898,
|
|
"num_tokens": 2316014.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.035770273208618,
|
|
"epoch": 0.10566321416638824,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999945095166433,
|
|
"loss": 5.9742,
|
|
"mean_token_accuracy": 0.14057080522179605,
|
|
"num_tokens": 2326326.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.115755558013916,
|
|
"epoch": 0.10608085532910123,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999942995752354,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.13691574186086655,
|
|
"num_tokens": 2335108.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 5.959864377975464,
|
|
"epoch": 0.10649849649181423,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999940856950315,
|
|
"loss": 5.9885,
|
|
"mean_token_accuracy": 0.14240883886814118,
|
|
"num_tokens": 2343971.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.033252716064453,
|
|
"epoch": 0.10691613765452723,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999938678760354,
|
|
"loss": 6.0546,
|
|
"mean_token_accuracy": 0.13366041257977485,
|
|
"num_tokens": 2353742.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 5.9920961380004885,
|
|
"epoch": 0.10733377881724022,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999936461182507,
|
|
"loss": 5.9948,
|
|
"mean_token_accuracy": 0.14326683208346366,
|
|
"num_tokens": 2363629.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 5.8916154384613035,
|
|
"epoch": 0.10775141997995323,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999934204216814,
|
|
"loss": 5.8557,
|
|
"mean_token_accuracy": 0.14521737545728683,
|
|
"num_tokens": 2372705.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 5.9855352401733395,
|
|
"epoch": 0.10816906114266622,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999931907863315,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.14111716747283937,
|
|
"num_tokens": 2382136.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 5.877673768997193,
|
|
"epoch": 0.10858670230537922,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499992957212205,
|
|
"loss": 5.9341,
|
|
"mean_token_accuracy": 0.1387516625225544,
|
|
"num_tokens": 2391060.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.04531421661377,
|
|
"epoch": 0.10900434346809222,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999927196993059,
|
|
"loss": 6.0668,
|
|
"mean_token_accuracy": 0.136396811157465,
|
|
"num_tokens": 2399885.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.001427459716797,
|
|
"epoch": 0.10942198463080521,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999924782476384,
|
|
"loss": 5.931,
|
|
"mean_token_accuracy": 0.14695603102445604,
|
|
"num_tokens": 2409654.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.023379850387573,
|
|
"epoch": 0.1098396257935182,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999922328572068,
|
|
"loss": 6.0087,
|
|
"mean_token_accuracy": 0.13872749507427215,
|
|
"num_tokens": 2419342.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 5.900698280334472,
|
|
"epoch": 0.11025726695623121,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999919835280154,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.14329665824770926,
|
|
"num_tokens": 2428845.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.046743535995484,
|
|
"epoch": 0.1106749081189442,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999917302600684,
|
|
"loss": 5.8937,
|
|
"mean_token_accuracy": 0.14875416159629823,
|
|
"num_tokens": 2437134.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 5.708086442947388,
|
|
"epoch": 0.1110925492816572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999914730533704,
|
|
"loss": 5.7293,
|
|
"mean_token_accuracy": 0.15531845688819884,
|
|
"num_tokens": 2445438.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.002161979675293,
|
|
"epoch": 0.1115101904443702,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999912119079258,
|
|
"loss": 6.0527,
|
|
"mean_token_accuracy": 0.13914170265197753,
|
|
"num_tokens": 2455039.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.0124329090118405,
|
|
"epoch": 0.1119278316070832,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999909468237393,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.13686869218945502,
|
|
"num_tokens": 2465170.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.87831563949585,
|
|
"epoch": 0.11234547276979619,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999906778008153,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.1533431127667427,
|
|
"num_tokens": 2473688.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 5.915750741958618,
|
|
"epoch": 0.11276311393250919,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999904048391588,
|
|
"loss": 6.0191,
|
|
"mean_token_accuracy": 0.13419281020760537,
|
|
"num_tokens": 2482335.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 5.989591646194458,
|
|
"epoch": 0.11318075509522219,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999901279387743,
|
|
"loss": 5.9312,
|
|
"mean_token_accuracy": 0.14448264613747597,
|
|
"num_tokens": 2491808.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.086487817764282,
|
|
"epoch": 0.11359839625793518,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999898470996669,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.13440220579504966,
|
|
"num_tokens": 2501422.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 5.9091236114501955,
|
|
"epoch": 0.11401603742064818,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999895623218415,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.14603495746850967,
|
|
"num_tokens": 2511201.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 5.936640071868896,
|
|
"epoch": 0.11443367858336118,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999892736053027,
|
|
"loss": 5.8957,
|
|
"mean_token_accuracy": 0.1403353899717331,
|
|
"num_tokens": 2519798.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.891090345382691,
|
|
"epoch": 0.11485131974607417,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999889809500561,
|
|
"loss": 5.8755,
|
|
"mean_token_accuracy": 0.1445053994655609,
|
|
"num_tokens": 2529177.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.015834188461303,
|
|
"epoch": 0.11526896090878717,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999886843561065,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.14721576496958733,
|
|
"num_tokens": 2537571.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 5.768728446960449,
|
|
"epoch": 0.11568660207150017,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999883838234592,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.1494941793382168,
|
|
"num_tokens": 2546258.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.879445552825928,
|
|
"epoch": 0.11610424323421316,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999880793521194,
|
|
"loss": 5.8101,
|
|
"mean_token_accuracy": 0.14160490334033965,
|
|
"num_tokens": 2555862.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.703860473632813,
|
|
"epoch": 0.11652188439692616,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999877709420924,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.14771698862314225,
|
|
"num_tokens": 2564583.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.946020936965942,
|
|
"epoch": 0.11693952555963916,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999874585933837,
|
|
"loss": 5.9224,
|
|
"mean_token_accuracy": 0.14428764581680298,
|
|
"num_tokens": 2574217.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 5.874564838409424,
|
|
"epoch": 0.11735716672235215,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999871423059987,
|
|
"loss": 5.8278,
|
|
"mean_token_accuracy": 0.14492169469594957,
|
|
"num_tokens": 2582821.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.90300989151001,
|
|
"epoch": 0.11777480788506516,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499986822079943,
|
|
"loss": 6.0026,
|
|
"mean_token_accuracy": 0.1350848987698555,
|
|
"num_tokens": 2592748.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.979686975479126,
|
|
"epoch": 0.11819244904777815,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999864979152221,
|
|
"loss": 5.8824,
|
|
"mean_token_accuracy": 0.14854978621006013,
|
|
"num_tokens": 2602053.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.808524131774902,
|
|
"epoch": 0.11861009021049114,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999861698118417,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.14355539306998252,
|
|
"num_tokens": 2610557.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.955320358276367,
|
|
"epoch": 0.11902773137320415,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999858377698076,
|
|
"loss": 5.8513,
|
|
"mean_token_accuracy": 0.14397183433175087,
|
|
"num_tokens": 2619628.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.067613363265991,
|
|
"epoch": 0.11944537253591714,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999855017891256,
|
|
"loss": 6.0207,
|
|
"mean_token_accuracy": 0.14067387729883193,
|
|
"num_tokens": 2629284.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.882795715332032,
|
|
"epoch": 0.11986301369863013,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999851618698017,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.14827706664800644,
|
|
"num_tokens": 2638001.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 5.891476774215699,
|
|
"epoch": 0.12028065486134314,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999848180118416,
|
|
"loss": 5.9157,
|
|
"mean_token_accuracy": 0.15219354629516602,
|
|
"num_tokens": 2647071.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.973889017105103,
|
|
"epoch": 0.12069829602405613,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999844702152516,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.14990584850311278,
|
|
"num_tokens": 2655826.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.833336019515992,
|
|
"epoch": 0.12111593718676913,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999841184800374,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.15365617871284484,
|
|
"num_tokens": 2664431.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.761509227752685,
|
|
"epoch": 0.12153357834948213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999837628062055,
|
|
"loss": 5.6995,
|
|
"mean_token_accuracy": 0.15763423219323158,
|
|
"num_tokens": 2673631.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 5.807348442077637,
|
|
"epoch": 0.12195121951219512,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999834031937621,
|
|
"loss": 5.9755,
|
|
"mean_token_accuracy": 0.1450788274407387,
|
|
"num_tokens": 2683363.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.004406070709228,
|
|
"epoch": 0.12236886067490813,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999830396427133,
|
|
"loss": 5.9219,
|
|
"mean_token_accuracy": 0.14206716865301133,
|
|
"num_tokens": 2692533.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.8194908618927,
|
|
"epoch": 0.12278650183762112,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999826721530657,
|
|
"loss": 5.9232,
|
|
"mean_token_accuracy": 0.15276242047548294,
|
|
"num_tokens": 2701211.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.959702110290527,
|
|
"epoch": 0.12320414300033411,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999823007248255,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.14682099223136902,
|
|
"num_tokens": 2709543.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.9004326343536375,
|
|
"epoch": 0.12362178416304712,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999819253579992,
|
|
"loss": 5.9041,
|
|
"mean_token_accuracy": 0.14219618514180182,
|
|
"num_tokens": 2718336.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.887391233444214,
|
|
"epoch": 0.12403942532576011,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999815460525938,
|
|
"loss": 5.8491,
|
|
"mean_token_accuracy": 0.15181448459625244,
|
|
"num_tokens": 2726504.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.889515399932861,
|
|
"epoch": 0.1244570664884731,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999811628086155,
|
|
"loss": 5.8877,
|
|
"mean_token_accuracy": 0.14508116692304612,
|
|
"num_tokens": 2736076.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.805719614028931,
|
|
"epoch": 0.1248747076511861,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499980775626071,
|
|
"loss": 5.7985,
|
|
"mean_token_accuracy": 0.1503925770521164,
|
|
"num_tokens": 2745497.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.8484405994415285,
|
|
"epoch": 0.12529234881389908,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999803845049674,
|
|
"loss": 5.9377,
|
|
"mean_token_accuracy": 0.14518412500619887,
|
|
"num_tokens": 2754455.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.031361675262451,
|
|
"epoch": 0.1257099899766121,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999799894453112,
|
|
"loss": 5.9596,
|
|
"mean_token_accuracy": 0.14515393003821372,
|
|
"num_tokens": 2763603.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.842563438415527,
|
|
"epoch": 0.1261276311393251,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999795904471095,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.14701997935771943,
|
|
"num_tokens": 2772152.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.936494588851929,
|
|
"epoch": 0.12654527230203808,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999791875103694,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.14711305350065232,
|
|
"num_tokens": 2781459.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.912358713150025,
|
|
"epoch": 0.12696291346475108,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999787806350977,
|
|
"loss": 5.8773,
|
|
"mean_token_accuracy": 0.14168751537799834,
|
|
"num_tokens": 2791177.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.809263038635254,
|
|
"epoch": 0.1273805546274641,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999783698213016,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.1511882796883583,
|
|
"num_tokens": 2800543.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.718258190155029,
|
|
"epoch": 0.12779819579017707,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999779550689885,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.1562495306134224,
|
|
"num_tokens": 2809301.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.946142387390137,
|
|
"epoch": 0.12821583695289007,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999775363781654,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.13951645120978357,
|
|
"num_tokens": 2818269.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.855810689926147,
|
|
"epoch": 0.12863347811560308,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999771137488395,
|
|
"loss": 5.7879,
|
|
"mean_token_accuracy": 0.15382847785949708,
|
|
"num_tokens": 2827170.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.764991426467896,
|
|
"epoch": 0.12905111927831608,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999766871810188,
|
|
"loss": 5.7656,
|
|
"mean_token_accuracy": 0.15415056496858598,
|
|
"num_tokens": 2835320.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.850279855728149,
|
|
"epoch": 0.12946876044102906,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999762566747101,
|
|
"loss": 5.8505,
|
|
"mean_token_accuracy": 0.14932266920804976,
|
|
"num_tokens": 2843755.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.914557886123657,
|
|
"epoch": 0.12988640160374207,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999758222299214,
|
|
"loss": 5.8955,
|
|
"mean_token_accuracy": 0.1388828009366989,
|
|
"num_tokens": 2853462.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.80288872718811,
|
|
"epoch": 0.13030404276645507,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999753838466601,
|
|
"loss": 5.8131,
|
|
"mean_token_accuracy": 0.14732857197523117,
|
|
"num_tokens": 2863041.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.004314374923706,
|
|
"epoch": 0.13072168392916805,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999749415249338,
|
|
"loss": 6.0175,
|
|
"mean_token_accuracy": 0.14584584459662436,
|
|
"num_tokens": 2873019.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.770129728317261,
|
|
"epoch": 0.13113932509188106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999744952647505,
|
|
"loss": 5.7567,
|
|
"mean_token_accuracy": 0.14778472259640693,
|
|
"num_tokens": 2881467.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.8767143249511715,
|
|
"epoch": 0.13155696625459407,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999740450661176,
|
|
"loss": 5.8573,
|
|
"mean_token_accuracy": 0.14663312584161758,
|
|
"num_tokens": 2890914.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.784161996841431,
|
|
"epoch": 0.13197460741730704,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999735909290436,
|
|
"loss": 5.7828,
|
|
"mean_token_accuracy": 0.14994997084140776,
|
|
"num_tokens": 2901164.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.883551549911499,
|
|
"epoch": 0.13239224858002005,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999731328535358,
|
|
"loss": 5.9144,
|
|
"mean_token_accuracy": 0.1454067997634411,
|
|
"num_tokens": 2910560.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.796862983703614,
|
|
"epoch": 0.13280988974273306,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999726708396026,
|
|
"loss": 5.7264,
|
|
"mean_token_accuracy": 0.1551614746451378,
|
|
"num_tokens": 2918980.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.845749855041504,
|
|
"epoch": 0.13322753090544603,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499972204887252,
|
|
"loss": 5.9292,
|
|
"mean_token_accuracy": 0.14284173548221588,
|
|
"num_tokens": 2929516.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.866528034210205,
|
|
"epoch": 0.13364517206815904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999717349964922,
|
|
"loss": 6.0135,
|
|
"mean_token_accuracy": 0.13401781842112542,
|
|
"num_tokens": 2940603.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.975286054611206,
|
|
"epoch": 0.13406281323087205,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999712611673313,
|
|
"loss": 5.8426,
|
|
"mean_token_accuracy": 0.1439616158604622,
|
|
"num_tokens": 2950082.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.723266506195069,
|
|
"epoch": 0.13448045439358502,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999707833997777,
|
|
"loss": 5.7138,
|
|
"mean_token_accuracy": 0.1633479043841362,
|
|
"num_tokens": 2959098.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.87523307800293,
|
|
"epoch": 0.13489809555629803,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999703016938398,
|
|
"loss": 5.8386,
|
|
"mean_token_accuracy": 0.15109211057424546,
|
|
"num_tokens": 2968585.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.831326818466186,
|
|
"epoch": 0.13531573671901104,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499969816049526,
|
|
"loss": 5.878,
|
|
"mean_token_accuracy": 0.14930004104971886,
|
|
"num_tokens": 2978430.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.996936225891114,
|
|
"epoch": 0.13573337788172402,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999693264668446,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.14231408908963203,
|
|
"num_tokens": 2988398.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.878012323379517,
|
|
"epoch": 0.13615101904443702,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999688329458045,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.14286330938339234,
|
|
"num_tokens": 2999255.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.927907991409302,
|
|
"epoch": 0.13656866020715003,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999683354864141,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.14798136353492736,
|
|
"num_tokens": 3008638.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.776216173171997,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999678340886823,
|
|
"loss": 5.857,
|
|
"mean_token_accuracy": 0.1482193261384964,
|
|
"num_tokens": 3018070.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.791409111022949,
|
|
"epoch": 0.137403942532576,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999673287526176,
|
|
"loss": 5.8119,
|
|
"mean_token_accuracy": 0.14728376343846322,
|
|
"num_tokens": 3027878.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.978458023071289,
|
|
"epoch": 0.13782158369528902,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999668194782291,
|
|
"loss": 5.9885,
|
|
"mean_token_accuracy": 0.1419169157743454,
|
|
"num_tokens": 3037031.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.949056673049927,
|
|
"epoch": 0.138239224858002,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999663062655257,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.140587417781353,
|
|
"num_tokens": 3046311.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.834480047225952,
|
|
"epoch": 0.138656866020715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999657891145162,
|
|
"loss": 5.737,
|
|
"mean_token_accuracy": 0.1507701277732849,
|
|
"num_tokens": 3055108.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.703247451782227,
|
|
"epoch": 0.139074507183428,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999652680252099,
|
|
"loss": 5.7811,
|
|
"mean_token_accuracy": 0.15281276553869247,
|
|
"num_tokens": 3063492.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.96858491897583,
|
|
"epoch": 0.139492148346141,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999647429976157,
|
|
"loss": 5.839,
|
|
"mean_token_accuracy": 0.15251049250364304,
|
|
"num_tokens": 3072572.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.884686231613159,
|
|
"epoch": 0.139909789508854,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999642140317429,
|
|
"loss": 5.8876,
|
|
"mean_token_accuracy": 0.1460355408489704,
|
|
"num_tokens": 3082942.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.78411111831665,
|
|
"epoch": 0.140327430671567,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999636811276007,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.14870428889989853,
|
|
"num_tokens": 3091410.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.933750295639038,
|
|
"epoch": 0.14074507183427998,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999631442851986,
|
|
"loss": 5.9126,
|
|
"mean_token_accuracy": 0.1502613291144371,
|
|
"num_tokens": 3100626.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.747744131088257,
|
|
"epoch": 0.14116271299699298,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999626035045458,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.15668077766895294,
|
|
"num_tokens": 3109339.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.869397354125977,
|
|
"epoch": 0.141580354159706,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999620587856519,
|
|
"loss": 5.8462,
|
|
"mean_token_accuracy": 0.1474672093987465,
|
|
"num_tokens": 3118636.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.770104169845581,
|
|
"epoch": 0.14199799532241897,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999615101285262,
|
|
"loss": 5.8111,
|
|
"mean_token_accuracy": 0.14746451154351234,
|
|
"num_tokens": 3128162.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.8655181407928465,
|
|
"epoch": 0.14241563648513197,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999609575331786,
|
|
"loss": 5.8179,
|
|
"mean_token_accuracy": 0.15379944443702698,
|
|
"num_tokens": 3136451.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.857501363754272,
|
|
"epoch": 0.14283327764784498,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999604009996186,
|
|
"loss": 5.8331,
|
|
"mean_token_accuracy": 0.14673274308443068,
|
|
"num_tokens": 3146599.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.884437608718872,
|
|
"epoch": 0.14325091881055796,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499959840527856,
|
|
"loss": 5.8732,
|
|
"mean_token_accuracy": 0.14682791605591775,
|
|
"num_tokens": 3155941.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.824529457092285,
|
|
"epoch": 0.14366855997327097,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999592761179007,
|
|
"loss": 5.8059,
|
|
"mean_token_accuracy": 0.15331910401582718,
|
|
"num_tokens": 3164641.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.833645057678223,
|
|
"epoch": 0.14408620113598397,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999587077697624,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.15982660353183747,
|
|
"num_tokens": 3173701.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.684833717346192,
|
|
"epoch": 0.14450384229869695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999581354834512,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.1520286552608013,
|
|
"num_tokens": 3182268.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.74345817565918,
|
|
"epoch": 0.14492148346140996,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499957559258977,
|
|
"loss": 5.7711,
|
|
"mean_token_accuracy": 0.15220290571451187,
|
|
"num_tokens": 3191513.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.77564492225647,
|
|
"epoch": 0.14533912462412296,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049995697909635,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.15256546586751937,
|
|
"num_tokens": 3200580.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.737341022491455,
|
|
"epoch": 0.14575676578683594,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999563949955803,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.15687910318374634,
|
|
"num_tokens": 3209053.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.808221817016602,
|
|
"epoch": 0.14617440694954895,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499955806956678,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.1543448254466057,
|
|
"num_tokens": 3218241.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.880738401412964,
|
|
"epoch": 0.14659204811226195,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999552149796536,
|
|
"loss": 5.8514,
|
|
"mean_token_accuracy": 0.1490916818380356,
|
|
"num_tokens": 3227887.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.768217468261719,
|
|
"epoch": 0.14700968927497493,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999546190645175,
|
|
"loss": 5.6692,
|
|
"mean_token_accuracy": 0.16196279525756835,
|
|
"num_tokens": 3237281.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.684476280212403,
|
|
"epoch": 0.14742733043768794,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999540192112799,
|
|
"loss": 5.7118,
|
|
"mean_token_accuracy": 0.15405311733484267,
|
|
"num_tokens": 3246907.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.660418939590454,
|
|
"epoch": 0.14784497160040094,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999534154199514,
|
|
"loss": 5.7163,
|
|
"mean_token_accuracy": 0.1486714243888855,
|
|
"num_tokens": 3256312.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.922216749191284,
|
|
"epoch": 0.14826261276311392,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999528076905426,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.1525414004921913,
|
|
"num_tokens": 3265554.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.621938705444336,
|
|
"epoch": 0.14868025392582693,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999521960230641,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.15837963819503784,
|
|
"num_tokens": 3274731.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.7696099281311035,
|
|
"epoch": 0.14909789508853993,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.1475925050675869,
|
|
"num_tokens": 3283518.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.852998208999634,
|
|
"epoch": 0.1495155362512529,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499950960873941,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.1533878356218338,
|
|
"num_tokens": 3292244.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.8209583282470705,
|
|
"epoch": 0.14993317741396592,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999503373923182,
|
|
"loss": 5.7746,
|
|
"mean_token_accuracy": 0.15582873076200485,
|
|
"num_tokens": 3301198.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.733056211471558,
|
|
"epoch": 0.15035081857667892,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999497099726687,
|
|
"loss": 5.7494,
|
|
"mean_token_accuracy": 0.15889813750982285,
|
|
"num_tokens": 3309983.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.81738691329956,
|
|
"epoch": 0.1507684597393919,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999490786150039,
|
|
"loss": 5.8432,
|
|
"mean_token_accuracy": 0.147987063229084,
|
|
"num_tokens": 3319313.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.742344903945923,
|
|
"epoch": 0.1511861009021049,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999484433193348,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.15073793679475783,
|
|
"num_tokens": 3327497.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.707638788223266,
|
|
"epoch": 0.15160374206481791,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999478040856722,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.1553061291575432,
|
|
"num_tokens": 3337029.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.660393095016479,
|
|
"epoch": 0.1520213832275309,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999471609140276,
|
|
"loss": 5.675,
|
|
"mean_token_accuracy": 0.15133372247219085,
|
|
"num_tokens": 3346243.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.844138050079346,
|
|
"epoch": 0.1524390243902439,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999465138044122,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.150594063103199,
|
|
"num_tokens": 3354846.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.748153495788574,
|
|
"epoch": 0.1528566655529569,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999458627568373,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.1485428184270859,
|
|
"num_tokens": 3364683.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.829200696945191,
|
|
"epoch": 0.15327430671566988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999452077713144,
|
|
"loss": 5.7401,
|
|
"mean_token_accuracy": 0.14999438524246217,
|
|
"num_tokens": 3374652.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.692996788024902,
|
|
"epoch": 0.1536919478783829,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999445488478547,
|
|
"loss": 5.7464,
|
|
"mean_token_accuracy": 0.1528235137462616,
|
|
"num_tokens": 3384040.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.801222896575927,
|
|
"epoch": 0.1541095890410959,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00049994388598647,
|
|
"loss": 5.8162,
|
|
"mean_token_accuracy": 0.14949264377355576,
|
|
"num_tokens": 3393185.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.708631277084351,
|
|
"epoch": 0.15452723020380887,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999432191871719,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.15880197882652283,
|
|
"num_tokens": 3403077.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.772182989120483,
|
|
"epoch": 0.15494487136652188,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999425484499718,
|
|
"loss": 5.7194,
|
|
"mean_token_accuracy": 0.16176845729351044,
|
|
"num_tokens": 3412165.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.772862243652344,
|
|
"epoch": 0.1553625125292349,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999418737748817,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.14864142686128617,
|
|
"num_tokens": 3421162.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.872934341430664,
|
|
"epoch": 0.15578015369194786,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999411951619134,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.1428262896835804,
|
|
"num_tokens": 3430363.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.807984781265259,
|
|
"epoch": 0.15619779485466087,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999405126110786,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.15092551931738854,
|
|
"num_tokens": 3439199.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.957257461547852,
|
|
"epoch": 0.15661543601737388,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999398261223895,
|
|
"loss": 5.8731,
|
|
"mean_token_accuracy": 0.14979226514697075,
|
|
"num_tokens": 3448720.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.749342966079712,
|
|
"epoch": 0.15703307718008688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999391356958579,
|
|
"loss": 5.8455,
|
|
"mean_token_accuracy": 0.14971398413181305,
|
|
"num_tokens": 3458472.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.749511766433716,
|
|
"epoch": 0.15745071834279986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499938441331496,
|
|
"loss": 5.7952,
|
|
"mean_token_accuracy": 0.15146801769733428,
|
|
"num_tokens": 3467140.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.867589330673217,
|
|
"epoch": 0.15786835950551287,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999377430293159,
|
|
"loss": 5.7745,
|
|
"mean_token_accuracy": 0.15411789417266847,
|
|
"num_tokens": 3476431.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.766841220855713,
|
|
"epoch": 0.15828600066822587,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999370407893299,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.15346913933753967,
|
|
"num_tokens": 3485768.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.807104873657226,
|
|
"epoch": 0.15870364183093885,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999363346115501,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.14504164904356004,
|
|
"num_tokens": 3495678.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.785052108764648,
|
|
"epoch": 0.15912128299365186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999356244959893,
|
|
"loss": 5.8342,
|
|
"mean_token_accuracy": 0.1516023814678192,
|
|
"num_tokens": 3505168.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.740941047668457,
|
|
"epoch": 0.15953892415636486,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999349104426594,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.15149827301502228,
|
|
"num_tokens": 3514498.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.848452997207642,
|
|
"epoch": 0.15995656531907784,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999341924515732,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.15026968866586685,
|
|
"num_tokens": 3524617.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.668032789230347,
|
|
"epoch": 0.16037420648179085,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999334705227431,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.15639639049768447,
|
|
"num_tokens": 3533523.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.7723455905914305,
|
|
"epoch": 0.16079184764450385,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499932744656182,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.15217868536710738,
|
|
"num_tokens": 3542922.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.797222757339478,
|
|
"epoch": 0.16120948880721683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999320148519024,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.154755599796772,
|
|
"num_tokens": 3551827.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.708801507949829,
|
|
"epoch": 0.16162712996992984,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999312811099171,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.15864891856908797,
|
|
"num_tokens": 3560911.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.6975208759307865,
|
|
"epoch": 0.16204477113264285,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999305434302391,
|
|
"loss": 5.7543,
|
|
"mean_token_accuracy": 0.14677345082163812,
|
|
"num_tokens": 3569473.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.7810064315795895,
|
|
"epoch": 0.16246241229535582,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499929801812881,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.15499909371137618,
|
|
"num_tokens": 3578843.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.788356876373291,
|
|
"epoch": 0.16288005345806883,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999290562578561,
|
|
"loss": 5.7561,
|
|
"mean_token_accuracy": 0.15244330316781998,
|
|
"num_tokens": 3588304.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.7127964973449705,
|
|
"epoch": 0.16329769462078184,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999283067651773,
|
|
"loss": 5.8055,
|
|
"mean_token_accuracy": 0.14917491376399994,
|
|
"num_tokens": 3598354.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.894095182418823,
|
|
"epoch": 0.16371533578349481,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999275533348577,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.14917806088924407,
|
|
"num_tokens": 3607503.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.645402431488037,
|
|
"epoch": 0.16413297694620782,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999267959669106,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.15993930548429489,
|
|
"num_tokens": 3617467.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.7752259254455565,
|
|
"epoch": 0.16455061810892083,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999260346613491,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.15142679512500762,
|
|
"num_tokens": 3627048.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.651623249053955,
|
|
"epoch": 0.1649682592716338,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999252694181867,
|
|
"loss": 5.6978,
|
|
"mean_token_accuracy": 0.1521272361278534,
|
|
"num_tokens": 3636683.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.696958827972412,
|
|
"epoch": 0.1653859004343468,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999245002374367,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.16368645280599595,
|
|
"num_tokens": 3645231.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.720323944091797,
|
|
"epoch": 0.16580354159705982,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999237271191125,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.15285556465387345,
|
|
"num_tokens": 3653851.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.692817211151123,
|
|
"epoch": 0.1662211827597728,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999229500632279,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.1602617844939232,
|
|
"num_tokens": 3662720.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.616102457046509,
|
|
"epoch": 0.1666388239224858,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999221690697961,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.15996311008930206,
|
|
"num_tokens": 3671777.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.6898268699646,
|
|
"epoch": 0.1670564650851988,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999213841388312,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.16112901419401168,
|
|
"num_tokens": 3681390.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.791441488265991,
|
|
"epoch": 0.16747410624791179,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999205952703466,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.15657739117741584,
|
|
"num_tokens": 3690899.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.80651216506958,
|
|
"epoch": 0.1678917474106248,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999198024643563,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.14452483803033828,
|
|
"num_tokens": 3699891.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.6384241580963135,
|
|
"epoch": 0.1683093885733378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999190057208741,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.1593468502163887,
|
|
"num_tokens": 3709860.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.729552555084228,
|
|
"epoch": 0.16872702973605078,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499918205039914,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.15205028057098388,
|
|
"num_tokens": 3718896.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.710118341445923,
|
|
"epoch": 0.16914467089876378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999174004214899,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.1561296820640564,
|
|
"num_tokens": 3727355.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.6436944007873535,
|
|
"epoch": 0.1695623120614768,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999165918656161,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.15167264267802238,
|
|
"num_tokens": 3736191.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.8228062152862545,
|
|
"epoch": 0.16997995322418977,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999157793723065,
|
|
"loss": 5.7164,
|
|
"mean_token_accuracy": 0.1563839003443718,
|
|
"num_tokens": 3744832.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.607315397262573,
|
|
"epoch": 0.17039759438690277,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999149629415755,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.15334342569112777,
|
|
"num_tokens": 3753835.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.858393764495849,
|
|
"epoch": 0.17081523554961578,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999141425734374,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.15258873701095582,
|
|
"num_tokens": 3762816.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.651172780990601,
|
|
"epoch": 0.17123287671232876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999133182679064,
|
|
"loss": 5.805,
|
|
"mean_token_accuracy": 0.1495609924197197,
|
|
"num_tokens": 3773244.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.733507108688355,
|
|
"epoch": 0.17165051787504176,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999124900249971,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.16301829516887664,
|
|
"num_tokens": 3782122.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.688563394546509,
|
|
"epoch": 0.17206815903775477,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999116578447239,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.16714497208595275,
|
|
"num_tokens": 3791303.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.7102601528167725,
|
|
"epoch": 0.17248580020046775,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999108217271015,
|
|
"loss": 5.7161,
|
|
"mean_token_accuracy": 0.15428307950496672,
|
|
"num_tokens": 3800991.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.698825216293335,
|
|
"epoch": 0.17290344136318075,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999099816721444,
|
|
"loss": 5.6302,
|
|
"mean_token_accuracy": 0.15540433079004287,
|
|
"num_tokens": 3811293.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.766291332244873,
|
|
"epoch": 0.17332108252589376,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999091376798673,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.15168866515159607,
|
|
"num_tokens": 3820013.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.655336523056031,
|
|
"epoch": 0.17373872368860674,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999082897502849,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.1611282467842102,
|
|
"num_tokens": 3829099.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.651612615585327,
|
|
"epoch": 0.17415636485131974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999074378834123,
|
|
"loss": 5.7326,
|
|
"mean_token_accuracy": 0.15682385265827178,
|
|
"num_tokens": 3838308.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.738585424423218,
|
|
"epoch": 0.17457400601403275,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999065820792644,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.15595242530107498,
|
|
"num_tokens": 3847650.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.805827569961548,
|
|
"epoch": 0.17499164717674573,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999057223378559,
|
|
"loss": 5.8611,
|
|
"mean_token_accuracy": 0.14233408570289613,
|
|
"num_tokens": 3857252.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.754422426223755,
|
|
"epoch": 0.17540928833945874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499904858659202,
|
|
"loss": 5.6955,
|
|
"mean_token_accuracy": 0.15864840149879456,
|
|
"num_tokens": 3865747.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.674372434616089,
|
|
"epoch": 0.17582692950217174,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999039910433179,
|
|
"loss": 5.6711,
|
|
"mean_token_accuracy": 0.16594497859477997,
|
|
"num_tokens": 3874958.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.588525819778442,
|
|
"epoch": 0.17624457066488472,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999031194902187,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.16458353102207185,
|
|
"num_tokens": 3885216.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.748322677612305,
|
|
"epoch": 0.17666221182759773,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999022439999198,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.16610947996377945,
|
|
"num_tokens": 3893973.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.731654167175293,
|
|
"epoch": 0.17707985299031073,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999013645724362,
|
|
"loss": 5.7414,
|
|
"mean_token_accuracy": 0.15839334726333618,
|
|
"num_tokens": 3903532.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.741130352020264,
|
|
"epoch": 0.1774974941530237,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999004812077836,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.16057559847831726,
|
|
"num_tokens": 3913427.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.7038579940795895,
|
|
"epoch": 0.17791513531573672,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998995939059773,
|
|
"loss": 5.8097,
|
|
"mean_token_accuracy": 0.14798093736171722,
|
|
"num_tokens": 3923870.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.693835687637329,
|
|
"epoch": 0.17833277647844972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499898702667033,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.16271054297685622,
|
|
"num_tokens": 3933469.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.6254839420318605,
|
|
"epoch": 0.1787504176411627,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998978074909661,
|
|
"loss": 5.6403,
|
|
"mean_token_accuracy": 0.16687489449977874,
|
|
"num_tokens": 3942427.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.688601303100586,
|
|
"epoch": 0.1791680588038757,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998969083777925,
|
|
"loss": 5.673,
|
|
"mean_token_accuracy": 0.16252454817295076,
|
|
"num_tokens": 3951250.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.682954549789429,
|
|
"epoch": 0.1795856999665887,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998960053275277,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.15424496978521346,
|
|
"num_tokens": 3959969.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.671282815933227,
|
|
"epoch": 0.1800033411293017,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998950983401875,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.1546568527817726,
|
|
"num_tokens": 3968171.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.702560186386108,
|
|
"epoch": 0.1804209822920147,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998941874157882,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.16684609055519103,
|
|
"num_tokens": 3976686.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.5957166194915775,
|
|
"epoch": 0.1808386234547277,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998932725543453,
|
|
"loss": 5.7366,
|
|
"mean_token_accuracy": 0.1542557030916214,
|
|
"num_tokens": 3986552.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.746101808547974,
|
|
"epoch": 0.18125626461744068,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998923537558749,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.15404898673295975,
|
|
"num_tokens": 3995501.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.577417039871216,
|
|
"epoch": 0.1816739057801537,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998914310203932,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.16384028941392897,
|
|
"num_tokens": 4004423.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.705241107940674,
|
|
"epoch": 0.1820915469428667,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998905043479163,
|
|
"loss": 5.7633,
|
|
"mean_token_accuracy": 0.15359411537647247,
|
|
"num_tokens": 4013324.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.720277500152588,
|
|
"epoch": 0.18250918810557967,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998895737384605,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.15625456869602203,
|
|
"num_tokens": 4021896.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.585773658752442,
|
|
"epoch": 0.18292682926829268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998886391920418,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.15853976160287858,
|
|
"num_tokens": 4030590.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.639527130126953,
|
|
"epoch": 0.18334447043100568,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998877007086769,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.16841819733381272,
|
|
"num_tokens": 4040041.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.724634075164795,
|
|
"epoch": 0.18376211159371866,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998867582883821,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.14944272637367248,
|
|
"num_tokens": 4049119.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.675548553466797,
|
|
"epoch": 0.18417975275643167,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998858119311739,
|
|
"loss": 5.6431,
|
|
"mean_token_accuracy": 0.1540763944387436,
|
|
"num_tokens": 4059265.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.692709350585938,
|
|
"epoch": 0.18459739391914468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998848616370689,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.15441271513700486,
|
|
"num_tokens": 4068363.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.612869834899902,
|
|
"epoch": 0.18501503508185768,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998839074060837,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.16939774602651597,
|
|
"num_tokens": 4077390.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.602217435836792,
|
|
"epoch": 0.18543267624457066,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499882949238235,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.15488070547580718,
|
|
"num_tokens": 4087331.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.898349380493164,
|
|
"epoch": 0.18585031740728367,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998819871335396,
|
|
"loss": 5.8585,
|
|
"mean_token_accuracy": 0.1453448213636875,
|
|
"num_tokens": 4096425.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.599613237380981,
|
|
"epoch": 0.18626795856999667,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998810210920142,
|
|
"loss": 5.6084,
|
|
"mean_token_accuracy": 0.16011494100093843,
|
|
"num_tokens": 4106056.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.683730888366699,
|
|
"epoch": 0.18668559973270965,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998800511136759,
|
|
"loss": 5.6968,
|
|
"mean_token_accuracy": 0.1584601417183876,
|
|
"num_tokens": 4115133.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.667567729949951,
|
|
"epoch": 0.18710324089542266,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998790771985417,
|
|
"loss": 5.5964,
|
|
"mean_token_accuracy": 0.1586738795042038,
|
|
"num_tokens": 4123630.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.640010595321655,
|
|
"epoch": 0.18752088205813566,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998780993466284,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.15695928037166595,
|
|
"num_tokens": 4133337.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.728957223892212,
|
|
"epoch": 0.18793852322084864,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998771175579534,
|
|
"loss": 5.6701,
|
|
"mean_token_accuracy": 0.15720749497413636,
|
|
"num_tokens": 4142240.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.650001859664917,
|
|
"epoch": 0.18835616438356165,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998761318325337,
|
|
"loss": 5.6434,
|
|
"mean_token_accuracy": 0.15715699940919875,
|
|
"num_tokens": 4151297.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.6392778873443605,
|
|
"epoch": 0.18877380554627465,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998751421703868,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.16495950818061828,
|
|
"num_tokens": 4160193.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.726975584030152,
|
|
"epoch": 0.18919144670898763,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998741485715297,
|
|
"loss": 5.7615,
|
|
"mean_token_accuracy": 0.15852496922016143,
|
|
"num_tokens": 4169948.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.873078060150147,
|
|
"epoch": 0.18960908787170064,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049987315103598,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.1499393455684185,
|
|
"num_tokens": 4179981.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.655186462402344,
|
|
"epoch": 0.19002672903441364,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998721495637551,
|
|
"loss": 5.8004,
|
|
"mean_token_accuracy": 0.15085280686616898,
|
|
"num_tokens": 4189172.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.6853272914886475,
|
|
"epoch": 0.19044437019712662,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998711441548726,
|
|
"loss": 5.5864,
|
|
"mean_token_accuracy": 0.15680087357759476,
|
|
"num_tokens": 4197312.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.708002233505249,
|
|
"epoch": 0.19086201135983963,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998701348093499,
|
|
"loss": 5.6636,
|
|
"mean_token_accuracy": 0.15665152966976165,
|
|
"num_tokens": 4206828.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.730845022201538,
|
|
"epoch": 0.19127965252255263,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499869121527205,
|
|
"loss": 5.6132,
|
|
"mean_token_accuracy": 0.16018779575824738,
|
|
"num_tokens": 4214835.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.6554999351501465,
|
|
"epoch": 0.1916972936852656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998681043084553,
|
|
"loss": 5.7972,
|
|
"mean_token_accuracy": 0.147630412876606,
|
|
"num_tokens": 4225119.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.660569190979004,
|
|
"epoch": 0.19211493484797862,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998670831531188,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.15618418008089066,
|
|
"num_tokens": 4235257.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.665428733825683,
|
|
"epoch": 0.19253257601069163,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998660580612135,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.16061737835407258,
|
|
"num_tokens": 4244211.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.724985074996948,
|
|
"epoch": 0.1929502171734046,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998650290327569,
|
|
"loss": 5.7158,
|
|
"mean_token_accuracy": 0.15692965239286422,
|
|
"num_tokens": 4253149.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.6536462783813475,
|
|
"epoch": 0.1933678583361176,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998639960677675,
|
|
"loss": 5.6279,
|
|
"mean_token_accuracy": 0.15889257192611694,
|
|
"num_tokens": 4262557.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.657335042953491,
|
|
"epoch": 0.19378549949883062,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998629591662631,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.16159564554691314,
|
|
"num_tokens": 4272881.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.599450969696045,
|
|
"epoch": 0.1942031406615436,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499861918328262,
|
|
"loss": 5.6326,
|
|
"mean_token_accuracy": 0.16337416023015977,
|
|
"num_tokens": 4281158.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.6304497718811035,
|
|
"epoch": 0.1946207818242566,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998608735537822,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.15982079207897187,
|
|
"num_tokens": 4290319.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.665145397186279,
|
|
"epoch": 0.1950384229869696,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998598248428423,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.16070850789546967,
|
|
"num_tokens": 4299276.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.7335333824157715,
|
|
"epoch": 0.19545606414968258,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998587721954604,
|
|
"loss": 5.687,
|
|
"mean_token_accuracy": 0.1566752687096596,
|
|
"num_tokens": 4308291.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.622469186782837,
|
|
"epoch": 0.1958737053123956,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.155308535695076,
|
|
"num_tokens": 4316654.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.631796360015869,
|
|
"epoch": 0.1962913464751086,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998566550914448,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.15566373467445374,
|
|
"num_tokens": 4325911.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.719413614273071,
|
|
"epoch": 0.19670898763782158,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998555906348481,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.15533148795366286,
|
|
"num_tokens": 4334846.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.713936042785645,
|
|
"epoch": 0.19712662880053458,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998545222418836,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.16010912209749223,
|
|
"num_tokens": 4343728.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.609404993057251,
|
|
"epoch": 0.1975442699632476,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998534499125701,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.1628926530480385,
|
|
"num_tokens": 4352774.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.750800704956054,
|
|
"epoch": 0.19796191112596057,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004998523736469263,
|
|
"loss": 5.746,
|
|
"mean_token_accuracy": 0.15442651212215425,
|
|
"num_tokens": 4361663.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.65933666229248,
|
|
"epoch": 0.19837955228867357,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499851293444971,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.1717977210879326,
|
|
"num_tokens": 4370278.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.68487024307251,
|
|
"epoch": 0.19879719345138658,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998502093067231,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.16009533107280732,
|
|
"num_tokens": 4379010.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.69346399307251,
|
|
"epoch": 0.19921483461409956,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998491212322017,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.1543926328420639,
|
|
"num_tokens": 4388145.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.6455628871917725,
|
|
"epoch": 0.19963247577681256,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998480292214258,
|
|
"loss": 5.7707,
|
|
"mean_token_accuracy": 0.1530858799815178,
|
|
"num_tokens": 4396321.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.702960968017578,
|
|
"epoch": 0.20005011693952557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998469332744144,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.16541909873485566,
|
|
"num_tokens": 4404854.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.469099617004394,
|
|
"epoch": 0.20046775810223855,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998458333911869,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.16603398621082305,
|
|
"num_tokens": 4413890.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.7079826354980465,
|
|
"epoch": 0.20088539926495155,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998447295717624,
|
|
"loss": 5.6872,
|
|
"mean_token_accuracy": 0.15662553459405898,
|
|
"num_tokens": 4423019.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.715851497650147,
|
|
"epoch": 0.20130304042766456,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998436218161602,
|
|
"loss": 5.6255,
|
|
"mean_token_accuracy": 0.15582710802555083,
|
|
"num_tokens": 4432340.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.611751461029053,
|
|
"epoch": 0.20172068159037754,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998425101243999,
|
|
"loss": 5.6121,
|
|
"mean_token_accuracy": 0.1572697326540947,
|
|
"num_tokens": 4441834.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.6097025871276855,
|
|
"epoch": 0.20213832275309054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998413944965007,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.16356834024190903,
|
|
"num_tokens": 4450864.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.6114274024963375,
|
|
"epoch": 0.20255596391580355,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998402749324823,
|
|
"loss": 5.7129,
|
|
"mean_token_accuracy": 0.15567796379327775,
|
|
"num_tokens": 4460697.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.893751335144043,
|
|
"epoch": 0.20297360507851653,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998391514323642,
|
|
"loss": 5.7085,
|
|
"mean_token_accuracy": 0.153797747194767,
|
|
"num_tokens": 4469926.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.583089590072632,
|
|
"epoch": 0.20339124624122953,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998380239961661,
|
|
"loss": 5.6422,
|
|
"mean_token_accuracy": 0.15996050238609313,
|
|
"num_tokens": 4478818.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.703447008132935,
|
|
"epoch": 0.20380888740394254,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998368926239078,
|
|
"loss": 5.5741,
|
|
"mean_token_accuracy": 0.15723517835140227,
|
|
"num_tokens": 4487451.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.678385782241821,
|
|
"epoch": 0.20422652856665552,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499835757315609,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.15110710263252258,
|
|
"num_tokens": 4497674.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.581616687774658,
|
|
"epoch": 0.20464416972936852,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998346180712898,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.16663052439689635,
|
|
"num_tokens": 4507666.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.625546884536743,
|
|
"epoch": 0.20506181089208153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998334748909698,
|
|
"loss": 5.7454,
|
|
"mean_token_accuracy": 0.15425530821084976,
|
|
"num_tokens": 4517409.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.657826280593872,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998323277746694,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.16149946302175522,
|
|
"num_tokens": 4526495.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.665003061294556,
|
|
"epoch": 0.20589709321750752,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998311767224081,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.16810937523841857,
|
|
"num_tokens": 4535240.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.631776237487793,
|
|
"epoch": 0.20631473438022052,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998300217342067,
|
|
"loss": 5.7025,
|
|
"mean_token_accuracy": 0.156618569791317,
|
|
"num_tokens": 4544716.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.6214515209198,
|
|
"epoch": 0.2067323755429335,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998288628100851,
|
|
"loss": 5.6206,
|
|
"mean_token_accuracy": 0.1633414626121521,
|
|
"num_tokens": 4553867.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.647698307037354,
|
|
"epoch": 0.2071500167056465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998276999500636,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.1532789349555969,
|
|
"num_tokens": 4562529.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.562749671936035,
|
|
"epoch": 0.2075676578683595,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.1752343535423279,
|
|
"num_tokens": 4571041.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.565519905090332,
|
|
"epoch": 0.2079852990310725,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998253624224026,
|
|
"loss": 5.6044,
|
|
"mean_token_accuracy": 0.161303348839283,
|
|
"num_tokens": 4579914.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.644900465011597,
|
|
"epoch": 0.2084029401937855,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499824187754804,
|
|
"loss": 5.6815,
|
|
"mean_token_accuracy": 0.16097000390291213,
|
|
"num_tokens": 4590277.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.66708197593689,
|
|
"epoch": 0.2088205813564985,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998230091513872,
|
|
"loss": 5.6005,
|
|
"mean_token_accuracy": 0.16419181376695632,
|
|
"num_tokens": 4598719.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.624560022354126,
|
|
"epoch": 0.20923822251921148,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998218266121731,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.1620894342660904,
|
|
"num_tokens": 4607804.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.510728168487549,
|
|
"epoch": 0.2096558636819245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998206401371823,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.16698947846889495,
|
|
"num_tokens": 4616529.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.637687015533447,
|
|
"epoch": 0.2100735048446375,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998194497264357,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.15697978138923646,
|
|
"num_tokens": 4624545.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.640446758270263,
|
|
"epoch": 0.21049114600735047,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998182553799538,
|
|
"loss": 5.5814,
|
|
"mean_token_accuracy": 0.1600236177444458,
|
|
"num_tokens": 4633316.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.585673189163208,
|
|
"epoch": 0.21090878717006348,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998170570977579,
|
|
"loss": 5.5394,
|
|
"mean_token_accuracy": 0.16961861550807952,
|
|
"num_tokens": 4643353.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.584037351608276,
|
|
"epoch": 0.21132642833277648,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998158548798687,
|
|
"loss": 5.632,
|
|
"mean_token_accuracy": 0.16008919924497605,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.621504116058349,
|
|
"epoch": 0.21174406949548946,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998146487263074,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.16083284914493562,
|
|
"num_tokens": 4659937.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.583824634552002,
|
|
"epoch": 0.21216171065820247,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998134386370951,
|
|
"loss": 5.5981,
|
|
"mean_token_accuracy": 0.1597536824643612,
|
|
"num_tokens": 4669396.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.717773294448852,
|
|
"epoch": 0.21257935182091547,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998122246122529,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.16459225714206696,
|
|
"num_tokens": 4679320.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.6832643985748295,
|
|
"epoch": 0.21299699298362845,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998110066518021,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.16294638812541962,
|
|
"num_tokens": 4688807.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.633354759216308,
|
|
"epoch": 0.21341463414634146,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499809784755764,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.17056376934051515,
|
|
"num_tokens": 4697819.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.584991502761841,
|
|
"epoch": 0.21383227530905446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049980855892416,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.16347702592611313,
|
|
"num_tokens": 4706931.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.608094644546509,
|
|
"epoch": 0.21424991647176747,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998073291570116,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.1649039328098297,
|
|
"num_tokens": 4716262.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.627374076843262,
|
|
"epoch": 0.21466755763448045,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998060954543404,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.16122105121612548,
|
|
"num_tokens": 4725415.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.546875810623169,
|
|
"epoch": 0.21508519879719346,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004998048578161678,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.16040805876255035,
|
|
"num_tokens": 4734580.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.58602876663208,
|
|
"epoch": 0.21550283995990646,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998036162425155,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.17046085894107818,
|
|
"num_tokens": 4742966.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.587724733352661,
|
|
"epoch": 0.21592048112261944,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998023707334055,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.1627469092607498,
|
|
"num_tokens": 4751696.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.655860662460327,
|
|
"epoch": 0.21633812228533245,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998011212888592,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.16377044171094896,
|
|
"num_tokens": 4760460.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.668825340270996,
|
|
"epoch": 0.21675576344804545,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997998679088988,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.16344082206487656,
|
|
"num_tokens": 4769004.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.5735485553741455,
|
|
"epoch": 0.21717340461075843,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997986105935461,
|
|
"loss": 5.5641,
|
|
"mean_token_accuracy": 0.17153629660606384,
|
|
"num_tokens": 4777204.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.688373565673828,
|
|
"epoch": 0.21759104577347144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997973493428231,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.1608117088675499,
|
|
"num_tokens": 4786766.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.573904323577881,
|
|
"epoch": 0.21800868693618444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997960841567519,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.16307419240474702,
|
|
"num_tokens": 4796676.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.784175872802734,
|
|
"epoch": 0.21842632809889742,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997948150353548,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.16198533475399018,
|
|
"num_tokens": 4805514.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.579783344268799,
|
|
"epoch": 0.21884396926161043,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997935419786537,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.15730978101491927,
|
|
"num_tokens": 4815487.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.642004919052124,
|
|
"epoch": 0.21926161042432343,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997922649866712,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.162903268635273,
|
|
"num_tokens": 4825044.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.533287715911865,
|
|
"epoch": 0.2196792515870364,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997909840594294,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.17537373900413514,
|
|
"num_tokens": 4833875.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.520668888092041,
|
|
"epoch": 0.22009689274974942,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997896991969509,
|
|
"loss": 5.646,
|
|
"mean_token_accuracy": 0.1582174703478813,
|
|
"num_tokens": 4843317.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.6602888107299805,
|
|
"epoch": 0.22051453391246242,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997884103992581,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.15556131601333617,
|
|
"num_tokens": 4852514.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.6012287616729735,
|
|
"epoch": 0.2209321750751754,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997871176663736,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.1639481171965599,
|
|
"num_tokens": 4861260.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.607472705841064,
|
|
"epoch": 0.2213498162378884,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997858209983201,
|
|
"loss": 5.5261,
|
|
"mean_token_accuracy": 0.1611647054553032,
|
|
"num_tokens": 4869654.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.620398616790771,
|
|
"epoch": 0.22176745740060141,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997845203951202,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.15774784982204437,
|
|
"num_tokens": 4878311.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.723662614822388,
|
|
"epoch": 0.2221850985633144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997832158567967,
|
|
"loss": 5.6628,
|
|
"mean_token_accuracy": 0.15765633732080458,
|
|
"num_tokens": 4887251.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.582074880599976,
|
|
"epoch": 0.2226027397260274,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997819073833724,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.16348181664943695,
|
|
"num_tokens": 4896528.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.570661401748657,
|
|
"epoch": 0.2230203808887404,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997805949748702,
|
|
"loss": 5.575,
|
|
"mean_token_accuracy": 0.16215746700763703,
|
|
"num_tokens": 4904962.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.605434513092041,
|
|
"epoch": 0.22343802205145338,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997792786313132,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.15934820771217345,
|
|
"num_tokens": 4914735.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.416878604888916,
|
|
"epoch": 0.2238556632141664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997779583527243,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.15913522839546204,
|
|
"num_tokens": 4924271.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.731436920166016,
|
|
"epoch": 0.2242733043768794,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997766341391268,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.15840027630329132,
|
|
"num_tokens": 4933928.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.586864900588989,
|
|
"epoch": 0.22469094553959237,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997753059905437,
|
|
"loss": 5.4023,
|
|
"mean_token_accuracy": 0.1752420797944069,
|
|
"num_tokens": 4942714.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.399338579177856,
|
|
"epoch": 0.22510858670230538,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997739739069981,
|
|
"loss": 5.5313,
|
|
"mean_token_accuracy": 0.164621265232563,
|
|
"num_tokens": 4952297.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.644370079040527,
|
|
"epoch": 0.22552622786501839,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997726378885138,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.1743430182337761,
|
|
"num_tokens": 4960947.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.593647527694702,
|
|
"epoch": 0.22594386902773136,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004997712979351137,
|
|
"loss": 5.6253,
|
|
"mean_token_accuracy": 0.1603491149842739,
|
|
"num_tokens": 4969705.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.6281603336334225,
|
|
"epoch": 0.22636151019044437,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997699540468216,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.16521542072296141,
|
|
"num_tokens": 4979112.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.5321063041687015,
|
|
"epoch": 0.22677915135315738,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997686062236609,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.16602300256490707,
|
|
"num_tokens": 4987894.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.633674669265747,
|
|
"epoch": 0.22719679251587035,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997672544656553,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.1612725928425789,
|
|
"num_tokens": 4997774.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.698086166381836,
|
|
"epoch": 0.22761443367858336,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997658987728283,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.1690062776207924,
|
|
"num_tokens": 5006183.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.591877269744873,
|
|
"epoch": 0.22803207484129637,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997645391452035,
|
|
"loss": 5.5916,
|
|
"mean_token_accuracy": 0.1632835417985916,
|
|
"num_tokens": 5016909.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.610874843597412,
|
|
"epoch": 0.22844971600400935,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499763175582805,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.1621117740869522,
|
|
"num_tokens": 5027326.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.632061624526978,
|
|
"epoch": 0.22886735716672235,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997618080856566,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.15901436507701874,
|
|
"num_tokens": 5037043.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.541202545166016,
|
|
"epoch": 0.22928499832943536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997604366537823,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.16744935959577562,
|
|
"num_tokens": 5045992.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.564315366744995,
|
|
"epoch": 0.22970263949214834,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997590612872058,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.16942261159420013,
|
|
"num_tokens": 5055568.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.63058443069458,
|
|
"epoch": 0.23012028065486134,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997576819859515,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.16200867295265198,
|
|
"num_tokens": 5065512.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.484599208831787,
|
|
"epoch": 0.23053792181757435,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997562987500434,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.17104848176240922,
|
|
"num_tokens": 5074776.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.583745384216309,
|
|
"epoch": 0.23095556298028733,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997549115795058,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.16588549315929413,
|
|
"num_tokens": 5084743.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.682448768615723,
|
|
"epoch": 0.23137320414300033,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499753520474363,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.16034545600414277,
|
|
"num_tokens": 5095387.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.587224912643433,
|
|
"epoch": 0.23179084530571334,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997521254346391,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.16626937463879585,
|
|
"num_tokens": 5104628.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.622297048568726,
|
|
"epoch": 0.23220848646842632,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997507264603589,
|
|
"loss": 5.5347,
|
|
"mean_token_accuracy": 0.16671543717384338,
|
|
"num_tokens": 5113169.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.549988460540772,
|
|
"epoch": 0.23262612763113932,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997493235515466,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.16756106466054915,
|
|
"num_tokens": 5122294.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.531440925598145,
|
|
"epoch": 0.23304376879385233,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997479167082269,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.17597562521696092,
|
|
"num_tokens": 5131191.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.549725675582886,
|
|
"epoch": 0.2334614099565653,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997465059304243,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.16252151429653167,
|
|
"num_tokens": 5141974.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.6808897972106935,
|
|
"epoch": 0.23387905111927831,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997450912181637,
|
|
"loss": 5.5764,
|
|
"mean_token_accuracy": 0.16537160128355027,
|
|
"num_tokens": 5151412.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.547338819503784,
|
|
"epoch": 0.23429669228199132,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997436725714696,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.1739228755235672,
|
|
"num_tokens": 5160989.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.551234436035156,
|
|
"epoch": 0.2347143334447043,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997422499903671,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.16309013664722444,
|
|
"num_tokens": 5170241.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.731640720367432,
|
|
"epoch": 0.2351319746074173,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499740823474881,
|
|
"loss": 5.7214,
|
|
"mean_token_accuracy": 0.1557489424943924,
|
|
"num_tokens": 5180247.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.54374361038208,
|
|
"epoch": 0.2355496157701303,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997393930250363,
|
|
"loss": 5.5933,
|
|
"mean_token_accuracy": 0.16376214027404784,
|
|
"num_tokens": 5189144.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.623880338668823,
|
|
"epoch": 0.2359672569328433,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499737958640858,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.16290141642093658,
|
|
"num_tokens": 5199410.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.6456780433654785,
|
|
"epoch": 0.2363848980955563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997365203223711,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.17000638246536254,
|
|
"num_tokens": 5209032.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.440157270431518,
|
|
"epoch": 0.2368025392582693,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499735078069601,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.17118311822414398,
|
|
"num_tokens": 5217787.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.555545091629028,
|
|
"epoch": 0.23722018042098228,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997336318825728,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.1703398510813713,
|
|
"num_tokens": 5226962.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.52580771446228,
|
|
"epoch": 0.23763782158369529,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997321817613119,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.16689039915800094,
|
|
"num_tokens": 5236111.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.645787096023559,
|
|
"epoch": 0.2380554627464083,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997307277058436,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.16265233159065245,
|
|
"num_tokens": 5246628.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.622815704345703,
|
|
"epoch": 0.23847310390912127,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997292697161935,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.15912623330950737,
|
|
"num_tokens": 5255543.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.467281913757324,
|
|
"epoch": 0.23889074507183428,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499727807792387,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.17852753698825835,
|
|
"num_tokens": 5264559.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.447366380691529,
|
|
"epoch": 0.23930838623454728,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997263419344495,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.16848173439502717,
|
|
"num_tokens": 5274599.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.553721141815186,
|
|
"epoch": 0.23972602739726026,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997248721424071,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.17135296761989594,
|
|
"num_tokens": 5283495.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.591934013366699,
|
|
"epoch": 0.24014366855997327,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997233984162853,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.1711369827389717,
|
|
"num_tokens": 5292064.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.527604627609253,
|
|
"epoch": 0.24056130972268627,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997219207561099,
|
|
"loss": 5.535,
|
|
"mean_token_accuracy": 0.16105968952178956,
|
|
"num_tokens": 5301696.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.675354480743408,
|
|
"epoch": 0.24097895088539925,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997204391619068,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.15840594172477723,
|
|
"num_tokens": 5311427.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.684924793243408,
|
|
"epoch": 0.24139659204811226,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997189536337018,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.16174941658973693,
|
|
"num_tokens": 5321406.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.551355266571045,
|
|
"epoch": 0.24181423321082526,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004997174641715211,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.1644423484802246,
|
|
"num_tokens": 5332257.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.504457902908325,
|
|
"epoch": 0.24223187437353827,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997159707753906,
|
|
"loss": 5.4042,
|
|
"mean_token_accuracy": 0.1703709304332733,
|
|
"num_tokens": 5341857.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.511201333999634,
|
|
"epoch": 0.24264951553625125,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.16949305385351182,
|
|
"num_tokens": 5351367.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.391738796234131,
|
|
"epoch": 0.24306715669896425,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997129721813853,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.17349923253059388,
|
|
"num_tokens": 5360627.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.531809091567993,
|
|
"epoch": 0.24348479786167726,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997114669835629,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.17700317949056626,
|
|
"num_tokens": 5369703.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.5716290950775145,
|
|
"epoch": 0.24390243902439024,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997099578518959,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.16404612362384796,
|
|
"num_tokens": 5378432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.438390588760376,
|
|
"epoch": 0.24432008018710324,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997084447864105,
|
|
"loss": 5.3909,
|
|
"mean_token_accuracy": 0.1708747535943985,
|
|
"num_tokens": 5386489.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.610124492645264,
|
|
"epoch": 0.24473772134981625,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997069277871333,
|
|
"loss": 5.6231,
|
|
"mean_token_accuracy": 0.16265049129724501,
|
|
"num_tokens": 5395908.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.710176420211792,
|
|
"epoch": 0.24515536251252923,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997054068540908,
|
|
"loss": 5.539,
|
|
"mean_token_accuracy": 0.16824057847261428,
|
|
"num_tokens": 5404822.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.442877244949341,
|
|
"epoch": 0.24557300367524224,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997038819873098,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.1711698964238167,
|
|
"num_tokens": 5413980.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.5252721309661865,
|
|
"epoch": 0.24599064483795524,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997023531868167,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.16247909963130952,
|
|
"num_tokens": 5423538.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.515257501602173,
|
|
"epoch": 0.24640828600066822,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997008204526386,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.16875504106283187,
|
|
"num_tokens": 5431930.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.48965220451355,
|
|
"epoch": 0.24682592716338123,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996992837848021,
|
|
"loss": 5.4508,
|
|
"mean_token_accuracy": 0.1761811926960945,
|
|
"num_tokens": 5440721.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.506892585754395,
|
|
"epoch": 0.24724356832609423,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996977431833342,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.1642148897051811,
|
|
"num_tokens": 5449617.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.5657142162322994,
|
|
"epoch": 0.2476612094888072,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996961986482618,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.16744059771299363,
|
|
"num_tokens": 5458827.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.565783166885376,
|
|
"epoch": 0.24807885065152022,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996946501796119,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.17086558043956757,
|
|
"num_tokens": 5467348.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.554220914840698,
|
|
"epoch": 0.24849649181423322,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996930977774118,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.15979193449020385,
|
|
"num_tokens": 5476645.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.590994024276734,
|
|
"epoch": 0.2489141329769462,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996915414416885,
|
|
"loss": 5.5611,
|
|
"mean_token_accuracy": 0.16303199231624604,
|
|
"num_tokens": 5486120.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.6555492877960205,
|
|
"epoch": 0.2493317741396592,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996899811724693,
|
|
"loss": 5.5378,
|
|
"mean_token_accuracy": 0.1691664695739746,
|
|
"num_tokens": 5495313.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.537061023712158,
|
|
"epoch": 0.2497494153023722,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996884169697816,
|
|
"loss": 5.5371,
|
|
"mean_token_accuracy": 0.16722940653562546,
|
|
"num_tokens": 5504587.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.468687248229981,
|
|
"epoch": 0.2501670564650852,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996868488336526,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.16358605027198792,
|
|
"num_tokens": 5514188.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.579990291595459,
|
|
"epoch": 0.25058469762779817,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996852767641099,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.16043460369110107,
|
|
"num_tokens": 5524075.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.25058469762779817,
|
|
"eval_entropy": 5.461522004887654,
|
|
"eval_loss": 5.523029327392578,
|
|
"eval_mean_token_accuracy": 0.17474948998569836,
|
|
"eval_num_tokens": 5524075.0,
|
|
"eval_runtime": 27.2289,
|
|
"eval_samples_per_second": 1386.87,
|
|
"eval_steps_per_second": 173.382,
|
|
"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": 8148212379648000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|