4084acfd66
Model: fpadovani/urd-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 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": 0.357355568790947,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.8313291549682615,
|
|
"epoch": 0.0005955926146515784,
|
|
"grad_norm": 18.125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.4302,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 14043.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.836077260971069,
|
|
"epoch": 0.0011911852293031567,
|
|
"grad_norm": 19.375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.3519,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 27431.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.8866355419158936,
|
|
"epoch": 0.001786777843954735,
|
|
"grad_norm": 20.75,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.1783,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 41546.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.034542465209961,
|
|
"epoch": 0.0023823704586063135,
|
|
"grad_norm": 24.75,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.7001,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 55610.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.020096302032471,
|
|
"epoch": 0.0029779630732578916,
|
|
"grad_norm": 18.75,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 12.5307,
|
|
"mean_token_accuracy": 6.816632812842727e-05,
|
|
"num_tokens": 67719.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 9.150710821151733,
|
|
"epoch": 0.00357355568790947,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 11.261,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 82309.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.670249271392823,
|
|
"epoch": 0.004169148302561048,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.8013,
|
|
"mean_token_accuracy": 4.861448833253235e-05,
|
|
"num_tokens": 95752.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.707376766204835,
|
|
"epoch": 0.004764740917212627,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.5681,
|
|
"mean_token_accuracy": 0.01290286296280101,
|
|
"num_tokens": 109473.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.699721717834473,
|
|
"epoch": 0.005360333531864205,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.2878,
|
|
"mean_token_accuracy": 0.02838722914457321,
|
|
"num_tokens": 124193.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.666810226440429,
|
|
"epoch": 0.005955926146515783,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.9667,
|
|
"mean_token_accuracy": 0.03413830101490021,
|
|
"num_tokens": 136870.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.616733837127686,
|
|
"epoch": 0.006551518761167362,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.8201,
|
|
"mean_token_accuracy": 0.0349402779713273,
|
|
"num_tokens": 150613.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.599438667297363,
|
|
"epoch": 0.00714711137581894,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.694,
|
|
"mean_token_accuracy": 0.034979277104139325,
|
|
"num_tokens": 164213.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.597020053863526,
|
|
"epoch": 0.007742703990470518,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.5658,
|
|
"mean_token_accuracy": 0.03644208796322346,
|
|
"num_tokens": 177408.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.587311840057373,
|
|
"epoch": 0.008338296605122097,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.4815,
|
|
"mean_token_accuracy": 0.035931960307061674,
|
|
"num_tokens": 190273.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.569261169433593,
|
|
"epoch": 0.008933889219773675,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.3822,
|
|
"mean_token_accuracy": 0.03670790996402502,
|
|
"num_tokens": 203323.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.54176959991455,
|
|
"epoch": 0.009529481834425254,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.3181,
|
|
"mean_token_accuracy": 0.0352932145819068,
|
|
"num_tokens": 218647.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.516415119171143,
|
|
"epoch": 0.01012507444907683,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.2157,
|
|
"mean_token_accuracy": 0.03231475837528706,
|
|
"num_tokens": 232910.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.49910831451416,
|
|
"epoch": 0.01072066706372841,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.123,
|
|
"mean_token_accuracy": 0.03363412488251925,
|
|
"num_tokens": 246683.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.459693241119385,
|
|
"epoch": 0.011316259678379988,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.9972,
|
|
"mean_token_accuracy": 0.031005607172846793,
|
|
"num_tokens": 260150.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.377124214172364,
|
|
"epoch": 0.011911852293031567,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.8852,
|
|
"mean_token_accuracy": 0.034673300199210645,
|
|
"num_tokens": 273788.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.319822216033936,
|
|
"epoch": 0.012507444907683145,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.746,
|
|
"mean_token_accuracy": 0.03429920971393585,
|
|
"num_tokens": 287625.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.25199098587036,
|
|
"epoch": 0.013103037522334724,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.625,
|
|
"mean_token_accuracy": 0.03484415449202061,
|
|
"num_tokens": 302938.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.111868000030517,
|
|
"epoch": 0.0136986301369863,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.4859,
|
|
"mean_token_accuracy": 0.03487641792744398,
|
|
"num_tokens": 316905.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.927003860473633,
|
|
"epoch": 0.01429422275163788,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.3018,
|
|
"mean_token_accuracy": 0.03559151701629162,
|
|
"num_tokens": 331131.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.733693885803223,
|
|
"epoch": 0.014889815366289458,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.1762,
|
|
"mean_token_accuracy": 0.03266423176974058,
|
|
"num_tokens": 344995.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.51575584411621,
|
|
"epoch": 0.015485407980941036,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.0047,
|
|
"mean_token_accuracy": 0.03661343269050121,
|
|
"num_tokens": 361057.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.236015033721923,
|
|
"epoch": 0.016081000595592615,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8971,
|
|
"mean_token_accuracy": 0.033833478763699534,
|
|
"num_tokens": 375037.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 8.986121940612794,
|
|
"epoch": 0.016676593210244194,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.799,
|
|
"mean_token_accuracy": 0.029642431996762753,
|
|
"num_tokens": 389797.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.731746292114257,
|
|
"epoch": 0.017272185824895772,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.7468,
|
|
"mean_token_accuracy": 0.03149167206138372,
|
|
"num_tokens": 403743.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.546319484710693,
|
|
"epoch": 0.01786777843954735,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.6925,
|
|
"mean_token_accuracy": 0.02860908694565296,
|
|
"num_tokens": 417337.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.36656312942505,
|
|
"epoch": 0.01846337105419893,
|
|
"grad_norm": 0.72265625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.5836,
|
|
"mean_token_accuracy": 0.035039109736680986,
|
|
"num_tokens": 430106.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.201282215118407,
|
|
"epoch": 0.019058963668850508,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.6104,
|
|
"mean_token_accuracy": 0.034445393830537796,
|
|
"num_tokens": 444654.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.112825393676758,
|
|
"epoch": 0.019654556283502083,
|
|
"grad_norm": 0.69921875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.6193,
|
|
"mean_token_accuracy": 0.029377650842070578,
|
|
"num_tokens": 457837.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.070330810546874,
|
|
"epoch": 0.02025014889815366,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.5242,
|
|
"mean_token_accuracy": 0.03372163213789463,
|
|
"num_tokens": 472006.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.9470103740692135,
|
|
"epoch": 0.02084574151280524,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.5158,
|
|
"mean_token_accuracy": 0.03393659349530935,
|
|
"num_tokens": 486155.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.91849193572998,
|
|
"epoch": 0.02144133412745682,
|
|
"grad_norm": 0.65625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.614,
|
|
"mean_token_accuracy": 0.03578196074813604,
|
|
"num_tokens": 501152.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.8957664489746096,
|
|
"epoch": 0.022036926742108397,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5518,
|
|
"mean_token_accuracy": 0.035484511591494086,
|
|
"num_tokens": 514856.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.849284267425537,
|
|
"epoch": 0.022632519356759976,
|
|
"grad_norm": 0.74609375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.5634,
|
|
"mean_token_accuracy": 0.03569753393530846,
|
|
"num_tokens": 529356.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.8729674339294435,
|
|
"epoch": 0.023228111971411555,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.531,
|
|
"mean_token_accuracy": 0.032332938723266126,
|
|
"num_tokens": 542876.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.819821453094482,
|
|
"epoch": 0.023823704586063133,
|
|
"grad_norm": 0.5859375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.5222,
|
|
"mean_token_accuracy": 0.035688727907836434,
|
|
"num_tokens": 557245.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.872504854202271,
|
|
"epoch": 0.024419297200714712,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4524,
|
|
"mean_token_accuracy": 0.038831068016588685,
|
|
"num_tokens": 571458.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.879109287261963,
|
|
"epoch": 0.02501488981536629,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.4328,
|
|
"mean_token_accuracy": 0.038509660959243776,
|
|
"num_tokens": 588000.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.834728860855103,
|
|
"epoch": 0.02561048243001787,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.4685,
|
|
"mean_token_accuracy": 0.04405377022922039,
|
|
"num_tokens": 602302.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.883588743209839,
|
|
"epoch": 0.026206075044669448,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.4867,
|
|
"mean_token_accuracy": 0.04842556305229664,
|
|
"num_tokens": 616708.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.869970273971558,
|
|
"epoch": 0.026801667659321026,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3351,
|
|
"mean_token_accuracy": 0.04784993939101696,
|
|
"num_tokens": 629236.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.854291677474976,
|
|
"epoch": 0.0273972602739726,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.4034,
|
|
"mean_token_accuracy": 0.04960230849683285,
|
|
"num_tokens": 642934.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.824396181106567,
|
|
"epoch": 0.02799285288862418,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2672,
|
|
"mean_token_accuracy": 0.05327465645968914,
|
|
"num_tokens": 656008.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.7845237255096436,
|
|
"epoch": 0.02858844550327576,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.4951,
|
|
"mean_token_accuracy": 0.055526412278413775,
|
|
"num_tokens": 668843.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.871533012390136,
|
|
"epoch": 0.029184038117927337,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.3695,
|
|
"mean_token_accuracy": 0.05766946561634541,
|
|
"num_tokens": 681883.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.764459466934204,
|
|
"epoch": 0.029779630732578916,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.3497,
|
|
"mean_token_accuracy": 0.0560417152941227,
|
|
"num_tokens": 694282.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.781893491744995,
|
|
"epoch": 0.030375223347230494,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.2693,
|
|
"mean_token_accuracy": 0.06042251475155354,
|
|
"num_tokens": 708158.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.65718445777893,
|
|
"epoch": 0.030970815961882073,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.2628,
|
|
"mean_token_accuracy": 0.05864739269018173,
|
|
"num_tokens": 722083.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.700867509841919,
|
|
"epoch": 0.03156640857653365,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.2707,
|
|
"mean_token_accuracy": 0.05824490748345852,
|
|
"num_tokens": 737806.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.645946598052978,
|
|
"epoch": 0.03216200119118523,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.1346,
|
|
"mean_token_accuracy": 0.06385715305805206,
|
|
"num_tokens": 754100.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.690670967102051,
|
|
"epoch": 0.03275759380583681,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.2431,
|
|
"mean_token_accuracy": 0.05750864483416081,
|
|
"num_tokens": 769128.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.662474203109741,
|
|
"epoch": 0.03335318642048839,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.262,
|
|
"mean_token_accuracy": 0.06334917359054089,
|
|
"num_tokens": 781259.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.586826419830322,
|
|
"epoch": 0.033948779035139966,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.1542,
|
|
"mean_token_accuracy": 0.06608949862420559,
|
|
"num_tokens": 796152.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.676979112625122,
|
|
"epoch": 0.034544371649791544,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1926,
|
|
"mean_token_accuracy": 0.06706391647458076,
|
|
"num_tokens": 809686.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.527735328674316,
|
|
"epoch": 0.03513996426444312,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.1397,
|
|
"mean_token_accuracy": 0.06850280910730362,
|
|
"num_tokens": 824500.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.5874134540557865,
|
|
"epoch": 0.0357355568790947,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0864,
|
|
"mean_token_accuracy": 0.06510574333369731,
|
|
"num_tokens": 840643.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.571641063690185,
|
|
"epoch": 0.03633114949374628,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.1422,
|
|
"mean_token_accuracy": 0.06657714620232583,
|
|
"num_tokens": 853207.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.574310922622681,
|
|
"epoch": 0.03692674210839786,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.1908,
|
|
"mean_token_accuracy": 0.06848344206809998,
|
|
"num_tokens": 867735.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.612939357757568,
|
|
"epoch": 0.03752233472304944,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.0878,
|
|
"mean_token_accuracy": 0.0748877253383398,
|
|
"num_tokens": 881237.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.493647766113281,
|
|
"epoch": 0.038117927337701016,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.1092,
|
|
"mean_token_accuracy": 0.07337070256471634,
|
|
"num_tokens": 894288.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.517692279815674,
|
|
"epoch": 0.03871351995235259,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.047,
|
|
"mean_token_accuracy": 0.07527537047863006,
|
|
"num_tokens": 907492.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.46037449836731,
|
|
"epoch": 0.039309112567004166,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.9751,
|
|
"mean_token_accuracy": 0.07526533678174019,
|
|
"num_tokens": 922255.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.4556077003479,
|
|
"epoch": 0.039904705181655745,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.0248,
|
|
"mean_token_accuracy": 0.07310252115130425,
|
|
"num_tokens": 937055.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.40892858505249,
|
|
"epoch": 0.04050029779630732,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.9198,
|
|
"mean_token_accuracy": 0.0829333208501339,
|
|
"num_tokens": 951248.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.424974250793457,
|
|
"epoch": 0.0410958904109589,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9268,
|
|
"mean_token_accuracy": 0.08168905824422837,
|
|
"num_tokens": 965211.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.35948486328125,
|
|
"epoch": 0.04169148302561048,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.8982,
|
|
"mean_token_accuracy": 0.08257426097989082,
|
|
"num_tokens": 979787.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.327857494354248,
|
|
"epoch": 0.04228707564026206,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.899,
|
|
"mean_token_accuracy": 0.0832743663340807,
|
|
"num_tokens": 993412.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.3454547882080075,
|
|
"epoch": 0.04288266825491364,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8965,
|
|
"mean_token_accuracy": 0.08764276057481765,
|
|
"num_tokens": 1006819.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.293627500534058,
|
|
"epoch": 0.043478260869565216,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8934,
|
|
"mean_token_accuracy": 0.08295368179678916,
|
|
"num_tokens": 1022287.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.347591924667358,
|
|
"epoch": 0.044073853484216795,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.8917,
|
|
"mean_token_accuracy": 0.08488502353429794,
|
|
"num_tokens": 1034908.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.298069429397583,
|
|
"epoch": 0.04466944609886837,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.9273,
|
|
"mean_token_accuracy": 0.08334985077381134,
|
|
"num_tokens": 1051506.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.278151607513427,
|
|
"epoch": 0.04526503871351995,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8016,
|
|
"mean_token_accuracy": 0.07929958626627923,
|
|
"num_tokens": 1066382.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.273221397399903,
|
|
"epoch": 0.04586063132817153,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8922,
|
|
"mean_token_accuracy": 0.07912624552845955,
|
|
"num_tokens": 1082030.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.334939050674438,
|
|
"epoch": 0.04645622394282311,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.8883,
|
|
"mean_token_accuracy": 0.08404726162552834,
|
|
"num_tokens": 1095926.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.172577381134033,
|
|
"epoch": 0.04705181655747469,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7822,
|
|
"mean_token_accuracy": 0.08988622054457665,
|
|
"num_tokens": 1110579.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.259484338760376,
|
|
"epoch": 0.047647409172126266,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.816,
|
|
"mean_token_accuracy": 0.08736216723918915,
|
|
"num_tokens": 1124001.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.269467163085937,
|
|
"epoch": 0.048243001786777845,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8531,
|
|
"mean_token_accuracy": 0.08359652012586594,
|
|
"num_tokens": 1138316.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.1539130210876465,
|
|
"epoch": 0.048838594401429423,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7617,
|
|
"mean_token_accuracy": 0.09034412279725075,
|
|
"num_tokens": 1150055.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.232608604431152,
|
|
"epoch": 0.049434187016081,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.8714,
|
|
"mean_token_accuracy": 0.08702659085392953,
|
|
"num_tokens": 1163645.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.214559555053711,
|
|
"epoch": 0.05002977963073258,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.7167,
|
|
"mean_token_accuracy": 0.09158963859081268,
|
|
"num_tokens": 1176660.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.138844728469849,
|
|
"epoch": 0.05062537224538416,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8125,
|
|
"mean_token_accuracy": 0.08576413616538048,
|
|
"num_tokens": 1193169.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.21035943031311,
|
|
"epoch": 0.05122096486003574,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7673,
|
|
"mean_token_accuracy": 0.08956543728709221,
|
|
"num_tokens": 1208484.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.134724426269531,
|
|
"epoch": 0.051816557474687316,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7891,
|
|
"mean_token_accuracy": 0.09439030438661575,
|
|
"num_tokens": 1222925.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.176211738586426,
|
|
"epoch": 0.052412150089338895,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7304,
|
|
"mean_token_accuracy": 0.09262275099754333,
|
|
"num_tokens": 1237949.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.128346967697143,
|
|
"epoch": 0.053007742703990474,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7479,
|
|
"mean_token_accuracy": 0.09496347159147263,
|
|
"num_tokens": 1251535.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.070934915542603,
|
|
"epoch": 0.05360333531864205,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6667,
|
|
"mean_token_accuracy": 0.09655397906899452,
|
|
"num_tokens": 1265453.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.061871910095215,
|
|
"epoch": 0.054198927933293624,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.7003,
|
|
"mean_token_accuracy": 0.09210864752531052,
|
|
"num_tokens": 1280662.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.078719282150269,
|
|
"epoch": 0.0547945205479452,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7557,
|
|
"mean_token_accuracy": 0.08713515400886536,
|
|
"num_tokens": 1294980.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.058428335189819,
|
|
"epoch": 0.05539011316259678,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6355,
|
|
"mean_token_accuracy": 0.09095051512122154,
|
|
"num_tokens": 1309686.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.989340925216675,
|
|
"epoch": 0.05598570577724836,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.6265,
|
|
"mean_token_accuracy": 0.09936674162745476,
|
|
"num_tokens": 1324815.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.9802086353302,
|
|
"epoch": 0.05658129839189994,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.684,
|
|
"mean_token_accuracy": 0.09216802343726158,
|
|
"num_tokens": 1337829.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.004001188278198,
|
|
"epoch": 0.05717689100655152,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6883,
|
|
"mean_token_accuracy": 0.09686136618256569,
|
|
"num_tokens": 1352163.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.097426795959473,
|
|
"epoch": 0.057772483621203095,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.616,
|
|
"mean_token_accuracy": 0.09604597613215446,
|
|
"num_tokens": 1364954.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.972438669204712,
|
|
"epoch": 0.058368076235854674,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6398,
|
|
"mean_token_accuracy": 0.08891589269042015,
|
|
"num_tokens": 1379414.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.947280073165894,
|
|
"epoch": 0.05896366885050625,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.529,
|
|
"mean_token_accuracy": 0.10238926038146019,
|
|
"num_tokens": 1393515.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.855033922195434,
|
|
"epoch": 0.05955926146515783,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.5368,
|
|
"mean_token_accuracy": 0.0994467243552208,
|
|
"num_tokens": 1408986.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.936503171920776,
|
|
"epoch": 0.06015485407980941,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.5558,
|
|
"mean_token_accuracy": 0.09889275133609772,
|
|
"num_tokens": 1423176.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.947684907913208,
|
|
"epoch": 0.06075044669446099,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6849,
|
|
"mean_token_accuracy": 0.09629747048020362,
|
|
"num_tokens": 1436802.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.9376726150512695,
|
|
"epoch": 0.06134603930911257,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5501,
|
|
"mean_token_accuracy": 0.09848419949412346,
|
|
"num_tokens": 1449212.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.991093397140503,
|
|
"epoch": 0.061941631923764146,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6016,
|
|
"mean_token_accuracy": 0.10005390420556068,
|
|
"num_tokens": 1463357.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.963415336608887,
|
|
"epoch": 0.06253722453841572,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.599,
|
|
"mean_token_accuracy": 0.09710575267672539,
|
|
"num_tokens": 1477494.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.917751359939575,
|
|
"epoch": 0.0631328171530673,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.524,
|
|
"mean_token_accuracy": 0.10168539136648178,
|
|
"num_tokens": 1491687.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.814596652984619,
|
|
"epoch": 0.06372840976771887,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.4731,
|
|
"mean_token_accuracy": 0.1022674635052681,
|
|
"num_tokens": 1506656.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.872687768936157,
|
|
"epoch": 0.06432400238237046,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.526,
|
|
"mean_token_accuracy": 0.10296604335308075,
|
|
"num_tokens": 1519336.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.920898389816284,
|
|
"epoch": 0.06491959499702203,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6655,
|
|
"mean_token_accuracy": 0.09182084426283836,
|
|
"num_tokens": 1535204.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.810980796813965,
|
|
"epoch": 0.06551518761167362,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.4614,
|
|
"mean_token_accuracy": 0.10793502181768418,
|
|
"num_tokens": 1547876.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.866818284988403,
|
|
"epoch": 0.06611078022632519,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5846,
|
|
"mean_token_accuracy": 0.09650774598121643,
|
|
"num_tokens": 1560315.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.915607261657715,
|
|
"epoch": 0.06670637284097677,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6379,
|
|
"mean_token_accuracy": 0.09755613207817078,
|
|
"num_tokens": 1576379.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.900129795074463,
|
|
"epoch": 0.06730196545562835,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.4841,
|
|
"mean_token_accuracy": 0.1018719919025898,
|
|
"num_tokens": 1590480.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.76942195892334,
|
|
"epoch": 0.06789755807027993,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.5712,
|
|
"mean_token_accuracy": 0.0946121223270893,
|
|
"num_tokens": 1605328.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.830248785018921,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.4961,
|
|
"mean_token_accuracy": 0.10186498910188675,
|
|
"num_tokens": 1619814.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.79195203781128,
|
|
"epoch": 0.06908874329958309,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.4321,
|
|
"mean_token_accuracy": 0.10531904101371765,
|
|
"num_tokens": 1632561.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.829716062545776,
|
|
"epoch": 0.06968433591423466,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.5314,
|
|
"mean_token_accuracy": 0.10198022872209549,
|
|
"num_tokens": 1645669.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.837934589385986,
|
|
"epoch": 0.07027992852888625,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.4758,
|
|
"mean_token_accuracy": 0.10381783097982407,
|
|
"num_tokens": 1660479.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.66625747680664,
|
|
"epoch": 0.07087552114353782,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5107,
|
|
"mean_token_accuracy": 0.10095196142792702,
|
|
"num_tokens": 1673966.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.682705497741699,
|
|
"epoch": 0.0714711137581894,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.3698,
|
|
"mean_token_accuracy": 0.10811003074049949,
|
|
"num_tokens": 1688866.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.692874574661255,
|
|
"epoch": 0.07206670637284097,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.3886,
|
|
"mean_token_accuracy": 0.10743283107876778,
|
|
"num_tokens": 1703810.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.8178516864776615,
|
|
"epoch": 0.07266229898749256,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6076,
|
|
"mean_token_accuracy": 0.10134734436869622,
|
|
"num_tokens": 1719308.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.808244848251343,
|
|
"epoch": 0.07325789160214413,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.3798,
|
|
"mean_token_accuracy": 0.11242888495326042,
|
|
"num_tokens": 1734508.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.68076720237732,
|
|
"epoch": 0.07385348421679572,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.3672,
|
|
"mean_token_accuracy": 0.11125868856906891,
|
|
"num_tokens": 1745999.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.622215604782104,
|
|
"epoch": 0.07444907683144729,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.3755,
|
|
"mean_token_accuracy": 0.10476350486278534,
|
|
"num_tokens": 1761083.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.577097368240357,
|
|
"epoch": 0.07504466944609887,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.3218,
|
|
"mean_token_accuracy": 0.1131422147154808,
|
|
"num_tokens": 1774948.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.801549434661865,
|
|
"epoch": 0.07564026206075045,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.4314,
|
|
"mean_token_accuracy": 0.10259917750954628,
|
|
"num_tokens": 1787897.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.578335189819336,
|
|
"epoch": 0.07623585467540203,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.3244,
|
|
"mean_token_accuracy": 0.10745472609996795,
|
|
"num_tokens": 1801208.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.574746179580688,
|
|
"epoch": 0.0768314472900536,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.332,
|
|
"mean_token_accuracy": 0.11013660952448845,
|
|
"num_tokens": 1815439.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.600382614135742,
|
|
"epoch": 0.07742703990470517,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.3542,
|
|
"mean_token_accuracy": 0.10833032503724098,
|
|
"num_tokens": 1828177.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.656797552108765,
|
|
"epoch": 0.07802263251935676,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.3214,
|
|
"mean_token_accuracy": 0.10862169042229652,
|
|
"num_tokens": 1844854.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.581733703613281,
|
|
"epoch": 0.07861822513400833,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.323,
|
|
"mean_token_accuracy": 0.11257945150136947,
|
|
"num_tokens": 1858245.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.638799571990967,
|
|
"epoch": 0.07921381774865992,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.4281,
|
|
"mean_token_accuracy": 0.10286775305867195,
|
|
"num_tokens": 1872167.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.627243375778198,
|
|
"epoch": 0.07980941036331149,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.3738,
|
|
"mean_token_accuracy": 0.10839225575327874,
|
|
"num_tokens": 1885376.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.654307746887207,
|
|
"epoch": 0.08040500297796307,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.10483642816543579,
|
|
"num_tokens": 1899318.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.590982151031494,
|
|
"epoch": 0.08100059559261465,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4351,
|
|
"mean_token_accuracy": 0.10326916947960854,
|
|
"num_tokens": 1914028.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.684178638458252,
|
|
"epoch": 0.08159618820726623,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.11002843976020812,
|
|
"num_tokens": 1927653.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.597846174240113,
|
|
"epoch": 0.0821917808219178,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.3526,
|
|
"mean_token_accuracy": 0.10854012072086335,
|
|
"num_tokens": 1941397.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.603009176254273,
|
|
"epoch": 0.08278737343656939,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.3154,
|
|
"mean_token_accuracy": 0.11639049127697945,
|
|
"num_tokens": 1955941.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.531544780731201,
|
|
"epoch": 0.08338296605122096,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3378,
|
|
"mean_token_accuracy": 0.11506927385926247,
|
|
"num_tokens": 1970440.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.508570957183838,
|
|
"epoch": 0.08397855866587255,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2619,
|
|
"mean_token_accuracy": 0.11228064522147178,
|
|
"num_tokens": 1985770.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.570549583435058,
|
|
"epoch": 0.08457415128052412,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.3924,
|
|
"mean_token_accuracy": 0.10573711916804314,
|
|
"num_tokens": 1999314.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.559501218795776,
|
|
"epoch": 0.0851697438951757,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.2506,
|
|
"mean_token_accuracy": 0.11841808259487152,
|
|
"num_tokens": 2014578.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.529557180404663,
|
|
"epoch": 0.08576533650982728,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.3527,
|
|
"mean_token_accuracy": 0.11220865100622177,
|
|
"num_tokens": 2027650.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.549836015701294,
|
|
"epoch": 0.08636092912447886,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.2942,
|
|
"mean_token_accuracy": 0.11042425483465194,
|
|
"num_tokens": 2042215.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.5296502113342285,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3333,
|
|
"mean_token_accuracy": 0.11251013353466988,
|
|
"num_tokens": 2055818.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.478091764450073,
|
|
"epoch": 0.08755211435378202,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.269,
|
|
"mean_token_accuracy": 0.1072472244501114,
|
|
"num_tokens": 2069040.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.4354370594024655,
|
|
"epoch": 0.08814770696843359,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.2801,
|
|
"mean_token_accuracy": 0.11433858945965766,
|
|
"num_tokens": 2085085.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.527103233337402,
|
|
"epoch": 0.08874329958308518,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3706,
|
|
"mean_token_accuracy": 0.10901240557432175,
|
|
"num_tokens": 2100780.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.6975359439849855,
|
|
"epoch": 0.08933889219773675,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.355,
|
|
"mean_token_accuracy": 0.10414705723524094,
|
|
"num_tokens": 2116317.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.4591529846191404,
|
|
"epoch": 0.08993448481238833,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2955,
|
|
"mean_token_accuracy": 0.1131321668624878,
|
|
"num_tokens": 2130865.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.512085676193237,
|
|
"epoch": 0.0905300774270399,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3262,
|
|
"mean_token_accuracy": 0.11273712068796157,
|
|
"num_tokens": 2145791.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.423099613189697,
|
|
"epoch": 0.09112567004169149,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.2401,
|
|
"mean_token_accuracy": 0.11704929918050766,
|
|
"num_tokens": 2158750.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.556084394454956,
|
|
"epoch": 0.09172126265634306,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.10720572769641876,
|
|
"num_tokens": 2175026.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.3942100524902346,
|
|
"epoch": 0.09231685527099463,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.2269,
|
|
"mean_token_accuracy": 0.10797101855278016,
|
|
"num_tokens": 2189597.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.539155578613281,
|
|
"epoch": 0.09291244788564622,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4094,
|
|
"mean_token_accuracy": 0.10737727358937263,
|
|
"num_tokens": 2203663.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.493429231643677,
|
|
"epoch": 0.09350804050029779,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2194,
|
|
"mean_token_accuracy": 0.11081875488162041,
|
|
"num_tokens": 2218784.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.399382591247559,
|
|
"epoch": 0.09410363311494938,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.2409,
|
|
"mean_token_accuracy": 0.10967378914356232,
|
|
"num_tokens": 2233256.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.414550352096557,
|
|
"epoch": 0.09469922572960095,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.2574,
|
|
"mean_token_accuracy": 0.11340164989233018,
|
|
"num_tokens": 2247689.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.391186666488648,
|
|
"epoch": 0.09529481834425253,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.108,
|
|
"mean_token_accuracy": 0.11849050521850586,
|
|
"num_tokens": 2261158.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.336691284179688,
|
|
"epoch": 0.0958904109589041,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.0658,
|
|
"mean_token_accuracy": 0.12222642973065376,
|
|
"num_tokens": 2274013.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.393833875656128,
|
|
"epoch": 0.09648600357355569,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3357,
|
|
"mean_token_accuracy": 0.11333975717425346,
|
|
"num_tokens": 2287471.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.281843757629394,
|
|
"epoch": 0.09708159618820726,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.155,
|
|
"mean_token_accuracy": 0.11718202605843545,
|
|
"num_tokens": 2302536.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.497118377685547,
|
|
"epoch": 0.09767718880285885,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3451,
|
|
"mean_token_accuracy": 0.1120209239423275,
|
|
"num_tokens": 2315235.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.487940311431885,
|
|
"epoch": 0.09827278141751042,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4064,
|
|
"mean_token_accuracy": 0.1106854259967804,
|
|
"num_tokens": 2329010.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.468513631820679,
|
|
"epoch": 0.098868374032162,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.12238088548183441,
|
|
"num_tokens": 2342862.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.339007472991943,
|
|
"epoch": 0.09946396664681358,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.12445630058646202,
|
|
"num_tokens": 2354680.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.439451789855957,
|
|
"epoch": 0.10005955926146516,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.2147,
|
|
"mean_token_accuracy": 0.11520385593175889,
|
|
"num_tokens": 2369251.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.236489772796631,
|
|
"epoch": 0.10065515187611673,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.253,
|
|
"mean_token_accuracy": 0.11649648323655129,
|
|
"num_tokens": 2382880.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.354185771942139,
|
|
"epoch": 0.10125074449076832,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.1206,
|
|
"mean_token_accuracy": 0.12046246901154518,
|
|
"num_tokens": 2397627.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.437240266799927,
|
|
"epoch": 0.10184633710541989,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.11783369481563569,
|
|
"num_tokens": 2411923.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.422359657287598,
|
|
"epoch": 0.10244192972007148,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.2769,
|
|
"mean_token_accuracy": 0.10963128358125687,
|
|
"num_tokens": 2426253.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.263160324096679,
|
|
"epoch": 0.10303752233472305,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.11795227006077766,
|
|
"num_tokens": 2440887.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.384651327133179,
|
|
"epoch": 0.10363311494937463,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1555,
|
|
"mean_token_accuracy": 0.12060579136013985,
|
|
"num_tokens": 2453556.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.326425170898437,
|
|
"epoch": 0.1042287075640262,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.2142,
|
|
"mean_token_accuracy": 0.12140618488192559,
|
|
"num_tokens": 2467374.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.30199031829834,
|
|
"epoch": 0.10482430017867779,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.1804,
|
|
"mean_token_accuracy": 0.123384477943182,
|
|
"num_tokens": 2481106.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.317232608795166,
|
|
"epoch": 0.10541989279332936,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.121,
|
|
"mean_token_accuracy": 0.12105304449796676,
|
|
"num_tokens": 2495431.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.264630317687988,
|
|
"epoch": 0.10601548540798095,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2037,
|
|
"mean_token_accuracy": 0.1106337383389473,
|
|
"num_tokens": 2511312.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.330672264099121,
|
|
"epoch": 0.10661107802263252,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.1307,
|
|
"mean_token_accuracy": 0.11806633621454239,
|
|
"num_tokens": 2524960.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.309416007995606,
|
|
"epoch": 0.1072066706372841,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.1918,
|
|
"mean_token_accuracy": 0.12466888576745987,
|
|
"num_tokens": 2537965.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.334802722930908,
|
|
"epoch": 0.10780226325193568,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2007,
|
|
"mean_token_accuracy": 0.11948587447404861,
|
|
"num_tokens": 2550802.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.284816074371338,
|
|
"epoch": 0.10839785586658725,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2053,
|
|
"mean_token_accuracy": 0.11889010146260262,
|
|
"num_tokens": 2565844.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.314342594146728,
|
|
"epoch": 0.10899344848123883,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.1847,
|
|
"mean_token_accuracy": 0.12024665251374245,
|
|
"num_tokens": 2580049.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.272147846221924,
|
|
"epoch": 0.1095890410958904,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.0723,
|
|
"mean_token_accuracy": 0.1256310187280178,
|
|
"num_tokens": 2594516.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.1829633712768555,
|
|
"epoch": 0.11018463371054199,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1416,
|
|
"mean_token_accuracy": 0.1155655913054943,
|
|
"num_tokens": 2610528.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.294937372207642,
|
|
"epoch": 0.11078022632519356,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.1155,
|
|
"mean_token_accuracy": 0.11875416040420532,
|
|
"num_tokens": 2624357.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.172679758071899,
|
|
"epoch": 0.11137581893984515,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.0184,
|
|
"mean_token_accuracy": 0.12533122226595877,
|
|
"num_tokens": 2640422.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.129613590240479,
|
|
"epoch": 0.11197141155449672,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.025,
|
|
"mean_token_accuracy": 0.12043802663683892,
|
|
"num_tokens": 2653573.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.23607611656189,
|
|
"epoch": 0.1125670041691483,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.027,
|
|
"mean_token_accuracy": 0.12452024072408677,
|
|
"num_tokens": 2667746.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.131921672821045,
|
|
"epoch": 0.11316259678379988,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.0558,
|
|
"mean_token_accuracy": 0.12360034808516503,
|
|
"num_tokens": 2681158.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.248904609680176,
|
|
"epoch": 0.11375818939845146,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.1247,
|
|
"mean_token_accuracy": 0.12168019115924836,
|
|
"num_tokens": 2693093.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.238854789733887,
|
|
"epoch": 0.11435378201310303,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.1349,
|
|
"mean_token_accuracy": 0.12076621502637863,
|
|
"num_tokens": 2704664.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.1245146751403805,
|
|
"epoch": 0.11494937462775462,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 5.9786,
|
|
"mean_token_accuracy": 0.11912716627120971,
|
|
"num_tokens": 2718495.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.239951133728027,
|
|
"epoch": 0.11554496724240619,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.1273331493139267,
|
|
"num_tokens": 2731529.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.079785490036011,
|
|
"epoch": 0.11614055985705778,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 5.9914,
|
|
"mean_token_accuracy": 0.12656966224312782,
|
|
"num_tokens": 2745382.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.203353357315064,
|
|
"epoch": 0.11673615247170935,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.0886,
|
|
"mean_token_accuracy": 0.12444658502936363,
|
|
"num_tokens": 2758291.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.122103357315064,
|
|
"epoch": 0.11733174508636093,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.12958693206310273,
|
|
"num_tokens": 2771179.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.140854740142823,
|
|
"epoch": 0.1179273377010125,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.0667,
|
|
"mean_token_accuracy": 0.12540014907717706,
|
|
"num_tokens": 2784172.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.256523656845093,
|
|
"epoch": 0.11852293031566409,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.136,
|
|
"mean_token_accuracy": 0.12193455398082734,
|
|
"num_tokens": 2798402.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.121761846542358,
|
|
"epoch": 0.11911852293031566,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.1234335795044899,
|
|
"num_tokens": 2813371.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.133089637756347,
|
|
"epoch": 0.11971411554496725,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999999974174771,
|
|
"loss": 6.015,
|
|
"mean_token_accuracy": 0.12509532943367957,
|
|
"num_tokens": 2825837.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.220070838928223,
|
|
"epoch": 0.12030970815961882,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999869259778,
|
|
"loss": 6.0694,
|
|
"mean_token_accuracy": 0.12010028138756752,
|
|
"num_tokens": 2837988.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.105342245101928,
|
|
"epoch": 0.1209053007742704,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999999683640947,
|
|
"loss": 5.9796,
|
|
"mean_token_accuracy": 0.12876347005367278,
|
|
"num_tokens": 2851396.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.032329750061035,
|
|
"epoch": 0.12150089338892198,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999999417318286,
|
|
"loss": 6.0423,
|
|
"mean_token_accuracy": 0.12623496055603028,
|
|
"num_tokens": 2863958.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.242678785324097,
|
|
"epoch": 0.12209648600357356,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999070291805,
|
|
"loss": 6.1269,
|
|
"mean_token_accuracy": 0.11811491474509239,
|
|
"num_tokens": 2876179.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.156660556793213,
|
|
"epoch": 0.12269207861822513,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998642561514,
|
|
"loss": 6.1333,
|
|
"mean_token_accuracy": 0.12322013601660728,
|
|
"num_tokens": 2890023.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.156386804580689,
|
|
"epoch": 0.1232876712328767,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999998134127432,
|
|
"loss": 6.0044,
|
|
"mean_token_accuracy": 0.12466984316706657,
|
|
"num_tokens": 2902345.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.155143404006958,
|
|
"epoch": 0.12388326384752829,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999997544989574,
|
|
"loss": 6.1163,
|
|
"mean_token_accuracy": 0.11543303802609443,
|
|
"num_tokens": 2916310.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.038448905944824,
|
|
"epoch": 0.12447885646217986,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999996875147963,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.12575222179293633,
|
|
"num_tokens": 2928523.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.218308925628662,
|
|
"epoch": 0.12507444907683143,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999996124602621,
|
|
"loss": 6.1384,
|
|
"mean_token_accuracy": 0.12007349729537964,
|
|
"num_tokens": 2943367.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.125283241271973,
|
|
"epoch": 0.12567004169148302,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999995293353578,
|
|
"loss": 6.0472,
|
|
"mean_token_accuracy": 0.12148560509085655,
|
|
"num_tokens": 2956995.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.094510746002197,
|
|
"epoch": 0.1262656343061346,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999994381400862,
|
|
"loss": 6.0225,
|
|
"mean_token_accuracy": 0.12709481567144393,
|
|
"num_tokens": 2971380.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.054570245742798,
|
|
"epoch": 0.1268612269207862,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999993388744504,
|
|
"loss": 6.0224,
|
|
"mean_token_accuracy": 0.12784620597958565,
|
|
"num_tokens": 2986048.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.168426752090454,
|
|
"epoch": 0.12745681953543775,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999992315384543,
|
|
"loss": 6.0531,
|
|
"mean_token_accuracy": 0.1305770047008991,
|
|
"num_tokens": 2997058.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.075695133209228,
|
|
"epoch": 0.12805241215008933,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999991161321014,
|
|
"loss": 6.0253,
|
|
"mean_token_accuracy": 0.12606261819601058,
|
|
"num_tokens": 3011844.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.1227617263793945,
|
|
"epoch": 0.12864800476474092,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999989926553962,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.13007696568965912,
|
|
"num_tokens": 3024648.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.063864231109619,
|
|
"epoch": 0.1292435973793925,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499998861108343,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.1270127885043621,
|
|
"num_tokens": 3038533.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.017603158950806,
|
|
"epoch": 0.12983918999404406,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999987214909464,
|
|
"loss": 5.893,
|
|
"mean_token_accuracy": 0.1318114221096039,
|
|
"num_tokens": 3052531.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.156506204605103,
|
|
"epoch": 0.13043478260869565,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999985738032115,
|
|
"loss": 6.0331,
|
|
"mean_token_accuracy": 0.11994639709591866,
|
|
"num_tokens": 3066526.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.000065565109253,
|
|
"epoch": 0.13103037522334723,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999984180451436,
|
|
"loss": 5.9346,
|
|
"mean_token_accuracy": 0.12969892397522925,
|
|
"num_tokens": 3080729.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.11169171333313,
|
|
"epoch": 0.13162596783799882,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999982542167483,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.12554007694125174,
|
|
"num_tokens": 3093776.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 5.954249620437622,
|
|
"epoch": 0.13222156045265038,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999980823180314,
|
|
"loss": 5.9234,
|
|
"mean_token_accuracy": 0.13084314540028572,
|
|
"num_tokens": 3107005.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.159169912338257,
|
|
"epoch": 0.13281715306730196,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499997902348999,
|
|
"loss": 6.1685,
|
|
"mean_token_accuracy": 0.11998955681920051,
|
|
"num_tokens": 3120840.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.067917442321777,
|
|
"epoch": 0.13341274568195355,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999977143096578,
|
|
"loss": 5.9303,
|
|
"mean_token_accuracy": 0.13456045612692832,
|
|
"num_tokens": 3134894.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.162211799621582,
|
|
"epoch": 0.13400833829660513,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999975182000143,
|
|
"loss": 6.1178,
|
|
"mean_token_accuracy": 0.12521427497267723,
|
|
"num_tokens": 3146917.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.085057544708252,
|
|
"epoch": 0.1346039309112567,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999973140200759,
|
|
"loss": 6.0004,
|
|
"mean_token_accuracy": 0.12693992480635644,
|
|
"num_tokens": 3162161.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.02038984298706,
|
|
"epoch": 0.13519952352590828,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999971017698495,
|
|
"loss": 5.9444,
|
|
"mean_token_accuracy": 0.1285225346684456,
|
|
"num_tokens": 3176627.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.050753974914551,
|
|
"epoch": 0.13579511614055986,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999968814493428,
|
|
"loss": 5.9873,
|
|
"mean_token_accuracy": 0.1245907999575138,
|
|
"num_tokens": 3190139.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 5.881817102432251,
|
|
"epoch": 0.13639070875521145,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999966530585639,
|
|
"loss": 5.7838,
|
|
"mean_token_accuracy": 0.13395376428961753,
|
|
"num_tokens": 3202312.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.076900434494019,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999964165975209,
|
|
"loss": 5.949,
|
|
"mean_token_accuracy": 0.12764090895652772,
|
|
"num_tokens": 3219052.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 5.920963859558105,
|
|
"epoch": 0.1375818939845146,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999961720662221,
|
|
"loss": 5.8668,
|
|
"mean_token_accuracy": 0.13792282938957215,
|
|
"num_tokens": 3233706.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.0697290897369385,
|
|
"epoch": 0.13817748659916618,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999959194646766,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.12914232015609742,
|
|
"num_tokens": 3249947.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.001479244232177,
|
|
"epoch": 0.13877307921381773,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999956587928932,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.1353149361908436,
|
|
"num_tokens": 3264308.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.003630208969116,
|
|
"epoch": 0.13936867182846932,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999953900508814,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.14206771701574325,
|
|
"num_tokens": 3277171.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 5.932111120223999,
|
|
"epoch": 0.1399642644431209,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999951132386507,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.13024417757987977,
|
|
"num_tokens": 3290445.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.034594345092773,
|
|
"epoch": 0.1405598570577725,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999948283562111,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.1353663869202137,
|
|
"num_tokens": 3304850.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 5.916999483108521,
|
|
"epoch": 0.14115544967242405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499994535403573,
|
|
"loss": 5.9107,
|
|
"mean_token_accuracy": 0.1338230200111866,
|
|
"num_tokens": 3318765.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.021168041229248,
|
|
"epoch": 0.14175104228707563,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999942343807465,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.12999824807047844,
|
|
"num_tokens": 3330403.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.017589950561524,
|
|
"epoch": 0.14234663490172722,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999939252877428,
|
|
"loss": 5.9031,
|
|
"mean_token_accuracy": 0.1311019204556942,
|
|
"num_tokens": 3346420.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.04552264213562,
|
|
"epoch": 0.1429422275163788,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999936081245727,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.1281133323907852,
|
|
"num_tokens": 3361853.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 5.927685737609863,
|
|
"epoch": 0.14353782013103036,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999932828912478,
|
|
"loss": 5.9222,
|
|
"mean_token_accuracy": 0.1316317394375801,
|
|
"num_tokens": 3375907.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.026217603683472,
|
|
"epoch": 0.14413341274568195,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999929495877796,
|
|
"loss": 5.9329,
|
|
"mean_token_accuracy": 0.12971090972423555,
|
|
"num_tokens": 3390151.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 5.9505268096923825,
|
|
"epoch": 0.14472900536033353,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999926082141801,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.12363883629441261,
|
|
"num_tokens": 3405151.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.028708839416504,
|
|
"epoch": 0.14532459797498512,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999922587704616,
|
|
"loss": 5.945,
|
|
"mean_token_accuracy": 0.1303933598101139,
|
|
"num_tokens": 3420510.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 5.931709337234497,
|
|
"epoch": 0.14592019058963668,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999919012566366,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.13435358107089995,
|
|
"num_tokens": 3435162.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.036328411102295,
|
|
"epoch": 0.14651578320428826,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999915356727179,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.12724584117531776,
|
|
"num_tokens": 3450923.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 5.912316751480103,
|
|
"epoch": 0.14711137581893985,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999911620187186,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.13225295692682265,
|
|
"num_tokens": 3464575.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 5.9586883068084715,
|
|
"epoch": 0.14770696843359143,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999907802946521,
|
|
"loss": 5.8034,
|
|
"mean_token_accuracy": 0.14033481776714324,
|
|
"num_tokens": 3477494.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.103541851043701,
|
|
"epoch": 0.148302561048243,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999903905005323,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.12562865763902664,
|
|
"num_tokens": 3492314.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 5.976743364334107,
|
|
"epoch": 0.14889815366289458,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999899926363729,
|
|
"loss": 5.855,
|
|
"mean_token_accuracy": 0.13544159680604934,
|
|
"num_tokens": 3504913.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.0377197265625,
|
|
"epoch": 0.14949374627754616,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999895867021882,
|
|
"loss": 5.9966,
|
|
"mean_token_accuracy": 0.1272701993584633,
|
|
"num_tokens": 3519758.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 5.899927043914795,
|
|
"epoch": 0.15008933889219775,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999891726979928,
|
|
"loss": 5.7799,
|
|
"mean_token_accuracy": 0.143826425075531,
|
|
"num_tokens": 3531268.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.011205720901489,
|
|
"epoch": 0.1506849315068493,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999887506238018,
|
|
"loss": 5.9634,
|
|
"mean_token_accuracy": 0.12081619277596474,
|
|
"num_tokens": 3546560.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 5.9060577869415285,
|
|
"epoch": 0.1512805241215009,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049998832047963,
|
|
"loss": 5.8788,
|
|
"mean_token_accuracy": 0.1419125407934189,
|
|
"num_tokens": 3560602.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 5.923432683944702,
|
|
"epoch": 0.15187611673615248,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999878822654929,
|
|
"loss": 5.8492,
|
|
"mean_token_accuracy": 0.1282820850610733,
|
|
"num_tokens": 3575611.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 5.9302064895629885,
|
|
"epoch": 0.15247170935080406,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999874359814064,
|
|
"loss": 5.8245,
|
|
"mean_token_accuracy": 0.1341463267803192,
|
|
"num_tokens": 3589933.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 5.930386114120483,
|
|
"epoch": 0.15306730196545562,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999869816273863,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.13333613201975822,
|
|
"num_tokens": 3602513.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 5.979178810119629,
|
|
"epoch": 0.1536628945801072,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999865192034489,
|
|
"loss": 5.9155,
|
|
"mean_token_accuracy": 0.12899079769849778,
|
|
"num_tokens": 3615488.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 5.912979173660278,
|
|
"epoch": 0.1542584871947588,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499986048709611,
|
|
"loss": 5.8021,
|
|
"mean_token_accuracy": 0.13999683931469917,
|
|
"num_tokens": 3629292.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 5.807839107513428,
|
|
"epoch": 0.15485407980941035,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999855701458893,
|
|
"loss": 5.8186,
|
|
"mean_token_accuracy": 0.13712158128619195,
|
|
"num_tokens": 3647010.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 5.9487380027771,
|
|
"epoch": 0.15544967242406194,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999850835123009,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.14222911149263381,
|
|
"num_tokens": 3661994.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 5.9588648796081545,
|
|
"epoch": 0.15604526503871352,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999845888088635,
|
|
"loss": 5.886,
|
|
"mean_token_accuracy": 0.1360446184873581,
|
|
"num_tokens": 3676789.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 5.856528997421265,
|
|
"epoch": 0.1566408576533651,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999840860355946,
|
|
"loss": 5.8195,
|
|
"mean_token_accuracy": 0.133524090051651,
|
|
"num_tokens": 3689598.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 5.940479564666748,
|
|
"epoch": 0.15723645026801666,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999835751925124,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.13627201095223426,
|
|
"num_tokens": 3703597.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 5.906275892257691,
|
|
"epoch": 0.15783204288266825,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999830562796351,
|
|
"loss": 5.8525,
|
|
"mean_token_accuracy": 0.13642849624156952,
|
|
"num_tokens": 3717312.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 5.876447772979736,
|
|
"epoch": 0.15842763549731984,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999825292969814,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.13880409449338912,
|
|
"num_tokens": 3731677.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 5.965097093582154,
|
|
"epoch": 0.15902322811197142,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999819942445703,
|
|
"loss": 5.9153,
|
|
"mean_token_accuracy": 0.13254718035459517,
|
|
"num_tokens": 3746648.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 5.833016109466553,
|
|
"epoch": 0.15961882072662298,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999814511224207,
|
|
"loss": 5.7966,
|
|
"mean_token_accuracy": 0.13968296349048615,
|
|
"num_tokens": 3760859.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.913193416595459,
|
|
"epoch": 0.16021441334127456,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999808999305523,
|
|
"loss": 5.7545,
|
|
"mean_token_accuracy": 0.14480277746915818,
|
|
"num_tokens": 3774743.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 5.9066485404968265,
|
|
"epoch": 0.16081000595592615,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999803406689848,
|
|
"loss": 5.8317,
|
|
"mean_token_accuracy": 0.13871036767959594,
|
|
"num_tokens": 3789566.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 5.926655054092407,
|
|
"epoch": 0.16140559857057774,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999797733377384,
|
|
"loss": 5.8038,
|
|
"mean_token_accuracy": 0.13857394009828566,
|
|
"num_tokens": 3802875.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 5.827342462539673,
|
|
"epoch": 0.1620011911852293,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999791979368332,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.13635163232684136,
|
|
"num_tokens": 3816197.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 5.820569038391113,
|
|
"epoch": 0.16259678379988088,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999786144662899,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.14140567183494568,
|
|
"num_tokens": 3829196.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 5.986719036102295,
|
|
"epoch": 0.16319237641453246,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999780229261295,
|
|
"loss": 5.9262,
|
|
"mean_token_accuracy": 0.13423893749713897,
|
|
"num_tokens": 3842618.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.985431957244873,
|
|
"epoch": 0.16378796902918405,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999774233163734,
|
|
"loss": 5.9037,
|
|
"mean_token_accuracy": 0.1337181843817234,
|
|
"num_tokens": 3854833.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 5.928055143356323,
|
|
"epoch": 0.1643835616438356,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999768156370428,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.14388710930943488,
|
|
"num_tokens": 3867971.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 5.865712642669678,
|
|
"epoch": 0.1649791542584872,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999761998881596,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.14262602031230925,
|
|
"num_tokens": 3881555.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.82703857421875,
|
|
"epoch": 0.16557474687313878,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999755760697459,
|
|
"loss": 5.7713,
|
|
"mean_token_accuracy": 0.14329167380928992,
|
|
"num_tokens": 3894717.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.917602491378784,
|
|
"epoch": 0.16617033948779036,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499974944181824,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.1336645595729351,
|
|
"num_tokens": 3909381.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.814576435089111,
|
|
"epoch": 0.16676593210244192,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999743042244167,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.1413685366511345,
|
|
"num_tokens": 3923828.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 5.825763845443726,
|
|
"epoch": 0.1673615247170935,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499973656197547,
|
|
"loss": 5.7272,
|
|
"mean_token_accuracy": 0.14536863341927528,
|
|
"num_tokens": 3936901.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.864505004882813,
|
|
"epoch": 0.1679571173317451,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999730001012379,
|
|
"loss": 5.8022,
|
|
"mean_token_accuracy": 0.14182989448308944,
|
|
"num_tokens": 3949052.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.884924507141113,
|
|
"epoch": 0.16855270994639668,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999723359355131,
|
|
"loss": 5.8695,
|
|
"mean_token_accuracy": 0.13713218793272972,
|
|
"num_tokens": 3963099.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.916450643539429,
|
|
"epoch": 0.16914830256104824,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999716637003965,
|
|
"loss": 5.7679,
|
|
"mean_token_accuracy": 0.13467698618769647,
|
|
"num_tokens": 3977598.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.947037076950073,
|
|
"epoch": 0.16974389517569982,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499970983395912,
|
|
"loss": 5.9176,
|
|
"mean_token_accuracy": 0.13662929236888885,
|
|
"num_tokens": 3989995.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 5.873909616470337,
|
|
"epoch": 0.1703394877903514,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999702950220841,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.137424598634243,
|
|
"num_tokens": 4002971.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.8123640537261965,
|
|
"epoch": 0.17093508040500296,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999695985789376,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.13508190885186194,
|
|
"num_tokens": 4017380.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 5.878342390060425,
|
|
"epoch": 0.17153067301965455,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999688940664972,
|
|
"loss": 5.8233,
|
|
"mean_token_accuracy": 0.13803602904081344,
|
|
"num_tokens": 4031125.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.843517732620239,
|
|
"epoch": 0.17212626563430614,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999681814847884,
|
|
"loss": 5.8015,
|
|
"mean_token_accuracy": 0.13652853295207024,
|
|
"num_tokens": 4046416.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.844456815719605,
|
|
"epoch": 0.17272185824895772,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999674608338367,
|
|
"loss": 5.8414,
|
|
"mean_token_accuracy": 0.13705504685640335,
|
|
"num_tokens": 4061024.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.8956903457641605,
|
|
"epoch": 0.17331745086360928,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999667321136681,
|
|
"loss": 5.7552,
|
|
"mean_token_accuracy": 0.14218715354800224,
|
|
"num_tokens": 4074753.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 5.7974687099456785,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999659953243085,
|
|
"loss": 5.7454,
|
|
"mean_token_accuracy": 0.13901349678635597,
|
|
"num_tokens": 4089954.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 5.833855056762696,
|
|
"epoch": 0.17450863609291245,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999652504657844,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.1415618307888508,
|
|
"num_tokens": 4105220.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.819709730148316,
|
|
"epoch": 0.17510422870756404,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999644975381226,
|
|
"loss": 5.7486,
|
|
"mean_token_accuracy": 0.14364008754491805,
|
|
"num_tokens": 4117578.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.780221319198608,
|
|
"epoch": 0.1756998213222156,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049996373654135,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.14047368094325066,
|
|
"num_tokens": 4131113.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.7004999160766605,
|
|
"epoch": 0.17629541393686718,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999629674754939,
|
|
"loss": 5.6451,
|
|
"mean_token_accuracy": 0.14624442309141159,
|
|
"num_tokens": 4145029.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.831697750091553,
|
|
"epoch": 0.17689100655151876,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999621903405819,
|
|
"loss": 5.7997,
|
|
"mean_token_accuracy": 0.14258266165852546,
|
|
"num_tokens": 4157227.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.770886516571045,
|
|
"epoch": 0.17748659916617035,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999614051366421,
|
|
"loss": 5.7737,
|
|
"mean_token_accuracy": 0.13888279870152473,
|
|
"num_tokens": 4171172.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.858391666412354,
|
|
"epoch": 0.1780821917808219,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999606118637022,
|
|
"loss": 5.7108,
|
|
"mean_token_accuracy": 0.1485131248831749,
|
|
"num_tokens": 4184219.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.714126491546631,
|
|
"epoch": 0.1786777843954735,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999598105217911,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.14674964547157288,
|
|
"num_tokens": 4199317.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.913051748275757,
|
|
"epoch": 0.17927337701012508,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999590011109373,
|
|
"loss": 5.8201,
|
|
"mean_token_accuracy": 0.13885035812854768,
|
|
"num_tokens": 4213905.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.752098417282104,
|
|
"epoch": 0.17986896962477666,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00049995818363117,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.13993846252560616,
|
|
"num_tokens": 4228123.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.836214542388916,
|
|
"epoch": 0.18046456223942822,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999573580825182,
|
|
"loss": 5.7158,
|
|
"mean_token_accuracy": 0.1386741206049919,
|
|
"num_tokens": 4243024.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.7391456127166744,
|
|
"epoch": 0.1810601548540798,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999565244650119,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.1376780353486538,
|
|
"num_tokens": 4259061.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.846730136871338,
|
|
"epoch": 0.1816557474687314,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999556827786807,
|
|
"loss": 5.8768,
|
|
"mean_token_accuracy": 0.13757510483264923,
|
|
"num_tokens": 4273010.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.847012567520141,
|
|
"epoch": 0.18225134008338298,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999548330235549,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.14503360763192177,
|
|
"num_tokens": 4286515.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.778463125228882,
|
|
"epoch": 0.18284693269803454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999539751996651,
|
|
"loss": 5.6774,
|
|
"mean_token_accuracy": 0.14557320773601531,
|
|
"num_tokens": 4300125.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.700612115859985,
|
|
"epoch": 0.18344252531268612,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499953109307042,
|
|
"loss": 5.694,
|
|
"mean_token_accuracy": 0.14429860413074494,
|
|
"num_tokens": 4313962.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.78266339302063,
|
|
"epoch": 0.1840381179273377,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999522353457165,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.14360445588827134,
|
|
"num_tokens": 4328776.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.797319126129151,
|
|
"epoch": 0.18463371054198927,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999513533157201,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.1413066007196903,
|
|
"num_tokens": 4340933.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.849434852600098,
|
|
"epoch": 0.18522930315664085,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999504632170844,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.13764437884092331,
|
|
"num_tokens": 4355463.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.8289103507995605,
|
|
"epoch": 0.18582489577129244,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999495650498413,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.14221151322126388,
|
|
"num_tokens": 4369717.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.850962543487549,
|
|
"epoch": 0.18642048838594402,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999486588140231,
|
|
"loss": 5.755,
|
|
"mean_token_accuracy": 0.1466390907764435,
|
|
"num_tokens": 4383713.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.693731641769409,
|
|
"epoch": 0.18701608100059558,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999477445096623,
|
|
"loss": 5.69,
|
|
"mean_token_accuracy": 0.14818094223737716,
|
|
"num_tokens": 4396487.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.924489593505859,
|
|
"epoch": 0.18761167361524717,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999468221367916,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.1486361064016819,
|
|
"num_tokens": 4408762.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.671824932098389,
|
|
"epoch": 0.18820726622989875,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999458916954442,
|
|
"loss": 5.6832,
|
|
"mean_token_accuracy": 0.1417291820049286,
|
|
"num_tokens": 4422871.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.778762626647949,
|
|
"epoch": 0.18880285884455034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999449531856532,
|
|
"loss": 5.7278,
|
|
"mean_token_accuracy": 0.14532867521047593,
|
|
"num_tokens": 4436399.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.71506028175354,
|
|
"epoch": 0.1893984514592019,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999440066074526,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.14706211239099504,
|
|
"num_tokens": 4450799.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.666831207275391,
|
|
"epoch": 0.18999404407385348,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999430519608762,
|
|
"loss": 5.6657,
|
|
"mean_token_accuracy": 0.15264638811349868,
|
|
"num_tokens": 4464567.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.838018226623535,
|
|
"epoch": 0.19058963668850507,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999420892459584,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.14266677126288413,
|
|
"num_tokens": 4478461.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.717880964279175,
|
|
"epoch": 0.19118522930315665,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999411184627334,
|
|
"loss": 5.6591,
|
|
"mean_token_accuracy": 0.1413282111287117,
|
|
"num_tokens": 4493252.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.751201725006103,
|
|
"epoch": 0.1917808219178082,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999401396112364,
|
|
"loss": 5.7666,
|
|
"mean_token_accuracy": 0.14517319947481155,
|
|
"num_tokens": 4507716.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.811801958084106,
|
|
"epoch": 0.1923764145324598,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499939152691502,
|
|
"loss": 5.6796,
|
|
"mean_token_accuracy": 0.14442481696605683,
|
|
"num_tokens": 4520903.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.753574323654175,
|
|
"epoch": 0.19297200714711138,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999381577035663,
|
|
"loss": 5.7269,
|
|
"mean_token_accuracy": 0.14681699872016907,
|
|
"num_tokens": 4534939.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.754568815231323,
|
|
"epoch": 0.19356759976176297,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999371546474643,
|
|
"loss": 5.6904,
|
|
"mean_token_accuracy": 0.14536458998918533,
|
|
"num_tokens": 4547502.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.744916915893555,
|
|
"epoch": 0.19416319237641452,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999361435232324,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.15529515445232392,
|
|
"num_tokens": 4560531.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.708981323242187,
|
|
"epoch": 0.1947587849910661,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999351243309069,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.14250724613666535,
|
|
"num_tokens": 4573678.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.693622684478759,
|
|
"epoch": 0.1953543776057177,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999340970705241,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.15324094593524934,
|
|
"num_tokens": 4586313.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.660975122451783,
|
|
"epoch": 0.19594997022036928,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999330617421209,
|
|
"loss": 5.6654,
|
|
"mean_token_accuracy": 0.1470079317688942,
|
|
"num_tokens": 4600030.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.744958543777466,
|
|
"epoch": 0.19654556283502084,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999320183457346,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.14200517982244493,
|
|
"num_tokens": 4613289.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.7531548023223875,
|
|
"epoch": 0.19714115544967242,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999309668814024,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.14955921322107316,
|
|
"num_tokens": 4626642.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.802632856369018,
|
|
"epoch": 0.197736748064324,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999299073491623,
|
|
"loss": 5.7113,
|
|
"mean_token_accuracy": 0.14076168164610864,
|
|
"num_tokens": 4639750.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.688930177688599,
|
|
"epoch": 0.1983323406789756,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999288397490519,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.14825851768255233,
|
|
"num_tokens": 4656894.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.615651369094849,
|
|
"epoch": 0.19892793329362715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999277640811099,
|
|
"loss": 5.5645,
|
|
"mean_token_accuracy": 0.152063050866127,
|
|
"num_tokens": 4670229.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.749063539505005,
|
|
"epoch": 0.19952352590827874,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999266803453747,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.14660252779722213,
|
|
"num_tokens": 4683754.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.666091346740723,
|
|
"epoch": 0.20011911852293032,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999255885418852,
|
|
"loss": 5.6395,
|
|
"mean_token_accuracy": 0.144394089281559,
|
|
"num_tokens": 4697824.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.853172492980957,
|
|
"epoch": 0.20071471113758188,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999244886706804,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.14478822872042657,
|
|
"num_tokens": 4711004.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.6760022163391115,
|
|
"epoch": 0.20131030375223347,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999233807318001,
|
|
"loss": 5.5994,
|
|
"mean_token_accuracy": 0.14986197873950005,
|
|
"num_tokens": 4724992.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.757878923416138,
|
|
"epoch": 0.20190589636688505,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999222647252837,
|
|
"loss": 5.7139,
|
|
"mean_token_accuracy": 0.14750109761953353,
|
|
"num_tokens": 4737770.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.7295561790466305,
|
|
"epoch": 0.20250148898153664,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999211406511714,
|
|
"loss": 5.6061,
|
|
"mean_token_accuracy": 0.1532321348786354,
|
|
"num_tokens": 4753807.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.556725978851318,
|
|
"epoch": 0.2030970815961882,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999200085095035,
|
|
"loss": 5.563,
|
|
"mean_token_accuracy": 0.14614253863692284,
|
|
"num_tokens": 4766294.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.663970327377319,
|
|
"epoch": 0.20369267421083978,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999188683003207,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.15323146283626557,
|
|
"num_tokens": 4780143.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.713444089889526,
|
|
"epoch": 0.20428826682549137,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999177200236635,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.1427561655640602,
|
|
"num_tokens": 4793717.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.814268589019775,
|
|
"epoch": 0.20488385944014295,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999165636795736,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.14456237405538558,
|
|
"num_tokens": 4808925.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.629719400405884,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999153992680923,
|
|
"loss": 5.6177,
|
|
"mean_token_accuracy": 0.14926180988550186,
|
|
"num_tokens": 4821439.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.744844388961792,
|
|
"epoch": 0.2060750446694461,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999142267892612,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.1535386934876442,
|
|
"num_tokens": 4835511.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.562971830368042,
|
|
"epoch": 0.20667063728409768,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999130462431224,
|
|
"loss": 5.5572,
|
|
"mean_token_accuracy": 0.15393677055835725,
|
|
"num_tokens": 4849500.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.670279788970947,
|
|
"epoch": 0.20726622989874927,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999118576297185,
|
|
"loss": 5.6481,
|
|
"mean_token_accuracy": 0.15215967297554017,
|
|
"num_tokens": 4863372.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.80070424079895,
|
|
"epoch": 0.20786182251340082,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999106609490918,
|
|
"loss": 5.7004,
|
|
"mean_token_accuracy": 0.14259007200598717,
|
|
"num_tokens": 4876643.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.767299032211303,
|
|
"epoch": 0.2084574151280524,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999094562012855,
|
|
"loss": 5.6586,
|
|
"mean_token_accuracy": 0.14787682592868806,
|
|
"num_tokens": 4890274.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.554810047149658,
|
|
"epoch": 0.209053007742704,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999082433863426,
|
|
"loss": 5.4929,
|
|
"mean_token_accuracy": 0.15669869333505632,
|
|
"num_tokens": 4905643.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.660882949829102,
|
|
"epoch": 0.20964860035735558,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999070225043068,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.1471147671341896,
|
|
"num_tokens": 4920106.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.697982835769653,
|
|
"epoch": 0.21024419297200714,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999057935552217,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.14976467937231064,
|
|
"num_tokens": 4934498.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.660724258422851,
|
|
"epoch": 0.21083978558665872,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999045565391313,
|
|
"loss": 5.6604,
|
|
"mean_token_accuracy": 0.1444019690155983,
|
|
"num_tokens": 4947562.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.722606897354126,
|
|
"epoch": 0.2114353782013103,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999033114560803,
|
|
"loss": 5.6536,
|
|
"mean_token_accuracy": 0.14802739769220352,
|
|
"num_tokens": 4962375.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.713058757781982,
|
|
"epoch": 0.2120309708159619,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999020583061132,
|
|
"loss": 5.6863,
|
|
"mean_token_accuracy": 0.14991741329431535,
|
|
"num_tokens": 4975683.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.710582971572876,
|
|
"epoch": 0.21262656343061345,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999007970892749,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.1476786330342293,
|
|
"num_tokens": 4989662.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.725884580612183,
|
|
"epoch": 0.21322215604526504,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998995278056107,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.15325377508997917,
|
|
"num_tokens": 5003778.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.678715658187866,
|
|
"epoch": 0.21381774865991662,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998982504551661,
|
|
"loss": 5.6612,
|
|
"mean_token_accuracy": 0.1461940385401249,
|
|
"num_tokens": 5016556.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.655481481552124,
|
|
"epoch": 0.2144133412745682,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998969650379869,
|
|
"loss": 5.5428,
|
|
"mean_token_accuracy": 0.1571403995156288,
|
|
"num_tokens": 5029732.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.592453908920288,
|
|
"epoch": 0.21500893388921977,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998956715541192,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.1576982893049717,
|
|
"num_tokens": 5042123.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.637670278549194,
|
|
"epoch": 0.21560452650387135,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998943700036095,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.15231473967432976,
|
|
"num_tokens": 5055537.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.631247663497925,
|
|
"epoch": 0.21620011911852294,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998930603865042,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.15170310884714128,
|
|
"num_tokens": 5068795.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.7385759353637695,
|
|
"epoch": 0.2167957117331745,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998917427028507,
|
|
"loss": 5.6262,
|
|
"mean_token_accuracy": 0.14561639875173568,
|
|
"num_tokens": 5083149.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.605957984924316,
|
|
"epoch": 0.21739130434782608,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998904169526959,
|
|
"loss": 5.5561,
|
|
"mean_token_accuracy": 0.15438568145036696,
|
|
"num_tokens": 5096879.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.694739484786988,
|
|
"epoch": 0.21798689696247767,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998890831360876,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.1545515924692154,
|
|
"num_tokens": 5110692.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.612382650375366,
|
|
"epoch": 0.21858248957712925,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998877412530735,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.14909972250461578,
|
|
"num_tokens": 5125981.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.68169059753418,
|
|
"epoch": 0.2191780821917808,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998863913037017,
|
|
"loss": 5.5773,
|
|
"mean_token_accuracy": 0.15180341750383378,
|
|
"num_tokens": 5138755.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.721497344970703,
|
|
"epoch": 0.2197736748064324,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998850332880208,
|
|
"loss": 5.7464,
|
|
"mean_token_accuracy": 0.13585808202624322,
|
|
"num_tokens": 5154208.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.7908600807189945,
|
|
"epoch": 0.22036926742108398,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998836672060795,
|
|
"loss": 5.776,
|
|
"mean_token_accuracy": 0.14516220688819886,
|
|
"num_tokens": 5169633.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.628995180130005,
|
|
"epoch": 0.22096486003573557,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998822930579264,
|
|
"loss": 5.6522,
|
|
"mean_token_accuracy": 0.1412796288728714,
|
|
"num_tokens": 5186213.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.762254667282105,
|
|
"epoch": 0.22156045265038712,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998809108436112,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.15179598480463027,
|
|
"num_tokens": 5201171.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.602789258956909,
|
|
"epoch": 0.2221560452650387,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998795205631834,
|
|
"loss": 5.5958,
|
|
"mean_token_accuracy": 0.1582248568534851,
|
|
"num_tokens": 5216669.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.812329053878784,
|
|
"epoch": 0.2227516378796903,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998781222166929,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.14661820232868195,
|
|
"num_tokens": 5229774.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.69528169631958,
|
|
"epoch": 0.22334723049434188,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998767158041897,
|
|
"loss": 5.676,
|
|
"mean_token_accuracy": 0.14594807475805283,
|
|
"num_tokens": 5241862.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.672992753982544,
|
|
"epoch": 0.22394282310899344,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998753013257242,
|
|
"loss": 5.6004,
|
|
"mean_token_accuracy": 0.15651677101850509,
|
|
"num_tokens": 5255768.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.678339672088623,
|
|
"epoch": 0.22453841572364502,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998738787813475,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.15575681626796722,
|
|
"num_tokens": 5268472.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.616141653060913,
|
|
"epoch": 0.2251340083382966,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998724481711103,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.15830223262310028,
|
|
"num_tokens": 5284309.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.667019271850586,
|
|
"epoch": 0.2257296009529482,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499871009495064,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.14107155799865723,
|
|
"num_tokens": 5298559.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.62891321182251,
|
|
"epoch": 0.22632519356759975,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998695627532601,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.15495284125208855,
|
|
"num_tokens": 5312024.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.598840045928955,
|
|
"epoch": 0.22692078618225134,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998681079457507,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.14768995717167854,
|
|
"num_tokens": 5326848.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.579456901550293,
|
|
"epoch": 0.22751637879690292,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499866645072588,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.1525164946913719,
|
|
"num_tokens": 5341382.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.719262027740479,
|
|
"epoch": 0.2281119714115545,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998651741338242,
|
|
"loss": 5.7094,
|
|
"mean_token_accuracy": 0.1537460394203663,
|
|
"num_tokens": 5355477.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.615902900695801,
|
|
"epoch": 0.22870756402620607,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998636951295122,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.146601539850235,
|
|
"num_tokens": 5369271.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.675575494766235,
|
|
"epoch": 0.22930315664085765,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998622080597052,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.14624156355857848,
|
|
"num_tokens": 5385016.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.570502996444702,
|
|
"epoch": 0.22989874925550924,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998607129244563,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.15071004033088684,
|
|
"num_tokens": 5398838.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.631121397018433,
|
|
"epoch": 0.23049434187016082,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998592097238192,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.15902339667081833,
|
|
"num_tokens": 5413297.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.713748598098755,
|
|
"epoch": 0.23108993448481238,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998576984578479,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.14549344182014465,
|
|
"num_tokens": 5428013.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.671467876434326,
|
|
"epoch": 0.23168552709946397,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998561791265966,
|
|
"loss": 5.6269,
|
|
"mean_token_accuracy": 0.1540614977478981,
|
|
"num_tokens": 5442252.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.716458415985107,
|
|
"epoch": 0.23228111971411555,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998546517301196,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.15530451983213425,
|
|
"num_tokens": 5455919.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.5860871315002445,
|
|
"epoch": 0.2328767123287671,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499853116268472,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.15352986454963685,
|
|
"num_tokens": 5469615.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.607357501983643,
|
|
"epoch": 0.2334723049434187,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998515727417086,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.1546195924282074,
|
|
"num_tokens": 5483955.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.677700614929199,
|
|
"epoch": 0.23406789755807028,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998500211498848,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.14768026620149613,
|
|
"num_tokens": 5498304.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.601519441604614,
|
|
"epoch": 0.23466349017272187,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998484614930566,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.1533688098192215,
|
|
"num_tokens": 5512674.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.655286693572998,
|
|
"epoch": 0.23525908278737342,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998468937712794,
|
|
"loss": 5.6157,
|
|
"mean_token_accuracy": 0.14667619466781617,
|
|
"num_tokens": 5527553.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.5839423656463625,
|
|
"epoch": 0.235854675402025,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998453179846098,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.16222523152828217,
|
|
"num_tokens": 5539818.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.567504596710205,
|
|
"epoch": 0.2364502680166766,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998437341331043,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.15266029834747313,
|
|
"num_tokens": 5554619.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.621807622909546,
|
|
"epoch": 0.23704586063132818,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998421422168195,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.1577894791960716,
|
|
"num_tokens": 5568539.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.57590274810791,
|
|
"epoch": 0.23764145324597974,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998405422358126,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.1569964498281479,
|
|
"num_tokens": 5581476.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.515435028076172,
|
|
"epoch": 0.23823704586063132,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998389341901411,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.15987358763813972,
|
|
"num_tokens": 5593774.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.681409120559692,
|
|
"epoch": 0.2388326384752829,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998373180798626,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.14954582899808883,
|
|
"num_tokens": 5606425.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.698127126693725,
|
|
"epoch": 0.2394282310899345,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998356939050351,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.1490649998188019,
|
|
"num_tokens": 5620472.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.511173677444458,
|
|
"epoch": 0.24002382370458605,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998340616657168,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.15103939771652222,
|
|
"num_tokens": 5634744.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.656479930877685,
|
|
"epoch": 0.24061941631923764,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998324213619661,
|
|
"loss": 5.4934,
|
|
"mean_token_accuracy": 0.15743449032306672,
|
|
"num_tokens": 5648555.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.4267346382141115,
|
|
"epoch": 0.24121500893388922,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998307729938423,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.16206952780485154,
|
|
"num_tokens": 5661780.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.623158979415893,
|
|
"epoch": 0.2418106015485408,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499829116561404,
|
|
"loss": 5.6234,
|
|
"mean_token_accuracy": 0.1468779467046261,
|
|
"num_tokens": 5674713.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.690124034881592,
|
|
"epoch": 0.24240619416319237,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998274520647109,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.16054057329893112,
|
|
"num_tokens": 5689152.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.583641386032104,
|
|
"epoch": 0.24300178677784395,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998257795038227,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.15361087173223495,
|
|
"num_tokens": 5704097.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.633381462097168,
|
|
"epoch": 0.24359737939249554,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998240988787992,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.15389581471681596,
|
|
"num_tokens": 5716579.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.611303758621216,
|
|
"epoch": 0.24419297200714712,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998224101897009,
|
|
"loss": 5.5643,
|
|
"mean_token_accuracy": 0.15748964250087738,
|
|
"num_tokens": 5731114.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.692147159576416,
|
|
"epoch": 0.24478856462179868,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998207134365883,
|
|
"loss": 5.5761,
|
|
"mean_token_accuracy": 0.1496018260717392,
|
|
"num_tokens": 5744843.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.611758852005005,
|
|
"epoch": 0.24538415723645027,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998190086195223,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.14455359131097795,
|
|
"num_tokens": 5759277.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.64444932937622,
|
|
"epoch": 0.24597974985110185,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998172957385638,
|
|
"loss": 5.6263,
|
|
"mean_token_accuracy": 0.14574807211756707,
|
|
"num_tokens": 5774754.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.661249732971191,
|
|
"epoch": 0.2465753424657534,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998155747937746,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.15210289657115936,
|
|
"num_tokens": 5788524.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.56767463684082,
|
|
"epoch": 0.247170935080405,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998138457852162,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.159522745013237,
|
|
"num_tokens": 5800617.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.54328031539917,
|
|
"epoch": 0.24776652769505658,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998121087129507,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.1630222752690315,
|
|
"num_tokens": 5812433.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.623016452789306,
|
|
"epoch": 0.24836212030970817,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998103635770404,
|
|
"loss": 5.4954,
|
|
"mean_token_accuracy": 0.16417578607797623,
|
|
"num_tokens": 5825507.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.564632797241211,
|
|
"epoch": 0.24895771292435973,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998086103775478,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.15830203965306283,
|
|
"num_tokens": 5841214.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.594978523254395,
|
|
"epoch": 0.2495533055390113,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998068491145359,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.15446049422025682,
|
|
"num_tokens": 5854788.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.511869955062866,
|
|
"epoch": 0.25014889815366287,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004998050797880678,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.1616917222738266,
|
|
"num_tokens": 5870241.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.543193435668945,
|
|
"epoch": 0.25074449076831445,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998033023982071,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.15495291948318482,
|
|
"num_tokens": 5883245.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.586559152603149,
|
|
"epoch": 0.25134008338296604,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998015169450174,
|
|
"loss": 5.5046,
|
|
"mean_token_accuracy": 0.15716590434312822,
|
|
"num_tokens": 5896103.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.5384437084198,
|
|
"epoch": 0.2519356759976176,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997997234285627,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.15776269584894181,
|
|
"num_tokens": 5909633.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.598070430755615,
|
|
"epoch": 0.2525312686122692,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997979218489076,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.15916108042001725,
|
|
"num_tokens": 5924211.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.475820541381836,
|
|
"epoch": 0.2531268612269208,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997961122061164,
|
|
"loss": 5.4692,
|
|
"mean_token_accuracy": 0.15873253494501113,
|
|
"num_tokens": 5937484.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.5854846954345705,
|
|
"epoch": 0.2537224538415724,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997942945002543,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.16419692784547807,
|
|
"num_tokens": 5951224.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.536117029190064,
|
|
"epoch": 0.25431804645622397,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997924687313862,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.15814073085784913,
|
|
"num_tokens": 5964762.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.634080266952514,
|
|
"epoch": 0.2549136390708755,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004997906348995777,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.14516225978732109,
|
|
"num_tokens": 5978215.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.523203134536743,
|
|
"epoch": 0.2555092316855271,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997887930048947,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.1571016401052475,
|
|
"num_tokens": 5992951.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.6488135814666744,
|
|
"epoch": 0.25610482430017867,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997869430474033,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.15189958214759827,
|
|
"num_tokens": 6005853.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.504804563522339,
|
|
"epoch": 0.25670041691483025,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997850850271696,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.15702622681856154,
|
|
"num_tokens": 6021502.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.594699192047119,
|
|
"epoch": 0.25729600952948184,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997832189442604,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.14950817972421646,
|
|
"num_tokens": 6038098.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.6026708602905275,
|
|
"epoch": 0.2578916021441334,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997813447987426,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.15161591470241548,
|
|
"num_tokens": 6053957.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.601854991912842,
|
|
"epoch": 0.258487194758785,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997794625906834,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.15173256993293763,
|
|
"num_tokens": 6069018.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.590760087966919,
|
|
"epoch": 0.2590827873734366,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997775723201504,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.15668721497058868,
|
|
"num_tokens": 6085202.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.500996780395508,
|
|
"epoch": 0.2596783799880881,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997756739872112,
|
|
"loss": 5.54,
|
|
"mean_token_accuracy": 0.15955919474363328,
|
|
"num_tokens": 6098351.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.6388637065887455,
|
|
"epoch": 0.2602739726027397,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997737675919344,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.15923120230436325,
|
|
"num_tokens": 6111322.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.453147077560425,
|
|
"epoch": 0.2608695652173913,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997718531343877,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.15894087851047517,
|
|
"num_tokens": 6124438.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.666197633743286,
|
|
"epoch": 0.2614651578320429,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997699306146402,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.15582602024078368,
|
|
"num_tokens": 6139409.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.545898342132569,
|
|
"epoch": 0.26206075044669447,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997680000327607,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.15541320592164992,
|
|
"num_tokens": 6156678.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.611967277526856,
|
|
"epoch": 0.26265634306134605,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997660613888185,
|
|
"loss": 5.6047,
|
|
"mean_token_accuracy": 0.1504083275794983,
|
|
"num_tokens": 6171149.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.529516172409058,
|
|
"epoch": 0.26325193567599764,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997641146828831,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.16315413266420364,
|
|
"num_tokens": 6184179.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.537165927886963,
|
|
"epoch": 0.26384752829064917,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004997621599150244,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.16214351505041122,
|
|
"num_tokens": 6197564.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.6120904922485355,
|
|
"epoch": 0.26444312090530075,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997601970853124,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.1543891116976738,
|
|
"num_tokens": 6211018.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.440726089477539,
|
|
"epoch": 0.26503871351995234,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997582261938177,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.16143474131822586,
|
|
"num_tokens": 6223129.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.659415912628174,
|
|
"epoch": 0.2656343061346039,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997562472406107,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.15370842665433884,
|
|
"num_tokens": 6238236.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.5119054317474365,
|
|
"epoch": 0.2662298987492555,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997542602257626,
|
|
"loss": 5.469,
|
|
"mean_token_accuracy": 0.15984549671411513,
|
|
"num_tokens": 6251285.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.487235736846924,
|
|
"epoch": 0.2668254913639071,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997522651493447,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.15966383814811708,
|
|
"num_tokens": 6266221.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.545065307617188,
|
|
"epoch": 0.2674210839785587,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997502620114284,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.1591477006673813,
|
|
"num_tokens": 6278991.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.48484525680542,
|
|
"epoch": 0.26801667659321027,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997482508120856,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.1601554974913597,
|
|
"num_tokens": 6293095.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.494444274902344,
|
|
"epoch": 0.2686122692078618,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997462315513884,
|
|
"loss": 5.4536,
|
|
"mean_token_accuracy": 0.15989998430013658,
|
|
"num_tokens": 6306162.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.637510204315186,
|
|
"epoch": 0.2692078618225134,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004997442042294095,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.15719001591205597,
|
|
"num_tokens": 6318636.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.4183434009552,
|
|
"epoch": 0.26980345443716497,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997421688462213,
|
|
"loss": 5.4689,
|
|
"mean_token_accuracy": 0.16192460358142852,
|
|
"num_tokens": 6332815.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.4836592197418215,
|
|
"epoch": 0.27039904705181655,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997401254018969,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.16635967195034027,
|
|
"num_tokens": 6346887.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.4917974948883055,
|
|
"epoch": 0.27099463966646814,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997380738965096,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.1597378931939602,
|
|
"num_tokens": 6360688.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.598917627334595,
|
|
"epoch": 0.2715902322811197,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499736014330133,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.16202907115221024,
|
|
"num_tokens": 6376560.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.561813592910767,
|
|
"epoch": 0.2721858248957713,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997339467028409,
|
|
"loss": 5.5727,
|
|
"mean_token_accuracy": 0.15398326218128205,
|
|
"num_tokens": 6390434.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.438629102706909,
|
|
"epoch": 0.2727814175104229,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997318710147076,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.16990384459495544,
|
|
"num_tokens": 6403585.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.5534590721130375,
|
|
"epoch": 0.2733770101250744,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997297872658075,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.15509413406252862,
|
|
"num_tokens": 6414663.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.595748519897461,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997276954562152,
|
|
"loss": 5.4489,
|
|
"mean_token_accuracy": 0.15962238162755965,
|
|
"num_tokens": 6428655.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.491033840179443,
|
|
"epoch": 0.2745681953543776,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499725595586006,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.16174840778112412,
|
|
"num_tokens": 6443494.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.615800285339356,
|
|
"epoch": 0.2751637879690292,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499723487655255,
|
|
"loss": 5.4809,
|
|
"mean_token_accuracy": 0.1576072946190834,
|
|
"num_tokens": 6456078.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.525338411331177,
|
|
"epoch": 0.27575938058368077,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997213716640378,
|
|
"loss": 5.4784,
|
|
"mean_token_accuracy": 0.15406707674264908,
|
|
"num_tokens": 6469805.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.4333641052246096,
|
|
"epoch": 0.27635497319833235,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997192476124306,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.15855297595262527,
|
|
"num_tokens": 6484209.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.565700960159302,
|
|
"epoch": 0.27695056581298394,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997171155005091,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.1606983035802841,
|
|
"num_tokens": 6498471.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.542387533187866,
|
|
"epoch": 0.27754615842763547,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997149753283502,
|
|
"loss": 5.5432,
|
|
"mean_token_accuracy": 0.15546615421772003,
|
|
"num_tokens": 6513558.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.56558084487915,
|
|
"epoch": 0.27814175104228706,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997128270960304,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.15300780087709426,
|
|
"num_tokens": 6527538.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.5026407718658445,
|
|
"epoch": 0.27873734365693864,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997106708036268,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.166699580848217,
|
|
"num_tokens": 6542188.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.521106910705567,
|
|
"epoch": 0.2793329362715902,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499708506451217,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.15900327563285827,
|
|
"num_tokens": 6557774.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.5282464027404785,
|
|
"epoch": 0.2799285288862418,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997063340388783,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.16098930835723876,
|
|
"num_tokens": 6571868.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.499476432800293,
|
|
"epoch": 0.2805241215008934,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997041535666888,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.16377512663602828,
|
|
"num_tokens": 6585534.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.5892613410949705,
|
|
"epoch": 0.281119714115545,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997019650347266,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.16054147630929946,
|
|
"num_tokens": 6599855.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.4842444896698,
|
|
"epoch": 0.28171530673019657,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996997684430703,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.15642998218536378,
|
|
"num_tokens": 6615496.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.539278411865235,
|
|
"epoch": 0.2823108993448481,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996975637917986,
|
|
"loss": 5.5016,
|
|
"mean_token_accuracy": 0.16009412556886674,
|
|
"num_tokens": 6629993.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.446123552322388,
|
|
"epoch": 0.2829064919594997,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996953510809906,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.16449547559022903,
|
|
"num_tokens": 6644076.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.405404996871948,
|
|
"epoch": 0.28350208457415127,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996931303107258,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.16974804401397706,
|
|
"num_tokens": 6656924.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.442859029769897,
|
|
"epoch": 0.28409767718880286,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996909014810837,
|
|
"loss": 5.46,
|
|
"mean_token_accuracy": 0.159835547208786,
|
|
"num_tokens": 6670350.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.5534443855285645,
|
|
"epoch": 0.28469326980345444,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996886645921442,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.16855843961238862,
|
|
"num_tokens": 6683174.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.5839756488800045,
|
|
"epoch": 0.285288862418106,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996864196439877,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.16144317388534546,
|
|
"num_tokens": 6699648.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.498330307006836,
|
|
"epoch": 0.2858844550327576,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996841666366947,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.16081369370222093,
|
|
"num_tokens": 6712174.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.436912679672242,
|
|
"epoch": 0.2864800476474092,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996819055703458,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.15880908966064453,
|
|
"num_tokens": 6725376.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.37857084274292,
|
|
"epoch": 0.2870756402620607,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996796364450224,
|
|
"loss": 5.2356,
|
|
"mean_token_accuracy": 0.1749272659420967,
|
|
"num_tokens": 6738177.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.494842958450318,
|
|
"epoch": 0.2876712328767123,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996773592608057,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.16030344367027283,
|
|
"num_tokens": 6751521.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.481282758712768,
|
|
"epoch": 0.2882668254913639,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996750740177775,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.16008735746145247,
|
|
"num_tokens": 6765901.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.465423536300659,
|
|
"epoch": 0.2888624181060155,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996727807160196,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.170657017827034,
|
|
"num_tokens": 6778473.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.506843948364258,
|
|
"epoch": 0.28945801072066707,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996704793556144,
|
|
"loss": 5.544,
|
|
"mean_token_accuracy": 0.14725017696619033,
|
|
"num_tokens": 6792067.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.554066801071167,
|
|
"epoch": 0.29005360333531865,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996681699366443,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.16248080879449844,
|
|
"num_tokens": 6807534.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.428509283065796,
|
|
"epoch": 0.29064919594997024,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996658524591924,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.16184908598661424,
|
|
"num_tokens": 6821600.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.534212589263916,
|
|
"epoch": 0.2912447885646218,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996635269233415,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.1645249232649803,
|
|
"num_tokens": 6835044.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.448882293701172,
|
|
"epoch": 0.29184038117927336,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996611933291752,
|
|
"loss": 5.4921,
|
|
"mean_token_accuracy": 0.1541204959154129,
|
|
"num_tokens": 6847745.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.532335805892944,
|
|
"epoch": 0.29243597379392494,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996588516767772,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.16137346625328064,
|
|
"num_tokens": 6861403.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.388396310806274,
|
|
"epoch": 0.2930315664085765,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996565019662315,
|
|
"loss": 5.4767,
|
|
"mean_token_accuracy": 0.16086889207363128,
|
|
"num_tokens": 6874418.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.644299840927124,
|
|
"epoch": 0.2936271590232281,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996541441976223,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.1515096940100193,
|
|
"num_tokens": 6890166.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.467857789993286,
|
|
"epoch": 0.2942227516378797,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996517783710342,
|
|
"loss": 5.4593,
|
|
"mean_token_accuracy": 0.15384903848171233,
|
|
"num_tokens": 6904569.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.5155377864837645,
|
|
"epoch": 0.2948183442525313,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996494044865521,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.16120530366897584,
|
|
"num_tokens": 6918562.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.555597162246704,
|
|
"epoch": 0.29541393686718287,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996470225442611,
|
|
"loss": 5.4451,
|
|
"mean_token_accuracy": 0.15555806905031205,
|
|
"num_tokens": 6934751.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.473335218429566,
|
|
"epoch": 0.2960095294818344,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004996446325442466,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.16467892974615098,
|
|
"num_tokens": 6947669.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.589768600463867,
|
|
"epoch": 0.296605122096486,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996422344865945,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.15757396072149277,
|
|
"num_tokens": 6959993.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.434958744049072,
|
|
"epoch": 0.29720071471113757,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996398283713907,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.16603365838527678,
|
|
"num_tokens": 6974637.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.416078090667725,
|
|
"epoch": 0.29779630732578916,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996374141987215,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.17085353285074234,
|
|
"num_tokens": 6989182.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.423217391967773,
|
|
"epoch": 0.29839189994044074,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996349919686733,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.16468697041273117,
|
|
"num_tokens": 7003681.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.453787326812744,
|
|
"epoch": 0.2989874925550923,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996325616813334,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.1682152807712555,
|
|
"num_tokens": 7017919.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.497931432723999,
|
|
"epoch": 0.2995830851697439,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004996301233367886,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.1598147213459015,
|
|
"num_tokens": 7033405.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.427138757705689,
|
|
"epoch": 0.3001786777843955,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996276769351265,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.16556495130062104,
|
|
"num_tokens": 7046938.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.4695882320404055,
|
|
"epoch": 0.30077427039904703,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996252224764349,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.15967679843306543,
|
|
"num_tokens": 7059708.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.414870929718018,
|
|
"epoch": 0.3013698630136986,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996227599608018,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.1649050384759903,
|
|
"num_tokens": 7074554.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.429904413223267,
|
|
"epoch": 0.3019654556283502,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996202893883156,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.1608701840043068,
|
|
"num_tokens": 7089654.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.496702766418457,
|
|
"epoch": 0.3025610482430018,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996178107590648,
|
|
"loss": 5.4357,
|
|
"mean_token_accuracy": 0.15785154104232788,
|
|
"num_tokens": 7103137.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.372678518295288,
|
|
"epoch": 0.30315664085765337,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996153240731381,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.17022061347961426,
|
|
"num_tokens": 7114857.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.507655000686645,
|
|
"epoch": 0.30375223347230496,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996128293306251,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.15959791839122772,
|
|
"num_tokens": 7128243.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.508147478103638,
|
|
"epoch": 0.30434782608695654,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996103265316152,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.16230685710906984,
|
|
"num_tokens": 7142505.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.336689853668213,
|
|
"epoch": 0.3049434187016081,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996078156761979,
|
|
"loss": 5.3728,
|
|
"mean_token_accuracy": 0.16422040462493898,
|
|
"num_tokens": 7157877.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.505233478546143,
|
|
"epoch": 0.30553901131625966,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996052967644636,
|
|
"loss": 5.429,
|
|
"mean_token_accuracy": 0.15885090082883835,
|
|
"num_tokens": 7170819.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.447253179550171,
|
|
"epoch": 0.30613460393091124,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996027697965024,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.1655766934156418,
|
|
"num_tokens": 7183013.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.413886642456054,
|
|
"epoch": 0.3067301965455628,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499600234772405,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.1570427656173706,
|
|
"num_tokens": 7196530.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.701424169540405,
|
|
"epoch": 0.3073257891602144,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995976916922624,
|
|
"loss": 5.5099,
|
|
"mean_token_accuracy": 0.15338003933429717,
|
|
"num_tokens": 7210657.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.377353286743164,
|
|
"epoch": 0.307921381774866,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995951405561658,
|
|
"loss": 5.3486,
|
|
"mean_token_accuracy": 0.16219091266393662,
|
|
"num_tokens": 7224450.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.447744226455688,
|
|
"epoch": 0.3085169743895176,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995925813642068,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.1668688863515854,
|
|
"num_tokens": 7238767.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.5132781028747555,
|
|
"epoch": 0.30911256700416917,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995900141164768,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.164970363676548,
|
|
"num_tokens": 7253326.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.351834678649903,
|
|
"epoch": 0.3097081596188207,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004995874388130683,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.16675262302160263,
|
|
"num_tokens": 7268256.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.423310947418213,
|
|
"epoch": 0.3103037522334723,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995848554540734,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.1643177017569542,
|
|
"num_tokens": 7281561.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.496531534194946,
|
|
"epoch": 0.31089934484812387,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499582264039585,
|
|
"loss": 5.5076,
|
|
"mean_token_accuracy": 0.16121220886707305,
|
|
"num_tokens": 7294302.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.4235679626464846,
|
|
"epoch": 0.31149493746277546,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499579664569696,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.16629114300012587,
|
|
"num_tokens": 7309257.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.452440881729126,
|
|
"epoch": 0.31209053007742704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995770570444996,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.16688948273658752,
|
|
"num_tokens": 7322797.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.4272215366363525,
|
|
"epoch": 0.3126861226920786,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995744414640892,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.17104785293340682,
|
|
"num_tokens": 7336913.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.4998206615448,
|
|
"epoch": 0.3132817153067302,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995718178285587,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.16472650915384293,
|
|
"num_tokens": 7350267.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.42825026512146,
|
|
"epoch": 0.3138773079213818,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995691861380022,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.16759289056062698,
|
|
"num_tokens": 7365592.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.479157209396362,
|
|
"epoch": 0.31447290053603333,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995665463925142,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.17266064286231994,
|
|
"num_tokens": 7380045.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.442907238006592,
|
|
"epoch": 0.3150684931506849,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995638985921893,
|
|
"loss": 5.4594,
|
|
"mean_token_accuracy": 0.16305454522371293,
|
|
"num_tokens": 7392487.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.51395206451416,
|
|
"epoch": 0.3156640857653365,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995612427371224,
|
|
"loss": 5.4854,
|
|
"mean_token_accuracy": 0.15603170394897461,
|
|
"num_tokens": 7405578.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.495937919616699,
|
|
"epoch": 0.3162596783799881,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499558578827409,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.16521623879671096,
|
|
"num_tokens": 7418940.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.428271007537842,
|
|
"epoch": 0.31685527099463967,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995559068631444,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.166995607316494,
|
|
"num_tokens": 7432688.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.5285642623901365,
|
|
"epoch": 0.31745086360929126,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995532268444244,
|
|
"loss": 5.5345,
|
|
"mean_token_accuracy": 0.15511924028396606,
|
|
"num_tokens": 7446238.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.537379455566406,
|
|
"epoch": 0.31804645622394284,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004995505387713453,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.15701714158058167,
|
|
"num_tokens": 7460781.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.468899393081665,
|
|
"epoch": 0.3186420488385944,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995478426440037,
|
|
"loss": 5.5099,
|
|
"mean_token_accuracy": 0.15298325568437576,
|
|
"num_tokens": 7475041.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.542052173614502,
|
|
"epoch": 0.31923764145324596,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995451384624959,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.15271706581115724,
|
|
"num_tokens": 7491027.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.525603199005127,
|
|
"epoch": 0.31983323406789754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995424262269191,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.1601056858897209,
|
|
"num_tokens": 7503070.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.3651683807373045,
|
|
"epoch": 0.32042882668254913,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995397059373704,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.17039613723754882,
|
|
"num_tokens": 7515553.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.3878929138183596,
|
|
"epoch": 0.3210244192972007,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995369775939478,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.1641643077135086,
|
|
"num_tokens": 7529603.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.5057416439056395,
|
|
"epoch": 0.3216200119118523,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995342411967487,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.1564752236008644,
|
|
"num_tokens": 7543320.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.439134740829468,
|
|
"epoch": 0.3222156045265039,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995314967458715,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.1580772154033184,
|
|
"num_tokens": 7556413.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.475128126144409,
|
|
"epoch": 0.32281119714115547,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995287442414145,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.16409741938114167,
|
|
"num_tokens": 7570427.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.507748413085937,
|
|
"epoch": 0.323406789755807,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995259836834767,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.15937935709953308,
|
|
"num_tokens": 7585143.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.546754980087281,
|
|
"epoch": 0.3240023823704586,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995232150721568,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.16581834703683854,
|
|
"num_tokens": 7597429.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.347131824493408,
|
|
"epoch": 0.32459797498511017,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995204384075542,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.17426720559597014,
|
|
"num_tokens": 7610203.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.4376050472259525,
|
|
"epoch": 0.32519356759976176,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995176536897685,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.1575453221797943,
|
|
"num_tokens": 7625343.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.438621568679809,
|
|
"epoch": 0.32578916021441334,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995148609188997,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.16086258739233017,
|
|
"num_tokens": 7637850.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.394261074066162,
|
|
"epoch": 0.32638475282906493,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004995120600950479,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.16461118310689926,
|
|
"num_tokens": 7651877.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.514844512939453,
|
|
"epoch": 0.3269803454437165,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995092512183134,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.15847574919462204,
|
|
"num_tokens": 7666457.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.413395547866822,
|
|
"epoch": 0.3275759380583681,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995064342887972,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.16699886322021484,
|
|
"num_tokens": 7678979.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.397037076950073,
|
|
"epoch": 0.32817153067301963,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995036093066001,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.16832471638917923,
|
|
"num_tokens": 7692357.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.48453722000122,
|
|
"epoch": 0.3287671232876712,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995007762718237,
|
|
"loss": 5.4404,
|
|
"mean_token_accuracy": 0.159495110809803,
|
|
"num_tokens": 7707537.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.4237676620483395,
|
|
"epoch": 0.3293627159023228,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994979351845693,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.16477575451135634,
|
|
"num_tokens": 7719737.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.409489345550537,
|
|
"epoch": 0.3299583085169744,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994950860449392,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.16485470980405809,
|
|
"num_tokens": 7734612.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.512462997436524,
|
|
"epoch": 0.33055390113162597,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004994922288530353,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.15519903898239135,
|
|
"num_tokens": 7749109.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.343546915054321,
|
|
"epoch": 0.33114949374627756,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994893636089601,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.16800356060266494,
|
|
"num_tokens": 7761972.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.459216833114624,
|
|
"epoch": 0.33174508636092914,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994864903128164,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.15864378213882446,
|
|
"num_tokens": 7777769.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.44635796546936,
|
|
"epoch": 0.33234067897558073,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994836089647073,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.16482885777950287,
|
|
"num_tokens": 7792576.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.3996556282043455,
|
|
"epoch": 0.33293627159023226,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994807195647362,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.16411443501710893,
|
|
"num_tokens": 7805997.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.372546863555908,
|
|
"epoch": 0.33353186420488384,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994778221130066,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.161911341547966,
|
|
"num_tokens": 7819548.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.468026876449585,
|
|
"epoch": 0.33412745681953543,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994749166096226,
|
|
"loss": 5.353,
|
|
"mean_token_accuracy": 0.1635708898305893,
|
|
"num_tokens": 7832786.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.4425122261047365,
|
|
"epoch": 0.334723049434187,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994720030546882,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.16255557388067246,
|
|
"num_tokens": 7847524.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.354201459884644,
|
|
"epoch": 0.3353186420488386,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994690814483081,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.17212553173303605,
|
|
"num_tokens": 7861783.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.430348110198975,
|
|
"epoch": 0.3359142346634902,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994661517905869,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.16057730168104173,
|
|
"num_tokens": 7875671.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.401807117462158,
|
|
"epoch": 0.33650982727814177,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994632140816299,
|
|
"loss": 5.3147,
|
|
"mean_token_accuracy": 0.1645515263080597,
|
|
"num_tokens": 7890624.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.432481288909912,
|
|
"epoch": 0.33710541989279336,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994602683215424,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.15535128116607666,
|
|
"num_tokens": 7904296.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.364171028137207,
|
|
"epoch": 0.3377010125074449,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049945731451043,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.16897024661302568,
|
|
"num_tokens": 7918588.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.36690034866333,
|
|
"epoch": 0.33829660512209647,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994543526483985,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.16793306022882462,
|
|
"num_tokens": 7933087.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.38888144493103,
|
|
"epoch": 0.33889219773674806,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994513827355546,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.17012295722961426,
|
|
"num_tokens": 7945477.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.473477840423584,
|
|
"epoch": 0.33948779035139964,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994484047720043,
|
|
"loss": 5.4992,
|
|
"mean_token_accuracy": 0.15650015622377395,
|
|
"num_tokens": 7961488.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.452339458465576,
|
|
"epoch": 0.34008338296605123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994454187578547,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.17281302511692048,
|
|
"num_tokens": 7974533.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.370311307907104,
|
|
"epoch": 0.3406789755807028,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994424246932129,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.16259245872497557,
|
|
"num_tokens": 7988481.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.40788516998291,
|
|
"epoch": 0.3412745681953544,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994394225781863,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.16687000244855882,
|
|
"num_tokens": 8003589.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.3925856590271,
|
|
"epoch": 0.34187016081000593,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994364124128825,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.16481602936983109,
|
|
"num_tokens": 8017560.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.392977476119995,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004994333941974094,
|
|
"loss": 5.4092,
|
|
"mean_token_accuracy": 0.16044452488422395,
|
|
"num_tokens": 8032339.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.426511287689209,
|
|
"epoch": 0.3430613460393091,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994303679318754,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.1583537071943283,
|
|
"num_tokens": 8047634.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.493017482757568,
|
|
"epoch": 0.3436569386539607,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994273336163891,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.16036514937877655,
|
|
"num_tokens": 8061267.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.328645086288452,
|
|
"epoch": 0.34425253126861227,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994242912510591,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.16638380885124207,
|
|
"num_tokens": 8076225.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.495432662963867,
|
|
"epoch": 0.34484812388326386,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994212408359948,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.16790373772382736,
|
|
"num_tokens": 8089997.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.409817886352539,
|
|
"epoch": 0.34544371649791544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994181823713054,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.16812920272350312,
|
|
"num_tokens": 8102739.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.38054895401001,
|
|
"epoch": 0.34603930911256703,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994151158571006,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.16031926423311232,
|
|
"num_tokens": 8115435.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.48614821434021,
|
|
"epoch": 0.34663490172721856,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994120412934906,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.1668205291032791,
|
|
"num_tokens": 8129833.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.4338020324707035,
|
|
"epoch": 0.34723049434187014,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.1699073314666748,
|
|
"num_tokens": 8144316.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.376609134674072,
|
|
"epoch": 0.34782608695652173,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994058680184959,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.16706625521183013,
|
|
"num_tokens": 8158927.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.446486473083496,
|
|
"epoch": 0.3484216795711733,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994027693073327,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.16445603370666503,
|
|
"num_tokens": 8172297.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.443706798553467,
|
|
"epoch": 0.3490172721858249,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993996625472071,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.1584927871823311,
|
|
"num_tokens": 8184985.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.488152742385864,
|
|
"epoch": 0.3496128648004765,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993965477382304,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.16814447045326233,
|
|
"num_tokens": 8198936.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.358643865585327,
|
|
"epoch": 0.35020845741512807,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993934248805143,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.1625220373272896,
|
|
"num_tokens": 8213538.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.516407823562622,
|
|
"epoch": 0.35080405002977966,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993902939741709,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.15863357335329056,
|
|
"num_tokens": 8226794.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.369873523712158,
|
|
"epoch": 0.3513996426444312,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993871550193126,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.16571945548057557,
|
|
"num_tokens": 8241671.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.374324989318848,
|
|
"epoch": 0.3519952352590828,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993840080160519,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.17032549977302552,
|
|
"num_tokens": 8255079.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.433959293365478,
|
|
"epoch": 0.35259082787373436,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993808529645016,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.16986847370862962,
|
|
"num_tokens": 8267958.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.416842651367188,
|
|
"epoch": 0.35318642048838594,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993776898647749,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.1560832977294922,
|
|
"num_tokens": 8281082.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.422732591629028,
|
|
"epoch": 0.35378201310303753,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993745187169852,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.16604986935853958,
|
|
"num_tokens": 8292675.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.35556435585022,
|
|
"epoch": 0.3543776057176891,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993713395212464,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.17108903378248214,
|
|
"num_tokens": 8304481.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.416813850402832,
|
|
"epoch": 0.3549731983323407,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993681522776725,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.16116093695163727,
|
|
"num_tokens": 8318529.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.424474716186523,
|
|
"epoch": 0.35556879094699223,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004993649569863778,
|
|
"loss": 5.398,
|
|
"mean_token_accuracy": 0.16214808076620102,
|
|
"num_tokens": 8333181.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.36681227684021,
|
|
"epoch": 0.3561643835616438,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993617536474768,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.18034850507974626,
|
|
"num_tokens": 8346036.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.346827793121338,
|
|
"epoch": 0.3567599761762954,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004993585422610845,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.1635763615369797,
|
|
"num_tokens": 8361037.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.457519102096557,
|
|
"epoch": 0.357355568790947,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993553228273161,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.1655959889292717,
|
|
"num_tokens": 8374802.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.357355568790947,
|
|
"eval_entropy": 5.211937710633472,
|
|
"eval_loss": 5.32589864730835,
|
|
"eval_mean_token_accuracy": 0.17636413536089995,
|
|
"eval_num_tokens": 8374802.0,
|
|
"eval_runtime": 24.6391,
|
|
"eval_samples_per_second": 1035.468,
|
|
"eval_steps_per_second": 129.469,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 83940,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.4989188888576e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|