4084acfd66
Model: fpadovani/urd-arab-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 Source: Original Platform
60145 lines
1.6 MiB
60145 lines
1.6 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.5735556879094696,
|
|
"eval_steps": 3000,
|
|
"global_step": 30000,
|
|
"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
|
|
},
|
|
{
|
|
"entropy": 5.317358779907226,
|
|
"epoch": 0.3579511614055986,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499352095346287,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.1787054032087326,
|
|
"num_tokens": 8389127.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.484448337554932,
|
|
"epoch": 0.35854675402025016,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993488598181131,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.15273169055581093,
|
|
"num_tokens": 8403358.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.416276311874389,
|
|
"epoch": 0.35914234663490174,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993456162429103,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.16509442329406737,
|
|
"num_tokens": 8418693.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.39211597442627,
|
|
"epoch": 0.35973793924955333,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004993423646207951,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.1723127394914627,
|
|
"num_tokens": 8429968.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.380735063552857,
|
|
"epoch": 0.36033353186420486,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499339104951884,
|
|
"loss": 5.332,
|
|
"mean_token_accuracy": 0.16865921765565872,
|
|
"num_tokens": 8443700.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.414226865768432,
|
|
"epoch": 0.36092912447885644,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993358372362939,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.16608230620622635,
|
|
"num_tokens": 8457919.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.4140712261199955,
|
|
"epoch": 0.36152471709350803,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004993325614741421,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.1614885464310646,
|
|
"num_tokens": 8472787.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.380614471435547,
|
|
"epoch": 0.3621203097081596,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993292776655461,
|
|
"loss": 5.3482,
|
|
"mean_token_accuracy": 0.17318668812513352,
|
|
"num_tokens": 8484235.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.322636413574219,
|
|
"epoch": 0.3627159023228112,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993259858106236,
|
|
"loss": 5.2608,
|
|
"mean_token_accuracy": 0.1752901032567024,
|
|
"num_tokens": 8496971.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.380193662643433,
|
|
"epoch": 0.3633114949374628,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993226859094927,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.17305238097906112,
|
|
"num_tokens": 8510531.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.383162212371826,
|
|
"epoch": 0.36390708755211437,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993193779622719,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.16861678510904313,
|
|
"num_tokens": 8522492.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.443447923660278,
|
|
"epoch": 0.36450268016676596,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004993160619690796,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.16582634449005126,
|
|
"num_tokens": 8537119.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.280929613113403,
|
|
"epoch": 0.3650982727814175,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993127379300349,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.16823295950889589,
|
|
"num_tokens": 8549899.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.455180931091308,
|
|
"epoch": 0.3656938653960691,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499309405845257,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.1582242727279663,
|
|
"num_tokens": 8563604.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.4586444854736325,
|
|
"epoch": 0.36628945801072066,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993060657148654,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.16324716657400132,
|
|
"num_tokens": 8577948.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.38478274345398,
|
|
"epoch": 0.36688505062537224,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00049930271753898,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.17629851698875426,
|
|
"num_tokens": 8591750.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.4728888988494875,
|
|
"epoch": 0.36748064324002383,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992993613177208,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.16979584097862244,
|
|
"num_tokens": 8604091.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.251353311538696,
|
|
"epoch": 0.3680762358546754,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992959970512082,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.17604580670595169,
|
|
"num_tokens": 8617314.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.290686893463135,
|
|
"epoch": 0.368671828469327,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992926247395627,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.17441726475954056,
|
|
"num_tokens": 8630050.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.295737886428833,
|
|
"epoch": 0.36926742108397853,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004992892443829057,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.17215442955493926,
|
|
"num_tokens": 8643462.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.359369087219238,
|
|
"epoch": 0.3698630136986301,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499285855981358,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.17045309245586396,
|
|
"num_tokens": 8657207.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.350285482406616,
|
|
"epoch": 0.3704586063132817,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992824595350414,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.1720702603459358,
|
|
"num_tokens": 8671129.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.424204397201538,
|
|
"epoch": 0.3710541989279333,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992790550440775,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.1713881641626358,
|
|
"num_tokens": 8684308.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.2932538986206055,
|
|
"epoch": 0.3716497915425849,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992756425085887,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.17133163064718246,
|
|
"num_tokens": 8697651.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.372791862487793,
|
|
"epoch": 0.37224538415723646,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004992722219286972,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.16233277171850205,
|
|
"num_tokens": 8714559.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.424596929550171,
|
|
"epoch": 0.37284097677188804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992687933045258,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.1686181589961052,
|
|
"num_tokens": 8729999.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.315368366241455,
|
|
"epoch": 0.37343656938653963,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992653566361974,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.16937260329723358,
|
|
"num_tokens": 8742503.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.413096237182617,
|
|
"epoch": 0.37403216200119116,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992619119238351,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.16781239956617355,
|
|
"num_tokens": 8755034.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.378695058822632,
|
|
"epoch": 0.37462775461584275,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499258459167563,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.16792970150709152,
|
|
"num_tokens": 8770410.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.3465495109558105,
|
|
"epoch": 0.37522334723049433,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992549983675043,
|
|
"loss": 5.2871,
|
|
"mean_token_accuracy": 0.17326726615428925,
|
|
"num_tokens": 8784020.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.320108366012573,
|
|
"epoch": 0.3758189398451459,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992515295237835,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.16584887504577636,
|
|
"num_tokens": 8797763.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.368948888778687,
|
|
"epoch": 0.3764145324597975,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499248052636525,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.17275409698486327,
|
|
"num_tokens": 8810306.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.259959125518799,
|
|
"epoch": 0.3770101250744491,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992445677058534,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.17758919894695283,
|
|
"num_tokens": 8822345.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.392199373245239,
|
|
"epoch": 0.3776057176891007,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992410747318938,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.17028617560863496,
|
|
"num_tokens": 8836024.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.414326763153076,
|
|
"epoch": 0.37820131030375226,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992375737147715,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.16182660758495332,
|
|
"num_tokens": 8849994.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.320485544204712,
|
|
"epoch": 0.3787969029184038,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004992340646546118,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.17230262756347656,
|
|
"num_tokens": 8863867.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.324657011032104,
|
|
"epoch": 0.3793924955330554,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499230547551541,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.1698233053088188,
|
|
"num_tokens": 8878077.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.405715084075927,
|
|
"epoch": 0.37998808814770696,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992270224056849,
|
|
"loss": 5.3186,
|
|
"mean_token_accuracy": 0.16629047840833663,
|
|
"num_tokens": 8892729.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.32261905670166,
|
|
"epoch": 0.38058368076235854,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992234892171702,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.17428217679262162,
|
|
"num_tokens": 8906242.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.33727536201477,
|
|
"epoch": 0.38117927337701013,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992199479861235,
|
|
"loss": 5.354,
|
|
"mean_token_accuracy": 0.16397698372602462,
|
|
"num_tokens": 8919814.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.340610408782959,
|
|
"epoch": 0.3817748659916617,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004992163987126717,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.173421473801136,
|
|
"num_tokens": 8934345.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.277923059463501,
|
|
"epoch": 0.3823704586063133,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992128413969423,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.17873043566942215,
|
|
"num_tokens": 8947825.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.466353559494019,
|
|
"epoch": 0.3829660512209649,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992092760390628,
|
|
"loss": 5.4196,
|
|
"mean_token_accuracy": 0.16915350630879403,
|
|
"num_tokens": 8962270.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.381490993499756,
|
|
"epoch": 0.3835616438356164,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004992057026391612,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.17274802327156066,
|
|
"num_tokens": 8974453.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.378891563415527,
|
|
"epoch": 0.384157236450268,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004992021211973655,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.16626788675785065,
|
|
"num_tokens": 8991689.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.374792242050171,
|
|
"epoch": 0.3847528290649196,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991985317138043,
|
|
"loss": 5.3371,
|
|
"mean_token_accuracy": 0.17625548541545868,
|
|
"num_tokens": 9005783.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.382846307754517,
|
|
"epoch": 0.3853484216795712,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991949341886063,
|
|
"loss": 5.303,
|
|
"mean_token_accuracy": 0.16657574474811554,
|
|
"num_tokens": 9019733.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.325779628753662,
|
|
"epoch": 0.38594401429422276,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004991913286219004,
|
|
"loss": 5.2834,
|
|
"mean_token_accuracy": 0.17000704407691955,
|
|
"num_tokens": 9035131.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.371550798416138,
|
|
"epoch": 0.38653960690887434,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991877150138162,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.17297192811965942,
|
|
"num_tokens": 9047954.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.33264479637146,
|
|
"epoch": 0.38713519952352593,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991840933644831,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.1738293409347534,
|
|
"num_tokens": 9059945.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.385032510757446,
|
|
"epoch": 0.38773079213817746,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499180463674031,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.17210409492254258,
|
|
"num_tokens": 9074128.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.308764696121216,
|
|
"epoch": 0.38832638475282905,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991768259425903,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.16413030922412872,
|
|
"num_tokens": 9086760.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.455681467056275,
|
|
"epoch": 0.38892197736748063,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004991731801702914,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.16147148609161377,
|
|
"num_tokens": 9100632.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.344516277313232,
|
|
"epoch": 0.3895175699821322,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991695263572648,
|
|
"loss": 5.4225,
|
|
"mean_token_accuracy": 0.1624326542019844,
|
|
"num_tokens": 9115092.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.335514211654663,
|
|
"epoch": 0.3901131625967838,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991658645036419,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.1770961433649063,
|
|
"num_tokens": 9127473.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.374756765365601,
|
|
"epoch": 0.3907087552114354,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991621946095539,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.1700092598795891,
|
|
"num_tokens": 9141028.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.330485534667969,
|
|
"epoch": 0.391304347826087,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991585166751325,
|
|
"loss": 5.2627,
|
|
"mean_token_accuracy": 0.17225174009799957,
|
|
"num_tokens": 9154526.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.3875657081604,
|
|
"epoch": 0.39189994044073856,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991548307005094,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.16934126019477844,
|
|
"num_tokens": 9167220.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.396041679382324,
|
|
"epoch": 0.3924955330553901,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991511366858172,
|
|
"loss": 5.4114,
|
|
"mean_token_accuracy": 0.16995712965726853,
|
|
"num_tokens": 9181648.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.349484205245972,
|
|
"epoch": 0.3930911256700417,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991474346311879,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.1783977657556534,
|
|
"num_tokens": 9194714.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.205827331542968,
|
|
"epoch": 0.39368671828469326,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991437245367547,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.17131887674331664,
|
|
"num_tokens": 9211467.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.550635957717896,
|
|
"epoch": 0.39428231089934485,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991400064026506,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.154654623568058,
|
|
"num_tokens": 9226409.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.286458158493042,
|
|
"epoch": 0.39487790351399643,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991362802290089,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.1652798593044281,
|
|
"num_tokens": 9240476.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.2871228694915775,
|
|
"epoch": 0.395473496128648,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004991325460159631,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.1688476249575615,
|
|
"num_tokens": 9254020.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.341579294204712,
|
|
"epoch": 0.3960690887432996,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991288037636474,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.17881344705820085,
|
|
"num_tokens": 9269150.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.41578483581543,
|
|
"epoch": 0.3966646813579512,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991250534721959,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.15788045525550842,
|
|
"num_tokens": 9285184.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.412091588973999,
|
|
"epoch": 0.3972602739726027,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991212951417431,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.17704390436410905,
|
|
"num_tokens": 9298622.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.370463609695435,
|
|
"epoch": 0.3978558665872543,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991175287724239,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.16377182006835939,
|
|
"num_tokens": 9314653.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.34685697555542,
|
|
"epoch": 0.3984514592019059,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991137543643733,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.1735073909163475,
|
|
"num_tokens": 9328428.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.406731271743775,
|
|
"epoch": 0.3990470518165575,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004991099719177268,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.16612121909856797,
|
|
"num_tokens": 9341250.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.351215362548828,
|
|
"epoch": 0.39964264443120906,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991061814326198,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.17343611568212508,
|
|
"num_tokens": 9355706.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.482937335968018,
|
|
"epoch": 0.40023823704586065,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991023829091887,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.16030003428459166,
|
|
"num_tokens": 9368562.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.403771448135376,
|
|
"epoch": 0.40083382966051223,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990985763475694,
|
|
"loss": 5.3412,
|
|
"mean_token_accuracy": 0.16436890214681626,
|
|
"num_tokens": 9383484.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.226717376708985,
|
|
"epoch": 0.40142942227516376,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990947617478984,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.17794403731822966,
|
|
"num_tokens": 9397364.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.243013048171997,
|
|
"epoch": 0.40202501488981535,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990909391103127,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.1719819650053978,
|
|
"num_tokens": 9411738.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.311656188964844,
|
|
"epoch": 0.40262060750446693,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990871084349494,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.1762864649295807,
|
|
"num_tokens": 9426660.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.357159185409546,
|
|
"epoch": 0.4032162001191185,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990832697219459,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.16538622826337815,
|
|
"num_tokens": 9440878.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.363180303573609,
|
|
"epoch": 0.4038117927337701,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990794229714398,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.16661185026168823,
|
|
"num_tokens": 9455174.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.347669696807861,
|
|
"epoch": 0.4044073853484217,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990755681835693,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.17822938561439514,
|
|
"num_tokens": 9467936.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.2902974605560305,
|
|
"epoch": 0.4050029779630733,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990717053584723,
|
|
"loss": 5.3251,
|
|
"mean_token_accuracy": 0.16453895419836045,
|
|
"num_tokens": 9482529.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.369814872741699,
|
|
"epoch": 0.40559857057772486,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990678344962876,
|
|
"loss": 5.3504,
|
|
"mean_token_accuracy": 0.17185690253973007,
|
|
"num_tokens": 9497141.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.4025795459747314,
|
|
"epoch": 0.4061941631923764,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990639555971539,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.165517657995224,
|
|
"num_tokens": 9509878.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.266278839111328,
|
|
"epoch": 0.406789755807028,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990600686612106,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.17320700585842133,
|
|
"num_tokens": 9522720.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.36631760597229,
|
|
"epoch": 0.40738534842167956,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990561736885968,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.1721126601099968,
|
|
"num_tokens": 9536418.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.353341817855835,
|
|
"epoch": 0.40798094103633115,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990522706794523,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.17489612549543382,
|
|
"num_tokens": 9552336.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.307628965377807,
|
|
"epoch": 0.40857653365098273,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990483596339174,
|
|
"loss": 5.2442,
|
|
"mean_token_accuracy": 0.17427762150764464,
|
|
"num_tokens": 9565676.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.215011835098267,
|
|
"epoch": 0.4091721262656343,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990444405521318,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.18366799354553223,
|
|
"num_tokens": 9579361.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.263802862167358,
|
|
"epoch": 0.4097677188802859,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990405134342366,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.1768967628479004,
|
|
"num_tokens": 9591779.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.33215651512146,
|
|
"epoch": 0.4103633114949375,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990365782803724,
|
|
"loss": 5.2774,
|
|
"mean_token_accuracy": 0.16902955919504165,
|
|
"num_tokens": 9608353.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.2639445781707765,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990326350906803,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.17052658051252365,
|
|
"num_tokens": 9623236.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.3393572807312015,
|
|
"epoch": 0.4115544967242406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990286838653019,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.16557589620351792,
|
|
"num_tokens": 9635746.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.251279640197754,
|
|
"epoch": 0.4121500893388922,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990247246043789,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.1741189643740654,
|
|
"num_tokens": 9650458.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.333756732940674,
|
|
"epoch": 0.4127456819535438,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990207573080533,
|
|
"loss": 5.3056,
|
|
"mean_token_accuracy": 0.17288769781589508,
|
|
"num_tokens": 9665486.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.3913905143737795,
|
|
"epoch": 0.41334127456819536,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990167819764672,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.16703656315803528,
|
|
"num_tokens": 9679977.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.39796290397644,
|
|
"epoch": 0.41393686718284695,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990127986097636,
|
|
"loss": 5.342,
|
|
"mean_token_accuracy": 0.16605288833379744,
|
|
"num_tokens": 9695092.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.19821310043335,
|
|
"epoch": 0.41453245979749853,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499008807208085,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.17773980945348739,
|
|
"num_tokens": 9707836.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.420686674118042,
|
|
"epoch": 0.4151280524121501,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990048077715746,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.16310545653104783,
|
|
"num_tokens": 9721936.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.2826074123382565,
|
|
"epoch": 0.41572364502680165,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990008003003762,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.1797080844640732,
|
|
"num_tokens": 9734876.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.287394666671753,
|
|
"epoch": 0.41631923764145323,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989967847946331,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.16180697083473206,
|
|
"num_tokens": 9748870.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.507581806182861,
|
|
"epoch": 0.4169148302561048,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004989927612544895,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.1704806625843048,
|
|
"num_tokens": 9763605.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.36821026802063,
|
|
"epoch": 0.4175104228707564,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989887296800899,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.1703335389494896,
|
|
"num_tokens": 9779312.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.2759678840637205,
|
|
"epoch": 0.418106015485408,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989846900715786,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.16032240390777588,
|
|
"num_tokens": 9791770.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.344533920288086,
|
|
"epoch": 0.4187016081000596,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989806424291008,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.16780513226985933,
|
|
"num_tokens": 9807341.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.284126853942871,
|
|
"epoch": 0.41929720071471116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989765867528014,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.17260883152484893,
|
|
"num_tokens": 9821829.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.236743068695068,
|
|
"epoch": 0.4198927933293627,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989725230428262,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.17957783490419388,
|
|
"num_tokens": 9836554.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.328051662445068,
|
|
"epoch": 0.4204883859440143,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989684512993205,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.17180219888687134,
|
|
"num_tokens": 9849904.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.333499240875244,
|
|
"epoch": 0.42108397855866586,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989643715224307,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.17358710765838622,
|
|
"num_tokens": 9863935.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.321998596191406,
|
|
"epoch": 0.42167957117331745,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989602837123031,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.17418841272592545,
|
|
"num_tokens": 9878230.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.29806170463562,
|
|
"epoch": 0.42227516378796903,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989561878690842,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.18030119091272354,
|
|
"num_tokens": 9891411.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.178905963897705,
|
|
"epoch": 0.4228707564026206,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498952083992921,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.1756322056055069,
|
|
"num_tokens": 9904891.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.294816207885742,
|
|
"epoch": 0.4234663490172722,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989479720839605,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.16916252970695494,
|
|
"num_tokens": 9918920.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.319990348815918,
|
|
"epoch": 0.4240619416319238,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004989438521423506,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.1781326487660408,
|
|
"num_tokens": 9932975.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.311943387985229,
|
|
"epoch": 0.4246575342465753,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989397241682387,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.16910770684480667,
|
|
"num_tokens": 9946704.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.273131513595581,
|
|
"epoch": 0.4252531268612269,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000498935588161773,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.17367026060819626,
|
|
"num_tokens": 9961729.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.348623180389405,
|
|
"epoch": 0.4258487194758785,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989314441231019,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.16874732375144957,
|
|
"num_tokens": 9976980.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.327210283279419,
|
|
"epoch": 0.4264443120905301,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989272920523741,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.17219207137823106,
|
|
"num_tokens": 9991963.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.314000749588013,
|
|
"epoch": 0.42703990470518166,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989231319497382,
|
|
"loss": 5.273,
|
|
"mean_token_accuracy": 0.17501886039972306,
|
|
"num_tokens": 10005323.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.263321828842163,
|
|
"epoch": 0.42763549731983325,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989189638153437,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.17625982612371444,
|
|
"num_tokens": 10018352.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.261756563186646,
|
|
"epoch": 0.42823108993448483,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989147876493401,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.17386772334575654,
|
|
"num_tokens": 10032371.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.392148971557617,
|
|
"epoch": 0.4288266825491364,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989106034518771,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.17259630262851716,
|
|
"num_tokens": 10044221.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.371559953689575,
|
|
"epoch": 0.42942227516378795,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989064112231049,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.17167444080114364,
|
|
"num_tokens": 10057475.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.317913484573364,
|
|
"epoch": 0.43001786777843953,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989022109631736,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.17184336483478546,
|
|
"num_tokens": 10072272.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.3278844356536865,
|
|
"epoch": 0.4306134603930911,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988980026722341,
|
|
"loss": 5.3191,
|
|
"mean_token_accuracy": 0.16157803684473038,
|
|
"num_tokens": 10086757.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.367853164672852,
|
|
"epoch": 0.4312090530077427,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004988937863504373,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.1640655905008316,
|
|
"num_tokens": 10100471.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.3761989116668705,
|
|
"epoch": 0.4318046456223943,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988895619979344,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.17002047151327132,
|
|
"num_tokens": 10112764.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.344563722610474,
|
|
"epoch": 0.4324002382370459,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498885329614877,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.1817211925983429,
|
|
"num_tokens": 10125830.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.143599033355713,
|
|
"epoch": 0.43299583085169746,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988810892014168,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.17835563570261,
|
|
"num_tokens": 10140007.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.342664909362793,
|
|
"epoch": 0.433591423466349,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988768407577058,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.1794012188911438,
|
|
"num_tokens": 10154508.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.261961030960083,
|
|
"epoch": 0.4341870160810006,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988725842838968,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.17919831871986389,
|
|
"num_tokens": 10167832.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.353896379470825,
|
|
"epoch": 0.43478260869565216,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498868319780142,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.1731872633099556,
|
|
"num_tokens": 10182421.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.2683042049407955,
|
|
"epoch": 0.43537820131030375,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004988640472465947,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.18189208805561066,
|
|
"num_tokens": 10196210.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.305925369262695,
|
|
"epoch": 0.43597379392495533,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004988597666834078,
|
|
"loss": 5.2472,
|
|
"mean_token_accuracy": 0.17245521396398544,
|
|
"num_tokens": 10210930.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.253030681610108,
|
|
"epoch": 0.4365693865396069,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988554780907353,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.17164668589830398,
|
|
"num_tokens": 10225758.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.315539216995239,
|
|
"epoch": 0.4371649791542585,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988511814687306,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.17417529970407486,
|
|
"num_tokens": 10239924.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.351163578033447,
|
|
"epoch": 0.4377605717689101,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988468768175479,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.17340963035821916,
|
|
"num_tokens": 10254713.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.311220359802246,
|
|
"epoch": 0.4383561643835616,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988425641373418,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.1692033439874649,
|
|
"num_tokens": 10270335.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.369412136077881,
|
|
"epoch": 0.4389517569982132,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988382434282668,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.17365427166223527,
|
|
"num_tokens": 10286368.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.332020664215088,
|
|
"epoch": 0.4395473496128648,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498833914690478,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.16653933078050615,
|
|
"num_tokens": 10302073.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.231152200698853,
|
|
"epoch": 0.4401429422275164,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988295779241306,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.1794533208012581,
|
|
"num_tokens": 10317741.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.29537615776062,
|
|
"epoch": 0.44073853484216796,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988252331293802,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.17125927954912185,
|
|
"num_tokens": 10331439.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.412912082672119,
|
|
"epoch": 0.44133412745681955,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988208803063827,
|
|
"loss": 5.4032,
|
|
"mean_token_accuracy": 0.1637168288230896,
|
|
"num_tokens": 10345107.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.390082311630249,
|
|
"epoch": 0.44192972007147113,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988165194552939,
|
|
"loss": 5.2906,
|
|
"mean_token_accuracy": 0.17395940124988557,
|
|
"num_tokens": 10360078.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.264197301864624,
|
|
"epoch": 0.4425253126861227,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004988121505762706,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.17000083327293397,
|
|
"num_tokens": 10373221.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.3661713123321535,
|
|
"epoch": 0.44312090530077425,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004988077736694693,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.165135358273983,
|
|
"num_tokens": 10386200.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.322316312789917,
|
|
"epoch": 0.44371649791542583,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004988033887350471,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.17439838647842407,
|
|
"num_tokens": 10398680.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.355290365219116,
|
|
"epoch": 0.4443120905300774,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987989957731611,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.17133977860212327,
|
|
"num_tokens": 10414483.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.315198612213135,
|
|
"epoch": 0.444907683144729,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987945947839691,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.17299814224243165,
|
|
"num_tokens": 10428962.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.420834875106811,
|
|
"epoch": 0.4455032757593806,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498790185767629,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.16779448166489602,
|
|
"num_tokens": 10442273.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.424126434326172,
|
|
"epoch": 0.4460988683740322,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987857687242986,
|
|
"loss": 5.3217,
|
|
"mean_token_accuracy": 0.16621219366788864,
|
|
"num_tokens": 10456610.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.248274517059326,
|
|
"epoch": 0.44669446098868376,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987813436541366,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.17247937321662904,
|
|
"num_tokens": 10470144.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.361557197570801,
|
|
"epoch": 0.4472900536033353,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987769105573016,
|
|
"loss": 5.2121,
|
|
"mean_token_accuracy": 0.17979683429002763,
|
|
"num_tokens": 10483866.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.2181275367736815,
|
|
"epoch": 0.4478856462179869,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987724694339526,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.1779528796672821,
|
|
"num_tokens": 10497350.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.288441705703735,
|
|
"epoch": 0.44848123883263846,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987680202842491,
|
|
"loss": 5.2802,
|
|
"mean_token_accuracy": 0.17278729677200316,
|
|
"num_tokens": 10510808.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.2817065715789795,
|
|
"epoch": 0.44907683144729005,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987635631083505,
|
|
"loss": 5.112,
|
|
"mean_token_accuracy": 0.1789168134331703,
|
|
"num_tokens": 10525965.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.292351007461548,
|
|
"epoch": 0.44967242406194163,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987590979064167,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.17260973155498505,
|
|
"num_tokens": 10539900.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.344563913345337,
|
|
"epoch": 0.4502680166765932,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004987546246786078,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.16723538488149642,
|
|
"num_tokens": 10553653.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.229969644546509,
|
|
"epoch": 0.4508636092912448,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987501434250844,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.17360801100730897,
|
|
"num_tokens": 10568202.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.228050708770752,
|
|
"epoch": 0.4514592019058964,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000498745654146007,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.17932818830013275,
|
|
"num_tokens": 10581290.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.286312866210937,
|
|
"epoch": 0.4520547945205479,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498741156841537,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.17296536713838578,
|
|
"num_tokens": 10596697.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.3026618480682375,
|
|
"epoch": 0.4526503871351995,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987366515118353,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.17213900834321977,
|
|
"num_tokens": 10610052.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.279774141311646,
|
|
"epoch": 0.4532459797498511,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987321381570638,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.17870575934648514,
|
|
"num_tokens": 10624268.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.211029386520385,
|
|
"epoch": 0.4538415723645027,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987276167773842,
|
|
"loss": 5.1333,
|
|
"mean_token_accuracy": 0.18040878176689149,
|
|
"num_tokens": 10636463.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.278153991699218,
|
|
"epoch": 0.45443716497915426,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987230873729588,
|
|
"loss": 5.1969,
|
|
"mean_token_accuracy": 0.1783073827624321,
|
|
"num_tokens": 10649566.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.300192356109619,
|
|
"epoch": 0.45503275759380585,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049871854994395,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.17470222413539888,
|
|
"num_tokens": 10661373.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.194976091384888,
|
|
"epoch": 0.45562835020845743,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987140044905205,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.17984156906604767,
|
|
"num_tokens": 10677008.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.354965305328369,
|
|
"epoch": 0.456223942823109,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987094510128335,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.17574340850114822,
|
|
"num_tokens": 10690497.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.324583673477173,
|
|
"epoch": 0.45681953543776055,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987048895110522,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.17815289050340652,
|
|
"num_tokens": 10705315.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.2292530059814455,
|
|
"epoch": 0.45741512805241213,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987003199853401,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.18042684048414231,
|
|
"num_tokens": 10718536.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.293408393859863,
|
|
"epoch": 0.4580107206670637,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986957424358613,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.1727812260389328,
|
|
"num_tokens": 10735402.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.31691164970398,
|
|
"epoch": 0.4586063132817153,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049869115686278,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.1734998643398285,
|
|
"num_tokens": 10748809.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.169680500030518,
|
|
"epoch": 0.4592019058963669,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986865632662606,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.17547816783189774,
|
|
"num_tokens": 10761935.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.275300741195679,
|
|
"epoch": 0.4597974985110185,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986819616464678,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.16600763350725173,
|
|
"num_tokens": 10778252.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.404610061645508,
|
|
"epoch": 0.46039309112567006,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986773520035667,
|
|
"loss": 5.3901,
|
|
"mean_token_accuracy": 0.16567778289318086,
|
|
"num_tokens": 10792606.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.325445032119751,
|
|
"epoch": 0.46098868374032165,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986727343377227,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.16799498051404954,
|
|
"num_tokens": 10805433.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.273412227630615,
|
|
"epoch": 0.4615842763549732,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986681086491014,
|
|
"loss": 5.2742,
|
|
"mean_token_accuracy": 0.1711922451853752,
|
|
"num_tokens": 10818648.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.250712966918945,
|
|
"epoch": 0.46217986896962476,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986634749378686,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.17692007422447203,
|
|
"num_tokens": 10833089.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.258233451843262,
|
|
"epoch": 0.46277546158427635,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004986588332041908,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.17295440584421157,
|
|
"num_tokens": 10847850.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.346755409240723,
|
|
"epoch": 0.46337105419892793,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004986541834482342,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.17560209184885026,
|
|
"num_tokens": 10861354.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.314890193939209,
|
|
"epoch": 0.4639666468135795,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004986495256701657,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.16152886748313905,
|
|
"num_tokens": 10877986.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.2230151176452635,
|
|
"epoch": 0.4645622394282311,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004986448598701523,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.18182764947414398,
|
|
"num_tokens": 10891253.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.306602239608765,
|
|
"epoch": 0.4651578320428827,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986401860483615,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.178652386367321,
|
|
"num_tokens": 10905916.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.278542613983154,
|
|
"epoch": 0.4657534246575342,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004986355042049608,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.1803273543715477,
|
|
"num_tokens": 10920038.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.219434404373169,
|
|
"epoch": 0.4663490172721858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986308143401181,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.17948027551174164,
|
|
"num_tokens": 10933161.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.25840916633606,
|
|
"epoch": 0.4669446098868374,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004986261164540018,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.17323225140571594,
|
|
"num_tokens": 10946573.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.299171304702758,
|
|
"epoch": 0.467540202501489,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986214105467801,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.17076320499181746,
|
|
"num_tokens": 10960727.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.299115371704102,
|
|
"epoch": 0.46813579511614056,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986166966186223,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.1716752380132675,
|
|
"num_tokens": 10973298.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.3563824653625485,
|
|
"epoch": 0.46873138773079215,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986119746696969,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.1736910343170166,
|
|
"num_tokens": 10988214.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.326999950408935,
|
|
"epoch": 0.46932698034544373,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004986072447001736,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.1756324663758278,
|
|
"num_tokens": 11003526.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.346063232421875,
|
|
"epoch": 0.4699225729600953,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986025067102221,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.16597171723842621,
|
|
"num_tokens": 11019600.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.22307276725769,
|
|
"epoch": 0.47051816557474685,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985977607000121,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.18096638470888138,
|
|
"num_tokens": 11032591.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.194874429702759,
|
|
"epoch": 0.47111375818939843,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985930066697141,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.17885678261518478,
|
|
"num_tokens": 11045724.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.33377046585083,
|
|
"epoch": 0.47170935080405,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985882446194984,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.16944465935230255,
|
|
"num_tokens": 11059149.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.297083044052124,
|
|
"epoch": 0.4723049434187016,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498583474549536,
|
|
"loss": 5.2605,
|
|
"mean_token_accuracy": 0.17053062170743943,
|
|
"num_tokens": 11073489.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.241413116455078,
|
|
"epoch": 0.4729005360333532,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985786964599978,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.17258585691452027,
|
|
"num_tokens": 11086535.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.199859094619751,
|
|
"epoch": 0.4734961286480048,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985739103510553,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.17810686975717543,
|
|
"num_tokens": 11100142.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.246997451782226,
|
|
"epoch": 0.47409172126265636,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004985691162228802,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.18628436475992202,
|
|
"num_tokens": 11113364.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.29514799118042,
|
|
"epoch": 0.47468731387730795,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985643140756442,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.1663251504302025,
|
|
"num_tokens": 11127127.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.296467733383179,
|
|
"epoch": 0.4752829064919595,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049855950390952,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.17076850831508636,
|
|
"num_tokens": 11139788.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.295640373229981,
|
|
"epoch": 0.47587849910661106,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985546857246797,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.17027414441108704,
|
|
"num_tokens": 11156470.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.275999355316162,
|
|
"epoch": 0.47647409172126265,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985498595212964,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.17905441522598267,
|
|
"num_tokens": 11168923.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.219401502609253,
|
|
"epoch": 0.47706968433591423,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004985450252995431,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.1775607243180275,
|
|
"num_tokens": 11181328.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.42423791885376,
|
|
"epoch": 0.4776652769505658,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985401830595932,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.16532307118177414,
|
|
"num_tokens": 11197800.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.364238309860229,
|
|
"epoch": 0.4782608695652174,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004985353328016204,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.17026508301496507,
|
|
"num_tokens": 11209862.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.238272762298584,
|
|
"epoch": 0.478856462179869,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985304745257986,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.1738913983106613,
|
|
"num_tokens": 11223433.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.3707146644592285,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985256082323022,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.1680361807346344,
|
|
"num_tokens": 11236975.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.278060102462769,
|
|
"epoch": 0.4800476474091721,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985207339213057,
|
|
"loss": 5.2423,
|
|
"mean_token_accuracy": 0.16932326108217238,
|
|
"num_tokens": 11250277.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.316738605499268,
|
|
"epoch": 0.4806432400238237,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985158515929837,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.17600054740905763,
|
|
"num_tokens": 11264990.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.35556468963623,
|
|
"epoch": 0.4812388326384753,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985109612475116,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.1696727991104126,
|
|
"num_tokens": 11277496.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.261840343475342,
|
|
"epoch": 0.48183442525312686,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004985060628850648,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.17574242800474166,
|
|
"num_tokens": 11290263.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.2809374809265135,
|
|
"epoch": 0.48243001786777845,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985011565058189,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.18181141018867492,
|
|
"num_tokens": 11305611.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.331931400299072,
|
|
"epoch": 0.48302561048243003,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984962421099498,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.1721456378698349,
|
|
"num_tokens": 11321216.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.268821430206299,
|
|
"epoch": 0.4836212030970816,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498491319697634,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.1842049241065979,
|
|
"num_tokens": 11335029.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.250873994827271,
|
|
"epoch": 0.48421679571173315,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498486389269048,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.16528143584728242,
|
|
"num_tokens": 11349301.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.349119806289673,
|
|
"epoch": 0.48481238832638474,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004984814508243685,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.17489668875932693,
|
|
"num_tokens": 11364561.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.1716554164886475,
|
|
"epoch": 0.4854079809410363,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004984765043637727,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.1789498120546341,
|
|
"num_tokens": 11379470.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.3589623928070065,
|
|
"epoch": 0.4860035735556879,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498471549887438,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.17785462737083435,
|
|
"num_tokens": 11393433.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.194477462768555,
|
|
"epoch": 0.4865991661703395,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984665873955422,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.1758410170674324,
|
|
"num_tokens": 11406673.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.231308555603027,
|
|
"epoch": 0.4871947587849911,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004984616168882632,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.1756559982895851,
|
|
"num_tokens": 11420395.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.304987668991089,
|
|
"epoch": 0.48779035139964266,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984566383657794,
|
|
"loss": 5.2594,
|
|
"mean_token_accuracy": 0.16861254274845122,
|
|
"num_tokens": 11432866.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.191527223587036,
|
|
"epoch": 0.48838594401429425,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984516518282692,
|
|
"loss": 5.2447,
|
|
"mean_token_accuracy": 0.17258132249116898,
|
|
"num_tokens": 11447062.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.281417369842529,
|
|
"epoch": 0.4889815366289458,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004984466572759117,
|
|
"loss": 5.2412,
|
|
"mean_token_accuracy": 0.1829113781452179,
|
|
"num_tokens": 11461255.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.394562149047852,
|
|
"epoch": 0.48957712924359736,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984416547088858,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.17497455328702927,
|
|
"num_tokens": 11475711.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.240410470962525,
|
|
"epoch": 0.49017272185824895,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984366441273711,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.1695879027247429,
|
|
"num_tokens": 11491199.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.313310956954956,
|
|
"epoch": 0.49076831447290054,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984316255315472,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.17966444939374923,
|
|
"num_tokens": 11504365.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.304496383666992,
|
|
"epoch": 0.4913639070875521,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004984265989215942,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.16686510145664216,
|
|
"num_tokens": 11517969.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.2761146068573,
|
|
"epoch": 0.4919594997022037,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004984215642976923,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.17133453041315078,
|
|
"num_tokens": 11533203.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.28263783454895,
|
|
"epoch": 0.4925550923168553,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004984165216600224,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.17159003168344497,
|
|
"num_tokens": 11547820.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.2806384563446045,
|
|
"epoch": 0.4931506849315068,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004984114710087648,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.18293206095695497,
|
|
"num_tokens": 11561591.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.225991106033325,
|
|
"epoch": 0.4937462775461584,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004984064123441011,
|
|
"loss": 5.2259,
|
|
"mean_token_accuracy": 0.17683966606855392,
|
|
"num_tokens": 11576722.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.344530391693115,
|
|
"epoch": 0.49434187016081,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004984013456662127,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.17393892109394074,
|
|
"num_tokens": 11590455.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.32809853553772,
|
|
"epoch": 0.4949374627754616,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983962709752812,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.1709906429052353,
|
|
"num_tokens": 11605495.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.224591302871704,
|
|
"epoch": 0.49553305539011316,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983911882714886,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.17775264978408814,
|
|
"num_tokens": 11619692.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.2711444854736325,
|
|
"epoch": 0.49612864800476475,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004983860975550174,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.17580137252807618,
|
|
"num_tokens": 11633806.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.272823715209961,
|
|
"epoch": 0.49672424061941634,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983809988260501,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.1876682683825493,
|
|
"num_tokens": 11649871.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.217583417892456,
|
|
"epoch": 0.4973198332340679,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983758920847696,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.1765337884426117,
|
|
"num_tokens": 11661472.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.177469301223755,
|
|
"epoch": 0.49791542584871945,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983707773313589,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.18148375898599625,
|
|
"num_tokens": 11674689.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.204212951660156,
|
|
"epoch": 0.49851101846337104,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983656545660016,
|
|
"loss": 5.0474,
|
|
"mean_token_accuracy": 0.18675675094127656,
|
|
"num_tokens": 11687867.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.174596166610717,
|
|
"epoch": 0.4991066110780226,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004983605237888815,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.17650242000818253,
|
|
"num_tokens": 11704611.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.295996141433716,
|
|
"epoch": 0.4997022036926742,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004983553850001826,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.17741442024707793,
|
|
"num_tokens": 11719448.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.206750583648682,
|
|
"epoch": 0.5002977963073257,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983502382000892,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.17514424920082092,
|
|
"num_tokens": 11731160.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.245828247070312,
|
|
"epoch": 0.5008933889219773,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983450833887859,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.17865489572286605,
|
|
"num_tokens": 11744319.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.273895692825318,
|
|
"epoch": 0.5014889815366289,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983399205664575,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.1767744392156601,
|
|
"num_tokens": 11757861.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.2192299365997314,
|
|
"epoch": 0.5020845741512805,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004983347497332894,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.17682270258665084,
|
|
"num_tokens": 11770707.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.232171869277954,
|
|
"epoch": 0.5026801667659321,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983295708894668,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.1852179706096649,
|
|
"num_tokens": 11785155.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.2256707668304445,
|
|
"epoch": 0.5032757593805837,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983243840351757,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.17690593451261521,
|
|
"num_tokens": 11798532.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.174641275405884,
|
|
"epoch": 0.5038713519952353,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004983191891706021,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.17542819380760194,
|
|
"num_tokens": 11812708.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.270325613021851,
|
|
"epoch": 0.5044669446098868,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004983139862959322,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.17213946729898452,
|
|
"num_tokens": 11828844.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.219538927078247,
|
|
"epoch": 0.5050625372245384,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983087754113527,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.17257264703512193,
|
|
"num_tokens": 11845070.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.189782190322876,
|
|
"epoch": 0.50565812983919,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983035565170505,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.18096585869789122,
|
|
"num_tokens": 11858299.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.237399387359619,
|
|
"epoch": 0.5062537224538416,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004982983296132128,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.17845821678638457,
|
|
"num_tokens": 11873805.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.229075193405151,
|
|
"epoch": 0.5068493150684932,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982930947000271,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.16812702566385268,
|
|
"num_tokens": 11888304.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.28016037940979,
|
|
"epoch": 0.5074449076831448,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982878517776812,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.18070859611034393,
|
|
"num_tokens": 11901914.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.259359884262085,
|
|
"epoch": 0.5080405002977963,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498282600846363,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.1849267899990082,
|
|
"num_tokens": 11913225.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.2378973960876465,
|
|
"epoch": 0.5086360929124479,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000498277341906261,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.17736517637968063,
|
|
"num_tokens": 11927200.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.2281006336212155,
|
|
"epoch": 0.5092316855270994,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982720749575637,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.17693739235401154,
|
|
"num_tokens": 11939826.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.276907110214234,
|
|
"epoch": 0.509827278141751,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004982668000004602,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.18145885318517685,
|
|
"num_tokens": 11951983.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.270376443862915,
|
|
"epoch": 0.5104228707564026,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004982615170351395,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.1713082581758499,
|
|
"num_tokens": 11965642.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.281287765502929,
|
|
"epoch": 0.5110184633710542,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982562260617912,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.16900748163461685,
|
|
"num_tokens": 11981472.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.273958921432495,
|
|
"epoch": 0.5116140559857058,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004982509270806052,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.1734770268201828,
|
|
"num_tokens": 11995739.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.322076749801636,
|
|
"epoch": 0.5122096486003573,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982456200917712,
|
|
"loss": 5.2585,
|
|
"mean_token_accuracy": 0.1708080917596817,
|
|
"num_tokens": 12007850.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.2892052173614506,
|
|
"epoch": 0.5128052412150089,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049824030509548,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.18507602363824843,
|
|
"num_tokens": 12022893.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.244344425201416,
|
|
"epoch": 0.5134008338296605,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000498234982091922,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.18310781121253966,
|
|
"num_tokens": 12035520.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.190734148025513,
|
|
"epoch": 0.5139964264443121,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982296510812879,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.17806994020938874,
|
|
"num_tokens": 12047938.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.211571598052979,
|
|
"epoch": 0.5145920190589637,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982243120637694,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.1750247821211815,
|
|
"num_tokens": 12061236.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.2245203971862795,
|
|
"epoch": 0.5151876116736153,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982189650395577,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.17965906113386154,
|
|
"num_tokens": 12074427.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.193080425262451,
|
|
"epoch": 0.5157832042882668,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982136100088447,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.1832956314086914,
|
|
"num_tokens": 12088128.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.2763172626495365,
|
|
"epoch": 0.5163787969029184,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982082469718224,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.16761377602815627,
|
|
"num_tokens": 12100938.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.250015830993652,
|
|
"epoch": 0.51697438951757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982028759286831,
|
|
"loss": 5.1623,
|
|
"mean_token_accuracy": 0.17643774300813675,
|
|
"num_tokens": 12113464.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.189460277557373,
|
|
"epoch": 0.5175699821322216,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004981974968796197,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.1747959464788437,
|
|
"num_tokens": 12129113.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.3201072216033936,
|
|
"epoch": 0.5181655747468732,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004981921098248249,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.1683783233165741,
|
|
"num_tokens": 12142024.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.308768701553345,
|
|
"epoch": 0.5187611673615247,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000498186714764492,
|
|
"loss": 5.2283,
|
|
"mean_token_accuracy": 0.17253553867340088,
|
|
"num_tokens": 12157889.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.253926420211792,
|
|
"epoch": 0.5193567599761763,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981813116988145,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.17434800267219544,
|
|
"num_tokens": 12171527.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.292338037490845,
|
|
"epoch": 0.5199523525908278,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981759006279864,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.17215657532215117,
|
|
"num_tokens": 12186453.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.151060390472412,
|
|
"epoch": 0.5205479452054794,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981704815522014,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.1783852234482765,
|
|
"num_tokens": 12201401.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.192245006561279,
|
|
"epoch": 0.521143537820131,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981650544716542,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.17321754097938538,
|
|
"num_tokens": 12215219.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.278519058227539,
|
|
"epoch": 0.5217391304347826,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981596193865393,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.16782683730125428,
|
|
"num_tokens": 12229932.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.23015251159668,
|
|
"epoch": 0.5223347230494342,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004981541762970517,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.18350773304700851,
|
|
"num_tokens": 12241718.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.324075412750244,
|
|
"epoch": 0.5229303156640858,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004981487252033866,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.17404266744852065,
|
|
"num_tokens": 12256395.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.179274034500122,
|
|
"epoch": 0.5235259082787374,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981432661057396,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.18428031653165816,
|
|
"num_tokens": 12269966.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.269523191452026,
|
|
"epoch": 0.5241215008933889,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981377990043064,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.1694381982088089,
|
|
"num_tokens": 12284410.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.1364734172821045,
|
|
"epoch": 0.5247170935080405,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981323238992831,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.185785274207592,
|
|
"num_tokens": 12298931.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.219696521759033,
|
|
"epoch": 0.5253126861226921,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004981268407908662,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.17774450033903122,
|
|
"num_tokens": 12313857.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.173709392547607,
|
|
"epoch": 0.5259082787373437,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004981213496792523,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.17624765038490295,
|
|
"num_tokens": 12327732.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.196479034423828,
|
|
"epoch": 0.5265038713519953,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004981158505646383,
|
|
"loss": 5.1922,
|
|
"mean_token_accuracy": 0.174234776198864,
|
|
"num_tokens": 12341754.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.2345991134643555,
|
|
"epoch": 0.5270994639666469,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981103434472216,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.17855749577283858,
|
|
"num_tokens": 12355656.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.128445959091186,
|
|
"epoch": 0.5276950565812983,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981048283271997,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.1849416136741638,
|
|
"num_tokens": 12368346.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.169057941436767,
|
|
"epoch": 0.5282906491959499,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004980993052047701,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.17359172254800798,
|
|
"num_tokens": 12381844.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.338162803649903,
|
|
"epoch": 0.5288862418106015,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980937740801313,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.16773327589035034,
|
|
"num_tokens": 12395432.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.222998714447021,
|
|
"epoch": 0.5294818344252531,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980882349534816,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.17222893089056016,
|
|
"num_tokens": 12408897.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.2135625839233395,
|
|
"epoch": 0.5300774270399047,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980826878250195,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.1832023084163666,
|
|
"num_tokens": 12421480.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.208907270431519,
|
|
"epoch": 0.5306730196545563,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980771326949442,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.16961990892887116,
|
|
"num_tokens": 12436931.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.262372589111328,
|
|
"epoch": 0.5312686122692079,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980715695634549,
|
|
"loss": 5.2429,
|
|
"mean_token_accuracy": 0.17897117137908936,
|
|
"num_tokens": 12451687.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.248861980438233,
|
|
"epoch": 0.5318642048838594,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004980659984307511,
|
|
"loss": 5.147,
|
|
"mean_token_accuracy": 0.18268181681632994,
|
|
"num_tokens": 12464338.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.2263209342956545,
|
|
"epoch": 0.532459797498511,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004980604192970325,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.17683452218770981,
|
|
"num_tokens": 12482520.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.385048151016235,
|
|
"epoch": 0.5330553901131626,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004980548321624993,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.17145491689443587,
|
|
"num_tokens": 12495791.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.195588445663452,
|
|
"epoch": 0.5336509827278142,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498049237027352,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.1742942988872528,
|
|
"num_tokens": 12509963.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.210734891891479,
|
|
"epoch": 0.5342465753424658,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980436338917914,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.17368560433387756,
|
|
"num_tokens": 12522825.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.25645489692688,
|
|
"epoch": 0.5348421679571174,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498038022756018,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.17796911299228668,
|
|
"num_tokens": 12536097.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.1863185405731205,
|
|
"epoch": 0.535437760571769,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980324036202335,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.18404089212417601,
|
|
"num_tokens": 12551441.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.245156002044678,
|
|
"epoch": 0.5360333531864205,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004980267764846393,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.18332220613956451,
|
|
"num_tokens": 12566271.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.218369770050049,
|
|
"epoch": 0.5366289458010721,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004980211413494373,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.17700253129005433,
|
|
"num_tokens": 12580585.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.1883237838745115,
|
|
"epoch": 0.5372245384157236,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980154982148296,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.18448085188865662,
|
|
"num_tokens": 12592389.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.130449104309082,
|
|
"epoch": 0.5378201310303752,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980098470810185,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.191366708278656,
|
|
"num_tokens": 12606487.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.157979965209961,
|
|
"epoch": 0.5384157236450268,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980041879482068,
|
|
"loss": 5.1853,
|
|
"mean_token_accuracy": 0.18097048550844191,
|
|
"num_tokens": 12621036.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.240445375442505,
|
|
"epoch": 0.5390113162596784,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979985208165975,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.18635114282369614,
|
|
"num_tokens": 12634911.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.204083108901978,
|
|
"epoch": 0.5396069088743299,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979928456863937,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.18393225818872452,
|
|
"num_tokens": 12649165.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.229859066009522,
|
|
"epoch": 0.5402025014889815,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979871625577991,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.17978449761867524,
|
|
"num_tokens": 12663803.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.268910503387451,
|
|
"epoch": 0.5407980941036331,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979814714310177,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.1802477717399597,
|
|
"num_tokens": 12676336.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.110779333114624,
|
|
"epoch": 0.5413936867182847,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004979757723062533,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.18374361395835875,
|
|
"num_tokens": 12689619.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.16949315071106,
|
|
"epoch": 0.5419892793329363,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979700651837107,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.1770714372396469,
|
|
"num_tokens": 12703964.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.2367839336395265,
|
|
"epoch": 0.5425848719475879,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979643500635942,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.17908920645713805,
|
|
"num_tokens": 12716832.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.2394781589508055,
|
|
"epoch": 0.5431804645622395,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979586269461089,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.18450819104909896,
|
|
"num_tokens": 12729665.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.17684383392334,
|
|
"epoch": 0.543776057176891,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004979528958314604,
|
|
"loss": 5.1029,
|
|
"mean_token_accuracy": 0.18215738534927367,
|
|
"num_tokens": 12743576.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.137889242172241,
|
|
"epoch": 0.5443716497915426,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004979471567198539,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.1765195608139038,
|
|
"num_tokens": 12758511.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.164740419387817,
|
|
"epoch": 0.5449672424061942,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979414096114953,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.17864427268505095,
|
|
"num_tokens": 12771694.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.223935317993164,
|
|
"epoch": 0.5455628350208458,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000497935654506591,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.17748285979032516,
|
|
"num_tokens": 12786367.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.149479722976684,
|
|
"epoch": 0.5461584276354973,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000497929891405347,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.18830176442861557,
|
|
"num_tokens": 12801177.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.227723693847656,
|
|
"epoch": 0.5467540202501489,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979241203079705,
|
|
"loss": 5.238,
|
|
"mean_token_accuracy": 0.167804816365242,
|
|
"num_tokens": 12817347.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.294123888015747,
|
|
"epoch": 0.5473496128648004,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004979183412146681,
|
|
"loss": 5.2271,
|
|
"mean_token_accuracy": 0.17414859384298326,
|
|
"num_tokens": 12830304.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.139929866790771,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979125541256474,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.1909378007054329,
|
|
"num_tokens": 12843813.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.267768526077271,
|
|
"epoch": 0.5485407980941036,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004979067590411157,
|
|
"loss": 5.2441,
|
|
"mean_token_accuracy": 0.17381819486618041,
|
|
"num_tokens": 12857989.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.256014060974121,
|
|
"epoch": 0.5491363907087552,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497900955961281,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.1820851594209671,
|
|
"num_tokens": 12871529.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.164897203445435,
|
|
"epoch": 0.5497319833234068,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978951448863514,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.17941290885210037,
|
|
"num_tokens": 12884907.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.230252456665039,
|
|
"epoch": 0.5503275759380584,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004978893258165354,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.18103968650102614,
|
|
"num_tokens": 12898403.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.188966417312622,
|
|
"epoch": 0.55092316855271,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004978834987520417,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.1797717273235321,
|
|
"num_tokens": 12913982.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.222314739227295,
|
|
"epoch": 0.5515187611673615,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978776636930792,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.17826985865831374,
|
|
"num_tokens": 12928826.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.172670888900757,
|
|
"epoch": 0.5521143537820131,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978718206398574,
|
|
"loss": 5.1583,
|
|
"mean_token_accuracy": 0.18043944090604783,
|
|
"num_tokens": 12941905.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.235024881362915,
|
|
"epoch": 0.5527099463966647,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004978659695925856,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.17512058168649675,
|
|
"num_tokens": 12955522.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.254268455505371,
|
|
"epoch": 0.5533055390113163,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004978601105514739,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.1818908706307411,
|
|
"num_tokens": 12968491.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.196907186508179,
|
|
"epoch": 0.5539011316259679,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004978542435167324,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.17815342396497727,
|
|
"num_tokens": 12983258.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.245917129516601,
|
|
"epoch": 0.5544967242406195,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978483684885716,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.17995801120996474,
|
|
"num_tokens": 12996271.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.2382955074310305,
|
|
"epoch": 0.5550923168552709,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978424854672021,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.1791140466928482,
|
|
"num_tokens": 13010920.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.1294129371643065,
|
|
"epoch": 0.5556879094699225,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978365944528349,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.1882008746266365,
|
|
"num_tokens": 13023499.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.27125654220581,
|
|
"epoch": 0.5562835020845741,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004978306954456814,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.17528896331787108,
|
|
"num_tokens": 13040510.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.223342227935791,
|
|
"epoch": 0.5568790946992257,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004978247884459532,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.18334135860204698,
|
|
"num_tokens": 13053708.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.172295236587525,
|
|
"epoch": 0.5574746873138773,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004978188734538621,
|
|
"loss": 5.2032,
|
|
"mean_token_accuracy": 0.18163803964853287,
|
|
"num_tokens": 13068666.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.1906883239746096,
|
|
"epoch": 0.5580702799285289,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004978129504696203,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.17810050696134566,
|
|
"num_tokens": 13082549.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.365301656723022,
|
|
"epoch": 0.5586658725431805,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978070194934402,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.1678910255432129,
|
|
"num_tokens": 13096685.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.169544744491577,
|
|
"epoch": 0.559261465157832,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978010805255347,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.18189408630132675,
|
|
"num_tokens": 13110187.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.112721538543701,
|
|
"epoch": 0.5598570577724836,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977951335661165,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.18113861083984376,
|
|
"num_tokens": 13124105.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.312156295776367,
|
|
"epoch": 0.5604526503871352,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004977891786153992,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.18169096857309341,
|
|
"num_tokens": 13139675.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.176735591888428,
|
|
"epoch": 0.5610482430017868,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004977832156735963,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.1763705715537071,
|
|
"num_tokens": 13154105.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.077876901626587,
|
|
"epoch": 0.5616438356164384,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977772447409217,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.1820295751094818,
|
|
"num_tokens": 13168473.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.262841367721558,
|
|
"epoch": 0.56223942823109,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004977712658175894,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.18185813277959822,
|
|
"num_tokens": 13182873.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.160497617721558,
|
|
"epoch": 0.5628350208457416,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977652789038142,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.1796020969748497,
|
|
"num_tokens": 13196894.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.199895620346069,
|
|
"epoch": 0.5634306134603931,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004977592839998105,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.17902853041887284,
|
|
"num_tokens": 13212285.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.257394218444825,
|
|
"epoch": 0.5640262060750447,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004977532811057936,
|
|
"loss": 5.1586,
|
|
"mean_token_accuracy": 0.1744452655315399,
|
|
"num_tokens": 13227272.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.175339603424073,
|
|
"epoch": 0.5646217986896962,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004977472702219786,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.1782020404934883,
|
|
"num_tokens": 13241544.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.166709661483765,
|
|
"epoch": 0.5652173913043478,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977412513485812,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.1747167870402336,
|
|
"num_tokens": 13255605.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.229501628875733,
|
|
"epoch": 0.5658129839189994,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004977352244858172,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.18133992999792098,
|
|
"num_tokens": 13269143.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.266266822814941,
|
|
"epoch": 0.566408576533651,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004977291896339029,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.18818714320659638,
|
|
"num_tokens": 13284316.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.130814695358277,
|
|
"epoch": 0.5670041691483025,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004977231467930546,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.18938491493463516,
|
|
"num_tokens": 13297714.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.138743114471436,
|
|
"epoch": 0.5675997617629541,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004977170959634893,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.1781224399805069,
|
|
"num_tokens": 13311759.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.099688386917114,
|
|
"epoch": 0.5681953543776057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977110371454239,
|
|
"loss": 5.0614,
|
|
"mean_token_accuracy": 0.18708940595388412,
|
|
"num_tokens": 13325966.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.2609600067138675,
|
|
"epoch": 0.5687909469922573,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004977049703390755,
|
|
"loss": 5.2172,
|
|
"mean_token_accuracy": 0.17768857777118682,
|
|
"num_tokens": 13340939.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.276161050796508,
|
|
"epoch": 0.5693865396069089,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976988955446622,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.17790772318840026,
|
|
"num_tokens": 13354400.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.3839751243591305,
|
|
"epoch": 0.5699821322215605,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004976928127624013,
|
|
"loss": 5.2739,
|
|
"mean_token_accuracy": 0.16176303923130037,
|
|
"num_tokens": 13368819.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.178058671951294,
|
|
"epoch": 0.570577724836212,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004976867219925116,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.18744570016860962,
|
|
"num_tokens": 13381106.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.214951372146606,
|
|
"epoch": 0.5711733174508636,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497680623235211,
|
|
"loss": 5.1223,
|
|
"mean_token_accuracy": 0.17983683496713637,
|
|
"num_tokens": 13394718.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.225713872909546,
|
|
"epoch": 0.5717689100655152,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004976745164907185,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.17706361263990403,
|
|
"num_tokens": 13408416.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.2250690937042235,
|
|
"epoch": 0.5723645026801668,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976684017592533,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.17703333348035813,
|
|
"num_tokens": 13422287.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.252969455718994,
|
|
"epoch": 0.5729600952948184,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004976622790410345,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.1764609098434448,
|
|
"num_tokens": 13438080.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.195742130279541,
|
|
"epoch": 0.5735556879094699,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004976561483362818,
|
|
"loss": 5.1413,
|
|
"mean_token_accuracy": 0.1781737208366394,
|
|
"num_tokens": 13454781.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.219676733016968,
|
|
"epoch": 0.5741512805241215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497650009645215,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.17610154747962953,
|
|
"num_tokens": 13467021.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.099160194396973,
|
|
"epoch": 0.574746873138773,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004976438629680543,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.1821634963154793,
|
|
"num_tokens": 13479125.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.1606322765350345,
|
|
"epoch": 0.5753424657534246,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004976377083050204,
|
|
"loss": 5.1013,
|
|
"mean_token_accuracy": 0.18928865045309068,
|
|
"num_tokens": 13493444.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.306022500991821,
|
|
"epoch": 0.5759380583680762,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004976315456563339,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.17792827636003494,
|
|
"num_tokens": 13508261.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.243772315979004,
|
|
"epoch": 0.5765336509827278,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004976253750222157,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.17793318778276443,
|
|
"num_tokens": 13521371.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.17854905128479,
|
|
"epoch": 0.5771292435973794,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976191964028874,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.17971789389848708,
|
|
"num_tokens": 13536944.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.237271404266357,
|
|
"epoch": 0.577724836212031,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004976130097985703,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.1809883326292038,
|
|
"num_tokens": 13552281.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.2221063613891605,
|
|
"epoch": 0.5783204288266826,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004976068152094867,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.17720084339380265,
|
|
"num_tokens": 13567376.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.261990976333618,
|
|
"epoch": 0.5789160214413341,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976006126358584,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.16733331829309464,
|
|
"num_tokens": 13580688.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.2045165538787845,
|
|
"epoch": 0.5795116140559857,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004975944020779082,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.18033565878868102,
|
|
"num_tokens": 13594823.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.164249467849731,
|
|
"epoch": 0.5801072066706373,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975881835358586,
|
|
"loss": 5.1561,
|
|
"mean_token_accuracy": 0.18103431761264802,
|
|
"num_tokens": 13606702.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.224457693099976,
|
|
"epoch": 0.5807027992852889,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975819570099328,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.1817796602845192,
|
|
"num_tokens": 13620651.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.159754943847656,
|
|
"epoch": 0.5812983918999405,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000497575722500354,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.18392266780138017,
|
|
"num_tokens": 13633192.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.146773481369019,
|
|
"epoch": 0.5818939845145921,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000497569480007346,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.1832946866750717,
|
|
"num_tokens": 13647082.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.173042869567871,
|
|
"epoch": 0.5824895771292437,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004975632295311327,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.18012381345033646,
|
|
"num_tokens": 13662753.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.081233787536621,
|
|
"epoch": 0.5830851697438951,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004975569710719382,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.1814989075064659,
|
|
"num_tokens": 13678548.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.266300106048584,
|
|
"epoch": 0.5836807623585467,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975507046299869,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.17480891346931457,
|
|
"num_tokens": 13690969.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.230375051498413,
|
|
"epoch": 0.5842763549731983,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004975444302055038,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.18192968517541885,
|
|
"num_tokens": 13704519.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.115694189071656,
|
|
"epoch": 0.5848719475878499,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975381477987136,
|
|
"loss": 5.1547,
|
|
"mean_token_accuracy": 0.18197610080242158,
|
|
"num_tokens": 13719664.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.2385283470153805,
|
|
"epoch": 0.5854675402025015,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004975318574098422,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.18394592255353928,
|
|
"num_tokens": 13733527.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.2079691886901855,
|
|
"epoch": 0.586063132817153,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004975255590391147,
|
|
"loss": 5.1751,
|
|
"mean_token_accuracy": 0.1807098239660263,
|
|
"num_tokens": 13747788.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.201961088180542,
|
|
"epoch": 0.5866587254318046,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004975192526867572,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.1831030324101448,
|
|
"num_tokens": 13761389.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.174371671676636,
|
|
"epoch": 0.5872543180464562,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004975129383529959,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.1824611097574234,
|
|
"num_tokens": 13774153.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.118953227996826,
|
|
"epoch": 0.5878499106611078,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004975066160380573,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.17844999134540557,
|
|
"num_tokens": 13788167.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.275248241424561,
|
|
"epoch": 0.5884455032757594,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004975002857421681,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.18547591269016267,
|
|
"num_tokens": 13801190.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.2057374000549315,
|
|
"epoch": 0.589041095890411,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004974939474655554,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.18067824393510817,
|
|
"num_tokens": 13815744.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.183224678039551,
|
|
"epoch": 0.5896366885050626,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004974876012084468,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.18850277811288835,
|
|
"num_tokens": 13829329.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.226964807510376,
|
|
"epoch": 0.5902322811197142,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004974812469710694,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.17810710072517394,
|
|
"num_tokens": 13842401.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.162192058563233,
|
|
"epoch": 0.5908278737343657,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004974748847536516,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.174159374833107,
|
|
"num_tokens": 13857156.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.147190284729004,
|
|
"epoch": 0.5914234663490173,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004974685145564213,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.1778504028916359,
|
|
"num_tokens": 13870863.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.252858686447143,
|
|
"epoch": 0.5920190589636688,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004974621363796071,
|
|
"loss": 5.2563,
|
|
"mean_token_accuracy": 0.17743273228406906,
|
|
"num_tokens": 13886121.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.29874210357666,
|
|
"epoch": 0.5926146515783204,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974557502234378,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.17740725576877595,
|
|
"num_tokens": 13898928.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.17262749671936,
|
|
"epoch": 0.593210244192972,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004974493560881423,
|
|
"loss": 5.214,
|
|
"mean_token_accuracy": 0.17938876301050186,
|
|
"num_tokens": 13911648.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.2426046371459964,
|
|
"epoch": 0.5938058368076236,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004974429539739502,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.17338140606880187,
|
|
"num_tokens": 13924705.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.183375263214112,
|
|
"epoch": 0.5944014294222751,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974365438810911,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.17455219030380248,
|
|
"num_tokens": 13939495.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.17784857749939,
|
|
"epoch": 0.5949970220369267,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004974301258097948,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.18196219354867935,
|
|
"num_tokens": 13952236.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.236195087432861,
|
|
"epoch": 0.5955926146515783,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004974236997602915,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.17552151083946227,
|
|
"num_tokens": 13967699.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.2500985622406,
|
|
"epoch": 0.5961882072662299,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974172657328116,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.18113546520471574,
|
|
"num_tokens": 13980619.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.123591423034668,
|
|
"epoch": 0.5967837998808815,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497410823727586,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.1769114464521408,
|
|
"num_tokens": 13995965.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.229843282699585,
|
|
"epoch": 0.5973793924955331,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497404373744846,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.18097723871469498,
|
|
"num_tokens": 14010325.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.245762300491333,
|
|
"epoch": 0.5979749851101847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973979157848227,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.17533625066280364,
|
|
"num_tokens": 14025368.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.039739084243775,
|
|
"epoch": 0.5985705777248362,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004973914498477475,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.18162713795900345,
|
|
"num_tokens": 14039609.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.307625675201416,
|
|
"epoch": 0.5991661703394878,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004973849759338527,
|
|
"loss": 5.2142,
|
|
"mean_token_accuracy": 0.17925260066986085,
|
|
"num_tokens": 14053680.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.31685962677002,
|
|
"epoch": 0.5997617629541394,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004973784940433706,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.17684580981731415,
|
|
"num_tokens": 14067262.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.148140287399292,
|
|
"epoch": 0.600357355568791,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004973720041765332,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.18098252415657043,
|
|
"num_tokens": 14080821.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.252492141723633,
|
|
"epoch": 0.6009529481834425,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004973655063335736,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.17932077944278718,
|
|
"num_tokens": 14093586.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.118400764465332,
|
|
"epoch": 0.6015485407980941,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497359000514725,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.18585658371448516,
|
|
"num_tokens": 14108138.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.1857654571533205,
|
|
"epoch": 0.6021441334127456,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004973524867202205,
|
|
"loss": 5.1046,
|
|
"mean_token_accuracy": 0.18404096513986587,
|
|
"num_tokens": 14122495.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.06021146774292,
|
|
"epoch": 0.6027397260273972,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004973459649502939,
|
|
"loss": 5.1079,
|
|
"mean_token_accuracy": 0.1816594645380974,
|
|
"num_tokens": 14136838.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.150394868850708,
|
|
"epoch": 0.6033353186420488,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004973394352051789,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.1807115137577057,
|
|
"num_tokens": 14150910.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.232677984237671,
|
|
"epoch": 0.6039309112567004,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049733289748511,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.1822654649615288,
|
|
"num_tokens": 14164116.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.16414442062378,
|
|
"epoch": 0.604526503871352,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004973263517903213,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.18939581662416458,
|
|
"num_tokens": 14178549.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.145142698287964,
|
|
"epoch": 0.6051220964860036,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004973197981210481,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.18265034407377242,
|
|
"num_tokens": 14191625.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.176723861694336,
|
|
"epoch": 0.6057176891006552,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973132364775252,
|
|
"loss": 5.1126,
|
|
"mean_token_accuracy": 0.1838211387395859,
|
|
"num_tokens": 14205396.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.14218578338623,
|
|
"epoch": 0.6063132817153067,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004973066668599879,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.17931349128484725,
|
|
"num_tokens": 14216957.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.2461021900177,
|
|
"epoch": 0.6069088743299583,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004973000892686719,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.18061835318803787,
|
|
"num_tokens": 14232891.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.156010389328003,
|
|
"epoch": 0.6075044669446099,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004972935037038131,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.19000444263219834,
|
|
"num_tokens": 14245628.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.158107614517212,
|
|
"epoch": 0.6081000595592615,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972869101656478,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.1826571300625801,
|
|
"num_tokens": 14260164.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.258916234970092,
|
|
"epoch": 0.6086956521739131,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004972803086544125,
|
|
"loss": 5.1953,
|
|
"mean_token_accuracy": 0.1798940420150757,
|
|
"num_tokens": 14274828.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.226157188415527,
|
|
"epoch": 0.6092912447885647,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004972736991703439,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.1779553085565567,
|
|
"num_tokens": 14287779.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.185812282562256,
|
|
"epoch": 0.6098868374032163,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004972670817136791,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.17741499990224838,
|
|
"num_tokens": 14300946.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.113795328140259,
|
|
"epoch": 0.6104824300178677,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004972604562846554,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.1860035017132759,
|
|
"num_tokens": 14314944.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.192084074020386,
|
|
"epoch": 0.6110780226325193,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004972538228835106,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.1829154223203659,
|
|
"num_tokens": 14330069.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.181971311569214,
|
|
"epoch": 0.6116736152471709,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004972471815104825,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.17779692262411118,
|
|
"num_tokens": 14344262.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.215149641036987,
|
|
"epoch": 0.6122692078618225,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004972405321658094,
|
|
"loss": 5.1454,
|
|
"mean_token_accuracy": 0.18649697452783584,
|
|
"num_tokens": 14358358.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.153236246109008,
|
|
"epoch": 0.6128648004764741,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972338748497297,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.1890925332903862,
|
|
"num_tokens": 14371520.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.105041551589966,
|
|
"epoch": 0.6134603930911257,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004972272095624822,
|
|
"loss": 4.995,
|
|
"mean_token_accuracy": 0.19609591960906983,
|
|
"num_tokens": 14384901.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.052249765396118,
|
|
"epoch": 0.6140559857057772,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000497220536304306,
|
|
"loss": 4.9826,
|
|
"mean_token_accuracy": 0.19938225895166398,
|
|
"num_tokens": 14397740.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.165998649597168,
|
|
"epoch": 0.6146515783204288,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004972138550754405,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.17828192561864853,
|
|
"num_tokens": 14412850.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.283820867538452,
|
|
"epoch": 0.6152471709350804,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972071658761254,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.17418527901172637,
|
|
"num_tokens": 14426174.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.180602645874023,
|
|
"epoch": 0.615842763549732,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004972004687066005,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.17746622115373611,
|
|
"num_tokens": 14442736.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.238783740997315,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004971937635671061,
|
|
"loss": 5.1518,
|
|
"mean_token_accuracy": 0.18061379194259644,
|
|
"num_tokens": 14459631.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.174577760696411,
|
|
"epoch": 0.6170339487790352,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004971870504578825,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.18387468308210372,
|
|
"num_tokens": 14472896.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.129262018203735,
|
|
"epoch": 0.6176295413936868,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971803293791708,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.1779097333550453,
|
|
"num_tokens": 14487959.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.0543663024902346,
|
|
"epoch": 0.6182251340083383,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004971736003312119,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.1908903881907463,
|
|
"num_tokens": 14501420.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.156183433532715,
|
|
"epoch": 0.6188207266229899,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004971668633142472,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.18705689162015915,
|
|
"num_tokens": 14514800.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.247159814834594,
|
|
"epoch": 0.6194163192376414,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004971601183285183,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.1762465715408325,
|
|
"num_tokens": 14530254.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.254759407043457,
|
|
"epoch": 0.620011911852293,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004971533653742672,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.17780477404594422,
|
|
"num_tokens": 14545635.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.154357194900513,
|
|
"epoch": 0.6206075044669446,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497146604451736,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.17536162137985228,
|
|
"num_tokens": 14558672.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.10100908279419,
|
|
"epoch": 0.6212030970815962,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971398355611674,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.18515998721122742,
|
|
"num_tokens": 14571706.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.225375127792359,
|
|
"epoch": 0.6217986896962477,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000497133058702804,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.18573766350746154,
|
|
"num_tokens": 14584732.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.207407903671265,
|
|
"epoch": 0.6223942823108993,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497126273876889,
|
|
"loss": 5.1158,
|
|
"mean_token_accuracy": 0.1808028057217598,
|
|
"num_tokens": 14598883.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.149447917938232,
|
|
"epoch": 0.6229898749255509,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004971194810836657,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.18023434430360794,
|
|
"num_tokens": 14613202.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.302868604660034,
|
|
"epoch": 0.6235854675402025,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971126803233778,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.17348726242780685,
|
|
"num_tokens": 14627267.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.209963178634643,
|
|
"epoch": 0.6241810601548541,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004971058715962691,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.17819032818078995,
|
|
"num_tokens": 14640300.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.169673776626587,
|
|
"epoch": 0.6247766527695057,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497099054902584,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.1778849333524704,
|
|
"num_tokens": 14655029.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.257773923873901,
|
|
"epoch": 0.6253722453841573,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004970922302425669,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.1825217917561531,
|
|
"num_tokens": 14669321.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.113165426254272,
|
|
"epoch": 0.6259678379988088,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004970853976164624,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.18621155619621277,
|
|
"num_tokens": 14682280.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.1739335536956785,
|
|
"epoch": 0.6265634306134604,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000497078557024516,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.18658248484134674,
|
|
"num_tokens": 14693761.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.252684688568115,
|
|
"epoch": 0.627159023228112,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004970717084669728,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.18066257536411284,
|
|
"num_tokens": 14706024.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.153377199172974,
|
|
"epoch": 0.6277546158427636,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004970648519440785,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.17712539732456206,
|
|
"num_tokens": 14721273.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.112338876724243,
|
|
"epoch": 0.6283502084574152,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004970579874560789,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.1767741098999977,
|
|
"num_tokens": 14737033.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.233368682861328,
|
|
"epoch": 0.6289458010720667,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004970511150032205,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.1839930906891823,
|
|
"num_tokens": 14751881.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.161387538909912,
|
|
"epoch": 0.6295413936867182,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004970442345857495,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.18435181230306624,
|
|
"num_tokens": 14764866.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.223604345321656,
|
|
"epoch": 0.6301369863013698,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004970373462039128,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.18571309000253677,
|
|
"num_tokens": 14777703.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.195456457138062,
|
|
"epoch": 0.6307325789160214,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004970304498579576,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.18478434383869172,
|
|
"num_tokens": 14792819.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.0047344207763675,
|
|
"epoch": 0.631328171530673,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004970235455481312,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.18484549075365067,
|
|
"num_tokens": 14806612.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.142909812927246,
|
|
"epoch": 0.6319237641453246,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004970166332746811,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.19029434621334076,
|
|
"num_tokens": 14820313.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.254210805892944,
|
|
"epoch": 0.6325193567599762,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004970097130378554,
|
|
"loss": 5.1669,
|
|
"mean_token_accuracy": 0.1831810712814331,
|
|
"num_tokens": 14832874.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.1873694896698,
|
|
"epoch": 0.6331149493746278,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004970027848379023,
|
|
"loss": 5.1596,
|
|
"mean_token_accuracy": 0.18021899759769439,
|
|
"num_tokens": 14845021.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.278657007217407,
|
|
"epoch": 0.6337105419892793,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004969958486750702,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.178573277592659,
|
|
"num_tokens": 14860928.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.1841010570526125,
|
|
"epoch": 0.6343061346039309,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000496988904549608,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.18640349358320235,
|
|
"num_tokens": 14874709.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.1552544116973875,
|
|
"epoch": 0.6349017272185825,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004969819524617647,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.17232930809259414,
|
|
"num_tokens": 14888323.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.1758991241455075,
|
|
"epoch": 0.6354973198332341,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969749924117896,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.17781804203987123,
|
|
"num_tokens": 14901410.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.177754688262939,
|
|
"epoch": 0.6360929124478857,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004969680243999325,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.1807839885354042,
|
|
"num_tokens": 14915335.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.220339679718018,
|
|
"epoch": 0.6366885050625373,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004969610484264433,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.17709024995565414,
|
|
"num_tokens": 14931549.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.138054037094117,
|
|
"epoch": 0.6372840976771889,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004969540644915721,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.1849476382136345,
|
|
"num_tokens": 14943745.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.202829360961914,
|
|
"epoch": 0.6378796902918403,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004969470725955695,
|
|
"loss": 5.1845,
|
|
"mean_token_accuracy": 0.17944231480360032,
|
|
"num_tokens": 14957662.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.210152578353882,
|
|
"epoch": 0.6384752829064919,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004969400727386864,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.1791303649544716,
|
|
"num_tokens": 14970175.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.209267902374267,
|
|
"epoch": 0.6390708755211435,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004969330649211737,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.17758345305919648,
|
|
"num_tokens": 14983901.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.301709842681885,
|
|
"epoch": 0.6396664681357951,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004969260491432826,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.1800248682498932,
|
|
"num_tokens": 14997637.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.1487464427948,
|
|
"epoch": 0.6402620607504467,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969190254052651,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.1714664578437805,
|
|
"num_tokens": 15014576.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.21416745185852,
|
|
"epoch": 0.6408576533650983,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004969119937073731,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.17964652478694915,
|
|
"num_tokens": 15031049.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.100450086593628,
|
|
"epoch": 0.6414532459797498,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004969049540498585,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.18261099755764007,
|
|
"num_tokens": 15044632.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.098171186447144,
|
|
"epoch": 0.6420488385944014,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004968979064329741,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.18239010572433473,
|
|
"num_tokens": 15057500.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.215753507614136,
|
|
"epoch": 0.642644431209053,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004968908508569725,
|
|
"loss": 5.1329,
|
|
"mean_token_accuracy": 0.1840141847729683,
|
|
"num_tokens": 15070994.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.122771120071411,
|
|
"epoch": 0.6432400238237046,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968837873221069,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.17668900787830352,
|
|
"num_tokens": 15085824.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.16472601890564,
|
|
"epoch": 0.6438356164383562,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004968767158286306,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.18158290684223174,
|
|
"num_tokens": 15101263.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.185609960556031,
|
|
"epoch": 0.6444312090530078,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004968696363767972,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.18943183720111847,
|
|
"num_tokens": 15113830.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.201430797576904,
|
|
"epoch": 0.6450268016676594,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004968625489668607,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.17698225229978562,
|
|
"num_tokens": 15128427.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.130856704711914,
|
|
"epoch": 0.6456223942823109,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004968554535990754,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.1890598490834236,
|
|
"num_tokens": 15143790.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.159629869461059,
|
|
"epoch": 0.6462179868969625,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968483502736956,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.18111879527568817,
|
|
"num_tokens": 15157533.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.133475875854492,
|
|
"epoch": 0.646813579511614,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004968412389909762,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.18462124168872834,
|
|
"num_tokens": 15172164.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.157847261428833,
|
|
"epoch": 0.6474091721262656,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004968341197511722,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.19217817336320878,
|
|
"num_tokens": 15184334.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.121783304214477,
|
|
"epoch": 0.6480047647409172,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004968269925545391,
|
|
"loss": 5.0759,
|
|
"mean_token_accuracy": 0.18414950072765351,
|
|
"num_tokens": 15198783.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.121270561218262,
|
|
"epoch": 0.6486003573555688,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968198574013323,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.18392328768968583,
|
|
"num_tokens": 15214153.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.239373111724854,
|
|
"epoch": 0.6491959499702203,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004968127142918081,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.17513516843318938,
|
|
"num_tokens": 15229029.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.144827508926392,
|
|
"epoch": 0.6497915425848719,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004968055632262223,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.1799148827791214,
|
|
"num_tokens": 15244724.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.1620079517364506,
|
|
"epoch": 0.6503871351995235,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967984042048317,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.18069817274808883,
|
|
"num_tokens": 15258703.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.330232572555542,
|
|
"epoch": 0.6509827278141751,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004967912372278928,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.17098044604063034,
|
|
"num_tokens": 15272281.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.17631573677063,
|
|
"epoch": 0.6515783204288267,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000496784062295663,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.18606678098440171,
|
|
"num_tokens": 15286657.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.166531085968018,
|
|
"epoch": 0.6521739130434783,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004967768794083994,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.17764725685119628,
|
|
"num_tokens": 15300416.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.1798773288726805,
|
|
"epoch": 0.6527695056581299,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004967696885663597,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.18333374410867692,
|
|
"num_tokens": 15313945.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.098284816741943,
|
|
"epoch": 0.6533650982727814,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000496762489769802,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.18641230911016465,
|
|
"num_tokens": 15328995.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.128042793273925,
|
|
"epoch": 0.653960690887433,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004967552830189842,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.1825200602412224,
|
|
"num_tokens": 15342588.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.157743310928344,
|
|
"epoch": 0.6545562835020846,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004967480683141651,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.18709973692893983,
|
|
"num_tokens": 15357411.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.068438482284546,
|
|
"epoch": 0.6551518761167362,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000496740845655603,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.18810683339834214,
|
|
"num_tokens": 15371968.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.175538635253906,
|
|
"epoch": 0.6557474687313878,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004967336150435576,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.1795051634311676,
|
|
"num_tokens": 15387186.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.133205509185791,
|
|
"epoch": 0.6563430613460393,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004967263764782878,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.18769401907920838,
|
|
"num_tokens": 15398842.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.109816312789917,
|
|
"epoch": 0.6569386539606908,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004967191299600535,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.18342134356498718,
|
|
"num_tokens": 15411687.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.096859502792358,
|
|
"epoch": 0.6575342465753424,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004967118754891144,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.18985231071710587,
|
|
"num_tokens": 15425868.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.219020128250122,
|
|
"epoch": 0.658129839189994,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967046130657309,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.1717542976140976,
|
|
"num_tokens": 15439489.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.217660856246948,
|
|
"epoch": 0.6587254318046456,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004966973426901634,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.18219080865383147,
|
|
"num_tokens": 15453067.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.089633417129517,
|
|
"epoch": 0.6593210244192972,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966900643626726,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.1899539679288864,
|
|
"num_tokens": 15465357.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.145211791992187,
|
|
"epoch": 0.6599166170339488,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966827780835197,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.1858248844742775,
|
|
"num_tokens": 15479657.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.397228479385376,
|
|
"epoch": 0.6605122096486004,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966754838529659,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.16885491609573364,
|
|
"num_tokens": 15495245.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.164352464675903,
|
|
"epoch": 0.6611078022632519,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000496668181671273,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.18535182774066924,
|
|
"num_tokens": 15507788.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.18265929222107,
|
|
"epoch": 0.6617033948779035,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004966608715387029,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.17673799991607667,
|
|
"num_tokens": 15521970.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.159046030044555,
|
|
"epoch": 0.6622989874925551,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004966535534555175,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.18454302996397018,
|
|
"num_tokens": 15534720.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.1024768352508545,
|
|
"epoch": 0.6628945801072067,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004966462274219797,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.1810507744550705,
|
|
"num_tokens": 15549345.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.305191707611084,
|
|
"epoch": 0.6634901727218583,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000496638893438352,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.18325956612825395,
|
|
"num_tokens": 15562838.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.220038747787475,
|
|
"epoch": 0.6640857653365099,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004966315515048977,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.18733064234256744,
|
|
"num_tokens": 15575044.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.103044939041138,
|
|
"epoch": 0.6646813579511615,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004966242016218799,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.18513426482677459,
|
|
"num_tokens": 15591912.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.2108512878417965,
|
|
"epoch": 0.6652769505658129,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004966168437895624,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.1800141379237175,
|
|
"num_tokens": 15606903.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.1230498313903805,
|
|
"epoch": 0.6658725431804645,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004966094780082089,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.1888783797621727,
|
|
"num_tokens": 15620885.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.213608169555664,
|
|
"epoch": 0.6664681357951161,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004966021042780837,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.1805955573916435,
|
|
"num_tokens": 15634927.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.148025608062744,
|
|
"epoch": 0.6670637284097677,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004965947225994516,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.181685009598732,
|
|
"num_tokens": 15649369.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.153276586532593,
|
|
"epoch": 0.6676593210244193,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004965873329725769,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.17707206904888154,
|
|
"num_tokens": 15665288.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.17413182258606,
|
|
"epoch": 0.6682549136390709,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004965799353977248,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.18647549748420716,
|
|
"num_tokens": 15679117.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.098924398422241,
|
|
"epoch": 0.6688505062537224,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004965725298751608,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.19048406332731246,
|
|
"num_tokens": 15692177.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.220395851135254,
|
|
"epoch": 0.669446098868374,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004965651164051504,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.1871796056628227,
|
|
"num_tokens": 15706047.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.163528823852539,
|
|
"epoch": 0.6700416914830256,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004965576949879594,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.17980898469686507,
|
|
"num_tokens": 15721191.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.2103180408477785,
|
|
"epoch": 0.6706372840976772,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004965502656238543,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.1773851826786995,
|
|
"num_tokens": 15735569.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.139539957046509,
|
|
"epoch": 0.6712328767123288,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004965428283131013,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.1858354926109314,
|
|
"num_tokens": 15749125.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.070421934127808,
|
|
"epoch": 0.6718284693269804,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004965353830559671,
|
|
"loss": 5.0858,
|
|
"mean_token_accuracy": 0.18898898214101792,
|
|
"num_tokens": 15765641.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.234346342086792,
|
|
"epoch": 0.672424061941632,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004965279298527192,
|
|
"loss": 5.1501,
|
|
"mean_token_accuracy": 0.17766165137290954,
|
|
"num_tokens": 15780816.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.263462162017822,
|
|
"epoch": 0.6730196545562835,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004965204687036244,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.17181509733200073,
|
|
"num_tokens": 15795123.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.139407539367676,
|
|
"epoch": 0.6736152471709351,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004965129996089507,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.18693562895059584,
|
|
"num_tokens": 15808428.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.178461742401123,
|
|
"epoch": 0.6742108397855867,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004965055225689658,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.1720685437321663,
|
|
"num_tokens": 15820618.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.150962066650391,
|
|
"epoch": 0.6748064324002382,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004964980375839379,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.18664471060037613,
|
|
"num_tokens": 15833431.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.156425619125367,
|
|
"epoch": 0.6754020250148898,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004964905446541355,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.18924424946308135,
|
|
"num_tokens": 15845629.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.228535842895508,
|
|
"epoch": 0.6759976176295414,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004964830437798276,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.17730524241924286,
|
|
"num_tokens": 15859464.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.068280935287476,
|
|
"epoch": 0.6765932102441929,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004964755349612829,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.19303703904151917,
|
|
"num_tokens": 15873207.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.149933481216431,
|
|
"epoch": 0.6771888028588445,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004964680181987709,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.18508615344762802,
|
|
"num_tokens": 15888856.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.115545034408569,
|
|
"epoch": 0.6777843954734961,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000496460493492561,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.19292995035648347,
|
|
"num_tokens": 15901841.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.1422912120819095,
|
|
"epoch": 0.6783799880881477,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004964529608429234,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.18390501141548157,
|
|
"num_tokens": 15914960.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.111570596694946,
|
|
"epoch": 0.6789755807027993,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004964454202501282,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.18615592867136002,
|
|
"num_tokens": 15929466.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.245803546905518,
|
|
"epoch": 0.6795711733174509,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004964378717144458,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.18130764216184617,
|
|
"num_tokens": 15943934.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.166830587387085,
|
|
"epoch": 0.6801667659321025,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000496430315236147,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.19243866503238677,
|
|
"num_tokens": 15956214.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.177258062362671,
|
|
"epoch": 0.680762358546754,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004964227508155027,
|
|
"loss": 5.0682,
|
|
"mean_token_accuracy": 0.17956816107034684,
|
|
"num_tokens": 15970943.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.202236700057983,
|
|
"epoch": 0.6813579511614056,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964151784527844,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.18135780841112137,
|
|
"num_tokens": 15985539.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.129438209533691,
|
|
"epoch": 0.6819535437760572,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004964075981482637,
|
|
"loss": 5.0097,
|
|
"mean_token_accuracy": 0.19469093531370163,
|
|
"num_tokens": 15998622.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.114571523666382,
|
|
"epoch": 0.6825491363907088,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964000099022124,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.18817032426595687,
|
|
"num_tokens": 16013820.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.301574420928955,
|
|
"epoch": 0.6831447290053604,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004963924137149027,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.1722538262605667,
|
|
"num_tokens": 16026615.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.19732084274292,
|
|
"epoch": 0.6837403216200119,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004963848095866072,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.1782216399908066,
|
|
"num_tokens": 16039921.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.062488651275634,
|
|
"epoch": 0.6843359142346634,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004963771975175984,
|
|
"loss": 4.9806,
|
|
"mean_token_accuracy": 0.1878690540790558,
|
|
"num_tokens": 16054790.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.120508003234863,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004963695775081495,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.17732814997434615,
|
|
"num_tokens": 16069778.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.115518808364868,
|
|
"epoch": 0.6855270994639666,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004963619495585338,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.1849559187889099,
|
|
"num_tokens": 16086472.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.178507661819458,
|
|
"epoch": 0.6861226920786182,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963543136690247,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.18223277479410172,
|
|
"num_tokens": 16100743.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.117795991897583,
|
|
"epoch": 0.6867182846932698,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004963466698398965,
|
|
"loss": 5.0354,
|
|
"mean_token_accuracy": 0.18542540967464446,
|
|
"num_tokens": 16114894.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.167334699630738,
|
|
"epoch": 0.6873138773079214,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004963390180714231,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.18793819099664688,
|
|
"num_tokens": 16129232.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.1699402809143065,
|
|
"epoch": 0.687909469922573,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000496331358363879,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.1860453188419342,
|
|
"num_tokens": 16142983.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.165724754333496,
|
|
"epoch": 0.6885050625372245,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004963236907175388,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.1789120689034462,
|
|
"num_tokens": 16157195.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.1641686916351315,
|
|
"epoch": 0.6891006551518761,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004963160151326778,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.18177830874919892,
|
|
"num_tokens": 16171240.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.254708337783813,
|
|
"epoch": 0.6896962477665277,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963083316095712,
|
|
"loss": 5.14,
|
|
"mean_token_accuracy": 0.17941446602344513,
|
|
"num_tokens": 16186313.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.146623039245606,
|
|
"epoch": 0.6902918403811793,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004963006401484945,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.1801187738776207,
|
|
"num_tokens": 16201394.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.111140251159668,
|
|
"epoch": 0.6908874329958309,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004962929407497236,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.19007892310619354,
|
|
"num_tokens": 16214917.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.134295129776001,
|
|
"epoch": 0.6914830256104825,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004962852334135348,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.1908194899559021,
|
|
"num_tokens": 16228700.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.105864858627319,
|
|
"epoch": 0.6920786182251341,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004962775181402044,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.1943821981549263,
|
|
"num_tokens": 16240262.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.134650564193725,
|
|
"epoch": 0.6926742108397855,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004962697949300093,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.189499332010746,
|
|
"num_tokens": 16254830.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.081654644012451,
|
|
"epoch": 0.6932698034544371,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004962620637832263,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.1968621477484703,
|
|
"num_tokens": 16267547.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.050497102737427,
|
|
"epoch": 0.6938653960690887,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004962543247001329,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.1884341225028038,
|
|
"num_tokens": 16281223.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.206281566619873,
|
|
"epoch": 0.6944609886837403,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004962465776810066,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.18201261311769484,
|
|
"num_tokens": 16295366.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.214591789245605,
|
|
"epoch": 0.6950565812983919,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962388227261253,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.1824623629450798,
|
|
"num_tokens": 16310081.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.230112886428833,
|
|
"epoch": 0.6956521739130435,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004962310598357672,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.17705531120300294,
|
|
"num_tokens": 16324544.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.263324642181397,
|
|
"epoch": 0.696247766527695,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004962232890102106,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.18482587933540345,
|
|
"num_tokens": 16339128.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.152918958663941,
|
|
"epoch": 0.6968433591423466,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004962155102497342,
|
|
"loss": 5.023,
|
|
"mean_token_accuracy": 0.1903870552778244,
|
|
"num_tokens": 16351997.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.074641704559326,
|
|
"epoch": 0.6974389517569982,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004962077235546173,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.19519052505493165,
|
|
"num_tokens": 16365075.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.167453241348267,
|
|
"epoch": 0.6980345443716498,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004961999289251389,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.1929730921983719,
|
|
"num_tokens": 16378635.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.098785448074341,
|
|
"epoch": 0.6986301369863014,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004961921263615788,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.19139465540647507,
|
|
"num_tokens": 16392224.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.071713876724243,
|
|
"epoch": 0.699225729600953,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004961843158642167,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.18802954256534576,
|
|
"num_tokens": 16407830.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.086405849456787,
|
|
"epoch": 0.6998213222156046,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004961764974333328,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.1887590393424034,
|
|
"num_tokens": 16421576.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.2013884544372555,
|
|
"epoch": 0.7004169148302561,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961686710692076,
|
|
"loss": 5.1326,
|
|
"mean_token_accuracy": 0.18628792315721512,
|
|
"num_tokens": 16436548.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.150346040725708,
|
|
"epoch": 0.7010125074449077,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004961608367721217,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.18267455846071243,
|
|
"num_tokens": 16451435.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.213262128829956,
|
|
"epoch": 0.7016081000595593,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004961529945423563,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.17726118266582488,
|
|
"num_tokens": 16465786.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.200294923782349,
|
|
"epoch": 0.7022036926742108,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004961451443801924,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.18139133155345916,
|
|
"num_tokens": 16479832.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.147436332702637,
|
|
"epoch": 0.7027992852888624,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004961372862859119,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.19274667650461197,
|
|
"num_tokens": 16491824.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.187462663650512,
|
|
"epoch": 0.703394877903514,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004961294202597962,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.18546834141016005,
|
|
"num_tokens": 16507273.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.14963846206665,
|
|
"epoch": 0.7039904705181655,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004961215463021281,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.1835980609059334,
|
|
"num_tokens": 16521041.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.131033086776734,
|
|
"epoch": 0.7045860631328171,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004961136644131894,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.19261125922203065,
|
|
"num_tokens": 16534837.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.186826753616333,
|
|
"epoch": 0.7051816557474687,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004961057745932633,
|
|
"loss": 5.1164,
|
|
"mean_token_accuracy": 0.1856675922870636,
|
|
"num_tokens": 16549183.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.132089614868164,
|
|
"epoch": 0.7057772483621203,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004960978768426323,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.1863751456141472,
|
|
"num_tokens": 16562044.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.208128499984741,
|
|
"epoch": 0.7063728409767719,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049608997116158,
|
|
"loss": 5.1614,
|
|
"mean_token_accuracy": 0.18353822380304335,
|
|
"num_tokens": 16577014.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.171472263336182,
|
|
"epoch": 0.7069684335914235,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049608205755039,
|
|
"loss": 5.0533,
|
|
"mean_token_accuracy": 0.19414664357900618,
|
|
"num_tokens": 16588289.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.095102596282959,
|
|
"epoch": 0.7075640262060751,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004960741360093459,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.1807206839323044,
|
|
"num_tokens": 16602433.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.241059827804565,
|
|
"epoch": 0.7081596188207266,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004960662065387322,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.17793085426092148,
|
|
"num_tokens": 16618178.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.224620580673218,
|
|
"epoch": 0.7087552114353782,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496058269138833,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.1857418179512024,
|
|
"num_tokens": 16634090.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.103030395507813,
|
|
"epoch": 0.7093508040500298,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004960503238099331,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.18988511562347413,
|
|
"num_tokens": 16646713.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.135226011276245,
|
|
"epoch": 0.7099463966646814,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004960423705523175,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.18603692203760147,
|
|
"num_tokens": 16659172.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.174362993240356,
|
|
"epoch": 0.710541989279333,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960344093662714,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.18120039701461793,
|
|
"num_tokens": 16672592.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.198557806015015,
|
|
"epoch": 0.7111375818939845,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004960264402520804,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.18150104731321334,
|
|
"num_tokens": 16687026.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.083840990066529,
|
|
"epoch": 0.711733174508636,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004960184632100304,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.19775885045528413,
|
|
"num_tokens": 16699489.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.1341643810272215,
|
|
"epoch": 0.7123287671232876,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004960104782404075,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.18620463758707045,
|
|
"num_tokens": 16713821.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.189363145828247,
|
|
"epoch": 0.7129243597379392,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960024853434982,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.1814249724149704,
|
|
"num_tokens": 16727271.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.165784311294556,
|
|
"epoch": 0.7135199523525908,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000495994484519589,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.18650438040494918,
|
|
"num_tokens": 16740387.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.078182363510132,
|
|
"epoch": 0.7141155449672424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959864757689669,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.1841212496161461,
|
|
"num_tokens": 16756131.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.148395252227783,
|
|
"epoch": 0.714711137581894,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959784590919192,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.18915590792894363,
|
|
"num_tokens": 16768781.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.714711137581894,
|
|
"eval_entropy": 5.013815109258909,
|
|
"eval_loss": 5.054040431976318,
|
|
"eval_mean_token_accuracy": 0.19505963621655228,
|
|
"eval_num_tokens": 16768781.0,
|
|
"eval_runtime": 24.626,
|
|
"eval_samples_per_second": 1036.017,
|
|
"eval_steps_per_second": 129.538,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.193441486358642,
|
|
"epoch": 0.7153067301965456,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004959704344887335,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.1790403112769127,
|
|
"num_tokens": 16782933.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.115491056442261,
|
|
"epoch": 0.7159023228111971,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959624019596976,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.19006347358226777,
|
|
"num_tokens": 16795999.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.188798236846924,
|
|
"epoch": 0.7164979154258487,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004959543615050996,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.18514799922704697,
|
|
"num_tokens": 16809042.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.1404726028442385,
|
|
"epoch": 0.7170935080405003,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004959463131252278,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.18235979229211807,
|
|
"num_tokens": 16820896.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.154704570770264,
|
|
"epoch": 0.7176891006551519,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004959382568203711,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.1825295001268387,
|
|
"num_tokens": 16834418.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.092682790756226,
|
|
"epoch": 0.7182846932698035,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959301925908184,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.18695866018533708,
|
|
"num_tokens": 16848818.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.1724752426147464,
|
|
"epoch": 0.7188802858844551,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004959221204368588,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.18239349126815796,
|
|
"num_tokens": 16863145.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.192418193817138,
|
|
"epoch": 0.7194758784991067,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004959140403587819,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.18186245411634444,
|
|
"num_tokens": 16876342.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.194745254516602,
|
|
"epoch": 0.7200714711137582,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004959059523568778,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.1777186244726181,
|
|
"num_tokens": 16892113.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.199955224990845,
|
|
"epoch": 0.7206670637284097,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004958978564314361,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.17914552241563797,
|
|
"num_tokens": 16906103.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.138527774810791,
|
|
"epoch": 0.7212626563430613,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004958897525827476,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.18429365158081054,
|
|
"num_tokens": 16921655.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.141930675506591,
|
|
"epoch": 0.7218582489577129,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004958816408111027,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.1855818048119545,
|
|
"num_tokens": 16936143.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.058515167236328,
|
|
"epoch": 0.7224538415723645,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004958735211167926,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.18901057541370392,
|
|
"num_tokens": 16950232.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.122758245468139,
|
|
"epoch": 0.7230494341870161,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004958653935001083,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.19119074642658235,
|
|
"num_tokens": 16963407.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.126193618774414,
|
|
"epoch": 0.7236450268016676,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004958572579613415,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.19106634706258774,
|
|
"num_tokens": 16975758.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.149709844589234,
|
|
"epoch": 0.7242406194163192,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000495849114500784,
|
|
"loss": 5.058,
|
|
"mean_token_accuracy": 0.19249855130910873,
|
|
"num_tokens": 16989496.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.198471975326538,
|
|
"epoch": 0.7248362120309708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004958409631187278,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.18142579048871993,
|
|
"num_tokens": 17002790.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.21793565750122,
|
|
"epoch": 0.7254318046456224,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004958328038154652,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.1873983472585678,
|
|
"num_tokens": 17016384.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.1530517578125,
|
|
"epoch": 0.726027397260274,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004958246365912891,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.1922671914100647,
|
|
"num_tokens": 17031331.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.157634162902832,
|
|
"epoch": 0.7266229898749256,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004958164614464923,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.18183269202709199,
|
|
"num_tokens": 17043820.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.056698942184449,
|
|
"epoch": 0.7272185824895772,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.19559904038906098,
|
|
"num_tokens": 17057826.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.143988990783692,
|
|
"epoch": 0.7278141751042287,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004958000873962099,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.18169133216142655,
|
|
"num_tokens": 17073410.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.148937368392945,
|
|
"epoch": 0.7284097677188803,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004957918884913115,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.18738909512758256,
|
|
"num_tokens": 17086705.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.1849898338317875,
|
|
"epoch": 0.7290053603335319,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004957836816669672,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.1809255987405777,
|
|
"num_tokens": 17100787.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.161887454986572,
|
|
"epoch": 0.7296009529481834,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004957754669234711,
|
|
"loss": 5.0734,
|
|
"mean_token_accuracy": 0.18783474564552308,
|
|
"num_tokens": 17116381.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.052583312988281,
|
|
"epoch": 0.730196545562835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000495767244261118,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.1947282463312149,
|
|
"num_tokens": 17129214.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.209374666213989,
|
|
"epoch": 0.7307921381774866,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004957590136802028,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.18653339445590972,
|
|
"num_tokens": 17143033.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.10239086151123,
|
|
"epoch": 0.7313877307921381,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004957507751810207,
|
|
"loss": 5.023,
|
|
"mean_token_accuracy": 0.18617512732744218,
|
|
"num_tokens": 17156325.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.174205589294433,
|
|
"epoch": 0.7319833234067897,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004957425287638673,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.18414744436740876,
|
|
"num_tokens": 17173031.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.15957989692688,
|
|
"epoch": 0.7325789160214413,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004957342744290381,
|
|
"loss": 5.0803,
|
|
"mean_token_accuracy": 0.17955523282289504,
|
|
"num_tokens": 17186579.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.044646263122559,
|
|
"epoch": 0.7331745086360929,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004957260121768296,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.19375538676977158,
|
|
"num_tokens": 17200987.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.149649238586425,
|
|
"epoch": 0.7337701012507445,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004957177420075377,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.1935843512415886,
|
|
"num_tokens": 17215429.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.111565065383911,
|
|
"epoch": 0.7343656938653961,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004957094639214594,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.19057456403970718,
|
|
"num_tokens": 17229460.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.139765977859497,
|
|
"epoch": 0.7349612864800477,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004957011779188915,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.18866951167583465,
|
|
"num_tokens": 17243399.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.008938360214233,
|
|
"epoch": 0.7355568790946992,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004956928840001312,
|
|
"loss": 4.9462,
|
|
"mean_token_accuracy": 0.194428913295269,
|
|
"num_tokens": 17258028.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.069272422790528,
|
|
"epoch": 0.7361524717093508,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004956845821654758,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.19180883467197418,
|
|
"num_tokens": 17271666.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.241506671905517,
|
|
"epoch": 0.7367480643240024,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004956762724152234,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.17708930224180222,
|
|
"num_tokens": 17285423.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.180853366851807,
|
|
"epoch": 0.737343656938654,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004956679547496719,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.18059624433517457,
|
|
"num_tokens": 17299134.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.198074293136597,
|
|
"epoch": 0.7379392495533056,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004956596291691197,
|
|
"loss": 5.1383,
|
|
"mean_token_accuracy": 0.1837226167321205,
|
|
"num_tokens": 17311835.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.1668023586273195,
|
|
"epoch": 0.7385348421679571,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004956512956738652,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.18435196578502655,
|
|
"num_tokens": 17324943.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.121694421768188,
|
|
"epoch": 0.7391304347826086,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004956429542642075,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.1715490698814392,
|
|
"num_tokens": 17339710.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.225850820541382,
|
|
"epoch": 0.7397260273972602,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004956346049404459,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.18651323020458221,
|
|
"num_tokens": 17353391.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.162018299102783,
|
|
"epoch": 0.7403216200119118,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004956262477028797,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.18440537601709367,
|
|
"num_tokens": 17367811.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.141384792327881,
|
|
"epoch": 0.7409172126265634,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956178825518087,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.19215934425592424,
|
|
"num_tokens": 17380323.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.151019287109375,
|
|
"epoch": 0.741512805241215,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004956095094875329,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.19675270318984986,
|
|
"num_tokens": 17394650.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.137577724456787,
|
|
"epoch": 0.7421083978558666,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004956011285103528,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.19083491414785386,
|
|
"num_tokens": 17408461.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.162902116775513,
|
|
"epoch": 0.7427039904705182,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004955927396205689,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.18499673157930374,
|
|
"num_tokens": 17422086.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.147048807144165,
|
|
"epoch": 0.7432995830851697,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000495584342818482,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.19537004977464675,
|
|
"num_tokens": 17436845.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.054245519638061,
|
|
"epoch": 0.7438951756998213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004955759381043934,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.18674032539129257,
|
|
"num_tokens": 17451783.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.236276721954345,
|
|
"epoch": 0.7444907683144729,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004955675254786045,
|
|
"loss": 5.2844,
|
|
"mean_token_accuracy": 0.17241936326026916,
|
|
"num_tokens": 17466310.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.159708547592163,
|
|
"epoch": 0.7450863609291245,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004955591049414171,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.18829360455274582,
|
|
"num_tokens": 17481595.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.157144784927368,
|
|
"epoch": 0.7456819535437761,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004955506764931332,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.1893065720796585,
|
|
"num_tokens": 17496947.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.110296297073364,
|
|
"epoch": 0.7462775461584277,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004955422401340553,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.189514821767807,
|
|
"num_tokens": 17509772.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.15053973197937,
|
|
"epoch": 0.7468731387730793,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004955337958644857,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.18902104943990708,
|
|
"num_tokens": 17522819.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.175016117095947,
|
|
"epoch": 0.7474687313877308,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004955253436847273,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.18742719292640686,
|
|
"num_tokens": 17536524.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.14547209739685,
|
|
"epoch": 0.7480643240023823,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004955168835950835,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.18980516195297242,
|
|
"num_tokens": 17549033.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.142885637283325,
|
|
"epoch": 0.7486599166170339,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004955084155958576,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.18651102036237716,
|
|
"num_tokens": 17562615.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.14340124130249,
|
|
"epoch": 0.7492555092316855,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004954999396873534,
|
|
"loss": 4.9809,
|
|
"mean_token_accuracy": 0.18617075830698013,
|
|
"num_tokens": 17576388.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.049432849884033,
|
|
"epoch": 0.7498511018463371,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004954914558698748,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.1930848941206932,
|
|
"num_tokens": 17588275.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.087641048431396,
|
|
"epoch": 0.7504466944609887,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004954829641437261,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.18823176473379136,
|
|
"num_tokens": 17601534.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.137945222854614,
|
|
"epoch": 0.7510422870756402,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004954744645092121,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.19069733321666718,
|
|
"num_tokens": 17614801.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.099888706207276,
|
|
"epoch": 0.7516378796902918,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004954659569666375,
|
|
"loss": 4.9643,
|
|
"mean_token_accuracy": 0.20073682963848113,
|
|
"num_tokens": 17628056.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.137530755996704,
|
|
"epoch": 0.7522334723049434,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004954574415163075,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.18275633305311204,
|
|
"num_tokens": 17642676.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.147878789901734,
|
|
"epoch": 0.752829064919595,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004954489181585275,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.18779446482658385,
|
|
"num_tokens": 17655911.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.0864519596099855,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004954403868936032,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.18275066167116166,
|
|
"num_tokens": 17669386.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.208632850646973,
|
|
"epoch": 0.7540202501488982,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004954318477218406,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.18981702327728273,
|
|
"num_tokens": 17683426.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.241774988174439,
|
|
"epoch": 0.7546158427635498,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000495423300643546,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.1738034278154373,
|
|
"num_tokens": 17697188.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.189122438430786,
|
|
"epoch": 0.7552114353782013,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004954147456590262,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.187900909781456,
|
|
"num_tokens": 17711302.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.154025077819824,
|
|
"epoch": 0.7558070279928529,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004954061827685877,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.18611872047185898,
|
|
"num_tokens": 17725173.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.135112285614014,
|
|
"epoch": 0.7564026206075045,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953976119725378,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.17925739288330078,
|
|
"num_tokens": 17740770.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.14046425819397,
|
|
"epoch": 0.756998213222156,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953890332711839,
|
|
"loss": 5.0554,
|
|
"mean_token_accuracy": 0.18648056834936141,
|
|
"num_tokens": 17754077.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.1745997905731205,
|
|
"epoch": 0.7575938058368076,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004953804466648337,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.18792295306921006,
|
|
"num_tokens": 17768572.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.137367296218872,
|
|
"epoch": 0.7581893984514592,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004953718521537952,
|
|
"loss": 5.1068,
|
|
"mean_token_accuracy": 0.1813020408153534,
|
|
"num_tokens": 17783678.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.169736337661743,
|
|
"epoch": 0.7587849910661107,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004953632497383766,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.18250204622745514,
|
|
"num_tokens": 17796453.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.109682941436768,
|
|
"epoch": 0.7593805836807623,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004953546394188867,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.1912486359477043,
|
|
"num_tokens": 17810459.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.085922908782959,
|
|
"epoch": 0.7599761762954139,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000495346021195634,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.18568429052829744,
|
|
"num_tokens": 17822976.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.120298433303833,
|
|
"epoch": 0.7605717689100655,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004953373950689279,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.18646348565816878,
|
|
"num_tokens": 17836842.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.13086462020874,
|
|
"epoch": 0.7611673615247171,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004953287610390775,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.18605746179819108,
|
|
"num_tokens": 17849300.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.138026475906372,
|
|
"epoch": 0.7617629541393687,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004953201191063928,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.19807063788175583,
|
|
"num_tokens": 17862526.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.091169309616089,
|
|
"epoch": 0.7623585467540203,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004953114692711837,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.18819862157106398,
|
|
"num_tokens": 17874895.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.228110933303833,
|
|
"epoch": 0.7629541393686718,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953028115337603,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.17837830483913422,
|
|
"num_tokens": 17888898.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.1803686141967775,
|
|
"epoch": 0.7635497319833234,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004952941458944333,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.1860194444656372,
|
|
"num_tokens": 17902185.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.12270188331604,
|
|
"epoch": 0.764145324597975,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004952854723535134,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.18297204673290252,
|
|
"num_tokens": 17917309.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.208725118637085,
|
|
"epoch": 0.7647409172126266,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004952767909113118,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.18261702209711075,
|
|
"num_tokens": 17931147.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.194628524780273,
|
|
"epoch": 0.7653365098272782,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004952681015681398,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.18325742781162263,
|
|
"num_tokens": 17944792.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.1732690811157225,
|
|
"epoch": 0.7659321024419298,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004952594043243092,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.182292141020298,
|
|
"num_tokens": 17958580.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.159625816345215,
|
|
"epoch": 0.7665276950565812,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004952506991801319,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.18836802393198013,
|
|
"num_tokens": 17972245.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.132342004776001,
|
|
"epoch": 0.7671232876712328,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004952419861359201,
|
|
"loss": 5.0332,
|
|
"mean_token_accuracy": 0.19164235293865203,
|
|
"num_tokens": 17987082.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.168048954010009,
|
|
"epoch": 0.7677188802858844,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004952332651919864,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.18685587495565414,
|
|
"num_tokens": 18001477.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.172272729873657,
|
|
"epoch": 0.768314472900536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004952245363486435,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.18444893956184388,
|
|
"num_tokens": 18014553.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.126869773864746,
|
|
"epoch": 0.7689100655151876,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004952157996062046,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.1870729386806488,
|
|
"num_tokens": 18027454.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.138991403579712,
|
|
"epoch": 0.7695056581298392,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000495207054964983,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.18986473530530928,
|
|
"num_tokens": 18040632.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.106136989593506,
|
|
"epoch": 0.7701012507444908,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004951983024252924,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.20226272344589233,
|
|
"num_tokens": 18053859.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.088018226623535,
|
|
"epoch": 0.7706968433591423,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004951895419874466,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.18779000341892244,
|
|
"num_tokens": 18067734.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.16777606010437,
|
|
"epoch": 0.7712924359737939,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00049518077365176,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.18512145876884462,
|
|
"num_tokens": 18083831.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.153817653656006,
|
|
"epoch": 0.7718880285884455,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495171997418547,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.19527969062328338,
|
|
"num_tokens": 18097085.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.110301828384399,
|
|
"epoch": 0.7724836212030971,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004951632132881225,
|
|
"loss": 4.9937,
|
|
"mean_token_accuracy": 0.19228847175836564,
|
|
"num_tokens": 18111311.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.148785734176636,
|
|
"epoch": 0.7730792138177487,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004951544212608015,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.18610097616910934,
|
|
"num_tokens": 18126622.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.194220352172851,
|
|
"epoch": 0.7736748064324003,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004951456213368994,
|
|
"loss": 5.0983,
|
|
"mean_token_accuracy": 0.18712305575609206,
|
|
"num_tokens": 18138074.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.125834560394287,
|
|
"epoch": 0.7742703990470519,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004951368135167316,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.1892332598567009,
|
|
"num_tokens": 18150865.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.096454048156739,
|
|
"epoch": 0.7748659916617034,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004951279978006143,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.19691172391176223,
|
|
"num_tokens": 18163779.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.058171272277832,
|
|
"epoch": 0.7754615842763549,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004951191741888638,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.18211302608251573,
|
|
"num_tokens": 18177924.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.229700040817261,
|
|
"epoch": 0.7760571768910065,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004951103426817961,
|
|
"loss": 5.1485,
|
|
"mean_token_accuracy": 0.1762078195810318,
|
|
"num_tokens": 18191818.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.182648134231568,
|
|
"epoch": 0.7766527695056581,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004951015032797286,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.18400835990905762,
|
|
"num_tokens": 18205681.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.116304397583008,
|
|
"epoch": 0.7772483621203097,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004950926559829778,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.1831788569688797,
|
|
"num_tokens": 18220420.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.066957426071167,
|
|
"epoch": 0.7778439547349613,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004950838007918615,
|
|
"loss": 4.9748,
|
|
"mean_token_accuracy": 0.19564986675977708,
|
|
"num_tokens": 18233891.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.10734748840332,
|
|
"epoch": 0.7784395473496128,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000495074937706697,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.18927569836378097,
|
|
"num_tokens": 18246671.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.136499643325806,
|
|
"epoch": 0.7790351399642644,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004950660667278023,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.1896110162138939,
|
|
"num_tokens": 18260351.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.080105924606324,
|
|
"epoch": 0.779630732578916,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004950571878554956,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.19243946373462678,
|
|
"num_tokens": 18275475.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.119350004196167,
|
|
"epoch": 0.7802263251935676,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004950483010900953,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.18038942962884902,
|
|
"num_tokens": 18289598.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.127745771408081,
|
|
"epoch": 0.7808219178082192,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004950394064319203,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.19021693617105484,
|
|
"num_tokens": 18302118.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.211107969284058,
|
|
"epoch": 0.7814175104228708,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004950305038812895,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.18345028162002563,
|
|
"num_tokens": 18316462.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.126726675033569,
|
|
"epoch": 0.7820131030375224,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004950215934385223,
|
|
"loss": 5.0108,
|
|
"mean_token_accuracy": 0.19415764808654784,
|
|
"num_tokens": 18328241.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.171604251861572,
|
|
"epoch": 0.782608695652174,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004950126751039382,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.18449520468711852,
|
|
"num_tokens": 18341580.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.100817489624023,
|
|
"epoch": 0.7832042882668255,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004950037488778572,
|
|
"loss": 5.1057,
|
|
"mean_token_accuracy": 0.18435827195644378,
|
|
"num_tokens": 18354996.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.13550181388855,
|
|
"epoch": 0.7837998808814771,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004949948147605996,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.19239344894886018,
|
|
"num_tokens": 18369284.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.20641770362854,
|
|
"epoch": 0.7843954734961287,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004949858727524855,
|
|
"loss": 5.1565,
|
|
"mean_token_accuracy": 0.1823109820485115,
|
|
"num_tokens": 18383008.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.131191539764404,
|
|
"epoch": 0.7849910661107802,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004949769228538359,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.187278214097023,
|
|
"num_tokens": 18396676.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.086823987960815,
|
|
"epoch": 0.7855866587254318,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004949679650649717,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.1834925413131714,
|
|
"num_tokens": 18411155.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.140738582611084,
|
|
"epoch": 0.7861822513400833,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004949589993862143,
|
|
"loss": 4.9915,
|
|
"mean_token_accuracy": 0.18864058703184128,
|
|
"num_tokens": 18425793.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.033724737167359,
|
|
"epoch": 0.7867778439547349,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004949500258178851,
|
|
"loss": 4.9709,
|
|
"mean_token_accuracy": 0.2000346377491951,
|
|
"num_tokens": 18438920.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.115068960189819,
|
|
"epoch": 0.7873734365693865,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004949410443603062,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.18469759076833725,
|
|
"num_tokens": 18454440.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.175503396987915,
|
|
"epoch": 0.7879690291840381,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004949320550137996,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.1861233726143837,
|
|
"num_tokens": 18469269.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.17389554977417,
|
|
"epoch": 0.7885646217986897,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004949230577786877,
|
|
"loss": 5.1481,
|
|
"mean_token_accuracy": 0.17587748765945435,
|
|
"num_tokens": 18484071.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.176200342178345,
|
|
"epoch": 0.7891602144133413,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004949140526552934,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.18778427839279174,
|
|
"num_tokens": 18498647.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.1708310604095455,
|
|
"epoch": 0.7897558070279929,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004949050396439395,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.18320827931165695,
|
|
"num_tokens": 18513406.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.104892206192017,
|
|
"epoch": 0.7903513996426444,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004948960187449495,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.18366205245256423,
|
|
"num_tokens": 18528150.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.203045177459717,
|
|
"epoch": 0.790946992257296,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948869899586467,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.17668164670467376,
|
|
"num_tokens": 18542402.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.199600887298584,
|
|
"epoch": 0.7915425848719476,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004948779532853552,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.17935796827077866,
|
|
"num_tokens": 18557156.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.0383055210113525,
|
|
"epoch": 0.7921381774865992,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004948689087253989,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.1959547370672226,
|
|
"num_tokens": 18570544.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.1539534568786625,
|
|
"epoch": 0.7927337701012508,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004948598562791025,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.19004946798086167,
|
|
"num_tokens": 18583755.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.1526471138000485,
|
|
"epoch": 0.7933293627159024,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948507959467905,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.18419763594865798,
|
|
"num_tokens": 18596991.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.156637573242188,
|
|
"epoch": 0.7939249553305538,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004948417277287877,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.18994908928871154,
|
|
"num_tokens": 18611206.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.2220231056213375,
|
|
"epoch": 0.7945205479452054,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004948326516254197,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.1810159593820572,
|
|
"num_tokens": 18626567.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.218685913085937,
|
|
"epoch": 0.795116140559857,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000494823567637012,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.18068719655275345,
|
|
"num_tokens": 18641515.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.155432653427124,
|
|
"epoch": 0.7957117331745086,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004948144757638902,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.18333082348108293,
|
|
"num_tokens": 18656622.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.142264556884766,
|
|
"epoch": 0.7963073257891602,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004948053760063806,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.18532575219869613,
|
|
"num_tokens": 18669919.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.088769197463989,
|
|
"epoch": 0.7969029184038118,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004947962683648095,
|
|
"loss": 5.0085,
|
|
"mean_token_accuracy": 0.20004120022058486,
|
|
"num_tokens": 18683254.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.1343029022216795,
|
|
"epoch": 0.7974985110184634,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004947871528395038,
|
|
"loss": 5.0122,
|
|
"mean_token_accuracy": 0.18418822139501573,
|
|
"num_tokens": 18697611.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.1421685218811035,
|
|
"epoch": 0.798094103633115,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049477802943079,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.18653523325920104,
|
|
"num_tokens": 18711363.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.130171823501587,
|
|
"epoch": 0.7986896962477665,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004947688981389958,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.18712179064750672,
|
|
"num_tokens": 18725641.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.167790222167969,
|
|
"epoch": 0.7992852888624181,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004947597589644484,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.18828388154506684,
|
|
"num_tokens": 18739724.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.130439281463623,
|
|
"epoch": 0.7998808814770697,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004947506119074759,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.1907961204648018,
|
|
"num_tokens": 18755257.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.133617162704468,
|
|
"epoch": 0.8004764740917213,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004947414569684062,
|
|
"loss": 5.0415,
|
|
"mean_token_accuracy": 0.18500542342662812,
|
|
"num_tokens": 18770300.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.037832450866699,
|
|
"epoch": 0.8010720667063729,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004947322941475677,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.19327011108398437,
|
|
"num_tokens": 18781939.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.092839193344116,
|
|
"epoch": 0.8016676593210245,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004947231234452891,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.1852808937430382,
|
|
"num_tokens": 18794851.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.109786558151245,
|
|
"epoch": 0.802263251935676,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004947139448618994,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.18595764338970183,
|
|
"num_tokens": 18810776.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.105339765548706,
|
|
"epoch": 0.8028588445503275,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004947047583977276,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.19732133001089097,
|
|
"num_tokens": 18825602.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.167734527587891,
|
|
"epoch": 0.8034544371649791,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004946955640531033,
|
|
"loss": 5.1062,
|
|
"mean_token_accuracy": 0.18327415585517884,
|
|
"num_tokens": 18840284.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.096452093124389,
|
|
"epoch": 0.8040500297796307,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004946863618283565,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.18644148409366607,
|
|
"num_tokens": 18853372.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.149384689331055,
|
|
"epoch": 0.8046456223942823,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004946771517238169,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.1906224876642227,
|
|
"num_tokens": 18867320.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.159115123748779,
|
|
"epoch": 0.8052412150089339,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946679337398151,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.18190647661685944,
|
|
"num_tokens": 18881441.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.127479219436646,
|
|
"epoch": 0.8058368076235854,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946587078766818,
|
|
"loss": 5.0431,
|
|
"mean_token_accuracy": 0.18778251856565475,
|
|
"num_tokens": 18895225.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.22914981842041,
|
|
"epoch": 0.806432400238237,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946494741347476,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.1871239259839058,
|
|
"num_tokens": 18909834.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.120537519454956,
|
|
"epoch": 0.8070279928528886,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004946402325143439,
|
|
"loss": 5.0185,
|
|
"mean_token_accuracy": 0.18926303088665009,
|
|
"num_tokens": 18922304.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.150529766082764,
|
|
"epoch": 0.8076235854675402,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004946309830158024,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.18450450152158737,
|
|
"num_tokens": 18935959.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.152016973495483,
|
|
"epoch": 0.8082191780821918,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004946217256394544,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.1907554268836975,
|
|
"num_tokens": 18950468.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.0896961212158205,
|
|
"epoch": 0.8088147706968434,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004946124603856322,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.18828955739736558,
|
|
"num_tokens": 18966015.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.09833083152771,
|
|
"epoch": 0.809410363311495,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004946031872546683,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.18688211739063262,
|
|
"num_tokens": 18980689.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.142998933792114,
|
|
"epoch": 0.8100059559261465,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000494593906246895,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.1852771446108818,
|
|
"num_tokens": 18994111.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.14407000541687,
|
|
"epoch": 0.8106015485407981,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004945846173626453,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.18714706897735595,
|
|
"num_tokens": 19006845.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.042282962799073,
|
|
"epoch": 0.8111971411554497,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004945753206022525,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.19146559089422227,
|
|
"num_tokens": 19021182.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.044564628601075,
|
|
"epoch": 0.8117927337701013,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004945660159660499,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.19517843723297118,
|
|
"num_tokens": 19034850.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.063855600357056,
|
|
"epoch": 0.8123883263847528,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004945567034543712,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.1828899785876274,
|
|
"num_tokens": 19047405.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.116838693618774,
|
|
"epoch": 0.8129839189994044,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004945473830675507,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.1857633873820305,
|
|
"num_tokens": 19061475.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.166309785842896,
|
|
"epoch": 0.813579511614056,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004945380548059224,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.18473125547170638,
|
|
"num_tokens": 19077312.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.23982343673706,
|
|
"epoch": 0.8141751042287075,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004945287186698211,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.18545602411031722,
|
|
"num_tokens": 19091066.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.090615844726562,
|
|
"epoch": 0.8147706968433591,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945193746595815,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.18763521760702134,
|
|
"num_tokens": 19105081.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.1341465473175045,
|
|
"epoch": 0.8153662894580107,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004945100227755389,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.17870895117521285,
|
|
"num_tokens": 19119223.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.163990259170532,
|
|
"epoch": 0.8159618820726623,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004945006630180288,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.18921846747398377,
|
|
"num_tokens": 19132704.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.068717002868652,
|
|
"epoch": 0.8165574746873139,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004944912953873865,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.19340575486421585,
|
|
"num_tokens": 19147882.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.093496656417846,
|
|
"epoch": 0.8171530673019655,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004944819198839486,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.19308175146579742,
|
|
"num_tokens": 19160815.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.0421970844268795,
|
|
"epoch": 0.817748659916617,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000494472536508051,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.18348561823368073,
|
|
"num_tokens": 19175654.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.099155235290527,
|
|
"epoch": 0.8183442525312686,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004944631452600303,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.19108876287937165,
|
|
"num_tokens": 19189428.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.071003150939942,
|
|
"epoch": 0.8189398451459202,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004944537461402234,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.20043654590845109,
|
|
"num_tokens": 19203050.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.016652536392212,
|
|
"epoch": 0.8195354377605718,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004944443391489676,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.20238869190216063,
|
|
"num_tokens": 19216875.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.075893688201904,
|
|
"epoch": 0.8201310303752234,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004944349242865999,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.19432783126831055,
|
|
"num_tokens": 19231423.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.11176323890686,
|
|
"epoch": 0.820726622989875,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004944255015534585,
|
|
"loss": 5.0441,
|
|
"mean_token_accuracy": 0.18397695422172547,
|
|
"num_tokens": 19245360.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.106947040557861,
|
|
"epoch": 0.8213222156045265,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000494416070949881,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.18424613326787947,
|
|
"num_tokens": 19261233.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.092726182937622,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004944066324762058,
|
|
"loss": 4.9021,
|
|
"mean_token_accuracy": 0.19309760332107545,
|
|
"num_tokens": 19274656.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.084658479690551,
|
|
"epoch": 0.8225134008338296,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004943971861327713,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.1928071841597557,
|
|
"num_tokens": 19290243.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.078370237350464,
|
|
"epoch": 0.8231089934484812,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004943877319199167,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.19118031561374665,
|
|
"num_tokens": 19303314.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.182858896255493,
|
|
"epoch": 0.8237045860631328,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004943782698379807,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.1852895885705948,
|
|
"num_tokens": 19317856.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.1245866298675535,
|
|
"epoch": 0.8243001786777844,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004943687998873029,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.19061789959669112,
|
|
"num_tokens": 19332876.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.136573648452758,
|
|
"epoch": 0.824895771292436,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943593220682229,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.1872744783759117,
|
|
"num_tokens": 19345938.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.066201639175415,
|
|
"epoch": 0.8254913639070875,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004943498363810807,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.19313440173864366,
|
|
"num_tokens": 19359439.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.111890697479248,
|
|
"epoch": 0.8260869565217391,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004943403428262164,
|
|
"loss": 5.0022,
|
|
"mean_token_accuracy": 0.18664806336164474,
|
|
"num_tokens": 19374440.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.108871030807495,
|
|
"epoch": 0.8266825491363907,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004943308414039708,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.18776292651891707,
|
|
"num_tokens": 19386937.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.187880134582519,
|
|
"epoch": 0.8272781417510423,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004943213321146843,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.1878279209136963,
|
|
"num_tokens": 19401077.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.16385064125061,
|
|
"epoch": 0.8278737343656939,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004943118149586984,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.184230937063694,
|
|
"num_tokens": 19416093.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.135784101486206,
|
|
"epoch": 0.8284693269803455,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004943022899363542,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.186602783203125,
|
|
"num_tokens": 19428961.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.114277505874634,
|
|
"epoch": 0.8290649195949971,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004942927570479934,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.1896004319190979,
|
|
"num_tokens": 19442909.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.04258098602295,
|
|
"epoch": 0.8296605122096486,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004942832162939581,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.19776798337697982,
|
|
"num_tokens": 19457702.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.080227851867676,
|
|
"epoch": 0.8302561048243002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004942736676745902,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.18065378069877625,
|
|
"num_tokens": 19471662.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.037929439544678,
|
|
"epoch": 0.8308516974389517,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004942641111902324,
|
|
"loss": 4.9896,
|
|
"mean_token_accuracy": 0.19782114177942275,
|
|
"num_tokens": 19486109.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.103415250778198,
|
|
"epoch": 0.8314472900536033,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942545468412275,
|
|
"loss": 5.0511,
|
|
"mean_token_accuracy": 0.18711979538202286,
|
|
"num_tokens": 19501600.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.121896600723266,
|
|
"epoch": 0.8320428826682549,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004942449746279184,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.18665237873792648,
|
|
"num_tokens": 19515721.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.199591493606567,
|
|
"epoch": 0.8326384752829065,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004942353945506485,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.18672991096973418,
|
|
"num_tokens": 19530536.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.096620273590088,
|
|
"epoch": 0.833234067897558,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004942258066097617,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.1919369652867317,
|
|
"num_tokens": 19542976.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.048670911788941,
|
|
"epoch": 0.8338296605122096,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942162108056015,
|
|
"loss": 4.9451,
|
|
"mean_token_accuracy": 0.19572204798460008,
|
|
"num_tokens": 19557884.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.1136938571929935,
|
|
"epoch": 0.8344252531268612,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004942066071385122,
|
|
"loss": 4.9916,
|
|
"mean_token_accuracy": 0.1924108698964119,
|
|
"num_tokens": 19572438.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.1885065078735355,
|
|
"epoch": 0.8350208457415128,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004941969956088383,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.1799759715795517,
|
|
"num_tokens": 19586114.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.011860370635986,
|
|
"epoch": 0.8356164383561644,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004941873762169246,
|
|
"loss": 4.9226,
|
|
"mean_token_accuracy": 0.19270216971635817,
|
|
"num_tokens": 19600338.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.181015872955323,
|
|
"epoch": 0.836212030970816,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004941777489631161,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.18904242515563965,
|
|
"num_tokens": 19613049.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.074179840087891,
|
|
"epoch": 0.8368076235854676,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004941681138477582,
|
|
"loss": 4.9782,
|
|
"mean_token_accuracy": 0.1953282505273819,
|
|
"num_tokens": 19626685.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.094531106948852,
|
|
"epoch": 0.8374032162001191,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004941584708711962,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.19140578508377076,
|
|
"num_tokens": 19642114.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.164622402191162,
|
|
"epoch": 0.8379988088147707,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004941488200337763,
|
|
"loss": 4.9996,
|
|
"mean_token_accuracy": 0.1947053700685501,
|
|
"num_tokens": 19655505.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.072566843032837,
|
|
"epoch": 0.8385944014294223,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004941391613358444,
|
|
"loss": 5.0151,
|
|
"mean_token_accuracy": 0.18348502814769746,
|
|
"num_tokens": 19671845.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.106756162643433,
|
|
"epoch": 0.8391899940440739,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004941294947777473,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.19319649338722228,
|
|
"num_tokens": 19683578.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.144046449661255,
|
|
"epoch": 0.8397855866587254,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004941198203598314,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.18911621123552322,
|
|
"num_tokens": 19697974.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.094581079483032,
|
|
"epoch": 0.840381179273377,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004941101380824438,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.19829243272542954,
|
|
"num_tokens": 19713024.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.167317628860474,
|
|
"epoch": 0.8409767718880286,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004941004479459318,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.18257631361484528,
|
|
"num_tokens": 19726562.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.103216505050659,
|
|
"epoch": 0.8415723645026801,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000494090749950643,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.18865234702825545,
|
|
"num_tokens": 19741838.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.090511131286621,
|
|
"epoch": 0.8421679571173317,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004940810440969253,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.19052026718854903,
|
|
"num_tokens": 19754852.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.053966283798218,
|
|
"epoch": 0.8427635497319833,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004940713303851265,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.2046578884124756,
|
|
"num_tokens": 19767355.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.025482130050659,
|
|
"epoch": 0.8433591423466349,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004940616088155954,
|
|
"loss": 4.9455,
|
|
"mean_token_accuracy": 0.18899933099746705,
|
|
"num_tokens": 19780861.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.082515621185303,
|
|
"epoch": 0.8439547349612865,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004940518793886807,
|
|
"loss": 5.0326,
|
|
"mean_token_accuracy": 0.19342152327299117,
|
|
"num_tokens": 19793802.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.21843786239624,
|
|
"epoch": 0.8445503275759381,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004940421421047311,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.1811137929558754,
|
|
"num_tokens": 19810748.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.079158353805542,
|
|
"epoch": 0.8451459201905897,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000494032396964096,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.18543216437101365,
|
|
"num_tokens": 19826046.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.086914491653443,
|
|
"epoch": 0.8457415128052412,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000494022643967125,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.18617990612983704,
|
|
"num_tokens": 19839591.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.096063709259033,
|
|
"epoch": 0.8463371054198928,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004940128831141679,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.1922281101346016,
|
|
"num_tokens": 19852560.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.155503749847412,
|
|
"epoch": 0.8469326980345444,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004940031144055747,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.1866885632276535,
|
|
"num_tokens": 19867663.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.069973182678223,
|
|
"epoch": 0.847528290649196,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004939933378416959,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.18838819861412048,
|
|
"num_tokens": 19883761.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.108990716934204,
|
|
"epoch": 0.8481238832638476,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004939835534228821,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.185645754635334,
|
|
"num_tokens": 19897205.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.236863613128662,
|
|
"epoch": 0.848719475878499,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004939737611494842,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.18304286897182465,
|
|
"num_tokens": 19912563.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.143927001953125,
|
|
"epoch": 0.8493150684931506,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004939639610218536,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.1868225485086441,
|
|
"num_tokens": 19926308.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.045386600494385,
|
|
"epoch": 0.8499106611078022,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004939541530403419,
|
|
"loss": 4.981,
|
|
"mean_token_accuracy": 0.19301261454820634,
|
|
"num_tokens": 19939372.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.129878950119019,
|
|
"epoch": 0.8505062537224538,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004939443372053004,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.18840377926826476,
|
|
"num_tokens": 19952755.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.080508756637573,
|
|
"epoch": 0.8511018463371054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004939345135170818,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.19804585576057435,
|
|
"num_tokens": 19965678.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.103389835357666,
|
|
"epoch": 0.851697438951757,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000493924681976038,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.19560402929782866,
|
|
"num_tokens": 19979022.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.093899536132812,
|
|
"epoch": 0.8522930315664086,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004939148425825219,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.19414179176092147,
|
|
"num_tokens": 19991861.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.077882099151611,
|
|
"epoch": 0.8528886241810602,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004939049953368863,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.1947579339146614,
|
|
"num_tokens": 20004444.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.0425084114074705,
|
|
"epoch": 0.8534842167957117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004938951402394844,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.1944648489356041,
|
|
"num_tokens": 20018302.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.035734796524048,
|
|
"epoch": 0.8540798094103633,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004938852772906697,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.1988450586795807,
|
|
"num_tokens": 20031193.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.089770793914795,
|
|
"epoch": 0.8546754020250149,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938754064907961,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.19593191891908646,
|
|
"num_tokens": 20044883.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.142323589324951,
|
|
"epoch": 0.8552709946396665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004938655278402175,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.18611244410276412,
|
|
"num_tokens": 20058024.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.190737581253051,
|
|
"epoch": 0.8558665872543181,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004938556413392882,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.18227855563163758,
|
|
"num_tokens": 20072622.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.179588365554809,
|
|
"epoch": 0.8564621798689697,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004938457469883629,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.1929074212908745,
|
|
"num_tokens": 20086774.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.140833234786987,
|
|
"epoch": 0.8570577724836212,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004938358447877966,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.18460829555988312,
|
|
"num_tokens": 20102435.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.123792886734009,
|
|
"epoch": 0.8576533650982728,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004938259347379442,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.18925742357969283,
|
|
"num_tokens": 20115860.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.0814038753509525,
|
|
"epoch": 0.8582489577129243,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004938160168391614,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.1966782718896866,
|
|
"num_tokens": 20130910.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.0408202648162845,
|
|
"epoch": 0.8588445503275759,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004938060910918038,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.1942405954003334,
|
|
"num_tokens": 20143093.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.07690167427063,
|
|
"epoch": 0.8594401429422275,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004937961574962274,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.19121821224689484,
|
|
"num_tokens": 20157637.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.152603578567505,
|
|
"epoch": 0.8600357355568791,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004937862160527887,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.18953161388635636,
|
|
"num_tokens": 20170455.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.082599878311157,
|
|
"epoch": 0.8606313281715307,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004937762667618441,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.19373772740364076,
|
|
"num_tokens": 20186452.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.135745906829834,
|
|
"epoch": 0.8612269207861822,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004937663096237505,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.1926318034529686,
|
|
"num_tokens": 20199754.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.173078536987305,
|
|
"epoch": 0.8618225134008338,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004937563446388652,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.1831686407327652,
|
|
"num_tokens": 20215765.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.126636791229248,
|
|
"epoch": 0.8624181060154854,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004937463718075453,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.18394626975059508,
|
|
"num_tokens": 20229225.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.129624462127685,
|
|
"epoch": 0.863013698630137,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004937363911301488,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.1906237334012985,
|
|
"num_tokens": 20242729.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.129443264007568,
|
|
"epoch": 0.8636092912447886,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004937264026070336,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.1933988079428673,
|
|
"num_tokens": 20252914.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.011073923110962,
|
|
"epoch": 0.8642048838594402,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000493716406238558,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.20138137191534042,
|
|
"num_tokens": 20265611.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.196710777282715,
|
|
"epoch": 0.8648004764740918,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004937064020250804,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.17272776812314988,
|
|
"num_tokens": 20279808.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.044396638870239,
|
|
"epoch": 0.8653960690887433,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004936963899669599,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.20098137110471725,
|
|
"num_tokens": 20295028.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.1308026790618895,
|
|
"epoch": 0.8659916617033949,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004936863700645554,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.1959221825003624,
|
|
"num_tokens": 20308780.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.235619640350341,
|
|
"epoch": 0.8665872543180465,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004936763423182264,
|
|
"loss": 5.1238,
|
|
"mean_token_accuracy": 0.18986420929431916,
|
|
"num_tokens": 20322513.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.20010895729065,
|
|
"epoch": 0.867182846932698,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004936663067283325,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.1825157880783081,
|
|
"num_tokens": 20336457.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.1735927104949955,
|
|
"epoch": 0.8677784395473496,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004936562632952337,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.19538018107414246,
|
|
"num_tokens": 20349063.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.093681859970093,
|
|
"epoch": 0.8683740321620012,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004936462120192903,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.18865400850772857,
|
|
"num_tokens": 20361832.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.055441856384277,
|
|
"epoch": 0.8689696247766527,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004936361529008627,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.19093923568725585,
|
|
"num_tokens": 20376291.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 4.980146837234497,
|
|
"epoch": 0.8695652173913043,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936260859403119,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.19500485360622405,
|
|
"num_tokens": 20389654.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.170837354660034,
|
|
"epoch": 0.8701608100059559,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004936160111379987,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.1875081479549408,
|
|
"num_tokens": 20403782.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.125169706344605,
|
|
"epoch": 0.8707564026206075,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004936059284942848,
|
|
"loss": 4.944,
|
|
"mean_token_accuracy": 0.20031750798225403,
|
|
"num_tokens": 20416547.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.133488416671753,
|
|
"epoch": 0.8713519952352591,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004935958380095316,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.18071189075708388,
|
|
"num_tokens": 20430831.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.055322360992432,
|
|
"epoch": 0.8719475878499107,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000493585739684101,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.19301650673151016,
|
|
"num_tokens": 20445905.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.227130937576294,
|
|
"epoch": 0.8725431804645623,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004935756335183554,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.1822204902768135,
|
|
"num_tokens": 20461506.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.160520219802857,
|
|
"epoch": 0.8731387730792138,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004935655195126572,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.1919237866997719,
|
|
"num_tokens": 20474753.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.118248653411865,
|
|
"epoch": 0.8737343656938654,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004935553976673692,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.19300244152545928,
|
|
"num_tokens": 20489877.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.055674123764038,
|
|
"epoch": 0.874329958308517,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004935452679828545,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.19854919612407684,
|
|
"num_tokens": 20503693.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.132047271728515,
|
|
"epoch": 0.8749255509231686,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004935351304594763,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.18517500907182693,
|
|
"num_tokens": 20519188.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.144096088409424,
|
|
"epoch": 0.8755211435378202,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004935249850975983,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.18747574388980864,
|
|
"num_tokens": 20535218.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.067215538024902,
|
|
"epoch": 0.8761167361524718,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004935148318975843,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.19799831807613372,
|
|
"num_tokens": 20548037.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.06547589302063,
|
|
"epoch": 0.8767123287671232,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004935046708597986,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.18899944871664048,
|
|
"num_tokens": 20562248.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.16151123046875,
|
|
"epoch": 0.8773079213817748,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004934945019846057,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.18715542703866958,
|
|
"num_tokens": 20577796.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.155225849151611,
|
|
"epoch": 0.8779035139964264,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004934843252723702,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.189596264064312,
|
|
"num_tokens": 20591413.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.0900484085083,
|
|
"epoch": 0.878499106611078,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004934741407234572,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.19022757858037947,
|
|
"num_tokens": 20606648.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.209651947021484,
|
|
"epoch": 0.8790946992257296,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000493463948338232,
|
|
"loss": 5.1479,
|
|
"mean_token_accuracy": 0.1873461738228798,
|
|
"num_tokens": 20620531.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.145799922943115,
|
|
"epoch": 0.8796902918403812,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004934537481170602,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.1878426790237427,
|
|
"num_tokens": 20636639.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.0872656345367435,
|
|
"epoch": 0.8802858844550328,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004934435400603077,
|
|
"loss": 5.0195,
|
|
"mean_token_accuracy": 0.19114547669887544,
|
|
"num_tokens": 20648799.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.09381594657898,
|
|
"epoch": 0.8808814770696843,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004934333241683404,
|
|
"loss": 4.9605,
|
|
"mean_token_accuracy": 0.19382885992527008,
|
|
"num_tokens": 20662612.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.09590163230896,
|
|
"epoch": 0.8814770696843359,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004934231004415251,
|
|
"loss": 5.0084,
|
|
"mean_token_accuracy": 0.19511168748140334,
|
|
"num_tokens": 20676382.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.080713129043579,
|
|
"epoch": 0.8820726622989875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004934128688802282,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.19045990109443664,
|
|
"num_tokens": 20691659.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.109708213806153,
|
|
"epoch": 0.8826682549136391,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004934026294848168,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.19112411588430406,
|
|
"num_tokens": 20705276.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.156528425216675,
|
|
"epoch": 0.8832638475282907,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004933923822556583,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.19055755883455278,
|
|
"num_tokens": 20719632.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.130133962631225,
|
|
"epoch": 0.8838594401429423,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049338212719312,
|
|
"loss": 5.0897,
|
|
"mean_token_accuracy": 0.1926139399409294,
|
|
"num_tokens": 20733190.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.166853046417236,
|
|
"epoch": 0.8844550327575939,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049337186429757,
|
|
"loss": 5.1305,
|
|
"mean_token_accuracy": 0.18483820259571077,
|
|
"num_tokens": 20749019.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.1265514373779295,
|
|
"epoch": 0.8850506253722454,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004933615935693762,
|
|
"loss": 4.9675,
|
|
"mean_token_accuracy": 0.19310675114393233,
|
|
"num_tokens": 20762731.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.107151460647583,
|
|
"epoch": 0.8856462179868969,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004933513150089069,
|
|
"loss": 5.0378,
|
|
"mean_token_accuracy": 0.18219801485538484,
|
|
"num_tokens": 20775599.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.110572957992554,
|
|
"epoch": 0.8862418106015485,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004933410286165311,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.20163044035434724,
|
|
"num_tokens": 20788945.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.0115845680236815,
|
|
"epoch": 0.8868374032162001,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004933307343926177,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.192365562915802,
|
|
"num_tokens": 20803079.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.075363397598267,
|
|
"epoch": 0.8874329958308517,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004933204323375358,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.19007326662540436,
|
|
"num_tokens": 20816321.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.093033933639527,
|
|
"epoch": 0.8880285884455033,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000493310122451655,
|
|
"loss": 4.9664,
|
|
"mean_token_accuracy": 0.19365850687026978,
|
|
"num_tokens": 20830095.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.049651718139648,
|
|
"epoch": 0.8886241810601548,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004932998047353449,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.19247621893882752,
|
|
"num_tokens": 20845022.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.151341485977173,
|
|
"epoch": 0.8892197736748064,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004932894791889759,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.19757362306118012,
|
|
"num_tokens": 20857851.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.144725704193116,
|
|
"epoch": 0.889815366289458,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004932791458129181,
|
|
"loss": 4.953,
|
|
"mean_token_accuracy": 0.1961090698838234,
|
|
"num_tokens": 20870343.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.12801833152771,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004932688046075422,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.1844380334019661,
|
|
"num_tokens": 20883805.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.106091833114624,
|
|
"epoch": 0.8910065515187612,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004932584555732192,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.18840889930725097,
|
|
"num_tokens": 20898160.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.140251731872558,
|
|
"epoch": 0.8916021441334128,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004932480987103204,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.19366686344146727,
|
|
"num_tokens": 20912528.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.170067214965821,
|
|
"epoch": 0.8921977367480644,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004932377340192169,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.1897507905960083,
|
|
"num_tokens": 20925603.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.054325151443481,
|
|
"epoch": 0.8927933293627159,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004932273615002809,
|
|
"loss": 4.9244,
|
|
"mean_token_accuracy": 0.19193495213985443,
|
|
"num_tokens": 20937319.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.030549669265747,
|
|
"epoch": 0.8933889219773675,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932169811538843,
|
|
"loss": 4.9535,
|
|
"mean_token_accuracy": 0.19421723037958144,
|
|
"num_tokens": 20952963.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.100352811813354,
|
|
"epoch": 0.8939845145920191,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004932065929803993,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.19195546507835387,
|
|
"num_tokens": 20966696.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.096163988113403,
|
|
"epoch": 0.8945801072066706,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004931961969801985,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.19200406819581986,
|
|
"num_tokens": 20981093.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.079677438735962,
|
|
"epoch": 0.8951756998213222,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000493185793153655,
|
|
"loss": 5.0555,
|
|
"mean_token_accuracy": 0.1890881448984146,
|
|
"num_tokens": 20997069.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.090252161026001,
|
|
"epoch": 0.8957712924359738,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004931753815011419,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.2039131060242653,
|
|
"num_tokens": 21010123.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.104824686050415,
|
|
"epoch": 0.8963668850506253,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004931649620230325,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.1844482511281967,
|
|
"num_tokens": 21024774.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.143555974960327,
|
|
"epoch": 0.8969624776652769,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004931545347197006,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.18916488587856292,
|
|
"num_tokens": 21039533.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.069677257537842,
|
|
"epoch": 0.8975580702799285,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004931440995915203,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.1944185361266136,
|
|
"num_tokens": 21053593.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.085530424118042,
|
|
"epoch": 0.8981536628945801,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004931336566388658,
|
|
"loss": 4.9569,
|
|
"mean_token_accuracy": 0.19646163880825043,
|
|
"num_tokens": 21064659.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.002637624740601,
|
|
"epoch": 0.8987492555092317,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004931232058621117,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.19550828635692596,
|
|
"num_tokens": 21078815.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.0202507972717285,
|
|
"epoch": 0.8993448481238833,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004931127472616328,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.1987414687871933,
|
|
"num_tokens": 21093415.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.199513673782349,
|
|
"epoch": 0.8999404407385349,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004931022808378044,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.18648864775896073,
|
|
"num_tokens": 21108347.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.092032146453858,
|
|
"epoch": 0.9005360333531864,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004930918065910018,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.18546903431415557,
|
|
"num_tokens": 21122647.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.1157890319824215,
|
|
"epoch": 0.901131625967838,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004930813245216005,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.19153734296560287,
|
|
"num_tokens": 21136465.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.133356618881225,
|
|
"epoch": 0.9017272185824896,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004930708346299769,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.18229297399520875,
|
|
"num_tokens": 21152047.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.119125032424927,
|
|
"epoch": 0.9023228111971412,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004930603369165069,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.18986293971538543,
|
|
"num_tokens": 21166355.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.084667730331421,
|
|
"epoch": 0.9029184038117928,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004930498313815672,
|
|
"loss": 4.9434,
|
|
"mean_token_accuracy": 0.19426887929439546,
|
|
"num_tokens": 21180676.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.010160255432129,
|
|
"epoch": 0.9035139964264444,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004930393180255345,
|
|
"loss": 5.0038,
|
|
"mean_token_accuracy": 0.19484446942806244,
|
|
"num_tokens": 21193091.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.159858655929566,
|
|
"epoch": 0.9041095890410958,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000493028796848786,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.18414405584335328,
|
|
"num_tokens": 21208072.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.086567068099976,
|
|
"epoch": 0.9047051816557474,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004930182678516992,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.19969944953918456,
|
|
"num_tokens": 21220249.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.0398541450500485,
|
|
"epoch": 0.905300774270399,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004930077310346515,
|
|
"loss": 4.933,
|
|
"mean_token_accuracy": 0.19839099049568176,
|
|
"num_tokens": 21233609.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.086992979049683,
|
|
"epoch": 0.9058963668850506,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004929971863980209,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.19001745581626892,
|
|
"num_tokens": 21247083.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.065076541900635,
|
|
"epoch": 0.9064919594997022,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004929866339421857,
|
|
"loss": 4.9825,
|
|
"mean_token_accuracy": 0.1902614027261734,
|
|
"num_tokens": 21260614.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.174501991271972,
|
|
"epoch": 0.9070875521143538,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004929760736675243,
|
|
"loss": 4.9836,
|
|
"mean_token_accuracy": 0.19513046145439147,
|
|
"num_tokens": 21275823.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.024958896636963,
|
|
"epoch": 0.9076831447290054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004929655055744157,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.1951867625117302,
|
|
"num_tokens": 21288787.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.015161800384521,
|
|
"epoch": 0.9082787373436569,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004929549296632387,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.18134687840938568,
|
|
"num_tokens": 21304060.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.10153226852417,
|
|
"epoch": 0.9088743299583085,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004929443459343728,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.1995783969759941,
|
|
"num_tokens": 21317116.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.008592510223389,
|
|
"epoch": 0.9094699225729601,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004929337543881975,
|
|
"loss": 4.9492,
|
|
"mean_token_accuracy": 0.1921396702528,
|
|
"num_tokens": 21330894.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.07371563911438,
|
|
"epoch": 0.9100655151876117,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004929231550250927,
|
|
"loss": 4.9944,
|
|
"mean_token_accuracy": 0.19411227405071257,
|
|
"num_tokens": 21344933.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.164973211288452,
|
|
"epoch": 0.9106611078022633,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004929125478454389,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.18336756229400636,
|
|
"num_tokens": 21358675.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.075775909423828,
|
|
"epoch": 0.9112567004169149,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004929019328496161,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.18481978625059128,
|
|
"num_tokens": 21373611.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.013048791885376,
|
|
"epoch": 0.9118522930315665,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004928913100380053,
|
|
"loss": 4.9089,
|
|
"mean_token_accuracy": 0.20326182395219802,
|
|
"num_tokens": 21387292.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.12844877243042,
|
|
"epoch": 0.912447885646218,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004928806794109875,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.18328915983438493,
|
|
"num_tokens": 21400950.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.1758870601654055,
|
|
"epoch": 0.9130434782608695,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000492870040968944,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.18625225126743317,
|
|
"num_tokens": 21414625.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.025144767761231,
|
|
"epoch": 0.9136390708755211,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004928593947122564,
|
|
"loss": 5.0174,
|
|
"mean_token_accuracy": 0.19768897742033004,
|
|
"num_tokens": 21430408.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.129427719116211,
|
|
"epoch": 0.9142346634901727,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004928487406413065,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.19076740443706514,
|
|
"num_tokens": 21444921.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.095398569107056,
|
|
"epoch": 0.9148302561048243,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004928380787564764,
|
|
"loss": 5.0354,
|
|
"mean_token_accuracy": 0.18711184710264206,
|
|
"num_tokens": 21458541.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.111386251449585,
|
|
"epoch": 0.9154258487194759,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004928274090581486,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.19653140902519226,
|
|
"num_tokens": 21472117.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.128750610351562,
|
|
"epoch": 0.9160214413341274,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004928167315467059,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.19489681273698806,
|
|
"num_tokens": 21484983.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.100516366958618,
|
|
"epoch": 0.916617033948779,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004928060462225312,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.19015735238790513,
|
|
"num_tokens": 21498786.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.097968626022339,
|
|
"epoch": 0.9172126265634306,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004927953530860077,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.19084935635328293,
|
|
"num_tokens": 21513482.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.056329679489136,
|
|
"epoch": 0.9178082191780822,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004927846521375189,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.19212561696767808,
|
|
"num_tokens": 21528648.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.107635354995727,
|
|
"epoch": 0.9184038117927338,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004927739433774489,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.19406019598245622,
|
|
"num_tokens": 21541490.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.0465004444122314,
|
|
"epoch": 0.9189994044073854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004927632268061815,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.1959388479590416,
|
|
"num_tokens": 21557156.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 4.986437749862671,
|
|
"epoch": 0.919594997022037,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004927525024241013,
|
|
"loss": 4.8773,
|
|
"mean_token_accuracy": 0.20037508010864258,
|
|
"num_tokens": 21571697.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.003045749664307,
|
|
"epoch": 0.9201905896366885,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004927417702315928,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.1970121368765831,
|
|
"num_tokens": 21585936.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.134245157241821,
|
|
"epoch": 0.9207861822513401,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004927310302290411,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.19214562475681304,
|
|
"num_tokens": 21601003.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.084166049957275,
|
|
"epoch": 0.9213817748659917,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004927202824168313,
|
|
"loss": 4.9098,
|
|
"mean_token_accuracy": 0.19669660031795502,
|
|
"num_tokens": 21616018.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.100702714920044,
|
|
"epoch": 0.9219773674806433,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000492709526795349,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.18901181668043138,
|
|
"num_tokens": 21628548.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.140497779846191,
|
|
"epoch": 0.9225729600952948,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049269876336498,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.18383269459009172,
|
|
"num_tokens": 21643637.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.074079179763794,
|
|
"epoch": 0.9231685527099464,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004926879921261101,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.1928054541349411,
|
|
"num_tokens": 21658189.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.170826435089111,
|
|
"epoch": 0.9237641453245979,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004926772130791261,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.1817980393767357,
|
|
"num_tokens": 21673023.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.1251305103302,
|
|
"epoch": 0.9243597379392495,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004926664262244143,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.18655893057584763,
|
|
"num_tokens": 21687417.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.0697096824646,
|
|
"epoch": 0.9249553305539011,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004926556315623617,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.19095257222652434,
|
|
"num_tokens": 21700679.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.186417722702027,
|
|
"epoch": 0.9255509231685527,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004926448290933555,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.1915004700422287,
|
|
"num_tokens": 21715832.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.071523761749267,
|
|
"epoch": 0.9261465157832043,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004926340188177831,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.19216983020305634,
|
|
"num_tokens": 21730193.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.117644739151001,
|
|
"epoch": 0.9267421083978559,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004926232007360324,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.18864122927188873,
|
|
"num_tokens": 21743177.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.028144788742066,
|
|
"epoch": 0.9273377010125075,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004926123748484911,
|
|
"loss": 4.835,
|
|
"mean_token_accuracy": 0.20717582553625108,
|
|
"num_tokens": 21757379.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.024472427368164,
|
|
"epoch": 0.927933293627159,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000492601541155548,
|
|
"loss": 4.9572,
|
|
"mean_token_accuracy": 0.1913255125284195,
|
|
"num_tokens": 21769872.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.126287174224854,
|
|
"epoch": 0.9285288862418106,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004925906996575912,
|
|
"loss": 4.9986,
|
|
"mean_token_accuracy": 0.19173368960618972,
|
|
"num_tokens": 21784367.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.040414237976075,
|
|
"epoch": 0.9291244788564622,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004925798503550099,
|
|
"loss": 4.922,
|
|
"mean_token_accuracy": 0.19950623512268068,
|
|
"num_tokens": 21797896.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.024103307723999,
|
|
"epoch": 0.9297200714711138,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004925689932481931,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.1932633861899376,
|
|
"num_tokens": 21810668.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.097339725494384,
|
|
"epoch": 0.9303156640857654,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004925581283375303,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.18924632519483567,
|
|
"num_tokens": 21824923.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.097132730484009,
|
|
"epoch": 0.930911256700417,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004925472556234111,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.187184701859951,
|
|
"num_tokens": 21839967.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.086600255966187,
|
|
"epoch": 0.9315068493150684,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004925363751062256,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.19739340841770173,
|
|
"num_tokens": 21852254.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.043318033218384,
|
|
"epoch": 0.93210244192972,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000492525486786364,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.18730796724557877,
|
|
"num_tokens": 21865227.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.145238924026489,
|
|
"epoch": 0.9326980345443716,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004925145906642169,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.188159017264843,
|
|
"num_tokens": 21880235.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.074481630325318,
|
|
"epoch": 0.9332936271590232,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004925036867401751,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.19794002771377564,
|
|
"num_tokens": 21892514.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.073555326461792,
|
|
"epoch": 0.9338892197736748,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004924927750146296,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.19038517028093338,
|
|
"num_tokens": 21907212.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.079469156265259,
|
|
"epoch": 0.9344848123883264,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004924818554879718,
|
|
"loss": 4.881,
|
|
"mean_token_accuracy": 0.19967318326234818,
|
|
"num_tokens": 21920627.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.107089900970459,
|
|
"epoch": 0.935080405002978,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004924709281605938,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.19344266653060913,
|
|
"num_tokens": 21933557.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.11221079826355,
|
|
"epoch": 0.9356759976176295,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004924599930328869,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.19300634115934373,
|
|
"num_tokens": 21948122.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.124204444885254,
|
|
"epoch": 0.9362715902322811,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004924490501052437,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.19438213109970093,
|
|
"num_tokens": 21961925.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.163843727111816,
|
|
"epoch": 0.9368671828469327,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004924380993780566,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.18793850243091584,
|
|
"num_tokens": 21976825.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.015263462066651,
|
|
"epoch": 0.9374627754615843,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004924271408517185,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.18964421302080153,
|
|
"num_tokens": 21989599.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.131538581848145,
|
|
"epoch": 0.9380583680762359,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004924161745266222,
|
|
"loss": 5.0085,
|
|
"mean_token_accuracy": 0.1930345356464386,
|
|
"num_tokens": 22002921.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.083857154846191,
|
|
"epoch": 0.9386539606908875,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004924052004031613,
|
|
"loss": 4.9109,
|
|
"mean_token_accuracy": 0.19435508102178572,
|
|
"num_tokens": 22015933.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 4.986158323287964,
|
|
"epoch": 0.939249553305539,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004923942184817293,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.2025024861097336,
|
|
"num_tokens": 22029769.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.040314102172852,
|
|
"epoch": 0.9398451459201906,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004923832287627202,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.18775488436222076,
|
|
"num_tokens": 22044025.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.048053741455078,
|
|
"epoch": 0.9404407385348421,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004923722312465281,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.19899895042181015,
|
|
"num_tokens": 22057875.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.020674180984497,
|
|
"epoch": 0.9410363311494937,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004923612259335476,
|
|
"loss": 4.8921,
|
|
"mean_token_accuracy": 0.19689923524856567,
|
|
"num_tokens": 22070995.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.042281246185302,
|
|
"epoch": 0.9416319237641453,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923502128241732,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.19346890449523926,
|
|
"num_tokens": 22086429.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 4.987186861038208,
|
|
"epoch": 0.9422275163787969,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004923391919188001,
|
|
"loss": 4.8676,
|
|
"mean_token_accuracy": 0.20306818336248397,
|
|
"num_tokens": 22101146.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.043812942504883,
|
|
"epoch": 0.9428231089934485,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004923281632178236,
|
|
"loss": 4.9362,
|
|
"mean_token_accuracy": 0.2022297963500023,
|
|
"num_tokens": 22113103.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.075213956832886,
|
|
"epoch": 0.9434187016081,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004923171267216392,
|
|
"loss": 4.95,
|
|
"mean_token_accuracy": 0.19426364898681642,
|
|
"num_tokens": 22126540.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.0661234855651855,
|
|
"epoch": 0.9440142942227516,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004923060824306428,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.18609203398227692,
|
|
"num_tokens": 22141219.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.1404393196105955,
|
|
"epoch": 0.9446098868374032,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004922950303452306,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.1873786121606827,
|
|
"num_tokens": 22156178.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.049093246459961,
|
|
"epoch": 0.9452054794520548,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004922839704657988,
|
|
"loss": 4.8898,
|
|
"mean_token_accuracy": 0.19401755630970002,
|
|
"num_tokens": 22168981.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.058233642578125,
|
|
"epoch": 0.9458010720667064,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004922729027927444,
|
|
"loss": 4.9501,
|
|
"mean_token_accuracy": 0.19439758062362672,
|
|
"num_tokens": 22182288.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.142622470855713,
|
|
"epoch": 0.946396664681358,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004922618273264642,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.18788709938526155,
|
|
"num_tokens": 22197564.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.103839635848999,
|
|
"epoch": 0.9469922572960096,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004922507440673555,
|
|
"loss": 5.1242,
|
|
"mean_token_accuracy": 0.18191175907850266,
|
|
"num_tokens": 22212030.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.069695568084716,
|
|
"epoch": 0.9475878499106611,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004922396530158159,
|
|
"loss": 4.978,
|
|
"mean_token_accuracy": 0.1836741864681244,
|
|
"num_tokens": 22226941.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.0871045112609865,
|
|
"epoch": 0.9481834425253127,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004922285541722431,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.19462450444698334,
|
|
"num_tokens": 22241129.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.107628726959229,
|
|
"epoch": 0.9487790351399643,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004922174475370352,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.18631521463394166,
|
|
"num_tokens": 22256298.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.064291858673096,
|
|
"epoch": 0.9493746277546159,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004922063331105907,
|
|
"loss": 4.9763,
|
|
"mean_token_accuracy": 0.19331541359424592,
|
|
"num_tokens": 22270128.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.162991237640381,
|
|
"epoch": 0.9499702203692674,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004921952108933083,
|
|
"loss": 5.0371,
|
|
"mean_token_accuracy": 0.1872197210788727,
|
|
"num_tokens": 22284847.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 4.983519887924194,
|
|
"epoch": 0.950565812983919,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004921840808855865,
|
|
"loss": 4.8555,
|
|
"mean_token_accuracy": 0.20492184311151504,
|
|
"num_tokens": 22300010.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.00769076347351,
|
|
"epoch": 0.9511614055985705,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004921729430878252,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.1997019812464714,
|
|
"num_tokens": 22313339.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.1102782726287845,
|
|
"epoch": 0.9517569982132221,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004921617975004233,
|
|
"loss": 4.9631,
|
|
"mean_token_accuracy": 0.18561028838157653,
|
|
"num_tokens": 22327659.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.181092357635498,
|
|
"epoch": 0.9523525908278737,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004921506441237809,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.19042967706918718,
|
|
"num_tokens": 22343910.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 4.960132503509522,
|
|
"epoch": 0.9529481834425253,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004921394829582979,
|
|
"loss": 4.9327,
|
|
"mean_token_accuracy": 0.19823235124349595,
|
|
"num_tokens": 22359705.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.081367111206054,
|
|
"epoch": 0.9535437760571769,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004921283140043748,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.18719975650310516,
|
|
"num_tokens": 22373446.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.119373178482055,
|
|
"epoch": 0.9541393686718285,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004921171372624121,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.19035490602254868,
|
|
"num_tokens": 22386628.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.094591999053955,
|
|
"epoch": 0.95473496128648,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004921059527328106,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.19036705195903778,
|
|
"num_tokens": 22400084.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.115833568572998,
|
|
"epoch": 0.9553305539011316,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004920947604159716,
|
|
"loss": 4.9526,
|
|
"mean_token_accuracy": 0.1884820953011513,
|
|
"num_tokens": 22414135.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.017858171463013,
|
|
"epoch": 0.9559261465157832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004920835603122965,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.192671038210392,
|
|
"num_tokens": 22427738.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.081096839904785,
|
|
"epoch": 0.9565217391304348,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004920723524221871,
|
|
"loss": 4.992,
|
|
"mean_token_accuracy": 0.19911700934171678,
|
|
"num_tokens": 22440024.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.104733800888061,
|
|
"epoch": 0.9571173317450864,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004920611367460453,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.19778343439102172,
|
|
"num_tokens": 22453948.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.10758695602417,
|
|
"epoch": 0.957712924359738,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004920499132842734,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.19018565714359284,
|
|
"num_tokens": 22465613.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.0351855754852295,
|
|
"epoch": 0.9583085169743896,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004920386820372741,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.1856833890080452,
|
|
"num_tokens": 22478702.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.1184834957122805,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004920274430054502,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.1916889265179634,
|
|
"num_tokens": 22490947.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.048297977447509,
|
|
"epoch": 0.9594997022036926,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004920161961892047,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.18809459507465362,
|
|
"num_tokens": 22506308.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.218025779724121,
|
|
"epoch": 0.9600952948183442,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004920049415889411,
|
|
"loss": 5.0218,
|
|
"mean_token_accuracy": 0.1881923869252205,
|
|
"num_tokens": 22522045.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.010546016693115,
|
|
"epoch": 0.9606908874329958,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004919936792050631,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.18910309225320815,
|
|
"num_tokens": 22536183.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.005211400985718,
|
|
"epoch": 0.9612864800476474,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004919824090379747,
|
|
"loss": 4.9247,
|
|
"mean_token_accuracy": 0.19474902451038362,
|
|
"num_tokens": 22548239.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.127394771575927,
|
|
"epoch": 0.961882072662299,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049197113108808,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.20171088129281997,
|
|
"num_tokens": 22563467.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.027299785614014,
|
|
"epoch": 0.9624776652769506,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004919598453557836,
|
|
"loss": 4.9715,
|
|
"mean_token_accuracy": 0.18986407071352004,
|
|
"num_tokens": 22577446.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.017820692062378,
|
|
"epoch": 0.9630732578916021,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004919485518414902,
|
|
"loss": 4.9325,
|
|
"mean_token_accuracy": 0.1933164730668068,
|
|
"num_tokens": 22591044.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.069725608825683,
|
|
"epoch": 0.9636688505062537,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004919372505456051,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.19488901942968367,
|
|
"num_tokens": 22604872.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.107310056686401,
|
|
"epoch": 0.9642644431209053,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004919259414685336,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.18613791912794114,
|
|
"num_tokens": 22620138.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.1261077404022215,
|
|
"epoch": 0.9648600357355569,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004919146246106812,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.18406704515218736,
|
|
"num_tokens": 22635580.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.093494272232055,
|
|
"epoch": 0.9654556283502085,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004919032999724539,
|
|
"loss": 4.9465,
|
|
"mean_token_accuracy": 0.19842396825551986,
|
|
"num_tokens": 22650223.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 4.974842214584351,
|
|
"epoch": 0.9660512209648601,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004918919675542579,
|
|
"loss": 4.8924,
|
|
"mean_token_accuracy": 0.20174490064382553,
|
|
"num_tokens": 22664899.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.122016477584839,
|
|
"epoch": 0.9666468135795117,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004918806273564996,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.1923731178045273,
|
|
"num_tokens": 22680052.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.069881534576416,
|
|
"epoch": 0.9672424061941632,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000491869279379586,
|
|
"loss": 4.9269,
|
|
"mean_token_accuracy": 0.19947224706411362,
|
|
"num_tokens": 22693740.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 4.969121980667114,
|
|
"epoch": 0.9678379988088148,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004918579236239238,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.200943960249424,
|
|
"num_tokens": 22707795.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.092825222015381,
|
|
"epoch": 0.9684335914234663,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004918465600899205,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.1958304911851883,
|
|
"num_tokens": 22720296.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.1468830585479735,
|
|
"epoch": 0.9690291840381179,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004918351887779837,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.19172873347997665,
|
|
"num_tokens": 22733680.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 4.982396078109741,
|
|
"epoch": 0.9696247766527695,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004918238096885213,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.19478340297937394,
|
|
"num_tokens": 22746202.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.0833642959594725,
|
|
"epoch": 0.9702203692674211,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004918124228219412,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.18891605883836746,
|
|
"num_tokens": 22759547.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.10478949546814,
|
|
"epoch": 0.9708159618820726,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004918010281786522,
|
|
"loss": 4.9185,
|
|
"mean_token_accuracy": 0.1962537258863449,
|
|
"num_tokens": 22772593.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.082954072952271,
|
|
"epoch": 0.9714115544967242,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004917896257590627,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.18954053819179534,
|
|
"num_tokens": 22786482.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.0829963207244875,
|
|
"epoch": 0.9720071471113758,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004917782155635817,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.19017141163349152,
|
|
"num_tokens": 22800582.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.062156915664673,
|
|
"epoch": 0.9726027397260274,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004917667975926187,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.19297014325857162,
|
|
"num_tokens": 22813661.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.1083152294158936,
|
|
"epoch": 0.973198332340679,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004917553718465832,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.19248986542224883,
|
|
"num_tokens": 22827648.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.139140939712524,
|
|
"epoch": 0.9737939249553306,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004917439383258848,
|
|
"loss": 5.0491,
|
|
"mean_token_accuracy": 0.18515831083059311,
|
|
"num_tokens": 22843345.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.134329891204834,
|
|
"epoch": 0.9743895175699822,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004917324970309337,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.1909800201654434,
|
|
"num_tokens": 22857474.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.0696268558502195,
|
|
"epoch": 0.9749851101846337,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004917210479621404,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.19655824154615403,
|
|
"num_tokens": 22870233.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.084625196456909,
|
|
"epoch": 0.9755807027992853,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004917095911199155,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.19641029089689255,
|
|
"num_tokens": 22885616.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.030050611495971,
|
|
"epoch": 0.9761762954139369,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00049169812650467,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.20111970752477645,
|
|
"num_tokens": 22899553.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.021179914474487,
|
|
"epoch": 0.9767718880285885,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004916866541168148,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.1963580295443535,
|
|
"num_tokens": 22912671.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.1396692276000975,
|
|
"epoch": 0.97736748064324,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004916751739567617,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.18179590553045272,
|
|
"num_tokens": 22926112.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.065869569778442,
|
|
"epoch": 0.9779630732578916,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004916636860249225,
|
|
"loss": 4.8882,
|
|
"mean_token_accuracy": 0.207993283867836,
|
|
"num_tokens": 22940348.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.03212251663208,
|
|
"epoch": 0.9785586658725431,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000491652190321709,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.19446438401937485,
|
|
"num_tokens": 22953347.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.147462844848633,
|
|
"epoch": 0.9791542584871947,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004916406868475338,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.17628038674592972,
|
|
"num_tokens": 22967963.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.147698402404785,
|
|
"epoch": 0.9797498511018463,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004916291756028094,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.18843270987272262,
|
|
"num_tokens": 22985611.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.058805704116821,
|
|
"epoch": 0.9803454437164979,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004916176565879487,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.18787189424037934,
|
|
"num_tokens": 22999210.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.084155750274658,
|
|
"epoch": 0.9809410363311495,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004916061298033648,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.19295574277639388,
|
|
"num_tokens": 23012315.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.0917102813720705,
|
|
"epoch": 0.9815366289458011,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004915945952494713,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.1931993171572685,
|
|
"num_tokens": 23025886.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.012954378128052,
|
|
"epoch": 0.9821322215604527,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004915830529266818,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.2020668238401413,
|
|
"num_tokens": 23040308.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.06901593208313,
|
|
"epoch": 0.9827278141751042,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004915715028354102,
|
|
"loss": 5.0062,
|
|
"mean_token_accuracy": 0.19543693363666534,
|
|
"num_tokens": 23053608.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.1178723812103275,
|
|
"epoch": 0.9833234067897558,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004915599449760711,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.19904492795467377,
|
|
"num_tokens": 23068153.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.104277610778809,
|
|
"epoch": 0.9839189994044074,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004915483793490788,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.18928018510341643,
|
|
"num_tokens": 23081334.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.099558019638062,
|
|
"epoch": 0.984514592019059,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004915368059548482,
|
|
"loss": 4.9775,
|
|
"mean_token_accuracy": 0.18988694101572037,
|
|
"num_tokens": 23095943.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.058677911758423,
|
|
"epoch": 0.9851101846337106,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004915252247937944,
|
|
"loss": 4.9477,
|
|
"mean_token_accuracy": 0.19432459622621537,
|
|
"num_tokens": 23110311.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.080077123641968,
|
|
"epoch": 0.9857057772483622,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000491513635866333,
|
|
"loss": 5.0181,
|
|
"mean_token_accuracy": 0.19464367777109146,
|
|
"num_tokens": 23123783.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.152615165710449,
|
|
"epoch": 0.9863013698630136,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004915020391728792,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.18961218893527984,
|
|
"num_tokens": 23139147.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.050826692581177,
|
|
"epoch": 0.9868969624776652,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004914904347138495,
|
|
"loss": 4.9265,
|
|
"mean_token_accuracy": 0.20177064090967178,
|
|
"num_tokens": 23153216.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 4.991344213485718,
|
|
"epoch": 0.9874925550923168,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004914788224896599,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.19838655292987822,
|
|
"num_tokens": 23166263.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.05782732963562,
|
|
"epoch": 0.9880881477069684,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004914672025007269,
|
|
"loss": 4.9415,
|
|
"mean_token_accuracy": 0.19152321964502333,
|
|
"num_tokens": 23182093.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.027847480773926,
|
|
"epoch": 0.98868374032162,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004914555747474673,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.19148550927639008,
|
|
"num_tokens": 23195492.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.178847360610962,
|
|
"epoch": 0.9892793329362716,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004914439392302981,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.18752850890159606,
|
|
"num_tokens": 23208333.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.0872642517089846,
|
|
"epoch": 0.9898749255509232,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004914322959496367,
|
|
"loss": 4.9453,
|
|
"mean_token_accuracy": 0.1899363860487938,
|
|
"num_tokens": 23223265.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.062381315231323,
|
|
"epoch": 0.9904705181655747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004914206449059008,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.1996154084801674,
|
|
"num_tokens": 23237534.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.069556951522827,
|
|
"epoch": 0.9910661107802263,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004914089860995084,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.19675934612751006,
|
|
"num_tokens": 23252038.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.046561288833618,
|
|
"epoch": 0.9916617033948779,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004913973195308772,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.19327277690172195,
|
|
"num_tokens": 23265728.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.109036493301391,
|
|
"epoch": 0.9922572960095295,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004913856452004262,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.19125291109085082,
|
|
"num_tokens": 23278282.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.0437134265899655,
|
|
"epoch": 0.9928528886241811,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913739631085739,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.19422955214977264,
|
|
"num_tokens": 23293041.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.065673542022705,
|
|
"epoch": 0.9934484812388327,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913622732557394,
|
|
"loss": 4.9424,
|
|
"mean_token_accuracy": 0.1953333467245102,
|
|
"num_tokens": 23307307.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.169987583160401,
|
|
"epoch": 0.9940440738534843,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004913505756423418,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.1880421370267868,
|
|
"num_tokens": 23324064.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.073513460159302,
|
|
"epoch": 0.9946396664681358,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004913388702688009,
|
|
"loss": 4.8943,
|
|
"mean_token_accuracy": 0.19872620701789856,
|
|
"num_tokens": 23338498.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.018943738937378,
|
|
"epoch": 0.9952352590827874,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004913271571355365,
|
|
"loss": 4.937,
|
|
"mean_token_accuracy": 0.19844323843717576,
|
|
"num_tokens": 23352252.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.078090763092041,
|
|
"epoch": 0.9958308516974389,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004913154362429686,
|
|
"loss": 5.025,
|
|
"mean_token_accuracy": 0.18747786730527877,
|
|
"num_tokens": 23366220.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.097681903839112,
|
|
"epoch": 0.9964264443120905,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004913037075915178,
|
|
"loss": 4.9264,
|
|
"mean_token_accuracy": 0.1955217093229294,
|
|
"num_tokens": 23378926.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.085453081130981,
|
|
"epoch": 0.9970220369267421,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004912919711816047,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.19111245423555373,
|
|
"num_tokens": 23391252.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.039633131027221,
|
|
"epoch": 0.9976176295413937,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004912802270136503,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.19562479704618455,
|
|
"num_tokens": 23403812.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.101621770858765,
|
|
"epoch": 0.9982132221560452,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004912684750880757,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.19582012444734573,
|
|
"num_tokens": 23417536.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.128674793243408,
|
|
"epoch": 0.9988088147706968,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004912567154053025,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.18871770203113555,
|
|
"num_tokens": 23431897.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.102613544464111,
|
|
"epoch": 0.9994044073853484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004912449479657526,
|
|
"loss": 4.9754,
|
|
"mean_token_accuracy": 0.19687847942113876,
|
|
"num_tokens": 23446561.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.014394092559814,
|
|
"epoch": 1.0,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004912331727698481,
|
|
"loss": 4.9496,
|
|
"mean_token_accuracy": 0.19261296838521957,
|
|
"num_tokens": 23461012.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.064652442932129,
|
|
"epoch": 1.0005955926146515,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004912213898180111,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.20148869156837462,
|
|
"num_tokens": 23473208.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.094340133666992,
|
|
"epoch": 1.0011911852293032,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004912095991106644,
|
|
"loss": 4.9601,
|
|
"mean_token_accuracy": 0.19071294516324996,
|
|
"num_tokens": 23487450.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.0879371643066404,
|
|
"epoch": 1.0017867778439546,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004911978006482311,
|
|
"loss": 4.9929,
|
|
"mean_token_accuracy": 0.18930389136075973,
|
|
"num_tokens": 23500630.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.122085905075073,
|
|
"epoch": 1.0023823704586063,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004911859944311341,
|
|
"loss": 4.9436,
|
|
"mean_token_accuracy": 0.1951187178492546,
|
|
"num_tokens": 23513999.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.125235271453858,
|
|
"epoch": 1.0029779630732578,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000491174180459797,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.18977785110473633,
|
|
"num_tokens": 23529046.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.14847617149353,
|
|
"epoch": 1.0035735556879095,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004911623587346434,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.19200653284788133,
|
|
"num_tokens": 23545040.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.061241149902344,
|
|
"epoch": 1.004169148302561,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004911505292560977,
|
|
"loss": 4.9054,
|
|
"mean_token_accuracy": 0.1964845761656761,
|
|
"num_tokens": 23558019.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.0510961532592775,
|
|
"epoch": 1.0047647409172127,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004911386920245837,
|
|
"loss": 4.9014,
|
|
"mean_token_accuracy": 0.20152904093265533,
|
|
"num_tokens": 23571263.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.062455320358277,
|
|
"epoch": 1.0053603335318642,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004911268470405263,
|
|
"loss": 4.9444,
|
|
"mean_token_accuracy": 0.19749818593263627,
|
|
"num_tokens": 23584992.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 4.958836317062378,
|
|
"epoch": 1.0059559261465159,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004911149943043504,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.20705998986959456,
|
|
"num_tokens": 23597751.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.003343629837036,
|
|
"epoch": 1.0065515187611673,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000491103133816481,
|
|
"loss": 4.9108,
|
|
"mean_token_accuracy": 0.19975962936878205,
|
|
"num_tokens": 23613045.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.125131416320801,
|
|
"epoch": 1.007147111375819,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004910912655773436,
|
|
"loss": 4.8831,
|
|
"mean_token_accuracy": 0.1996394231915474,
|
|
"num_tokens": 23626785.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.026131582260132,
|
|
"epoch": 1.0077427039904705,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004910793895873637,
|
|
"loss": 4.8736,
|
|
"mean_token_accuracy": 0.19697239100933076,
|
|
"num_tokens": 23640496.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.076176691055298,
|
|
"epoch": 1.0083382966051222,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004910675058469675,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.19589489251375197,
|
|
"num_tokens": 23652604.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.058649253845215,
|
|
"epoch": 1.0089338892197737,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004910556143565812,
|
|
"loss": 4.8647,
|
|
"mean_token_accuracy": 0.20103295594453813,
|
|
"num_tokens": 23666326.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.002215099334717,
|
|
"epoch": 1.0095294818344251,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004910437151166312,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.20069751590490342,
|
|
"num_tokens": 23680728.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 4.9392945766448975,
|
|
"epoch": 1.0101250744490768,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004910318081275445,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.19968757182359695,
|
|
"num_tokens": 23694326.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.0887597560882565,
|
|
"epoch": 1.0107206670637283,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000491019893389748,
|
|
"loss": 4.8197,
|
|
"mean_token_accuracy": 0.19687612652778624,
|
|
"num_tokens": 23709459.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.042415571212769,
|
|
"epoch": 1.01131625967838,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004910079709036692,
|
|
"loss": 4.9373,
|
|
"mean_token_accuracy": 0.19359365999698638,
|
|
"num_tokens": 23725227.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.090095853805542,
|
|
"epoch": 1.0119118522930315,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004909960406697358,
|
|
"loss": 4.9824,
|
|
"mean_token_accuracy": 0.19007028341293336,
|
|
"num_tokens": 23738733.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.043685960769653,
|
|
"epoch": 1.0125074449076832,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004909841026883755,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.1882927343249321,
|
|
"num_tokens": 23753189.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.1063238143920895,
|
|
"epoch": 1.0131030375223347,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004909721569600166,
|
|
"loss": 4.9321,
|
|
"mean_token_accuracy": 0.19867532849311828,
|
|
"num_tokens": 23766665.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.076293087005615,
|
|
"epoch": 1.0136986301369864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004909602034850875,
|
|
"loss": 4.8402,
|
|
"mean_token_accuracy": 0.19781273305416108,
|
|
"num_tokens": 23780190.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 4.977902412414551,
|
|
"epoch": 1.0142942227516378,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004909482422640172,
|
|
"loss": 4.8558,
|
|
"mean_token_accuracy": 0.20071635395288467,
|
|
"num_tokens": 23794652.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.038762092590332,
|
|
"epoch": 1.0148898153662895,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004909362732972344,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.1951649010181427,
|
|
"num_tokens": 23810423.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.076127767562866,
|
|
"epoch": 1.015485407980941,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004909242965851688,
|
|
"loss": 4.9005,
|
|
"mean_token_accuracy": 0.2025016203522682,
|
|
"num_tokens": 23823676.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.019517135620117,
|
|
"epoch": 1.0160810005955927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004909123121282495,
|
|
"loss": 4.8447,
|
|
"mean_token_accuracy": 0.19880737960338593,
|
|
"num_tokens": 23836703.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 4.909541416168213,
|
|
"epoch": 1.0166765932102442,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004909003199269068,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.20263745933771132,
|
|
"num_tokens": 23850804.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.079055976867676,
|
|
"epoch": 1.0172721858248959,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004908883199815705,
|
|
"loss": 4.9256,
|
|
"mean_token_accuracy": 0.1891650065779686,
|
|
"num_tokens": 23864893.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.013314247131348,
|
|
"epoch": 1.0178677784395473,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004908763122926712,
|
|
"loss": 4.8329,
|
|
"mean_token_accuracy": 0.1948847144842148,
|
|
"num_tokens": 23878268.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 4.965462923049927,
|
|
"epoch": 1.018463371054199,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004908642968606396,
|
|
"loss": 4.856,
|
|
"mean_token_accuracy": 0.2005317136645317,
|
|
"num_tokens": 23892398.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 4.987096071243286,
|
|
"epoch": 1.0190589636688505,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004908522736859068,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.20327674150466918,
|
|
"num_tokens": 23907268.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.056459999084472,
|
|
"epoch": 1.019654556283502,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004908402427689037,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.19765596836805344,
|
|
"num_tokens": 23921484.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 4.901800870895386,
|
|
"epoch": 1.0202501488981537,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004908282041100621,
|
|
"loss": 4.8071,
|
|
"mean_token_accuracy": 0.2035224437713623,
|
|
"num_tokens": 23934312.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.053831720352173,
|
|
"epoch": 1.0208457415128052,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004908161577098137,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.19343692511320115,
|
|
"num_tokens": 23946866.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.07602481842041,
|
|
"epoch": 1.0214413341274569,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004908041035685907,
|
|
"loss": 4.8875,
|
|
"mean_token_accuracy": 0.20022224634885788,
|
|
"num_tokens": 23960582.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.070292329788208,
|
|
"epoch": 1.0220369267421083,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004907920416868253,
|
|
"loss": 4.9015,
|
|
"mean_token_accuracy": 0.19306163042783736,
|
|
"num_tokens": 23976130.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.096119117736817,
|
|
"epoch": 1.02263251935676,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004907799720649502,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.19455282986164094,
|
|
"num_tokens": 23989740.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.055537605285645,
|
|
"epoch": 1.0232281119714115,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004907678947033984,
|
|
"loss": 4.9217,
|
|
"mean_token_accuracy": 0.19660041928291322,
|
|
"num_tokens": 24005840.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.097821187973023,
|
|
"epoch": 1.0238237045860632,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004907558096026031,
|
|
"loss": 4.949,
|
|
"mean_token_accuracy": 0.1904837116599083,
|
|
"num_tokens": 24019861.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.041545772552491,
|
|
"epoch": 1.0244192972007147,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004907437167629976,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.19773643016815184,
|
|
"num_tokens": 24034741.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.040019130706787,
|
|
"epoch": 1.0250148898153664,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004907316161850158,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.19001074731349946,
|
|
"num_tokens": 24048905.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 4.988021755218506,
|
|
"epoch": 1.0256104824300178,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004907195078690916,
|
|
"loss": 4.8435,
|
|
"mean_token_accuracy": 0.19464731216430664,
|
|
"num_tokens": 24064937.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 4.979356718063355,
|
|
"epoch": 1.0262060750446695,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004907073918156595,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.1940657064318657,
|
|
"num_tokens": 24080293.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.14317831993103,
|
|
"epoch": 1.026801667659321,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004906952680251539,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.1910681203007698,
|
|
"num_tokens": 24092048.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.03330283164978,
|
|
"epoch": 1.0273972602739727,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004906831364980098,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.19857764691114427,
|
|
"num_tokens": 24106446.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.011397123336792,
|
|
"epoch": 1.0279928528886242,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004906709972346623,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.1909236043691635,
|
|
"num_tokens": 24120867.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.062542915344238,
|
|
"epoch": 1.0285884455032757,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004906588502355467,
|
|
"loss": 4.8567,
|
|
"mean_token_accuracy": 0.19683483839035035,
|
|
"num_tokens": 24135139.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 4.982117080688477,
|
|
"epoch": 1.0291840381179274,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004906466955010988,
|
|
"loss": 4.7861,
|
|
"mean_token_accuracy": 0.2019197016954422,
|
|
"num_tokens": 24147649.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 4.954188203811645,
|
|
"epoch": 1.0297796307325788,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004906345330317546,
|
|
"loss": 4.8097,
|
|
"mean_token_accuracy": 0.20423834025859833,
|
|
"num_tokens": 24162408.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.0495809555053714,
|
|
"epoch": 1.0303752233472305,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004906223628279502,
|
|
"loss": 4.8445,
|
|
"mean_token_accuracy": 0.19633971750736237,
|
|
"num_tokens": 24175011.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.067824411392212,
|
|
"epoch": 1.030970815961882,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004906101848901224,
|
|
"loss": 4.8482,
|
|
"mean_token_accuracy": 0.19775989949703215,
|
|
"num_tokens": 24187832.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.021482610702515,
|
|
"epoch": 1.0315664085765337,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004905979992187076,
|
|
"loss": 4.9067,
|
|
"mean_token_accuracy": 0.1951156660914421,
|
|
"num_tokens": 24202347.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.054401397705078,
|
|
"epoch": 1.0321620011911852,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004905858058141433,
|
|
"loss": 4.8805,
|
|
"mean_token_accuracy": 0.20432865023612976,
|
|
"num_tokens": 24216988.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.078740072250366,
|
|
"epoch": 1.0327575938058369,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004905736046768665,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.1914765268564224,
|
|
"num_tokens": 24231091.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.020196437835693,
|
|
"epoch": 1.0333531864204883,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004905613958073151,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.202582710981369,
|
|
"num_tokens": 24244684.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 4.940138339996338,
|
|
"epoch": 1.03394877903514,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000490549179205927,
|
|
"loss": 4.8224,
|
|
"mean_token_accuracy": 0.20351965278387069,
|
|
"num_tokens": 24259637.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.050007724761963,
|
|
"epoch": 1.0345443716497915,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004905369548731402,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.19266010373830794,
|
|
"num_tokens": 24274046.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.080617666244507,
|
|
"epoch": 1.0351399642644432,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004905247228093933,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.19491729140281677,
|
|
"num_tokens": 24288266.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.040188312530518,
|
|
"epoch": 1.0357355568790947,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000490512483015125,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.18574268668889998,
|
|
"num_tokens": 24303029.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 4.956378602981568,
|
|
"epoch": 1.0363311494937464,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004905002354907743,
|
|
"loss": 4.7237,
|
|
"mean_token_accuracy": 0.21351334750652312,
|
|
"num_tokens": 24315369.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.146809005737305,
|
|
"epoch": 1.0369267421083979,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004904879802367806,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.19567129462957383,
|
|
"num_tokens": 24327049.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.101212215423584,
|
|
"epoch": 1.0375223347230493,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004904757172535833,
|
|
"loss": 4.9091,
|
|
"mean_token_accuracy": 0.19417060911655426,
|
|
"num_tokens": 24341797.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 4.984847974777222,
|
|
"epoch": 1.038117927337701,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004904634465416226,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.19308515787124633,
|
|
"num_tokens": 24357560.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.023865413665772,
|
|
"epoch": 1.0387135199523525,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004904511681013382,
|
|
"loss": 4.8574,
|
|
"mean_token_accuracy": 0.19370461404323577,
|
|
"num_tokens": 24371856.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.051117372512818,
|
|
"epoch": 1.0393091125670042,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004904388819331707,
|
|
"loss": 4.8883,
|
|
"mean_token_accuracy": 0.20143260508775712,
|
|
"num_tokens": 24384494.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.125233554840088,
|
|
"epoch": 1.0399047051816557,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004904265880375609,
|
|
"loss": 4.9349,
|
|
"mean_token_accuracy": 0.19605440199375151,
|
|
"num_tokens": 24398901.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.016664791107178,
|
|
"epoch": 1.0405002977963074,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004904142864149496,
|
|
"loss": 4.8658,
|
|
"mean_token_accuracy": 0.19416883885860442,
|
|
"num_tokens": 24413900.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.04030408859253,
|
|
"epoch": 1.0410958904109588,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000490401977065778,
|
|
"loss": 4.9219,
|
|
"mean_token_accuracy": 0.19655062705278398,
|
|
"num_tokens": 24427764.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.026684427261353,
|
|
"epoch": 1.0416914830256105,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004903896599904878,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.19823668897151947,
|
|
"num_tokens": 24442510.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.13445086479187,
|
|
"epoch": 1.042287075640262,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004903773351895206,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.19448655396699904,
|
|
"num_tokens": 24457119.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.075462436676025,
|
|
"epoch": 1.0428826682549137,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004903650026633187,
|
|
"loss": 4.8975,
|
|
"mean_token_accuracy": 0.19145826548337935,
|
|
"num_tokens": 24470232.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.012204647064209,
|
|
"epoch": 1.0434782608695652,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004903526624123243,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.1978543996810913,
|
|
"num_tokens": 24484886.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.0866797924041744,
|
|
"epoch": 1.0440738534842169,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049034031443698,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.19373629987239838,
|
|
"num_tokens": 24499682.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.105514001846314,
|
|
"epoch": 1.0446694460988684,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004903279587377287,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.19567244350910187,
|
|
"num_tokens": 24514812.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.049972677230835,
|
|
"epoch": 1.04526503871352,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004903155953150137,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.1967035338282585,
|
|
"num_tokens": 24527723.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.033420181274414,
|
|
"epoch": 1.0458606313281715,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004903032241692784,
|
|
"loss": 4.8545,
|
|
"mean_token_accuracy": 0.2057415321469307,
|
|
"num_tokens": 24542082.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.0285999298095705,
|
|
"epoch": 1.046456223942823,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004902908453009664,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.19492818862199784,
|
|
"num_tokens": 24556854.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 4.921629238128662,
|
|
"epoch": 1.0470518165574747,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004902784587105218,
|
|
"loss": 4.7374,
|
|
"mean_token_accuracy": 0.2083793103694916,
|
|
"num_tokens": 24570927.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 4.985281944274902,
|
|
"epoch": 1.0476474091721262,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000490266064398389,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.2023928478360176,
|
|
"num_tokens": 24584458.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 4.990630006790161,
|
|
"epoch": 1.0482430017867779,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004902536623650125,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.20341007262468339,
|
|
"num_tokens": 24597576.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 4.970416307449341,
|
|
"epoch": 1.0488385944014293,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004902412526108371,
|
|
"loss": 4.8004,
|
|
"mean_token_accuracy": 0.20301900655031205,
|
|
"num_tokens": 24613022.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.107708740234375,
|
|
"epoch": 1.049434187016081,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004902288351363079,
|
|
"loss": 4.9347,
|
|
"mean_token_accuracy": 0.19322830438613892,
|
|
"num_tokens": 24627730.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 4.991311550140381,
|
|
"epoch": 1.0500297796307325,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004902164099418703,
|
|
"loss": 4.8336,
|
|
"mean_token_accuracy": 0.198539100587368,
|
|
"num_tokens": 24642870.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.1095428466796875,
|
|
"epoch": 1.0506253722453842,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049020397702797,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.18689721822738647,
|
|
"num_tokens": 24658416.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.076093626022339,
|
|
"epoch": 1.0512209648600357,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000490191536395053,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.193826562166214,
|
|
"num_tokens": 24673294.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 4.963676071166992,
|
|
"epoch": 1.0518165574746874,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004901790880435655,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.19720330089330673,
|
|
"num_tokens": 24687841.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 4.987818574905395,
|
|
"epoch": 1.0524121500893389,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004901666319739537,
|
|
"loss": 4.7583,
|
|
"mean_token_accuracy": 0.20505035370588304,
|
|
"num_tokens": 24701489.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 4.99290132522583,
|
|
"epoch": 1.0530077427039906,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004901541681866649,
|
|
"loss": 4.84,
|
|
"mean_token_accuracy": 0.1965749204158783,
|
|
"num_tokens": 24714312.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.0520720958709715,
|
|
"epoch": 1.053603335318642,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004901416966821459,
|
|
"loss": 4.8328,
|
|
"mean_token_accuracy": 0.20263777375221254,
|
|
"num_tokens": 24728982.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.051071500778198,
|
|
"epoch": 1.0541989279332937,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000490129217460844,
|
|
"loss": 4.8879,
|
|
"mean_token_accuracy": 0.20061112940311432,
|
|
"num_tokens": 24744374.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.080051898956299,
|
|
"epoch": 1.0547945205479452,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004901167305232068,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.18939522355794908,
|
|
"num_tokens": 24759129.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.049275207519531,
|
|
"epoch": 1.0553901131625967,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004901042358696823,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.2042466014623642,
|
|
"num_tokens": 24772154.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.012396335601807,
|
|
"epoch": 1.0559857057772484,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004900917335007186,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.2025101289153099,
|
|
"num_tokens": 24785961.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 4.990875101089477,
|
|
"epoch": 1.0565812983918998,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004900792234167642,
|
|
"loss": 4.8723,
|
|
"mean_token_accuracy": 0.20356411188840867,
|
|
"num_tokens": 24797337.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.073643541336059,
|
|
"epoch": 1.0571768910065515,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004900667056182676,
|
|
"loss": 4.9687,
|
|
"mean_token_accuracy": 0.19410279542207717,
|
|
"num_tokens": 24811023.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.093304634094238,
|
|
"epoch": 1.057772483621203,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004900541801056781,
|
|
"loss": 4.9288,
|
|
"mean_token_accuracy": 0.1942291721701622,
|
|
"num_tokens": 24823951.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 4.992415142059326,
|
|
"epoch": 1.0583680762358547,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004900416468794446,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.20063202679157258,
|
|
"num_tokens": 24838856.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.063638830184937,
|
|
"epoch": 1.0589636688505062,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004900291059400171,
|
|
"loss": 4.9335,
|
|
"mean_token_accuracy": 0.19716560393571853,
|
|
"num_tokens": 24853539.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.052640438079834,
|
|
"epoch": 1.0595592614651579,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000490016557287845,
|
|
"loss": 4.8147,
|
|
"mean_token_accuracy": 0.20472349971532822,
|
|
"num_tokens": 24866385.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.0363260269165036,
|
|
"epoch": 1.0601548540798094,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004900040009233787,
|
|
"loss": 4.9147,
|
|
"mean_token_accuracy": 0.1916353926062584,
|
|
"num_tokens": 24880168.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.084288215637207,
|
|
"epoch": 1.060750446694461,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004899914368470685,
|
|
"loss": 4.8664,
|
|
"mean_token_accuracy": 0.19721296578645706,
|
|
"num_tokens": 24893673.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.064557361602783,
|
|
"epoch": 1.0613460393091125,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004899788650593648,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.19648659527301787,
|
|
"num_tokens": 24907950.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.016775798797608,
|
|
"epoch": 1.0619416319237642,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004899662855607189,
|
|
"loss": 4.8382,
|
|
"mean_token_accuracy": 0.2039511412382126,
|
|
"num_tokens": 24921443.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.042681360244751,
|
|
"epoch": 1.0625372245384157,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004899536983515819,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.19788728207349776,
|
|
"num_tokens": 24935485.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.012244367599488,
|
|
"epoch": 1.0631328171530674,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004899411034324051,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.19425939321517943,
|
|
"num_tokens": 24950372.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 4.963319206237793,
|
|
"epoch": 1.0637284097677189,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004899285008036406,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.2016940727829933,
|
|
"num_tokens": 24964360.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.0792004585266115,
|
|
"epoch": 1.0643240023823703,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048991589046574,
|
|
"loss": 4.8249,
|
|
"mean_token_accuracy": 0.20329871475696565,
|
|
"num_tokens": 24979101.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.021714115142823,
|
|
"epoch": 1.064919594997022,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004899032724191559,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.19656761586666108,
|
|
"num_tokens": 24994350.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 4.941089868545532,
|
|
"epoch": 1.0655151876116735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004898906466643409,
|
|
"loss": 4.7932,
|
|
"mean_token_accuracy": 0.20221594125032424,
|
|
"num_tokens": 25007343.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.1445177555084225,
|
|
"epoch": 1.0661107802263252,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004898780132017478,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.18821272403001785,
|
|
"num_tokens": 25020191.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 4.985881042480469,
|
|
"epoch": 1.0667063728409767,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004898653720318296,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.19284402579069138,
|
|
"num_tokens": 25034910.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.0301533222198485,
|
|
"epoch": 1.0673019654556284,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048985272315504,
|
|
"loss": 4.8795,
|
|
"mean_token_accuracy": 0.2012111261487007,
|
|
"num_tokens": 25048958.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.141404151916504,
|
|
"epoch": 1.0678975580702799,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004898400665718325,
|
|
"loss": 4.9787,
|
|
"mean_token_accuracy": 0.19089988619089127,
|
|
"num_tokens": 25065752.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.027279090881348,
|
|
"epoch": 1.0684931506849316,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004898274022826611,
|
|
"loss": 4.8181,
|
|
"mean_token_accuracy": 0.20397913604974746,
|
|
"num_tokens": 25078569.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 4.972070741653442,
|
|
"epoch": 1.069088743299583,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004898147302879801,
|
|
"loss": 4.8755,
|
|
"mean_token_accuracy": 0.20229159593582152,
|
|
"num_tokens": 25093973.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.012189245223999,
|
|
"epoch": 1.0696843359142347,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004898020505882441,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.20567487925291061,
|
|
"num_tokens": 25109338.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.015009784698487,
|
|
"epoch": 1.0702799285288862,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004897893631839076,
|
|
"loss": 4.8761,
|
|
"mean_token_accuracy": 0.19811885207891464,
|
|
"num_tokens": 25124902.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.016126728057861,
|
|
"epoch": 1.070875521143538,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000489776668075426,
|
|
"loss": 4.8442,
|
|
"mean_token_accuracy": 0.20293078571558,
|
|
"num_tokens": 25138982.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 4.974462985992432,
|
|
"epoch": 1.0714711137581894,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004897639652632544,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.20451183915138244,
|
|
"num_tokens": 25152684.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.02135066986084,
|
|
"epoch": 1.072066706372841,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004897512547478487,
|
|
"loss": 4.867,
|
|
"mean_token_accuracy": 0.19807157069444656,
|
|
"num_tokens": 25167275.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.072066706372841,
|
|
"eval_entropy": 4.890390589543644,
|
|
"eval_loss": 4.923820972442627,
|
|
"eval_mean_token_accuracy": 0.2055872492585623,
|
|
"eval_num_tokens": 25167275.0,
|
|
"eval_runtime": 24.0854,
|
|
"eval_samples_per_second": 1059.273,
|
|
"eval_steps_per_second": 132.445,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.093267583847046,
|
|
"epoch": 1.0726622989874925,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004897385365296645,
|
|
"loss": 4.8899,
|
|
"mean_token_accuracy": 0.19941316545009613,
|
|
"num_tokens": 25178117.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 4.975747442245483,
|
|
"epoch": 1.073257891602144,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004897258106091582,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.2058466911315918,
|
|
"num_tokens": 25191002.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 4.933670234680176,
|
|
"epoch": 1.0738534842167957,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004897130769867862,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.20846014171838761,
|
|
"num_tokens": 25204749.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.0447125911712645,
|
|
"epoch": 1.0744490768314472,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004897003356630052,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.1980380967259407,
|
|
"num_tokens": 25219324.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.0338311195373535,
|
|
"epoch": 1.0750446694460989,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004896875866382723,
|
|
"loss": 4.8871,
|
|
"mean_token_accuracy": 0.196134752035141,
|
|
"num_tokens": 25234032.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.039020013809204,
|
|
"epoch": 1.0756402620607504,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004896748299130447,
|
|
"loss": 4.7803,
|
|
"mean_token_accuracy": 0.20347682684659957,
|
|
"num_tokens": 25245922.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.087958335876465,
|
|
"epoch": 1.076235854675402,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048966206548778,
|
|
"loss": 4.9159,
|
|
"mean_token_accuracy": 0.19273755103349685,
|
|
"num_tokens": 25257614.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 4.9136162281036375,
|
|
"epoch": 1.0768314472900535,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000489649293362936,
|
|
"loss": 4.798,
|
|
"mean_token_accuracy": 0.20632123053073884,
|
|
"num_tokens": 25271705.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.076625967025757,
|
|
"epoch": 1.0774270399047052,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004896365135389709,
|
|
"loss": 4.8804,
|
|
"mean_token_accuracy": 0.1971295014023781,
|
|
"num_tokens": 25286963.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.016149806976318,
|
|
"epoch": 1.0780226325193567,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000489623726016343,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.19473930895328523,
|
|
"num_tokens": 25301953.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.033776426315308,
|
|
"epoch": 1.0786182251340084,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000489610930795511,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.2050413027405739,
|
|
"num_tokens": 25314417.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.077972745895385,
|
|
"epoch": 1.0792138177486599,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000489598127876934,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.19984832555055618,
|
|
"num_tokens": 25327555.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 4.969013500213623,
|
|
"epoch": 1.0798094103633116,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004895853172610709,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.19979369640350342,
|
|
"num_tokens": 25342840.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.042658138275146,
|
|
"epoch": 1.080405002977963,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004895724989483814,
|
|
"loss": 4.82,
|
|
"mean_token_accuracy": 0.20447528064250947,
|
|
"num_tokens": 25354922.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.056599378585815,
|
|
"epoch": 1.0810005955926147,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004895596729393252,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.19543307274580002,
|
|
"num_tokens": 25370331.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 4.946786308288575,
|
|
"epoch": 1.0815961882072662,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004895468392343623,
|
|
"loss": 4.8297,
|
|
"mean_token_accuracy": 0.2006353974342346,
|
|
"num_tokens": 25383392.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 4.987021780014038,
|
|
"epoch": 1.0821917808219177,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004895339978339534,
|
|
"loss": 4.8103,
|
|
"mean_token_accuracy": 0.2013200432062149,
|
|
"num_tokens": 25395613.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.060411548614502,
|
|
"epoch": 1.0827873734365694,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004895211487385586,
|
|
"loss": 4.8485,
|
|
"mean_token_accuracy": 0.197254079580307,
|
|
"num_tokens": 25409141.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.036264276504516,
|
|
"epoch": 1.0833829660512209,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000489508291948639,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.19576458185911177,
|
|
"num_tokens": 25423128.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 4.998009490966797,
|
|
"epoch": 1.0839785586658726,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004894954274646557,
|
|
"loss": 4.82,
|
|
"mean_token_accuracy": 0.18894511312246323,
|
|
"num_tokens": 25437641.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 4.997322702407837,
|
|
"epoch": 1.084574151280524,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004894825552870703,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.19589025974273683,
|
|
"num_tokens": 25452719.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.015948963165283,
|
|
"epoch": 1.0851697438951757,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004894696754163442,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.20007359385490417,
|
|
"num_tokens": 25466239.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 4.985665559768677,
|
|
"epoch": 1.0857653365098272,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004894567878529397,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.19884259402751922,
|
|
"num_tokens": 25478477.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.0623626708984375,
|
|
"epoch": 1.086360929124479,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004894438925973189,
|
|
"loss": 4.9478,
|
|
"mean_token_accuracy": 0.18405379354953766,
|
|
"num_tokens": 25492525.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.135350751876831,
|
|
"epoch": 1.0869565217391304,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004894309896499443,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.19508383125066758,
|
|
"num_tokens": 25507725.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.068548965454101,
|
|
"epoch": 1.087552114353782,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004894180790112787,
|
|
"loss": 4.9033,
|
|
"mean_token_accuracy": 0.19675173163414,
|
|
"num_tokens": 25522716.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 4.984253454208374,
|
|
"epoch": 1.0881477069684335,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004894051606817851,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.20213190615177154,
|
|
"num_tokens": 25536805.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 4.9742178440094,
|
|
"epoch": 1.0887432995830852,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004893922346619272,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.20727020055055617,
|
|
"num_tokens": 25550253.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.02170991897583,
|
|
"epoch": 1.0893388921977367,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004893793009521684,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.19513909965753556,
|
|
"num_tokens": 25564975.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.101642417907715,
|
|
"epoch": 1.0899344848123884,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004893663595529725,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.20240864902734756,
|
|
"num_tokens": 25578467.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 4.980619144439697,
|
|
"epoch": 1.09053007742704,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000489353410464804,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.19483088850975036,
|
|
"num_tokens": 25591931.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 4.937533855438232,
|
|
"epoch": 1.0911256700416916,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004893404536881271,
|
|
"loss": 4.7045,
|
|
"mean_token_accuracy": 0.19898597598075868,
|
|
"num_tokens": 25605553.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.008884000778198,
|
|
"epoch": 1.091721262656343,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004893274892234066,
|
|
"loss": 4.8031,
|
|
"mean_token_accuracy": 0.19889994263648986,
|
|
"num_tokens": 25620946.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.049139165878296,
|
|
"epoch": 1.0923168552709945,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004893145170711075,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.19942134767770767,
|
|
"num_tokens": 25633704.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 4.97772970199585,
|
|
"epoch": 1.0929124478856462,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004893015372316953,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.20324245244264602,
|
|
"num_tokens": 25646770.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 4.982447099685669,
|
|
"epoch": 1.0935080405002977,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004892885497056353,
|
|
"loss": 4.876,
|
|
"mean_token_accuracy": 0.19435426145792006,
|
|
"num_tokens": 25660440.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.034783363342285,
|
|
"epoch": 1.0941036331149494,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004892755544933934,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.19326403737068176,
|
|
"num_tokens": 25673730.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 4.952899599075318,
|
|
"epoch": 1.0946992257296009,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004892625515954357,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.2033802568912506,
|
|
"num_tokens": 25688300.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.060263729095459,
|
|
"epoch": 1.0952948183442526,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004892495410122288,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.19405255019664763,
|
|
"num_tokens": 25702158.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.097706604003906,
|
|
"epoch": 1.095890410958904,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004892365227442392,
|
|
"loss": 4.9309,
|
|
"mean_token_accuracy": 0.19469030648469926,
|
|
"num_tokens": 25715505.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 4.98168454170227,
|
|
"epoch": 1.0964860035735557,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004892234967919337,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.19861892312765123,
|
|
"num_tokens": 25729566.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.006694984436035,
|
|
"epoch": 1.0970815961882072,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004892104631557797,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.2018948018550873,
|
|
"num_tokens": 25742777.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.047379493713379,
|
|
"epoch": 1.097677188802859,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004891974218362448,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.1906789019703865,
|
|
"num_tokens": 25757689.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.076013040542603,
|
|
"epoch": 1.0982727814175104,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004891843728337965,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.19297424256801604,
|
|
"num_tokens": 25770699.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.111573934555054,
|
|
"epoch": 1.098868374032162,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004891713161489031,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.19522452354431152,
|
|
"num_tokens": 25782692.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.018472719192505,
|
|
"epoch": 1.0994639666468136,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004891582517820328,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.19968447387218474,
|
|
"num_tokens": 25798900.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.055496311187744,
|
|
"epoch": 1.1000595592614653,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004891451797336541,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.196898153424263,
|
|
"num_tokens": 25814443.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.073392057418824,
|
|
"epoch": 1.1006551518761167,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004891321000042361,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.19584862589836122,
|
|
"num_tokens": 25830620.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 4.971656608581543,
|
|
"epoch": 1.1012507444907684,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004891190125942478,
|
|
"loss": 4.8812,
|
|
"mean_token_accuracy": 0.1970725655555725,
|
|
"num_tokens": 25845364.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 4.956662225723266,
|
|
"epoch": 1.10184633710542,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004891059175041586,
|
|
"loss": 4.7513,
|
|
"mean_token_accuracy": 0.2035593181848526,
|
|
"num_tokens": 25858418.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.013526201248169,
|
|
"epoch": 1.1024419297200714,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004890928147344383,
|
|
"loss": 4.8355,
|
|
"mean_token_accuracy": 0.20243369787931442,
|
|
"num_tokens": 25870669.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.0863035202026365,
|
|
"epoch": 1.103037522334723,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004890797042855569,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.1924319252371788,
|
|
"num_tokens": 25883785.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.122548007965088,
|
|
"epoch": 1.1036331149493745,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004890665861579845,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.19363020360469818,
|
|
"num_tokens": 25895566.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.073461294174194,
|
|
"epoch": 1.1042287075640262,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004890534603521917,
|
|
"loss": 4.9073,
|
|
"mean_token_accuracy": 0.19600623697042466,
|
|
"num_tokens": 25908751.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 4.967155122756958,
|
|
"epoch": 1.1048243001786777,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004890403268686494,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.20633351653814316,
|
|
"num_tokens": 25922070.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 4.972639894485473,
|
|
"epoch": 1.1054198927933294,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004890271857078285,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.20800906121730806,
|
|
"num_tokens": 25935772.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.043239498138428,
|
|
"epoch": 1.106015485407981,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004890140368702003,
|
|
"loss": 4.8145,
|
|
"mean_token_accuracy": 0.19918791055679322,
|
|
"num_tokens": 25950443.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 4.972781181335449,
|
|
"epoch": 1.1066110780226326,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004890008803562368,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.20453625172376633,
|
|
"num_tokens": 25964585.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 4.88982310295105,
|
|
"epoch": 1.107206670637284,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.20469935983419418,
|
|
"num_tokens": 25977952.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.086190795898437,
|
|
"epoch": 1.1078022632519358,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004889745443011909,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.1895545467734337,
|
|
"num_tokens": 25993164.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.081191635131836,
|
|
"epoch": 1.1083978558665872,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004889613647610532,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.19640983045101165,
|
|
"num_tokens": 26007710.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.08320837020874,
|
|
"epoch": 1.108993448481239,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004889481775464692,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.19327017962932586,
|
|
"num_tokens": 26023311.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.012568998336792,
|
|
"epoch": 1.1095890410958904,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000488934982657912,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.19465167969465255,
|
|
"num_tokens": 26037485.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 4.953014087677002,
|
|
"epoch": 1.110184633710542,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004889217800958548,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.2007157325744629,
|
|
"num_tokens": 26053621.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.061465263366699,
|
|
"epoch": 1.1107802263251936,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004889085698607711,
|
|
"loss": 4.884,
|
|
"mean_token_accuracy": 0.2023625835776329,
|
|
"num_tokens": 26066724.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 4.983478307723999,
|
|
"epoch": 1.111375818939845,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004888953519531349,
|
|
"loss": 4.89,
|
|
"mean_token_accuracy": 0.1975637599825859,
|
|
"num_tokens": 26080818.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.117685985565186,
|
|
"epoch": 1.1119714115544967,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048888212637342,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.192641282081604,
|
|
"num_tokens": 26096455.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.037825202941894,
|
|
"epoch": 1.1125670041691482,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004888688931221012,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.19698332846164704,
|
|
"num_tokens": 26113194.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.008957719802856,
|
|
"epoch": 1.1131625967838,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004888556521996529,
|
|
"loss": 4.8976,
|
|
"mean_token_accuracy": 0.19887442290782928,
|
|
"num_tokens": 26127489.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.069400119781494,
|
|
"epoch": 1.1137581893984514,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048884240360655,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.20719363391399384,
|
|
"num_tokens": 26140008.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.029912281036377,
|
|
"epoch": 1.114353782013103,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004888291473432678,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.19092827886343003,
|
|
"num_tokens": 26154849.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.099413013458252,
|
|
"epoch": 1.1149493746277546,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004888158834102816,
|
|
"loss": 4.9322,
|
|
"mean_token_accuracy": 0.19549115002155304,
|
|
"num_tokens": 26168600.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.047944831848144,
|
|
"epoch": 1.1155449672424063,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004888026118080675,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.20191113650798798,
|
|
"num_tokens": 26182933.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.045944404602051,
|
|
"epoch": 1.1161405598570577,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004887893325371013,
|
|
"loss": 4.9096,
|
|
"mean_token_accuracy": 0.19423434883356094,
|
|
"num_tokens": 26198152.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 4.9648277282714846,
|
|
"epoch": 1.1167361524717094,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004887760455978592,
|
|
"loss": 4.7935,
|
|
"mean_token_accuracy": 0.20789142400026323,
|
|
"num_tokens": 26212395.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.058839988708496,
|
|
"epoch": 1.117331745086361,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000488762750990818,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.20888863056898116,
|
|
"num_tokens": 26226188.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.048543500900268,
|
|
"epoch": 1.1179273377010126,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004887494487164546,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.19181848764419557,
|
|
"num_tokens": 26242259.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.0189149379730225,
|
|
"epoch": 1.118522930315664,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004887361387752459,
|
|
"loss": 4.882,
|
|
"mean_token_accuracy": 0.2019242227077484,
|
|
"num_tokens": 26256458.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.0775329113006595,
|
|
"epoch": 1.1191185229303158,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004887228211676694,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.1944353923201561,
|
|
"num_tokens": 26270575.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 4.956373929977417,
|
|
"epoch": 1.1197141155449672,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004887094958942029,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.20898105949163437,
|
|
"num_tokens": 26283770.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 4.976693534851075,
|
|
"epoch": 1.1203097081596187,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004886961629553242,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.2119318127632141,
|
|
"num_tokens": 26296563.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 4.9855071067810055,
|
|
"epoch": 1.1209053007742704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004886828223515115,
|
|
"loss": 4.8095,
|
|
"mean_token_accuracy": 0.1993648037314415,
|
|
"num_tokens": 26310473.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.028509140014648,
|
|
"epoch": 1.121500893388922,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004886694740832434,
|
|
"loss": 4.9093,
|
|
"mean_token_accuracy": 0.1980767920613289,
|
|
"num_tokens": 26324953.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.034451484680176,
|
|
"epoch": 1.1220964860035736,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004886561181509988,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.20029702931642532,
|
|
"num_tokens": 26337561.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.01399450302124,
|
|
"epoch": 1.122692078618225,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004886427545552567,
|
|
"loss": 4.825,
|
|
"mean_token_accuracy": 0.2018891081213951,
|
|
"num_tokens": 26350953.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 4.939621353149414,
|
|
"epoch": 1.1232876712328768,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004886293832964961,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.20083486437797546,
|
|
"num_tokens": 26365829.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.01025128364563,
|
|
"epoch": 1.1238832638475282,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000488616004375197,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.20145967453718186,
|
|
"num_tokens": 26380938.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 4.989844083786011,
|
|
"epoch": 1.12447885646218,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000488602617791839,
|
|
"loss": 4.8096,
|
|
"mean_token_accuracy": 0.20449201613664628,
|
|
"num_tokens": 26394799.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 4.959778308868408,
|
|
"epoch": 1.1250744490768314,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004885892235469026,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.20006206184625625,
|
|
"num_tokens": 26408898.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.027499628067017,
|
|
"epoch": 1.125670041691483,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000488575821640868,
|
|
"loss": 4.8827,
|
|
"mean_token_accuracy": 0.19783377051353454,
|
|
"num_tokens": 26423104.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.0458167552947994,
|
|
"epoch": 1.1262656343061346,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004885624120742158,
|
|
"loss": 4.8728,
|
|
"mean_token_accuracy": 0.19783004373311996,
|
|
"num_tokens": 26437583.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 4.980867385864258,
|
|
"epoch": 1.1268612269207863,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004885489948474272,
|
|
"loss": 4.7975,
|
|
"mean_token_accuracy": 0.19677907973527908,
|
|
"num_tokens": 26449959.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.042170429229737,
|
|
"epoch": 1.1274568195354377,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004885355699609834,
|
|
"loss": 4.9382,
|
|
"mean_token_accuracy": 0.18929311484098435,
|
|
"num_tokens": 26461519.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 4.977874135971069,
|
|
"epoch": 1.1280524121500894,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004885221374153657,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.20199625343084335,
|
|
"num_tokens": 26474620.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.108799648284912,
|
|
"epoch": 1.128648004764741,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004885086972110563,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.1920786902308464,
|
|
"num_tokens": 26490599.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.038034248352051,
|
|
"epoch": 1.1292435973793924,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000488495249348537,
|
|
"loss": 4.8566,
|
|
"mean_token_accuracy": 0.19885783940553664,
|
|
"num_tokens": 26504071.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.021721696853637,
|
|
"epoch": 1.129839189994044,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004884817938282902,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.19664399772882463,
|
|
"num_tokens": 26516308.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.040789413452148,
|
|
"epoch": 1.1304347826086956,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004884683306507987,
|
|
"loss": 4.831,
|
|
"mean_token_accuracy": 0.20466828346252441,
|
|
"num_tokens": 26529271.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.017858600616455,
|
|
"epoch": 1.1310303752233473,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000488454859816545,
|
|
"loss": 4.8546,
|
|
"mean_token_accuracy": 0.1998257592320442,
|
|
"num_tokens": 26544514.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.000914669036865,
|
|
"epoch": 1.1316259678379987,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004884413813260127,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.19620441645383835,
|
|
"num_tokens": 26559582.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.011322021484375,
|
|
"epoch": 1.1322215604526504,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004884278951796851,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.20340623259544371,
|
|
"num_tokens": 26574002.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.000078105926514,
|
|
"epoch": 1.132817153067302,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004884144013780459,
|
|
"loss": 4.8352,
|
|
"mean_token_accuracy": 0.20807304233312607,
|
|
"num_tokens": 26587708.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.039568185806274,
|
|
"epoch": 1.1334127456819536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004884008999215792,
|
|
"loss": 4.9125,
|
|
"mean_token_accuracy": 0.20109095722436904,
|
|
"num_tokens": 26601548.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.000548028945923,
|
|
"epoch": 1.134008338296605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000488387390810769,
|
|
"loss": 4.8067,
|
|
"mean_token_accuracy": 0.20107102543115615,
|
|
"num_tokens": 26615037.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.078168964385986,
|
|
"epoch": 1.1346039309112568,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004883738740461001,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.19356405287981032,
|
|
"num_tokens": 26630510.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 4.99601035118103,
|
|
"epoch": 1.1351995235259082,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004883603496280573,
|
|
"loss": 4.8358,
|
|
"mean_token_accuracy": 0.19445820450782775,
|
|
"num_tokens": 26645720.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.019972276687622,
|
|
"epoch": 1.13579511614056,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004883468175571256,
|
|
"loss": 4.8447,
|
|
"mean_token_accuracy": 0.1990897014737129,
|
|
"num_tokens": 26658412.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.031278944015503,
|
|
"epoch": 1.1363907087552114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004883332778337905,
|
|
"loss": 4.8838,
|
|
"mean_token_accuracy": 0.2013247564435005,
|
|
"num_tokens": 26672930.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 4.96619291305542,
|
|
"epoch": 1.1369863013698631,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004883197304585376,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.2075143501162529,
|
|
"num_tokens": 26688151.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 4.987266778945923,
|
|
"epoch": 1.1375818939845146,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004883061754318528,
|
|
"loss": 4.9117,
|
|
"mean_token_accuracy": 0.2017013430595398,
|
|
"num_tokens": 26701920.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.046884250640869,
|
|
"epoch": 1.138177486599166,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004882926127542222,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.1898960217833519,
|
|
"num_tokens": 26717355.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.1032203197479244,
|
|
"epoch": 1.1387730792138178,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004882790424261325,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.19343914091587067,
|
|
"num_tokens": 26734026.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 4.948913526535034,
|
|
"epoch": 1.1393686718284692,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004882654644480702,
|
|
"loss": 4.7558,
|
|
"mean_token_accuracy": 0.20905401110649108,
|
|
"num_tokens": 26748570.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.015862131118775,
|
|
"epoch": 1.139964264443121,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004882518788205225,
|
|
"loss": 4.8806,
|
|
"mean_token_accuracy": 0.19242725223302842,
|
|
"num_tokens": 26762227.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 4.981135654449463,
|
|
"epoch": 1.1405598570577724,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048823828554397664,
|
|
"loss": 4.8326,
|
|
"mean_token_accuracy": 0.2052588105201721,
|
|
"num_tokens": 26776884.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.025912284851074,
|
|
"epoch": 1.141155449672424,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004882246846189202,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.19632137566804886,
|
|
"num_tokens": 26790470.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 4.927927160263062,
|
|
"epoch": 1.1417510422870756,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048821107604584096,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.21311191469430923,
|
|
"num_tokens": 26805188.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.069136381149292,
|
|
"epoch": 1.1423466349017273,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004881974598252271,
|
|
"loss": 4.8693,
|
|
"mean_token_accuracy": 0.19748279303312302,
|
|
"num_tokens": 26819680.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 4.997722482681274,
|
|
"epoch": 1.1429422275163788,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000488183835957567,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.20507937520742417,
|
|
"num_tokens": 26834138.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 4.930808734893799,
|
|
"epoch": 1.1435378201310304,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048817020444334936,
|
|
"loss": 4.8002,
|
|
"mean_token_accuracy": 0.20101552307605744,
|
|
"num_tokens": 26847147.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.044656991958618,
|
|
"epoch": 1.144133412745682,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048815656528306304,
|
|
"loss": 4.873,
|
|
"mean_token_accuracy": 0.2088528022170067,
|
|
"num_tokens": 26860491.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 4.980186605453492,
|
|
"epoch": 1.1447290053603336,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004881429184771973,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.20423152148723603,
|
|
"num_tokens": 26875702.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 4.971163034439087,
|
|
"epoch": 1.145324597974985,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004881292640262416,
|
|
"loss": 4.7948,
|
|
"mean_token_accuracy": 0.20344564467668533,
|
|
"num_tokens": 26890724.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.036615991592408,
|
|
"epoch": 1.1459201905896368,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004881156019306857,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.20446324050426484,
|
|
"num_tokens": 26904920.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.053045034408569,
|
|
"epoch": 1.1465157832042883,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004881019321910198,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.19502165168523788,
|
|
"num_tokens": 26920289.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.017702627182007,
|
|
"epoch": 1.1471113758189397,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048808825480773396,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.19426969587802886,
|
|
"num_tokens": 26932942.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 4.882041072845459,
|
|
"epoch": 1.1477069684335914,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004880745697813189,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.20563751757144927,
|
|
"num_tokens": 26948215.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 4.9891575336456295,
|
|
"epoch": 1.148302561048243,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004880608771122654,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.20110174119472504,
|
|
"num_tokens": 26961402.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.03801383972168,
|
|
"epoch": 1.1488981536628946,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048804717680106475,
|
|
"loss": 4.8159,
|
|
"mean_token_accuracy": 0.20729828923940657,
|
|
"num_tokens": 26974476.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 4.923747253417969,
|
|
"epoch": 1.149493746277546,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004880334688482082,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.2101810798048973,
|
|
"num_tokens": 26987384.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.083722734451294,
|
|
"epoch": 1.1500893388921978,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004880197532541875,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.19421740472316742,
|
|
"num_tokens": 27002829.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 4.968387413024902,
|
|
"epoch": 1.1506849315068493,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004880060300194947,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.19983127117156982,
|
|
"num_tokens": 27016638.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 4.967184162139892,
|
|
"epoch": 1.151280524121501,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004879922991446218,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.20001384764909744,
|
|
"num_tokens": 27030412.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 4.986966228485107,
|
|
"epoch": 1.1518761167361524,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048797856063006144,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.2022860735654831,
|
|
"num_tokens": 27043563.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 4.909019136428833,
|
|
"epoch": 1.1524717093508041,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048796481447630646,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.20770370215177536,
|
|
"num_tokens": 27058344.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.0503747940063475,
|
|
"epoch": 1.1530673019654556,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048795106068384985,
|
|
"loss": 4.8699,
|
|
"mean_token_accuracy": 0.201594215631485,
|
|
"num_tokens": 27071273.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.0518638610839846,
|
|
"epoch": 1.1536628945801073,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004879372992531849,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.20686760246753694,
|
|
"num_tokens": 27085478.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 4.908310270309448,
|
|
"epoch": 1.1542584871947588,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004879235301848052,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.2034907191991806,
|
|
"num_tokens": 27098457.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.084486961364746,
|
|
"epoch": 1.1548540798094105,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004879097534792047,
|
|
"loss": 4.9321,
|
|
"mean_token_accuracy": 0.19300007522106172,
|
|
"num_tokens": 27113563.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.053286933898926,
|
|
"epoch": 1.155449672424062,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004878959691368776,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.20083911269903182,
|
|
"num_tokens": 27126221.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 4.9970701217651365,
|
|
"epoch": 1.1560452650387134,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004878821771583181,
|
|
"loss": 4.84,
|
|
"mean_token_accuracy": 0.20708136409521102,
|
|
"num_tokens": 27137897.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 4.991877698898316,
|
|
"epoch": 1.156640857653365,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048786837754402114,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.2054072469472885,
|
|
"num_tokens": 27152880.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.031663036346435,
|
|
"epoch": 1.1572364502680166,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004878545702944815,
|
|
"loss": 4.8427,
|
|
"mean_token_accuracy": 0.2024913176894188,
|
|
"num_tokens": 27167204.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 4.945098352432251,
|
|
"epoch": 1.1578320428826683,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048784075541019454,
|
|
"loss": 4.8038,
|
|
"mean_token_accuracy": 0.2079797714948654,
|
|
"num_tokens": 27182732.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.03946852684021,
|
|
"epoch": 1.1584276354973198,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004878269328916557,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.19515952914953233,
|
|
"num_tokens": 27198354.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.106041669845581,
|
|
"epoch": 1.1590232281119714,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004878131027393609,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.18953243643045425,
|
|
"num_tokens": 27212040.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.088720655441284,
|
|
"epoch": 1.159618820726623,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000487799264953806,
|
|
"loss": 4.896,
|
|
"mean_token_accuracy": 0.20162579864263536,
|
|
"num_tokens": 27225597.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 4.997718954086304,
|
|
"epoch": 1.1602144133412746,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048778541953548753,
|
|
"loss": 4.865,
|
|
"mean_token_accuracy": 0.20358519852161408,
|
|
"num_tokens": 27240395.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.016867685317993,
|
|
"epoch": 1.160810005955926,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000487771566484902,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.19352492243051528,
|
|
"num_tokens": 27253457.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.003967046737671,
|
|
"epoch": 1.1614055985705778,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048775770580254636,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.2032770484685898,
|
|
"num_tokens": 27266406.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.047627353668213,
|
|
"epoch": 1.1620011911852293,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048774383748891774,
|
|
"loss": 4.81,
|
|
"mean_token_accuracy": 0.19842354208230972,
|
|
"num_tokens": 27280366.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.000188398361206,
|
|
"epoch": 1.162596783799881,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048772996154451356,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.20393364280462264,
|
|
"num_tokens": 27293471.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.0182537078857425,
|
|
"epoch": 1.1631923764145324,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004877160779698315,
|
|
"loss": 4.7826,
|
|
"mean_token_accuracy": 0.20358533412218094,
|
|
"num_tokens": 27308564.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 4.961307048797607,
|
|
"epoch": 1.1637879690291841,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048770218676536957,
|
|
"loss": 4.838,
|
|
"mean_token_accuracy": 0.2038780555129051,
|
|
"num_tokens": 27321949.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 4.947978067398071,
|
|
"epoch": 1.1643835616438356,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048768828793162614,
|
|
"loss": 4.7679,
|
|
"mean_token_accuracy": 0.2056581810116768,
|
|
"num_tokens": 27335422.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.062573003768921,
|
|
"epoch": 1.164979154258487,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004876743814690995,
|
|
"loss": 4.8869,
|
|
"mean_token_accuracy": 0.20534598082304,
|
|
"num_tokens": 27348607.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.005766296386719,
|
|
"epoch": 1.1655747468731388,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004876604673782887,
|
|
"loss": 4.8638,
|
|
"mean_token_accuracy": 0.20436668545007705,
|
|
"num_tokens": 27364034.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.103998041152954,
|
|
"epoch": 1.1661703394877905,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004876465456596926,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.19811435043811798,
|
|
"num_tokens": 27378053.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.012095260620117,
|
|
"epoch": 1.166765932102442,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048763261631381075,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.19894817769527434,
|
|
"num_tokens": 27391871.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.0652539253234865,
|
|
"epoch": 1.1673615247170934,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004876186793411426,
|
|
"loss": 4.9648,
|
|
"mean_token_accuracy": 0.19058784544467927,
|
|
"num_tokens": 27405472.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.02398190498352,
|
|
"epoch": 1.1679571173317451,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048760473474218814,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.20507313311100006,
|
|
"num_tokens": 27418757.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 4.948153257369995,
|
|
"epoch": 1.1685527099463966,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048759078251744747,
|
|
"loss": 4.7572,
|
|
"mean_token_accuracy": 0.20585643947124482,
|
|
"num_tokens": 27431375.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 4.959178066253662,
|
|
"epoch": 1.1691483025610483,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048757682266742115,
|
|
"loss": 4.788,
|
|
"mean_token_accuracy": 0.20840132385492324,
|
|
"num_tokens": 27444739.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.031442880630493,
|
|
"epoch": 1.1697438951756998,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004875628551926098,
|
|
"loss": 4.8869,
|
|
"mean_token_accuracy": 0.20069870799779893,
|
|
"num_tokens": 27458580.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.055660915374756,
|
|
"epoch": 1.1703394877903515,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004875488800935144,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.19873436093330382,
|
|
"num_tokens": 27471844.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.019562244415283,
|
|
"epoch": 1.170935080405003,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004875348973706363,
|
|
"loss": 4.8577,
|
|
"mean_token_accuracy": 0.19645291417837143,
|
|
"num_tokens": 27485777.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.002020645141601,
|
|
"epoch": 1.1715306730196546,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000487520907024477,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.19390217512845992,
|
|
"num_tokens": 27501350.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 4.960358667373657,
|
|
"epoch": 1.172126265634306,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048750690905553833,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.20640719532966614,
|
|
"num_tokens": 27514788.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.019156265258789,
|
|
"epoch": 1.1727218582489578,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004874929034643223,
|
|
"loss": 4.9195,
|
|
"mean_token_accuracy": 0.19101880192756654,
|
|
"num_tokens": 27531024.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.047652626037598,
|
|
"epoch": 1.1733174508636093,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004874788902513314,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.19533469825983046,
|
|
"num_tokens": 27545606.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.043625259399414,
|
|
"epoch": 1.1739130434782608,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004874648694170681,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.20132575035095215,
|
|
"num_tokens": 27561640.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.054903507232666,
|
|
"epoch": 1.1745086360929125,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048745084096203536,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.20088944137096404,
|
|
"num_tokens": 27574933.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 4.942908430099488,
|
|
"epoch": 1.1751042287075641,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004874368048867364,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.20048965364694596,
|
|
"num_tokens": 27589493.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.054736089706421,
|
|
"epoch": 1.1756998213222156,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048742276119167463,
|
|
"loss": 4.8798,
|
|
"mean_token_accuracy": 0.19989855885505675,
|
|
"num_tokens": 27603290.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.015584516525268,
|
|
"epoch": 1.176295413936867,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048740870987735383,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.20407182723283768,
|
|
"num_tokens": 27616792.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.075062227249146,
|
|
"epoch": 1.1768910065515188,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004873946509442779,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.1982635200023651,
|
|
"num_tokens": 27632646.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.029089069366455,
|
|
"epoch": 1.1774865991661703,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004873805843929512,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.19513070732355117,
|
|
"num_tokens": 27647433.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.013483047485352,
|
|
"epoch": 1.178082191780822,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004873665102238783,
|
|
"loss": 4.8476,
|
|
"mean_token_accuracy": 0.20126909911632537,
|
|
"num_tokens": 27661456.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.069734144210815,
|
|
"epoch": 1.1786777843954734,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048735242843756394,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.1932743713259697,
|
|
"num_tokens": 27676109.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.087816572189331,
|
|
"epoch": 1.1792733770101251,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004873383390345132,
|
|
"loss": 4.8899,
|
|
"mean_token_accuracy": 0.1950700730085373,
|
|
"num_tokens": 27690575.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.00384407043457,
|
|
"epoch": 1.1798689696247766,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048732424201523156,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.19476369619369507,
|
|
"num_tokens": 27704318.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.094726514816284,
|
|
"epoch": 1.1804645622394283,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004873101373802245,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.1887198805809021,
|
|
"num_tokens": 27719946.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.049914073944092,
|
|
"epoch": 1.1810601548540798,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004872960251299981,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.20147241801023483,
|
|
"num_tokens": 27734338.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 4.955135011672974,
|
|
"epoch": 1.1816557474687315,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048728190526505834,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.19860226064920425,
|
|
"num_tokens": 27750074.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.015163230895996,
|
|
"epoch": 1.182251340083383,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048726777778591184,
|
|
"loss": 4.8393,
|
|
"mean_token_accuracy": 0.19780487716197967,
|
|
"num_tokens": 27762879.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.031249475479126,
|
|
"epoch": 1.1828469326980344,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004872536426930653,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.2051407888531685,
|
|
"num_tokens": 27774492.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 4.978406572341919,
|
|
"epoch": 1.1834425253126861,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004872394999870256,
|
|
"loss": 4.8929,
|
|
"mean_token_accuracy": 0.20078513473272325,
|
|
"num_tokens": 27789988.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.057415103912353,
|
|
"epoch": 1.1840381179273378,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048722534966830027,
|
|
"loss": 4.8884,
|
|
"mean_token_accuracy": 0.19104861170053483,
|
|
"num_tokens": 27806217.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.0027988910675045,
|
|
"epoch": 1.1846337105419893,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048721119173739667,
|
|
"loss": 4.7796,
|
|
"mean_token_accuracy": 0.20451902151107787,
|
|
"num_tokens": 27821265.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.029722404479981,
|
|
"epoch": 1.1852293031566408,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048719702619482255,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.20014568716287612,
|
|
"num_tokens": 27833977.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 4.929647397994995,
|
|
"epoch": 1.1858248957712925,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048718285304108613,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.21193558275699614,
|
|
"num_tokens": 27847341.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.001297044754028,
|
|
"epoch": 1.186420488385944,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004871686722766958,
|
|
"loss": 4.7778,
|
|
"mean_token_accuracy": 0.2067580610513687,
|
|
"num_tokens": 27861364.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.007062292098999,
|
|
"epoch": 1.1870160810005956,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048715448390216015,
|
|
"loss": 4.8603,
|
|
"mean_token_accuracy": 0.1960997313261032,
|
|
"num_tokens": 27875226.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 4.969042205810547,
|
|
"epoch": 1.187611673615247,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048714028791798817,
|
|
"loss": 4.8171,
|
|
"mean_token_accuracy": 0.20071472227573395,
|
|
"num_tokens": 27887966.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.093284177780151,
|
|
"epoch": 1.1882072662298988,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004871260843246889,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.19970788508653642,
|
|
"num_tokens": 27903083.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.050842666625977,
|
|
"epoch": 1.1888028588445503,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048711187312277187,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.20344230979681016,
|
|
"num_tokens": 27916277.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 4.93755350112915,
|
|
"epoch": 1.189398451459202,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048709765431274686,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.19454192221164704,
|
|
"num_tokens": 27932543.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.055555391311645,
|
|
"epoch": 1.1899940440738535,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004870834278951238,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.2047305017709732,
|
|
"num_tokens": 27948425.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.039781951904297,
|
|
"epoch": 1.1905896366885051,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004870691938704131,
|
|
"loss": 4.7933,
|
|
"mean_token_accuracy": 0.21093253940343856,
|
|
"num_tokens": 27962175.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 4.947259902954102,
|
|
"epoch": 1.1911852293031566,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004870549522391252,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.19396800249814988,
|
|
"num_tokens": 27976027.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 4.912618398666382,
|
|
"epoch": 1.191780821917808,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048704070300177094,
|
|
"loss": 4.7982,
|
|
"mean_token_accuracy": 0.20307156443595886,
|
|
"num_tokens": 27990532.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.070600748062134,
|
|
"epoch": 1.1923764145324598,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048702644615886137,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.19978172183036805,
|
|
"num_tokens": 28004591.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.061868476867676,
|
|
"epoch": 1.1929720071471115,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004870121817109079,
|
|
"loss": 4.8933,
|
|
"mean_token_accuracy": 0.20176432132720948,
|
|
"num_tokens": 28019634.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.051878595352173,
|
|
"epoch": 1.193567599761763,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048699790965842224,
|
|
"loss": 4.8951,
|
|
"mean_token_accuracy": 0.19894930571317673,
|
|
"num_tokens": 28035388.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.052830171585083,
|
|
"epoch": 1.1941631923764144,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004869836300019162,
|
|
"loss": 4.8899,
|
|
"mean_token_accuracy": 0.1950811728835106,
|
|
"num_tokens": 28049666.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 4.989547252655029,
|
|
"epoch": 1.1947587849910661,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004869693427419021,
|
|
"loss": 4.787,
|
|
"mean_token_accuracy": 0.20066587775945663,
|
|
"num_tokens": 28065059.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 4.876992082595825,
|
|
"epoch": 1.1953543776057176,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004869550478788922,
|
|
"loss": 4.63,
|
|
"mean_token_accuracy": 0.22485224455595015,
|
|
"num_tokens": 28077567.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 4.9262927055358885,
|
|
"epoch": 1.1959499702203693,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048694074541339946,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.20799451023340226,
|
|
"num_tokens": 28089741.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.040322875976562,
|
|
"epoch": 1.1965455628350208,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048692643534593665,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.1954711377620697,
|
|
"num_tokens": 28104962.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 4.975605249404907,
|
|
"epoch": 1.1971411554496725,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004869121176770173,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.20484752357006072,
|
|
"num_tokens": 28119754.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 4.994054508209229,
|
|
"epoch": 1.197736748064324,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048689779240715484,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.2052476719021797,
|
|
"num_tokens": 28133638.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 4.956996154785156,
|
|
"epoch": 1.1983323406789756,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048688345953686296,
|
|
"loss": 4.8218,
|
|
"mean_token_accuracy": 0.2066796451807022,
|
|
"num_tokens": 28146706.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.069190549850464,
|
|
"epoch": 1.1989279332936271,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048686911906665597,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.19462414234876632,
|
|
"num_tokens": 28159104.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 4.995441913604736,
|
|
"epoch": 1.1995235259082788,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048685477099704816,
|
|
"loss": 4.8831,
|
|
"mean_token_accuracy": 0.2015887975692749,
|
|
"num_tokens": 28173317.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 4.946767711639405,
|
|
"epoch": 1.2001191185229303,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048684041532855415,
|
|
"loss": 4.7968,
|
|
"mean_token_accuracy": 0.20589756071567536,
|
|
"num_tokens": 28186946.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 4.992169570922852,
|
|
"epoch": 1.2007147111375818,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004868260520616889,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.19597677886486053,
|
|
"num_tokens": 28201416.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.073597192764282,
|
|
"epoch": 1.2013103037522335,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048681168119696757,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.2002493515610695,
|
|
"num_tokens": 28215608.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 4.988716411590576,
|
|
"epoch": 1.2019058963668852,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004867973027349056,
|
|
"loss": 4.8541,
|
|
"mean_token_accuracy": 0.196384297311306,
|
|
"num_tokens": 28228046.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 4.980427980422974,
|
|
"epoch": 1.2025014889815366,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004867829166760188,
|
|
"loss": 4.8186,
|
|
"mean_token_accuracy": 0.19977599382400513,
|
|
"num_tokens": 28241287.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 4.983764553070069,
|
|
"epoch": 1.2030970815961881,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048676852302082305,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.2044236719608307,
|
|
"num_tokens": 28253600.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 4.9118200778961185,
|
|
"epoch": 1.2036926742108398,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004867541217698347,
|
|
"loss": 4.7436,
|
|
"mean_token_accuracy": 0.19942502528429032,
|
|
"num_tokens": 28266324.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.044206523895264,
|
|
"epoch": 1.2042882668254913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048673971292357025,
|
|
"loss": 4.8174,
|
|
"mean_token_accuracy": 0.20301806032657624,
|
|
"num_tokens": 28281222.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.012623023986817,
|
|
"epoch": 1.204883859440143,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004867252964825467,
|
|
"loss": 4.8334,
|
|
"mean_token_accuracy": 0.19854243248701095,
|
|
"num_tokens": 28296529.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 4.940370368957519,
|
|
"epoch": 1.2054794520547945,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048671087244728093,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.20826301574707032,
|
|
"num_tokens": 28311620.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 4.954184341430664,
|
|
"epoch": 1.2060750446694462,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048669644081829035,
|
|
"loss": 4.7208,
|
|
"mean_token_accuracy": 0.21065933853387833,
|
|
"num_tokens": 28324762.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.002648735046387,
|
|
"epoch": 1.2066706372840976,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048668200159609267,
|
|
"loss": 4.899,
|
|
"mean_token_accuracy": 0.19716682732105256,
|
|
"num_tokens": 28338856.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 4.897027015686035,
|
|
"epoch": 1.2072662298987493,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048666755478120576,
|
|
"loss": 4.6272,
|
|
"mean_token_accuracy": 0.21894955188035964,
|
|
"num_tokens": 28352171.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 4.978466987609863,
|
|
"epoch": 1.2078618225134008,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048665310037414777,
|
|
"loss": 4.7832,
|
|
"mean_token_accuracy": 0.2049686297774315,
|
|
"num_tokens": 28365027.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.009418487548828,
|
|
"epoch": 1.2084574151280525,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004866386383754373,
|
|
"loss": 4.8146,
|
|
"mean_token_accuracy": 0.2057540476322174,
|
|
"num_tokens": 28378495.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 4.955214500427246,
|
|
"epoch": 1.209053007742704,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004866241687855929,
|
|
"loss": 4.8507,
|
|
"mean_token_accuracy": 0.19562555104494095,
|
|
"num_tokens": 28392708.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 4.950752639770508,
|
|
"epoch": 1.2096486003573557,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048660969160513367,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.21031655073165895,
|
|
"num_tokens": 28406041.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.037499904632568,
|
|
"epoch": 1.2102441929720071,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004865952068345788,
|
|
"loss": 4.9095,
|
|
"mean_token_accuracy": 0.19157772660255432,
|
|
"num_tokens": 28421522.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.014294147491455,
|
|
"epoch": 1.2108397855866588,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048658071447444794,
|
|
"loss": 4.8731,
|
|
"mean_token_accuracy": 0.19678382724523544,
|
|
"num_tokens": 28437974.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.097883176803589,
|
|
"epoch": 1.2114353782013103,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004865662145252609,
|
|
"loss": 4.8669,
|
|
"mean_token_accuracy": 0.19756295382976533,
|
|
"num_tokens": 28452111.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.0162670612335205,
|
|
"epoch": 1.2120309708159618,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048655170698753774,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.19619808793067933,
|
|
"num_tokens": 28466008.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 4.965204954147339,
|
|
"epoch": 1.2126265634306135,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048653719186179874,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.20905969887971879,
|
|
"num_tokens": 28478610.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 4.939093494415284,
|
|
"epoch": 1.213222156045265,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004865226691485646,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.20838161259889604,
|
|
"num_tokens": 28493372.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.056162357330322,
|
|
"epoch": 1.2138177486599167,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048650813884835634,
|
|
"loss": 4.8631,
|
|
"mean_token_accuracy": 0.19844866693019866,
|
|
"num_tokens": 28507704.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 4.963916635513305,
|
|
"epoch": 1.2144133412745681,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004864936009616949,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.19963490962982178,
|
|
"num_tokens": 28522249.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.052824687957764,
|
|
"epoch": 1.2150089338892198,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000486479055489102,
|
|
"loss": 4.8741,
|
|
"mean_token_accuracy": 0.20235439091920854,
|
|
"num_tokens": 28534285.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 4.985045051574707,
|
|
"epoch": 1.2156045265038713,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004864645024310991,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.2063760757446289,
|
|
"num_tokens": 28547932.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 4.981267833709717,
|
|
"epoch": 1.216200119118523,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004864499417882084,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.2062734290957451,
|
|
"num_tokens": 28559853.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 4.939281892776489,
|
|
"epoch": 1.2167957117331745,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000486435373560952,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.1940043419599533,
|
|
"num_tokens": 28573048.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.103665924072265,
|
|
"epoch": 1.2173913043478262,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048642079774985255,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.19270424842834472,
|
|
"num_tokens": 28586481.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.066869306564331,
|
|
"epoch": 1.2179868969624776,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048640621435543286,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.19683153331279754,
|
|
"num_tokens": 28601003.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.034177303314209,
|
|
"epoch": 1.2185824895771293,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000486391623378216,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.20597000569105148,
|
|
"num_tokens": 28614290.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.131781005859375,
|
|
"epoch": 1.2191780821917808,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004863770248187253,
|
|
"loss": 4.9469,
|
|
"mean_token_accuracy": 0.19353623688220978,
|
|
"num_tokens": 28627604.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.0900050640106205,
|
|
"epoch": 1.2197736748064325,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004863624186774844,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.19957030266523362,
|
|
"num_tokens": 28640957.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 4.916883897781372,
|
|
"epoch": 1.220369267421084,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004863478049550171,
|
|
"loss": 4.8186,
|
|
"mean_token_accuracy": 0.20411536544561387,
|
|
"num_tokens": 28654664.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.008029937744141,
|
|
"epoch": 1.2209648600357355,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048633318365184783,
|
|
"loss": 4.8082,
|
|
"mean_token_accuracy": 0.20009994357824326,
|
|
"num_tokens": 28669584.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 4.948563051223755,
|
|
"epoch": 1.2215604526503872,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048631855476850074,
|
|
"loss": 4.8249,
|
|
"mean_token_accuracy": 0.20302773863077164,
|
|
"num_tokens": 28684253.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 4.922312259674072,
|
|
"epoch": 1.2221560452650386,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048630391830550076,
|
|
"loss": 4.7064,
|
|
"mean_token_accuracy": 0.20707712769508363,
|
|
"num_tokens": 28698164.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 4.927629613876343,
|
|
"epoch": 1.2227516378796903,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004862892742633727,
|
|
"loss": 4.7822,
|
|
"mean_token_accuracy": 0.2090747818350792,
|
|
"num_tokens": 28712054.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.028921604156494,
|
|
"epoch": 1.2233472304943418,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000486274622642642,
|
|
"loss": 4.8989,
|
|
"mean_token_accuracy": 0.1987484946846962,
|
|
"num_tokens": 28725243.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.0567232131958,
|
|
"epoch": 1.2239428231089935,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048625996344383405,
|
|
"loss": 4.8907,
|
|
"mean_token_accuracy": 0.1959948718547821,
|
|
"num_tokens": 28740584.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.029776477813721,
|
|
"epoch": 1.224538415723645,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004862452966674747,
|
|
"loss": 4.8869,
|
|
"mean_token_accuracy": 0.19825668781995773,
|
|
"num_tokens": 28753390.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 4.976008319854737,
|
|
"epoch": 1.2251340083382967,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004862306223140901,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.20190440118312836,
|
|
"num_tokens": 28766479.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.0206667423248295,
|
|
"epoch": 1.2257296009529481,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004862159403842064,
|
|
"loss": 4.8411,
|
|
"mean_token_accuracy": 0.19884761273860932,
|
|
"num_tokens": 28778670.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.010876750946045,
|
|
"epoch": 1.2263251935675998,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048620125087835045,
|
|
"loss": 4.9209,
|
|
"mean_token_accuracy": 0.19564347714185715,
|
|
"num_tokens": 28790774.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.036612033843994,
|
|
"epoch": 1.2269207861822513,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004861865537970489,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.20207082331180573,
|
|
"num_tokens": 28805743.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.032458353042602,
|
|
"epoch": 1.227516378796903,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004861718491408291,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.19579292386770247,
|
|
"num_tokens": 28822125.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.042454195022583,
|
|
"epoch": 1.2281119714115545,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004861571369102184,
|
|
"loss": 4.8915,
|
|
"mean_token_accuracy": 0.19770726710557937,
|
|
"num_tokens": 28835718.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 4.997860097885132,
|
|
"epoch": 1.2287075640262062,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004861424171057445,
|
|
"loss": 4.8252,
|
|
"mean_token_accuracy": 0.20016597360372543,
|
|
"num_tokens": 28848874.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 4.958086109161377,
|
|
"epoch": 1.2293031566408577,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004861276897279354,
|
|
"loss": 4.8051,
|
|
"mean_token_accuracy": 0.20358021259307862,
|
|
"num_tokens": 28861915.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 4.9897270679473875,
|
|
"epoch": 1.2298987492555091,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004861129547773194,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.19669397324323654,
|
|
"num_tokens": 28875500.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.118544197082519,
|
|
"epoch": 1.2304943418701608,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048609821225442494,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.19924269765615463,
|
|
"num_tokens": 28888480.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.015426397323608,
|
|
"epoch": 1.2310899344848123,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004860834621597808,
|
|
"loss": 4.8373,
|
|
"mean_token_accuracy": 0.20254217237234115,
|
|
"num_tokens": 28904680.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.016291952133178,
|
|
"epoch": 1.231685527099464,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048606870449391604,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.1995968297123909,
|
|
"num_tokens": 28919201.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 4.953518629074097,
|
|
"epoch": 1.2322811197141155,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004860539392573601,
|
|
"loss": 4.7199,
|
|
"mean_token_accuracy": 0.21410973519086837,
|
|
"num_tokens": 28930934.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 4.9659356594085695,
|
|
"epoch": 1.2328767123287672,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048603916645064256,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.21028620898723602,
|
|
"num_tokens": 28942837.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 4.987350416183472,
|
|
"epoch": 1.2334723049434186,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048602438607429313,
|
|
"loss": 4.8108,
|
|
"mean_token_accuracy": 0.20151353478431702,
|
|
"num_tokens": 28956449.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 4.994728899002075,
|
|
"epoch": 1.2340678975580703,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048600959812884217,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.19707950800657273,
|
|
"num_tokens": 28969654.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.0245307922363285,
|
|
"epoch": 1.2346634901727218,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004859948026148199,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.18679238855838776,
|
|
"num_tokens": 28985242.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.048918008804321,
|
|
"epoch": 1.2352590827873735,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048597999953275717,
|
|
"loss": 4.8538,
|
|
"mean_token_accuracy": 0.19789346009492875,
|
|
"num_tokens": 29001167.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 4.974992990493774,
|
|
"epoch": 1.235854675402025,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048596518888318485,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.2030254513025284,
|
|
"num_tokens": 29015379.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.0061346054077145,
|
|
"epoch": 1.2364502680166767,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048595037066663434,
|
|
"loss": 4.8254,
|
|
"mean_token_accuracy": 0.19964139759540558,
|
|
"num_tokens": 29029596.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 4.947215032577515,
|
|
"epoch": 1.2370458606313282,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004859355448836369,
|
|
"loss": 4.7496,
|
|
"mean_token_accuracy": 0.20929126143455506,
|
|
"num_tokens": 29043259.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 4.958660697937011,
|
|
"epoch": 1.2376414532459799,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048592071153472446,
|
|
"loss": 4.8431,
|
|
"mean_token_accuracy": 0.20294266939163208,
|
|
"num_tokens": 29056084.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.016014862060547,
|
|
"epoch": 1.2382370458606313,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048590587062042907,
|
|
"loss": 4.7838,
|
|
"mean_token_accuracy": 0.20493665635585784,
|
|
"num_tokens": 29069785.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 4.981940793991089,
|
|
"epoch": 1.2388326384752828,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004858910221412829,
|
|
"loss": 4.7508,
|
|
"mean_token_accuracy": 0.21534116417169571,
|
|
"num_tokens": 29083751.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 4.9786107540130615,
|
|
"epoch": 1.2394282310899345,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004858761660978188,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.20331796407699584,
|
|
"num_tokens": 29097398.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.06610894203186,
|
|
"epoch": 1.240023823704586,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004858613024905694,
|
|
"loss": 4.8835,
|
|
"mean_token_accuracy": 0.1947340413928032,
|
|
"num_tokens": 29111787.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.009963655471802,
|
|
"epoch": 1.2406194163192377,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004858464313200679,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.20373031944036485,
|
|
"num_tokens": 29127130.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.006883001327514,
|
|
"epoch": 1.2412150089338891,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004858315525868478,
|
|
"loss": 4.7767,
|
|
"mean_token_accuracy": 0.2025809109210968,
|
|
"num_tokens": 29140343.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.025279188156128,
|
|
"epoch": 1.2418106015485408,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004858166662914426,
|
|
"loss": 4.8716,
|
|
"mean_token_accuracy": 0.20028401613235475,
|
|
"num_tokens": 29153710.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.025206565856934,
|
|
"epoch": 1.2424061941631923,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004858017724343864,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.20203285813331603,
|
|
"num_tokens": 29167736.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.000972270965576,
|
|
"epoch": 1.243001786777844,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048578687101621346,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.20206585228443147,
|
|
"num_tokens": 29179789.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 4.936364078521729,
|
|
"epoch": 1.2435973793924955,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000485771962037458,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.20134733319282533,
|
|
"num_tokens": 29192449.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.016347026824951,
|
|
"epoch": 1.2441929720071472,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048575704549865505,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.20628636181354523,
|
|
"num_tokens": 29203863.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 4.990973806381225,
|
|
"epoch": 1.2447885646217987,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048574212140033965,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.196600241959095,
|
|
"num_tokens": 29217937.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 4.997859811782837,
|
|
"epoch": 1.2453841572364504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048572718974304683,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.2103799268603325,
|
|
"num_tokens": 29231706.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 4.9674327850341795,
|
|
"epoch": 1.2459797498511018,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048571225052731245,
|
|
"loss": 4.7855,
|
|
"mean_token_accuracy": 0.21549329906702042,
|
|
"num_tokens": 29242552.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 4.991679859161377,
|
|
"epoch": 1.2465753424657535,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048569730375367217,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.20479784160852432,
|
|
"num_tokens": 29256770.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.010225868225097,
|
|
"epoch": 1.247170935080405,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048568234942266217,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.203346411883831,
|
|
"num_tokens": 29270711.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.076801776885986,
|
|
"epoch": 1.2477665276950565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048566738753481886,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.18459630161523818,
|
|
"num_tokens": 29285410.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.112462759017944,
|
|
"epoch": 1.2483621203097082,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004856524180906789,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.20168566107749938,
|
|
"num_tokens": 29299126.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.017069482803345,
|
|
"epoch": 1.2489577129243596,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048563744109077916,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.1979082852602005,
|
|
"num_tokens": 29313261.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 4.975375509262085,
|
|
"epoch": 1.2495533055390113,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004856224565356569,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.20931822210550308,
|
|
"num_tokens": 29327618.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.005472183227539,
|
|
"epoch": 1.2501488981536628,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048560746442584965,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.2038499101996422,
|
|
"num_tokens": 29342055.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 4.911301136016846,
|
|
"epoch": 1.2507444907683145,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000485592464761895,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.21117192655801773,
|
|
"num_tokens": 29355943.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 4.996909523010254,
|
|
"epoch": 1.251340083382966,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004855774575443311,
|
|
"loss": 4.8346,
|
|
"mean_token_accuracy": 0.20227280408143997,
|
|
"num_tokens": 29368462.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.055750465393066,
|
|
"epoch": 1.2519356759976177,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004855624427736961,
|
|
"loss": 4.9163,
|
|
"mean_token_accuracy": 0.19652855396270752,
|
|
"num_tokens": 29384441.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.0906219482421875,
|
|
"epoch": 1.2525312686122692,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004855474204505287,
|
|
"loss": 4.9126,
|
|
"mean_token_accuracy": 0.1928618848323822,
|
|
"num_tokens": 29397802.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 4.949554204940796,
|
|
"epoch": 1.2531268612269209,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048553239057536757,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.2103222742676735,
|
|
"num_tokens": 29411999.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 4.994694805145263,
|
|
"epoch": 1.2537224538415723,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048551735314875203,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.20730260461568834,
|
|
"num_tokens": 29424844.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 4.982161283493042,
|
|
"epoch": 1.254318046456224,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004855023081712212,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.20454542487859725,
|
|
"num_tokens": 29438245.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 4.996662759780884,
|
|
"epoch": 1.2549136390708755,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004854872556433149,
|
|
"loss": 4.8267,
|
|
"mean_token_accuracy": 0.19924525916576385,
|
|
"num_tokens": 29453304.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 4.927427434921265,
|
|
"epoch": 1.2555092316855272,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004854721955655729,
|
|
"loss": 4.75,
|
|
"mean_token_accuracy": 0.2055121049284935,
|
|
"num_tokens": 29466662.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 4.9697192192077635,
|
|
"epoch": 1.2561048243001787,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048545712793853554,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.20389226973056793,
|
|
"num_tokens": 29480953.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.009240055084229,
|
|
"epoch": 1.2567004169148301,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004854420527627431,
|
|
"loss": 4.8662,
|
|
"mean_token_accuracy": 0.19254371970891954,
|
|
"num_tokens": 29495630.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.0712470531463625,
|
|
"epoch": 1.2572960095294818,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048542697003873636,
|
|
"loss": 4.8358,
|
|
"mean_token_accuracy": 0.20458318740129472,
|
|
"num_tokens": 29509426.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 4.872716188430786,
|
|
"epoch": 1.2578916021441335,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048541187976705645,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.20799392014741896,
|
|
"num_tokens": 29521836.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.024547052383423,
|
|
"epoch": 1.258487194758785,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004853967819482445,
|
|
"loss": 4.8753,
|
|
"mean_token_accuracy": 0.19538291841745375,
|
|
"num_tokens": 29536825.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.039446210861206,
|
|
"epoch": 1.2590827873734365,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000485381676582842,
|
|
"loss": 4.8751,
|
|
"mean_token_accuracy": 0.19611568599939347,
|
|
"num_tokens": 29549972.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 4.9899006366729735,
|
|
"epoch": 1.2596783799880882,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048536656367139085,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.2055298075079918,
|
|
"num_tokens": 29563521.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 4.977808570861816,
|
|
"epoch": 1.2602739726027397,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048535144321443317,
|
|
"loss": 4.781,
|
|
"mean_token_accuracy": 0.2078685373067856,
|
|
"num_tokens": 29576915.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 4.970290803909302,
|
|
"epoch": 1.2608695652173914,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048533631521251115,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.2033543974161148,
|
|
"num_tokens": 29590660.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 4.9992858409881595,
|
|
"epoch": 1.2614651578320428,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004853211796661675,
|
|
"loss": 4.8052,
|
|
"mean_token_accuracy": 0.20469695776700975,
|
|
"num_tokens": 29606364.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.025606441497803,
|
|
"epoch": 1.2620607504466945,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004853060365759451,
|
|
"loss": 4.7986,
|
|
"mean_token_accuracy": 0.20436286479234694,
|
|
"num_tokens": 29621361.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 4.962552261352539,
|
|
"epoch": 1.262656343061346,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048529088594238714,
|
|
"loss": 4.827,
|
|
"mean_token_accuracy": 0.19921231716871263,
|
|
"num_tokens": 29634945.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.00734691619873,
|
|
"epoch": 1.2632519356759977,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004852757277660369,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.2102778062224388,
|
|
"num_tokens": 29649080.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.047264289855957,
|
|
"epoch": 1.2638475282906492,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048526056204743827,
|
|
"loss": 4.9089,
|
|
"mean_token_accuracy": 0.19170040488243104,
|
|
"num_tokens": 29663469.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.020766544342041,
|
|
"epoch": 1.2644431209053009,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048524538878713517,
|
|
"loss": 4.8226,
|
|
"mean_token_accuracy": 0.19963158369064332,
|
|
"num_tokens": 29676163.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 4.989909982681274,
|
|
"epoch": 1.2650387135199523,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004852302079856718,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.20900487899780273,
|
|
"num_tokens": 29690237.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.051612854003906,
|
|
"epoch": 1.2656343061346038,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004852150196435927,
|
|
"loss": 4.8675,
|
|
"mean_token_accuracy": 0.2018847793340683,
|
|
"num_tokens": 29704924.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 4.948747634887695,
|
|
"epoch": 1.2662298987492555,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048519982376144254,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.2100688934326172,
|
|
"num_tokens": 29718855.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.001461124420166,
|
|
"epoch": 1.2668254913639072,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048518462033976653,
|
|
"loss": 4.8731,
|
|
"mean_token_accuracy": 0.19615048468112944,
|
|
"num_tokens": 29732402.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 4.981675529479981,
|
|
"epoch": 1.2674210839785587,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048516940937910996,
|
|
"loss": 4.8894,
|
|
"mean_token_accuracy": 0.20072223246097565,
|
|
"num_tokens": 29747767.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.08253755569458,
|
|
"epoch": 1.2680166765932102,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004851541908800184,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.20042402446269988,
|
|
"num_tokens": 29759178.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.04611873626709,
|
|
"epoch": 1.2686122692078619,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048513896484303763,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.20206507295370102,
|
|
"num_tokens": 29773164.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 4.918459701538086,
|
|
"epoch": 1.2692078618225133,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048512373126871383,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.20706605464220046,
|
|
"num_tokens": 29786783.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.013127183914184,
|
|
"epoch": 1.269803454437165,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004851084901575935,
|
|
"loss": 4.8352,
|
|
"mean_token_accuracy": 0.20152673572301866,
|
|
"num_tokens": 29800920.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 4.996255731582641,
|
|
"epoch": 1.2703990470518165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048509324151022325,
|
|
"loss": 4.7615,
|
|
"mean_token_accuracy": 0.20561096519231797,
|
|
"num_tokens": 29815100.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 4.936759805679321,
|
|
"epoch": 1.2709946396664682,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048507798532715005,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.19942035973072053,
|
|
"num_tokens": 29827513.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.0625543117523195,
|
|
"epoch": 1.2715902322811197,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000485062721608921,
|
|
"loss": 4.8836,
|
|
"mean_token_accuracy": 0.19919665306806564,
|
|
"num_tokens": 29840111.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 4.99708399772644,
|
|
"epoch": 1.2721858248957714,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004850474503560837,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.201425002515316,
|
|
"num_tokens": 29854007.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 4.973114681243897,
|
|
"epoch": 1.2727814175104228,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004850321715691858,
|
|
"loss": 4.7847,
|
|
"mean_token_accuracy": 0.21019789278507234,
|
|
"num_tokens": 29868743.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 4.9958068370819095,
|
|
"epoch": 1.2733770101250745,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048501688524877555,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.20411428809165955,
|
|
"num_tokens": 29882958.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 4.996694660186767,
|
|
"epoch": 1.273972602739726,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000485001591395401,
|
|
"loss": 4.8261,
|
|
"mean_token_accuracy": 0.20220931321382524,
|
|
"num_tokens": 29898769.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 4.936664342880249,
|
|
"epoch": 1.2745681953543775,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004849862900096108,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.2078769713640213,
|
|
"num_tokens": 29914149.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 4.904691696166992,
|
|
"epoch": 1.2751637879690292,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048497098109195387,
|
|
"loss": 4.6931,
|
|
"mean_token_accuracy": 0.20771493315696715,
|
|
"num_tokens": 29927092.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 4.975332117080688,
|
|
"epoch": 1.2757593805836809,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048495566464297913,
|
|
"loss": 4.7778,
|
|
"mean_token_accuracy": 0.2063599184155464,
|
|
"num_tokens": 29942033.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.067654466629028,
|
|
"epoch": 1.2763549731983324,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004849403406632361,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.19740158766508104,
|
|
"num_tokens": 29954987.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 4.958537197113037,
|
|
"epoch": 1.2769505658129838,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004849250091532744,
|
|
"loss": 4.8398,
|
|
"mean_token_accuracy": 0.2120709463953972,
|
|
"num_tokens": 29968227.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.015549802780152,
|
|
"epoch": 1.2775461584276355,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048490967011364394,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.21082098931074142,
|
|
"num_tokens": 29981234.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.124855852127075,
|
|
"epoch": 1.278141751042287,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048489432354489496,
|
|
"loss": 4.9762,
|
|
"mean_token_accuracy": 0.20014822483062744,
|
|
"num_tokens": 29994420.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 4.983826303482056,
|
|
"epoch": 1.2787373436569387,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048487896944757777,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.20535205751657487,
|
|
"num_tokens": 30007241.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 4.981337404251098,
|
|
"epoch": 1.2793329362715902,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004848636078222433,
|
|
"loss": 4.8433,
|
|
"mean_token_accuracy": 0.20049768090248107,
|
|
"num_tokens": 30021804.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.056884717941284,
|
|
"epoch": 1.2799285288862419,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004848482386694424,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.2018810659646988,
|
|
"num_tokens": 30035782.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 4.985973072052002,
|
|
"epoch": 1.2805241215008933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048483286198972627,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.20039381980895996,
|
|
"num_tokens": 30051157.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 4.984639120101929,
|
|
"epoch": 1.281119714115545,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004848174777836466,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.20193452388048172,
|
|
"num_tokens": 30066360.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.053862237930298,
|
|
"epoch": 1.2817153067301965,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004848020860517552,
|
|
"loss": 4.873,
|
|
"mean_token_accuracy": 0.20172751396894456,
|
|
"num_tokens": 30079714.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 4.958968782424927,
|
|
"epoch": 1.2823108993448482,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000484786686794604,
|
|
"loss": 4.7785,
|
|
"mean_token_accuracy": 0.20954974740743637,
|
|
"num_tokens": 30091880.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.0217901229858395,
|
|
"epoch": 1.2829064919594997,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048477128001274557,
|
|
"loss": 4.8623,
|
|
"mean_token_accuracy": 0.2050068974494934,
|
|
"num_tokens": 30105211.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 4.998468828201294,
|
|
"epoch": 1.2835020845741512,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048475586570673223,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.201315800845623,
|
|
"num_tokens": 30121064.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 4.940003824234009,
|
|
"epoch": 1.2840976771888029,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004847404438771172,
|
|
"loss": 4.8015,
|
|
"mean_token_accuracy": 0.20540062785148622,
|
|
"num_tokens": 30135347.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 4.962780332565307,
|
|
"epoch": 1.2846932698034546,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048472501452445334,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.2025151953101158,
|
|
"num_tokens": 30149652.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.0898980617523195,
|
|
"epoch": 1.285288862418106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004847095776492942,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.18917446732521057,
|
|
"num_tokens": 30165003.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.054747724533081,
|
|
"epoch": 1.2858844550327575,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048469413325219355,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.1998534843325615,
|
|
"num_tokens": 30179567.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 4.930440425872803,
|
|
"epoch": 1.2864800476474092,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048467868133370527,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.20806074440479277,
|
|
"num_tokens": 30193773.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 4.988194704055786,
|
|
"epoch": 1.2870756402620607,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048466322189438354,
|
|
"loss": 4.7614,
|
|
"mean_token_accuracy": 0.2113039970397949,
|
|
"num_tokens": 30208233.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.042905330657959,
|
|
"epoch": 1.2876712328767124,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048464775493478303,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.19076564013957978,
|
|
"num_tokens": 30223136.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 4.988844585418701,
|
|
"epoch": 1.2882668254913638,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048463228045545837,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.21590242981910707,
|
|
"num_tokens": 30236549.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 4.944187450408935,
|
|
"epoch": 1.2888624181060155,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048461679845696466,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.20426671355962753,
|
|
"num_tokens": 30251870.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.013523149490356,
|
|
"epoch": 1.289458010720667,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004846013089398572,
|
|
"loss": 4.8349,
|
|
"mean_token_accuracy": 0.19976818114519118,
|
|
"num_tokens": 30266649.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 4.963063907623291,
|
|
"epoch": 1.2900536033353187,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048458581190469153,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.20812999755144118,
|
|
"num_tokens": 30279811.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 4.953090333938599,
|
|
"epoch": 1.2906491959499702,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004845703073520236,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.2052966445684433,
|
|
"num_tokens": 30291950.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 4.93378267288208,
|
|
"epoch": 1.2912447885646219,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004845547952824095,
|
|
"loss": 4.7712,
|
|
"mean_token_accuracy": 0.2052724227309227,
|
|
"num_tokens": 30304289.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 4.962939977645874,
|
|
"epoch": 1.2918403811792734,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048453927569640557,
|
|
"loss": 4.863,
|
|
"mean_token_accuracy": 0.2041819930076599,
|
|
"num_tokens": 30318182.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.015676689147949,
|
|
"epoch": 1.2924359737939248,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048452374859456855,
|
|
"loss": 4.815,
|
|
"mean_token_accuracy": 0.20813145488500595,
|
|
"num_tokens": 30330470.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 4.955663013458252,
|
|
"epoch": 1.2930315664085765,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004845082139774553,
|
|
"loss": 4.7641,
|
|
"mean_token_accuracy": 0.20712753832340242,
|
|
"num_tokens": 30345544.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 4.970620965957641,
|
|
"epoch": 1.2936271590232282,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004844926718456231,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.20926581472158431,
|
|
"num_tokens": 30358952.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 4.988886737823487,
|
|
"epoch": 1.2942227516378797,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004844771221996293,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.20884154736995697,
|
|
"num_tokens": 30372652.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 4.976165151596069,
|
|
"epoch": 1.2948183442525312,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004844615650400318,
|
|
"loss": 4.8115,
|
|
"mean_token_accuracy": 0.20288865864276887,
|
|
"num_tokens": 30385439.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 4.960357666015625,
|
|
"epoch": 1.2954139368671829,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048444600036738844,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.2082279220223427,
|
|
"num_tokens": 30399006.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 4.998214769363403,
|
|
"epoch": 1.2960095294818343,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048443042818225766,
|
|
"loss": 4.7993,
|
|
"mean_token_accuracy": 0.20508748143911362,
|
|
"num_tokens": 30412143.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 4.997975826263428,
|
|
"epoch": 1.296605122096486,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048441484848519786,
|
|
"loss": 4.865,
|
|
"mean_token_accuracy": 0.202947998046875,
|
|
"num_tokens": 30424874.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.094007968902588,
|
|
"epoch": 1.2972007147111375,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048439926127676796,
|
|
"loss": 4.8856,
|
|
"mean_token_accuracy": 0.19894395768642426,
|
|
"num_tokens": 30438938.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.022711086273193,
|
|
"epoch": 1.2977963073257892,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048438366655752707,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.20033160597085953,
|
|
"num_tokens": 30453470.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 4.96672248840332,
|
|
"epoch": 1.2983918999404407,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004843680643280345,
|
|
"loss": 4.8339,
|
|
"mean_token_accuracy": 0.20396167337894439,
|
|
"num_tokens": 30466463.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.083738851547241,
|
|
"epoch": 1.2989874925550924,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004843524545888498,
|
|
"loss": 4.8493,
|
|
"mean_token_accuracy": 0.20348720103502274,
|
|
"num_tokens": 30481241.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 4.976214218139648,
|
|
"epoch": 1.2995830851697439,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000484336837340533,
|
|
"loss": 4.7427,
|
|
"mean_token_accuracy": 0.2009783312678337,
|
|
"num_tokens": 30493346.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 4.892196321487427,
|
|
"epoch": 1.3001786777843956,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048432121258364417,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.19712637960910798,
|
|
"num_tokens": 30510073.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.0116692066192625,
|
|
"epoch": 1.300774270399047,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004843055803187438,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.19756914377212526,
|
|
"num_tokens": 30524480.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.107074022293091,
|
|
"epoch": 1.3013698630136985,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048428994054639256,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.19315995275974274,
|
|
"num_tokens": 30539502.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.0531463623046875,
|
|
"epoch": 1.3019654556283502,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004842742932671514,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.19647155404090882,
|
|
"num_tokens": 30553974.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 4.996968126296997,
|
|
"epoch": 1.302561048243002,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004842586384815817,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.20447124689817428,
|
|
"num_tokens": 30567445.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 4.9253950119018555,
|
|
"epoch": 1.3031566408576534,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004842429761902448,
|
|
"loss": 4.8322,
|
|
"mean_token_accuracy": 0.20524459928274155,
|
|
"num_tokens": 30581835.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 4.96894154548645,
|
|
"epoch": 1.3037522334723048,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048422730639370256,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.2071860834956169,
|
|
"num_tokens": 30595851.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 4.9820472240448,
|
|
"epoch": 1.3043478260869565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004842116290925171,
|
|
"loss": 4.7852,
|
|
"mean_token_accuracy": 0.20891092866659164,
|
|
"num_tokens": 30610732.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 4.960160207748413,
|
|
"epoch": 1.3049434187016082,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004841959442872505,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.20218420028686523,
|
|
"num_tokens": 30624836.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 4.93225884437561,
|
|
"epoch": 1.3055390113162597,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004841802519784656,
|
|
"loss": 4.7308,
|
|
"mean_token_accuracy": 0.2081671714782715,
|
|
"num_tokens": 30638860.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 4.949984884262085,
|
|
"epoch": 1.3061346039309112,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048416455216672525,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.2010616734623909,
|
|
"num_tokens": 30652660.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.047907781600952,
|
|
"epoch": 1.3067301965455629,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048414884485259235,
|
|
"loss": 4.8156,
|
|
"mean_token_accuracy": 0.2035391792654991,
|
|
"num_tokens": 30664181.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 4.947963809967041,
|
|
"epoch": 1.3073257891602144,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004841331300366306,
|
|
"loss": 4.8256,
|
|
"mean_token_accuracy": 0.20292976796627044,
|
|
"num_tokens": 30676795.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 4.984719753265381,
|
|
"epoch": 1.307921381774866,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004841174077194033,
|
|
"loss": 4.8767,
|
|
"mean_token_accuracy": 0.2013798847794533,
|
|
"num_tokens": 30690173.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.004882860183716,
|
|
"epoch": 1.3085169743895175,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004841016779014747,
|
|
"loss": 4.8798,
|
|
"mean_token_accuracy": 0.2069995731115341,
|
|
"num_tokens": 30704490.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.019241237640381,
|
|
"epoch": 1.3091125670041692,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048408594058340894,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.20558395236730576,
|
|
"num_tokens": 30720148.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.029375600814819,
|
|
"epoch": 1.3097081596188207,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048407019576577037,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.2055475264787674,
|
|
"num_tokens": 30733307.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 4.95620059967041,
|
|
"epoch": 1.3103037522334722,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004840544434491238,
|
|
"loss": 4.7996,
|
|
"mean_token_accuracy": 0.20805155783891677,
|
|
"num_tokens": 30747455.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.12611951828003,
|
|
"epoch": 1.3108993448481239,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048403868363403437,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.1939173623919487,
|
|
"num_tokens": 30763173.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.085270118713379,
|
|
"epoch": 1.3114949374627756,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004840229163210671,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.20389198064804076,
|
|
"num_tokens": 30777676.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 4.979105472564697,
|
|
"epoch": 1.312090530077427,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048400714151078774,
|
|
"loss": 4.8537,
|
|
"mean_token_accuracy": 0.20282281786203385,
|
|
"num_tokens": 30792155.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.055874872207641,
|
|
"epoch": 1.3126861226920785,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048399135920376197,
|
|
"loss": 4.87,
|
|
"mean_token_accuracy": 0.20763079226016998,
|
|
"num_tokens": 30805042.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.009566068649292,
|
|
"epoch": 1.3132817153067302,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000483975569400556,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.20416798442602158,
|
|
"num_tokens": 30821069.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.0198742866516115,
|
|
"epoch": 1.313877307921382,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048395977210173607,
|
|
"loss": 4.8582,
|
|
"mean_token_accuracy": 0.20187818557024,
|
|
"num_tokens": 30835442.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 4.939566373825073,
|
|
"epoch": 1.3144729005360334,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004839439673078689,
|
|
"loss": 4.7467,
|
|
"mean_token_accuracy": 0.21629378348588943,
|
|
"num_tokens": 30848691.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.06324028968811,
|
|
"epoch": 1.3150684931506849,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004839281550195214,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.19813164621591567,
|
|
"num_tokens": 30863023.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.016808700561524,
|
|
"epoch": 1.3156640857653366,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004839123352372606,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.2041790872812271,
|
|
"num_tokens": 30877280.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 4.952530860900879,
|
|
"epoch": 1.316259678379988,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048389650796165407,
|
|
"loss": 4.8664,
|
|
"mean_token_accuracy": 0.2004685416817665,
|
|
"num_tokens": 30891460.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.00219144821167,
|
|
"epoch": 1.3168552709946397,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048388067319326937,
|
|
"loss": 4.778,
|
|
"mean_token_accuracy": 0.20687363892793656,
|
|
"num_tokens": 30906012.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.0613046169281,
|
|
"epoch": 1.3174508636092912,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048386483093267464,
|
|
"loss": 4.9117,
|
|
"mean_token_accuracy": 0.19558082073926925,
|
|
"num_tokens": 30921866.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.061756801605225,
|
|
"epoch": 1.318046456223943,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004838489811804379,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.19370562881231307,
|
|
"num_tokens": 30936526.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 4.9871114730834964,
|
|
"epoch": 1.3186420488385944,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048383312393712784,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.20923946797847748,
|
|
"num_tokens": 30951960.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 4.974361181259155,
|
|
"epoch": 1.3192376414532458,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004838172592033132,
|
|
"loss": 4.8295,
|
|
"mean_token_accuracy": 0.20488090366125106,
|
|
"num_tokens": 30966927.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.0074094295501705,
|
|
"epoch": 1.3198332340678975,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048380138697956294,
|
|
"loss": 4.8455,
|
|
"mean_token_accuracy": 0.20337767750024796,
|
|
"num_tokens": 30980808.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 4.997608232498169,
|
|
"epoch": 1.3204288266825492,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048378550726644644,
|
|
"loss": 4.7557,
|
|
"mean_token_accuracy": 0.20835752487182618,
|
|
"num_tokens": 30995105.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 4.905448532104492,
|
|
"epoch": 1.3210244192972007,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048376962006453324,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.21015170365571975,
|
|
"num_tokens": 31009647.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.0056007385253904,
|
|
"epoch": 1.3216200119118522,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004837537253743932,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.20594711899757384,
|
|
"num_tokens": 31023861.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.005692720413208,
|
|
"epoch": 1.3222156045265039,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004837378231965965,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.2088353991508484,
|
|
"num_tokens": 31037075.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 4.979086780548096,
|
|
"epoch": 1.3228111971411556,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048372191353171333,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.21365648955106736,
|
|
"num_tokens": 31049198.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 4.994476222991944,
|
|
"epoch": 1.323406789755807,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048370599638031464,
|
|
"loss": 4.8334,
|
|
"mean_token_accuracy": 0.20943629890680313,
|
|
"num_tokens": 31063980.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.032133769989014,
|
|
"epoch": 1.3240023823704585,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048369007174297115,
|
|
"loss": 4.8968,
|
|
"mean_token_accuracy": 0.20123893320560454,
|
|
"num_tokens": 31078561.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 4.973922824859619,
|
|
"epoch": 1.3245979749851102,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000483674139620254,
|
|
"loss": 4.7372,
|
|
"mean_token_accuracy": 0.20639688521623611,
|
|
"num_tokens": 31094704.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.02674503326416,
|
|
"epoch": 1.3251935675997617,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004836582000127349,
|
|
"loss": 4.8663,
|
|
"mean_token_accuracy": 0.1935450851917267,
|
|
"num_tokens": 31109003.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 4.939487743377685,
|
|
"epoch": 1.3257891602144134,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004836422529209853,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.2089265689253807,
|
|
"num_tokens": 31123287.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 4.953764200210571,
|
|
"epoch": 1.3263847528290649,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048362629834557743,
|
|
"loss": 4.7772,
|
|
"mean_token_accuracy": 0.2079390123486519,
|
|
"num_tokens": 31138199.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.044088220596313,
|
|
"epoch": 1.3269803454437166,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048361033628708334,
|
|
"loss": 4.8758,
|
|
"mean_token_accuracy": 0.20820365399122237,
|
|
"num_tokens": 31150897.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 4.943185710906983,
|
|
"epoch": 1.327575938058368,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048359436674607573,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.21315356343984604,
|
|
"num_tokens": 31164075.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 4.974759864807129,
|
|
"epoch": 1.3281715306730195,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004835783897231273,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.20404451191425324,
|
|
"num_tokens": 31176274.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 4.980543565750122,
|
|
"epoch": 1.3287671232876712,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048356240521881113,
|
|
"loss": 4.8307,
|
|
"mean_token_accuracy": 0.2016194075345993,
|
|
"num_tokens": 31190227.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.006785678863525,
|
|
"epoch": 1.329362715902323,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004835464132337007,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.20683738738298416,
|
|
"num_tokens": 31201717.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.021809720993042,
|
|
"epoch": 1.3299583085169744,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048353041376836937,
|
|
"loss": 4.8683,
|
|
"mean_token_accuracy": 0.19346913844347,
|
|
"num_tokens": 31216612.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.037441158294678,
|
|
"epoch": 1.3305539011316259,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048351440682339126,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.20313013046979905,
|
|
"num_tokens": 31230146.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 4.956961917877197,
|
|
"epoch": 1.3311494937462776,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048349839239934035,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.21443534940481185,
|
|
"num_tokens": 31245278.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 4.997611093521118,
|
|
"epoch": 1.3317450863609293,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048348237049679105,
|
|
"loss": 4.7971,
|
|
"mean_token_accuracy": 0.20371762067079544,
|
|
"num_tokens": 31260846.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 4.967585659027099,
|
|
"epoch": 1.3323406789755807,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004834663411163182,
|
|
"loss": 4.7992,
|
|
"mean_token_accuracy": 0.20908249467611312,
|
|
"num_tokens": 31274007.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 4.972033214569092,
|
|
"epoch": 1.3329362715902322,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004834503042584966,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.20336466431617736,
|
|
"num_tokens": 31287739.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 4.895246744155884,
|
|
"epoch": 1.333531864204884,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004834342599239015,
|
|
"loss": 4.7261,
|
|
"mean_token_accuracy": 0.20796656608581543,
|
|
"num_tokens": 31301601.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 4.967719268798828,
|
|
"epoch": 1.3341274568195354,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048341820811310834,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.19885379821062088,
|
|
"num_tokens": 31315297.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 4.952856063842773,
|
|
"epoch": 1.334723049434187,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048340214882669296,
|
|
"loss": 4.7217,
|
|
"mean_token_accuracy": 0.20930778831243516,
|
|
"num_tokens": 31330167.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 4.936014699935913,
|
|
"epoch": 1.3353186420488385,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004833860820652314,
|
|
"loss": 4.6526,
|
|
"mean_token_accuracy": 0.21762435585260392,
|
|
"num_tokens": 31343704.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 4.949815130233764,
|
|
"epoch": 1.3359142346634902,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004833700078292998,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.20456861853599548,
|
|
"num_tokens": 31355397.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.085966300964356,
|
|
"epoch": 1.3365098272781417,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004833539261194749,
|
|
"loss": 4.933,
|
|
"mean_token_accuracy": 0.19418812394142151,
|
|
"num_tokens": 31369355.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 4.99163670539856,
|
|
"epoch": 1.3371054198927934,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004833378369363333,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.20040271878242494,
|
|
"num_tokens": 31383322.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 4.95737476348877,
|
|
"epoch": 1.3377010125074449,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004833217402804523,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.2039996176958084,
|
|
"num_tokens": 31396900.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.003328704833985,
|
|
"epoch": 1.3382966051220966,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004833056361524092,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.19726715683937074,
|
|
"num_tokens": 31413277.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 4.9523985385894775,
|
|
"epoch": 1.338892197736748,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004832895245527816,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.20722587555646896,
|
|
"num_tokens": 31428005.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 4.933874702453613,
|
|
"epoch": 1.3394877903513995,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004832734054821474,
|
|
"loss": 4.719,
|
|
"mean_token_accuracy": 0.22012734711170195,
|
|
"num_tokens": 31440418.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.021692991256714,
|
|
"epoch": 1.3400833829660512,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048325727894108487,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.20153998136520385,
|
|
"num_tokens": 31453431.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 4.931689310073852,
|
|
"epoch": 1.340678975580703,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004832411449301723,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.2013021394610405,
|
|
"num_tokens": 31469490.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 4.991297435760498,
|
|
"epoch": 1.3412745681953544,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004832250034499884,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.20814652889966964,
|
|
"num_tokens": 31482110.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.053521728515625,
|
|
"epoch": 1.3418701608100059,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004832088545011122,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.19826634526252745,
|
|
"num_tokens": 31494104.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 4.999327707290649,
|
|
"epoch": 1.3424657534246576,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004831926980841229,
|
|
"loss": 4.8005,
|
|
"mean_token_accuracy": 0.2046685114502907,
|
|
"num_tokens": 31507503.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 4.967664194107056,
|
|
"epoch": 1.343061346039309,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048317653419960007,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.20792919397354126,
|
|
"num_tokens": 31521213.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.023992443084717,
|
|
"epoch": 1.3436569386539607,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048316036284812335,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.19916924983263015,
|
|
"num_tokens": 31536552.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 4.9991011142730715,
|
|
"epoch": 1.3442525312686122,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004831441840302729,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.19871722757816315,
|
|
"num_tokens": 31550663.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 4.888650417327881,
|
|
"epoch": 1.344848123883264,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048312799774662905,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.19837794452905655,
|
|
"num_tokens": 31565694.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 4.9721301078796385,
|
|
"epoch": 1.3454437164979154,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004831118039977722,
|
|
"loss": 4.778,
|
|
"mean_token_accuracy": 0.20848615169525148,
|
|
"num_tokens": 31581533.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 4.990330743789673,
|
|
"epoch": 1.346039309112567,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004830956027842834,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.2078625366091728,
|
|
"num_tokens": 31594439.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 4.989918661117554,
|
|
"epoch": 1.3466349017272186,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004830793941067437,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.2043605074286461,
|
|
"num_tokens": 31609080.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.0067802429199215,
|
|
"epoch": 1.3472304943418703,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048306317796573426,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.20638394802808763,
|
|
"num_tokens": 31623017.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.075393009185791,
|
|
"epoch": 1.3478260869565217,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004830469543618371,
|
|
"loss": 4.8957,
|
|
"mean_token_accuracy": 0.18899365216493608,
|
|
"num_tokens": 31636845.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 4.97397027015686,
|
|
"epoch": 1.3484216795711732,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004830307232956339,
|
|
"loss": 4.8188,
|
|
"mean_token_accuracy": 0.2072492629289627,
|
|
"num_tokens": 31649216.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.048960542678833,
|
|
"epoch": 1.349017272185825,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004830144847677069,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.20565807074308395,
|
|
"num_tokens": 31662392.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 4.966921091079712,
|
|
"epoch": 1.3496128648004766,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048299823877863857,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.20759742856025695,
|
|
"num_tokens": 31677801.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.099369049072266,
|
|
"epoch": 1.350208457415128,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004829819853290116,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.19985919296741486,
|
|
"num_tokens": 31692204.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.011934852600097,
|
|
"epoch": 1.3508040500297795,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004829657244194089,
|
|
"loss": 4.813,
|
|
"mean_token_accuracy": 0.20961799323558808,
|
|
"num_tokens": 31707277.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 4.979270553588867,
|
|
"epoch": 1.3513996426444312,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048294945605041384,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.20269210487604142,
|
|
"num_tokens": 31721725.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 4.984065675735474,
|
|
"epoch": 1.3519952352590827,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048293318022260995,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.20819844901561738,
|
|
"num_tokens": 31734945.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.011014938354492,
|
|
"epoch": 1.3525908278737344,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004829168969365809,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.20288462638854982,
|
|
"num_tokens": 31747336.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 4.93504376411438,
|
|
"epoch": 1.3531864204883859,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048290060619291084,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.1994231790304184,
|
|
"num_tokens": 31760405.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.014814710617065,
|
|
"epoch": 1.3537820131030376,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048288430799218394,
|
|
"loss": 4.829,
|
|
"mean_token_accuracy": 0.19802069067955017,
|
|
"num_tokens": 31775720.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 4.972139024734497,
|
|
"epoch": 1.354377605717689,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004828680023349851,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.20489119589328766,
|
|
"num_tokens": 31790211.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.0669787406921385,
|
|
"epoch": 1.3549731983323408,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048285168922189886,
|
|
"loss": 4.8878,
|
|
"mean_token_accuracy": 0.19560770094394683,
|
|
"num_tokens": 31804840.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.083500242233276,
|
|
"epoch": 1.3555687909469922,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048283536865351053,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.1950969859957695,
|
|
"num_tokens": 31818633.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 4.981467151641846,
|
|
"epoch": 1.356164383561644,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004828190406304054,
|
|
"loss": 4.7374,
|
|
"mean_token_accuracy": 0.2152068495750427,
|
|
"num_tokens": 31831804.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 4.969049739837646,
|
|
"epoch": 1.3567599761762954,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004828027051531692,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.19869482666254043,
|
|
"num_tokens": 31844419.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.059780406951904,
|
|
"epoch": 1.3573555687909469,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048278636222238785,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.19955056458711623,
|
|
"num_tokens": 31857222.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 4.979853820800781,
|
|
"epoch": 1.3579511614055986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048277001183864756,
|
|
"loss": 4.7667,
|
|
"mean_token_accuracy": 0.20022135525941848,
|
|
"num_tokens": 31869377.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 4.90303602218628,
|
|
"epoch": 1.3585467540202503,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004827536540025347,
|
|
"loss": 4.7982,
|
|
"mean_token_accuracy": 0.21128324121236802,
|
|
"num_tokens": 31882934.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 4.950808906555176,
|
|
"epoch": 1.3591423466349017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004827372887146361,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.20429932624101638,
|
|
"num_tokens": 31895649.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 4.98167986869812,
|
|
"epoch": 1.3597379392495532,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048272091597553865,
|
|
"loss": 4.8607,
|
|
"mean_token_accuracy": 0.2025693714618683,
|
|
"num_tokens": 31911061.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.056916379928589,
|
|
"epoch": 1.360333531864205,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048270453578582974,
|
|
"loss": 4.871,
|
|
"mean_token_accuracy": 0.20584852546453475,
|
|
"num_tokens": 31923128.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.024510526657105,
|
|
"epoch": 1.3609291244788564,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004826881481460968,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.2016302913427353,
|
|
"num_tokens": 31937947.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 4.983739805221558,
|
|
"epoch": 1.361524717093508,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048267175305692774,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.20321067720651625,
|
|
"num_tokens": 31952010.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.035269737243652,
|
|
"epoch": 1.3621203097081596,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004826553505189104,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.19829848557710647,
|
|
"num_tokens": 31966068.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 4.985026025772095,
|
|
"epoch": 1.3627159023228113,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004826389405326334,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.2016348123550415,
|
|
"num_tokens": 31979442.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.14236478805542,
|
|
"epoch": 1.3633114949374627,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004826225230986851,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.20063327103853226,
|
|
"num_tokens": 31993564.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.032572078704834,
|
|
"epoch": 1.3639070875521144,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048260609821765456,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.2053678572177887,
|
|
"num_tokens": 32008589.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 4.952102947235107,
|
|
"epoch": 1.364502680166766,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004825896658901308,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.20183325409889222,
|
|
"num_tokens": 32021975.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 4.991461229324341,
|
|
"epoch": 1.3650982727814176,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048257322611670324,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.19803461134433747,
|
|
"num_tokens": 32035438.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.102389860153198,
|
|
"epoch": 1.365693865396069,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048255677889796157,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.19123586565256118,
|
|
"num_tokens": 32051294.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 4.9897678852081295,
|
|
"epoch": 1.3662894580107205,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004825403242344957,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.20818615555763245,
|
|
"num_tokens": 32064424.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 4.9547473907470705,
|
|
"epoch": 1.3668850506253722,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004825238621268958,
|
|
"loss": 4.7983,
|
|
"mean_token_accuracy": 0.2076668545603752,
|
|
"num_tokens": 32078402.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.00243239402771,
|
|
"epoch": 1.367480643240024,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004825073925757524,
|
|
"loss": 4.8289,
|
|
"mean_token_accuracy": 0.20642622858285903,
|
|
"num_tokens": 32091878.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.023251533508301,
|
|
"epoch": 1.3680762358546754,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004824909155816562,
|
|
"loss": 4.792,
|
|
"mean_token_accuracy": 0.21113034337759018,
|
|
"num_tokens": 32104405.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.002094554901123,
|
|
"epoch": 1.368671828469327,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048247443114519825,
|
|
"loss": 4.767,
|
|
"mean_token_accuracy": 0.21509941816329955,
|
|
"num_tokens": 32117927.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.008069467544556,
|
|
"epoch": 1.3692674210839786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004824579392669698,
|
|
"loss": 4.8077,
|
|
"mean_token_accuracy": 0.19838350266218185,
|
|
"num_tokens": 32132314.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.030283689498901,
|
|
"epoch": 1.36986301369863,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048244143994756233,
|
|
"loss": 4.8955,
|
|
"mean_token_accuracy": 0.20654943585395813,
|
|
"num_tokens": 32145426.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.05731430053711,
|
|
"epoch": 1.3704586063132818,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004824249331875677,
|
|
"loss": 4.81,
|
|
"mean_token_accuracy": 0.1998953104019165,
|
|
"num_tokens": 32160902.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 4.955597686767578,
|
|
"epoch": 1.3710541989279332,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048240841898757796,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.20249195545911788,
|
|
"num_tokens": 32173436.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.01048092842102,
|
|
"epoch": 1.371649791542585,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004823918973481855,
|
|
"loss": 4.8196,
|
|
"mean_token_accuracy": 0.20360801219940186,
|
|
"num_tokens": 32185822.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.068964433670044,
|
|
"epoch": 1.3722453841572364,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048237536826998287,
|
|
"loss": 4.9068,
|
|
"mean_token_accuracy": 0.19509289115667344,
|
|
"num_tokens": 32198995.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 4.949774932861328,
|
|
"epoch": 1.372840976771888,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000482358831753563,
|
|
"loss": 4.6659,
|
|
"mean_token_accuracy": 0.213786019384861,
|
|
"num_tokens": 32212090.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 4.963995790481567,
|
|
"epoch": 1.3734365693865396,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048234228779951883,
|
|
"loss": 4.809,
|
|
"mean_token_accuracy": 0.2048572853207588,
|
|
"num_tokens": 32225838.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.035737562179565,
|
|
"epoch": 1.3740321620011913,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048232573640844407,
|
|
"loss": 4.8663,
|
|
"mean_token_accuracy": 0.20030190348625182,
|
|
"num_tokens": 32239603.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.063906288146972,
|
|
"epoch": 1.3746277546158427,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004823091775809321,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.20174034237861632,
|
|
"num_tokens": 32252808.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.015069770812988,
|
|
"epoch": 1.3752233472304942,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048229261131757707,
|
|
"loss": 4.8827,
|
|
"mean_token_accuracy": 0.20243447422981262,
|
|
"num_tokens": 32265893.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.030023622512817,
|
|
"epoch": 1.375818939845146,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048227603761897316,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.1988911136984825,
|
|
"num_tokens": 32280529.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 4.93463101387024,
|
|
"epoch": 1.3764145324597976,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048225945648571475,
|
|
"loss": 4.7558,
|
|
"mean_token_accuracy": 0.20466848462820053,
|
|
"num_tokens": 32294222.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.080352258682251,
|
|
"epoch": 1.377010125074449,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048224286791839657,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.2005167931318283,
|
|
"num_tokens": 32308289.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 4.97474308013916,
|
|
"epoch": 1.3776057176891006,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004822262719176137,
|
|
"loss": 4.7391,
|
|
"mean_token_accuracy": 0.21005436182022094,
|
|
"num_tokens": 32321401.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 4.946643447875976,
|
|
"epoch": 1.3782013103037523,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048220966848396137,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.20556237548589706,
|
|
"num_tokens": 32335373.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.083570194244385,
|
|
"epoch": 1.3787969029184037,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004821930576180352,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.1945171296596527,
|
|
"num_tokens": 32349685.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.007641839981079,
|
|
"epoch": 1.3793924955330554,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004821764393204308,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.19826522022485732,
|
|
"num_tokens": 32363768.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 4.980726909637451,
|
|
"epoch": 1.379988088147707,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004821598135917445,
|
|
"loss": 4.8515,
|
|
"mean_token_accuracy": 0.20944153070449828,
|
|
"num_tokens": 32377483.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.026772832870483,
|
|
"epoch": 1.3805836807623586,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048214318043257246,
|
|
"loss": 4.8603,
|
|
"mean_token_accuracy": 0.19251317977905275,
|
|
"num_tokens": 32389693.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.0014289855957035,
|
|
"epoch": 1.38117927337701,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004821265398435113,
|
|
"loss": 4.7723,
|
|
"mean_token_accuracy": 0.21053268760442734,
|
|
"num_tokens": 32403479.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.053263425827026,
|
|
"epoch": 1.3817748659916618,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000482109891825158,
|
|
"loss": 4.8944,
|
|
"mean_token_accuracy": 0.20413966178894044,
|
|
"num_tokens": 32417152.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.027894020080566,
|
|
"epoch": 1.3823704586063132,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004820932363781096,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.20446065962314605,
|
|
"num_tokens": 32430653.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 4.9380927085876465,
|
|
"epoch": 1.382966051220965,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048207657350296345,
|
|
"loss": 4.8219,
|
|
"mean_token_accuracy": 0.20415910035371782,
|
|
"num_tokens": 32446058.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.035709810256958,
|
|
"epoch": 1.3835616438356164,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048205990320031734,
|
|
"loss": 4.8347,
|
|
"mean_token_accuracy": 0.20284838527441024,
|
|
"num_tokens": 32460061.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 4.971647024154663,
|
|
"epoch": 1.384157236450268,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048204322547076915,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.20107741057872772,
|
|
"num_tokens": 32472554.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 4.911098575592041,
|
|
"epoch": 1.3847528290649196,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048202654031491714,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.2100440740585327,
|
|
"num_tokens": 32485436.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.0565673351287845,
|
|
"epoch": 1.3853484216795713,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048200984773335973,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.20634933263063432,
|
|
"num_tokens": 32498618.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 4.992458009719849,
|
|
"epoch": 1.3859440142942228,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004819931477266956,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.21023426949977875,
|
|
"num_tokens": 32510924.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.021377658843994,
|
|
"epoch": 1.3865396069088742,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004819764402955239,
|
|
"loss": 4.9274,
|
|
"mean_token_accuracy": 0.1938974067568779,
|
|
"num_tokens": 32524347.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.093988943099975,
|
|
"epoch": 1.387135199523526,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048195972544044373,
|
|
"loss": 4.8578,
|
|
"mean_token_accuracy": 0.2012179583311081,
|
|
"num_tokens": 32537497.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.0367128372192385,
|
|
"epoch": 1.3877307921381774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048194300316205474,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.20271931439638138,
|
|
"num_tokens": 32552684.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.018499422073364,
|
|
"epoch": 1.388326384752829,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004819262734609567,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.20036672800779343,
|
|
"num_tokens": 32567202.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.024128532409668,
|
|
"epoch": 1.3889219773674806,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004819095363377496,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.1949957400560379,
|
|
"num_tokens": 32583085.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 4.915261125564575,
|
|
"epoch": 1.3895175699821323,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004818927917930339,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.21062068045139312,
|
|
"num_tokens": 32598610.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.015341138839721,
|
|
"epoch": 1.3901131625967837,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048187603982741015,
|
|
"loss": 4.7842,
|
|
"mean_token_accuracy": 0.2099978134036064,
|
|
"num_tokens": 32611591.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.0116418361663815,
|
|
"epoch": 1.3907087552114354,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004818592804414792,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.20698876678943634,
|
|
"num_tokens": 32625002.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 4.941718196868896,
|
|
"epoch": 1.391304347826087,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004818425136358422,
|
|
"loss": 4.8219,
|
|
"mean_token_accuracy": 0.20444320738315583,
|
|
"num_tokens": 32639812.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.002170658111572,
|
|
"epoch": 1.3918999404407386,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048182573941110056,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.20412651747465133,
|
|
"num_tokens": 32652045.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.070416831970215,
|
|
"epoch": 1.39249553305539,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004818089577678559,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.1921990543603897,
|
|
"num_tokens": 32666098.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.00654091835022,
|
|
"epoch": 1.3930911256700416,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004817921687067102,
|
|
"loss": 4.8135,
|
|
"mean_token_accuracy": 0.19793603718280792,
|
|
"num_tokens": 32681044.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 4.970672082901001,
|
|
"epoch": 1.3936867182846933,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004817753722282656,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.20842378437519074,
|
|
"num_tokens": 32696855.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 4.9197454929351805,
|
|
"epoch": 1.394282310899345,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048175856833312464,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.20452401638031006,
|
|
"num_tokens": 32712248.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 4.981601333618164,
|
|
"epoch": 1.3948779035139964,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048174175702189,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.20348249077796937,
|
|
"num_tokens": 32727498.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 4.998198175430298,
|
|
"epoch": 1.395473496128648,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048172493829516465,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.21534609347581862,
|
|
"num_tokens": 32741450.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 4.982216787338257,
|
|
"epoch": 1.3960690887432996,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004817081121535518,
|
|
"loss": 4.8016,
|
|
"mean_token_accuracy": 0.20785578340291977,
|
|
"num_tokens": 32756340.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 4.866336393356323,
|
|
"epoch": 1.3966646813579513,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004816912785976552,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.20843100994825364,
|
|
"num_tokens": 32770906.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.000244188308716,
|
|
"epoch": 1.3972602739726028,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048167443762807844,
|
|
"loss": 4.8177,
|
|
"mean_token_accuracy": 0.20710058212280275,
|
|
"num_tokens": 32785477.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.004383993148804,
|
|
"epoch": 1.3978558665872542,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004816575892454256,
|
|
"loss": 4.8261,
|
|
"mean_token_accuracy": 0.20363294929265977,
|
|
"num_tokens": 32798766.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 4.995565557479859,
|
|
"epoch": 1.398451459201906,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000481640733450301,
|
|
"loss": 4.8841,
|
|
"mean_token_accuracy": 0.2079027697443962,
|
|
"num_tokens": 32813918.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.000157594680786,
|
|
"epoch": 1.3990470518165574,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004816238702433094,
|
|
"loss": 4.8078,
|
|
"mean_token_accuracy": 0.2074541762471199,
|
|
"num_tokens": 32828701.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.096191692352295,
|
|
"epoch": 1.3996426444312091,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048160699962505546,
|
|
"loss": 4.8909,
|
|
"mean_token_accuracy": 0.19835307449102402,
|
|
"num_tokens": 32841517.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 4.9908043384552006,
|
|
"epoch": 1.4002382370458606,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048159012159614434,
|
|
"loss": 4.8199,
|
|
"mean_token_accuracy": 0.20103535950183868,
|
|
"num_tokens": 32857108.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.082440328598023,
|
|
"epoch": 1.4008338296605123,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004815732361571815,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.1887836918234825,
|
|
"num_tokens": 32872384.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 4.994474601745606,
|
|
"epoch": 1.4014294222751638,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048155634330877253,
|
|
"loss": 4.7708,
|
|
"mean_token_accuracy": 0.2043712019920349,
|
|
"num_tokens": 32885890.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 4.9716558933258055,
|
|
"epoch": 1.4020250148898152,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004815394430515234,
|
|
"loss": 4.7835,
|
|
"mean_token_accuracy": 0.20349554419517518,
|
|
"num_tokens": 32899789.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 4.999101352691651,
|
|
"epoch": 1.402620607504467,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004815225353860402,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.20339970141649247,
|
|
"num_tokens": 32914523.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 4.98720350265503,
|
|
"epoch": 1.4032162001191186,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004815056203129294,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.2095835268497467,
|
|
"num_tokens": 32929007.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 4.978275108337402,
|
|
"epoch": 1.40381179273377,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004814886978327978,
|
|
"loss": 4.787,
|
|
"mean_token_accuracy": 0.2082023173570633,
|
|
"num_tokens": 32943884.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 4.9927901268005375,
|
|
"epoch": 1.4044073853484216,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048147176794625235,
|
|
"loss": 4.7853,
|
|
"mean_token_accuracy": 0.20875025242567063,
|
|
"num_tokens": 32958828.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 4.998268413543701,
|
|
"epoch": 1.4050029779630733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004814548306539003,
|
|
"loss": 4.7914,
|
|
"mean_token_accuracy": 0.20574876219034194,
|
|
"num_tokens": 32971960.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.0530171394348145,
|
|
"epoch": 1.405598570577725,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048143788595634917,
|
|
"loss": 4.8803,
|
|
"mean_token_accuracy": 0.20237817019224166,
|
|
"num_tokens": 32986571.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.046493005752564,
|
|
"epoch": 1.4061941631923764,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004814209338542067,
|
|
"loss": 4.8803,
|
|
"mean_token_accuracy": 0.1997387155890465,
|
|
"num_tokens": 33000931.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 4.943894624710083,
|
|
"epoch": 1.406789755807028,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048140397434808094,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.21382093727588652,
|
|
"num_tokens": 33016451.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 4.926660585403442,
|
|
"epoch": 1.4073853484216796,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048138700743858014,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.21981566101312638,
|
|
"num_tokens": 33030901.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.019439077377319,
|
|
"epoch": 1.407980941036331,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048137003312631306,
|
|
"loss": 4.8068,
|
|
"mean_token_accuracy": 0.20624447613954544,
|
|
"num_tokens": 33045328.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.026814651489258,
|
|
"epoch": 1.4085765336509828,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004813530514118884,
|
|
"loss": 4.7453,
|
|
"mean_token_accuracy": 0.2103856012225151,
|
|
"num_tokens": 33060897.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 4.978694820404053,
|
|
"epoch": 1.4091721262656343,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048133606229591524,
|
|
"loss": 4.7752,
|
|
"mean_token_accuracy": 0.21279002875089645,
|
|
"num_tokens": 33074440.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.083093547821045,
|
|
"epoch": 1.409767718880286,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004813190657790031,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.19012542963027954,
|
|
"num_tokens": 33091184.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 4.987295293807984,
|
|
"epoch": 1.4103633114949374,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048130206186176145,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.206100794672966,
|
|
"num_tokens": 33107047.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.002450275421142,
|
|
"epoch": 1.410958904109589,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048128505054480036,
|
|
"loss": 4.7951,
|
|
"mean_token_accuracy": 0.20658639818429947,
|
|
"num_tokens": 33121814.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 4.948901653289795,
|
|
"epoch": 1.4115544967242406,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004812680318287298,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.20253624022006989,
|
|
"num_tokens": 33135665.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.0007568359375,
|
|
"epoch": 1.4121500893388923,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004812510057141603,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.1989122748374939,
|
|
"num_tokens": 33148995.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.012531709671021,
|
|
"epoch": 1.4127456819535438,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004812339722017027,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.20409797877073288,
|
|
"num_tokens": 33163055.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 4.957194662094116,
|
|
"epoch": 1.4133412745681952,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004812169312919677,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.2116309553384781,
|
|
"num_tokens": 33176203.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.01590747833252,
|
|
"epoch": 1.413936867182847,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048119988298556674,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.20200474709272384,
|
|
"num_tokens": 33191357.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.085434341430664,
|
|
"epoch": 1.4145324597974986,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004811828272831112,
|
|
"loss": 4.918,
|
|
"mean_token_accuracy": 0.19467503279447557,
|
|
"num_tokens": 33207534.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.02621865272522,
|
|
"epoch": 1.4151280524121501,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004811657641852129,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.20899222791194916,
|
|
"num_tokens": 33221186.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 4.97294511795044,
|
|
"epoch": 1.4157236450268016,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048114869369248386,
|
|
"loss": 4.7776,
|
|
"mean_token_accuracy": 0.20404811352491378,
|
|
"num_tokens": 33235279.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 4.969311857223511,
|
|
"epoch": 1.4163192376414533,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004811316158055363,
|
|
"loss": 4.8063,
|
|
"mean_token_accuracy": 0.20002788454294204,
|
|
"num_tokens": 33250457.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.0444615364074705,
|
|
"epoch": 1.4169148302561048,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004811145305249828,
|
|
"loss": 4.8647,
|
|
"mean_token_accuracy": 0.20329086482524872,
|
|
"num_tokens": 33263599.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 4.955706214904785,
|
|
"epoch": 1.4175104228707565,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048109743785143636,
|
|
"loss": 4.8367,
|
|
"mean_token_accuracy": 0.2063510775566101,
|
|
"num_tokens": 33277508.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 4.978083229064941,
|
|
"epoch": 1.418106015485408,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004810803377855098,
|
|
"loss": 4.8682,
|
|
"mean_token_accuracy": 0.20879041105508805,
|
|
"num_tokens": 33290161.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.043320178985596,
|
|
"epoch": 1.4187016081000596,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004810632303278166,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.19850790053606032,
|
|
"num_tokens": 33303174.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.0107183933258055,
|
|
"epoch": 1.419297200714711,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004810461154789704,
|
|
"loss": 4.8035,
|
|
"mean_token_accuracy": 0.20459985136985778,
|
|
"num_tokens": 33318070.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 4.962857580184936,
|
|
"epoch": 1.4198927933293626,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000481028993239585,
|
|
"loss": 4.8289,
|
|
"mean_token_accuracy": 0.20493555516004563,
|
|
"num_tokens": 33332135.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 4.987721061706543,
|
|
"epoch": 1.4204883859440143,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004810118636102747,
|
|
"loss": 4.8099,
|
|
"mean_token_accuracy": 0.20405295193195344,
|
|
"num_tokens": 33345414.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.010509586334228,
|
|
"epoch": 1.421083978558666,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004809947265916537,
|
|
"loss": 4.8545,
|
|
"mean_token_accuracy": 0.20687725394964218,
|
|
"num_tokens": 33359173.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 4.986047792434692,
|
|
"epoch": 1.4216795711733174,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048097758218433687,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.21010468006134034,
|
|
"num_tokens": 33371025.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 4.920355033874512,
|
|
"epoch": 1.422275163787969,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048096043038893895,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.21295412331819535,
|
|
"num_tokens": 33384482.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.051635837554931,
|
|
"epoch": 1.4228707564026206,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048094327120607534,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.2063414990901947,
|
|
"num_tokens": 33398250.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 4.9600872039794925,
|
|
"epoch": 1.4234663490172723,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048092610463636143,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.20778406113386155,
|
|
"num_tokens": 33412845.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.087013053894043,
|
|
"epoch": 1.4240619416319238,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000480908930680413,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.19738354682922363,
|
|
"num_tokens": 33425418.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.004936838150025,
|
|
"epoch": 1.4246575342465753,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048089174933884597,
|
|
"loss": 4.8195,
|
|
"mean_token_accuracy": 0.2034462198615074,
|
|
"num_tokens": 33439431.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 4.96083083152771,
|
|
"epoch": 1.425253126861227,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048087456061227666,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.2090853661298752,
|
|
"num_tokens": 33454504.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 4.953359937667846,
|
|
"epoch": 1.4258487194758784,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048085736450132155,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.20778948813676834,
|
|
"num_tokens": 33469243.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 4.99404935836792,
|
|
"epoch": 1.4264443120905301,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048084016100659755,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.20640518218278886,
|
|
"num_tokens": 33484068.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.000967073440552,
|
|
"epoch": 1.4270399047051816,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004808229501287216,
|
|
"loss": 4.842,
|
|
"mean_token_accuracy": 0.19773310124874116,
|
|
"num_tokens": 33497841.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 4.922737407684326,
|
|
"epoch": 1.4276354973198333,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048080573186831113,
|
|
"loss": 4.6882,
|
|
"mean_token_accuracy": 0.21357567906379699,
|
|
"num_tokens": 33512011.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 4.991517639160156,
|
|
"epoch": 1.4282310899344848,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048078850622598355,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.20807936191558837,
|
|
"num_tokens": 33525475.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 4.986700963973999,
|
|
"epoch": 1.4288266825491365,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048077127320235696,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.20766596794128417,
|
|
"num_tokens": 33540069.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 4.965911817550659,
|
|
"epoch": 1.429422275163788,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048075403279804934,
|
|
"loss": 4.7706,
|
|
"mean_token_accuracy": 0.20938747525215148,
|
|
"num_tokens": 33554060.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.429422275163788,
|
|
"eval_entropy": 4.765491417657619,
|
|
"eval_loss": 4.846749782562256,
|
|
"eval_mean_token_accuracy": 0.2118215665151146,
|
|
"eval_num_tokens": 33554060.0,
|
|
"eval_runtime": 24.2409,
|
|
"eval_samples_per_second": 1052.478,
|
|
"eval_steps_per_second": 131.596,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 4.98214430809021,
|
|
"epoch": 1.4300178677784396,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004807367850136791,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.20579417198896408,
|
|
"num_tokens": 33566502.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.005381631851196,
|
|
"epoch": 1.4306134603930911,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004807195298498649,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.20060374736785888,
|
|
"num_tokens": 33581192.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.06751127243042,
|
|
"epoch": 1.4312090530077426,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004807022673072257,
|
|
"loss": 4.8974,
|
|
"mean_token_accuracy": 0.1961734563112259,
|
|
"num_tokens": 33595298.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.002121353149414,
|
|
"epoch": 1.4318046456223943,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048068499738638046,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.1983067587018013,
|
|
"num_tokens": 33607349.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 4.9466108798980715,
|
|
"epoch": 1.432400238237046,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004806677200879489,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.2083392098546028,
|
|
"num_tokens": 33621443.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 4.970860576629638,
|
|
"epoch": 1.4329958308516975,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004806504354125505,
|
|
"loss": 4.7495,
|
|
"mean_token_accuracy": 0.2135242700576782,
|
|
"num_tokens": 33634430.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 4.998574495315552,
|
|
"epoch": 1.433591423466349,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048063314336080554,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.20117604583501816,
|
|
"num_tokens": 33649192.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 4.992417430877685,
|
|
"epoch": 1.4341870160810006,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004806158439333339,
|
|
"loss": 4.7735,
|
|
"mean_token_accuracy": 0.2093350663781166,
|
|
"num_tokens": 33662715.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 4.980864191055298,
|
|
"epoch": 1.434782608695652,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048059853713075637,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.20327016711235046,
|
|
"num_tokens": 33676363.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.0655515670776365,
|
|
"epoch": 1.4353782013103038,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048058122295369354,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.19853259921073912,
|
|
"num_tokens": 33693285.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 4.988378953933716,
|
|
"epoch": 1.4359737939249553,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004805639014027665,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.20898807048797607,
|
|
"num_tokens": 33707291.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 4.892063808441162,
|
|
"epoch": 1.436569386539607,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004805465724785966,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.20570092052221298,
|
|
"num_tokens": 33721629.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.007084941864013,
|
|
"epoch": 1.4371649791542584,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004805292361818053,
|
|
"loss": 4.783,
|
|
"mean_token_accuracy": 0.21244100630283355,
|
|
"num_tokens": 33737427.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 4.916879272460937,
|
|
"epoch": 1.4377605717689101,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048051189251301443,
|
|
"loss": 4.7691,
|
|
"mean_token_accuracy": 0.2061942845582962,
|
|
"num_tokens": 33750851.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 4.998251724243164,
|
|
"epoch": 1.4383561643835616,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004804945414728461,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.2049890488386154,
|
|
"num_tokens": 33764663.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 4.971512222290039,
|
|
"epoch": 1.4389517569982133,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004804771830619227,
|
|
"loss": 4.7566,
|
|
"mean_token_accuracy": 0.20518466979265212,
|
|
"num_tokens": 33779875.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 4.879307699203491,
|
|
"epoch": 1.4395473496128648,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048045981728086687,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.2120981127023697,
|
|
"num_tokens": 33791867.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 4.941224384307861,
|
|
"epoch": 1.4401429422275163,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004804424441303015,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.21607399433851243,
|
|
"num_tokens": 33804957.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 4.958344221115112,
|
|
"epoch": 1.440738534842168,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004804250636108496,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.21019369810819627,
|
|
"num_tokens": 33816409.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.0704930305480955,
|
|
"epoch": 1.4413341274568197,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004804076757231347,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.2016710162162781,
|
|
"num_tokens": 33830946.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.007609081268311,
|
|
"epoch": 1.4419297200714711,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048039028046778043,
|
|
"loss": 4.8435,
|
|
"mean_token_accuracy": 0.20608690828084947,
|
|
"num_tokens": 33846133.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 4.9283304691314695,
|
|
"epoch": 1.4425253126861226,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004803728778454108,
|
|
"loss": 4.7256,
|
|
"mean_token_accuracy": 0.20405020266771318,
|
|
"num_tokens": 33860168.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.0135150909423825,
|
|
"epoch": 1.4431209053007743,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048035546785664987,
|
|
"loss": 4.8856,
|
|
"mean_token_accuracy": 0.1977258712053299,
|
|
"num_tokens": 33873260.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.040597295761108,
|
|
"epoch": 1.4437164979154258,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004803380505021222,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.2036752849817276,
|
|
"num_tokens": 33887568.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.019445514678955,
|
|
"epoch": 1.4443120905300775,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048032062578245256,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.20435515642166138,
|
|
"num_tokens": 33900464.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 4.890314102172852,
|
|
"epoch": 1.444907683144729,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048030319369826594,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.21290547847747804,
|
|
"num_tokens": 33913155.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.0589948177337645,
|
|
"epoch": 1.4455032757593806,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004802857542501875,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.19936951696872712,
|
|
"num_tokens": 33928168.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 4.914515781402588,
|
|
"epoch": 1.4460988683740321,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048026830743884283,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.21095544695854188,
|
|
"num_tokens": 33941525.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 4.892117881774903,
|
|
"epoch": 1.4466944609886838,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004802508532648578,
|
|
"loss": 4.661,
|
|
"mean_token_accuracy": 0.2131388559937477,
|
|
"num_tokens": 33955300.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 4.968576145172119,
|
|
"epoch": 1.4472900536033353,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004802333917288583,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.207910892367363,
|
|
"num_tokens": 33968924.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.004907274246216,
|
|
"epoch": 1.447885646217987,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048021592283147073,
|
|
"loss": 4.7933,
|
|
"mean_token_accuracy": 0.20481641888618468,
|
|
"num_tokens": 33982725.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 4.949217796325684,
|
|
"epoch": 1.4484812388326385,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048019844657332166,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.20996870398521422,
|
|
"num_tokens": 33997263.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.023531055450439,
|
|
"epoch": 1.44907683144729,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000480180962955038,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.19625355452299117,
|
|
"num_tokens": 34013748.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.011174726486206,
|
|
"epoch": 1.4496724240619416,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048016347197724676,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.20351935625076295,
|
|
"num_tokens": 34028086.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 4.917971801757813,
|
|
"epoch": 1.4502680166765933,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004801459736405754,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.21087392419576645,
|
|
"num_tokens": 34042539.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.006447887420654,
|
|
"epoch": 1.4508636092912448,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048012846794565143,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.2071845278143883,
|
|
"num_tokens": 34055051.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 4.9772686004638675,
|
|
"epoch": 1.4514592019058963,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004801109548931029,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.2139446794986725,
|
|
"num_tokens": 34068861.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 4.945314693450928,
|
|
"epoch": 1.452054794520548,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004800934344835579,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.21132924556732177,
|
|
"num_tokens": 34082353.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 4.942129993438721,
|
|
"epoch": 1.4526503871351995,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004800759067176448,
|
|
"loss": 4.7862,
|
|
"mean_token_accuracy": 0.20703640431165696,
|
|
"num_tokens": 34096993.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 4.946364450454712,
|
|
"epoch": 1.4532459797498511,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004800583715959924,
|
|
"loss": 4.7658,
|
|
"mean_token_accuracy": 0.2038678526878357,
|
|
"num_tokens": 34110648.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 4.964265584945679,
|
|
"epoch": 1.4538415723645026,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004800408291192297,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.21004445850849152,
|
|
"num_tokens": 34123645.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 4.970122289657593,
|
|
"epoch": 1.4544371649791543,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004800232792879858,
|
|
"loss": 4.7885,
|
|
"mean_token_accuracy": 0.20209428369998933,
|
|
"num_tokens": 34139671.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.075044202804565,
|
|
"epoch": 1.4550327575938058,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048000572210289016,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.20180957913398742,
|
|
"num_tokens": 34154451.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.06718635559082,
|
|
"epoch": 1.4556283502084575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047998815756457265,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.20536500960588455,
|
|
"num_tokens": 34166974.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 4.998466539382934,
|
|
"epoch": 1.456223942823109,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047997058567366313,
|
|
"loss": 4.8447,
|
|
"mean_token_accuracy": 0.2073048710823059,
|
|
"num_tokens": 34180197.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 4.925379133224487,
|
|
"epoch": 1.4568195354377607,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004799530064307921,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.2103399306535721,
|
|
"num_tokens": 34193560.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 4.9801195621490475,
|
|
"epoch": 1.4574151280524121,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047993541983658983,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.20995697975158692,
|
|
"num_tokens": 34206420.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.061146926879883,
|
|
"epoch": 1.4580107206670636,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047991782589168724,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.1953488454222679,
|
|
"num_tokens": 34220557.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.01096396446228,
|
|
"epoch": 1.4586063132817153,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004799002245967156,
|
|
"loss": 4.8466,
|
|
"mean_token_accuracy": 0.1926433563232422,
|
|
"num_tokens": 34232852.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 4.979831027984619,
|
|
"epoch": 1.459201905896367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047988261595230587,
|
|
"loss": 4.7506,
|
|
"mean_token_accuracy": 0.20336673855781556,
|
|
"num_tokens": 34248410.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 4.992200040817261,
|
|
"epoch": 1.4597974985110185,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047986499995908996,
|
|
"loss": 4.8226,
|
|
"mean_token_accuracy": 0.20708154290914535,
|
|
"num_tokens": 34263600.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.018788862228393,
|
|
"epoch": 1.46039309112567,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004798473766176994,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.19703291058540345,
|
|
"num_tokens": 34277031.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.015087080001831,
|
|
"epoch": 1.4609886837403216,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047982974592876665,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.20313047468662263,
|
|
"num_tokens": 34291646.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 4.970969200134277,
|
|
"epoch": 1.4615842763549731,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047981210789292396,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.21397616416215898,
|
|
"num_tokens": 34304769.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 4.8980443477630615,
|
|
"epoch": 1.4621798689696248,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004797944625108039,
|
|
"loss": 4.7179,
|
|
"mean_token_accuracy": 0.21264096796512605,
|
|
"num_tokens": 34318186.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 4.907446765899659,
|
|
"epoch": 1.4627754615842763,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047977680978303946,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.2066466689109802,
|
|
"num_tokens": 34333305.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 4.967074298858643,
|
|
"epoch": 1.463371054198928,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004797591497102638,
|
|
"loss": 4.706,
|
|
"mean_token_accuracy": 0.21438079923391343,
|
|
"num_tokens": 34345999.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 4.929120635986328,
|
|
"epoch": 1.4639666468135795,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047974148229311034,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.1996595174074173,
|
|
"num_tokens": 34361462.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 4.945304584503174,
|
|
"epoch": 1.4645622394282312,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004797238075322128,
|
|
"loss": 4.7848,
|
|
"mean_token_accuracy": 0.2075412839651108,
|
|
"num_tokens": 34376638.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.054295492172241,
|
|
"epoch": 1.4651578320428826,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004797061254282052,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.2065901666879654,
|
|
"num_tokens": 34391091.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 4.9650571823120115,
|
|
"epoch": 1.4657534246575343,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004796884359817217,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.20834287703037263,
|
|
"num_tokens": 34404976.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 4.835704135894775,
|
|
"epoch": 1.4663490172721858,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004796707391933967,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.2161535769701004,
|
|
"num_tokens": 34416781.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 4.913621473312378,
|
|
"epoch": 1.4669446098868373,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004796530350638652,
|
|
"loss": 4.6584,
|
|
"mean_token_accuracy": 0.2211843505501747,
|
|
"num_tokens": 34431445.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 4.968872594833374,
|
|
"epoch": 1.467540202501489,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000479635323593762,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.21686617583036422,
|
|
"num_tokens": 34443515.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 4.95427680015564,
|
|
"epoch": 1.4681357951161407,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047961760478372245,
|
|
"loss": 4.6905,
|
|
"mean_token_accuracy": 0.22099240720272065,
|
|
"num_tokens": 34456511.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 4.907053852081299,
|
|
"epoch": 1.4687313877307921,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047959987863438214,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.20100453943014146,
|
|
"num_tokens": 34469156.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 4.942899465560913,
|
|
"epoch": 1.4693269803454436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004795821451463769,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.2054946705698967,
|
|
"num_tokens": 34483735.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.029971551895142,
|
|
"epoch": 1.4699225729600953,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047956440432034265,
|
|
"loss": 4.8524,
|
|
"mean_token_accuracy": 0.2033580020070076,
|
|
"num_tokens": 34496731.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.0236633777618405,
|
|
"epoch": 1.4705181655747468,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047954665615691577,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.20588728338479995,
|
|
"num_tokens": 34509373.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.041656160354615,
|
|
"epoch": 1.4711137581893985,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004795289006567331,
|
|
"loss": 4.8204,
|
|
"mean_token_accuracy": 0.20231379717588424,
|
|
"num_tokens": 34525550.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.034496164321899,
|
|
"epoch": 1.47170935080405,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047951113782043113,
|
|
"loss": 4.8546,
|
|
"mean_token_accuracy": 0.1996969148516655,
|
|
"num_tokens": 34540555.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 4.993985319137574,
|
|
"epoch": 1.4723049434187017,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004794933676486472,
|
|
"loss": 4.7895,
|
|
"mean_token_accuracy": 0.2126306712627411,
|
|
"num_tokens": 34554314.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 4.9508120059967045,
|
|
"epoch": 1.4729005360333531,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004794755901420187,
|
|
"loss": 4.7492,
|
|
"mean_token_accuracy": 0.20894405096769333,
|
|
"num_tokens": 34567932.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 4.921928739547729,
|
|
"epoch": 1.4734961286480048,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004794578053011833,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.20817292779684066,
|
|
"num_tokens": 34581556.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 4.886760091781616,
|
|
"epoch": 1.4740917212626563,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047944001312677867,
|
|
"loss": 4.7064,
|
|
"mean_token_accuracy": 0.2145438715815544,
|
|
"num_tokens": 34595765.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 4.909565448760986,
|
|
"epoch": 1.474687313877308,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047942221361944333,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.22207510322332383,
|
|
"num_tokens": 34608625.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 4.906855297088623,
|
|
"epoch": 1.4752829064919595,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047940440677981546,
|
|
"loss": 4.623,
|
|
"mean_token_accuracy": 0.21734666973352432,
|
|
"num_tokens": 34622699.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 4.938761138916016,
|
|
"epoch": 1.475878499106611,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004793865926085339,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.19994960874319076,
|
|
"num_tokens": 34635374.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 4.936974811553955,
|
|
"epoch": 1.4764740917212626,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004793687711062376,
|
|
"loss": 4.7329,
|
|
"mean_token_accuracy": 0.21729859709739685,
|
|
"num_tokens": 34648517.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 4.954454755783081,
|
|
"epoch": 1.4770696843359143,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004793509422735657,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.2120797246694565,
|
|
"num_tokens": 34662883.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 4.926637935638428,
|
|
"epoch": 1.4776652769505658,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047933310611115776,
|
|
"loss": 4.6892,
|
|
"mean_token_accuracy": 0.2107907310128212,
|
|
"num_tokens": 34677490.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 4.9764580726623535,
|
|
"epoch": 1.4782608695652173,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047931526261965363,
|
|
"loss": 4.7895,
|
|
"mean_token_accuracy": 0.20436190217733383,
|
|
"num_tokens": 34690900.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.026455593109131,
|
|
"epoch": 1.478856462179869,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004792974117996931,
|
|
"loss": 4.8823,
|
|
"mean_token_accuracy": 0.19561819434165956,
|
|
"num_tokens": 34704916.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.004166746139527,
|
|
"epoch": 1.4794520547945205,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004792795536519167,
|
|
"loss": 4.8503,
|
|
"mean_token_accuracy": 0.20219073593616485,
|
|
"num_tokens": 34719912.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.017113780975341,
|
|
"epoch": 1.4800476474091722,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047926168817696477,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.20806949585676193,
|
|
"num_tokens": 34735585.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 4.998546314239502,
|
|
"epoch": 1.4806432400238236,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004792438153754782,
|
|
"loss": 4.7971,
|
|
"mean_token_accuracy": 0.20180528610944748,
|
|
"num_tokens": 34750321.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 4.956284475326538,
|
|
"epoch": 1.4812388326384753,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047922593524809805,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.20771481990814208,
|
|
"num_tokens": 34763555.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.032370281219483,
|
|
"epoch": 1.4818344252531268,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004792080477954657,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.19856929779052734,
|
|
"num_tokens": 34777395.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 4.982528448104858,
|
|
"epoch": 1.4824300178677785,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047919015301822255,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.2046325221657753,
|
|
"num_tokens": 34791598.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 4.931077766418457,
|
|
"epoch": 1.48302561048243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004791722509170108,
|
|
"loss": 4.8242,
|
|
"mean_token_accuracy": 0.203303761780262,
|
|
"num_tokens": 34805647.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 4.963738298416137,
|
|
"epoch": 1.4836212030970817,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047915434149247224,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.21075683534145356,
|
|
"num_tokens": 34820167.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.017606925964356,
|
|
"epoch": 1.4842167957117332,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047913642474524946,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.20857302248477935,
|
|
"num_tokens": 34834458.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.028495264053345,
|
|
"epoch": 1.4848123883263846,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047911850067598494,
|
|
"loss": 4.8428,
|
|
"mean_token_accuracy": 0.19967901110649108,
|
|
"num_tokens": 34849058.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.033180665969849,
|
|
"epoch": 1.4854079809410363,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047910056928532173,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.20324524790048598,
|
|
"num_tokens": 34863215.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 4.9586700916290285,
|
|
"epoch": 1.486003573555688,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000479082630573903,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.21317076236009597,
|
|
"num_tokens": 34877198.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 4.941603136062622,
|
|
"epoch": 1.4865991661703395,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004790646845423721,
|
|
"loss": 4.825,
|
|
"mean_token_accuracy": 0.20691848695278167,
|
|
"num_tokens": 34892150.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 4.994528770446777,
|
|
"epoch": 1.487194758784991,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004790467311913727,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.20621577948331832,
|
|
"num_tokens": 34904775.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 4.984928989410401,
|
|
"epoch": 1.4877903513996427,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047902877052154885,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.20576796382665635,
|
|
"num_tokens": 34919306.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 4.944659757614136,
|
|
"epoch": 1.4883859440142944,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047901080253354476,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.2010747879743576,
|
|
"num_tokens": 34932524.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.00280351638794,
|
|
"epoch": 1.4889815366289458,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047899282722800487,
|
|
"loss": 4.7847,
|
|
"mean_token_accuracy": 0.20920856893062592,
|
|
"num_tokens": 34945665.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 4.982294988632202,
|
|
"epoch": 1.4895771292435973,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047897484460557397,
|
|
"loss": 4.7207,
|
|
"mean_token_accuracy": 0.216339635848999,
|
|
"num_tokens": 34958260.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 4.969104242324829,
|
|
"epoch": 1.490172721858249,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000478956854666897,
|
|
"loss": 4.7919,
|
|
"mean_token_accuracy": 0.20249186903238298,
|
|
"num_tokens": 34972047.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 4.893959999084473,
|
|
"epoch": 1.4907683144729005,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047893885741261924,
|
|
"loss": 4.7127,
|
|
"mean_token_accuracy": 0.21903261095285415,
|
|
"num_tokens": 34983672.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 4.9553446769714355,
|
|
"epoch": 1.4913639070875522,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004789208528433862,
|
|
"loss": 4.765,
|
|
"mean_token_accuracy": 0.21030547022819518,
|
|
"num_tokens": 34996639.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 4.9717505931854244,
|
|
"epoch": 1.4919594997022037,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004789028409598438,
|
|
"loss": 4.7803,
|
|
"mean_token_accuracy": 0.20837232172489167,
|
|
"num_tokens": 35010742.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 4.952628135681152,
|
|
"epoch": 1.4925550923168553,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047888482176263803,
|
|
"loss": 4.7658,
|
|
"mean_token_accuracy": 0.20373860895633697,
|
|
"num_tokens": 35024345.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 4.927370262145996,
|
|
"epoch": 1.4931506849315068,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047886679525241524,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.21187932938337325,
|
|
"num_tokens": 35036729.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 4.858332538604737,
|
|
"epoch": 1.4937462775461583,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004788487614298219,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.2178252786397934,
|
|
"num_tokens": 35050787.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 4.9490814208984375,
|
|
"epoch": 1.49434187016081,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047883072029550496,
|
|
"loss": 4.7298,
|
|
"mean_token_accuracy": 0.21785912066698074,
|
|
"num_tokens": 35062639.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 4.939334726333618,
|
|
"epoch": 1.4949374627754617,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047881267185011147,
|
|
"loss": 4.7629,
|
|
"mean_token_accuracy": 0.20397674292325974,
|
|
"num_tokens": 35075059.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 4.968837785720825,
|
|
"epoch": 1.4955330553901132,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047879461609428876,
|
|
"loss": 4.7383,
|
|
"mean_token_accuracy": 0.20682187676429747,
|
|
"num_tokens": 35088518.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.011457633972168,
|
|
"epoch": 1.4961286480047646,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004787765530286846,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.2081206664443016,
|
|
"num_tokens": 35102097.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 4.924982404708862,
|
|
"epoch": 1.4967242406194163,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004787584826539468,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.20657910257577897,
|
|
"num_tokens": 35114925.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 4.973607730865479,
|
|
"epoch": 1.497319833234068,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004787404049707235,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.21664641052484512,
|
|
"num_tokens": 35127718.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 4.98491063117981,
|
|
"epoch": 1.4979154258487195,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047872231997966316,
|
|
"loss": 4.8223,
|
|
"mean_token_accuracy": 0.21101500242948532,
|
|
"num_tokens": 35140687.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.062428998947143,
|
|
"epoch": 1.498511018463371,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004787042276814144,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.20509499311447144,
|
|
"num_tokens": 35153347.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 4.922581911087036,
|
|
"epoch": 1.4991066110780227,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047868612807662616,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.20935709476470948,
|
|
"num_tokens": 35165503.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.029170322418213,
|
|
"epoch": 1.4997022036926742,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047866802116594776,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.20919816493988036,
|
|
"num_tokens": 35180396.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.020761966705322,
|
|
"epoch": 1.5002977963073256,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004786499069500286,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.20284904837608336,
|
|
"num_tokens": 35194678.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.0439105987548825,
|
|
"epoch": 1.5008933889219773,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047863178542951833,
|
|
"loss": 4.8974,
|
|
"mean_token_accuracy": 0.20193243473768235,
|
|
"num_tokens": 35208394.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 4.954366016387939,
|
|
"epoch": 1.501488981536629,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000478613656605067,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.2091590791940689,
|
|
"num_tokens": 35222645.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 4.931335973739624,
|
|
"epoch": 1.5020845741512805,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047859552047732493,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.21283601522445678,
|
|
"num_tokens": 35237791.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 4.960096311569214,
|
|
"epoch": 1.502680166765932,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047857737704694255,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.21211832612752915,
|
|
"num_tokens": 35250036.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 4.885878038406372,
|
|
"epoch": 1.5032757593805837,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004785592263145705,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.212638159096241,
|
|
"num_tokens": 35264653.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 4.966540241241455,
|
|
"epoch": 1.5038713519952354,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047854106828086016,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.20118066370487214,
|
|
"num_tokens": 35278479.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.0546434879302975,
|
|
"epoch": 1.5044669446098868,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047852290294646255,
|
|
"loss": 4.81,
|
|
"mean_token_accuracy": 0.20685481578111647,
|
|
"num_tokens": 35291532.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.030246019363403,
|
|
"epoch": 1.5050625372245383,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047850473031202937,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.2031974971294403,
|
|
"num_tokens": 35305212.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.002581310272217,
|
|
"epoch": 1.50565812983919,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004784865503782124,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.21209218651056289,
|
|
"num_tokens": 35318317.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 4.994934368133545,
|
|
"epoch": 1.5062537224538417,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047846836314566356,
|
|
"loss": 4.8178,
|
|
"mean_token_accuracy": 0.20596205294132233,
|
|
"num_tokens": 35333081.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.073616361618042,
|
|
"epoch": 1.5068493150684932,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047845016861503556,
|
|
"loss": 4.8186,
|
|
"mean_token_accuracy": 0.20045359581708908,
|
|
"num_tokens": 35346417.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 4.970940113067627,
|
|
"epoch": 1.5074449076831447,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047843196678698063,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.20964124500751496,
|
|
"num_tokens": 35359939.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 4.919152164459229,
|
|
"epoch": 1.5080405002977963,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004784137576621519,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.21615587621927262,
|
|
"num_tokens": 35373105.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 4.9830280303955075,
|
|
"epoch": 1.508636092912448,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004783955412412024,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.20423397272825242,
|
|
"num_tokens": 35388576.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.0433642864227295,
|
|
"epoch": 1.5092316855270993,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004783773175247856,
|
|
"loss": 4.8728,
|
|
"mean_token_accuracy": 0.20081341713666917,
|
|
"num_tokens": 35402023.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.017186450958252,
|
|
"epoch": 1.509827278141751,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047835908651355503,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.20635250359773635,
|
|
"num_tokens": 35415870.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 4.936449670791626,
|
|
"epoch": 1.5104228707564027,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004783408482081646,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.20154616981744766,
|
|
"num_tokens": 35430027.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.093608093261719,
|
|
"epoch": 1.5110184633710542,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004783226026092687,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.19562913477420807,
|
|
"num_tokens": 35445210.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.02745246887207,
|
|
"epoch": 1.5116140559857056,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004783043497175215,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.2050511509180069,
|
|
"num_tokens": 35461138.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 4.974379301071167,
|
|
"epoch": 1.5122096486003573,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004782860895335779,
|
|
"loss": 4.8189,
|
|
"mean_token_accuracy": 0.20726484656333924,
|
|
"num_tokens": 35474923.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 4.952096939086914,
|
|
"epoch": 1.512805241215009,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004782678220580928,
|
|
"loss": 4.6984,
|
|
"mean_token_accuracy": 0.2140124499797821,
|
|
"num_tokens": 35489379.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 4.949326848983764,
|
|
"epoch": 1.5134008338296605,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047824954729172136,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.21270079761743546,
|
|
"num_tokens": 35502261.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 4.949016523361206,
|
|
"epoch": 1.513996426444312,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047823126523511916,
|
|
"loss": 4.7026,
|
|
"mean_token_accuracy": 0.21911040246486663,
|
|
"num_tokens": 35515958.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 4.9548417091369625,
|
|
"epoch": 1.5145920190589637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004782129758889419,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.20818388760089873,
|
|
"num_tokens": 35531559.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 4.9913427352905275,
|
|
"epoch": 1.5151876116736154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047819467925384564,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.20618354231119157,
|
|
"num_tokens": 35546995.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.055132722854614,
|
|
"epoch": 1.5157832042882668,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004781763753304866,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.20620675534009933,
|
|
"num_tokens": 35560327.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 4.9522723197937015,
|
|
"epoch": 1.5163787969029183,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004781580641195213,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.2038208872079849,
|
|
"num_tokens": 35574862.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 4.913293933868408,
|
|
"epoch": 1.51697438951757,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047813974562160654,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.21268394142389296,
|
|
"num_tokens": 35589429.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 4.980918836593628,
|
|
"epoch": 1.5175699821322217,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004781214198373994,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.20567197501659393,
|
|
"num_tokens": 35602846.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.000234794616699,
|
|
"epoch": 1.5181655747468732,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004781030867675572,
|
|
"loss": 4.8271,
|
|
"mean_token_accuracy": 0.20927721709012986,
|
|
"num_tokens": 35615724.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 4.986189603805542,
|
|
"epoch": 1.5187611673615247,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047808474641273743,
|
|
"loss": 4.8676,
|
|
"mean_token_accuracy": 0.19755880683660507,
|
|
"num_tokens": 35629602.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.016387033462524,
|
|
"epoch": 1.5193567599761764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047806639877359805,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.2134910434484482,
|
|
"num_tokens": 35643736.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.046408700942993,
|
|
"epoch": 1.5199523525908278,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004780480438507972,
|
|
"loss": 4.8129,
|
|
"mean_token_accuracy": 0.20983330011367798,
|
|
"num_tokens": 35658483.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 4.953840065002441,
|
|
"epoch": 1.5205479452054793,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000478029681644993,
|
|
"loss": 4.7385,
|
|
"mean_token_accuracy": 0.20664599686861038,
|
|
"num_tokens": 35672671.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.034356737136841,
|
|
"epoch": 1.521143537820131,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004780113121568443,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.19861513674259185,
|
|
"num_tokens": 35686326.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 4.953847646713257,
|
|
"epoch": 1.5217391304347827,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047799293538700993,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.2087235137820244,
|
|
"num_tokens": 35698855.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.017679643630982,
|
|
"epoch": 1.5223347230494342,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047797455133614903,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.19746570587158202,
|
|
"num_tokens": 35714118.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 4.957559251785279,
|
|
"epoch": 1.5229303156640857,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047795616000492086,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.20554113984107972,
|
|
"num_tokens": 35729467.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.006742477416992,
|
|
"epoch": 1.5235259082787374,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047793776139398535,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.20560993999242783,
|
|
"num_tokens": 35744566.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 4.941897535324097,
|
|
"epoch": 1.524121500893389,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004779193555040023,
|
|
"loss": 4.7011,
|
|
"mean_token_accuracy": 0.21924833208322525,
|
|
"num_tokens": 35756843.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.009699964523316,
|
|
"epoch": 1.5247170935080405,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047790094233563185,
|
|
"loss": 4.8778,
|
|
"mean_token_accuracy": 0.19405284523963928,
|
|
"num_tokens": 35770131.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 4.928595638275146,
|
|
"epoch": 1.525312686122692,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047788252188953447,
|
|
"loss": 4.7105,
|
|
"mean_token_accuracy": 0.21296041011810302,
|
|
"num_tokens": 35784294.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 4.975572872161865,
|
|
"epoch": 1.5259082787373437,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004778640941663709,
|
|
"loss": 4.7872,
|
|
"mean_token_accuracy": 0.20039464682340621,
|
|
"num_tokens": 35797947.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 4.984045219421387,
|
|
"epoch": 1.5265038713519954,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047784565916680216,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.20495408028364182,
|
|
"num_tokens": 35812978.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 4.933488559722901,
|
|
"epoch": 1.5270994639666469,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047782721689148936,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.20417031794786453,
|
|
"num_tokens": 35826094.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.039360284805298,
|
|
"epoch": 1.5276950565812983,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004778087673410942,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.20518628656864166,
|
|
"num_tokens": 35841192.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 4.9595259666442875,
|
|
"epoch": 1.52829064919595,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004777903105162782,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.21376739144325257,
|
|
"num_tokens": 35854519.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 4.936262893676758,
|
|
"epoch": 1.5288862418106015,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004777718464177035,
|
|
"loss": 4.783,
|
|
"mean_token_accuracy": 0.20608593076467513,
|
|
"num_tokens": 35870196.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 4.952179670333862,
|
|
"epoch": 1.529481834425253,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004777533750460323,
|
|
"loss": 4.683,
|
|
"mean_token_accuracy": 0.21960755288600922,
|
|
"num_tokens": 35882815.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 4.966578769683838,
|
|
"epoch": 1.5300774270399047,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047773489640192724,
|
|
"loss": 4.8285,
|
|
"mean_token_accuracy": 0.20308210253715514,
|
|
"num_tokens": 35894770.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 4.91791558265686,
|
|
"epoch": 1.5306730196545564,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047771641048605107,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.21401673406362534,
|
|
"num_tokens": 35909183.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 4.909058237075806,
|
|
"epoch": 1.5312686122692079,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047769791729906685,
|
|
"loss": 4.753,
|
|
"mean_token_accuracy": 0.20720727145671844,
|
|
"num_tokens": 35922625.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 4.956007194519043,
|
|
"epoch": 1.5318642048838593,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000477679416841638,
|
|
"loss": 4.7559,
|
|
"mean_token_accuracy": 0.20477476716041565,
|
|
"num_tokens": 35934805.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 4.982603263854981,
|
|
"epoch": 1.532459797498511,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047766090911442787,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.20346849262714387,
|
|
"num_tokens": 35949178.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.07785382270813,
|
|
"epoch": 1.5330553901131627,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004776423941181005,
|
|
"loss": 4.8561,
|
|
"mean_token_accuracy": 0.20086390674114227,
|
|
"num_tokens": 35963812.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.014813804626465,
|
|
"epoch": 1.5336509827278142,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004776238718533199,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.2056843176484108,
|
|
"num_tokens": 35977633.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 4.868997192382812,
|
|
"epoch": 1.5342465753424657,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047760534232075045,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.20658016353845596,
|
|
"num_tokens": 35990779.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.021004724502563,
|
|
"epoch": 1.5348421679571174,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004775868055210568,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.20523912459611893,
|
|
"num_tokens": 36004482.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.007277154922486,
|
|
"epoch": 1.535437760571769,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047756826145490383,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.202079838514328,
|
|
"num_tokens": 36017430.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 4.967703008651734,
|
|
"epoch": 1.5360333531864205,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047754971012295666,
|
|
"loss": 4.8115,
|
|
"mean_token_accuracy": 0.2096850574016571,
|
|
"num_tokens": 36031141.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 4.9950474262237545,
|
|
"epoch": 1.536628945801072,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004775311515258807,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.20879328697919847,
|
|
"num_tokens": 36046318.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.0037092685699465,
|
|
"epoch": 1.5372245384157237,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047751258566434176,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.2021751418709755,
|
|
"num_tokens": 36060911.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 4.947737073898315,
|
|
"epoch": 1.5378201310303752,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004774940125390055,
|
|
"loss": 4.8053,
|
|
"mean_token_accuracy": 0.20460309386253356,
|
|
"num_tokens": 36074760.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.026568508148193,
|
|
"epoch": 1.5384157236450267,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004774754321505383,
|
|
"loss": 4.8117,
|
|
"mean_token_accuracy": 0.20172973424196244,
|
|
"num_tokens": 36089281.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.043565273284912,
|
|
"epoch": 1.5390113162596784,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047745684449960655,
|
|
"loss": 4.8447,
|
|
"mean_token_accuracy": 0.1995377317070961,
|
|
"num_tokens": 36105313.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 4.933754539489746,
|
|
"epoch": 1.53960690887433,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047743824958687694,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.20894138514995575,
|
|
"num_tokens": 36121212.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.072877550125122,
|
|
"epoch": 1.5402025014889815,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004774196474130165,
|
|
"loss": 4.8693,
|
|
"mean_token_accuracy": 0.20279552042484283,
|
|
"num_tokens": 36135904.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 4.903985118865966,
|
|
"epoch": 1.540798094103633,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047740103797869237,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.20335299670696258,
|
|
"num_tokens": 36149455.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 4.913683652877808,
|
|
"epoch": 1.5413936867182847,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047738242128457216,
|
|
"loss": 4.7413,
|
|
"mean_token_accuracy": 0.20784134417772293,
|
|
"num_tokens": 36163843.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.027645826339722,
|
|
"epoch": 1.5419892793329364,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047736379733132343,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.2032011017203331,
|
|
"num_tokens": 36180268.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.064872360229492,
|
|
"epoch": 1.5425848719475879,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047734516611961443,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.20374036729335784,
|
|
"num_tokens": 36193116.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 4.911268472671509,
|
|
"epoch": 1.5431804645622393,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004773265276501133,
|
|
"loss": 4.7733,
|
|
"mean_token_accuracy": 0.21502237170934677,
|
|
"num_tokens": 36205383.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 4.938145446777344,
|
|
"epoch": 1.543776057176891,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047730788192348856,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.21443276554346086,
|
|
"num_tokens": 36219028.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.0258870124816895,
|
|
"epoch": 1.5443716497915427,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047728922894040905,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.20027956813573838,
|
|
"num_tokens": 36233804.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 4.950965118408203,
|
|
"epoch": 1.5449672424061942,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004772705687015437,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.2041042849421501,
|
|
"num_tokens": 36246900.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 4.963247776031494,
|
|
"epoch": 1.5455628350208457,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047725190120756207,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.2138900190591812,
|
|
"num_tokens": 36260060.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 4.998151874542236,
|
|
"epoch": 1.5461584276354974,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047723322645913354,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.20971481651067733,
|
|
"num_tokens": 36274529.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.02972412109375,
|
|
"epoch": 1.5467540202501489,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047721454445692795,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.20496117621660231,
|
|
"num_tokens": 36288089.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.011529111862183,
|
|
"epoch": 1.5473496128648003,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047719585520161544,
|
|
"loss": 4.8314,
|
|
"mean_token_accuracy": 0.20206328779458999,
|
|
"num_tokens": 36301498.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 4.898112678527832,
|
|
"epoch": 1.547945205479452,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004771771586938664,
|
|
"loss": 4.6899,
|
|
"mean_token_accuracy": 0.21779363602399826,
|
|
"num_tokens": 36314087.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 4.96155309677124,
|
|
"epoch": 1.5485407980941037,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047715845493435135,
|
|
"loss": 4.8426,
|
|
"mean_token_accuracy": 0.20137815326452255,
|
|
"num_tokens": 36328573.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 4.956763362884521,
|
|
"epoch": 1.5491363907087552,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004771397439237412,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.2168680191040039,
|
|
"num_tokens": 36341536.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 4.983940935134887,
|
|
"epoch": 1.5497319833234067,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047712102566270715,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.20375103652477264,
|
|
"num_tokens": 36357125.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 4.976821374893189,
|
|
"epoch": 1.5503275759380584,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047710230015192054,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.20683923959732056,
|
|
"num_tokens": 36372466.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 4.989191579818725,
|
|
"epoch": 1.55092316855271,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047708356739205294,
|
|
"loss": 4.7018,
|
|
"mean_token_accuracy": 0.21019307076931,
|
|
"num_tokens": 36386207.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.006897401809693,
|
|
"epoch": 1.5515187611673615,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004770648273837764,
|
|
"loss": 4.8718,
|
|
"mean_token_accuracy": 0.19635456651449204,
|
|
"num_tokens": 36403862.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 4.977526140213013,
|
|
"epoch": 1.552114353782013,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000477046080127763,
|
|
"loss": 4.8002,
|
|
"mean_token_accuracy": 0.20480083376169206,
|
|
"num_tokens": 36417813.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 4.981815958023072,
|
|
"epoch": 1.5527099463966647,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004770273256246853,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.2092190444469452,
|
|
"num_tokens": 36431346.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 4.86539888381958,
|
|
"epoch": 1.5533055390113164,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047700856387521585,
|
|
"loss": 4.6549,
|
|
"mean_token_accuracy": 0.21408039033412934,
|
|
"num_tokens": 36445027.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.060624122619629,
|
|
"epoch": 1.5539011316259679,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004769897948800276,
|
|
"loss": 4.8925,
|
|
"mean_token_accuracy": 0.20054322481155396,
|
|
"num_tokens": 36461727.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.01222791671753,
|
|
"epoch": 1.5544967242406194,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047697101863979394,
|
|
"loss": 4.8097,
|
|
"mean_token_accuracy": 0.19681201428174971,
|
|
"num_tokens": 36477715.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 4.961147022247315,
|
|
"epoch": 1.555092316855271,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004769522351551882,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.2114467814564705,
|
|
"num_tokens": 36490478.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.033575201034546,
|
|
"epoch": 1.5556879094699225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004769334444268841,
|
|
"loss": 4.753,
|
|
"mean_token_accuracy": 0.20827415436506272,
|
|
"num_tokens": 36505876.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 4.937522840499878,
|
|
"epoch": 1.556283502084574,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047691464645555564,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.20993805825710296,
|
|
"num_tokens": 36519773.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 4.9806352138519285,
|
|
"epoch": 1.5568790946992257,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004768958412418772,
|
|
"loss": 4.832,
|
|
"mean_token_accuracy": 0.20076310336589814,
|
|
"num_tokens": 36534828.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 4.973097515106201,
|
|
"epoch": 1.5574746873138774,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047687702878652303,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.2029601275920868,
|
|
"num_tokens": 36550067.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 4.940093851089477,
|
|
"epoch": 1.5580702799285289,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047685820909016823,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.21006074398756028,
|
|
"num_tokens": 36564051.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 4.886382722854615,
|
|
"epoch": 1.5586658725431803,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004768393821534877,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.21591683179140092,
|
|
"num_tokens": 36578606.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 4.881505489349365,
|
|
"epoch": 1.559261465157832,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004768205479771566,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.21817180067300795,
|
|
"num_tokens": 36592192.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 4.98256483078003,
|
|
"epoch": 1.5598570577724837,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004768017065618506,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.20565610975027085,
|
|
"num_tokens": 36606896.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 4.922077178955078,
|
|
"epoch": 1.5604526503871352,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047678285790824556,
|
|
"loss": 4.7774,
|
|
"mean_token_accuracy": 0.20208290517330169,
|
|
"num_tokens": 36621133.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.001809978485108,
|
|
"epoch": 1.5610482430017867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004767640020170174,
|
|
"loss": 4.8024,
|
|
"mean_token_accuracy": 0.20350489467382432,
|
|
"num_tokens": 36636738.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 4.97994818687439,
|
|
"epoch": 1.5616438356164384,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004767451388888426,
|
|
"loss": 4.7218,
|
|
"mean_token_accuracy": 0.21226968318223954,
|
|
"num_tokens": 36649544.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 4.947807741165161,
|
|
"epoch": 1.56223942823109,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004767262685243976,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.21459754854440688,
|
|
"num_tokens": 36663821.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 4.953933620452881,
|
|
"epoch": 1.5628350208457416,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004767073909243594,
|
|
"loss": 4.7888,
|
|
"mean_token_accuracy": 0.20948553532361985,
|
|
"num_tokens": 36677707.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.0008752822875975,
|
|
"epoch": 1.563430613460393,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047668850608940504,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.20131853669881822,
|
|
"num_tokens": 36691704.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 4.994894647598267,
|
|
"epoch": 1.5640262060750447,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004766696140202119,
|
|
"loss": 4.8579,
|
|
"mean_token_accuracy": 0.20862697660923005,
|
|
"num_tokens": 36706636.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.0172406196594235,
|
|
"epoch": 1.5646217986896962,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047665071471745754,
|
|
"loss": 4.8255,
|
|
"mean_token_accuracy": 0.21077784150838852,
|
|
"num_tokens": 36720035.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 4.948790979385376,
|
|
"epoch": 1.5652173913043477,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047663180818181995,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.214656001329422,
|
|
"num_tokens": 36735102.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 4.94052267074585,
|
|
"epoch": 1.5658129839189994,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047661289441397724,
|
|
"loss": 4.8434,
|
|
"mean_token_accuracy": 0.19880405217409133,
|
|
"num_tokens": 36751666.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.026543855667114,
|
|
"epoch": 1.566408576533651,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004765939734146078,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.20287375301122665,
|
|
"num_tokens": 36767217.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.001867628097534,
|
|
"epoch": 1.5670041691483025,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004765750451843904,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.20823122859001159,
|
|
"num_tokens": 36784961.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 4.966748285293579,
|
|
"epoch": 1.567599761762954,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004765561097240037,
|
|
"loss": 4.8121,
|
|
"mean_token_accuracy": 0.21221720725297927,
|
|
"num_tokens": 36798166.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 4.879564666748047,
|
|
"epoch": 1.5681953543776057,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047653716703412717,
|
|
"loss": 4.76,
|
|
"mean_token_accuracy": 0.21338466554880142,
|
|
"num_tokens": 36813356.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.038466548919677,
|
|
"epoch": 1.5687909469922574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004765182171154401,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.20483713150024413,
|
|
"num_tokens": 36826502.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 4.94911937713623,
|
|
"epoch": 1.5693865396069089,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004764992599686222,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.21017406433820723,
|
|
"num_tokens": 36841359.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 4.922452354431153,
|
|
"epoch": 1.5699821322215604,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004764802955943535,
|
|
"loss": 4.7198,
|
|
"mean_token_accuracy": 0.21831945031881334,
|
|
"num_tokens": 36853908.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 4.913569736480713,
|
|
"epoch": 1.570577724836212,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047646132399331413,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.21062490791082383,
|
|
"num_tokens": 36866429.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 4.962885093688965,
|
|
"epoch": 1.5711733174508637,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047644234516618474,
|
|
"loss": 4.7652,
|
|
"mean_token_accuracy": 0.20365103632211684,
|
|
"num_tokens": 36879744.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.000160503387451,
|
|
"epoch": 1.5717689100655152,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047642335911364585,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.2055663913488388,
|
|
"num_tokens": 36894123.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.081522846221924,
|
|
"epoch": 1.5723645026801667,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047640436583637865,
|
|
"loss": 4.8035,
|
|
"mean_token_accuracy": 0.20311045348644258,
|
|
"num_tokens": 36908090.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 4.972617483139038,
|
|
"epoch": 1.5729600952948184,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047638536533506424,
|
|
"loss": 4.7948,
|
|
"mean_token_accuracy": 0.20661808997392656,
|
|
"num_tokens": 36925074.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.000595903396606,
|
|
"epoch": 1.5735556879094699,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047636635761038427,
|
|
"loss": 4.7997,
|
|
"mean_token_accuracy": 0.20039218962192534,
|
|
"num_tokens": 36940133.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 4.901806211471557,
|
|
"epoch": 1.5741512805241213,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047634734266302037,
|
|
"loss": 4.7193,
|
|
"mean_token_accuracy": 0.2101663500070572,
|
|
"num_tokens": 36954035.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.030431270599365,
|
|
"epoch": 1.574746873138773,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004763283204936547,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.20603307634592055,
|
|
"num_tokens": 36967072.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.0085962295532225,
|
|
"epoch": 1.5753424657534247,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004763092911029695,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.20999908745288848,
|
|
"num_tokens": 36980774.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 4.945301103591919,
|
|
"epoch": 1.5759380583680762,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004762902544916474,
|
|
"loss": 4.7422,
|
|
"mean_token_accuracy": 0.20813999325037003,
|
|
"num_tokens": 36993388.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 4.981873846054077,
|
|
"epoch": 1.5765336509827277,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004762712106603711,
|
|
"loss": 4.7643,
|
|
"mean_token_accuracy": 0.21007291376590728,
|
|
"num_tokens": 37007074.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.068686628341675,
|
|
"epoch": 1.5771292435973794,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047625215960982376,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.19938590377569199,
|
|
"num_tokens": 37021133.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 4.956632137298584,
|
|
"epoch": 1.577724836212031,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047623310134068867,
|
|
"loss": 4.6986,
|
|
"mean_token_accuracy": 0.20853076875209808,
|
|
"num_tokens": 37035584.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 4.93380217552185,
|
|
"epoch": 1.5783204288266826,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004762140358536493,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.20326432287693025,
|
|
"num_tokens": 37048374.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 4.9157191753387455,
|
|
"epoch": 1.578916021441334,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047619496314938977,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.20836919844150542,
|
|
"num_tokens": 37062340.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.014022302627564,
|
|
"epoch": 1.5795116140559857,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047617588322859395,
|
|
"loss": 4.7981,
|
|
"mean_token_accuracy": 0.2056633248925209,
|
|
"num_tokens": 37077469.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.0143474578857425,
|
|
"epoch": 1.5801072066706374,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004761567960919463,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.19919868260622026,
|
|
"num_tokens": 37092941.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 4.950302648544311,
|
|
"epoch": 1.580702799285289,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047613770174013146,
|
|
"loss": 4.6546,
|
|
"mean_token_accuracy": 0.22288692593574524,
|
|
"num_tokens": 37105033.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.015937376022339,
|
|
"epoch": 1.5812983918999404,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004761186001738342,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.20213811248540878,
|
|
"num_tokens": 37119182.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 4.982263135910034,
|
|
"epoch": 1.581893984514592,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047609949139373994,
|
|
"loss": 4.8256,
|
|
"mean_token_accuracy": 0.20247662514448167,
|
|
"num_tokens": 37135354.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 4.91712646484375,
|
|
"epoch": 1.5824895771292438,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004760803754005337,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.2144347533583641,
|
|
"num_tokens": 37150453.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.048561239242554,
|
|
"epoch": 1.583085169743895,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004760612521949014,
|
|
"loss": 4.9334,
|
|
"mean_token_accuracy": 0.19726980179548265,
|
|
"num_tokens": 37164714.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.078659534454346,
|
|
"epoch": 1.5836807623585467,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047604212177752885,
|
|
"loss": 4.8455,
|
|
"mean_token_accuracy": 0.20187220722436905,
|
|
"num_tokens": 37178904.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.035371732711792,
|
|
"epoch": 1.5842763549731984,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047602298414910237,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.2048469141125679,
|
|
"num_tokens": 37194158.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.026085662841797,
|
|
"epoch": 1.5848719475878499,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047600383931030823,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.20510425865650178,
|
|
"num_tokens": 37206906.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 4.915517807006836,
|
|
"epoch": 1.5854675402025014,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004759846872618332,
|
|
"loss": 4.7706,
|
|
"mean_token_accuracy": 0.21110417693853378,
|
|
"num_tokens": 37220512.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 4.920953178405762,
|
|
"epoch": 1.586063132817153,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047596552800436426,
|
|
"loss": 4.6772,
|
|
"mean_token_accuracy": 0.21357131004333496,
|
|
"num_tokens": 37233481.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.002429580688476,
|
|
"epoch": 1.5866587254318048,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047594636153858844,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.20765192210674285,
|
|
"num_tokens": 37247421.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 4.97697958946228,
|
|
"epoch": 1.5872543180464562,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047592718786519347,
|
|
"loss": 4.7981,
|
|
"mean_token_accuracy": 0.20808887034654616,
|
|
"num_tokens": 37261126.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 4.969406509399414,
|
|
"epoch": 1.5878499106611077,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047590800698486693,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.20476409047842026,
|
|
"num_tokens": 37273951.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 4.934676742553711,
|
|
"epoch": 1.5884455032757594,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004758888188982969,
|
|
"loss": 4.738,
|
|
"mean_token_accuracy": 0.20848949402570724,
|
|
"num_tokens": 37286937.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 4.9210755825042725,
|
|
"epoch": 1.589041095890411,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004758696236061715,
|
|
"loss": 4.7264,
|
|
"mean_token_accuracy": 0.209813492000103,
|
|
"num_tokens": 37300030.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.040786933898926,
|
|
"epoch": 1.5896366885050626,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004758504211091793,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.2002556338906288,
|
|
"num_tokens": 37316025.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 4.96601448059082,
|
|
"epoch": 1.590232281119714,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047583121140800906,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.2043320894241333,
|
|
"num_tokens": 37328414.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.012646293640136,
|
|
"epoch": 1.5908278737343657,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004758119945033497,
|
|
"loss": 4.8335,
|
|
"mean_token_accuracy": 0.2067323550581932,
|
|
"num_tokens": 37342865.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.040162658691406,
|
|
"epoch": 1.5914234663490174,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004757927703958907,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.20876632183790206,
|
|
"num_tokens": 37356340.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 4.9401460647583,
|
|
"epoch": 1.5920190589636687,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047577353908632156,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.21020862460136414,
|
|
"num_tokens": 37371047.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.016618156433106,
|
|
"epoch": 1.5926146515783204,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004757543005753319,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.20735587626695634,
|
|
"num_tokens": 37383245.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.011020803451538,
|
|
"epoch": 1.593210244192972,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047573505486361183,
|
|
"loss": 4.8658,
|
|
"mean_token_accuracy": 0.20671919137239456,
|
|
"num_tokens": 37397346.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 4.890403795242309,
|
|
"epoch": 1.5938058368076236,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004757158019518519,
|
|
"loss": 4.6738,
|
|
"mean_token_accuracy": 0.21990108788013457,
|
|
"num_tokens": 37409223.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 4.967981481552124,
|
|
"epoch": 1.594401429422275,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004756965418407424,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.20268003940582274,
|
|
"num_tokens": 37424127.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.025609493255615,
|
|
"epoch": 1.5949970220369267,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047567727453097427,
|
|
"loss": 4.7583,
|
|
"mean_token_accuracy": 0.2109602376818657,
|
|
"num_tokens": 37437618.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 4.992918157577515,
|
|
"epoch": 1.5955926146515784,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004756580000232385,
|
|
"loss": 4.7964,
|
|
"mean_token_accuracy": 0.2025860369205475,
|
|
"num_tokens": 37452703.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 4.966474294662476,
|
|
"epoch": 1.59618820726623,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047563871831822664,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.20513133108615875,
|
|
"num_tokens": 37465895.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.018649959564209,
|
|
"epoch": 1.5967837998808814,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004756194294166301,
|
|
"loss": 4.8058,
|
|
"mean_token_accuracy": 0.200119224190712,
|
|
"num_tokens": 37480468.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.010133361816406,
|
|
"epoch": 1.597379392495533,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004756001333191409,
|
|
"loss": 4.8718,
|
|
"mean_token_accuracy": 0.19737257361412047,
|
|
"num_tokens": 37494742.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 4.912026214599609,
|
|
"epoch": 1.5979749851101848,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047558083002645097,
|
|
"loss": 4.71,
|
|
"mean_token_accuracy": 0.2098759353160858,
|
|
"num_tokens": 37511150.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 4.964348459243775,
|
|
"epoch": 1.5985705777248362,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047556151953925287,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.20765166431665422,
|
|
"num_tokens": 37525752.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 4.9855578422546385,
|
|
"epoch": 1.5991661703394877,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004755422018582391,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.2226234719157219,
|
|
"num_tokens": 37537982.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.008946704864502,
|
|
"epoch": 1.5997617629541394,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047552287698410267,
|
|
"loss": 4.8956,
|
|
"mean_token_accuracy": 0.19905033558607102,
|
|
"num_tokens": 37552220.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 4.962391948699951,
|
|
"epoch": 1.600357355568791,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004755035449175366,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.2092219963669777,
|
|
"num_tokens": 37565306.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 4.964897394180298,
|
|
"epoch": 1.6009529481834424,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004754842056592344,
|
|
"loss": 4.6739,
|
|
"mean_token_accuracy": 0.21782763451337814,
|
|
"num_tokens": 37579417.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 4.896974706649781,
|
|
"epoch": 1.601548540798094,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047546485920988975,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.2106873720884323,
|
|
"num_tokens": 37593506.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 4.944012308120728,
|
|
"epoch": 1.6021441334127458,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004754455055701965,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.20775247514247894,
|
|
"num_tokens": 37607441.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.048555994033814,
|
|
"epoch": 1.6027397260273972,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004754261447408489,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.20134230107069015,
|
|
"num_tokens": 37622723.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 4.9599710464477536,
|
|
"epoch": 1.6033353186420487,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004754067767225413,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.20981521904468536,
|
|
"num_tokens": 37637426.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 4.8821193218231205,
|
|
"epoch": 1.6039309112567004,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004753874015159685,
|
|
"loss": 4.6625,
|
|
"mean_token_accuracy": 0.22006224393844603,
|
|
"num_tokens": 37649996.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.027644109725952,
|
|
"epoch": 1.604526503871352,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004753680191218254,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.21505290865898133,
|
|
"num_tokens": 37664188.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 4.911983823776245,
|
|
"epoch": 1.6051220964860036,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004753486295408073,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.211063976585865,
|
|
"num_tokens": 37678058.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 4.925011205673218,
|
|
"epoch": 1.605717689100655,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004753292327736095,
|
|
"loss": 4.7072,
|
|
"mean_token_accuracy": 0.2157053604722023,
|
|
"num_tokens": 37692830.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 4.937045383453369,
|
|
"epoch": 1.6063132817153067,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047530982882092794,
|
|
"loss": 4.7349,
|
|
"mean_token_accuracy": 0.2057565778493881,
|
|
"num_tokens": 37706587.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 4.93394284248352,
|
|
"epoch": 1.6069088743299584,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004752904176834584,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.20735469609498977,
|
|
"num_tokens": 37720625.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.10218358039856,
|
|
"epoch": 1.60750446694461,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047527099936189735,
|
|
"loss": 4.9124,
|
|
"mean_token_accuracy": 0.2045360803604126,
|
|
"num_tokens": 37734826.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.139401578903199,
|
|
"epoch": 1.6081000595592614,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000475251573856941,
|
|
"loss": 4.8202,
|
|
"mean_token_accuracy": 0.20638855695724487,
|
|
"num_tokens": 37747856.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 4.911412525177002,
|
|
"epoch": 1.608695652173913,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004752321411692864,
|
|
"loss": 4.8383,
|
|
"mean_token_accuracy": 0.2082383692264557,
|
|
"num_tokens": 37760291.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 4.894526576995849,
|
|
"epoch": 1.6092912447885648,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047521270129963043,
|
|
"loss": 4.6489,
|
|
"mean_token_accuracy": 0.21895756274461747,
|
|
"num_tokens": 37773704.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 4.9808649063110355,
|
|
"epoch": 1.6098868374032163,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004751932542486705,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.20494979470968247,
|
|
"num_tokens": 37787461.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.047716665267944,
|
|
"epoch": 1.6104824300178677,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004751738000171039,
|
|
"loss": 4.8908,
|
|
"mean_token_accuracy": 0.19672890454530717,
|
|
"num_tokens": 37802484.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.018007612228393,
|
|
"epoch": 1.6110780226325194,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047515433860562855,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.20702372193336488,
|
|
"num_tokens": 37816741.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.050218915939331,
|
|
"epoch": 1.611673615247171,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047513487001494257,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.19545359164476395,
|
|
"num_tokens": 37834424.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 4.982122421264648,
|
|
"epoch": 1.6122692078618224,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004751153942457442,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.20416463166475296,
|
|
"num_tokens": 37848392.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 4.955207872390747,
|
|
"epoch": 1.612864800476474,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000475095911298732,
|
|
"loss": 4.7704,
|
|
"mean_token_accuracy": 0.21047957688570024,
|
|
"num_tokens": 37862014.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 4.895503759384155,
|
|
"epoch": 1.6134603930911258,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004750764211746048,
|
|
"loss": 4.7121,
|
|
"mean_token_accuracy": 0.21145318895578386,
|
|
"num_tokens": 37876378.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.008826780319214,
|
|
"epoch": 1.6140559857057772,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047505692387406163,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.2098092958331108,
|
|
"num_tokens": 37888854.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 4.905754947662354,
|
|
"epoch": 1.6146515783204287,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047503741939780195,
|
|
"loss": 4.7046,
|
|
"mean_token_accuracy": 0.2152540698647499,
|
|
"num_tokens": 37902659.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 4.945415258407593,
|
|
"epoch": 1.6152471709350804,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004750179077465252,
|
|
"loss": 4.8374,
|
|
"mean_token_accuracy": 0.20342419743537904,
|
|
"num_tokens": 37917218.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.062634515762329,
|
|
"epoch": 1.615842763549732,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047499838892093134,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.20784399807453155,
|
|
"num_tokens": 37932141.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 4.976197624206543,
|
|
"epoch": 1.6164383561643836,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047497886292172044,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.2084738790988922,
|
|
"num_tokens": 37945817.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 4.841643285751343,
|
|
"epoch": 1.617033948779035,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047495932974959287,
|
|
"loss": 4.7418,
|
|
"mean_token_accuracy": 0.21596221178770064,
|
|
"num_tokens": 37960475.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 4.9394773006439205,
|
|
"epoch": 1.6176295413936868,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004749397894052493,
|
|
"loss": 4.7066,
|
|
"mean_token_accuracy": 0.21159276366233826,
|
|
"num_tokens": 37973211.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 4.950933742523193,
|
|
"epoch": 1.6182251340083385,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047492024188939056,
|
|
"loss": 4.6695,
|
|
"mean_token_accuracy": 0.21843355745077134,
|
|
"num_tokens": 37986760.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 4.990965032577515,
|
|
"epoch": 1.61882072662299,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004749006872027178,
|
|
"loss": 4.8809,
|
|
"mean_token_accuracy": 0.20346230566501616,
|
|
"num_tokens": 38002755.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.0933387756347654,
|
|
"epoch": 1.6194163192376414,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004748811253459324,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.1995992362499237,
|
|
"num_tokens": 38017735.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.053945112228393,
|
|
"epoch": 1.620011911852293,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004748615563197359,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.20673877894878387,
|
|
"num_tokens": 38033537.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 4.958750200271607,
|
|
"epoch": 1.6206075044669446,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004748419801248304,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.21155198365449907,
|
|
"num_tokens": 38049311.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 4.95852952003479,
|
|
"epoch": 1.621203097081596,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004748223967619181,
|
|
"loss": 4.7621,
|
|
"mean_token_accuracy": 0.20928653776645662,
|
|
"num_tokens": 38063269.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 4.976302433013916,
|
|
"epoch": 1.6217986896962477,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047480280623170116,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.19224278777837753,
|
|
"num_tokens": 38077642.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.0695576667785645,
|
|
"epoch": 1.6223942823108994,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047478320853488256,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.1963461548089981,
|
|
"num_tokens": 38091910.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.03663911819458,
|
|
"epoch": 1.622989874925551,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047476360367216505,
|
|
"loss": 4.8942,
|
|
"mean_token_accuracy": 0.1928950220346451,
|
|
"num_tokens": 38105105.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 4.9492346286773685,
|
|
"epoch": 1.6235854675402024,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004747439916442518,
|
|
"loss": 4.7572,
|
|
"mean_token_accuracy": 0.20152366608381272,
|
|
"num_tokens": 38118841.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 4.969115257263184,
|
|
"epoch": 1.624181060154854,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004747243724518465,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.21316577941179277,
|
|
"num_tokens": 38132116.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 4.959209299087524,
|
|
"epoch": 1.6247766527695058,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004747047460956525,
|
|
"loss": 4.6848,
|
|
"mean_token_accuracy": 0.2187585264444351,
|
|
"num_tokens": 38144944.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 4.85479507446289,
|
|
"epoch": 1.6253722453841573,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004746851125763741,
|
|
"loss": 4.6784,
|
|
"mean_token_accuracy": 0.2201787754893303,
|
|
"num_tokens": 38158464.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 4.951068925857544,
|
|
"epoch": 1.6259678379988087,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047466547189471534,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.20167431533336638,
|
|
"num_tokens": 38173807.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.011152982711792,
|
|
"epoch": 1.6265634306134604,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004746458240513807,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.2060869053006172,
|
|
"num_tokens": 38189478.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.000563240051269,
|
|
"epoch": 1.6271590232281121,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000474626169047075,
|
|
"loss": 4.7482,
|
|
"mean_token_accuracy": 0.20617880821228027,
|
|
"num_tokens": 38203478.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 4.918285369873047,
|
|
"epoch": 1.6277546158427636,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004746065068825032,
|
|
"loss": 4.6756,
|
|
"mean_token_accuracy": 0.2144153520464897,
|
|
"num_tokens": 38216273.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 4.979364204406738,
|
|
"epoch": 1.628350208457415,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047458683755837046,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.21242538541555406,
|
|
"num_tokens": 38228554.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 4.924009227752686,
|
|
"epoch": 1.6289458010720668,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004745671610753824,
|
|
"loss": 4.7661,
|
|
"mean_token_accuracy": 0.2000483587384224,
|
|
"num_tokens": 38242984.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 4.921609878540039,
|
|
"epoch": 1.6295413936867182,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004745474774342448,
|
|
"loss": 4.7937,
|
|
"mean_token_accuracy": 0.21981178522109984,
|
|
"num_tokens": 38256224.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.049601745605469,
|
|
"epoch": 1.6301369863013697,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004745277866356636,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.20404531210660934,
|
|
"num_tokens": 38269919.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 4.973023319244385,
|
|
"epoch": 1.6307325789160214,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004745080886803451,
|
|
"loss": 4.786,
|
|
"mean_token_accuracy": 0.21690429002046585,
|
|
"num_tokens": 38284363.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 4.987517881393432,
|
|
"epoch": 1.631328171530673,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004744883835689958,
|
|
"loss": 4.8139,
|
|
"mean_token_accuracy": 0.2050143748521805,
|
|
"num_tokens": 38299650.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 4.943052482604981,
|
|
"epoch": 1.6319237641453246,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047446867130232257,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.2115221917629242,
|
|
"num_tokens": 38313632.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 4.965347576141357,
|
|
"epoch": 1.632519356759976,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004744489518810324,
|
|
"loss": 4.8475,
|
|
"mean_token_accuracy": 0.20911132991313935,
|
|
"num_tokens": 38327037.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.002726602554321,
|
|
"epoch": 1.6331149493746278,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047442922530583265,
|
|
"loss": 4.8718,
|
|
"mean_token_accuracy": 0.20425430238246917,
|
|
"num_tokens": 38341833.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 4.981769847869873,
|
|
"epoch": 1.6337105419892795,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004744094915774308,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.19954196959733964,
|
|
"num_tokens": 38357261.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.012447023391724,
|
|
"epoch": 1.634306134603931,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047438975069653475,
|
|
"loss": 4.7862,
|
|
"mean_token_accuracy": 0.20413437336683274,
|
|
"num_tokens": 38371448.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 4.897135829925537,
|
|
"epoch": 1.6349017272185824,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004743700026638525,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.2238634169101715,
|
|
"num_tokens": 38385385.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 4.946589374542237,
|
|
"epoch": 1.635497319833234,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004743502474800924,
|
|
"loss": 4.7386,
|
|
"mean_token_accuracy": 0.21651485711336135,
|
|
"num_tokens": 38398506.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.00047116279602,
|
|
"epoch": 1.6360929124478858,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047433048514596303,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.2014414846897125,
|
|
"num_tokens": 38414283.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.000758504867553,
|
|
"epoch": 1.6366885050625373,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004743107156621733,
|
|
"loss": 4.7856,
|
|
"mean_token_accuracy": 0.20947671979665755,
|
|
"num_tokens": 38427436.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.010483741760254,
|
|
"epoch": 1.6372840976771887,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047429093902943227,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.1999393492937088,
|
|
"num_tokens": 38442414.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.012062835693359,
|
|
"epoch": 1.6378796902918404,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004742711552484492,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.20499683022499085,
|
|
"num_tokens": 38457196.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 4.92486572265625,
|
|
"epoch": 1.638475282906492,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004742513643199339,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.21719765663146973,
|
|
"num_tokens": 38470425.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 4.98419771194458,
|
|
"epoch": 1.6390708755211434,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000474231566244596,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.1984284222126007,
|
|
"num_tokens": 38484731.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.011884880065918,
|
|
"epoch": 1.639666468135795,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047421176102314586,
|
|
"loss": 4.7861,
|
|
"mean_token_accuracy": 0.21462200134992598,
|
|
"num_tokens": 38499291.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 4.97078127861023,
|
|
"epoch": 1.6402620607504468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047419194865629366,
|
|
"loss": 4.7075,
|
|
"mean_token_accuracy": 0.21178652495145797,
|
|
"num_tokens": 38513082.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 4.887765884399414,
|
|
"epoch": 1.6408576533650983,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047417212914475015,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.2112904742360115,
|
|
"num_tokens": 38526438.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 4.968595886230469,
|
|
"epoch": 1.6414532459797497,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047415230248922625,
|
|
"loss": 4.7207,
|
|
"mean_token_accuracy": 0.21329473257064818,
|
|
"num_tokens": 38541749.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 4.957650470733642,
|
|
"epoch": 1.6420488385944014,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004741324686904331,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.20574771165847777,
|
|
"num_tokens": 38555406.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 4.940942621231079,
|
|
"epoch": 1.6426444312090531,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047411262774908194,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.21723448783159255,
|
|
"num_tokens": 38567959.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.0031609535217285,
|
|
"epoch": 1.6432400238237046,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004740927796658846,
|
|
"loss": 4.8141,
|
|
"mean_token_accuracy": 0.21097390353679657,
|
|
"num_tokens": 38581199.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 4.972623348236084,
|
|
"epoch": 1.643835616438356,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000474072924441553,
|
|
"loss": 4.7258,
|
|
"mean_token_accuracy": 0.20868918299674988,
|
|
"num_tokens": 38594050.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 4.9387115955352785,
|
|
"epoch": 1.6444312090530078,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047405306207679926,
|
|
"loss": 4.8038,
|
|
"mean_token_accuracy": 0.21019413322210312,
|
|
"num_tokens": 38608649.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.020468044281006,
|
|
"epoch": 1.6450268016676595,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047403319257233585,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.20311961621046065,
|
|
"num_tokens": 38623023.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 4.944225835800171,
|
|
"epoch": 1.645622394282311,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004740133159288753,
|
|
"loss": 4.6851,
|
|
"mean_token_accuracy": 0.2173658788204193,
|
|
"num_tokens": 38637738.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 4.878592586517334,
|
|
"epoch": 1.6462179868969624,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004739934321471308,
|
|
"loss": 4.6831,
|
|
"mean_token_accuracy": 0.21441845148801802,
|
|
"num_tokens": 38651542.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.04253888130188,
|
|
"epoch": 1.6468135795116141,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004739735412278154,
|
|
"loss": 4.897,
|
|
"mean_token_accuracy": 0.1943783402442932,
|
|
"num_tokens": 38667607.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.0021594047546385,
|
|
"epoch": 1.6474091721262656,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004739536431716427,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.21372508108615876,
|
|
"num_tokens": 38681192.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 4.993165493011475,
|
|
"epoch": 1.648004764740917,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047393373797932614,
|
|
"loss": 4.8463,
|
|
"mean_token_accuracy": 0.2034062385559082,
|
|
"num_tokens": 38694124.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 4.930874443054199,
|
|
"epoch": 1.6486003573555688,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047391382565157994,
|
|
"loss": 4.7771,
|
|
"mean_token_accuracy": 0.2056779831647873,
|
|
"num_tokens": 38709225.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 4.903248882293701,
|
|
"epoch": 1.6491959499702205,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004738939061891182,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.21825917065143585,
|
|
"num_tokens": 38723662.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 4.971566963195801,
|
|
"epoch": 1.649791542584872,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004738739795926554,
|
|
"loss": 4.7919,
|
|
"mean_token_accuracy": 0.2078393965959549,
|
|
"num_tokens": 38738561.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 4.99254732131958,
|
|
"epoch": 1.6503871351995234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004738540458629063,
|
|
"loss": 4.8242,
|
|
"mean_token_accuracy": 0.20219926685094833,
|
|
"num_tokens": 38752795.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 4.932990837097168,
|
|
"epoch": 1.650982727814175,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004738341050005859,
|
|
"loss": 4.6915,
|
|
"mean_token_accuracy": 0.21306927055120467,
|
|
"num_tokens": 38764854.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 4.894563484191894,
|
|
"epoch": 1.6515783204288268,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047381415700640953,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.21345131248235702,
|
|
"num_tokens": 38778856.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 4.940117979049683,
|
|
"epoch": 1.6521739130434783,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047379420188109245,
|
|
"loss": 4.7447,
|
|
"mean_token_accuracy": 0.217704114317894,
|
|
"num_tokens": 38790970.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 4.905100154876709,
|
|
"epoch": 1.6527695056581297,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004737742396253506,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.21279367357492446,
|
|
"num_tokens": 38805311.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 4.96592230796814,
|
|
"epoch": 1.6533650982727814,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004737542702399,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.21509986519813537,
|
|
"num_tokens": 38818690.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 4.9495011329650875,
|
|
"epoch": 1.6539606908874331,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047373429372545695,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.20330231338739396,
|
|
"num_tokens": 38833166.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 4.941434049606324,
|
|
"epoch": 1.6545562835020846,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004737143100827378,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.20910973697900773,
|
|
"num_tokens": 38847630.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 4.971389436721802,
|
|
"epoch": 1.655151876116736,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004736943193124595,
|
|
"loss": 4.7404,
|
|
"mean_token_accuracy": 0.21218364983797072,
|
|
"num_tokens": 38862483.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 4.916759967803955,
|
|
"epoch": 1.6557474687313878,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000473674321415339,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.2097068965435028,
|
|
"num_tokens": 38876619.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.02146315574646,
|
|
"epoch": 1.6563430613460393,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004736543163920936,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.19968653172254563,
|
|
"num_tokens": 38889125.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.0082653045654295,
|
|
"epoch": 1.6569386539606907,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004736343042434409,
|
|
"loss": 4.7844,
|
|
"mean_token_accuracy": 0.2057318612933159,
|
|
"num_tokens": 38903392.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 4.962252426147461,
|
|
"epoch": 1.6575342465753424,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004736142849700986,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.19987883865833284,
|
|
"num_tokens": 38917610.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.036459016799927,
|
|
"epoch": 1.6581298391899941,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047359425857278485,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.2077454462647438,
|
|
"num_tokens": 38930659.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 4.901589965820312,
|
|
"epoch": 1.6587254318046456,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000473574225052218,
|
|
"loss": 4.6487,
|
|
"mean_token_accuracy": 0.208573617041111,
|
|
"num_tokens": 38945958.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 4.977940273284912,
|
|
"epoch": 1.659321024419297,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004735541844091165,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.20976955443620682,
|
|
"num_tokens": 38960817.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 4.986295509338379,
|
|
"epoch": 1.6599166170339488,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004735341366441993,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.20780259370803833,
|
|
"num_tokens": 38976227.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 4.959527778625488,
|
|
"epoch": 1.6605122096486005,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047351408175818537,
|
|
"loss": 4.7565,
|
|
"mean_token_accuracy": 0.20126869827508925,
|
|
"num_tokens": 38991586.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 4.930639123916626,
|
|
"epoch": 1.661107802263252,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004734940197517941,
|
|
"loss": 4.6984,
|
|
"mean_token_accuracy": 0.21428538113832474,
|
|
"num_tokens": 39004693.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 4.996437835693359,
|
|
"epoch": 1.6617033948779034,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000473473950625745,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.20299281030893326,
|
|
"num_tokens": 39018546.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 4.95429573059082,
|
|
"epoch": 1.6622989874925551,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047345387438075805,
|
|
"loss": 4.6962,
|
|
"mean_token_accuracy": 0.21171096265316008,
|
|
"num_tokens": 39032219.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 4.99734058380127,
|
|
"epoch": 1.6628945801072068,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004734337910175533,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.20037527978420258,
|
|
"num_tokens": 39047379.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 4.955996465682984,
|
|
"epoch": 1.6634901727218583,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047341370053685113,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.21915015131235122,
|
|
"num_tokens": 39060627.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 4.943799018859863,
|
|
"epoch": 1.6640857653365098,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004733936029393721,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.21682180911302568,
|
|
"num_tokens": 39073210.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 4.910370779037476,
|
|
"epoch": 1.6646813579511615,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004733734982258371,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.2127809926867485,
|
|
"num_tokens": 39087957.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 4.9398986339569095,
|
|
"epoch": 1.665276950565813,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047335338639696724,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.20695908963680268,
|
|
"num_tokens": 39102744.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.031782579421997,
|
|
"epoch": 1.6658725431804644,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004733332674534839,
|
|
"loss": 4.8629,
|
|
"mean_token_accuracy": 0.2044470027089119,
|
|
"num_tokens": 39116771.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 4.963303184509277,
|
|
"epoch": 1.666468135795116,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004733131413961087,
|
|
"loss": 4.8068,
|
|
"mean_token_accuracy": 0.20805037319660186,
|
|
"num_tokens": 39132634.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.0435652256011965,
|
|
"epoch": 1.6670637284097678,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047329300822556363,
|
|
"loss": 4.8344,
|
|
"mean_token_accuracy": 0.2053744986653328,
|
|
"num_tokens": 39146837.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 4.9884175777435305,
|
|
"epoch": 1.6676593210244193,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004732728679425707,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.2032952129840851,
|
|
"num_tokens": 39162067.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 4.944282341003418,
|
|
"epoch": 1.6682549136390707,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004732527205478524,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.21386218965053558,
|
|
"num_tokens": 39175466.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 4.916101026535034,
|
|
"epoch": 1.6688505062537224,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004732325660421314,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.20866165608167647,
|
|
"num_tokens": 39188943.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 4.910692119598389,
|
|
"epoch": 1.6694460988683741,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004732124044261304,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.21462552696466447,
|
|
"num_tokens": 39202544.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 4.930235528945923,
|
|
"epoch": 1.6700416914830256,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047319223570057293,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.21426481008529663,
|
|
"num_tokens": 39217183.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 4.96923713684082,
|
|
"epoch": 1.670637284097677,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004731720598661821,
|
|
"loss": 4.7245,
|
|
"mean_token_accuracy": 0.2155783087015152,
|
|
"num_tokens": 39232227.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.014634656906128,
|
|
"epoch": 1.6712328767123288,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047315187692368167,
|
|
"loss": 4.8104,
|
|
"mean_token_accuracy": 0.20814720243215562,
|
|
"num_tokens": 39245393.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 4.999180746078491,
|
|
"epoch": 1.6718284693269805,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004731316868737957,
|
|
"loss": 4.7835,
|
|
"mean_token_accuracy": 0.19876050800085068,
|
|
"num_tokens": 39258325.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.0163898944854735,
|
|
"epoch": 1.672424061941632,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047311148971724816,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.1996088445186615,
|
|
"num_tokens": 39271372.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 4.9488307476043705,
|
|
"epoch": 1.6730196545562834,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004730912854547636,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.21169735193252565,
|
|
"num_tokens": 39286054.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 4.999275588989258,
|
|
"epoch": 1.6736152471709351,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004730710740870667,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.2088916376233101,
|
|
"num_tokens": 39301005.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.00952672958374,
|
|
"epoch": 1.6742108397855868,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047305085561488247,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.20697644501924514,
|
|
"num_tokens": 39315931.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 4.921502494812012,
|
|
"epoch": 1.674806432400238,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047303063003893605,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.20945451706647872,
|
|
"num_tokens": 39330015.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 4.883656692504883,
|
|
"epoch": 1.6754020250148898,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004730103973599529,
|
|
"loss": 4.6983,
|
|
"mean_token_accuracy": 0.21092647314071655,
|
|
"num_tokens": 39346024.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 4.922253370285034,
|
|
"epoch": 1.6759976176295415,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004729901575786588,
|
|
"loss": 4.8223,
|
|
"mean_token_accuracy": 0.20366741567850113,
|
|
"num_tokens": 39359887.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.007746171951294,
|
|
"epoch": 1.676593210244193,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047296991069577953,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.20949654281139374,
|
|
"num_tokens": 39374999.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 4.96614146232605,
|
|
"epoch": 1.6771888028588444,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004729496567120415,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.2172719195485115,
|
|
"num_tokens": 39389246.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 4.858899927139282,
|
|
"epoch": 1.6777843954734961,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047292939562817115,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.21173237413167953,
|
|
"num_tokens": 39403026.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 4.930138397216797,
|
|
"epoch": 1.6783799880881478,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004729091274448952,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.20712943375110626,
|
|
"num_tokens": 39414933.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 4.991447782516479,
|
|
"epoch": 1.6789755807027993,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004728888521629406,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.21037475615739823,
|
|
"num_tokens": 39428369.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.002747297286987,
|
|
"epoch": 1.6795711733174508,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047286856978303465,
|
|
"loss": 4.7707,
|
|
"mean_token_accuracy": 0.20802400559186934,
|
|
"num_tokens": 39440892.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 4.997497940063477,
|
|
"epoch": 1.6801667659321025,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004728482803059048,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.20920956134796143,
|
|
"num_tokens": 39454607.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 4.881704616546631,
|
|
"epoch": 1.6807623585467542,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004728279837322788,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.21301850378513337,
|
|
"num_tokens": 39470112.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.008756256103515,
|
|
"epoch": 1.6813579511614056,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004728076800628847,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.21880352050065993,
|
|
"num_tokens": 39484498.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 4.927678060531616,
|
|
"epoch": 1.681953543776057,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004727873692984507,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.21255994886159896,
|
|
"num_tokens": 39500571.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 4.909414052963257,
|
|
"epoch": 1.6825491363907088,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004727670514397054,
|
|
"loss": 4.6794,
|
|
"mean_token_accuracy": 0.22000014930963516,
|
|
"num_tokens": 39514804.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 4.897302579879761,
|
|
"epoch": 1.6831447290053605,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004727467264873775,
|
|
"loss": 4.6602,
|
|
"mean_token_accuracy": 0.21686591506004332,
|
|
"num_tokens": 39527190.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 4.890182113647461,
|
|
"epoch": 1.6837403216200117,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000472726394442196,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.2092810720205307,
|
|
"num_tokens": 39540658.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 4.976966428756714,
|
|
"epoch": 1.6843359142346634,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047270605530489026,
|
|
"loss": 4.7325,
|
|
"mean_token_accuracy": 0.2127588525414467,
|
|
"num_tokens": 39553648.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.017618227005005,
|
|
"epoch": 1.6849315068493151,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047268570907618967,
|
|
"loss": 4.8307,
|
|
"mean_token_accuracy": 0.20345938950777054,
|
|
"num_tokens": 39569011.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 4.988108921051025,
|
|
"epoch": 1.6855270994639666,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004726653557568242,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.20816420018672943,
|
|
"num_tokens": 39582512.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 4.964961099624634,
|
|
"epoch": 1.686122692078618,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047264499534752384,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.2092190220952034,
|
|
"num_tokens": 39596806.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 4.968480920791626,
|
|
"epoch": 1.6867182846932698,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047262462784901875,
|
|
"loss": 4.6652,
|
|
"mean_token_accuracy": 0.20942565351724624,
|
|
"num_tokens": 39609905.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 4.917692995071411,
|
|
"epoch": 1.6873138773079215,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047260425326203965,
|
|
"loss": 4.7008,
|
|
"mean_token_accuracy": 0.21192629039287567,
|
|
"num_tokens": 39622152.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 4.869125509262085,
|
|
"epoch": 1.687909469922573,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004725838715873172,
|
|
"loss": 4.7141,
|
|
"mean_token_accuracy": 0.21088618487119676,
|
|
"num_tokens": 39634041.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 4.97875485420227,
|
|
"epoch": 1.6885050625372244,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047256348282558264,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.21228909790515899,
|
|
"num_tokens": 39647932.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 4.950129699707031,
|
|
"epoch": 1.6891006551518761,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047254308697756704,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.20634891390800475,
|
|
"num_tokens": 39662393.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 4.919709300994873,
|
|
"epoch": 1.6896962477665278,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004725226840440022,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.21863838285207748,
|
|
"num_tokens": 39676718.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.098130941390991,
|
|
"epoch": 1.6902918403811793,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047250227402561976,
|
|
"loss": 4.8926,
|
|
"mean_token_accuracy": 0.20428287386894226,
|
|
"num_tokens": 39692663.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 4.9635217666625975,
|
|
"epoch": 1.6908874329958308,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004724818569231519,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.21966644674539565,
|
|
"num_tokens": 39706874.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 4.887499189376831,
|
|
"epoch": 1.6914830256104825,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047246143273733097,
|
|
"loss": 4.7209,
|
|
"mean_token_accuracy": 0.21285279393196105,
|
|
"num_tokens": 39722194.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 4.967063951492309,
|
|
"epoch": 1.6920786182251342,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004724410014688894,
|
|
"loss": 4.773,
|
|
"mean_token_accuracy": 0.21392491906881334,
|
|
"num_tokens": 39735041.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 4.920918941497803,
|
|
"epoch": 1.6926742108397854,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047242056311856017,
|
|
"loss": 4.6858,
|
|
"mean_token_accuracy": 0.2243279367685318,
|
|
"num_tokens": 39749582.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.013016128540039,
|
|
"epoch": 1.6932698034544371,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004724001176870764,
|
|
"loss": 4.8545,
|
|
"mean_token_accuracy": 0.20525604635477065,
|
|
"num_tokens": 39764423.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.020413637161255,
|
|
"epoch": 1.6938653960690888,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004723796651751713,
|
|
"loss": 4.8196,
|
|
"mean_token_accuracy": 0.20894992500543594,
|
|
"num_tokens": 39778072.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 4.987286806106567,
|
|
"epoch": 1.6944609886837403,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004723592055835784,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.21073400378227233,
|
|
"num_tokens": 39791472.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 4.868895244598389,
|
|
"epoch": 1.6950565812983918,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047233873891303193,
|
|
"loss": 4.6546,
|
|
"mean_token_accuracy": 0.2216554045677185,
|
|
"num_tokens": 39804264.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 4.974124813079834,
|
|
"epoch": 1.6956521739130435,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047231826516426554,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.21263860911130905,
|
|
"num_tokens": 39818275.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 4.9651346683502195,
|
|
"epoch": 1.6962477665276952,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004722977843380139,
|
|
"loss": 4.726,
|
|
"mean_token_accuracy": 0.20541203767061234,
|
|
"num_tokens": 39832765.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 4.930977296829224,
|
|
"epoch": 1.6968433591423466,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004722772964350115,
|
|
"loss": 4.709,
|
|
"mean_token_accuracy": 0.20947428345680236,
|
|
"num_tokens": 39846113.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 4.991397762298584,
|
|
"epoch": 1.697438951756998,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047225680145599326,
|
|
"loss": 4.8295,
|
|
"mean_token_accuracy": 0.20590357929468156,
|
|
"num_tokens": 39860076.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 4.957652044296265,
|
|
"epoch": 1.6980345443716498,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004722362994016942,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.21698322594165803,
|
|
"num_tokens": 39873098.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.023602056503296,
|
|
"epoch": 1.6986301369863015,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004722157902728498,
|
|
"loss": 4.8574,
|
|
"mean_token_accuracy": 0.2017623722553253,
|
|
"num_tokens": 39886921.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.0349164485931395,
|
|
"epoch": 1.699225729600953,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047219527407019575,
|
|
"loss": 4.773,
|
|
"mean_token_accuracy": 0.206284998357296,
|
|
"num_tokens": 39900525.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 4.9233739376068115,
|
|
"epoch": 1.6998213222156044,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047217475079446773,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.21560959815979003,
|
|
"num_tokens": 39912302.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 4.939976501464844,
|
|
"epoch": 1.7004169148302561,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000472154220446402,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.2107322707772255,
|
|
"num_tokens": 39924575.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 4.9500244140625,
|
|
"epoch": 1.7010125074449078,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047213368302673496,
|
|
"loss": 4.7282,
|
|
"mean_token_accuracy": 0.2077522560954094,
|
|
"num_tokens": 39941997.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 4.9841841697692875,
|
|
"epoch": 1.7016081000595593,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004721131385362033,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.20899513810873033,
|
|
"num_tokens": 39955490.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.003642320632935,
|
|
"epoch": 1.7022036926742108,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004720925869755437,
|
|
"loss": 4.7643,
|
|
"mean_token_accuracy": 0.21234866380691528,
|
|
"num_tokens": 39968051.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 4.919752168655395,
|
|
"epoch": 1.7027992852888625,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047207202834549357,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.21105076968669892,
|
|
"num_tokens": 39980609.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 4.9442075252532955,
|
|
"epoch": 1.703394877903514,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047205146264679015,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.20169955790042876,
|
|
"num_tokens": 39995065.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 4.92035984992981,
|
|
"epoch": 1.7039904705181654,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047203088988017114,
|
|
"loss": 4.6891,
|
|
"mean_token_accuracy": 0.20941853523254395,
|
|
"num_tokens": 40010122.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.040221118927002,
|
|
"epoch": 1.7045860631328171,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047201031004637445,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.20298416614532472,
|
|
"num_tokens": 40022467.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 4.939500379562378,
|
|
"epoch": 1.7051816557474688,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004719897231461383,
|
|
"loss": 4.7396,
|
|
"mean_token_accuracy": 0.2139538511633873,
|
|
"num_tokens": 40036128.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.008707332611084,
|
|
"epoch": 1.7057772483621203,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004719691291802011,
|
|
"loss": 4.8834,
|
|
"mean_token_accuracy": 0.20457521677017212,
|
|
"num_tokens": 40049594.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 4.948508214950562,
|
|
"epoch": 1.7063728409767718,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047194852814930145,
|
|
"loss": 4.7736,
|
|
"mean_token_accuracy": 0.20207327008247375,
|
|
"num_tokens": 40064189.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.043017768859864,
|
|
"epoch": 1.7069684335914235,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047192792005417827,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.19485922306776046,
|
|
"num_tokens": 40079758.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 4.899400138854981,
|
|
"epoch": 1.7075640262060752,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004719073048955709,
|
|
"loss": 4.7093,
|
|
"mean_token_accuracy": 0.21757010817527772,
|
|
"num_tokens": 40093341.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 4.959854173660278,
|
|
"epoch": 1.7081596188207266,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004718866826742185,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.21306869089603425,
|
|
"num_tokens": 40106867.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 4.998501300811768,
|
|
"epoch": 1.7087552114353781,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000471866053390861,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.20775739550590516,
|
|
"num_tokens": 40121836.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 4.964433908462524,
|
|
"epoch": 1.7093508040500298,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047184541704623823,
|
|
"loss": 4.7566,
|
|
"mean_token_accuracy": 0.20593029409646987,
|
|
"num_tokens": 40135562.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 4.948807287216186,
|
|
"epoch": 1.7099463966646815,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047182477364109045,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.20882294178009034,
|
|
"num_tokens": 40149360.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 4.9686970710754395,
|
|
"epoch": 1.710541989279333,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000471804123176158,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.2100470632314682,
|
|
"num_tokens": 40164000.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.074799394607544,
|
|
"epoch": 1.7111375818939845,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004717834656521816,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.2063540607690811,
|
|
"num_tokens": 40179382.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 4.9056604385375975,
|
|
"epoch": 1.7117331745086362,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047176280106990233,
|
|
"loss": 4.723,
|
|
"mean_token_accuracy": 0.21406667828559875,
|
|
"num_tokens": 40193665.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 4.9019420623779295,
|
|
"epoch": 1.7123287671232876,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004717421294300612,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.21749064773321153,
|
|
"num_tokens": 40207139.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.042144012451172,
|
|
"epoch": 1.712924359737939,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004717214507333999,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.20536432266235352,
|
|
"num_tokens": 40220851.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 4.9258064270019535,
|
|
"epoch": 1.7135199523525908,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047170076498066,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.20281822085380555,
|
|
"num_tokens": 40235069.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 4.893875408172607,
|
|
"epoch": 1.7141155449672425,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004716800721725834,
|
|
"loss": 4.6776,
|
|
"mean_token_accuracy": 0.2231007233262062,
|
|
"num_tokens": 40247066.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 4.874076318740845,
|
|
"epoch": 1.714711137581894,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004716593723099124,
|
|
"loss": 4.6171,
|
|
"mean_token_accuracy": 0.22448783814907075,
|
|
"num_tokens": 40261083.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 4.9018291473388675,
|
|
"epoch": 1.7153067301965454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047163866539338945,
|
|
"loss": 4.6721,
|
|
"mean_token_accuracy": 0.2187030792236328,
|
|
"num_tokens": 40276961.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 4.852034044265747,
|
|
"epoch": 1.7159023228111971,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047161795142375735,
|
|
"loss": 4.6168,
|
|
"mean_token_accuracy": 0.22644728124141694,
|
|
"num_tokens": 40290024.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 4.9242658615112305,
|
|
"epoch": 1.7164979154258488,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047159723040175896,
|
|
"loss": 4.6397,
|
|
"mean_token_accuracy": 0.22085737586021423,
|
|
"num_tokens": 40301780.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 4.852041387557984,
|
|
"epoch": 1.7170935080405003,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004715765023281376,
|
|
"loss": 4.6565,
|
|
"mean_token_accuracy": 0.22201622724533082,
|
|
"num_tokens": 40315956.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 4.920735263824463,
|
|
"epoch": 1.7176891006551518,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004715557672036367,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.19906715154647828,
|
|
"num_tokens": 40330592.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 4.953486013412475,
|
|
"epoch": 1.7182846932698035,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047153502502899995,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.21366128623485564,
|
|
"num_tokens": 40343142.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 4.94919490814209,
|
|
"epoch": 1.7188802858844552,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047151427580497155,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.2040008544921875,
|
|
"num_tokens": 40355964.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 4.989862966537475,
|
|
"epoch": 1.7194758784991067,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004714935195322954,
|
|
"loss": 4.7193,
|
|
"mean_token_accuracy": 0.20472978353500365,
|
|
"num_tokens": 40368981.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 4.900966501235962,
|
|
"epoch": 1.7200714711137581,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004714727562117163,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.20878822803497316,
|
|
"num_tokens": 40384158.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 4.9176915168762205,
|
|
"epoch": 1.7206670637284098,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047145198584397884,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.2169020429253578,
|
|
"num_tokens": 40398202.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 4.969156408309937,
|
|
"epoch": 1.7212626563430613,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004714312084298281,
|
|
"loss": 4.718,
|
|
"mean_token_accuracy": 0.21037425547838212,
|
|
"num_tokens": 40412011.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.008573770523071,
|
|
"epoch": 1.7218582489577128,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004714104239700093,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.21080793291330338,
|
|
"num_tokens": 40424986.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 4.936797666549682,
|
|
"epoch": 1.7224538415723645,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004713896324652679,
|
|
"loss": 4.7293,
|
|
"mean_token_accuracy": 0.2187320500612259,
|
|
"num_tokens": 40440862.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 4.968926095962525,
|
|
"epoch": 1.7230494341870162,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047136883391634966,
|
|
"loss": 4.7774,
|
|
"mean_token_accuracy": 0.20737423598766327,
|
|
"num_tokens": 40454234.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 4.931639575958252,
|
|
"epoch": 1.7236450268016676,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004713480283240007,
|
|
"loss": 4.7557,
|
|
"mean_token_accuracy": 0.2114742264151573,
|
|
"num_tokens": 40467996.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 4.980147886276245,
|
|
"epoch": 1.7242406194163191,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004713272156889672,
|
|
"loss": 4.786,
|
|
"mean_token_accuracy": 0.2092204973101616,
|
|
"num_tokens": 40481334.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 4.9113904476165775,
|
|
"epoch": 1.7248362120309708,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004713063960119956,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.2163454696536064,
|
|
"num_tokens": 40493332.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 4.944243144989014,
|
|
"epoch": 1.7254318046456225,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047128556929383283,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.21211030930280686,
|
|
"num_tokens": 40507840.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 4.987086486816406,
|
|
"epoch": 1.726027397260274,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047126473553522576,
|
|
"loss": 4.8192,
|
|
"mean_token_accuracy": 0.20860666483640672,
|
|
"num_tokens": 40521061.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.062882661819458,
|
|
"epoch": 1.7266229898749255,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004712438947369218,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.20166956931352614,
|
|
"num_tokens": 40533844.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.000242900848389,
|
|
"epoch": 1.7272185824895772,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004712230468996684,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.20284539312124253,
|
|
"num_tokens": 40545889.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 4.903427600860596,
|
|
"epoch": 1.7278141751042289,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004712021920242133,
|
|
"loss": 4.6751,
|
|
"mean_token_accuracy": 0.21643412858247757,
|
|
"num_tokens": 40558904.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 4.944525051116943,
|
|
"epoch": 1.7284097677188803,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047118133011130465,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.20695166140794755,
|
|
"num_tokens": 40574045.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 4.909795951843262,
|
|
"epoch": 1.7290053603335318,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004711604611616905,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.21187723726034163,
|
|
"num_tokens": 40589619.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 4.925585508346558,
|
|
"epoch": 1.7296009529481835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004711395851761198,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.21903157830238343,
|
|
"num_tokens": 40602954.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 4.9854865074157715,
|
|
"epoch": 1.730196545562835,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004711187021553409,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.21308678090572358,
|
|
"num_tokens": 40617987.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 4.949057292938233,
|
|
"epoch": 1.7307921381774864,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047109781210010306,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.207129368185997,
|
|
"num_tokens": 40631355.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 4.91467547416687,
|
|
"epoch": 1.7313877307921381,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047107691501115556,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.2106470435857773,
|
|
"num_tokens": 40645196.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 4.90410099029541,
|
|
"epoch": 1.7319833234067898,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004710560108892479,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.2230506271123886,
|
|
"num_tokens": 40659114.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.018115758895874,
|
|
"epoch": 1.7325789160214413,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047103509973513,
|
|
"loss": 4.7445,
|
|
"mean_token_accuracy": 0.21352616101503372,
|
|
"num_tokens": 40672898.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 4.960417890548706,
|
|
"epoch": 1.7331745086360928,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047101418154955166,
|
|
"loss": 4.7513,
|
|
"mean_token_accuracy": 0.21023454517126083,
|
|
"num_tokens": 40686582.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 4.878598308563232,
|
|
"epoch": 1.7337701012507445,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004709932563332633,
|
|
"loss": 4.6631,
|
|
"mean_token_accuracy": 0.21126018911600114,
|
|
"num_tokens": 40701568.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 4.9970286846160885,
|
|
"epoch": 1.7343656938653962,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047097232408701564,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.2113347604870796,
|
|
"num_tokens": 40714642.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.0970663070678714,
|
|
"epoch": 1.7349612864800477,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047095138481155924,
|
|
"loss": 4.9125,
|
|
"mean_token_accuracy": 0.19725942760705947,
|
|
"num_tokens": 40728972.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 4.99816861152649,
|
|
"epoch": 1.7355568790946991,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047093043850764533,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.20843342393636705,
|
|
"num_tokens": 40742332.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 4.932028007507324,
|
|
"epoch": 1.7361524717093508,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004709094851760251,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.21585335433483124,
|
|
"num_tokens": 40755012.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 4.963821697235107,
|
|
"epoch": 1.7367480643240025,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004708885248174503,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.21497111469507219,
|
|
"num_tokens": 40768215.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 4.946560955047607,
|
|
"epoch": 1.737343656938654,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004708675574326724,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.21039287596940995,
|
|
"num_tokens": 40782939.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 4.9191817283630375,
|
|
"epoch": 1.7379392495533055,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004708465830224438,
|
|
"loss": 4.7781,
|
|
"mean_token_accuracy": 0.21796440482139587,
|
|
"num_tokens": 40797796.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 4.992841005325317,
|
|
"epoch": 1.7385348421679572,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047082560158751675,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.209404818713665,
|
|
"num_tokens": 40814349.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 4.98901333808899,
|
|
"epoch": 1.7391304347826086,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047080461312864363,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.20867680460214616,
|
|
"num_tokens": 40827820.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 4.963242292404175,
|
|
"epoch": 1.7397260273972601,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047078361764657745,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.2111409455537796,
|
|
"num_tokens": 40841801.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 4.940729141235352,
|
|
"epoch": 1.7403216200119118,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004707626151420713,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.21119434386491776,
|
|
"num_tokens": 40854095.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 4.94111590385437,
|
|
"epoch": 1.7409172126265635,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047074160561587835,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.21407258957624437,
|
|
"num_tokens": 40868449.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.007417869567871,
|
|
"epoch": 1.741512805241215,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004707205890687523,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.214486825466156,
|
|
"num_tokens": 40881408.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 4.97708911895752,
|
|
"epoch": 1.7421083978558665,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004706995655014469,
|
|
"loss": 4.8749,
|
|
"mean_token_accuracy": 0.19682459235191346,
|
|
"num_tokens": 40896474.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 4.882596063613891,
|
|
"epoch": 1.7427039904705182,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004706785349147163,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.2270573526620865,
|
|
"num_tokens": 40909141.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 4.940738773345947,
|
|
"epoch": 1.7432995830851699,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047065749730931485,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.2206147775053978,
|
|
"num_tokens": 40921928.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 4.9603018283844,
|
|
"epoch": 1.7438951756998213,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004706364526859971,
|
|
"loss": 4.7652,
|
|
"mean_token_accuracy": 0.20721684247255326,
|
|
"num_tokens": 40937385.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 4.988103580474854,
|
|
"epoch": 1.7444907683144728,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004706154010455178,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.21314988732337953,
|
|
"num_tokens": 40948726.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 4.947700166702271,
|
|
"epoch": 1.7450863609291245,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047059434238863206,
|
|
"loss": 4.6883,
|
|
"mean_token_accuracy": 0.2196518674492836,
|
|
"num_tokens": 40962200.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 4.928507089614868,
|
|
"epoch": 1.7456819535437762,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004705732767160954,
|
|
"loss": 4.6922,
|
|
"mean_token_accuracy": 0.22142314910888672,
|
|
"num_tokens": 40975176.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 4.956408929824829,
|
|
"epoch": 1.7462775461584277,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004705522040286632,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.21371060311794282,
|
|
"num_tokens": 40990193.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.017763280868531,
|
|
"epoch": 1.7468731387730791,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004705311243270915,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.20181089043617248,
|
|
"num_tokens": 41005433.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.043447351455688,
|
|
"epoch": 1.7474687313877308,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004705100376121362,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.2039751872420311,
|
|
"num_tokens": 41019122.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 4.951479053497314,
|
|
"epoch": 1.7480643240023823,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004704889438845537,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.21656654477119447,
|
|
"num_tokens": 41032791.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 4.967311239242553,
|
|
"epoch": 1.7486599166170338,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047046784314510074,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.20212714076042176,
|
|
"num_tokens": 41046145.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 4.930487728118896,
|
|
"epoch": 1.7492555092316855,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000470446735394534,
|
|
"loss": 4.6565,
|
|
"mean_token_accuracy": 0.21141578555107116,
|
|
"num_tokens": 41059597.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 4.925401735305786,
|
|
"epoch": 1.7498511018463372,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004704256206336106,
|
|
"loss": 4.7244,
|
|
"mean_token_accuracy": 0.21578361690044404,
|
|
"num_tokens": 41073990.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 4.963174676895141,
|
|
"epoch": 1.7504466944609887,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000470404498863088,
|
|
"loss": 4.7757,
|
|
"mean_token_accuracy": 0.20121525675058366,
|
|
"num_tokens": 41088509.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 4.841036748886109,
|
|
"epoch": 1.7510422870756401,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047038337008372365,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.21666089147329332,
|
|
"num_tokens": 41102307.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 4.972830152511596,
|
|
"epoch": 1.7516378796902918,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047036223429627557,
|
|
"loss": 4.7482,
|
|
"mean_token_accuracy": 0.21318026185035704,
|
|
"num_tokens": 41115540.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 4.911997842788696,
|
|
"epoch": 1.7522334723049435,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047034109150150184,
|
|
"loss": 4.6687,
|
|
"mean_token_accuracy": 0.2167411595582962,
|
|
"num_tokens": 41129271.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 4.888418054580688,
|
|
"epoch": 1.752829064919595,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004703199417001607,
|
|
"loss": 4.6915,
|
|
"mean_token_accuracy": 0.20756812542676925,
|
|
"num_tokens": 41144671.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 4.960987710952759,
|
|
"epoch": 1.7534246575342465,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047029878489301074,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.2057378038764,
|
|
"num_tokens": 41157825.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 4.9609636783599855,
|
|
"epoch": 1.7540202501488982,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004702776210808109,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.21399376094341277,
|
|
"num_tokens": 41171645.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.019249439239502,
|
|
"epoch": 1.7546158427635499,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004702564502643204,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.2137800246477127,
|
|
"num_tokens": 41185996.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 4.961927604675293,
|
|
"epoch": 1.7552114353782013,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047023527244429846,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.20714582800865172,
|
|
"num_tokens": 41199044.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 4.98872127532959,
|
|
"epoch": 1.7558070279928528,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004702140876215047,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.21025576144456865,
|
|
"num_tokens": 41213215.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 4.961813020706177,
|
|
"epoch": 1.7564026206075045,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004701928957966991,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.21135599315166473,
|
|
"num_tokens": 41227067.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 4.96177077293396,
|
|
"epoch": 1.756998213222156,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004701716969706416,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.2195218876004219,
|
|
"num_tokens": 41239272.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 4.905254936218261,
|
|
"epoch": 1.7575938058368075,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004701504911440927,
|
|
"loss": 4.7009,
|
|
"mean_token_accuracy": 0.21381148248910903,
|
|
"num_tokens": 41253230.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 4.954729604721069,
|
|
"epoch": 1.7581893984514592,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004701292783178129,
|
|
"loss": 4.8174,
|
|
"mean_token_accuracy": 0.2007545441389084,
|
|
"num_tokens": 41266349.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.052498245239258,
|
|
"epoch": 1.7587849910661109,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004701080584925633,
|
|
"loss": 4.7346,
|
|
"mean_token_accuracy": 0.21374078691005707,
|
|
"num_tokens": 41280301.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 4.92034683227539,
|
|
"epoch": 1.7593805836807623,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047008683166910477,
|
|
"loss": 4.696,
|
|
"mean_token_accuracy": 0.21415828317403793,
|
|
"num_tokens": 41294813.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 4.825264167785645,
|
|
"epoch": 1.7599761762954138,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004700655978481988,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.21714553982019424,
|
|
"num_tokens": 41310493.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 4.917851305007934,
|
|
"epoch": 1.7605717689100655,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000470044357030607,
|
|
"loss": 4.6302,
|
|
"mean_token_accuracy": 0.21652335822582244,
|
|
"num_tokens": 41324597.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 4.894087600708008,
|
|
"epoch": 1.7611673615247172,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047002310921709123,
|
|
"loss": 4.7434,
|
|
"mean_token_accuracy": 0.2166119173169136,
|
|
"num_tokens": 41338019.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 4.9444256782531735,
|
|
"epoch": 1.7617629541393687,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004700018544084136,
|
|
"loss": 4.6947,
|
|
"mean_token_accuracy": 0.2094060868024826,
|
|
"num_tokens": 41353199.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 4.9791065692901615,
|
|
"epoch": 1.7623585467540201,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004699805926053365,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.21140168011188507,
|
|
"num_tokens": 41367783.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 4.940293598175049,
|
|
"epoch": 1.7629541393686718,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046995932380862254,
|
|
"loss": 4.7081,
|
|
"mean_token_accuracy": 0.214135280251503,
|
|
"num_tokens": 41382371.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 4.9228979587554935,
|
|
"epoch": 1.7635497319833235,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046993804801903475,
|
|
"loss": 4.7376,
|
|
"mean_token_accuracy": 0.21204346865415574,
|
|
"num_tokens": 41394965.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 4.964366865158081,
|
|
"epoch": 1.764145324597975,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046991676523733603,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.20687600523233413,
|
|
"num_tokens": 41408158.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 4.965651988983154,
|
|
"epoch": 1.7647409172126265,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046989547546428986,
|
|
"loss": 4.7519,
|
|
"mean_token_accuracy": 0.2143443465232849,
|
|
"num_tokens": 41421672.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 4.878871631622315,
|
|
"epoch": 1.7653365098272782,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046987417870065985,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.209518364071846,
|
|
"num_tokens": 41435225.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 4.967955684661865,
|
|
"epoch": 1.7659321024419299,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004698528749472099,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.2003282740712166,
|
|
"num_tokens": 41449360.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.036211633682251,
|
|
"epoch": 1.7665276950565811,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004698315642047042,
|
|
"loss": 4.8052,
|
|
"mean_token_accuracy": 0.2011848658323288,
|
|
"num_tokens": 41462895.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 4.879158306121826,
|
|
"epoch": 1.7671232876712328,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000469810246473907,
|
|
"loss": 4.6534,
|
|
"mean_token_accuracy": 0.2181249275803566,
|
|
"num_tokens": 41477069.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 4.934395599365234,
|
|
"epoch": 1.7677188802858845,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046978892175558295,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.21154409646987915,
|
|
"num_tokens": 41491097.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.014869022369385,
|
|
"epoch": 1.768314472900536,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004697675900504971,
|
|
"loss": 4.8269,
|
|
"mean_token_accuracy": 0.20533665418624877,
|
|
"num_tokens": 41504570.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 4.990710926055908,
|
|
"epoch": 1.7689100655151875,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046974625135941445,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.20968741029500962,
|
|
"num_tokens": 41518618.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 4.99499020576477,
|
|
"epoch": 1.7695056581298392,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046972490568310043,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.21039841026067735,
|
|
"num_tokens": 41535802.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.018189430236816,
|
|
"epoch": 1.7701012507444909,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046970355302232056,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.21341346353292465,
|
|
"num_tokens": 41548588.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 4.884684467315674,
|
|
"epoch": 1.7706968433591423,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046968219337784083,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.21753836870193483,
|
|
"num_tokens": 41560934.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 4.851402044296265,
|
|
"epoch": 1.7712924359737938,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046966082675042745,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.21979269236326218,
|
|
"num_tokens": 41574066.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 4.974154853820801,
|
|
"epoch": 1.7718880285884455,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004696394531408466,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.2184661492705345,
|
|
"num_tokens": 41586586.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 4.945642375946045,
|
|
"epoch": 1.7724836212030972,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046961807254986503,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.21926094889640807,
|
|
"num_tokens": 41598945.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 4.924982070922852,
|
|
"epoch": 1.7730792138177487,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004695966849782497,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.2058517590165138,
|
|
"num_tokens": 41614034.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 4.845977020263672,
|
|
"epoch": 1.7736748064324002,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004695752904267676,
|
|
"loss": 4.637,
|
|
"mean_token_accuracy": 0.22569534182548523,
|
|
"num_tokens": 41627626.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 4.9368995189666744,
|
|
"epoch": 1.7742703990470519,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004695538888961862,
|
|
"loss": 4.7395,
|
|
"mean_token_accuracy": 0.20583613514900206,
|
|
"num_tokens": 41640060.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 4.917208671569824,
|
|
"epoch": 1.7748659916617036,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004695324803872732,
|
|
"loss": 4.7098,
|
|
"mean_token_accuracy": 0.21619091629981996,
|
|
"num_tokens": 41653689.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 4.989242744445801,
|
|
"epoch": 1.7754615842763548,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046951106490079636,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.20271608382463455,
|
|
"num_tokens": 41666873.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 4.868319416046143,
|
|
"epoch": 1.7760571768910065,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046948964243752393,
|
|
"loss": 4.5959,
|
|
"mean_token_accuracy": 0.2176255315542221,
|
|
"num_tokens": 41681418.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 4.873681545257568,
|
|
"epoch": 1.7766527695056582,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046946821299822416,
|
|
"loss": 4.7669,
|
|
"mean_token_accuracy": 0.21136853396892546,
|
|
"num_tokens": 41694728.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.021020412445068,
|
|
"epoch": 1.7772483621203097,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004694467765836659,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.21451413482427598,
|
|
"num_tokens": 41707361.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 4.997995328903198,
|
|
"epoch": 1.7778439547349612,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004694253331946178,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.2080879658460617,
|
|
"num_tokens": 41721746.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 4.941072177886963,
|
|
"epoch": 1.7784395473496128,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004694038828318492,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.20490549355745316,
|
|
"num_tokens": 41739296.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.007630395889282,
|
|
"epoch": 1.7790351399642645,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004693824254961294,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.1996065765619278,
|
|
"num_tokens": 41753416.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 4.864287424087524,
|
|
"epoch": 1.779630732578916,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046936096118822796,
|
|
"loss": 4.6716,
|
|
"mean_token_accuracy": 0.2211449086666107,
|
|
"num_tokens": 41764978.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 4.904167985916137,
|
|
"epoch": 1.7802263251935675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004693394899089149,
|
|
"loss": 4.6861,
|
|
"mean_token_accuracy": 0.21171445101499559,
|
|
"num_tokens": 41779467.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 4.979528617858887,
|
|
"epoch": 1.7808219178082192,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046931801165896035,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.21198361217975617,
|
|
"num_tokens": 41792541.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.00822343826294,
|
|
"epoch": 1.7814175104228709,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004692965264391346,
|
|
"loss": 4.8533,
|
|
"mean_token_accuracy": 0.20795208662748338,
|
|
"num_tokens": 41806127.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 4.931195783615112,
|
|
"epoch": 1.7820131030375224,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046927503425020847,
|
|
"loss": 4.7143,
|
|
"mean_token_accuracy": 0.2223634511232376,
|
|
"num_tokens": 41819632.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 4.952184104919434,
|
|
"epoch": 1.7826086956521738,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004692535350929525,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.21991646736860276,
|
|
"num_tokens": 41833144.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.010642194747925,
|
|
"epoch": 1.7832042882668255,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046923202896813825,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.21279854327440262,
|
|
"num_tokens": 41847994.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.005987024307251,
|
|
"epoch": 1.7837998808814772,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004692105158765369,
|
|
"loss": 4.8158,
|
|
"mean_token_accuracy": 0.20548930615186692,
|
|
"num_tokens": 41861708.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 4.864488315582276,
|
|
"epoch": 1.7843954734961287,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004691889958189201,
|
|
"loss": 4.6247,
|
|
"mean_token_accuracy": 0.22065138816833496,
|
|
"num_tokens": 41874609.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 4.957807970046997,
|
|
"epoch": 1.7849910661107802,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046916746879605974,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.20684752464294434,
|
|
"num_tokens": 41887105.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 4.939602518081665,
|
|
"epoch": 1.7855866587254319,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000469145934808728,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.2139011338353157,
|
|
"num_tokens": 41903298.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 4.997870302200317,
|
|
"epoch": 1.7861822513400833,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046912439385769723,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.2102961167693138,
|
|
"num_tokens": 41918173.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 4.932888698577881,
|
|
"epoch": 1.7867778439547348,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004691028459437401,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.2135471984744072,
|
|
"num_tokens": 41932050.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.7867778439547348,
|
|
"eval_entropy": 4.76950447992845,
|
|
"eval_loss": 4.7664875984191895,
|
|
"eval_mean_token_accuracy": 0.2199648528356911,
|
|
"eval_num_tokens": 41932050.0,
|
|
"eval_runtime": 24.0609,
|
|
"eval_samples_per_second": 1060.351,
|
|
"eval_steps_per_second": 132.58,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 4.930256462097168,
|
|
"epoch": 1.7873734365693865,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004690812910676294,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.21928282976150512,
|
|
"num_tokens": 41945874.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 4.930176067352295,
|
|
"epoch": 1.7879690291840382,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004690597292301384,
|
|
"loss": 4.7032,
|
|
"mean_token_accuracy": 0.22077237367630004,
|
|
"num_tokens": 41959084.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 4.933148574829102,
|
|
"epoch": 1.7885646217986897,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046903816043204045,
|
|
"loss": 4.7238,
|
|
"mean_token_accuracy": 0.21723862439393998,
|
|
"num_tokens": 41972872.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 4.891049337387085,
|
|
"epoch": 1.7891602144133412,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004690165846741092,
|
|
"loss": 4.6864,
|
|
"mean_token_accuracy": 0.21885701417922973,
|
|
"num_tokens": 41985045.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 4.96382966041565,
|
|
"epoch": 1.7897558070279929,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046899500195711843,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.21647416353225707,
|
|
"num_tokens": 41999760.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 4.954783010482788,
|
|
"epoch": 1.7903513996426446,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046897341228184237,
|
|
"loss": 4.67,
|
|
"mean_token_accuracy": 0.21012029200792312,
|
|
"num_tokens": 42013871.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 4.936635684967041,
|
|
"epoch": 1.790946992257296,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004689518156490554,
|
|
"loss": 4.7828,
|
|
"mean_token_accuracy": 0.21260943859815598,
|
|
"num_tokens": 42028701.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 4.989226388931274,
|
|
"epoch": 1.7915425848719475,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004689302120595322,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.20810211598873138,
|
|
"num_tokens": 42042455.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 4.946051502227784,
|
|
"epoch": 1.7921381774865992,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046890860151404753,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.20732981562614441,
|
|
"num_tokens": 42055813.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 4.989173221588135,
|
|
"epoch": 1.792733770101251,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046888698401337665,
|
|
"loss": 4.7336,
|
|
"mean_token_accuracy": 0.20545820891857147,
|
|
"num_tokens": 42070545.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 4.967262268066406,
|
|
"epoch": 1.7933293627159024,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046886535955829487,
|
|
"loss": 4.7127,
|
|
"mean_token_accuracy": 0.21212682276964187,
|
|
"num_tokens": 42086021.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 4.942718935012818,
|
|
"epoch": 1.7939249553305538,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004688437281495779,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.21211162060499192,
|
|
"num_tokens": 42097775.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 4.89931468963623,
|
|
"epoch": 1.7945205479452055,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004688220897880015,
|
|
"loss": 4.7447,
|
|
"mean_token_accuracy": 0.2046126440167427,
|
|
"num_tokens": 42112126.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.010500144958496,
|
|
"epoch": 1.795116140559857,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004688004444743419,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.20361392498016356,
|
|
"num_tokens": 42125694.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 4.948848009109497,
|
|
"epoch": 1.7957117331745085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046877879220937546,
|
|
"loss": 4.71,
|
|
"mean_token_accuracy": 0.20977079421281813,
|
|
"num_tokens": 42138996.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 4.9090354442596436,
|
|
"epoch": 1.7963073257891602,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004687571329938788,
|
|
"loss": 4.6211,
|
|
"mean_token_accuracy": 0.221540267765522,
|
|
"num_tokens": 42150896.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 4.917004346847534,
|
|
"epoch": 1.7969029184038119,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046873546682862883,
|
|
"loss": 4.6847,
|
|
"mean_token_accuracy": 0.222554612159729,
|
|
"num_tokens": 42163529.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 4.944142580032349,
|
|
"epoch": 1.7974985110184634,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046871379371440263,
|
|
"loss": 4.6822,
|
|
"mean_token_accuracy": 0.21166396737098694,
|
|
"num_tokens": 42177221.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 4.937584304809571,
|
|
"epoch": 1.7980941036331148,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004686921136519777,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.22103262990713118,
|
|
"num_tokens": 42190632.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 4.928494262695312,
|
|
"epoch": 1.7986896962477665,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004686704266421314,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.21505870521068574,
|
|
"num_tokens": 42204466.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 4.963140535354614,
|
|
"epoch": 1.7992852888624182,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004686487326856419,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.20363688915967942,
|
|
"num_tokens": 42219992.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 4.920693111419678,
|
|
"epoch": 1.7998808814770697,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004686270317832872,
|
|
"loss": 4.6828,
|
|
"mean_token_accuracy": 0.21692857444286345,
|
|
"num_tokens": 42233966.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 4.939632606506348,
|
|
"epoch": 1.8004764740917212,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004686053239358457,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.20598779022693633,
|
|
"num_tokens": 42246689.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.035974168777466,
|
|
"epoch": 1.8010720667063729,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046858360914409596,
|
|
"loss": 4.78,
|
|
"mean_token_accuracy": 0.20689933896064758,
|
|
"num_tokens": 42260145.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.025493907928467,
|
|
"epoch": 1.8016676593210246,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000468561887408817,
|
|
"loss": 4.8498,
|
|
"mean_token_accuracy": 0.20430277585983275,
|
|
"num_tokens": 42272851.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 4.950228881835938,
|
|
"epoch": 1.802263251935676,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004685401587307879,
|
|
"loss": 4.7027,
|
|
"mean_token_accuracy": 0.2126436024904251,
|
|
"num_tokens": 42286233.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 4.942458868026733,
|
|
"epoch": 1.8028588445503275,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004685184231107878,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.2126426577568054,
|
|
"num_tokens": 42301649.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 4.88987979888916,
|
|
"epoch": 1.8034544371649792,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004684966805495966,
|
|
"loss": 4.754,
|
|
"mean_token_accuracy": 0.21640886962413788,
|
|
"num_tokens": 42315115.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 4.886041355133057,
|
|
"epoch": 1.8040500297796307,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000468474931047994,
|
|
"loss": 4.6233,
|
|
"mean_token_accuracy": 0.21658001840114594,
|
|
"num_tokens": 42328838.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.034859752655029,
|
|
"epoch": 1.8046456223942822,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046845317460676033,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.21317932158708572,
|
|
"num_tokens": 42343918.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 4.8768250942230225,
|
|
"epoch": 1.8052412150089339,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046843141122667576,
|
|
"loss": 4.6315,
|
|
"mean_token_accuracy": 0.22377840280532837,
|
|
"num_tokens": 42356979.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 4.830185747146606,
|
|
"epoch": 1.8058368076235856,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046840964090852095,
|
|
"loss": 4.6352,
|
|
"mean_token_accuracy": 0.21743462830781937,
|
|
"num_tokens": 42370740.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 4.90168309211731,
|
|
"epoch": 1.806432400238237,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004683878636530768,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.21631396263837815,
|
|
"num_tokens": 42386232.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 4.949375343322754,
|
|
"epoch": 1.8070279928528885,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004683660794611244,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.2198723718523979,
|
|
"num_tokens": 42399234.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 4.909501791000366,
|
|
"epoch": 1.8076235854675402,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004683442883334451,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.21135881692171096,
|
|
"num_tokens": 42412753.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 4.994759273529053,
|
|
"epoch": 1.808219178082192,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004683224902708206,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.21263788193464278,
|
|
"num_tokens": 42427150.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 4.9975275039672855,
|
|
"epoch": 1.8088147706968434,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004683006852740326,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.2109058156609535,
|
|
"num_tokens": 42442245.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.0038230419158936,
|
|
"epoch": 1.8094103633114949,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004682788733438634,
|
|
"loss": 4.7618,
|
|
"mean_token_accuracy": 0.21573713570833206,
|
|
"num_tokens": 42456031.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 4.968279790878296,
|
|
"epoch": 1.8100059559261465,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004682570544810952,
|
|
"loss": 4.7837,
|
|
"mean_token_accuracy": 0.21487538814544677,
|
|
"num_tokens": 42470015.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 4.962930393218994,
|
|
"epoch": 1.8106015485407982,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046823522868651076,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.2097053736448288,
|
|
"num_tokens": 42482956.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 4.937529897689819,
|
|
"epoch": 1.8111971411554497,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004682133959608928,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.21136209666728972,
|
|
"num_tokens": 42495226.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 4.975719738006592,
|
|
"epoch": 1.8117927337701012,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004681915563050245,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.21018550395965577,
|
|
"num_tokens": 42509371.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 4.978839874267578,
|
|
"epoch": 1.812388326384753,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046816970971968916,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.21139013767242432,
|
|
"num_tokens": 42523360.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.074817705154419,
|
|
"epoch": 1.8129839189994044,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046814785620567036,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.2020023673772812,
|
|
"num_tokens": 42535661.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 4.972344207763672,
|
|
"epoch": 1.8135795116140558,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046812599576375206,
|
|
"loss": 4.7464,
|
|
"mean_token_accuracy": 0.21006715148687363,
|
|
"num_tokens": 42549342.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 4.939127349853516,
|
|
"epoch": 1.8141751042287075,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004681041283947182,
|
|
"loss": 4.6945,
|
|
"mean_token_accuracy": 0.2162005588412285,
|
|
"num_tokens": 42564904.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 4.937268352508545,
|
|
"epoch": 1.8147706968433592,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004680822540993534,
|
|
"loss": 4.6786,
|
|
"mean_token_accuracy": 0.2191829189658165,
|
|
"num_tokens": 42578877.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 4.918440961837769,
|
|
"epoch": 1.8153662894580107,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046806037287844195,
|
|
"loss": 4.681,
|
|
"mean_token_accuracy": 0.2192366227507591,
|
|
"num_tokens": 42592704.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.019015550613403,
|
|
"epoch": 1.8159618820726622,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004680384847327689,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.20976767390966417,
|
|
"num_tokens": 42606414.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 4.982526063919067,
|
|
"epoch": 1.8165574746873139,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046801658966311914,
|
|
"loss": 4.7626,
|
|
"mean_token_accuracy": 0.21257394105195998,
|
|
"num_tokens": 42620047.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.008677339553833,
|
|
"epoch": 1.8171530673019656,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046799468767027826,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.21384796798229216,
|
|
"num_tokens": 42634701.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 4.936839580535889,
|
|
"epoch": 1.817748659916617,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046797277875503164,
|
|
"loss": 4.7501,
|
|
"mean_token_accuracy": 0.20875152051448823,
|
|
"num_tokens": 42649619.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 4.934544849395752,
|
|
"epoch": 1.8183442525312685,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046795086291816516,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.20925240814685822,
|
|
"num_tokens": 42663753.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 4.974159145355225,
|
|
"epoch": 1.8189398451459202,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004679289401604651,
|
|
"loss": 4.726,
|
|
"mean_token_accuracy": 0.21365445405244826,
|
|
"num_tokens": 42678584.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 4.933241701126098,
|
|
"epoch": 1.819535437760572,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004679070104827176,
|
|
"loss": 4.7405,
|
|
"mean_token_accuracy": 0.2139880672097206,
|
|
"num_tokens": 42693125.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 4.90031590461731,
|
|
"epoch": 1.8201310303752234,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004678850738857092,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.21996762603521347,
|
|
"num_tokens": 42708218.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 4.962149047851563,
|
|
"epoch": 1.8207266229898749,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004678631303702268,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.21211342066526412,
|
|
"num_tokens": 42722137.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.052307844161987,
|
|
"epoch": 1.8213222156045266,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046784117993705753,
|
|
"loss": 4.7937,
|
|
"mean_token_accuracy": 0.20691823065280915,
|
|
"num_tokens": 42737105.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 4.924236059188843,
|
|
"epoch": 1.821917808219178,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004678192225869888,
|
|
"loss": 4.627,
|
|
"mean_token_accuracy": 0.22087445259094238,
|
|
"num_tokens": 42750912.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 4.901295137405396,
|
|
"epoch": 1.8225134008338295,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046779725832080793,
|
|
"loss": 4.7557,
|
|
"mean_token_accuracy": 0.21721333563327788,
|
|
"num_tokens": 42762022.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 4.930124807357788,
|
|
"epoch": 1.8231089934484812,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046777528713930287,
|
|
"loss": 4.7103,
|
|
"mean_token_accuracy": 0.21471501737833024,
|
|
"num_tokens": 42776195.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 4.997695636749268,
|
|
"epoch": 1.823704586063133,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004677533090432617,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.20551416277885437,
|
|
"num_tokens": 42792938.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.001307439804077,
|
|
"epoch": 1.8243001786777844,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004677313240334727,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.2060326263308525,
|
|
"num_tokens": 42806088.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.010191822052002,
|
|
"epoch": 1.8248957712924359,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004677093321107245,
|
|
"loss": 4.7291,
|
|
"mean_token_accuracy": 0.21228084564208985,
|
|
"num_tokens": 42818870.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.076185274124145,
|
|
"epoch": 1.8254913639070875,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046768733327580593,
|
|
"loss": 4.7978,
|
|
"mean_token_accuracy": 0.20542855709791183,
|
|
"num_tokens": 42833144.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 4.900299739837647,
|
|
"epoch": 1.8260869565217392,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046766532752950604,
|
|
"loss": 4.7193,
|
|
"mean_token_accuracy": 0.2173850268125534,
|
|
"num_tokens": 42847318.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 4.848849725723267,
|
|
"epoch": 1.8266825491363907,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000467643314872614,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.2142763614654541,
|
|
"num_tokens": 42862312.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.00791015625,
|
|
"epoch": 1.8272781417510422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004676212953059195,
|
|
"loss": 4.7082,
|
|
"mean_token_accuracy": 0.21098915934562684,
|
|
"num_tokens": 42876775.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 4.893521070480347,
|
|
"epoch": 1.827873734365694,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046759926883021234,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.2150734156370163,
|
|
"num_tokens": 42889864.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 4.940601253509522,
|
|
"epoch": 1.8284693269803456,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046757723544628253,
|
|
"loss": 4.6492,
|
|
"mean_token_accuracy": 0.218246953189373,
|
|
"num_tokens": 42902319.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 4.945732879638672,
|
|
"epoch": 1.829064919594997,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004675551951549204,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.21202046424150467,
|
|
"num_tokens": 42915864.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 4.933176803588867,
|
|
"epoch": 1.8296605122096485,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046753314795691653,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.21002239733934402,
|
|
"num_tokens": 42931724.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 4.9380487442016605,
|
|
"epoch": 1.8302561048243002,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004675110938530617,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.21264664679765702,
|
|
"num_tokens": 42945848.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 4.9425718784332275,
|
|
"epoch": 1.8308516974389517,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004674890328441469,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.20713284015655517,
|
|
"num_tokens": 42958443.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 4.975921535491944,
|
|
"epoch": 1.8314472900536032,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004674669649309634,
|
|
"loss": 4.7094,
|
|
"mean_token_accuracy": 0.2115694046020508,
|
|
"num_tokens": 42972286.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.028268098831177,
|
|
"epoch": 1.8320428826682549,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004674448901143029,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.20336896926164627,
|
|
"num_tokens": 42987029.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 4.975715494155883,
|
|
"epoch": 1.8326384752829066,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004674228083949571,
|
|
"loss": 4.6978,
|
|
"mean_token_accuracy": 0.21448006480932236,
|
|
"num_tokens": 43000039.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 4.969759464263916,
|
|
"epoch": 1.833234067897558,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004674007197737179,
|
|
"loss": 4.7383,
|
|
"mean_token_accuracy": 0.21332642883062364,
|
|
"num_tokens": 43012942.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 4.899760389328003,
|
|
"epoch": 1.8338296605122095,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004673786242513778,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.21302721947431563,
|
|
"num_tokens": 43027523.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 4.978391408920288,
|
|
"epoch": 1.8344252531268612,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046735652182872925,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.20996203720569612,
|
|
"num_tokens": 43044438.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 4.960096120834351,
|
|
"epoch": 1.835020845741513,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046733441250656495,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.20691315233707427,
|
|
"num_tokens": 43058458.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 4.962850093841553,
|
|
"epoch": 1.8356164383561644,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000467312296285678,
|
|
"loss": 4.7543,
|
|
"mean_token_accuracy": 0.21111691892147064,
|
|
"num_tokens": 43071269.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 4.948610496520996,
|
|
"epoch": 1.8362120309708159,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004672901731668617,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.21093682199716568,
|
|
"num_tokens": 43084024.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.032038784027099,
|
|
"epoch": 1.8368076235854676,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046726804315090956,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.21022139638662338,
|
|
"num_tokens": 43097857.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 4.991842555999756,
|
|
"epoch": 1.8374032162001193,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004672459062386152,
|
|
"loss": 4.7187,
|
|
"mean_token_accuracy": 0.21785185486078262,
|
|
"num_tokens": 43111481.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 4.90796537399292,
|
|
"epoch": 1.8379988088147707,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004672237624307729,
|
|
"loss": 4.6548,
|
|
"mean_token_accuracy": 0.21672140657901764,
|
|
"num_tokens": 43123926.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 4.988813829421997,
|
|
"epoch": 1.8385944014294222,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004672016117281767,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.20329382121562958,
|
|
"num_tokens": 43136005.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 4.882112741470337,
|
|
"epoch": 1.839189994044074,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004671794541316212,
|
|
"loss": 4.628,
|
|
"mean_token_accuracy": 0.21929675936698914,
|
|
"num_tokens": 43150641.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 4.925801420211792,
|
|
"epoch": 1.8397855866587254,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004671572896419011,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.20946784019470216,
|
|
"num_tokens": 43164077.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 4.959580802917481,
|
|
"epoch": 1.8403811792733769,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004671351182598116,
|
|
"loss": 4.7218,
|
|
"mean_token_accuracy": 0.21314697563648224,
|
|
"num_tokens": 43176694.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 4.957739448547363,
|
|
"epoch": 1.8409767718880286,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004671129399861476,
|
|
"loss": 4.695,
|
|
"mean_token_accuracy": 0.21123683005571364,
|
|
"num_tokens": 43190310.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 4.88712477684021,
|
|
"epoch": 1.8415723645026802,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046709075482170495,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.217373850941658,
|
|
"num_tokens": 43203642.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.016681289672851,
|
|
"epoch": 1.8421679571173317,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004670685627672792,
|
|
"loss": 4.8196,
|
|
"mean_token_accuracy": 0.21034473478794097,
|
|
"num_tokens": 43216512.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 4.908697175979614,
|
|
"epoch": 1.8427635497319832,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046704636382366633,
|
|
"loss": 4.6678,
|
|
"mean_token_accuracy": 0.20652736276388167,
|
|
"num_tokens": 43229713.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 4.917172241210937,
|
|
"epoch": 1.843359142346635,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004670241579916627,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.21830987483263015,
|
|
"num_tokens": 43242968.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 4.928996181488037,
|
|
"epoch": 1.8439547349612866,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046700194527206476,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.21474383920431137,
|
|
"num_tokens": 43256403.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 4.978890466690063,
|
|
"epoch": 1.844550327575938,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046697972566566917,
|
|
"loss": 4.7399,
|
|
"mean_token_accuracy": 0.2123802125453949,
|
|
"num_tokens": 43270004.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.015359878540039,
|
|
"epoch": 1.8451459201905895,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046695749917327297,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.20019313395023347,
|
|
"num_tokens": 43282934.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 4.971472311019897,
|
|
"epoch": 1.8457415128052412,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046693526579567337,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.2074686273932457,
|
|
"num_tokens": 43296378.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.012940216064453,
|
|
"epoch": 1.846337105419893,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046691302553366785,
|
|
"loss": 4.706,
|
|
"mean_token_accuracy": 0.21532754600048065,
|
|
"num_tokens": 43309832.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 4.944285440444946,
|
|
"epoch": 1.8469326980345444,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004668907783880542,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.21737894117832185,
|
|
"num_tokens": 43324222.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 4.985659837722778,
|
|
"epoch": 1.8475282906491959,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046686852435963016,
|
|
"loss": 4.74,
|
|
"mean_token_accuracy": 0.20863271206617356,
|
|
"num_tokens": 43339674.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 4.906384372711182,
|
|
"epoch": 1.8481238832638476,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004668462634491943,
|
|
"loss": 4.6883,
|
|
"mean_token_accuracy": 0.2219958245754242,
|
|
"num_tokens": 43352265.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 4.9714601039886475,
|
|
"epoch": 1.848719475878499,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004668239956575448,
|
|
"loss": 4.6989,
|
|
"mean_token_accuracy": 0.21935538351535797,
|
|
"num_tokens": 43365428.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 4.89877495765686,
|
|
"epoch": 1.8493150684931505,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046680172098548044,
|
|
"loss": 4.7037,
|
|
"mean_token_accuracy": 0.2105772912502289,
|
|
"num_tokens": 43379099.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 4.864028453826904,
|
|
"epoch": 1.8499106611078022,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046677943943380023,
|
|
"loss": 4.6294,
|
|
"mean_token_accuracy": 0.2192344218492508,
|
|
"num_tokens": 43393127.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 4.954372310638428,
|
|
"epoch": 1.850506253722454,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004667571510033034,
|
|
"loss": 4.7837,
|
|
"mean_token_accuracy": 0.21283565908670427,
|
|
"num_tokens": 43409560.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 4.99108657836914,
|
|
"epoch": 1.8511018463371054,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004667348556947893,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.21182413548231124,
|
|
"num_tokens": 43422986.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 4.985896110534668,
|
|
"epoch": 1.8516974389517569,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004667125535090577,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.21622608602046967,
|
|
"num_tokens": 43437176.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.084640884399414,
|
|
"epoch": 1.8522930315664086,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004666902444469084,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.205988410115242,
|
|
"num_tokens": 43449917.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 4.912136125564575,
|
|
"epoch": 1.8528886241810603,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004666679285091418,
|
|
"loss": 4.6691,
|
|
"mean_token_accuracy": 0.21467595994472505,
|
|
"num_tokens": 43462940.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 4.962233686447144,
|
|
"epoch": 1.8534842167957117,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046664560569655825,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.21152482479810714,
|
|
"num_tokens": 43477008.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 4.920981311798096,
|
|
"epoch": 1.8540798094103632,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004666232760099583,
|
|
"loss": 4.7372,
|
|
"mean_token_accuracy": 0.21834688782691955,
|
|
"num_tokens": 43492094.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 4.944347667694092,
|
|
"epoch": 1.854675402025015,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046660093945014307,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.21727163195610047,
|
|
"num_tokens": 43505256.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 4.881833219528199,
|
|
"epoch": 1.8552709946396666,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046657859601791367,
|
|
"loss": 4.6808,
|
|
"mean_token_accuracy": 0.21796075850725175,
|
|
"num_tokens": 43518056.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 4.926846504211426,
|
|
"epoch": 1.855866587254318,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004665562457140715,
|
|
"loss": 4.6831,
|
|
"mean_token_accuracy": 0.2150219425559044,
|
|
"num_tokens": 43531809.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 4.895972156524659,
|
|
"epoch": 1.8564621798689696,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004665338885394183,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.2160967469215393,
|
|
"num_tokens": 43545272.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 4.942248201370239,
|
|
"epoch": 1.8570577724836212,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004665115244947559,
|
|
"loss": 4.7011,
|
|
"mean_token_accuracy": 0.21263537555933,
|
|
"num_tokens": 43559981.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 4.95798397064209,
|
|
"epoch": 1.857653365098273,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004664891535808865,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.21274527609348298,
|
|
"num_tokens": 43574025.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 4.880942726135254,
|
|
"epoch": 1.8582489577129242,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046646677579861254,
|
|
"loss": 4.6675,
|
|
"mean_token_accuracy": 0.21206953823566438,
|
|
"num_tokens": 43586896.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 4.924657869338989,
|
|
"epoch": 1.858844550327576,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004664443911487366,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.21437233686447144,
|
|
"num_tokens": 43599289.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 4.94911789894104,
|
|
"epoch": 1.8594401429422276,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046642199963206155,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.20828302204608917,
|
|
"num_tokens": 43614172.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 4.931605386734009,
|
|
"epoch": 1.860035735556879,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046639960124939076,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.21247618794441223,
|
|
"num_tokens": 43626653.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 4.896553182601929,
|
|
"epoch": 1.8606313281715305,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046637719600152737,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.21992283761501313,
|
|
"num_tokens": 43641128.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.014578485488892,
|
|
"epoch": 1.8612269207861822,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004663547838892751,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.2032456561923027,
|
|
"num_tokens": 43656315.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 4.947763061523437,
|
|
"epoch": 1.861822513400834,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004663323649134379,
|
|
"loss": 4.7014,
|
|
"mean_token_accuracy": 0.2150794729590416,
|
|
"num_tokens": 43669451.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 4.891162872314453,
|
|
"epoch": 1.8624181060154854,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004663099390748199,
|
|
"loss": 4.7706,
|
|
"mean_token_accuracy": 0.21095479875802994,
|
|
"num_tokens": 43683282.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 4.941687726974488,
|
|
"epoch": 1.8630136986301369,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046628750637422534,
|
|
"loss": 4.7436,
|
|
"mean_token_accuracy": 0.20923854261636735,
|
|
"num_tokens": 43697369.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 4.93519229888916,
|
|
"epoch": 1.8636092912447886,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000466265066812459,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.21558488309383392,
|
|
"num_tokens": 43711270.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.020141458511352,
|
|
"epoch": 1.8642048838594403,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046624262039032566,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.20612771660089493,
|
|
"num_tokens": 43725029.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 4.996259641647339,
|
|
"epoch": 1.8648004764740918,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046622016710863053,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.21060218811035156,
|
|
"num_tokens": 43737953.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 4.928950071334839,
|
|
"epoch": 1.8653960690887432,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004661977069681789,
|
|
"loss": 4.7217,
|
|
"mean_token_accuracy": 0.21253954619169235,
|
|
"num_tokens": 43754006.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 4.980943965911865,
|
|
"epoch": 1.865991661703395,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004661752399697763,
|
|
"loss": 4.7666,
|
|
"mean_token_accuracy": 0.21214493364095688,
|
|
"num_tokens": 43767655.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 4.949898719787598,
|
|
"epoch": 1.8665872543180466,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046615276611422876,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.21090679615736008,
|
|
"num_tokens": 43780974.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 4.8753955364227295,
|
|
"epoch": 1.8671828469326979,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046613028540234226,
|
|
"loss": 4.6926,
|
|
"mean_token_accuracy": 0.21363013088703156,
|
|
"num_tokens": 43794479.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 4.951124620437622,
|
|
"epoch": 1.8677784395473496,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004661077978349232,
|
|
"loss": 4.6888,
|
|
"mean_token_accuracy": 0.21396940499544143,
|
|
"num_tokens": 43810184.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.034284591674805,
|
|
"epoch": 1.8683740321620013,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004660853034127781,
|
|
"loss": 4.7726,
|
|
"mean_token_accuracy": 0.20737743526697158,
|
|
"num_tokens": 43824436.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 4.830185890197754,
|
|
"epoch": 1.8689696247766527,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004660628021367139,
|
|
"loss": 4.6126,
|
|
"mean_token_accuracy": 0.21813203990459443,
|
|
"num_tokens": 43839095.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 4.947592306137085,
|
|
"epoch": 1.8695652173913042,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004660402940075377,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.21640446782112122,
|
|
"num_tokens": 43851850.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.008051919937134,
|
|
"epoch": 1.870160810005956,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004660177790260567,
|
|
"loss": 4.8714,
|
|
"mean_token_accuracy": 0.19823432117700576,
|
|
"num_tokens": 43866391.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 4.983281803131104,
|
|
"epoch": 1.8707564026206076,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004659952571930785,
|
|
"loss": 4.6997,
|
|
"mean_token_accuracy": 0.21467008590698242,
|
|
"num_tokens": 43881188.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 4.944690990447998,
|
|
"epoch": 1.871351995235259,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046597272850941104,
|
|
"loss": 4.712,
|
|
"mean_token_accuracy": 0.2197759136557579,
|
|
"num_tokens": 43893189.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 4.895982551574707,
|
|
"epoch": 1.8719475878499106,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046595019297586226,
|
|
"loss": 4.6604,
|
|
"mean_token_accuracy": 0.22488706856966018,
|
|
"num_tokens": 43905327.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 4.97210659980774,
|
|
"epoch": 1.8725431804645623,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004659276505932405,
|
|
"loss": 4.6952,
|
|
"mean_token_accuracy": 0.21132391393184663,
|
|
"num_tokens": 43921406.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 4.997434186935425,
|
|
"epoch": 1.873138773079214,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046590510136235435,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.20811518132686616,
|
|
"num_tokens": 43937218.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 4.940910387039184,
|
|
"epoch": 1.8737343656938654,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046588254528401264,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.2221936121582985,
|
|
"num_tokens": 43952259.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 4.9518272399902346,
|
|
"epoch": 1.874329958308517,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046585998235902437,
|
|
"loss": 4.7234,
|
|
"mean_token_accuracy": 0.2195736438035965,
|
|
"num_tokens": 43968016.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 4.880099058151245,
|
|
"epoch": 1.8749255509231686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046583741258819894,
|
|
"loss": 4.6509,
|
|
"mean_token_accuracy": 0.22410829067230226,
|
|
"num_tokens": 43980834.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 4.923909282684326,
|
|
"epoch": 1.8755211435378203,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004658148359723457,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.21225511133670807,
|
|
"num_tokens": 43994100.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 4.96882848739624,
|
|
"epoch": 1.8761167361524718,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004657922525122746,
|
|
"loss": 4.6941,
|
|
"mean_token_accuracy": 0.2187549114227295,
|
|
"num_tokens": 44007767.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.086216640472412,
|
|
"epoch": 1.8767123287671232,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004657696622087955,
|
|
"loss": 4.9937,
|
|
"mean_token_accuracy": 0.1894384115934372,
|
|
"num_tokens": 44022268.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 4.8964807987213135,
|
|
"epoch": 1.877307921381775,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004657470650627189,
|
|
"loss": 4.655,
|
|
"mean_token_accuracy": 0.2135670229792595,
|
|
"num_tokens": 44038254.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 4.9693803787231445,
|
|
"epoch": 1.8779035139964264,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046572446107485515,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.214166060090065,
|
|
"num_tokens": 44052595.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 4.950724840164185,
|
|
"epoch": 1.8784991066110779,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004657018502460152,
|
|
"loss": 4.6809,
|
|
"mean_token_accuracy": 0.22293803542852403,
|
|
"num_tokens": 44066036.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 4.965037775039673,
|
|
"epoch": 1.8790946992257296,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046567923257700983,
|
|
"loss": 4.7961,
|
|
"mean_token_accuracy": 0.2055445209145546,
|
|
"num_tokens": 44081931.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.025393533706665,
|
|
"epoch": 1.8796902918403813,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004656566080686504,
|
|
"loss": 4.8162,
|
|
"mean_token_accuracy": 0.2007318615913391,
|
|
"num_tokens": 44096461.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.034874057769775,
|
|
"epoch": 1.8802858844550328,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004656339767217485,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.20137130916118623,
|
|
"num_tokens": 44110475.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 4.94404296875,
|
|
"epoch": 1.8808814770696842,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046561133853711576,
|
|
"loss": 4.7312,
|
|
"mean_token_accuracy": 0.21036573648452758,
|
|
"num_tokens": 44125408.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 4.900430917739868,
|
|
"epoch": 1.881477069684336,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004655886935155643,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.20536168068647384,
|
|
"num_tokens": 44140678.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 4.989233827590942,
|
|
"epoch": 1.8820726622989876,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004655660416579062,
|
|
"loss": 4.723,
|
|
"mean_token_accuracy": 0.21054518222808838,
|
|
"num_tokens": 44153828.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.026680040359497,
|
|
"epoch": 1.882668254913639,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000465543382964954,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.20278455317020416,
|
|
"num_tokens": 44168063.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 4.884798192977906,
|
|
"epoch": 1.8832638475282906,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046552071743752055,
|
|
"loss": 4.649,
|
|
"mean_token_accuracy": 0.21574489772319794,
|
|
"num_tokens": 44182797.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 4.9346006393432615,
|
|
"epoch": 1.8838594401429423,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004654980450764186,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.2150595098733902,
|
|
"num_tokens": 44197191.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.00144853591919,
|
|
"epoch": 1.884455032757594,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046547536588246167,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.20763641148805617,
|
|
"num_tokens": 44209903.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 4.912179374694825,
|
|
"epoch": 1.8850506253722454,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046545267985646294,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.21618788093328475,
|
|
"num_tokens": 44223252.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 4.9154688835144045,
|
|
"epoch": 1.885646217986897,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046542998699923625,
|
|
"loss": 4.6571,
|
|
"mean_token_accuracy": 0.22103152573108673,
|
|
"num_tokens": 44236839.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 4.96137433052063,
|
|
"epoch": 1.8862418106015486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004654072873115956,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.21967219859361647,
|
|
"num_tokens": 44250125.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 4.937219285964966,
|
|
"epoch": 1.8868374032162,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046538458079435516,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.20649110823869704,
|
|
"num_tokens": 44265543.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 4.965050601959229,
|
|
"epoch": 1.8874329958308516,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004653618674483293,
|
|
"loss": 4.7815,
|
|
"mean_token_accuracy": 0.20733397752046584,
|
|
"num_tokens": 44278914.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.029762840270996,
|
|
"epoch": 1.8880285884455033,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046533914727433276,
|
|
"loss": 4.8023,
|
|
"mean_token_accuracy": 0.20523970276117326,
|
|
"num_tokens": 44292393.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 4.949517440795899,
|
|
"epoch": 1.888624181060155,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004653164202731804,
|
|
"loss": 4.713,
|
|
"mean_token_accuracy": 0.21215191036462783,
|
|
"num_tokens": 44305835.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 4.859322357177734,
|
|
"epoch": 1.8892197736748064,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046529368644568765,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.22344763278961183,
|
|
"num_tokens": 44320332.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 4.971170806884766,
|
|
"epoch": 1.889815366289458,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004652709457926697,
|
|
"loss": 4.7169,
|
|
"mean_token_accuracy": 0.20811486691236497,
|
|
"num_tokens": 44333440.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 4.9696742534637455,
|
|
"epoch": 1.8904109589041096,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046524819831494224,
|
|
"loss": 4.713,
|
|
"mean_token_accuracy": 0.21116380095481874,
|
|
"num_tokens": 44347351.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 4.9791124820709225,
|
|
"epoch": 1.8910065515187613,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004652254440133213,
|
|
"loss": 4.8265,
|
|
"mean_token_accuracy": 0.19769887179136275,
|
|
"num_tokens": 44362394.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 4.87616868019104,
|
|
"epoch": 1.8916021441334128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004652026828886229,
|
|
"loss": 4.5813,
|
|
"mean_token_accuracy": 0.225983689725399,
|
|
"num_tokens": 44375971.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 4.854461526870727,
|
|
"epoch": 1.8921977367480642,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004651799149416636,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.22537886202335358,
|
|
"num_tokens": 44389991.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 4.895719766616821,
|
|
"epoch": 1.892793329362716,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004651571401732599,
|
|
"loss": 4.6573,
|
|
"mean_token_accuracy": 0.22134605050086975,
|
|
"num_tokens": 44405737.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 4.957647037506104,
|
|
"epoch": 1.8933889219773676,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004651343585842287,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.21102841198444366,
|
|
"num_tokens": 44418641.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 4.994111585617065,
|
|
"epoch": 1.893984514592019,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004651115701753873,
|
|
"loss": 4.7702,
|
|
"mean_token_accuracy": 0.21382468044757844,
|
|
"num_tokens": 44433841.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 4.871664142608642,
|
|
"epoch": 1.8945801072066706,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046508877494755296,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.21650060266256332,
|
|
"num_tokens": 44448715.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 4.929262590408325,
|
|
"epoch": 1.8951756998213223,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046506597290154337,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.20803388208150864,
|
|
"num_tokens": 44462757.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 4.92743673324585,
|
|
"epoch": 1.8957712924359738,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046504316403817627,
|
|
"loss": 4.6816,
|
|
"mean_token_accuracy": 0.21340433061122893,
|
|
"num_tokens": 44477558.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 4.951457881927491,
|
|
"epoch": 1.8963668850506252,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004650203483582699,
|
|
"loss": 4.691,
|
|
"mean_token_accuracy": 0.21312494426965714,
|
|
"num_tokens": 44491520.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 4.96112961769104,
|
|
"epoch": 1.896962477665277,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046499752586264264,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.20428366363048553,
|
|
"num_tokens": 44505306.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 4.8872644901275635,
|
|
"epoch": 1.8975580702799286,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004649746965521129,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.2195603907108307,
|
|
"num_tokens": 44518969.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 4.864671754837036,
|
|
"epoch": 1.89815366289458,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004649518604274999,
|
|
"loss": 4.6171,
|
|
"mean_token_accuracy": 0.22855030447244645,
|
|
"num_tokens": 44532260.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 4.915559387207031,
|
|
"epoch": 1.8987492555092316,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004649290174896223,
|
|
"loss": 4.7996,
|
|
"mean_token_accuracy": 0.20806022882461547,
|
|
"num_tokens": 44545172.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 4.858493041992188,
|
|
"epoch": 1.8993448481238833,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004649061677392998,
|
|
"loss": 4.6438,
|
|
"mean_token_accuracy": 0.21932271867990494,
|
|
"num_tokens": 44558326.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 4.934250688552856,
|
|
"epoch": 1.899940440738535,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046488331117735176,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.21098292917013167,
|
|
"num_tokens": 44572517.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.012689876556396,
|
|
"epoch": 1.9005360333531864,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004648604478045981,
|
|
"loss": 4.8115,
|
|
"mean_token_accuracy": 0.21019667088985444,
|
|
"num_tokens": 44585148.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 4.90240445137024,
|
|
"epoch": 1.901131625967838,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046483757762185877,
|
|
"loss": 4.673,
|
|
"mean_token_accuracy": 0.2215358003973961,
|
|
"num_tokens": 44600103.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 4.9767731666564945,
|
|
"epoch": 1.9017272185824896,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004648147006299543,
|
|
"loss": 4.7802,
|
|
"mean_token_accuracy": 0.21274974048137665,
|
|
"num_tokens": 44614653.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.0215669631958,
|
|
"epoch": 1.9023228111971413,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004647918168297051,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.21726388335227967,
|
|
"num_tokens": 44629320.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 4.95092544555664,
|
|
"epoch": 1.9029184038117928,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046476892622193206,
|
|
"loss": 4.7067,
|
|
"mean_token_accuracy": 0.21184325367212295,
|
|
"num_tokens": 44645062.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 4.890785455703735,
|
|
"epoch": 1.9035139964264443,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004647460288074562,
|
|
"loss": 4.6362,
|
|
"mean_token_accuracy": 0.22027045637369155,
|
|
"num_tokens": 44659563.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.014591789245605,
|
|
"epoch": 1.904109589041096,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004647231245870987,
|
|
"loss": 4.8378,
|
|
"mean_token_accuracy": 0.20450664013624192,
|
|
"num_tokens": 44674259.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 4.923827600479126,
|
|
"epoch": 1.9047051816557474,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046470021356168116,
|
|
"loss": 4.6785,
|
|
"mean_token_accuracy": 0.21570128798484803,
|
|
"num_tokens": 44688057.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 4.929381227493286,
|
|
"epoch": 1.905300774270399,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046467729573202555,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.20736649632453918,
|
|
"num_tokens": 44705123.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 4.9955531597137455,
|
|
"epoch": 1.9058963668850506,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046465437109895365,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.21715840697288513,
|
|
"num_tokens": 44719702.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 4.893005466461181,
|
|
"epoch": 1.9064919594997023,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004646314396632878,
|
|
"loss": 4.6453,
|
|
"mean_token_accuracy": 0.2217704251408577,
|
|
"num_tokens": 44733331.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 4.832181167602539,
|
|
"epoch": 1.9070875521143538,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004646085014258506,
|
|
"loss": 4.6931,
|
|
"mean_token_accuracy": 0.21564959287643432,
|
|
"num_tokens": 44746095.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.0566388130187985,
|
|
"epoch": 1.9076831447290052,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046458555638746464,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.2040519267320633,
|
|
"num_tokens": 44761314.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 4.975952768325806,
|
|
"epoch": 1.908278737343657,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046456260454895307,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.21384167969226836,
|
|
"num_tokens": 44776186.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 4.8583437442779545,
|
|
"epoch": 1.9088743299583086,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046453964591113906,
|
|
"loss": 4.7044,
|
|
"mean_token_accuracy": 0.21403012573719024,
|
|
"num_tokens": 44791203.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.026323986053467,
|
|
"epoch": 1.90946992257296,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004645166804748462,
|
|
"loss": 4.7629,
|
|
"mean_token_accuracy": 0.22163974046707152,
|
|
"num_tokens": 44805114.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 4.883764600753784,
|
|
"epoch": 1.9100655151876116,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046449370824089807,
|
|
"loss": 4.6272,
|
|
"mean_token_accuracy": 0.22050727009773255,
|
|
"num_tokens": 44818873.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 4.909444999694824,
|
|
"epoch": 1.9106611078022633,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046447072921011875,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.21503969877958298,
|
|
"num_tokens": 44832438.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.005922603607178,
|
|
"epoch": 1.911256700416915,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046444774338333253,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.2127167448401451,
|
|
"num_tokens": 44848304.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 4.992622661590576,
|
|
"epoch": 1.9118522930315665,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004644247507613636,
|
|
"loss": 4.7482,
|
|
"mean_token_accuracy": 0.2105641096830368,
|
|
"num_tokens": 44862991.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 4.945120620727539,
|
|
"epoch": 1.912447885646218,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000464401751345037,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.2081649497151375,
|
|
"num_tokens": 44876815.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 4.964344263076782,
|
|
"epoch": 1.9130434782608696,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004643787451351774,
|
|
"loss": 4.7282,
|
|
"mean_token_accuracy": 0.21284895092248918,
|
|
"num_tokens": 44890574.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 4.983057117462158,
|
|
"epoch": 1.913639070875521,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004643557321326102,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.21222224831581116,
|
|
"num_tokens": 44904447.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 4.884874439239502,
|
|
"epoch": 1.9142346634901726,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004643327123381607,
|
|
"loss": 4.6452,
|
|
"mean_token_accuracy": 0.21788378357887267,
|
|
"num_tokens": 44916500.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 4.9100851058959964,
|
|
"epoch": 1.9148302561048243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004643096857526547,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.22721848785877227,
|
|
"num_tokens": 44929738.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 4.920885753631592,
|
|
"epoch": 1.915425848719476,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046428665237691806,
|
|
"loss": 4.672,
|
|
"mean_token_accuracy": 0.21985962688922883,
|
|
"num_tokens": 44942528.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 4.914173269271851,
|
|
"epoch": 1.9160214413341274,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000464263612211777,
|
|
"loss": 4.724,
|
|
"mean_token_accuracy": 0.21603098064661025,
|
|
"num_tokens": 44956126.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 4.932322931289673,
|
|
"epoch": 1.916617033948779,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004642405652580578,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.2129470318555832,
|
|
"num_tokens": 44969733.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 4.879689693450928,
|
|
"epoch": 1.9172126265634306,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004642175115165873,
|
|
"loss": 4.5462,
|
|
"mean_token_accuracy": 0.2295258805155754,
|
|
"num_tokens": 44982751.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 4.94248685836792,
|
|
"epoch": 1.9178082191780823,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046419445098819223,
|
|
"loss": 4.6795,
|
|
"mean_token_accuracy": 0.21721580177545546,
|
|
"num_tokens": 44997898.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 4.966833448410034,
|
|
"epoch": 1.9184038117927338,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046417138367369995,
|
|
"loss": 4.7589,
|
|
"mean_token_accuracy": 0.20989680141210557,
|
|
"num_tokens": 45012617.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 4.912861967086792,
|
|
"epoch": 1.9189994044073853,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046414830957393756,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.2257785826921463,
|
|
"num_tokens": 45025847.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 4.8937599658966064,
|
|
"epoch": 1.919594997022037,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046412522868973297,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.21417946070432664,
|
|
"num_tokens": 45040674.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 4.969879245758056,
|
|
"epoch": 1.9201905896366886,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004641021410219138,
|
|
"loss": 4.7733,
|
|
"mean_token_accuracy": 0.21379299759864806,
|
|
"num_tokens": 45053585.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 4.912044191360474,
|
|
"epoch": 1.9207861822513401,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046407904657130833,
|
|
"loss": 4.6567,
|
|
"mean_token_accuracy": 0.22240400016307832,
|
|
"num_tokens": 45069825.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 4.983568954467773,
|
|
"epoch": 1.9213817748659916,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004640559453387449,
|
|
"loss": 4.7374,
|
|
"mean_token_accuracy": 0.2083795413374901,
|
|
"num_tokens": 45085235.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 4.892353296279907,
|
|
"epoch": 1.9219773674806433,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004640328373250521,
|
|
"loss": 4.6659,
|
|
"mean_token_accuracy": 0.21934934258460997,
|
|
"num_tokens": 45099209.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 4.90319709777832,
|
|
"epoch": 1.9225729600952948,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046400972253105884,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.2114604413509369,
|
|
"num_tokens": 45114132.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 4.850765705108643,
|
|
"epoch": 1.9231685527099462,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000463986600957594,
|
|
"loss": 4.6536,
|
|
"mean_token_accuracy": 0.22124827057123184,
|
|
"num_tokens": 45126637.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 4.984485387802124,
|
|
"epoch": 1.923764145324598,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046396347260548715,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.20573774129152297,
|
|
"num_tokens": 45140950.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 4.905160999298095,
|
|
"epoch": 1.9243597379392496,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004639403374755678,
|
|
"loss": 4.5903,
|
|
"mean_token_accuracy": 0.22526517510414124,
|
|
"num_tokens": 45155050.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 4.9512214183807375,
|
|
"epoch": 1.9249553305539011,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004639171955686657,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.21131797283887863,
|
|
"num_tokens": 45169864.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 4.9435608863830565,
|
|
"epoch": 1.9255509231685526,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004638940468856109,
|
|
"loss": 4.669,
|
|
"mean_token_accuracy": 0.22092163562774658,
|
|
"num_tokens": 45183148.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 4.873573589324951,
|
|
"epoch": 1.9261465157832043,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046387089142723386,
|
|
"loss": 4.6458,
|
|
"mean_token_accuracy": 0.22189393192529677,
|
|
"num_tokens": 45196652.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 4.907633686065674,
|
|
"epoch": 1.926742108397856,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046384772919436497,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.2147594064474106,
|
|
"num_tokens": 45210628.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.04646110534668,
|
|
"epoch": 1.9273377010125075,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046382456018783513,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.2060976430773735,
|
|
"num_tokens": 45226276.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 4.941025876998902,
|
|
"epoch": 1.927933293627159,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004638013844084753,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.21607526540756225,
|
|
"num_tokens": 45242214.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.030568933486938,
|
|
"epoch": 1.9285288862418106,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004637782018571167,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.20716221779584884,
|
|
"num_tokens": 45256536.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 4.925836420059204,
|
|
"epoch": 1.9291244788564623,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004637550125345911,
|
|
"loss": 4.6982,
|
|
"mean_token_accuracy": 0.22002166956663133,
|
|
"num_tokens": 45269383.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.002072048187256,
|
|
"epoch": 1.9297200714711138,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046373181644173,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.21207770556211472,
|
|
"num_tokens": 45282265.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 4.999194717407226,
|
|
"epoch": 1.9303156640857653,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004637086135793655,
|
|
"loss": 4.6929,
|
|
"mean_token_accuracy": 0.21892343312501908,
|
|
"num_tokens": 45294379.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 4.895266437530518,
|
|
"epoch": 1.930911256700417,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004636854039483299,
|
|
"loss": 4.6711,
|
|
"mean_token_accuracy": 0.21660265773534776,
|
|
"num_tokens": 45307608.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 4.9956666946411135,
|
|
"epoch": 1.9315068493150684,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046366218754945556,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.21210551559925078,
|
|
"num_tokens": 45320382.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 4.956905221939087,
|
|
"epoch": 1.93210244192972,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004636389643835754,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.21799227893352507,
|
|
"num_tokens": 45334590.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 4.868472957611084,
|
|
"epoch": 1.9326980345443716,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046361573445152224,
|
|
"loss": 4.6316,
|
|
"mean_token_accuracy": 0.22114823162555694,
|
|
"num_tokens": 45348701.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 4.897781038284302,
|
|
"epoch": 1.9332936271590233,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046359249775412934,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.2168336480855942,
|
|
"num_tokens": 45362896.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 4.924170207977295,
|
|
"epoch": 1.9338892197736748,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004635692542922302,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.21967870444059373,
|
|
"num_tokens": 45378208.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 4.928525447845459,
|
|
"epoch": 1.9344848123883263,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046354600406665853,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.21280419528484346,
|
|
"num_tokens": 45392101.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 4.905991697311402,
|
|
"epoch": 1.935080405002978,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046352274707824823,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.21578491777181624,
|
|
"num_tokens": 45405829.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 4.914334058761597,
|
|
"epoch": 1.9356759976176297,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004634994833278334,
|
|
"loss": 4.7035,
|
|
"mean_token_accuracy": 0.20999237149953842,
|
|
"num_tokens": 45419772.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 4.937978076934814,
|
|
"epoch": 1.9362715902322811,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004634762128162487,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.21592063456773758,
|
|
"num_tokens": 45433192.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 4.910448598861694,
|
|
"epoch": 1.9368671828469326,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004634529355443287,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.2168759971857071,
|
|
"num_tokens": 45447409.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 4.936424970626831,
|
|
"epoch": 1.9374627754615843,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046342965151290836,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.20997560173273086,
|
|
"num_tokens": 45460768.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.055294752120972,
|
|
"epoch": 1.938058368076236,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046340636072282273,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.2055077999830246,
|
|
"num_tokens": 45474500.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.019304656982422,
|
|
"epoch": 1.9386539606908875,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004633830631749072,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.20576538443565368,
|
|
"num_tokens": 45486699.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 4.902675533294678,
|
|
"epoch": 1.939249553305539,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046335975886999754,
|
|
"loss": 4.6487,
|
|
"mean_token_accuracy": 0.21606584042310714,
|
|
"num_tokens": 45500431.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.005855131149292,
|
|
"epoch": 1.9398451459201906,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004633364478089296,
|
|
"loss": 4.7706,
|
|
"mean_token_accuracy": 0.21037062704563142,
|
|
"num_tokens": 45515813.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 4.939748287200928,
|
|
"epoch": 1.9404407385348421,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004633131299925395,
|
|
"loss": 4.6531,
|
|
"mean_token_accuracy": 0.22353535443544387,
|
|
"num_tokens": 45530454.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 4.968300724029541,
|
|
"epoch": 1.9410363311494936,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004632898054216636,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.21060958057641982,
|
|
"num_tokens": 45544526.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 4.918998289108276,
|
|
"epoch": 1.9416319237641453,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046326647409713844,
|
|
"loss": 4.6923,
|
|
"mean_token_accuracy": 0.22537928074598312,
|
|
"num_tokens": 45557992.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 4.944730663299561,
|
|
"epoch": 1.942227516378797,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046324313601980106,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.21490606516599656,
|
|
"num_tokens": 45572650.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 4.9330696105957035,
|
|
"epoch": 1.9428231089934485,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004632197911904884,
|
|
"loss": 4.6599,
|
|
"mean_token_accuracy": 0.21846500635147095,
|
|
"num_tokens": 45586151.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 4.878892660140991,
|
|
"epoch": 1.9434187016081,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046319643961003785,
|
|
"loss": 4.6535,
|
|
"mean_token_accuracy": 0.21693186610937118,
|
|
"num_tokens": 45599862.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 4.9786450386047365,
|
|
"epoch": 1.9440142942227516,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046317308127928706,
|
|
"loss": 4.6857,
|
|
"mean_token_accuracy": 0.21452597230672837,
|
|
"num_tokens": 45616075.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 4.906042051315308,
|
|
"epoch": 1.9446098868374033,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004631497161990738,
|
|
"loss": 4.5906,
|
|
"mean_token_accuracy": 0.2293053612112999,
|
|
"num_tokens": 45629006.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 4.946039485931396,
|
|
"epoch": 1.9452054794520548,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004631263443702361,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.2037975698709488,
|
|
"num_tokens": 45641802.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 4.941393232345581,
|
|
"epoch": 1.9458010720667063,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046310296579361225,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.21013537049293518,
|
|
"num_tokens": 45654982.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 4.891042280197143,
|
|
"epoch": 1.946396664681358,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004630795804700409,
|
|
"loss": 4.6682,
|
|
"mean_token_accuracy": 0.2184898927807808,
|
|
"num_tokens": 45669547.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 4.835631084442139,
|
|
"epoch": 1.9469922572960097,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004630561884003608,
|
|
"loss": 4.6824,
|
|
"mean_token_accuracy": 0.21903771311044692,
|
|
"num_tokens": 45682026.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 4.9406524181365965,
|
|
"epoch": 1.9475878499106611,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000463032789585411,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.2225414425134659,
|
|
"num_tokens": 45696637.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.039644622802735,
|
|
"epoch": 1.9481834425253126,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004630093840260307,
|
|
"loss": 4.7348,
|
|
"mean_token_accuracy": 0.21270721405744553,
|
|
"num_tokens": 45710846.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 4.925578641891479,
|
|
"epoch": 1.9487790351399643,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046298597172305956,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.21615642160177231,
|
|
"num_tokens": 45724479.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 4.913004350662232,
|
|
"epoch": 1.949374627754616,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004629625526773372,
|
|
"loss": 4.6559,
|
|
"mean_token_accuracy": 0.21634285300970077,
|
|
"num_tokens": 45738347.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 4.886160612106323,
|
|
"epoch": 1.9499702203692673,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004629391268897037,
|
|
"loss": 4.6985,
|
|
"mean_token_accuracy": 0.21954245567321778,
|
|
"num_tokens": 45751316.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.024319124221802,
|
|
"epoch": 1.950565812983919,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004629156943609993,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.2012477234005928,
|
|
"num_tokens": 45765479.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 4.960080194473266,
|
|
"epoch": 1.9511614055985707,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046289225509206445,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.2104956775903702,
|
|
"num_tokens": 45779645.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 4.951200008392334,
|
|
"epoch": 1.9517569982132221,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004628688090837399,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.21543668657541276,
|
|
"num_tokens": 45795057.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.003727293014526,
|
|
"epoch": 1.9523525908278736,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004628453563368666,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.2052126094698906,
|
|
"num_tokens": 45809055.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 4.957211303710937,
|
|
"epoch": 1.9529481834425253,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004628218968522859,
|
|
"loss": 4.696,
|
|
"mean_token_accuracy": 0.21591175049543382,
|
|
"num_tokens": 45822882.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 4.949285936355591,
|
|
"epoch": 1.953543776057177,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004627984306308391,
|
|
"loss": 4.7127,
|
|
"mean_token_accuracy": 0.2118979200720787,
|
|
"num_tokens": 45839325.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.043509149551392,
|
|
"epoch": 1.9541393686718285,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046277495767336785,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.20422326624393464,
|
|
"num_tokens": 45853143.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 4.951894903182984,
|
|
"epoch": 1.95473496128648,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004627514779807142,
|
|
"loss": 4.6912,
|
|
"mean_token_accuracy": 0.2182522639632225,
|
|
"num_tokens": 45866775.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 4.8412939548492435,
|
|
"epoch": 1.9553305539011316,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004627279915537204,
|
|
"loss": 4.6566,
|
|
"mean_token_accuracy": 0.21597682535648347,
|
|
"num_tokens": 45881164.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.0344747543334964,
|
|
"epoch": 1.9559261465157833,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046270449839322863,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.21000812202692032,
|
|
"num_tokens": 45894854.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 4.968385648727417,
|
|
"epoch": 1.9565217391304348,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046268099850008175,
|
|
"loss": 4.7566,
|
|
"mean_token_accuracy": 0.20574492812156678,
|
|
"num_tokens": 45909825.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 4.880395364761353,
|
|
"epoch": 1.9571173317450863,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004626574918751226,
|
|
"loss": 4.7141,
|
|
"mean_token_accuracy": 0.21286465376615524,
|
|
"num_tokens": 45924397.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 4.920567846298217,
|
|
"epoch": 1.957712924359738,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004626339785191944,
|
|
"loss": 4.5853,
|
|
"mean_token_accuracy": 0.22409781366586684,
|
|
"num_tokens": 45938178.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 4.9127685070037845,
|
|
"epoch": 1.9583085169743897,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004626104584331404,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.22219082564115525,
|
|
"num_tokens": 45951632.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.015047836303711,
|
|
"epoch": 1.958904109589041,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004625869316178043,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.21604648381471633,
|
|
"num_tokens": 45965524.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 4.903645849227905,
|
|
"epoch": 1.9594997022036926,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046256339807403,
|
|
"loss": 4.6393,
|
|
"mean_token_accuracy": 0.21802964061498642,
|
|
"num_tokens": 45978750.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 4.823912763595581,
|
|
"epoch": 1.9600952948183443,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004625398578026615,
|
|
"loss": 4.6316,
|
|
"mean_token_accuracy": 0.22021581381559371,
|
|
"num_tokens": 45992587.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 4.911178112030029,
|
|
"epoch": 1.9606908874329958,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046251631080454324,
|
|
"loss": 4.6892,
|
|
"mean_token_accuracy": 0.2178495019674301,
|
|
"num_tokens": 46008468.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.004069185256958,
|
|
"epoch": 1.9612864800476473,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004624927570805198,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.21534615904092788,
|
|
"num_tokens": 46022616.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 4.967078733444214,
|
|
"epoch": 1.961882072662299,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046246919663143603,
|
|
"loss": 4.7208,
|
|
"mean_token_accuracy": 0.21708188354969024,
|
|
"num_tokens": 46035890.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 4.903377437591553,
|
|
"epoch": 1.9624776652769507,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000462445629458137,
|
|
"loss": 4.651,
|
|
"mean_token_accuracy": 0.2187971442937851,
|
|
"num_tokens": 46049881.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 4.939310693740845,
|
|
"epoch": 1.9630732578916021,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046242205556146795,
|
|
"loss": 4.7755,
|
|
"mean_token_accuracy": 0.2067825362086296,
|
|
"num_tokens": 46063672.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 4.954992580413818,
|
|
"epoch": 1.9636688505062536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004623984749422745,
|
|
"loss": 4.6913,
|
|
"mean_token_accuracy": 0.21545346081256866,
|
|
"num_tokens": 46076500.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 4.941675662994385,
|
|
"epoch": 1.9642644431209053,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004623748876014025,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.21394609659910202,
|
|
"num_tokens": 46089469.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 4.900010633468628,
|
|
"epoch": 1.964860035735557,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004623512935396979,
|
|
"loss": 4.6064,
|
|
"mean_token_accuracy": 0.22086701393127442,
|
|
"num_tokens": 46103334.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 4.932797861099243,
|
|
"epoch": 1.9654556283502085,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000462327692758007,
|
|
"loss": 4.6705,
|
|
"mean_token_accuracy": 0.22009682804346084,
|
|
"num_tokens": 46116107.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 4.877291917800903,
|
|
"epoch": 1.96605122096486,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004623040852571764,
|
|
"loss": 4.6741,
|
|
"mean_token_accuracy": 0.21770022809505463,
|
|
"num_tokens": 46130416.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.035864639282226,
|
|
"epoch": 1.9666468135795117,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046228047103805277,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.20422906279563904,
|
|
"num_tokens": 46144020.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 4.899749708175659,
|
|
"epoch": 1.9672424061941634,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004622568501014831,
|
|
"loss": 4.6806,
|
|
"mean_token_accuracy": 0.21700058579444886,
|
|
"num_tokens": 46157395.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 4.976842212677002,
|
|
"epoch": 1.9678379988088148,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046223322244831475,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.21245893388986586,
|
|
"num_tokens": 46171861.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.0011680126190186,
|
|
"epoch": 1.9684335914234663,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000462209588079395,
|
|
"loss": 4.795,
|
|
"mean_token_accuracy": 0.2062891975045204,
|
|
"num_tokens": 46187486.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 4.99857120513916,
|
|
"epoch": 1.969029184038118,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004621859469955718,
|
|
"loss": 4.7579,
|
|
"mean_token_accuracy": 0.21100866943597793,
|
|
"num_tokens": 46199699.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.005572652816772,
|
|
"epoch": 1.9696247766527695,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046216229919769305,
|
|
"loss": 4.7826,
|
|
"mean_token_accuracy": 0.2107681468129158,
|
|
"num_tokens": 46214209.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 4.926738357543945,
|
|
"epoch": 1.970220369267421,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000462138644686607,
|
|
"loss": 4.7394,
|
|
"mean_token_accuracy": 0.21707690954208375,
|
|
"num_tokens": 46227475.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 4.950700044631958,
|
|
"epoch": 1.9708159618820726,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046211498346316194,
|
|
"loss": 4.7672,
|
|
"mean_token_accuracy": 0.21446318924427032,
|
|
"num_tokens": 46240131.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 4.93601245880127,
|
|
"epoch": 1.9714115544967243,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004620913155282066,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.2219202399253845,
|
|
"num_tokens": 46253039.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.028237628936767,
|
|
"epoch": 1.9720071471113758,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046206764088259003,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.21055082082748414,
|
|
"num_tokens": 46268618.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 4.957343196868896,
|
|
"epoch": 1.9726027397260273,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004620439595271613,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.22075213640928268,
|
|
"num_tokens": 46282447.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.000969123840332,
|
|
"epoch": 1.973198332340679,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004620202714627699,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.20375186651945115,
|
|
"num_tokens": 46295929.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 4.841608619689941,
|
|
"epoch": 1.9737939249553307,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004619965766902654,
|
|
"loss": 4.6133,
|
|
"mean_token_accuracy": 0.22337698340415954,
|
|
"num_tokens": 46310876.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.013442802429199,
|
|
"epoch": 1.9743895175699822,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046197287521049777,
|
|
"loss": 4.7467,
|
|
"mean_token_accuracy": 0.20974380671977996,
|
|
"num_tokens": 46325555.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 4.963163232803344,
|
|
"epoch": 1.9749851101846336,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004619491670243171,
|
|
"loss": 4.693,
|
|
"mean_token_accuracy": 0.21025158017873763,
|
|
"num_tokens": 46340226.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 4.958924627304077,
|
|
"epoch": 1.9755807027992853,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046192545213257375,
|
|
"loss": 4.6818,
|
|
"mean_token_accuracy": 0.20987565517425538,
|
|
"num_tokens": 46353268.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 4.963182973861694,
|
|
"epoch": 1.976176295413937,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004619017305361184,
|
|
"loss": 4.7616,
|
|
"mean_token_accuracy": 0.21181275993585585,
|
|
"num_tokens": 46367547.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 4.967603158950806,
|
|
"epoch": 1.9767718880285885,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004618780022358018,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.20443286001682281,
|
|
"num_tokens": 46382980.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 4.98084020614624,
|
|
"epoch": 1.97736748064324,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004618542672324751,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.2187956839799881,
|
|
"num_tokens": 46396449.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 4.9369165897369385,
|
|
"epoch": 1.9779630732578917,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046183052552698975,
|
|
"loss": 4.688,
|
|
"mean_token_accuracy": 0.21285978555679322,
|
|
"num_tokens": 46410569.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 4.9836287021636965,
|
|
"epoch": 1.9785586658725431,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046180677712019707,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.20308597534894943,
|
|
"num_tokens": 46424391.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.070505046844483,
|
|
"epoch": 1.9791542584871946,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004617830220129491,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.20897113382816315,
|
|
"num_tokens": 46439778.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 4.943332290649414,
|
|
"epoch": 1.9797498511018463,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004617592602060979,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.22086002677679062,
|
|
"num_tokens": 46454334.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 4.952193021774292,
|
|
"epoch": 1.980345443716498,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046173549170049554,
|
|
"loss": 4.6547,
|
|
"mean_token_accuracy": 0.22538573145866395,
|
|
"num_tokens": 46465954.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 4.944520282745361,
|
|
"epoch": 1.9809410363311495,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004617117164969948,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.21541976779699326,
|
|
"num_tokens": 46480947.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 4.927971458435058,
|
|
"epoch": 1.981536628945801,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046168793459644837,
|
|
"loss": 4.6873,
|
|
"mean_token_accuracy": 0.21910909116268157,
|
|
"num_tokens": 46494547.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 4.902251815795898,
|
|
"epoch": 1.9821322215604527,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004616641459997092,
|
|
"loss": 4.6375,
|
|
"mean_token_accuracy": 0.21995218992233276,
|
|
"num_tokens": 46507759.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 4.924126291275025,
|
|
"epoch": 1.9827278141751044,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004616403507076306,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.2152317315340042,
|
|
"num_tokens": 46522942.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 4.938023233413697,
|
|
"epoch": 1.9833234067897558,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004616165487210661,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.22198512703180312,
|
|
"num_tokens": 46537071.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.011099338531494,
|
|
"epoch": 1.9839189994044073,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004615927400408695,
|
|
"loss": 4.8021,
|
|
"mean_token_accuracy": 0.2048631951212883,
|
|
"num_tokens": 46550430.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 4.937311410903931,
|
|
"epoch": 1.984514592019059,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004615689246678946,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.2218635380268097,
|
|
"num_tokens": 46563206.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 4.867911624908447,
|
|
"epoch": 1.9851101846337107,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004615451026029957,
|
|
"loss": 4.6185,
|
|
"mean_token_accuracy": 0.21845539659261703,
|
|
"num_tokens": 46576841.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 4.988131904602051,
|
|
"epoch": 1.9857057772483622,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004615212738470273,
|
|
"loss": 4.7495,
|
|
"mean_token_accuracy": 0.21293379366397858,
|
|
"num_tokens": 46591217.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 4.958731746673584,
|
|
"epoch": 1.9863013698630136,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046149743840084406,
|
|
"loss": 4.6824,
|
|
"mean_token_accuracy": 0.21482615023851395,
|
|
"num_tokens": 46605393.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 4.931171703338623,
|
|
"epoch": 1.9868969624776653,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046147359626530103,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.21190572679042816,
|
|
"num_tokens": 46622283.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 4.884750604629517,
|
|
"epoch": 1.9874925550923168,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004614497474412532,
|
|
"loss": 4.6498,
|
|
"mean_token_accuracy": 0.21512353420257568,
|
|
"num_tokens": 46637274.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 4.890866041183472,
|
|
"epoch": 1.9880881477069683,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004614258919295561,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.2215416669845581,
|
|
"num_tokens": 46650722.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 4.956513118743897,
|
|
"epoch": 1.98868374032162,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004614020297310654,
|
|
"loss": 4.6866,
|
|
"mean_token_accuracy": 0.21452221274375916,
|
|
"num_tokens": 46665254.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 4.965430402755738,
|
|
"epoch": 1.9892793329362717,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004613781608466369,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.2167579635977745,
|
|
"num_tokens": 46678696.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.067149257659912,
|
|
"epoch": 1.9898749255509232,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004613542852771269,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.2096664562821388,
|
|
"num_tokens": 46692188.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.052944803237915,
|
|
"epoch": 1.9904705181655746,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046133040302339155,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.20769468694925308,
|
|
"num_tokens": 46707452.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.014668130874634,
|
|
"epoch": 1.9910661107802263,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004613065140862877,
|
|
"loss": 4.7862,
|
|
"mean_token_accuracy": 0.21539221256971358,
|
|
"num_tokens": 46721612.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 4.925550556182861,
|
|
"epoch": 1.991661703394878,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000461282618466672,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.21115005016326904,
|
|
"num_tokens": 46734760.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 4.932150793075562,
|
|
"epoch": 1.9922572960095295,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046125871616540165,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.21642966270446778,
|
|
"num_tokens": 46747202.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 4.9792375564575195,
|
|
"epoch": 1.992852888624181,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004612348071833341,
|
|
"loss": 4.7435,
|
|
"mean_token_accuracy": 0.21283803582191468,
|
|
"num_tokens": 46759652.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 4.883632230758667,
|
|
"epoch": 1.9934484812388327,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004612108915213268,
|
|
"loss": 4.6396,
|
|
"mean_token_accuracy": 0.2169135332107544,
|
|
"num_tokens": 46774424.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 4.967180156707764,
|
|
"epoch": 1.9940440738534844,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046118696918023757,
|
|
"loss": 4.7742,
|
|
"mean_token_accuracy": 0.21860322952270508,
|
|
"num_tokens": 46786916.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 4.90681791305542,
|
|
"epoch": 1.9946396664681358,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046116304016092445,
|
|
"loss": 4.6175,
|
|
"mean_token_accuracy": 0.23010889291763306,
|
|
"num_tokens": 46798453.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 4.844549560546875,
|
|
"epoch": 1.9952352590827873,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004611391044642458,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.2217252552509308,
|
|
"num_tokens": 46811619.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 4.833466339111328,
|
|
"epoch": 1.995830851697439,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046111516209106004,
|
|
"loss": 4.6517,
|
|
"mean_token_accuracy": 0.22470925003290176,
|
|
"num_tokens": 46824956.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 4.954610443115234,
|
|
"epoch": 1.9964264443120905,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046109121304222607,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.21641422808170319,
|
|
"num_tokens": 46837898.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 4.923254585266113,
|
|
"epoch": 1.997022036926742,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004610672573186029,
|
|
"loss": 4.6614,
|
|
"mean_token_accuracy": 0.22271255254745484,
|
|
"num_tokens": 46853574.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 4.876059293746948,
|
|
"epoch": 1.9976176295413937,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046104329492104967,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.22050172239542007,
|
|
"num_tokens": 46869010.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 4.980381441116333,
|
|
"epoch": 1.9982132221560454,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046101932585042597,
|
|
"loss": 4.785,
|
|
"mean_token_accuracy": 0.21287486404180528,
|
|
"num_tokens": 46882326.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 4.969910764694214,
|
|
"epoch": 1.9988088147706968,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004609953501075915,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.2089722990989685,
|
|
"num_tokens": 46897216.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 4.934994411468506,
|
|
"epoch": 1.9994044073853483,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004609713676934062,
|
|
"loss": 4.6548,
|
|
"mean_token_accuracy": 0.21624996215105058,
|
|
"num_tokens": 46908774.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.0274986743927,
|
|
"epoch": 2.0,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004609473786087303,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.217660491168499,
|
|
"num_tokens": 46922024.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 4.920351171493531,
|
|
"epoch": 2.0005955926146517,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004609233828544243,
|
|
"loss": 4.5808,
|
|
"mean_token_accuracy": 0.22471834123134612,
|
|
"num_tokens": 46934779.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 4.881848526000977,
|
|
"epoch": 2.001191185229303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004608993804313489,
|
|
"loss": 4.5762,
|
|
"mean_token_accuracy": 0.22074543684720993,
|
|
"num_tokens": 46950779.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 4.949295568466186,
|
|
"epoch": 2.0017867778439546,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046087537134036484,
|
|
"loss": 4.6145,
|
|
"mean_token_accuracy": 0.22350863218307496,
|
|
"num_tokens": 46964897.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 4.976459217071533,
|
|
"epoch": 2.0023823704586063,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046085135558233357,
|
|
"loss": 4.6155,
|
|
"mean_token_accuracy": 0.21766667515039445,
|
|
"num_tokens": 46978201.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 4.914805698394775,
|
|
"epoch": 2.002977963073258,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046082733315811625,
|
|
"loss": 4.6254,
|
|
"mean_token_accuracy": 0.2205462023615837,
|
|
"num_tokens": 46992259.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 4.8025730609893795,
|
|
"epoch": 2.0035735556879093,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046080330406857465,
|
|
"loss": 4.4879,
|
|
"mean_token_accuracy": 0.22814329266548156,
|
|
"num_tokens": 47005229.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 4.886287355422974,
|
|
"epoch": 2.004169148302561,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046077926831457073,
|
|
"loss": 4.6306,
|
|
"mean_token_accuracy": 0.22147900313138963,
|
|
"num_tokens": 47016671.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 4.9112410068511965,
|
|
"epoch": 2.0047647409172127,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046075522589696636,
|
|
"loss": 4.5113,
|
|
"mean_token_accuracy": 0.22678942531347274,
|
|
"num_tokens": 47031350.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 4.939398336410522,
|
|
"epoch": 2.0053603335318644,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046073117681662414,
|
|
"loss": 4.6152,
|
|
"mean_token_accuracy": 0.22120818495750427,
|
|
"num_tokens": 47043965.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 4.894019842147827,
|
|
"epoch": 2.0059559261465156,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004607071210744066,
|
|
"loss": 4.5443,
|
|
"mean_token_accuracy": 0.22897030413150787,
|
|
"num_tokens": 47058140.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 4.864012575149536,
|
|
"epoch": 2.0065515187611673,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046068305867117657,
|
|
"loss": 4.4153,
|
|
"mean_token_accuracy": 0.24492871314287185,
|
|
"num_tokens": 47072144.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 4.9054279804229735,
|
|
"epoch": 2.007147111375819,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046065898960779704,
|
|
"loss": 4.6187,
|
|
"mean_token_accuracy": 0.2186950922012329,
|
|
"num_tokens": 47087917.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 4.865862560272217,
|
|
"epoch": 2.0077427039904707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046063491388513144,
|
|
"loss": 4.5497,
|
|
"mean_token_accuracy": 0.2258133053779602,
|
|
"num_tokens": 47102494.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 4.860640001296997,
|
|
"epoch": 2.008338296605122,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004606108315040434,
|
|
"loss": 4.5959,
|
|
"mean_token_accuracy": 0.2231634020805359,
|
|
"num_tokens": 47115749.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 4.892506074905396,
|
|
"epoch": 2.0089338892197737,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046058674246539653,
|
|
"loss": 4.6069,
|
|
"mean_token_accuracy": 0.22528031915426255,
|
|
"num_tokens": 47130350.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.034998798370362,
|
|
"epoch": 2.0095294818344254,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004605626467700551,
|
|
"loss": 4.6542,
|
|
"mean_token_accuracy": 0.21668477207422257,
|
|
"num_tokens": 47144075.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 4.891066408157348,
|
|
"epoch": 2.0101250744490766,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046053854441888305,
|
|
"loss": 4.6124,
|
|
"mean_token_accuracy": 0.22081829756498336,
|
|
"num_tokens": 47156434.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 4.80493049621582,
|
|
"epoch": 2.0107206670637283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004605144354127451,
|
|
"loss": 4.475,
|
|
"mean_token_accuracy": 0.22472144812345504,
|
|
"num_tokens": 47169218.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 4.863481712341309,
|
|
"epoch": 2.01131625967838,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000460490319752506,
|
|
"loss": 4.5413,
|
|
"mean_token_accuracy": 0.22696388959884645,
|
|
"num_tokens": 47181517.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 4.9048011302948,
|
|
"epoch": 2.0119118522930317,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046046619743903087,
|
|
"loss": 4.635,
|
|
"mean_token_accuracy": 0.2116304412484169,
|
|
"num_tokens": 47195837.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 4.916071605682373,
|
|
"epoch": 2.012507444907683,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046044206847318457,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.21786839365959168,
|
|
"num_tokens": 47211186.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 4.95941653251648,
|
|
"epoch": 2.0131030375223347,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004604179328558329,
|
|
"loss": 4.5782,
|
|
"mean_token_accuracy": 0.23022273927927017,
|
|
"num_tokens": 47225737.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.026159715652466,
|
|
"epoch": 2.0136986301369864,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004603937905878414,
|
|
"loss": 4.7988,
|
|
"mean_token_accuracy": 0.21135950237512588,
|
|
"num_tokens": 47238202.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 4.909846782684326,
|
|
"epoch": 2.014294222751638,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046036964167007615,
|
|
"loss": 4.558,
|
|
"mean_token_accuracy": 0.22495843172073365,
|
|
"num_tokens": 47251757.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 4.912625026702881,
|
|
"epoch": 2.0148898153662893,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046034548610340316,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.21924195438623428,
|
|
"num_tokens": 47268089.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 4.932293891906738,
|
|
"epoch": 2.015485407980941,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046032132388868895,
|
|
"loss": 4.6681,
|
|
"mean_token_accuracy": 0.2166842743754387,
|
|
"num_tokens": 47282542.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 4.921790266036988,
|
|
"epoch": 2.0160810005955927,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004602971550268002,
|
|
"loss": 4.6496,
|
|
"mean_token_accuracy": 0.21828455477952957,
|
|
"num_tokens": 47295592.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 4.87606954574585,
|
|
"epoch": 2.0166765932102444,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004602729795186038,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.2216833621263504,
|
|
"num_tokens": 47310737.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 4.883085775375366,
|
|
"epoch": 2.0172721858248956,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046024879736496677,
|
|
"loss": 4.5905,
|
|
"mean_token_accuracy": 0.22363603562116624,
|
|
"num_tokens": 47323904.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 4.873883390426636,
|
|
"epoch": 2.0178677784395473,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046022460856675663,
|
|
"loss": 4.4883,
|
|
"mean_token_accuracy": 0.23801972419023515,
|
|
"num_tokens": 47337253.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 4.833599948883057,
|
|
"epoch": 2.018463371054199,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004602004131248409,
|
|
"loss": 4.4966,
|
|
"mean_token_accuracy": 0.22935336232185363,
|
|
"num_tokens": 47351634.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 4.865172100067139,
|
|
"epoch": 2.0190589636688503,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004601762110400875,
|
|
"loss": 4.572,
|
|
"mean_token_accuracy": 0.21951038837432862,
|
|
"num_tokens": 47364984.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 4.962703227996826,
|
|
"epoch": 2.019654556283502,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046015200231336453,
|
|
"loss": 4.6207,
|
|
"mean_token_accuracy": 0.2177645280957222,
|
|
"num_tokens": 47379357.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 4.917849349975586,
|
|
"epoch": 2.0202501488981537,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004601277869455402,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.21565579771995544,
|
|
"num_tokens": 47394088.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 4.8514723777771,
|
|
"epoch": 2.0208457415128054,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046010356493748325,
|
|
"loss": 4.5104,
|
|
"mean_token_accuracy": 0.24061761498451234,
|
|
"num_tokens": 47406896.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 4.9784643173217775,
|
|
"epoch": 2.0214413341274566,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046007933629006227,
|
|
"loss": 4.6694,
|
|
"mean_token_accuracy": 0.21605848968029023,
|
|
"num_tokens": 47422990.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 4.8760417938232425,
|
|
"epoch": 2.0220369267421083,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004600551010041464,
|
|
"loss": 4.5884,
|
|
"mean_token_accuracy": 0.22295502126216887,
|
|
"num_tokens": 47437239.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 4.935458850860596,
|
|
"epoch": 2.02263251935676,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046003085908060505,
|
|
"loss": 4.6404,
|
|
"mean_token_accuracy": 0.21541084498167037,
|
|
"num_tokens": 47452930.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 4.8042542934417725,
|
|
"epoch": 2.0232281119714117,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046000661052030765,
|
|
"loss": 4.505,
|
|
"mean_token_accuracy": 0.23539014905691147,
|
|
"num_tokens": 47464453.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 4.876990127563476,
|
|
"epoch": 2.023823704586063,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004599823553241238,
|
|
"loss": 4.5563,
|
|
"mean_token_accuracy": 0.22956598401069642,
|
|
"num_tokens": 47478856.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 4.930900192260742,
|
|
"epoch": 2.0244192972007147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004599580934929237,
|
|
"loss": 4.5743,
|
|
"mean_token_accuracy": 0.22563786804676056,
|
|
"num_tokens": 47493910.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 4.870608901977539,
|
|
"epoch": 2.0250148898153664,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004599338250275775,
|
|
"loss": 4.5779,
|
|
"mean_token_accuracy": 0.22290028482675553,
|
|
"num_tokens": 47506169.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 4.830197668075561,
|
|
"epoch": 2.025610482430018,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045990954992895566,
|
|
"loss": 4.5415,
|
|
"mean_token_accuracy": 0.2225767731666565,
|
|
"num_tokens": 47519379.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 4.922513055801391,
|
|
"epoch": 2.0262060750446693,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045988526819792897,
|
|
"loss": 4.5503,
|
|
"mean_token_accuracy": 0.22244488298892975,
|
|
"num_tokens": 47533054.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 4.85078182220459,
|
|
"epoch": 2.026801667659321,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004598609798353683,
|
|
"loss": 4.5991,
|
|
"mean_token_accuracy": 0.21786414980888366,
|
|
"num_tokens": 47546377.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 4.794735670089722,
|
|
"epoch": 2.0273972602739727,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004598366848421447,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.22545879930257798,
|
|
"num_tokens": 47559232.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 4.892415332794189,
|
|
"epoch": 2.027992852888624,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004598123832191299,
|
|
"loss": 4.5893,
|
|
"mean_token_accuracy": 0.2277670383453369,
|
|
"num_tokens": 47573415.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 4.878351449966431,
|
|
"epoch": 2.0285884455032757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004597880749671954,
|
|
"loss": 4.6505,
|
|
"mean_token_accuracy": 0.2180162027478218,
|
|
"num_tokens": 47588199.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 4.88696665763855,
|
|
"epoch": 2.0291840381179274,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045976376008721303,
|
|
"loss": 4.5453,
|
|
"mean_token_accuracy": 0.22276145964860916,
|
|
"num_tokens": 47602595.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 4.977674150466919,
|
|
"epoch": 2.029779630732579,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000459739438580055,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.21198504716157912,
|
|
"num_tokens": 47616162.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 4.934962034225464,
|
|
"epoch": 2.0303752233472303,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045971511044659374,
|
|
"loss": 4.6116,
|
|
"mean_token_accuracy": 0.2164445549249649,
|
|
"num_tokens": 47631199.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 4.830078792572022,
|
|
"epoch": 2.030970815961882,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004596907756877018,
|
|
"loss": 4.5461,
|
|
"mean_token_accuracy": 0.22239194810390472,
|
|
"num_tokens": 47645256.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 4.899409389495849,
|
|
"epoch": 2.0315664085765337,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045966643430425197,
|
|
"loss": 4.5961,
|
|
"mean_token_accuracy": 0.22331515848636627,
|
|
"num_tokens": 47657938.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 4.856191396713257,
|
|
"epoch": 2.0321620011911854,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004596420862971174,
|
|
"loss": 4.6049,
|
|
"mean_token_accuracy": 0.21801334321498872,
|
|
"num_tokens": 47672823.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 4.877491664886475,
|
|
"epoch": 2.0327575938058366,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004596177316671714,
|
|
"loss": 4.5923,
|
|
"mean_token_accuracy": 0.21970705837011337,
|
|
"num_tokens": 47685348.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 4.858077096939087,
|
|
"epoch": 2.0333531864204883,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045959337041528753,
|
|
"loss": 4.6135,
|
|
"mean_token_accuracy": 0.22630537152290345,
|
|
"num_tokens": 47698488.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 4.898901557922363,
|
|
"epoch": 2.03394877903514,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004595690025423396,
|
|
"loss": 4.6067,
|
|
"mean_token_accuracy": 0.22144592106342315,
|
|
"num_tokens": 47713158.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 4.8896301746368405,
|
|
"epoch": 2.0345443716497917,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004595446280492017,
|
|
"loss": 4.606,
|
|
"mean_token_accuracy": 0.2233523577451706,
|
|
"num_tokens": 47727882.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 4.946687173843384,
|
|
"epoch": 2.035139964264443,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045952024693674795,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.21590642780065536,
|
|
"num_tokens": 47742890.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 4.805355787277222,
|
|
"epoch": 2.0357355568790947,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045949585920585304,
|
|
"loss": 4.5561,
|
|
"mean_token_accuracy": 0.2222685143351555,
|
|
"num_tokens": 47757327.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 4.960154867172241,
|
|
"epoch": 2.0363311494937464,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045947146485739155,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.22172834426164628,
|
|
"num_tokens": 47772947.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 4.848352336883545,
|
|
"epoch": 2.036926742108398,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045944706389223854,
|
|
"loss": 4.5507,
|
|
"mean_token_accuracy": 0.22907704263925552,
|
|
"num_tokens": 47785859.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 4.876618146896362,
|
|
"epoch": 2.0375223347230493,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045942265631126935,
|
|
"loss": 4.6155,
|
|
"mean_token_accuracy": 0.22177807092666627,
|
|
"num_tokens": 47799842.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 4.864244985580444,
|
|
"epoch": 2.038117927337701,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045939824211535925,
|
|
"loss": 4.5996,
|
|
"mean_token_accuracy": 0.21948074847459792,
|
|
"num_tokens": 47812886.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 4.868069505691528,
|
|
"epoch": 2.0387135199523527,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000459373821305384,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.22500012069940567,
|
|
"num_tokens": 47827684.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 4.824190521240235,
|
|
"epoch": 2.039309112567004,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045934939388221966,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.23184532523155213,
|
|
"num_tokens": 47840907.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 4.986314916610718,
|
|
"epoch": 2.0399047051816557,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045932495984674223,
|
|
"loss": 4.684,
|
|
"mean_token_accuracy": 0.21912638247013091,
|
|
"num_tokens": 47854891.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 4.969859886169433,
|
|
"epoch": 2.0405002977963074,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045930051919982815,
|
|
"loss": 4.5811,
|
|
"mean_token_accuracy": 0.2272451862692833,
|
|
"num_tokens": 47867084.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 4.900922775268555,
|
|
"epoch": 2.041095890410959,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004592760719423541,
|
|
"loss": 4.6161,
|
|
"mean_token_accuracy": 0.22536188662052153,
|
|
"num_tokens": 47880892.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 4.910932493209839,
|
|
"epoch": 2.0416914830256103,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000459251618075197,
|
|
"loss": 4.6315,
|
|
"mean_token_accuracy": 0.22417232543230056,
|
|
"num_tokens": 47893688.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 4.934600114822388,
|
|
"epoch": 2.042287075640262,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045922715759923394,
|
|
"loss": 4.6474,
|
|
"mean_token_accuracy": 0.2168784260749817,
|
|
"num_tokens": 47908415.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 4.929975700378418,
|
|
"epoch": 2.0428826682549137,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045920269051534225,
|
|
"loss": 4.6584,
|
|
"mean_token_accuracy": 0.21733472794294356,
|
|
"num_tokens": 47922224.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 4.904376411437989,
|
|
"epoch": 2.0434782608695654,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045917821682439955,
|
|
"loss": 4.6502,
|
|
"mean_token_accuracy": 0.2215976372361183,
|
|
"num_tokens": 47935645.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 4.8849081039428714,
|
|
"epoch": 2.0440738534842167,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004591537365272837,
|
|
"loss": 4.5765,
|
|
"mean_token_accuracy": 0.22679631561040878,
|
|
"num_tokens": 47950357.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 4.856412410736084,
|
|
"epoch": 2.0446694460988684,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045912924962487276,
|
|
"loss": 4.5687,
|
|
"mean_token_accuracy": 0.22388002872467042,
|
|
"num_tokens": 47965930.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 4.9216968536376955,
|
|
"epoch": 2.04526503871352,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045910475611804486,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.21311984658241273,
|
|
"num_tokens": 47979935.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 4.964973783493042,
|
|
"epoch": 2.0458606313281713,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045908025600767887,
|
|
"loss": 4.674,
|
|
"mean_token_accuracy": 0.21929625123739244,
|
|
"num_tokens": 47995648.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 4.845994472503662,
|
|
"epoch": 2.046456223942823,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004590557492946533,
|
|
"loss": 4.6012,
|
|
"mean_token_accuracy": 0.22984810322523117,
|
|
"num_tokens": 48009613.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 4.987720394134522,
|
|
"epoch": 2.0470518165574747,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045903123597984725,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.21420419663190843,
|
|
"num_tokens": 48023032.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 4.924534702301026,
|
|
"epoch": 2.0476474091721264,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045900671606414003,
|
|
"loss": 4.5992,
|
|
"mean_token_accuracy": 0.226413793861866,
|
|
"num_tokens": 48037202.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 4.8100385665893555,
|
|
"epoch": 2.0482430017867777,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000458982189548411,
|
|
"loss": 4.5435,
|
|
"mean_token_accuracy": 0.23183637708425522,
|
|
"num_tokens": 48050373.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 4.928803634643555,
|
|
"epoch": 2.0488385944014293,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004589576564335401,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.21492877155542373,
|
|
"num_tokens": 48064029.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 4.8889693260192875,
|
|
"epoch": 2.049434187016081,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004589331167204071,
|
|
"loss": 4.4981,
|
|
"mean_token_accuracy": 0.23485268652439117,
|
|
"num_tokens": 48077176.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 4.880778741836548,
|
|
"epoch": 2.0500297796307327,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004589085704098922,
|
|
"loss": 4.5636,
|
|
"mean_token_accuracy": 0.2238682582974434,
|
|
"num_tokens": 48090279.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 4.8728104591369625,
|
|
"epoch": 2.050625372245384,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000458884017502876,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.22291285991668702,
|
|
"num_tokens": 48103650.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 4.940800333023072,
|
|
"epoch": 2.0512209648600357,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045885945800023896,
|
|
"loss": 4.6125,
|
|
"mean_token_accuracy": 0.22476604133844375,
|
|
"num_tokens": 48119197.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 4.892994117736817,
|
|
"epoch": 2.0518165574746874,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045883489190286214,
|
|
"loss": 4.6556,
|
|
"mean_token_accuracy": 0.21608103364706038,
|
|
"num_tokens": 48134326.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 4.948443412780762,
|
|
"epoch": 2.052412150089339,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004588103192116267,
|
|
"loss": 4.6585,
|
|
"mean_token_accuracy": 0.22275814414024353,
|
|
"num_tokens": 48149277.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 4.9318090915679935,
|
|
"epoch": 2.0530077427039903,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004587857399274139,
|
|
"loss": 4.643,
|
|
"mean_token_accuracy": 0.2251838132739067,
|
|
"num_tokens": 48162443.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 4.789141845703125,
|
|
"epoch": 2.053603335318642,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004587611540511055,
|
|
"loss": 4.4585,
|
|
"mean_token_accuracy": 0.23647489547729492,
|
|
"num_tokens": 48175537.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 4.844925594329834,
|
|
"epoch": 2.0541989279332937,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004587365615835832,
|
|
"loss": 4.6259,
|
|
"mean_token_accuracy": 0.21963447630405425,
|
|
"num_tokens": 48191976.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 4.910615253448486,
|
|
"epoch": 2.0547945205479454,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004587119625257292,
|
|
"loss": 4.6414,
|
|
"mean_token_accuracy": 0.21820462346076966,
|
|
"num_tokens": 48204891.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 4.883451223373413,
|
|
"epoch": 2.0553901131625967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045868735687842584,
|
|
"loss": 4.561,
|
|
"mean_token_accuracy": 0.2211340308189392,
|
|
"num_tokens": 48217957.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 4.819940996170044,
|
|
"epoch": 2.0559857057772484,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004586627446425556,
|
|
"loss": 4.5704,
|
|
"mean_token_accuracy": 0.2406160682439804,
|
|
"num_tokens": 48231605.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 4.8763267993927,
|
|
"epoch": 2.0565812983919,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004586381258190013,
|
|
"loss": 4.5784,
|
|
"mean_token_accuracy": 0.21959915459156037,
|
|
"num_tokens": 48245887.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 4.8937023162841795,
|
|
"epoch": 2.0571768910065513,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004586135004086461,
|
|
"loss": 4.6486,
|
|
"mean_token_accuracy": 0.2198842167854309,
|
|
"num_tokens": 48259913.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 4.950042390823365,
|
|
"epoch": 2.057772483621203,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004585888684123731,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.2159852132201195,
|
|
"num_tokens": 48273044.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 4.920922756195068,
|
|
"epoch": 2.0583680762358547,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004585642298310659,
|
|
"loss": 4.6163,
|
|
"mean_token_accuracy": 0.21799568831920624,
|
|
"num_tokens": 48286835.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 4.923020124435425,
|
|
"epoch": 2.0589636688505064,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004585395846656083,
|
|
"loss": 4.6721,
|
|
"mean_token_accuracy": 0.21138303130865096,
|
|
"num_tokens": 48301986.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 4.947223424911499,
|
|
"epoch": 2.0595592614651577,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004585149329168842,
|
|
"loss": 4.561,
|
|
"mean_token_accuracy": 0.22434256970882416,
|
|
"num_tokens": 48314994.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 4.947973680496216,
|
|
"epoch": 2.0601548540798094,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045849027458577776,
|
|
"loss": 4.6748,
|
|
"mean_token_accuracy": 0.21168205440044402,
|
|
"num_tokens": 48329905.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 4.82611722946167,
|
|
"epoch": 2.060750446694461,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004584656096731735,
|
|
"loss": 4.569,
|
|
"mean_token_accuracy": 0.21950690299272538,
|
|
"num_tokens": 48344582.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 4.981424188613891,
|
|
"epoch": 2.0613460393091128,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045844093817995615,
|
|
"loss": 4.6883,
|
|
"mean_token_accuracy": 0.2110792338848114,
|
|
"num_tokens": 48358373.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 4.898625659942627,
|
|
"epoch": 2.061941631923764,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045841626010701065,
|
|
"loss": 4.5382,
|
|
"mean_token_accuracy": 0.23108212649822235,
|
|
"num_tokens": 48371911.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 4.946793270111084,
|
|
"epoch": 2.0625372245384157,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004583915754552221,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.22068698555231095,
|
|
"num_tokens": 48384367.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.004331302642822,
|
|
"epoch": 2.0631328171530674,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004583668842254759,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.22463162392377853,
|
|
"num_tokens": 48397034.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 4.882065629959106,
|
|
"epoch": 2.0637284097677187,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004583421864186577,
|
|
"loss": 4.5456,
|
|
"mean_token_accuracy": 0.22982274740934372,
|
|
"num_tokens": 48410451.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 4.819010877609253,
|
|
"epoch": 2.0643240023823703,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045831748203565333,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.2238221362233162,
|
|
"num_tokens": 48424437.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 4.919869661331177,
|
|
"epoch": 2.064919594997022,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045829277107734895,
|
|
"loss": 4.6559,
|
|
"mean_token_accuracy": 0.21951936483383178,
|
|
"num_tokens": 48438979.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 4.886342859268188,
|
|
"epoch": 2.0655151876116737,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004582680535446309,
|
|
"loss": 4.5976,
|
|
"mean_token_accuracy": 0.22607158571481706,
|
|
"num_tokens": 48450907.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 4.905448722839355,
|
|
"epoch": 2.066110780226325,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004582433294383858,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.2269025981426239,
|
|
"num_tokens": 48466231.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 4.856344747543335,
|
|
"epoch": 2.0667063728409767,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045821859875950035,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.22343223690986633,
|
|
"num_tokens": 48480472.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 4.833391809463501,
|
|
"epoch": 2.0673019654556284,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045819386150886167,
|
|
"loss": 4.486,
|
|
"mean_token_accuracy": 0.2259410947561264,
|
|
"num_tokens": 48494535.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 4.9322648525238035,
|
|
"epoch": 2.06789755807028,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000458169117687357,
|
|
"loss": 4.6944,
|
|
"mean_token_accuracy": 0.20992900431156158,
|
|
"num_tokens": 48508696.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 4.9908373832702635,
|
|
"epoch": 2.0684931506849313,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004581443672958739,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.219740429520607,
|
|
"num_tokens": 48521868.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 4.865917778015136,
|
|
"epoch": 2.069088743299583,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045811961033530014,
|
|
"loss": 4.5521,
|
|
"mean_token_accuracy": 0.22066687792539597,
|
|
"num_tokens": 48535710.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 4.88524284362793,
|
|
"epoch": 2.0696843359142347,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045809484680652376,
|
|
"loss": 4.617,
|
|
"mean_token_accuracy": 0.22200814187526702,
|
|
"num_tokens": 48550868.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 4.901011657714844,
|
|
"epoch": 2.0702799285288864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004580700767104328,
|
|
"loss": 4.586,
|
|
"mean_token_accuracy": 0.22642900794744492,
|
|
"num_tokens": 48564827.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 4.89134521484375,
|
|
"epoch": 2.0708755211435377,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045804530004791595,
|
|
"loss": 4.5935,
|
|
"mean_token_accuracy": 0.22708706855773925,
|
|
"num_tokens": 48578790.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 4.884474658966065,
|
|
"epoch": 2.0714711137581894,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004580205168198617,
|
|
"loss": 4.5477,
|
|
"mean_token_accuracy": 0.23433395475149155,
|
|
"num_tokens": 48592327.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 4.873766136169434,
|
|
"epoch": 2.072066706372841,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004579957270271592,
|
|
"loss": 4.5451,
|
|
"mean_token_accuracy": 0.22094607055187226,
|
|
"num_tokens": 48606830.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 4.899532413482666,
|
|
"epoch": 2.0726622989874928,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045797093067069734,
|
|
"loss": 4.57,
|
|
"mean_token_accuracy": 0.22806672900915145,
|
|
"num_tokens": 48621790.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 4.8335521697998045,
|
|
"epoch": 2.073257891602144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045794612775136584,
|
|
"loss": 4.6051,
|
|
"mean_token_accuracy": 0.22562000453472136,
|
|
"num_tokens": 48636738.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 4.9248291015625,
|
|
"epoch": 2.0738534842167957,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004579213182700541,
|
|
"loss": 4.595,
|
|
"mean_token_accuracy": 0.22487313747406007,
|
|
"num_tokens": 48651254.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 4.990051221847534,
|
|
"epoch": 2.0744490768314474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004578965022276521,
|
|
"loss": 4.7004,
|
|
"mean_token_accuracy": 0.20893063843250276,
|
|
"num_tokens": 48666527.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 4.9176921367645265,
|
|
"epoch": 2.0750446694460987,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004578716796250501,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.21841969341039658,
|
|
"num_tokens": 48680005.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 4.97106523513794,
|
|
"epoch": 2.0756402620607504,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045784685046313804,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.2173308849334717,
|
|
"num_tokens": 48692819.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.0372716903686525,
|
|
"epoch": 2.076235854675402,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045782201474280684,
|
|
"loss": 4.7143,
|
|
"mean_token_accuracy": 0.21411429047584535,
|
|
"num_tokens": 48706480.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 4.890499401092529,
|
|
"epoch": 2.0768314472900538,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045779717246494724,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.2081574022769928,
|
|
"num_tokens": 48719720.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 4.831350898742675,
|
|
"epoch": 2.077427039904705,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004577723236304503,
|
|
"loss": 4.5336,
|
|
"mean_token_accuracy": 0.23346239775419236,
|
|
"num_tokens": 48731388.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 4.911939096450806,
|
|
"epoch": 2.0780226325193567,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004577474682402072,
|
|
"loss": 4.6137,
|
|
"mean_token_accuracy": 0.22373927682638167,
|
|
"num_tokens": 48746595.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.0326131820678714,
|
|
"epoch": 2.0786182251340084,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004577226062951096,
|
|
"loss": 4.6741,
|
|
"mean_token_accuracy": 0.21284785717725754,
|
|
"num_tokens": 48762067.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 4.9519712924957275,
|
|
"epoch": 2.07921381774866,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004576977377960492,
|
|
"loss": 4.6989,
|
|
"mean_token_accuracy": 0.2124399274587631,
|
|
"num_tokens": 48775913.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 4.810905981063843,
|
|
"epoch": 2.0798094103633114,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004576728627439179,
|
|
"loss": 4.5412,
|
|
"mean_token_accuracy": 0.22355666309595107,
|
|
"num_tokens": 48790291.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 4.867477321624756,
|
|
"epoch": 2.080405002977963,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004576479811396082,
|
|
"loss": 4.5788,
|
|
"mean_token_accuracy": 0.22236828953027726,
|
|
"num_tokens": 48804235.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 4.969612646102905,
|
|
"epoch": 2.0810005955926147,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004576230929840123,
|
|
"loss": 4.6695,
|
|
"mean_token_accuracy": 0.21148947030305862,
|
|
"num_tokens": 48819634.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 4.934616422653198,
|
|
"epoch": 2.0815961882072664,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004575981982780229,
|
|
"loss": 4.6079,
|
|
"mean_token_accuracy": 0.21979445070028306,
|
|
"num_tokens": 48835654.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 4.951300811767578,
|
|
"epoch": 2.0821917808219177,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004575732970225331,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.21337771117687226,
|
|
"num_tokens": 48851374.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 4.887032079696655,
|
|
"epoch": 2.0827873734365694,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045754838921843597,
|
|
"loss": 4.5462,
|
|
"mean_token_accuracy": 0.2291711762547493,
|
|
"num_tokens": 48865024.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 4.9229213237762455,
|
|
"epoch": 2.083382966051221,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004575234748666249,
|
|
"loss": 4.6925,
|
|
"mean_token_accuracy": 0.21535496264696122,
|
|
"num_tokens": 48878552.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 4.978520107269287,
|
|
"epoch": 2.0839785586658723,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004574985539679936,
|
|
"loss": 4.6258,
|
|
"mean_token_accuracy": 0.21923830956220627,
|
|
"num_tokens": 48891701.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 4.827670574188232,
|
|
"epoch": 2.084574151280524,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045747362652343585,
|
|
"loss": 4.4656,
|
|
"mean_token_accuracy": 0.23625820577144624,
|
|
"num_tokens": 48903961.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 4.931995105743408,
|
|
"epoch": 2.0851697438951757,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004574486925338458,
|
|
"loss": 4.6245,
|
|
"mean_token_accuracy": 0.22155738472938538,
|
|
"num_tokens": 48918240.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 4.928162574768066,
|
|
"epoch": 2.0857653365098274,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004574237520001178,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.21494049727916717,
|
|
"num_tokens": 48932558.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 4.819302082061768,
|
|
"epoch": 2.0863609291244787,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045739880492314645,
|
|
"loss": 4.5798,
|
|
"mean_token_accuracy": 0.22338734865188598,
|
|
"num_tokens": 48947267.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 4.99688024520874,
|
|
"epoch": 2.0869565217391304,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004573738513038265,
|
|
"loss": 4.685,
|
|
"mean_token_accuracy": 0.21049636602401733,
|
|
"num_tokens": 48962811.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 4.9344769477844235,
|
|
"epoch": 2.087552114353782,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000457348891143053,
|
|
"loss": 4.6598,
|
|
"mean_token_accuracy": 0.21490775495767594,
|
|
"num_tokens": 48975589.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 4.932843923568726,
|
|
"epoch": 2.0881477069684338,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004573239244417213,
|
|
"loss": 4.6366,
|
|
"mean_token_accuracy": 0.22215743064880372,
|
|
"num_tokens": 48987634.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 4.860768222808838,
|
|
"epoch": 2.088743299583085,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004572989512007268,
|
|
"loss": 4.5696,
|
|
"mean_token_accuracy": 0.22950922697782516,
|
|
"num_tokens": 49001023.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 4.9162280559539795,
|
|
"epoch": 2.0893388921977367,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045727397142096543,
|
|
"loss": 4.5447,
|
|
"mean_token_accuracy": 0.22708081305027009,
|
|
"num_tokens": 49015326.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 4.865576553344726,
|
|
"epoch": 2.0899344848123884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000457248985103333,
|
|
"loss": 4.6161,
|
|
"mean_token_accuracy": 0.22162641286849977,
|
|
"num_tokens": 49029798.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 4.953160953521729,
|
|
"epoch": 2.09053007742704,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004572239922487259,
|
|
"loss": 4.6922,
|
|
"mean_token_accuracy": 0.22083666175603867,
|
|
"num_tokens": 49043600.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 4.978031587600708,
|
|
"epoch": 2.0911256700416914,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045719899285804027,
|
|
"loss": 4.6675,
|
|
"mean_token_accuracy": 0.22649990469217302,
|
|
"num_tokens": 49057213.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 4.891602373123169,
|
|
"epoch": 2.091721262656343,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045717398693217315,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.21354375630617142,
|
|
"num_tokens": 49071835.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 4.927918767929077,
|
|
"epoch": 2.0923168552709948,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045714897447202125,
|
|
"loss": 4.6079,
|
|
"mean_token_accuracy": 0.22473724335432052,
|
|
"num_tokens": 49083944.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 4.938552379608154,
|
|
"epoch": 2.092912447885646,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045712395547848185,
|
|
"loss": 4.6524,
|
|
"mean_token_accuracy": 0.22122289538383483,
|
|
"num_tokens": 49097576.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 4.9455150127410885,
|
|
"epoch": 2.0935080405002977,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004570989299524523,
|
|
"loss": 4.6749,
|
|
"mean_token_accuracy": 0.22800844311714172,
|
|
"num_tokens": 49109580.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 4.926183795928955,
|
|
"epoch": 2.0941036331149494,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045707389789483016,
|
|
"loss": 4.6326,
|
|
"mean_token_accuracy": 0.22346321791410445,
|
|
"num_tokens": 49123646.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 4.868783330917358,
|
|
"epoch": 2.094699225729601,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004570488593065133,
|
|
"loss": 4.5895,
|
|
"mean_token_accuracy": 0.21977721899747849,
|
|
"num_tokens": 49137764.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 4.889441967010498,
|
|
"epoch": 2.0952948183442524,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004570238141883999,
|
|
"loss": 4.6292,
|
|
"mean_token_accuracy": 0.2224181264638901,
|
|
"num_tokens": 49151024.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 4.966428756713867,
|
|
"epoch": 2.095890410958904,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045699876254138823,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.21268241554498674,
|
|
"num_tokens": 49167439.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 4.872417831420899,
|
|
"epoch": 2.0964860035735557,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004569737043663768,
|
|
"loss": 4.5583,
|
|
"mean_token_accuracy": 0.22887771874666213,
|
|
"num_tokens": 49180856.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 4.885630178451538,
|
|
"epoch": 2.0970815961882074,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004569486396642645,
|
|
"loss": 4.6276,
|
|
"mean_token_accuracy": 0.22281551510095596,
|
|
"num_tokens": 49192577.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 4.820541095733643,
|
|
"epoch": 2.0976771888028587,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004569235684359504,
|
|
"loss": 4.5218,
|
|
"mean_token_accuracy": 0.2293888360261917,
|
|
"num_tokens": 49208026.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 4.9179830074310305,
|
|
"epoch": 2.0982727814175104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004568984906823337,
|
|
"loss": 4.6545,
|
|
"mean_token_accuracy": 0.22397881895303726,
|
|
"num_tokens": 49221688.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 4.997791004180908,
|
|
"epoch": 2.098868374032162,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045687340640431374,
|
|
"loss": 4.6233,
|
|
"mean_token_accuracy": 0.21528686732053756,
|
|
"num_tokens": 49237537.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 4.880546569824219,
|
|
"epoch": 2.099463966646814,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004568483156027905,
|
|
"loss": 4.5843,
|
|
"mean_token_accuracy": 0.22798132300376892,
|
|
"num_tokens": 49250586.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 4.869537353515625,
|
|
"epoch": 2.100059559261465,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045682321827866383,
|
|
"loss": 4.586,
|
|
"mean_token_accuracy": 0.2220591500401497,
|
|
"num_tokens": 49263579.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 4.904711675643921,
|
|
"epoch": 2.1006551518761167,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000456798114432834,
|
|
"loss": 4.546,
|
|
"mean_token_accuracy": 0.23243519514799119,
|
|
"num_tokens": 49275967.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 4.927015972137451,
|
|
"epoch": 2.1012507444907684,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004567730040662013,
|
|
"loss": 4.6104,
|
|
"mean_token_accuracy": 0.2192326918244362,
|
|
"num_tokens": 49290178.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 4.885321187973022,
|
|
"epoch": 2.1018463371054197,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004567478871796665,
|
|
"loss": 4.6508,
|
|
"mean_token_accuracy": 0.22210669815540313,
|
|
"num_tokens": 49302167.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 4.897438812255859,
|
|
"epoch": 2.1024419297200714,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045672276377413054,
|
|
"loss": 4.6085,
|
|
"mean_token_accuracy": 0.21860267370939254,
|
|
"num_tokens": 49316965.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 4.941949415206909,
|
|
"epoch": 2.103037522334723,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004566976338504945,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.21707527190446854,
|
|
"num_tokens": 49330670.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 4.904648303985596,
|
|
"epoch": 2.1036331149493748,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004566724974096597,
|
|
"loss": 4.6133,
|
|
"mean_token_accuracy": 0.22412541955709459,
|
|
"num_tokens": 49343786.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 4.823146629333496,
|
|
"epoch": 2.104228707564026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004566473544525279,
|
|
"loss": 4.5692,
|
|
"mean_token_accuracy": 0.22401367723941804,
|
|
"num_tokens": 49358668.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 4.891346883773804,
|
|
"epoch": 2.1048243001786777,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004566222049800008,
|
|
"loss": 4.6215,
|
|
"mean_token_accuracy": 0.21974369436502456,
|
|
"num_tokens": 49372127.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 4.852251195907593,
|
|
"epoch": 2.1054198927933294,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045659704899298045,
|
|
"loss": 4.596,
|
|
"mean_token_accuracy": 0.22179399579763412,
|
|
"num_tokens": 49387579.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 4.9057502269744875,
|
|
"epoch": 2.106015485407981,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004565718864923693,
|
|
"loss": 4.6606,
|
|
"mean_token_accuracy": 0.22080007195472717,
|
|
"num_tokens": 49400306.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 4.9550587177276615,
|
|
"epoch": 2.1066110780226324,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004565467174790697,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.22572636753320693,
|
|
"num_tokens": 49413735.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 4.936946439743042,
|
|
"epoch": 2.107206670637284,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004565215419539846,
|
|
"loss": 4.6772,
|
|
"mean_token_accuracy": 0.21631298065185547,
|
|
"num_tokens": 49428554.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 4.8853997707366945,
|
|
"epoch": 2.1078022632519358,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045649635991801686,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.22907941937446594,
|
|
"num_tokens": 49441694.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 4.908016490936279,
|
|
"epoch": 2.1083978558665875,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004564711713720698,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.21196395456790923,
|
|
"num_tokens": 49455222.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.005141401290894,
|
|
"epoch": 2.1089934484812387,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004564459763170469,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.2111097604036331,
|
|
"num_tokens": 49468768.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 4.906853914260864,
|
|
"epoch": 2.1095890410958904,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045642077475385186,
|
|
"loss": 4.6141,
|
|
"mean_token_accuracy": 0.2209692344069481,
|
|
"num_tokens": 49481399.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 4.902557992935181,
|
|
"epoch": 2.110184633710542,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045639556668338854,
|
|
"loss": 4.6023,
|
|
"mean_token_accuracy": 0.2199593737721443,
|
|
"num_tokens": 49496392.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 4.854091835021973,
|
|
"epoch": 2.1107802263251934,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045637035210656124,
|
|
"loss": 4.5392,
|
|
"mean_token_accuracy": 0.22862538695335388,
|
|
"num_tokens": 49509126.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 4.9196573257446286,
|
|
"epoch": 2.111375818939845,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045634513102427426,
|
|
"loss": 4.6811,
|
|
"mean_token_accuracy": 0.21474213898181915,
|
|
"num_tokens": 49522913.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 4.854739046096801,
|
|
"epoch": 2.1119714115544967,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004563199034374323,
|
|
"loss": 4.5858,
|
|
"mean_token_accuracy": 0.22039912641048431,
|
|
"num_tokens": 49536593.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 4.912686920166015,
|
|
"epoch": 2.1125670041691484,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004562946693469402,
|
|
"loss": 4.6089,
|
|
"mean_token_accuracy": 0.2104763686656952,
|
|
"num_tokens": 49551032.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 4.964586925506592,
|
|
"epoch": 2.1131625967837997,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004562694287537031,
|
|
"loss": 4.6014,
|
|
"mean_token_accuracy": 0.22518180906772614,
|
|
"num_tokens": 49564159.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 4.968143653869629,
|
|
"epoch": 2.1137581893984514,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045624418165862626,
|
|
"loss": 4.6935,
|
|
"mean_token_accuracy": 0.21583302766084672,
|
|
"num_tokens": 49577426.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 4.937816572189331,
|
|
"epoch": 2.114353782013103,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004562189280626154,
|
|
"loss": 4.6258,
|
|
"mean_token_accuracy": 0.22171501964330673,
|
|
"num_tokens": 49592020.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 4.848244571685791,
|
|
"epoch": 2.114949374627755,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004561936679665761,
|
|
"loss": 4.5387,
|
|
"mean_token_accuracy": 0.23062115758657456,
|
|
"num_tokens": 49606203.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 4.875724506378174,
|
|
"epoch": 2.115544967242406,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004561684013714147,
|
|
"loss": 4.5891,
|
|
"mean_token_accuracy": 0.22577957212924957,
|
|
"num_tokens": 49620951.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 4.945313549041748,
|
|
"epoch": 2.1161405598570577,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004561431282780372,
|
|
"loss": 4.6779,
|
|
"mean_token_accuracy": 0.21636412888765336,
|
|
"num_tokens": 49636864.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 4.934330081939697,
|
|
"epoch": 2.1167361524717094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045611784868735024,
|
|
"loss": 4.6303,
|
|
"mean_token_accuracy": 0.21713715195655822,
|
|
"num_tokens": 49650839.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 4.954050016403198,
|
|
"epoch": 2.117331745086361,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004560925626002605,
|
|
"loss": 4.6535,
|
|
"mean_token_accuracy": 0.2146823599934578,
|
|
"num_tokens": 49665920.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 4.890568351745605,
|
|
"epoch": 2.1179273377010124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000456067270017675,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.21967131048440933,
|
|
"num_tokens": 49680789.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 4.915760087966919,
|
|
"epoch": 2.118522930315664,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045604197094050087,
|
|
"loss": 4.5674,
|
|
"mean_token_accuracy": 0.2224210813641548,
|
|
"num_tokens": 49693069.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 4.860920047760009,
|
|
"epoch": 2.1191185229303158,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004560166653696457,
|
|
"loss": 4.6997,
|
|
"mean_token_accuracy": 0.21497241854667665,
|
|
"num_tokens": 49709958.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.0209558486938475,
|
|
"epoch": 2.1197141155449675,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000455991353306017,
|
|
"loss": 4.6924,
|
|
"mean_token_accuracy": 0.21707406193017958,
|
|
"num_tokens": 49723107.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 4.9154884815216064,
|
|
"epoch": 2.1203097081596187,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004559660347505228,
|
|
"loss": 4.5977,
|
|
"mean_token_accuracy": 0.22106953561306,
|
|
"num_tokens": 49738715.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 4.8822338581085205,
|
|
"epoch": 2.1209053007742704,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000455940709704071,
|
|
"loss": 4.618,
|
|
"mean_token_accuracy": 0.213177290558815,
|
|
"num_tokens": 49752244.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 4.820811223983765,
|
|
"epoch": 2.121500893388922,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045591537816757027,
|
|
"loss": 4.4908,
|
|
"mean_token_accuracy": 0.23285201489925383,
|
|
"num_tokens": 49766303.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 4.831678152084351,
|
|
"epoch": 2.1220964860035734,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045589004014192903,
|
|
"loss": 4.5055,
|
|
"mean_token_accuracy": 0.22618651539087295,
|
|
"num_tokens": 49782254.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 4.8865515232086185,
|
|
"epoch": 2.122692078618225,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045586469562805624,
|
|
"loss": 4.5886,
|
|
"mean_token_accuracy": 0.21967384964227676,
|
|
"num_tokens": 49797329.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 4.8719785690307615,
|
|
"epoch": 2.1232876712328768,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004558393446268608,
|
|
"loss": 4.5973,
|
|
"mean_token_accuracy": 0.22064937502145768,
|
|
"num_tokens": 49810732.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 4.87181978225708,
|
|
"epoch": 2.1238832638475285,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004558139871392521,
|
|
"loss": 4.6203,
|
|
"mean_token_accuracy": 0.21583431512117385,
|
|
"num_tokens": 49827098.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 4.873854255676269,
|
|
"epoch": 2.1244788564621797,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004557886231661396,
|
|
"loss": 4.5672,
|
|
"mean_token_accuracy": 0.2266459658741951,
|
|
"num_tokens": 49841563.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 4.872745990753174,
|
|
"epoch": 2.1250744490768314,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045576325270843326,
|
|
"loss": 4.6223,
|
|
"mean_token_accuracy": 0.2164354830980301,
|
|
"num_tokens": 49855890.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 4.8252410888671875,
|
|
"epoch": 2.125670041691483,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004557378757670429,
|
|
"loss": 4.5043,
|
|
"mean_token_accuracy": 0.23346010595560074,
|
|
"num_tokens": 49869146.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 4.93038911819458,
|
|
"epoch": 2.126265634306135,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004557124923428788,
|
|
"loss": 4.6149,
|
|
"mean_token_accuracy": 0.21685046553611756,
|
|
"num_tokens": 49882940.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 4.954266929626465,
|
|
"epoch": 2.126861226920786,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004556871024368514,
|
|
"loss": 4.6468,
|
|
"mean_token_accuracy": 0.21458294987678528,
|
|
"num_tokens": 49897588.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 4.818872928619385,
|
|
"epoch": 2.1274568195354377,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045566170604987145,
|
|
"loss": 4.5227,
|
|
"mean_token_accuracy": 0.22145656794309615,
|
|
"num_tokens": 49910848.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 4.848589515686035,
|
|
"epoch": 2.1280524121500894,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004556363031828498,
|
|
"loss": 4.6155,
|
|
"mean_token_accuracy": 0.2155602067708969,
|
|
"num_tokens": 49926178.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 4.933983898162841,
|
|
"epoch": 2.1286480047647407,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045561089383669776,
|
|
"loss": 4.5882,
|
|
"mean_token_accuracy": 0.22771768867969513,
|
|
"num_tokens": 49940774.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 4.855501174926758,
|
|
"epoch": 2.1292435973793924,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004555854780123265,
|
|
"loss": 4.5242,
|
|
"mean_token_accuracy": 0.22387197017669677,
|
|
"num_tokens": 49954573.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 4.933948087692261,
|
|
"epoch": 2.129839189994044,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004555600557106477,
|
|
"loss": 4.6625,
|
|
"mean_token_accuracy": 0.21802439242601396,
|
|
"num_tokens": 49967087.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 4.873450088500976,
|
|
"epoch": 2.130434782608696,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004555346269325734,
|
|
"loss": 4.5808,
|
|
"mean_token_accuracy": 0.22576793134212494,
|
|
"num_tokens": 49979147.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 4.8766992568969725,
|
|
"epoch": 2.131030375223347,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045550919167901553,
|
|
"loss": 4.6661,
|
|
"mean_token_accuracy": 0.22213581204414368,
|
|
"num_tokens": 49991389.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 4.889266872406006,
|
|
"epoch": 2.1316259678379987,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004554837499508864,
|
|
"loss": 4.5371,
|
|
"mean_token_accuracy": 0.22498800456523896,
|
|
"num_tokens": 50004803.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 4.8984095573425295,
|
|
"epoch": 2.1322215604526504,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004554583017490987,
|
|
"loss": 4.6925,
|
|
"mean_token_accuracy": 0.220061856508255,
|
|
"num_tokens": 50018012.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.0727112770080565,
|
|
"epoch": 2.132817153067302,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045543284707456514,
|
|
"loss": 4.7814,
|
|
"mean_token_accuracy": 0.21423722058534622,
|
|
"num_tokens": 50033246.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 4.881172847747803,
|
|
"epoch": 2.1334127456819534,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004554073859281986,
|
|
"loss": 4.5972,
|
|
"mean_token_accuracy": 0.214624260365963,
|
|
"num_tokens": 50046392.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 4.918669939041138,
|
|
"epoch": 2.134008338296605,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004553819183109125,
|
|
"loss": 4.6721,
|
|
"mean_token_accuracy": 0.21458762735128403,
|
|
"num_tokens": 50059342.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 4.918173217773438,
|
|
"epoch": 2.1346039309112568,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045535644422362026,
|
|
"loss": 4.6187,
|
|
"mean_token_accuracy": 0.21747925132513046,
|
|
"num_tokens": 50072787.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 4.795125150680542,
|
|
"epoch": 2.1351995235259085,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045533096366723563,
|
|
"loss": 4.5753,
|
|
"mean_token_accuracy": 0.2302174374461174,
|
|
"num_tokens": 50085305.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 4.933188152313233,
|
|
"epoch": 2.1357951161405597,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004553054766426725,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.2168698012828827,
|
|
"num_tokens": 50100974.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 4.907499027252197,
|
|
"epoch": 2.1363907087552114,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045527998315084513,
|
|
"loss": 4.6118,
|
|
"mean_token_accuracy": 0.22565249353647232,
|
|
"num_tokens": 50113752.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 4.876925086975097,
|
|
"epoch": 2.136986301369863,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004552544831926679,
|
|
"loss": 4.58,
|
|
"mean_token_accuracy": 0.22381683737039565,
|
|
"num_tokens": 50129337.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 4.879839515686035,
|
|
"epoch": 2.137581893984515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045522897676905535,
|
|
"loss": 4.5862,
|
|
"mean_token_accuracy": 0.2199673742055893,
|
|
"num_tokens": 50143268.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 4.916433429718017,
|
|
"epoch": 2.138177486599166,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004552034638809225,
|
|
"loss": 4.6184,
|
|
"mean_token_accuracy": 0.21318778097629548,
|
|
"num_tokens": 50158669.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 4.878197193145752,
|
|
"epoch": 2.1387730792138178,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004551779445291843,
|
|
"loss": 4.6218,
|
|
"mean_token_accuracy": 0.2163745015859604,
|
|
"num_tokens": 50173191.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 4.858408737182617,
|
|
"epoch": 2.1393686718284695,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045515241871475634,
|
|
"loss": 4.5106,
|
|
"mean_token_accuracy": 0.22571465969085694,
|
|
"num_tokens": 50188527.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 4.933630132675171,
|
|
"epoch": 2.1399642644431207,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004551268864385539,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.20517706423997878,
|
|
"num_tokens": 50202311.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 4.993191528320312,
|
|
"epoch": 2.1405598570577724,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000455101347701493,
|
|
"loss": 4.6946,
|
|
"mean_token_accuracy": 0.2178216338157654,
|
|
"num_tokens": 50217830.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 4.929560852050781,
|
|
"epoch": 2.141155449672424,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045507580250448955,
|
|
"loss": 4.5754,
|
|
"mean_token_accuracy": 0.2222967967391014,
|
|
"num_tokens": 50230464.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 4.8195538997650145,
|
|
"epoch": 2.141751042287076,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004550502508484598,
|
|
"loss": 4.5697,
|
|
"mean_token_accuracy": 0.22259098738431932,
|
|
"num_tokens": 50247201.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 4.860628414154053,
|
|
"epoch": 2.142346634901727,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004550246927343203,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.22118872851133348,
|
|
"num_tokens": 50260618.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 4.904287815093994,
|
|
"epoch": 2.1429422275163788,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004549991281629879,
|
|
"loss": 4.6416,
|
|
"mean_token_accuracy": 0.21871401220560074,
|
|
"num_tokens": 50273529.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 4.91530327796936,
|
|
"epoch": 2.1435378201310304,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004549735571353793,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.21364240497350692,
|
|
"num_tokens": 50287927.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 4.904927825927734,
|
|
"epoch": 2.144133412745682,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004549479796524119,
|
|
"loss": 4.5784,
|
|
"mean_token_accuracy": 0.2300340011715889,
|
|
"num_tokens": 50301318.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 2.144133412745682,
|
|
"eval_entropy": 4.72315327097256,
|
|
"eval_loss": 4.702234745025635,
|
|
"eval_mean_token_accuracy": 0.2269115158429714,
|
|
"eval_num_tokens": 50301318.0,
|
|
"eval_runtime": 24.3138,
|
|
"eval_samples_per_second": 1049.323,
|
|
"eval_steps_per_second": 131.201,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 4.925904369354248,
|
|
"epoch": 2.1447290053603334,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045492239571500305,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.2232791006565094,
|
|
"num_tokens": 50315160.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 4.898769330978394,
|
|
"epoch": 2.145324597974985,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004548968053240703,
|
|
"loss": 4.6746,
|
|
"mean_token_accuracy": 0.21330659538507463,
|
|
"num_tokens": 50330335.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 4.840593099594116,
|
|
"epoch": 2.145920190589637,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045487120848053175,
|
|
"loss": 4.5836,
|
|
"mean_token_accuracy": 0.2215599462389946,
|
|
"num_tokens": 50345693.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 4.9298101425170895,
|
|
"epoch": 2.146515783204288,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004548456051853053,
|
|
"loss": 4.5911,
|
|
"mean_token_accuracy": 0.22396050095558168,
|
|
"num_tokens": 50359261.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 4.925558233261109,
|
|
"epoch": 2.1471113758189397,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004548199954393095,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.21662145107984543,
|
|
"num_tokens": 50373729.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 4.947620248794555,
|
|
"epoch": 2.1477069684335914,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045479437924346276,
|
|
"loss": 4.6276,
|
|
"mean_token_accuracy": 0.22168825566768646,
|
|
"num_tokens": 50387316.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 4.949755239486694,
|
|
"epoch": 2.148302561048243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004547687565986841,
|
|
"loss": 4.6552,
|
|
"mean_token_accuracy": 0.22011319696903228,
|
|
"num_tokens": 50401148.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 4.884626150131226,
|
|
"epoch": 2.1488981536628944,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045474312750589226,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.22255406230688096,
|
|
"num_tokens": 50415852.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 4.8708741664886475,
|
|
"epoch": 2.149493746277546,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045471749196600677,
|
|
"loss": 4.567,
|
|
"mean_token_accuracy": 0.2272578239440918,
|
|
"num_tokens": 50429634.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 4.867157030105591,
|
|
"epoch": 2.1500893388921978,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045469184997994706,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.2243654325604439,
|
|
"num_tokens": 50445885.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 4.911463212966919,
|
|
"epoch": 2.1506849315068495,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045466620154863276,
|
|
"loss": 4.6104,
|
|
"mean_token_accuracy": 0.22835520505905152,
|
|
"num_tokens": 50459914.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 4.850181770324707,
|
|
"epoch": 2.1512805241215007,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000454640546672984,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.22759827673435212,
|
|
"num_tokens": 50473023.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 4.921176195144653,
|
|
"epoch": 2.1518761167361524,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004546148853539209,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.21943851113319396,
|
|
"num_tokens": 50487900.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 4.898761367797851,
|
|
"epoch": 2.152471709350804,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00045458921759236387,
|
|
"loss": 4.6089,
|
|
"mean_token_accuracy": 0.22389837205410004,
|
|
"num_tokens": 50502757.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.0134530544281,
|
|
"epoch": 2.153067301965456,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004545635433892337,
|
|
"loss": 4.6748,
|
|
"mean_token_accuracy": 0.21584005802869796,
|
|
"num_tokens": 50518636.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 4.971686887741089,
|
|
"epoch": 2.153662894580107,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045453786274545106,
|
|
"loss": 4.7238,
|
|
"mean_token_accuracy": 0.21320606470108033,
|
|
"num_tokens": 50532210.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 4.865463209152222,
|
|
"epoch": 2.1542584871947588,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045451217566193727,
|
|
"loss": 4.5577,
|
|
"mean_token_accuracy": 0.23278677761554717,
|
|
"num_tokens": 50545366.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 4.974821662902832,
|
|
"epoch": 2.1548540798094105,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004544864821396136,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.2122950479388237,
|
|
"num_tokens": 50560750.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 4.914874267578125,
|
|
"epoch": 2.155449672424062,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045446078217940155,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.2332109183073044,
|
|
"num_tokens": 50575529.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 4.91011004447937,
|
|
"epoch": 2.1560452650387134,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045443507578222316,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.22627847492694855,
|
|
"num_tokens": 50587989.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 4.851480484008789,
|
|
"epoch": 2.156640857653365,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045440936294900025,
|
|
"loss": 4.5218,
|
|
"mean_token_accuracy": 0.2287736192345619,
|
|
"num_tokens": 50600656.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 4.758456087112426,
|
|
"epoch": 2.157236450268017,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045438364368065526,
|
|
"loss": 4.4593,
|
|
"mean_token_accuracy": 0.23919077962636948,
|
|
"num_tokens": 50613939.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 4.906717109680176,
|
|
"epoch": 2.157832042882668,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004543579179781106,
|
|
"loss": 4.5795,
|
|
"mean_token_accuracy": 0.22553421109914779,
|
|
"num_tokens": 50627458.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 4.913496494293213,
|
|
"epoch": 2.1584276354973198,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045433218584228904,
|
|
"loss": 4.5741,
|
|
"mean_token_accuracy": 0.22698099464178084,
|
|
"num_tokens": 50642433.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 4.800421571731567,
|
|
"epoch": 2.1590232281119714,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004543064472741136,
|
|
"loss": 4.5111,
|
|
"mean_token_accuracy": 0.2278323397040367,
|
|
"num_tokens": 50656708.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 4.845487070083618,
|
|
"epoch": 2.159618820726623,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004542807022745073,
|
|
"loss": 4.61,
|
|
"mean_token_accuracy": 0.22641967833042145,
|
|
"num_tokens": 50670404.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 4.92844967842102,
|
|
"epoch": 2.1602144133412744,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004542549508443938,
|
|
"loss": 4.5921,
|
|
"mean_token_accuracy": 0.22149410098791122,
|
|
"num_tokens": 50684479.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 4.883677768707275,
|
|
"epoch": 2.160810005955926,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045422919298469664,
|
|
"loss": 4.5562,
|
|
"mean_token_accuracy": 0.22581265568733216,
|
|
"num_tokens": 50698958.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 4.85932879447937,
|
|
"epoch": 2.161405598570578,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004542034286963398,
|
|
"loss": 4.6236,
|
|
"mean_token_accuracy": 0.2233946904540062,
|
|
"num_tokens": 50711468.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 4.9287200450897215,
|
|
"epoch": 2.1620011911852295,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045417765798024716,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.21532327234745025,
|
|
"num_tokens": 50725864.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 4.952431917190552,
|
|
"epoch": 2.1625967837998807,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045415188083734346,
|
|
"loss": 4.6689,
|
|
"mean_token_accuracy": 0.2082477793097496,
|
|
"num_tokens": 50740504.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 4.813052988052368,
|
|
"epoch": 2.1631923764145324,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000454126097268553,
|
|
"loss": 4.5196,
|
|
"mean_token_accuracy": 0.2330220013856888,
|
|
"num_tokens": 50752846.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 4.9022132396698,
|
|
"epoch": 2.163787969029184,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045410030727480063,
|
|
"loss": 4.6453,
|
|
"mean_token_accuracy": 0.22109646946191788,
|
|
"num_tokens": 50767643.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 4.896021318435669,
|
|
"epoch": 2.1643835616438354,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045407451085701154,
|
|
"loss": 4.6371,
|
|
"mean_token_accuracy": 0.2255001336336136,
|
|
"num_tokens": 50780639.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 4.891604089736939,
|
|
"epoch": 2.164979154258487,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004540487080161108,
|
|
"loss": 4.6616,
|
|
"mean_token_accuracy": 0.21921190321445466,
|
|
"num_tokens": 50795597.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 4.949265813827514,
|
|
"epoch": 2.165574746873139,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045402289875302404,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.21557986736297607,
|
|
"num_tokens": 50810709.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 4.972989463806153,
|
|
"epoch": 2.1661703394877905,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000453997083068677,
|
|
"loss": 4.6126,
|
|
"mean_token_accuracy": 0.21684758961200715,
|
|
"num_tokens": 50824952.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 4.869951009750366,
|
|
"epoch": 2.1667659321024417,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004539712609639956,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.23087598234415055,
|
|
"num_tokens": 50838133.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 4.894849061965942,
|
|
"epoch": 2.1673615247170934,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004539454324399061,
|
|
"loss": 4.5824,
|
|
"mean_token_accuracy": 0.21738464683294295,
|
|
"num_tokens": 50853006.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 4.957299900054932,
|
|
"epoch": 2.167957117331745,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004539195974973348,
|
|
"loss": 4.6791,
|
|
"mean_token_accuracy": 0.21569168269634248,
|
|
"num_tokens": 50867484.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 4.910736703872681,
|
|
"epoch": 2.168552709946397,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004538937561372086,
|
|
"loss": 4.5725,
|
|
"mean_token_accuracy": 0.2290575161576271,
|
|
"num_tokens": 50881323.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 4.875525999069214,
|
|
"epoch": 2.169148302561048,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045386790836045407,
|
|
"loss": 4.5925,
|
|
"mean_token_accuracy": 0.2204459235072136,
|
|
"num_tokens": 50894411.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 4.861393594741822,
|
|
"epoch": 2.1697438951756998,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004538420541679986,
|
|
"loss": 4.6335,
|
|
"mean_token_accuracy": 0.21975788325071335,
|
|
"num_tokens": 50909344.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 4.8923522472381595,
|
|
"epoch": 2.1703394877903515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004538161935607693,
|
|
"loss": 4.5827,
|
|
"mean_token_accuracy": 0.22521060556173325,
|
|
"num_tokens": 50923610.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 4.961860942840576,
|
|
"epoch": 2.170935080405003,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004537903265396939,
|
|
"loss": 4.652,
|
|
"mean_token_accuracy": 0.22325101792812346,
|
|
"num_tokens": 50938157.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 4.9434455871582035,
|
|
"epoch": 2.1715306730196544,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004537644531057003,
|
|
"loss": 4.7378,
|
|
"mean_token_accuracy": 0.21322524547576904,
|
|
"num_tokens": 50953983.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 4.894415760040284,
|
|
"epoch": 2.172126265634306,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045373857325971636,
|
|
"loss": 4.5609,
|
|
"mean_token_accuracy": 0.2241925209760666,
|
|
"num_tokens": 50967630.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 4.890721464157105,
|
|
"epoch": 2.172721858248958,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045371268700267035,
|
|
"loss": 4.6395,
|
|
"mean_token_accuracy": 0.22146900445222856,
|
|
"num_tokens": 50982437.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 4.849739646911621,
|
|
"epoch": 2.1733174508636095,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004536867943354909,
|
|
"loss": 4.5274,
|
|
"mean_token_accuracy": 0.2361708700656891,
|
|
"num_tokens": 50996549.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 4.845167016983032,
|
|
"epoch": 2.1739130434782608,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045366089525910664,
|
|
"loss": 4.5758,
|
|
"mean_token_accuracy": 0.22217752784490585,
|
|
"num_tokens": 51012182.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 4.949145984649658,
|
|
"epoch": 2.1745086360929125,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045363498977444655,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.2135122761130333,
|
|
"num_tokens": 51026115.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 4.919349718093872,
|
|
"epoch": 2.175104228707564,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004536090778824398,
|
|
"loss": 4.6657,
|
|
"mean_token_accuracy": 0.2169966146349907,
|
|
"num_tokens": 51039685.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 4.872767591476441,
|
|
"epoch": 2.1756998213222154,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045358315958401584,
|
|
"loss": 4.569,
|
|
"mean_token_accuracy": 0.2280321955680847,
|
|
"num_tokens": 51052613.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 4.938307189941407,
|
|
"epoch": 2.176295413936867,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045355723488010435,
|
|
"loss": 4.636,
|
|
"mean_token_accuracy": 0.22287812680006028,
|
|
"num_tokens": 51066941.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 4.9702043533325195,
|
|
"epoch": 2.176891006551519,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045353130377163514,
|
|
"loss": 4.6546,
|
|
"mean_token_accuracy": 0.218821182847023,
|
|
"num_tokens": 51081495.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 4.893966102600098,
|
|
"epoch": 2.1774865991661705,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004535053662595383,
|
|
"loss": 4.6827,
|
|
"mean_token_accuracy": 0.21302675902843476,
|
|
"num_tokens": 51096030.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 4.814019250869751,
|
|
"epoch": 2.1780821917808217,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045347942234474426,
|
|
"loss": 4.5889,
|
|
"mean_token_accuracy": 0.2282996580004692,
|
|
"num_tokens": 51109183.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 4.85801134109497,
|
|
"epoch": 2.1786777843954734,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004534534720281835,
|
|
"loss": 4.5632,
|
|
"mean_token_accuracy": 0.22431123703718187,
|
|
"num_tokens": 51122882.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 4.921738195419311,
|
|
"epoch": 2.179273377010125,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004534275153107868,
|
|
"loss": 4.6542,
|
|
"mean_token_accuracy": 0.22240448743104935,
|
|
"num_tokens": 51136593.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 4.917095422744751,
|
|
"epoch": 2.179868969624777,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045340155219348536,
|
|
"loss": 4.6435,
|
|
"mean_token_accuracy": 0.22064619809389113,
|
|
"num_tokens": 51153092.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 4.878380870819091,
|
|
"epoch": 2.180464562239428,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004533755826772102,
|
|
"loss": 4.5765,
|
|
"mean_token_accuracy": 0.22271122336387633,
|
|
"num_tokens": 51167191.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 4.886454820632935,
|
|
"epoch": 2.18106015485408,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004533496067628929,
|
|
"loss": 4.6209,
|
|
"mean_token_accuracy": 0.22519396394491195,
|
|
"num_tokens": 51180310.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 4.880496644973755,
|
|
"epoch": 2.1816557474687315,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004533236244514652,
|
|
"loss": 4.6117,
|
|
"mean_token_accuracy": 0.22133441716432573,
|
|
"num_tokens": 51195249.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 4.8571068286895756,
|
|
"epoch": 2.182251340083383,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045329763574385905,
|
|
"loss": 4.5017,
|
|
"mean_token_accuracy": 0.22661753743886948,
|
|
"num_tokens": 51207651.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 4.858247184753418,
|
|
"epoch": 2.1828469326980344,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045327164064100654,
|
|
"loss": 4.5847,
|
|
"mean_token_accuracy": 0.22845280021429062,
|
|
"num_tokens": 51219106.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 4.891799354553223,
|
|
"epoch": 2.183442525312686,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045324563914384024,
|
|
"loss": 4.6124,
|
|
"mean_token_accuracy": 0.21713705509901046,
|
|
"num_tokens": 51234509.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 4.891693258285523,
|
|
"epoch": 2.184038117927338,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004532196312532926,
|
|
"loss": 4.5511,
|
|
"mean_token_accuracy": 0.21926608979701995,
|
|
"num_tokens": 51248284.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 4.87657527923584,
|
|
"epoch": 2.184633710541989,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004531936169702966,
|
|
"loss": 4.6319,
|
|
"mean_token_accuracy": 0.22170630246400833,
|
|
"num_tokens": 51260433.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 4.866620302200317,
|
|
"epoch": 2.1852293031566408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004531675962957853,
|
|
"loss": 4.6102,
|
|
"mean_token_accuracy": 0.21842013895511628,
|
|
"num_tokens": 51272196.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 4.9552319049835205,
|
|
"epoch": 2.1858248957712925,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004531415692306919,
|
|
"loss": 4.6821,
|
|
"mean_token_accuracy": 0.21601322740316392,
|
|
"num_tokens": 51284883.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 4.842431497573853,
|
|
"epoch": 2.186420488385944,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004531155357759501,
|
|
"loss": 4.5144,
|
|
"mean_token_accuracy": 0.22667134404182435,
|
|
"num_tokens": 51299547.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 4.7717667579650875,
|
|
"epoch": 2.1870160810005954,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004530894959324937,
|
|
"loss": 4.4852,
|
|
"mean_token_accuracy": 0.2343051627278328,
|
|
"num_tokens": 51313385.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 4.91908016204834,
|
|
"epoch": 2.187611673615247,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045306344970125656,
|
|
"loss": 4.6101,
|
|
"mean_token_accuracy": 0.22771822214126586,
|
|
"num_tokens": 51325605.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 4.813216352462769,
|
|
"epoch": 2.188207266229899,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045303739708317303,
|
|
"loss": 4.5346,
|
|
"mean_token_accuracy": 0.22464994043111802,
|
|
"num_tokens": 51338977.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 4.943297624588013,
|
|
"epoch": 2.1888028588445505,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004530113380791775,
|
|
"loss": 4.6756,
|
|
"mean_token_accuracy": 0.21288824081420898,
|
|
"num_tokens": 51352536.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 4.850827741622925,
|
|
"epoch": 2.1893984514592018,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004529852726902047,
|
|
"loss": 4.5692,
|
|
"mean_token_accuracy": 0.22261046767234802,
|
|
"num_tokens": 51366536.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 4.80405626296997,
|
|
"epoch": 2.1899940440738535,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004529592009171896,
|
|
"loss": 4.5218,
|
|
"mean_token_accuracy": 0.2312697559595108,
|
|
"num_tokens": 51380219.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 4.876440000534058,
|
|
"epoch": 2.190589636688505,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045293312276106735,
|
|
"loss": 4.6379,
|
|
"mean_token_accuracy": 0.22242172062397003,
|
|
"num_tokens": 51394644.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 4.869099760055542,
|
|
"epoch": 2.191185229303157,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004529070382227732,
|
|
"loss": 4.5072,
|
|
"mean_token_accuracy": 0.23427354246377946,
|
|
"num_tokens": 51408850.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 4.878261089324951,
|
|
"epoch": 2.191780821917808,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004528809473032428,
|
|
"loss": 4.628,
|
|
"mean_token_accuracy": 0.22632297575473787,
|
|
"num_tokens": 51423771.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 4.788392543792725,
|
|
"epoch": 2.19237641453246,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045285485000341215,
|
|
"loss": 4.5043,
|
|
"mean_token_accuracy": 0.22795200794935228,
|
|
"num_tokens": 51439288.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 4.868876361846924,
|
|
"epoch": 2.1929720071471115,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045282874632421717,
|
|
"loss": 4.6381,
|
|
"mean_token_accuracy": 0.22153555899858474,
|
|
"num_tokens": 51454394.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 4.899154710769653,
|
|
"epoch": 2.1935675997617627,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004528026362665942,
|
|
"loss": 4.627,
|
|
"mean_token_accuracy": 0.21682192832231523,
|
|
"num_tokens": 51468604.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 4.888340091705322,
|
|
"epoch": 2.1941631923764144,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004527765198314798,
|
|
"loss": 4.5952,
|
|
"mean_token_accuracy": 0.21905597746372224,
|
|
"num_tokens": 51482788.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 4.882995891571045,
|
|
"epoch": 2.194758784991066,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004527503970198105,
|
|
"loss": 4.561,
|
|
"mean_token_accuracy": 0.22720564752817154,
|
|
"num_tokens": 51499024.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 4.84158091545105,
|
|
"epoch": 2.195354377605718,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004527242678325236,
|
|
"loss": 4.5592,
|
|
"mean_token_accuracy": 0.2169646292924881,
|
|
"num_tokens": 51512951.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 4.795514154434204,
|
|
"epoch": 2.195949970220369,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004526981322705562,
|
|
"loss": 4.4906,
|
|
"mean_token_accuracy": 0.23780286610126494,
|
|
"num_tokens": 51526530.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 4.962154722213745,
|
|
"epoch": 2.196545562835021,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004526719903348457,
|
|
"loss": 4.6786,
|
|
"mean_token_accuracy": 0.21560291796922684,
|
|
"num_tokens": 51540663.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 4.832817459106446,
|
|
"epoch": 2.1971411554496725,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004526458420263297,
|
|
"loss": 4.541,
|
|
"mean_token_accuracy": 0.2292060896754265,
|
|
"num_tokens": 51554275.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 4.892115688323974,
|
|
"epoch": 2.197736748064324,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045261968734594624,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.22025662064552307,
|
|
"num_tokens": 51569148.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 4.918287849426269,
|
|
"epoch": 2.1983323406789754,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045259352629463336,
|
|
"loss": 4.5474,
|
|
"mean_token_accuracy": 0.22954947501420975,
|
|
"num_tokens": 51582391.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 4.825666236877441,
|
|
"epoch": 2.198927933293627,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004525673588733295,
|
|
"loss": 4.5717,
|
|
"mean_token_accuracy": 0.23235593140125274,
|
|
"num_tokens": 51598635.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 4.910577774047852,
|
|
"epoch": 2.199523525908279,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004525411850829732,
|
|
"loss": 4.6502,
|
|
"mean_token_accuracy": 0.22091065794229509,
|
|
"num_tokens": 51613169.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 4.930616188049316,
|
|
"epoch": 2.2001191185229305,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004525150049245032,
|
|
"loss": 4.6085,
|
|
"mean_token_accuracy": 0.21989351511001587,
|
|
"num_tokens": 51626675.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 4.887199735641479,
|
|
"epoch": 2.2007147111375818,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004524888183988586,
|
|
"loss": 4.5783,
|
|
"mean_token_accuracy": 0.22333298474550248,
|
|
"num_tokens": 51640022.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 4.904047679901123,
|
|
"epoch": 2.2013103037522335,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004524626255069786,
|
|
"loss": 4.6972,
|
|
"mean_token_accuracy": 0.21705981343984604,
|
|
"num_tokens": 51655243.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 4.923373556137085,
|
|
"epoch": 2.201905896366885,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045243642624980283,
|
|
"loss": 4.6428,
|
|
"mean_token_accuracy": 0.21735652834177016,
|
|
"num_tokens": 51668978.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 4.901650714874267,
|
|
"epoch": 2.202501488981537,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004524102206282709,
|
|
"loss": 4.5509,
|
|
"mean_token_accuracy": 0.22793880999088287,
|
|
"num_tokens": 51683468.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 4.898276090621948,
|
|
"epoch": 2.203097081596188,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004523840086433229,
|
|
"loss": 4.5941,
|
|
"mean_token_accuracy": 0.22996940612792968,
|
|
"num_tokens": 51699123.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 4.905904912948609,
|
|
"epoch": 2.20369267421084,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045235779029589884,
|
|
"loss": 4.6095,
|
|
"mean_token_accuracy": 0.22228358536958695,
|
|
"num_tokens": 51712152.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 4.909775686264038,
|
|
"epoch": 2.2042882668254915,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045233156558693925,
|
|
"loss": 4.5963,
|
|
"mean_token_accuracy": 0.22381581962108613,
|
|
"num_tokens": 51726345.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 4.839901781082153,
|
|
"epoch": 2.2048838594401428,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004523053345173848,
|
|
"loss": 4.5047,
|
|
"mean_token_accuracy": 0.2346494287252426,
|
|
"num_tokens": 51740155.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 4.852051830291748,
|
|
"epoch": 2.2054794520547945,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045227909708817613,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.22215379476547242,
|
|
"num_tokens": 51753260.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 4.81865701675415,
|
|
"epoch": 2.206075044669446,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004522528533002545,
|
|
"loss": 4.5176,
|
|
"mean_token_accuracy": 0.2273777425289154,
|
|
"num_tokens": 51767367.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 4.875251007080078,
|
|
"epoch": 2.206670637284098,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045222660315456125,
|
|
"loss": 4.6148,
|
|
"mean_token_accuracy": 0.2280870109796524,
|
|
"num_tokens": 51780350.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 4.848286867141724,
|
|
"epoch": 2.207266229898749,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045220034665203795,
|
|
"loss": 4.6089,
|
|
"mean_token_accuracy": 0.2256951555609703,
|
|
"num_tokens": 51794395.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 4.832491159439087,
|
|
"epoch": 2.207861822513401,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045217408379362635,
|
|
"loss": 4.5636,
|
|
"mean_token_accuracy": 0.2293944850564003,
|
|
"num_tokens": 51808472.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 4.870798969268799,
|
|
"epoch": 2.2084574151280525,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045214781458026833,
|
|
"loss": 4.5059,
|
|
"mean_token_accuracy": 0.23506497889757155,
|
|
"num_tokens": 51821744.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 4.820613765716553,
|
|
"epoch": 2.209053007742704,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004521215390129063,
|
|
"loss": 4.4759,
|
|
"mean_token_accuracy": 0.23453143686056138,
|
|
"num_tokens": 51834695.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 4.8724133491516115,
|
|
"epoch": 2.2096486003573554,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045209525709248257,
|
|
"loss": 4.561,
|
|
"mean_token_accuracy": 0.22685424685478212,
|
|
"num_tokens": 51847676.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 4.9189149856567385,
|
|
"epoch": 2.210244192972007,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045206896881994,
|
|
"loss": 4.6734,
|
|
"mean_token_accuracy": 0.21513693779706955,
|
|
"num_tokens": 51861982.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 4.895841264724732,
|
|
"epoch": 2.210839785586659,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004520426741962213,
|
|
"loss": 4.5723,
|
|
"mean_token_accuracy": 0.22660140693187714,
|
|
"num_tokens": 51875671.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 4.889076519012451,
|
|
"epoch": 2.21143537820131,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045201637322226984,
|
|
"loss": 4.6109,
|
|
"mean_token_accuracy": 0.22076918482780455,
|
|
"num_tokens": 51889695.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 4.894184732437134,
|
|
"epoch": 2.212030970815962,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045199006589902884,
|
|
"loss": 4.6208,
|
|
"mean_token_accuracy": 0.22734468579292297,
|
|
"num_tokens": 51903390.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 4.895395755767822,
|
|
"epoch": 2.2126265634306135,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045196375222744195,
|
|
"loss": 4.6084,
|
|
"mean_token_accuracy": 0.2280483141541481,
|
|
"num_tokens": 51917010.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 4.965999603271484,
|
|
"epoch": 2.213222156045265,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000451937432208453,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.21737156212329864,
|
|
"num_tokens": 51931025.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 4.936785125732422,
|
|
"epoch": 2.2138177486599164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000451911105843006,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.22231511622667313,
|
|
"num_tokens": 51945135.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 4.849786758422852,
|
|
"epoch": 2.214413341274568,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045188477313204536,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.22850871384143828,
|
|
"num_tokens": 51959301.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 4.856707954406739,
|
|
"epoch": 2.21500893388922,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045185843407651537,
|
|
"loss": 4.5746,
|
|
"mean_token_accuracy": 0.2268698826432228,
|
|
"num_tokens": 51973213.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 4.90093994140625,
|
|
"epoch": 2.2156045265038715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045183208867736097,
|
|
"loss": 4.5368,
|
|
"mean_token_accuracy": 0.22786012291908264,
|
|
"num_tokens": 51988208.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 4.775592517852783,
|
|
"epoch": 2.2162001191185228,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045180573693552714,
|
|
"loss": 4.5432,
|
|
"mean_token_accuracy": 0.2202335149049759,
|
|
"num_tokens": 52002708.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 4.89037127494812,
|
|
"epoch": 2.2167957117331745,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045177937885195884,
|
|
"loss": 4.6517,
|
|
"mean_token_accuracy": 0.21864872425794601,
|
|
"num_tokens": 52017418.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 4.935370302200317,
|
|
"epoch": 2.217391304347826,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004517530144276018,
|
|
"loss": 4.6462,
|
|
"mean_token_accuracy": 0.21941731125116348,
|
|
"num_tokens": 52033228.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 4.952778053283692,
|
|
"epoch": 2.217986896962478,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004517266436634014,
|
|
"loss": 4.7357,
|
|
"mean_token_accuracy": 0.21381584405899048,
|
|
"num_tokens": 52046658.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 4.887267637252807,
|
|
"epoch": 2.218582489577129,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004517002665603037,
|
|
"loss": 4.5269,
|
|
"mean_token_accuracy": 0.23643930554389953,
|
|
"num_tokens": 52059844.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 4.8637375831604,
|
|
"epoch": 2.219178082191781,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004516738831192547,
|
|
"loss": 4.595,
|
|
"mean_token_accuracy": 0.22534732073545455,
|
|
"num_tokens": 52073462.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 4.912369346618652,
|
|
"epoch": 2.2197736748064325,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045164749334120074,
|
|
"loss": 4.6381,
|
|
"mean_token_accuracy": 0.21568874567747115,
|
|
"num_tokens": 52089109.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 4.897021389007568,
|
|
"epoch": 2.220369267421084,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004516210972270885,
|
|
"loss": 4.6122,
|
|
"mean_token_accuracy": 0.2236565962433815,
|
|
"num_tokens": 52101390.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 4.941034412384033,
|
|
"epoch": 2.2209648600357355,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045159469477786457,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.21520757675170898,
|
|
"num_tokens": 52115489.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 4.939573049545288,
|
|
"epoch": 2.221560452650387,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004515682859944762,
|
|
"loss": 4.6668,
|
|
"mean_token_accuracy": 0.2182663157582283,
|
|
"num_tokens": 52129425.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 4.914370203018189,
|
|
"epoch": 2.222156045265039,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004515418708778704,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.2099138855934143,
|
|
"num_tokens": 52143119.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 4.8839020252227785,
|
|
"epoch": 2.22275163787969,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004515154494289947,
|
|
"loss": 4.5772,
|
|
"mean_token_accuracy": 0.2230546459555626,
|
|
"num_tokens": 52158569.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 4.951153373718261,
|
|
"epoch": 2.223347230494342,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045148902164879686,
|
|
"loss": 4.6519,
|
|
"mean_token_accuracy": 0.2155141144990921,
|
|
"num_tokens": 52172141.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 4.933822917938232,
|
|
"epoch": 2.2239428231089935,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045146258753822475,
|
|
"loss": 4.655,
|
|
"mean_token_accuracy": 0.21175964623689653,
|
|
"num_tokens": 52185562.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 4.817530488967895,
|
|
"epoch": 2.224538415723645,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004514361470982266,
|
|
"loss": 4.509,
|
|
"mean_token_accuracy": 0.23163293153047562,
|
|
"num_tokens": 52199817.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.019377136230469,
|
|
"epoch": 2.2251340083382964,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045140970032975057,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.21300691664218901,
|
|
"num_tokens": 52214409.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.000562953948974,
|
|
"epoch": 2.225729600952948,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045138324723374565,
|
|
"loss": 4.6821,
|
|
"mean_token_accuracy": 0.21876849383115768,
|
|
"num_tokens": 52228365.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 4.838756036758423,
|
|
"epoch": 2.2263251935676,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045135678781116025,
|
|
"loss": 4.5753,
|
|
"mean_token_accuracy": 0.2250610038638115,
|
|
"num_tokens": 52240863.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 4.795404672622681,
|
|
"epoch": 2.2269207861822515,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045133032206294365,
|
|
"loss": 4.5395,
|
|
"mean_token_accuracy": 0.22542305588722228,
|
|
"num_tokens": 52255664.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 4.886259651184082,
|
|
"epoch": 2.227516378796903,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004513038499900451,
|
|
"loss": 4.4863,
|
|
"mean_token_accuracy": 0.23005890399217604,
|
|
"num_tokens": 52269246.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 4.838205146789551,
|
|
"epoch": 2.2281119714115545,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045127737159341406,
|
|
"loss": 4.6007,
|
|
"mean_token_accuracy": 0.22738759070634842,
|
|
"num_tokens": 52281797.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 4.94292049407959,
|
|
"epoch": 2.228707564026206,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004512508868740004,
|
|
"loss": 4.6122,
|
|
"mean_token_accuracy": 0.21352992951869965,
|
|
"num_tokens": 52297420.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 4.910936403274536,
|
|
"epoch": 2.2293031566408574,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000451224395832754,
|
|
"loss": 4.5838,
|
|
"mean_token_accuracy": 0.2248566195368767,
|
|
"num_tokens": 52311340.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 4.834734058380127,
|
|
"epoch": 2.229898749255509,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045119789847062496,
|
|
"loss": 4.5483,
|
|
"mean_token_accuracy": 0.2305615723133087,
|
|
"num_tokens": 52323476.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 4.874025630950928,
|
|
"epoch": 2.230494341870161,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045117139478856376,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.22436923384666443,
|
|
"num_tokens": 52336615.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 4.822576808929443,
|
|
"epoch": 2.2310899344848125,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004511448847875212,
|
|
"loss": 4.5038,
|
|
"mean_token_accuracy": 0.23274952918291092,
|
|
"num_tokens": 52349864.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 4.928309345245362,
|
|
"epoch": 2.2316855270994638,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045111836846844795,
|
|
"loss": 4.676,
|
|
"mean_token_accuracy": 0.22218642234802247,
|
|
"num_tokens": 52363966.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 4.894815349578858,
|
|
"epoch": 2.2322811197141155,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045109184583229514,
|
|
"loss": 4.577,
|
|
"mean_token_accuracy": 0.21763756424188613,
|
|
"num_tokens": 52380348.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 4.946410846710205,
|
|
"epoch": 2.232876712328767,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045106531688001415,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.22246210724115373,
|
|
"num_tokens": 52394647.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 4.882353115081787,
|
|
"epoch": 2.233472304943419,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004510387816125566,
|
|
"loss": 4.5535,
|
|
"mean_token_accuracy": 0.22797614336013794,
|
|
"num_tokens": 52407940.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 4.876865386962891,
|
|
"epoch": 2.23406789755807,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000451012240030874,
|
|
"loss": 4.6795,
|
|
"mean_token_accuracy": 0.21859637647867203,
|
|
"num_tokens": 52421515.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 4.912072372436524,
|
|
"epoch": 2.234663490172722,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004509856921359186,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.21734991371631623,
|
|
"num_tokens": 52436709.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 4.885613536834716,
|
|
"epoch": 2.2352590827873735,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045095913792864265,
|
|
"loss": 4.5751,
|
|
"mean_token_accuracy": 0.22227185666561128,
|
|
"num_tokens": 52450225.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 4.817924213409424,
|
|
"epoch": 2.235854675402025,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004509325774099984,
|
|
"loss": 4.5737,
|
|
"mean_token_accuracy": 0.22205118387937545,
|
|
"num_tokens": 52464915.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 4.893287897109985,
|
|
"epoch": 2.2364502680166765,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045090601058093874,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.22148955166339873,
|
|
"num_tokens": 52479246.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 4.949371576309204,
|
|
"epoch": 2.237045860631328,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004508794374424164,
|
|
"loss": 4.6335,
|
|
"mean_token_accuracy": 0.22232962101697923,
|
|
"num_tokens": 52492359.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 4.9395060539245605,
|
|
"epoch": 2.23764145324598,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004508528579953846,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.22726732194423677,
|
|
"num_tokens": 52506075.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 4.88307409286499,
|
|
"epoch": 2.2382370458606315,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004508262722407968,
|
|
"loss": 4.594,
|
|
"mean_token_accuracy": 0.2336644396185875,
|
|
"num_tokens": 52521294.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 4.892723941802979,
|
|
"epoch": 2.238832638475283,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045079968017960637,
|
|
"loss": 4.5669,
|
|
"mean_token_accuracy": 0.2197821021080017,
|
|
"num_tokens": 52534680.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 4.904057788848877,
|
|
"epoch": 2.2394282310899345,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045077308181276735,
|
|
"loss": 4.6153,
|
|
"mean_token_accuracy": 0.22432130724191665,
|
|
"num_tokens": 52548420.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 4.835416316986084,
|
|
"epoch": 2.240023823704586,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004507464771412336,
|
|
"loss": 4.5156,
|
|
"mean_token_accuracy": 0.23369423896074296,
|
|
"num_tokens": 52561882.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 4.823817300796509,
|
|
"epoch": 2.2406194163192374,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045071986616595946,
|
|
"loss": 4.5277,
|
|
"mean_token_accuracy": 0.23023440241813659,
|
|
"num_tokens": 52575355.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 4.853879642486572,
|
|
"epoch": 2.241215008933889,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045069324888789955,
|
|
"loss": 4.6379,
|
|
"mean_token_accuracy": 0.21590401828289033,
|
|
"num_tokens": 52591125.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 4.962028503417969,
|
|
"epoch": 2.241810601548541,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045066662530800835,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.21102410256862641,
|
|
"num_tokens": 52604160.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 4.886420106887817,
|
|
"epoch": 2.2424061941631925,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004506399954272409,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.23218764662742614,
|
|
"num_tokens": 52617697.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 4.833433723449707,
|
|
"epoch": 2.243001786777844,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045061335924655236,
|
|
"loss": 4.5442,
|
|
"mean_token_accuracy": 0.2290235072374344,
|
|
"num_tokens": 52630941.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.048589754104614,
|
|
"epoch": 2.2435973793924955,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004505867167668983,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.217400224506855,
|
|
"num_tokens": 52644699.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 4.876737833023071,
|
|
"epoch": 2.244192972007147,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004505600679892341,
|
|
"loss": 4.5469,
|
|
"mean_token_accuracy": 0.22655072808265686,
|
|
"num_tokens": 52658617.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 4.863532018661499,
|
|
"epoch": 2.244788564621799,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045053341291451565,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.21293003410100936,
|
|
"num_tokens": 52672978.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 4.905601501464844,
|
|
"epoch": 2.24538415723645,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045050675154369917,
|
|
"loss": 4.5798,
|
|
"mean_token_accuracy": 0.22223871648311616,
|
|
"num_tokens": 52685806.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 4.912188005447388,
|
|
"epoch": 2.245979749851102,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004504800838777408,
|
|
"loss": 4.6351,
|
|
"mean_token_accuracy": 0.23244604021310805,
|
|
"num_tokens": 52699947.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 4.812384986877442,
|
|
"epoch": 2.2465753424657535,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004504534099175972,
|
|
"loss": 4.4676,
|
|
"mean_token_accuracy": 0.23193777799606324,
|
|
"num_tokens": 52712273.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 4.903852319717407,
|
|
"epoch": 2.2471709350804048,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045042672966422506,
|
|
"loss": 4.5909,
|
|
"mean_token_accuracy": 0.22835203111171723,
|
|
"num_tokens": 52725579.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 4.9026100635528564,
|
|
"epoch": 2.2477665276950565,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004504000431185813,
|
|
"loss": 4.5968,
|
|
"mean_token_accuracy": 0.226632921397686,
|
|
"num_tokens": 52741598.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 4.941233444213867,
|
|
"epoch": 2.248362120309708,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045037335028162327,
|
|
"loss": 4.6199,
|
|
"mean_token_accuracy": 0.21702312529087067,
|
|
"num_tokens": 52755787.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 4.895678091049194,
|
|
"epoch": 2.24895771292436,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045034665115430817,
|
|
"loss": 4.6451,
|
|
"mean_token_accuracy": 0.21714916229248046,
|
|
"num_tokens": 52767594.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 4.9764673709869385,
|
|
"epoch": 2.249553305539011,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004503199457375939,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.2164816752076149,
|
|
"num_tokens": 52783069.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 4.841197490692139,
|
|
"epoch": 2.250148898153663,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045029323403243817,
|
|
"loss": 4.5273,
|
|
"mean_token_accuracy": 0.22883228063583375,
|
|
"num_tokens": 52796456.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 4.898714160919189,
|
|
"epoch": 2.2507444907683145,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004502665160397991,
|
|
"loss": 4.6293,
|
|
"mean_token_accuracy": 0.22800116539001464,
|
|
"num_tokens": 52809224.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 4.909593105316162,
|
|
"epoch": 2.251340083382966,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004502397917606352,
|
|
"loss": 4.6545,
|
|
"mean_token_accuracy": 0.22007170021533967,
|
|
"num_tokens": 52821943.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.009417104721069,
|
|
"epoch": 2.2519356759976175,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004502130611959048,
|
|
"loss": 4.6911,
|
|
"mean_token_accuracy": 0.21293673664331436,
|
|
"num_tokens": 52835662.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 4.924415063858032,
|
|
"epoch": 2.252531268612269,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004501863243465668,
|
|
"loss": 4.6703,
|
|
"mean_token_accuracy": 0.21197704523801802,
|
|
"num_tokens": 52849087.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 4.880771923065185,
|
|
"epoch": 2.253126861226921,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045015958121358014,
|
|
"loss": 4.577,
|
|
"mean_token_accuracy": 0.22310164868831633,
|
|
"num_tokens": 52863714.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 4.8940177917480465,
|
|
"epoch": 2.2537224538415725,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004501328317979041,
|
|
"loss": 4.4899,
|
|
"mean_token_accuracy": 0.2307764247059822,
|
|
"num_tokens": 52876319.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 4.90675687789917,
|
|
"epoch": 2.254318046456224,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004501060761004982,
|
|
"loss": 4.7333,
|
|
"mean_token_accuracy": 0.21187163442373275,
|
|
"num_tokens": 52891005.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 4.930729484558105,
|
|
"epoch": 2.2549136390708755,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000450079314122322,
|
|
"loss": 4.5799,
|
|
"mean_token_accuracy": 0.22955282032489777,
|
|
"num_tokens": 52904780.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 4.863580799102783,
|
|
"epoch": 2.255509231685527,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004500525458643355,
|
|
"loss": 4.5318,
|
|
"mean_token_accuracy": 0.22847444117069243,
|
|
"num_tokens": 52917886.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 4.863152074813843,
|
|
"epoch": 2.256104824300179,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004500257713274988,
|
|
"loss": 4.6117,
|
|
"mean_token_accuracy": 0.22896872758865355,
|
|
"num_tokens": 52931450.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.0037580013275145,
|
|
"epoch": 2.25670041691483,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044999899051277213,
|
|
"loss": 4.6469,
|
|
"mean_token_accuracy": 0.2212200343608856,
|
|
"num_tokens": 52945434.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 4.920922708511353,
|
|
"epoch": 2.257296009529482,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044997220342111636,
|
|
"loss": 4.6489,
|
|
"mean_token_accuracy": 0.21570017635822297,
|
|
"num_tokens": 52959409.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 4.904844760894775,
|
|
"epoch": 2.2578916021441335,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044994541005349207,
|
|
"loss": 4.6264,
|
|
"mean_token_accuracy": 0.22609174251556396,
|
|
"num_tokens": 52972249.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 4.947845554351806,
|
|
"epoch": 2.258487194758785,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004499186104108604,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.21005346924066542,
|
|
"num_tokens": 52986865.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 4.853645086288452,
|
|
"epoch": 2.2590827873734365,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044989180449418254,
|
|
"loss": 4.5497,
|
|
"mean_token_accuracy": 0.225113408267498,
|
|
"num_tokens": 53000096.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 4.918147706985474,
|
|
"epoch": 2.259678379988088,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044986499230442,
|
|
"loss": 4.6571,
|
|
"mean_token_accuracy": 0.220538729429245,
|
|
"num_tokens": 53014136.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 4.8224772930145265,
|
|
"epoch": 2.26027397260274,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004498381738425346,
|
|
"loss": 4.5105,
|
|
"mean_token_accuracy": 0.23064762651920317,
|
|
"num_tokens": 53028801.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 4.921499967575073,
|
|
"epoch": 2.260869565217391,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044981134910948806,
|
|
"loss": 4.6607,
|
|
"mean_token_accuracy": 0.2246076136827469,
|
|
"num_tokens": 53042087.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 4.92157621383667,
|
|
"epoch": 2.261465157832043,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044978451810624264,
|
|
"loss": 4.6256,
|
|
"mean_token_accuracy": 0.22127630114555358,
|
|
"num_tokens": 53058372.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 4.906217575073242,
|
|
"epoch": 2.2620607504466945,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044975768083376085,
|
|
"loss": 4.6446,
|
|
"mean_token_accuracy": 0.21524120569229127,
|
|
"num_tokens": 53075299.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 4.9697013854980465,
|
|
"epoch": 2.262656343061346,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044973083729300513,
|
|
"loss": 4.6524,
|
|
"mean_token_accuracy": 0.21391669064760208,
|
|
"num_tokens": 53090702.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 4.954380464553833,
|
|
"epoch": 2.2632519356759975,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044970398748493836,
|
|
"loss": 4.6424,
|
|
"mean_token_accuracy": 0.22266964465379716,
|
|
"num_tokens": 53104709.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 4.8043286323547365,
|
|
"epoch": 2.263847528290649,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00044967713141052363,
|
|
"loss": 4.5969,
|
|
"mean_token_accuracy": 0.2241886854171753,
|
|
"num_tokens": 53119191.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 4.845853805541992,
|
|
"epoch": 2.264443120905301,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004496502690707242,
|
|
"loss": 4.5727,
|
|
"mean_token_accuracy": 0.22606610357761384,
|
|
"num_tokens": 53134424.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 4.919808340072632,
|
|
"epoch": 2.265038713519952,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044962340046650356,
|
|
"loss": 4.5552,
|
|
"mean_token_accuracy": 0.2230786129832268,
|
|
"num_tokens": 53148233.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 4.80731086730957,
|
|
"epoch": 2.265634306134604,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004495965255988255,
|
|
"loss": 4.4714,
|
|
"mean_token_accuracy": 0.22769751995801926,
|
|
"num_tokens": 53162068.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 4.908537101745606,
|
|
"epoch": 2.2662298987492555,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004495696444686539,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.21824840754270552,
|
|
"num_tokens": 53177448.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 4.919506072998047,
|
|
"epoch": 2.266825491363907,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044954275707695304,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.21930340826511383,
|
|
"num_tokens": 53193368.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 4.8813529968261715,
|
|
"epoch": 2.267421083978559,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00044951586342468727,
|
|
"loss": 4.5312,
|
|
"mean_token_accuracy": 0.2296704024076462,
|
|
"num_tokens": 53207924.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 4.9114134311676025,
|
|
"epoch": 2.26801667659321,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004494889635128211,
|
|
"loss": 4.6683,
|
|
"mean_token_accuracy": 0.2191665843129158,
|
|
"num_tokens": 53220620.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 4.928403282165528,
|
|
"epoch": 2.268612269207862,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044946205734231967,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.2256362944841385,
|
|
"num_tokens": 53232130.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 4.878983974456787,
|
|
"epoch": 2.2692078618225136,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00044943514491414783,
|
|
"loss": 4.5663,
|
|
"mean_token_accuracy": 0.22132455706596374,
|
|
"num_tokens": 53246882.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 4.865725517272949,
|
|
"epoch": 2.269803454437165,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044940822622927093,
|
|
"loss": 4.5794,
|
|
"mean_token_accuracy": 0.23027598559856416,
|
|
"num_tokens": 53259377.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 4.94687786102295,
|
|
"epoch": 2.2703990470518165,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044938130128865456,
|
|
"loss": 4.6486,
|
|
"mean_token_accuracy": 0.21994515806436538,
|
|
"num_tokens": 53272249.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 4.829949045181275,
|
|
"epoch": 2.270994639666468,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004493543700932645,
|
|
"loss": 4.5333,
|
|
"mean_token_accuracy": 0.22872905880212785,
|
|
"num_tokens": 53286131.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 4.895095300674439,
|
|
"epoch": 2.27159023228112,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004493274326440666,
|
|
"loss": 4.6269,
|
|
"mean_token_accuracy": 0.22616210132837294,
|
|
"num_tokens": 53299097.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 4.975771713256836,
|
|
"epoch": 2.272185824895771,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004493004889420271,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.2209823578596115,
|
|
"num_tokens": 53312345.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 4.884785604476929,
|
|
"epoch": 2.272781417510423,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004492735389881125,
|
|
"loss": 4.6224,
|
|
"mean_token_accuracy": 0.2200166955590248,
|
|
"num_tokens": 53325661.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 4.8961669445037845,
|
|
"epoch": 2.2733770101250745,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004492465827832894,
|
|
"loss": 4.557,
|
|
"mean_token_accuracy": 0.22842543721199035,
|
|
"num_tokens": 53337650.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 4.947115421295166,
|
|
"epoch": 2.2739726027397262,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044921962032852466,
|
|
"loss": 4.6846,
|
|
"mean_token_accuracy": 0.21771373152732848,
|
|
"num_tokens": 53352270.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 4.864893913269043,
|
|
"epoch": 2.2745681953543775,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004491926516247854,
|
|
"loss": 4.5258,
|
|
"mean_token_accuracy": 0.2265251725912094,
|
|
"num_tokens": 53367077.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 4.811251306533814,
|
|
"epoch": 2.275163787969029,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000449165676673039,
|
|
"loss": 4.5812,
|
|
"mean_token_accuracy": 0.2306109130382538,
|
|
"num_tokens": 53380217.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 4.910622644424438,
|
|
"epoch": 2.275759380583681,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004491386954742529,
|
|
"loss": 4.623,
|
|
"mean_token_accuracy": 0.2195812687277794,
|
|
"num_tokens": 53393819.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 4.889094495773316,
|
|
"epoch": 2.276354973198332,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000449111708029395,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.22176361382007598,
|
|
"num_tokens": 53407617.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 4.877429008483887,
|
|
"epoch": 2.276950565812984,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004490847143394332,
|
|
"loss": 4.599,
|
|
"mean_token_accuracy": 0.22816927582025529,
|
|
"num_tokens": 53420362.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 4.877704334259033,
|
|
"epoch": 2.2775461584276355,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004490577144053357,
|
|
"loss": 4.5799,
|
|
"mean_token_accuracy": 0.22270782738924028,
|
|
"num_tokens": 53435285.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 4.889735746383667,
|
|
"epoch": 2.278141751042287,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000449030708228071,
|
|
"loss": 4.5748,
|
|
"mean_token_accuracy": 0.2207629233598709,
|
|
"num_tokens": 53449274.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 4.953257989883423,
|
|
"epoch": 2.2787373436569385,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004490036958086078,
|
|
"loss": 4.6838,
|
|
"mean_token_accuracy": 0.21481972336769103,
|
|
"num_tokens": 53462932.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 4.894065904617309,
|
|
"epoch": 2.27933293627159,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004489766771479148,
|
|
"loss": 4.5817,
|
|
"mean_token_accuracy": 0.2261973351240158,
|
|
"num_tokens": 53477414.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 4.889758491516114,
|
|
"epoch": 2.279928528886242,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044894965224696144,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.2124330222606659,
|
|
"num_tokens": 53490975.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 4.950680828094482,
|
|
"epoch": 2.2805241215008936,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044892262110671677,
|
|
"loss": 4.6104,
|
|
"mean_token_accuracy": 0.22118851393461228,
|
|
"num_tokens": 53506982.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 4.991955900192261,
|
|
"epoch": 2.281119714115545,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004488955837281505,
|
|
"loss": 4.7483,
|
|
"mean_token_accuracy": 0.2124376267194748,
|
|
"num_tokens": 53521253.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 4.911313486099243,
|
|
"epoch": 2.2817153067301965,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044886854011223234,
|
|
"loss": 4.5428,
|
|
"mean_token_accuracy": 0.23091500103473664,
|
|
"num_tokens": 53533893.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 4.991867256164551,
|
|
"epoch": 2.282310899344848,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004488414902599323,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.21658164411783218,
|
|
"num_tokens": 53548289.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 4.870647001266479,
|
|
"epoch": 2.2829064919594995,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044881443417222076,
|
|
"loss": 4.5754,
|
|
"mean_token_accuracy": 0.2260487824678421,
|
|
"num_tokens": 53561856.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 4.780687046051026,
|
|
"epoch": 2.283502084574151,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044878737185006807,
|
|
"loss": 4.3978,
|
|
"mean_token_accuracy": 0.2364074245095253,
|
|
"num_tokens": 53575091.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 4.980452013015747,
|
|
"epoch": 2.284097677188803,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004487603032944448,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.21732164770364762,
|
|
"num_tokens": 53590138.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 4.891943788528442,
|
|
"epoch": 2.2846932698034546,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004487332285063221,
|
|
"loss": 4.5864,
|
|
"mean_token_accuracy": 0.2268313243985176,
|
|
"num_tokens": 53606784.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 4.910632133483887,
|
|
"epoch": 2.2852888624181062,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004487061474866709,
|
|
"loss": 4.6043,
|
|
"mean_token_accuracy": 0.22022827863693237,
|
|
"num_tokens": 53619111.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 4.897122383117676,
|
|
"epoch": 2.2858844550327575,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044867906023646263,
|
|
"loss": 4.666,
|
|
"mean_token_accuracy": 0.21756191551685333,
|
|
"num_tokens": 53632010.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 4.989614820480346,
|
|
"epoch": 2.286480047647409,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044865196675666886,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.2219468519091606,
|
|
"num_tokens": 53646913.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 4.902557516098023,
|
|
"epoch": 2.287075640262061,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004486248670482613,
|
|
"loss": 4.6348,
|
|
"mean_token_accuracy": 0.22122423350811005,
|
|
"num_tokens": 53660165.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 4.859898853302002,
|
|
"epoch": 2.287671232876712,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044859776111221217,
|
|
"loss": 4.6273,
|
|
"mean_token_accuracy": 0.2201223775744438,
|
|
"num_tokens": 53674459.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 4.970372676849365,
|
|
"epoch": 2.288266825491364,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044857064894949356,
|
|
"loss": 4.6537,
|
|
"mean_token_accuracy": 0.21858279556035995,
|
|
"num_tokens": 53687663.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 4.877784395217896,
|
|
"epoch": 2.2888624181060155,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000448543530561078,
|
|
"loss": 4.519,
|
|
"mean_token_accuracy": 0.22827487736940383,
|
|
"num_tokens": 53701101.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 4.788498401641846,
|
|
"epoch": 2.2894580107206672,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004485164059479381,
|
|
"loss": 4.5018,
|
|
"mean_token_accuracy": 0.23481235951185225,
|
|
"num_tokens": 53715631.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 4.878360891342163,
|
|
"epoch": 2.2900536033353185,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044848927511104695,
|
|
"loss": 4.591,
|
|
"mean_token_accuracy": 0.2325966775417328,
|
|
"num_tokens": 53729167.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 4.874802350997925,
|
|
"epoch": 2.29064919594997,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00044846213805137746,
|
|
"loss": 4.5145,
|
|
"mean_token_accuracy": 0.23331622928380966,
|
|
"num_tokens": 53742906.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 4.891437005996704,
|
|
"epoch": 2.291244788564622,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044843499476990317,
|
|
"loss": 4.6232,
|
|
"mean_token_accuracy": 0.22099646478891372,
|
|
"num_tokens": 53756145.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 4.849670886993408,
|
|
"epoch": 2.2918403811792736,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004484078452675977,
|
|
"loss": 4.546,
|
|
"mean_token_accuracy": 0.22508985698223113,
|
|
"num_tokens": 53769980.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 4.899761199951172,
|
|
"epoch": 2.292435973793925,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004483806895454346,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.21542604863643647,
|
|
"num_tokens": 53783542.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 4.812113571166992,
|
|
"epoch": 2.2930315664085765,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004483535276043881,
|
|
"loss": 4.5428,
|
|
"mean_token_accuracy": 0.23082321584224702,
|
|
"num_tokens": 53797849.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 4.894570016860962,
|
|
"epoch": 2.2936271590232282,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044832635944543243,
|
|
"loss": 4.5733,
|
|
"mean_token_accuracy": 0.23088075518608092,
|
|
"num_tokens": 53811709.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 4.894778203964234,
|
|
"epoch": 2.2942227516378795,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044829918506954214,
|
|
"loss": 4.5739,
|
|
"mean_token_accuracy": 0.22290045619010926,
|
|
"num_tokens": 53827446.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 4.8584339141845705,
|
|
"epoch": 2.294818344252531,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004482720044776918,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.2215276390314102,
|
|
"num_tokens": 53840468.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 4.861003732681274,
|
|
"epoch": 2.295413936867183,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004482448176708563,
|
|
"loss": 4.5,
|
|
"mean_token_accuracy": 0.22929618656635284,
|
|
"num_tokens": 53852937.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 4.845704984664917,
|
|
"epoch": 2.2960095294818346,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044821762465001096,
|
|
"loss": 4.6088,
|
|
"mean_token_accuracy": 0.222843499481678,
|
|
"num_tokens": 53865986.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 4.872810029983521,
|
|
"epoch": 2.296605122096486,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044819042541613104,
|
|
"loss": 4.6557,
|
|
"mean_token_accuracy": 0.22393962740898132,
|
|
"num_tokens": 53879307.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 4.823643350601197,
|
|
"epoch": 2.2972007147111375,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004481632199701921,
|
|
"loss": 4.5203,
|
|
"mean_token_accuracy": 0.22608682811260222,
|
|
"num_tokens": 53894247.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 4.882966136932373,
|
|
"epoch": 2.297796307325789,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044813600831317016,
|
|
"loss": 4.516,
|
|
"mean_token_accuracy": 0.22951168268918992,
|
|
"num_tokens": 53907467.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 4.910980653762818,
|
|
"epoch": 2.298391899940441,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00044810879044604094,
|
|
"loss": 4.5775,
|
|
"mean_token_accuracy": 0.22285373955965043,
|
|
"num_tokens": 53922453.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 4.92659912109375,
|
|
"epoch": 2.298987492555092,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044808156636978085,
|
|
"loss": 4.6481,
|
|
"mean_token_accuracy": 0.21593560129404069,
|
|
"num_tokens": 53937530.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 4.854206132888794,
|
|
"epoch": 2.299583085169744,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004480543360853665,
|
|
"loss": 4.5166,
|
|
"mean_token_accuracy": 0.2323103591799736,
|
|
"num_tokens": 53951014.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 4.844035196304321,
|
|
"epoch": 2.3001786777843956,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044802709959377446,
|
|
"loss": 4.5748,
|
|
"mean_token_accuracy": 0.2294919267296791,
|
|
"num_tokens": 53963739.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 4.918356227874756,
|
|
"epoch": 2.300774270399047,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044799985689598167,
|
|
"loss": 4.6105,
|
|
"mean_token_accuracy": 0.22252109795808792,
|
|
"num_tokens": 53976681.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 4.934746217727661,
|
|
"epoch": 2.3013698630136985,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044797260799296526,
|
|
"loss": 4.6426,
|
|
"mean_token_accuracy": 0.22126037031412124,
|
|
"num_tokens": 53990910.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 4.919530630111694,
|
|
"epoch": 2.30196545562835,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044794535288570264,
|
|
"loss": 4.6187,
|
|
"mean_token_accuracy": 0.22210036367177963,
|
|
"num_tokens": 54005311.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 4.944006729125976,
|
|
"epoch": 2.302561048243002,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004479180915751715,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.2105894923210144,
|
|
"num_tokens": 54017458.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 4.890598487854004,
|
|
"epoch": 2.3031566408576536,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044789082406234944,
|
|
"loss": 4.5986,
|
|
"mean_token_accuracy": 0.21746510416269302,
|
|
"num_tokens": 54031072.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 4.889159154891968,
|
|
"epoch": 2.303752233472305,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004478635503482147,
|
|
"loss": 4.5136,
|
|
"mean_token_accuracy": 0.23088805228471757,
|
|
"num_tokens": 54044742.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 4.876418781280518,
|
|
"epoch": 2.3043478260869565,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004478362704337454,
|
|
"loss": 4.6426,
|
|
"mean_token_accuracy": 0.22014937400817872,
|
|
"num_tokens": 54058993.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 4.86199984550476,
|
|
"epoch": 2.3049434187016082,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004478089843199202,
|
|
"loss": 4.6147,
|
|
"mean_token_accuracy": 0.22086817920207977,
|
|
"num_tokens": 54073291.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 4.9223603248596195,
|
|
"epoch": 2.3055390113162595,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044778169200771764,
|
|
"loss": 4.6644,
|
|
"mean_token_accuracy": 0.21880853027105332,
|
|
"num_tokens": 54087839.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 4.983666801452637,
|
|
"epoch": 2.306134603930911,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004477543934981167,
|
|
"loss": 4.6858,
|
|
"mean_token_accuracy": 0.2142466902732849,
|
|
"num_tokens": 54103886.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 4.918796253204346,
|
|
"epoch": 2.306730196545563,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044772708879209654,
|
|
"loss": 4.6369,
|
|
"mean_token_accuracy": 0.21783417463302612,
|
|
"num_tokens": 54118387.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 4.873619747161865,
|
|
"epoch": 2.3073257891602146,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004476997778906366,
|
|
"loss": 4.5464,
|
|
"mean_token_accuracy": 0.23063070476055145,
|
|
"num_tokens": 54131500.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 4.887642669677734,
|
|
"epoch": 2.307921381774866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004476724607947164,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.21863994896411895,
|
|
"num_tokens": 54144575.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 4.906035232543945,
|
|
"epoch": 2.3085169743895175,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004476451375053157,
|
|
"loss": 4.6035,
|
|
"mean_token_accuracy": 0.22211550921201706,
|
|
"num_tokens": 54158883.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 4.889388465881348,
|
|
"epoch": 2.3091125670041692,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004476178080234147,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.23067923337221147,
|
|
"num_tokens": 54171955.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 4.8737529754638675,
|
|
"epoch": 2.309708159618821,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044759047234999363,
|
|
"loss": 4.6243,
|
|
"mean_token_accuracy": 0.21858351975679396,
|
|
"num_tokens": 54190286.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 4.862568712234497,
|
|
"epoch": 2.310303752233472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004475631304860328,
|
|
"loss": 4.5834,
|
|
"mean_token_accuracy": 0.2225039079785347,
|
|
"num_tokens": 54205577.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 4.9259344100952145,
|
|
"epoch": 2.310899344848124,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044753578243251314,
|
|
"loss": 4.6019,
|
|
"mean_token_accuracy": 0.22382527589797974,
|
|
"num_tokens": 54219385.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 4.813744831085205,
|
|
"epoch": 2.3114949374627756,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044750842819041547,
|
|
"loss": 4.4875,
|
|
"mean_token_accuracy": 0.24192824065685273,
|
|
"num_tokens": 54231401.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 4.860719490051269,
|
|
"epoch": 2.312090530077427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044748106776072103,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.21410757452249526,
|
|
"num_tokens": 54244852.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 4.927753067016601,
|
|
"epoch": 2.3126861226920785,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00044745370114441103,
|
|
"loss": 4.5826,
|
|
"mean_token_accuracy": 0.22040657103061675,
|
|
"num_tokens": 54259295.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.010251188278199,
|
|
"epoch": 2.31328171530673,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044742632834246716,
|
|
"loss": 4.7073,
|
|
"mean_token_accuracy": 0.2095714896917343,
|
|
"num_tokens": 54273595.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 4.939740562438965,
|
|
"epoch": 2.313877307921382,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00044739894935587126,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.22438983321189881,
|
|
"num_tokens": 54288122.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 4.921152877807617,
|
|
"epoch": 2.314472900536033,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044737156418560536,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.2182333752512932,
|
|
"num_tokens": 54299901.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 4.900161409378052,
|
|
"epoch": 2.315068493150685,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004473441728326518,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.21958912760019303,
|
|
"num_tokens": 54314022.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 4.940250968933105,
|
|
"epoch": 2.3156640857653366,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044731677529799286,
|
|
"loss": 4.6202,
|
|
"mean_token_accuracy": 0.2257273718714714,
|
|
"num_tokens": 54328110.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 4.944718074798584,
|
|
"epoch": 2.3162596783799883,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004472893715826114,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.2141224041581154,
|
|
"num_tokens": 54341087.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 4.924611330032349,
|
|
"epoch": 2.3168552709946395,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004472619616874903,
|
|
"loss": 4.6388,
|
|
"mean_token_accuracy": 0.22805688232183458,
|
|
"num_tokens": 54355922.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 4.925021600723267,
|
|
"epoch": 2.317450863609291,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004472345456136127,
|
|
"loss": 4.6149,
|
|
"mean_token_accuracy": 0.22411873638629914,
|
|
"num_tokens": 54371577.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 4.885455322265625,
|
|
"epoch": 2.318046456223943,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044720712336196195,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.231519977748394,
|
|
"num_tokens": 54384586.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 4.859866380691528,
|
|
"epoch": 2.3186420488385946,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004471796949335217,
|
|
"loss": 4.5849,
|
|
"mean_token_accuracy": 0.22025695890188218,
|
|
"num_tokens": 54398548.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 4.836044836044311,
|
|
"epoch": 2.319237641453246,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044715226032927585,
|
|
"loss": 4.5944,
|
|
"mean_token_accuracy": 0.22546856701374055,
|
|
"num_tokens": 54413237.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 4.868294525146484,
|
|
"epoch": 2.3198332340678975,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004471248195502082,
|
|
"loss": 4.5036,
|
|
"mean_token_accuracy": 0.2310204967856407,
|
|
"num_tokens": 54427537.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 4.843667507171631,
|
|
"epoch": 2.3204288266825492,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044709737259730314,
|
|
"loss": 4.5724,
|
|
"mean_token_accuracy": 0.22984327822923661,
|
|
"num_tokens": 54441120.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 4.84261121749878,
|
|
"epoch": 2.321024419297201,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004470699194715452,
|
|
"loss": 4.5798,
|
|
"mean_token_accuracy": 0.22346077710390091,
|
|
"num_tokens": 54456303.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 4.8587730884552,
|
|
"epoch": 2.321620011911852,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044704246017391897,
|
|
"loss": 4.5157,
|
|
"mean_token_accuracy": 0.23149036020040512,
|
|
"num_tokens": 54469854.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 4.821031856536865,
|
|
"epoch": 2.322215604526504,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004470149947054095,
|
|
"loss": 4.5124,
|
|
"mean_token_accuracy": 0.2299915596842766,
|
|
"num_tokens": 54485080.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 4.828296804428101,
|
|
"epoch": 2.3228111971411556,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044698752306700175,
|
|
"loss": 4.5265,
|
|
"mean_token_accuracy": 0.22508586347103118,
|
|
"num_tokens": 54497451.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 4.873336362838745,
|
|
"epoch": 2.323406789755807,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004469600452596812,
|
|
"loss": 4.561,
|
|
"mean_token_accuracy": 0.22658736109733582,
|
|
"num_tokens": 54510681.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 4.899758434295654,
|
|
"epoch": 2.3240023823704585,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044693256128443336,
|
|
"loss": 4.6193,
|
|
"mean_token_accuracy": 0.21793998628854752,
|
|
"num_tokens": 54524231.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 4.839518260955811,
|
|
"epoch": 2.3245979749851102,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004469050711422442,
|
|
"loss": 4.5253,
|
|
"mean_token_accuracy": 0.2271038368344307,
|
|
"num_tokens": 54538687.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 4.768417549133301,
|
|
"epoch": 2.325193567599762,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044687757483409963,
|
|
"loss": 4.5369,
|
|
"mean_token_accuracy": 0.23493173718452454,
|
|
"num_tokens": 54552917.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 4.950789880752564,
|
|
"epoch": 2.325789160214413,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004468500723609859,
|
|
"loss": 4.7116,
|
|
"mean_token_accuracy": 0.21439450681209565,
|
|
"num_tokens": 54566528.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 4.901461267471314,
|
|
"epoch": 2.326384752829065,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004468225637238894,
|
|
"loss": 4.6306,
|
|
"mean_token_accuracy": 0.22055213898420334,
|
|
"num_tokens": 54581812.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 4.814733791351318,
|
|
"epoch": 2.3269803454437166,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000446795048923797,
|
|
"loss": 4.4696,
|
|
"mean_token_accuracy": 0.23292422145605088,
|
|
"num_tokens": 54596118.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 4.833561372756958,
|
|
"epoch": 2.3275759380583683,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004467675279616955,
|
|
"loss": 4.5453,
|
|
"mean_token_accuracy": 0.22501805871725084,
|
|
"num_tokens": 54610197.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 4.848571062088013,
|
|
"epoch": 2.3281715306730195,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044674000083857205,
|
|
"loss": 4.4889,
|
|
"mean_token_accuracy": 0.23166172206401825,
|
|
"num_tokens": 54623037.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 4.862465953826904,
|
|
"epoch": 2.328767123287671,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044671246755541397,
|
|
"loss": 4.5031,
|
|
"mean_token_accuracy": 0.22275477051734924,
|
|
"num_tokens": 54636914.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 4.859999418258667,
|
|
"epoch": 2.329362715902323,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004466849281132089,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.21808907836675645,
|
|
"num_tokens": 54652047.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 4.8351147174835205,
|
|
"epoch": 2.329958308516974,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004466573825129446,
|
|
"loss": 4.5622,
|
|
"mean_token_accuracy": 0.2245689332485199,
|
|
"num_tokens": 54665475.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 4.787443161010742,
|
|
"epoch": 2.330553901131626,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044662983075560904,
|
|
"loss": 4.5232,
|
|
"mean_token_accuracy": 0.23455826044082642,
|
|
"num_tokens": 54679239.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 4.924903535842896,
|
|
"epoch": 2.3311494937462776,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044660227284219056,
|
|
"loss": 4.5749,
|
|
"mean_token_accuracy": 0.2200819283723831,
|
|
"num_tokens": 54693327.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 4.9167516231536865,
|
|
"epoch": 2.3317450863609293,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004465747087736775,
|
|
"loss": 4.6193,
|
|
"mean_token_accuracy": 0.22009424567222596,
|
|
"num_tokens": 54707293.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 4.868965482711792,
|
|
"epoch": 2.332340678975581,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044654713855105864,
|
|
"loss": 4.5491,
|
|
"mean_token_accuracy": 0.22767094373703003,
|
|
"num_tokens": 54719706.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 4.981788587570191,
|
|
"epoch": 2.332936271590232,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004465195621753229,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.21853214204311372,
|
|
"num_tokens": 54734802.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 4.871761894226074,
|
|
"epoch": 2.333531864204884,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044649197964745927,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.21871979385614396,
|
|
"num_tokens": 54748048.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 4.8996209621429445,
|
|
"epoch": 2.3341274568195356,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004464643909684571,
|
|
"loss": 4.5845,
|
|
"mean_token_accuracy": 0.22077538222074508,
|
|
"num_tokens": 54763052.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 4.947468042373657,
|
|
"epoch": 2.334723049434187,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004464367961393061,
|
|
"loss": 4.6071,
|
|
"mean_token_accuracy": 0.22186922132968903,
|
|
"num_tokens": 54776403.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 4.921276807785034,
|
|
"epoch": 2.3353186420488385,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004464091951609959,
|
|
"loss": 4.6509,
|
|
"mean_token_accuracy": 0.21942633539438247,
|
|
"num_tokens": 54790736.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 4.892060708999634,
|
|
"epoch": 2.3359142346634902,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004463815880345166,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.2192445144057274,
|
|
"num_tokens": 54804756.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 4.974372673034668,
|
|
"epoch": 2.336509827278142,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044635397476085843,
|
|
"loss": 4.6688,
|
|
"mean_token_accuracy": 0.21882997155189515,
|
|
"num_tokens": 54821156.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 4.906231832504273,
|
|
"epoch": 2.337105419892793,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044632635534101175,
|
|
"loss": 4.5726,
|
|
"mean_token_accuracy": 0.22670690417289735,
|
|
"num_tokens": 54836658.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 4.878860759735107,
|
|
"epoch": 2.337701012507445,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044629872977596717,
|
|
"loss": 4.5739,
|
|
"mean_token_accuracy": 0.21591806858778,
|
|
"num_tokens": 54849848.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 4.930513525009156,
|
|
"epoch": 2.3382966051220966,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004462710980667158,
|
|
"loss": 4.634,
|
|
"mean_token_accuracy": 0.21999598443508148,
|
|
"num_tokens": 54862964.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 4.979275894165039,
|
|
"epoch": 2.3388921977367483,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004462434602142486,
|
|
"loss": 4.6785,
|
|
"mean_token_accuracy": 0.22845529168844222,
|
|
"num_tokens": 54876893.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 4.908138275146484,
|
|
"epoch": 2.3394877903513995,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044621581621955686,
|
|
"loss": 4.6259,
|
|
"mean_token_accuracy": 0.22353160828351976,
|
|
"num_tokens": 54889109.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 4.946637392044067,
|
|
"epoch": 2.3400833829660512,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004461881660836322,
|
|
"loss": 4.6668,
|
|
"mean_token_accuracy": 0.22077479362487792,
|
|
"num_tokens": 54904280.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 4.8457934856414795,
|
|
"epoch": 2.340678975580703,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044616050980746634,
|
|
"loss": 4.4615,
|
|
"mean_token_accuracy": 0.24225452095270156,
|
|
"num_tokens": 54917489.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 4.912842273712158,
|
|
"epoch": 2.341274568195354,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044613284739205124,
|
|
"loss": 4.6291,
|
|
"mean_token_accuracy": 0.2181570678949356,
|
|
"num_tokens": 54930122.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 4.895308542251587,
|
|
"epoch": 2.341870160810006,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044610517883837924,
|
|
"loss": 4.5554,
|
|
"mean_token_accuracy": 0.22833516001701354,
|
|
"num_tokens": 54943812.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 4.903328943252563,
|
|
"epoch": 2.3424657534246576,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004460775041474426,
|
|
"loss": 4.5683,
|
|
"mean_token_accuracy": 0.22939424067735673,
|
|
"num_tokens": 54957617.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 4.87625412940979,
|
|
"epoch": 2.3430613460393093,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004460498233202341,
|
|
"loss": 4.5668,
|
|
"mean_token_accuracy": 0.22989670187234879,
|
|
"num_tokens": 54970663.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 4.805641937255859,
|
|
"epoch": 2.3436569386539605,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004460221363577465,
|
|
"loss": 4.4853,
|
|
"mean_token_accuracy": 0.2321906492114067,
|
|
"num_tokens": 54984322.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 4.767376375198364,
|
|
"epoch": 2.344252531268612,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044599444326097297,
|
|
"loss": 4.467,
|
|
"mean_token_accuracy": 0.23896368891000747,
|
|
"num_tokens": 54997173.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 4.880326461791992,
|
|
"epoch": 2.344848123883264,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044596674403090677,
|
|
"loss": 4.5527,
|
|
"mean_token_accuracy": 0.22715531438589096,
|
|
"num_tokens": 55012818.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 4.920833158493042,
|
|
"epoch": 2.3454437164979156,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004459390386685414,
|
|
"loss": 4.6401,
|
|
"mean_token_accuracy": 0.22255273461341857,
|
|
"num_tokens": 55029483.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 4.940041399002075,
|
|
"epoch": 2.346039309112567,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004459113271748707,
|
|
"loss": 4.6582,
|
|
"mean_token_accuracy": 0.2152010440826416,
|
|
"num_tokens": 55043474.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 4.959172916412354,
|
|
"epoch": 2.3466349017272186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004458836095508886,
|
|
"loss": 4.6672,
|
|
"mean_token_accuracy": 0.2181386649608612,
|
|
"num_tokens": 55058685.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 4.908301448822021,
|
|
"epoch": 2.3472304943418703,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004458558857975892,
|
|
"loss": 4.5704,
|
|
"mean_token_accuracy": 0.2307134449481964,
|
|
"num_tokens": 55072025.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 4.762495613098144,
|
|
"epoch": 2.3478260869565215,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000445828155915967,
|
|
"loss": 4.4486,
|
|
"mean_token_accuracy": 0.23646389096975326,
|
|
"num_tokens": 55084752.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 4.797655868530273,
|
|
"epoch": 2.348421679571173,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044580041990701654,
|
|
"loss": 4.5347,
|
|
"mean_token_accuracy": 0.23030663132667542,
|
|
"num_tokens": 55100499.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 4.875308847427368,
|
|
"epoch": 2.349017272185825,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004457726777717328,
|
|
"loss": 4.5567,
|
|
"mean_token_accuracy": 0.22234915494918822,
|
|
"num_tokens": 55116702.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 4.872150659561157,
|
|
"epoch": 2.3496128648004766,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004457449295111108,
|
|
"loss": 4.4962,
|
|
"mean_token_accuracy": 0.23502961099147796,
|
|
"num_tokens": 55129205.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 4.8151366233825685,
|
|
"epoch": 2.3502084574151283,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044571717512614567,
|
|
"loss": 4.5661,
|
|
"mean_token_accuracy": 0.22659898549318314,
|
|
"num_tokens": 55142591.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 4.84481520652771,
|
|
"epoch": 2.3508040500297795,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004456894146178331,
|
|
"loss": 4.6,
|
|
"mean_token_accuracy": 0.22469497323036194,
|
|
"num_tokens": 55155876.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 4.925206279754638,
|
|
"epoch": 2.3513996426444312,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004456616479871687,
|
|
"loss": 4.5888,
|
|
"mean_token_accuracy": 0.2237638056278229,
|
|
"num_tokens": 55169829.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 4.872748327255249,
|
|
"epoch": 2.351995235259083,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044563387523514854,
|
|
"loss": 4.5643,
|
|
"mean_token_accuracy": 0.22736157923936845,
|
|
"num_tokens": 55182983.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 4.8370287895202635,
|
|
"epoch": 2.352590827873734,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004456060963627687,
|
|
"loss": 4.5838,
|
|
"mean_token_accuracy": 0.2272543951869011,
|
|
"num_tokens": 55196568.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 4.886367416381836,
|
|
"epoch": 2.353186420488386,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044557831137102556,
|
|
"loss": 4.5769,
|
|
"mean_token_accuracy": 0.22190753668546676,
|
|
"num_tokens": 55210245.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 4.8917395114898685,
|
|
"epoch": 2.3537820131030376,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044555052026091574,
|
|
"loss": 4.5453,
|
|
"mean_token_accuracy": 0.22695819586515426,
|
|
"num_tokens": 55224158.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 4.872515726089477,
|
|
"epoch": 2.3543776057176893,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044552272303343603,
|
|
"loss": 4.6345,
|
|
"mean_token_accuracy": 0.22169945985078812,
|
|
"num_tokens": 55237936.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 4.879650020599366,
|
|
"epoch": 2.3549731983323405,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044549491968958355,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.22271890044212342,
|
|
"num_tokens": 55252358.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 4.881699466705323,
|
|
"epoch": 2.3555687909469922,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044546711023035545,
|
|
"loss": 4.5026,
|
|
"mean_token_accuracy": 0.2340483099222183,
|
|
"num_tokens": 55267057.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 4.8161759853363035,
|
|
"epoch": 2.356164383561644,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044543929465674925,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.22626520693302155,
|
|
"num_tokens": 55279271.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 4.92928786277771,
|
|
"epoch": 2.3567599761762956,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044541147296976274,
|
|
"loss": 4.6402,
|
|
"mean_token_accuracy": 0.22254237830638884,
|
|
"num_tokens": 55291067.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 4.895636510848999,
|
|
"epoch": 2.357355568790947,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004453836451703937,
|
|
"loss": 4.5894,
|
|
"mean_token_accuracy": 0.21924210339784622,
|
|
"num_tokens": 55306398.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 4.805228662490845,
|
|
"epoch": 2.3579511614055986,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044535581125964045,
|
|
"loss": 4.5244,
|
|
"mean_token_accuracy": 0.22676373273134232,
|
|
"num_tokens": 55319511.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 4.8370081901550295,
|
|
"epoch": 2.3585467540202503,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004453279712385011,
|
|
"loss": 4.5253,
|
|
"mean_token_accuracy": 0.22891146093606948,
|
|
"num_tokens": 55333033.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 4.847773218154908,
|
|
"epoch": 2.3591423466349015,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044530012510797447,
|
|
"loss": 4.5534,
|
|
"mean_token_accuracy": 0.22725976556539534,
|
|
"num_tokens": 55345913.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 4.889541292190552,
|
|
"epoch": 2.359737939249553,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044527227286905914,
|
|
"loss": 4.5618,
|
|
"mean_token_accuracy": 0.22565318048000335,
|
|
"num_tokens": 55361220.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 4.806346988677978,
|
|
"epoch": 2.360333531864205,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044524441452275425,
|
|
"loss": 4.5179,
|
|
"mean_token_accuracy": 0.23089369833469392,
|
|
"num_tokens": 55375480.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 4.890882205963135,
|
|
"epoch": 2.3609291244788566,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044521655007005907,
|
|
"loss": 4.5292,
|
|
"mean_token_accuracy": 0.22957994043827057,
|
|
"num_tokens": 55389793.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 4.845723247528076,
|
|
"epoch": 2.361524717093508,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044518867951197296,
|
|
"loss": 4.5507,
|
|
"mean_token_accuracy": 0.2269059181213379,
|
|
"num_tokens": 55403206.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 4.9344099998474125,
|
|
"epoch": 2.3621203097081596,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004451608028494956,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.22515807896852494,
|
|
"num_tokens": 55417474.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 4.90148959159851,
|
|
"epoch": 2.3627159023228113,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044513292008362696,
|
|
"loss": 4.5455,
|
|
"mean_token_accuracy": 0.23347772657871246,
|
|
"num_tokens": 55430334.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 4.883139038085938,
|
|
"epoch": 2.363311494937463,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004451050312153671,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.22049858123064042,
|
|
"num_tokens": 55444910.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 4.900852060317993,
|
|
"epoch": 2.363907087552114,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044507713624571626,
|
|
"loss": 4.6583,
|
|
"mean_token_accuracy": 0.2186879187822342,
|
|
"num_tokens": 55459762.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 4.8652125835418705,
|
|
"epoch": 2.364502680166766,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044504923517567515,
|
|
"loss": 4.5237,
|
|
"mean_token_accuracy": 0.22780866473913192,
|
|
"num_tokens": 55474865.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 4.844087076187134,
|
|
"epoch": 2.3650982727814176,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004450213280062444,
|
|
"loss": 4.4933,
|
|
"mean_token_accuracy": 0.23258100301027299,
|
|
"num_tokens": 55488854.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 4.817742586135864,
|
|
"epoch": 2.365693865396069,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004449934147384251,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.22679295390844345,
|
|
"num_tokens": 55501467.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 4.960606670379638,
|
|
"epoch": 2.3662894580107205,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004449654953732183,
|
|
"loss": 4.6856,
|
|
"mean_token_accuracy": 0.21493518948554993,
|
|
"num_tokens": 55515293.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 4.807089900970459,
|
|
"epoch": 2.3668850506253722,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004449375699116257,
|
|
"loss": 4.5009,
|
|
"mean_token_accuracy": 0.22983348816633226,
|
|
"num_tokens": 55529103.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 4.840989065170288,
|
|
"epoch": 2.367480643240024,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004449096383546487,
|
|
"loss": 4.5435,
|
|
"mean_token_accuracy": 0.23550644814968108,
|
|
"num_tokens": 55544299.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 4.866276454925537,
|
|
"epoch": 2.3680762358546756,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004448817007032892,
|
|
"loss": 4.6294,
|
|
"mean_token_accuracy": 0.21671517193317413,
|
|
"num_tokens": 55560222.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 4.853604793548584,
|
|
"epoch": 2.368671828469327,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044485375695854927,
|
|
"loss": 4.5442,
|
|
"mean_token_accuracy": 0.2261776238679886,
|
|
"num_tokens": 55573910.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 4.87007884979248,
|
|
"epoch": 2.3692674210839786,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044482580712143136,
|
|
"loss": 4.5463,
|
|
"mean_token_accuracy": 0.22426618486642838,
|
|
"num_tokens": 55587832.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 4.888152313232422,
|
|
"epoch": 2.3698630136986303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044479785119293783,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.22414927035570145,
|
|
"num_tokens": 55601688.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 4.9693317890167235,
|
|
"epoch": 2.3704586063132815,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00044476988917407136,
|
|
"loss": 4.6576,
|
|
"mean_token_accuracy": 0.22384965866804124,
|
|
"num_tokens": 55617693.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 4.8947022438049315,
|
|
"epoch": 2.3710541989279332,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004447419210658351,
|
|
"loss": 4.5392,
|
|
"mean_token_accuracy": 0.2230165719985962,
|
|
"num_tokens": 55633485.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 4.8017041206359865,
|
|
"epoch": 2.371649791542585,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044471394686923206,
|
|
"loss": 4.6127,
|
|
"mean_token_accuracy": 0.22400473654270173,
|
|
"num_tokens": 55648086.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 4.771495580673218,
|
|
"epoch": 2.3722453841572366,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044468596658526566,
|
|
"loss": 4.5318,
|
|
"mean_token_accuracy": 0.2290056511759758,
|
|
"num_tokens": 55661614.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 4.955404329299927,
|
|
"epoch": 2.372840976771888,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004446579802149396,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.21904523074626922,
|
|
"num_tokens": 55675404.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 4.938895559310913,
|
|
"epoch": 2.3734365693865396,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044462998775925757,
|
|
"loss": 4.6005,
|
|
"mean_token_accuracy": 0.21829508543014525,
|
|
"num_tokens": 55689872.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 4.923954772949219,
|
|
"epoch": 2.3740321620011913,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004446019892192237,
|
|
"loss": 4.6446,
|
|
"mean_token_accuracy": 0.22277656942605972,
|
|
"num_tokens": 55706292.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 4.867429256439209,
|
|
"epoch": 2.374627754615843,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004445739845958423,
|
|
"loss": 4.5021,
|
|
"mean_token_accuracy": 0.2356554538011551,
|
|
"num_tokens": 55719716.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 4.869290065765381,
|
|
"epoch": 2.375223347230494,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004445459738901177,
|
|
"loss": 4.6095,
|
|
"mean_token_accuracy": 0.2265651270747185,
|
|
"num_tokens": 55734565.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 4.910802125930786,
|
|
"epoch": 2.375818939845146,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044451795710305476,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.21688025444746017,
|
|
"num_tokens": 55748392.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 4.902494955062866,
|
|
"epoch": 2.3764145324597976,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044448993423565824,
|
|
"loss": 4.5784,
|
|
"mean_token_accuracy": 0.22617863565683366,
|
|
"num_tokens": 55762489.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 4.832045650482177,
|
|
"epoch": 2.377010125074449,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004444619052889334,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.2187404602766037,
|
|
"num_tokens": 55777293.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 4.855766153335571,
|
|
"epoch": 2.3776057176891006,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004444338702638855,
|
|
"loss": 4.559,
|
|
"mean_token_accuracy": 0.23175411373376847,
|
|
"num_tokens": 55789996.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 4.870214939117432,
|
|
"epoch": 2.3782013103037523,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004444058291615202,
|
|
"loss": 4.573,
|
|
"mean_token_accuracy": 0.22103092819452286,
|
|
"num_tokens": 55803205.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 4.889011716842651,
|
|
"epoch": 2.378796902918404,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004443777819828432,
|
|
"loss": 4.5737,
|
|
"mean_token_accuracy": 0.22498714327812194,
|
|
"num_tokens": 55816476.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 4.992758321762085,
|
|
"epoch": 2.379392495533055,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004443497287288606,
|
|
"loss": 4.6411,
|
|
"mean_token_accuracy": 0.21376361101865768,
|
|
"num_tokens": 55829987.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 4.822220706939698,
|
|
"epoch": 2.379988088147707,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044432166940057855,
|
|
"loss": 4.5206,
|
|
"mean_token_accuracy": 0.22796374261379243,
|
|
"num_tokens": 55842903.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 4.854211664199829,
|
|
"epoch": 2.3805836807623586,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044429360399900355,
|
|
"loss": 4.5542,
|
|
"mean_token_accuracy": 0.22947887033224107,
|
|
"num_tokens": 55856253.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 4.802988910675049,
|
|
"epoch": 2.3811792733770103,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004442655325251422,
|
|
"loss": 4.5375,
|
|
"mean_token_accuracy": 0.22780649363994598,
|
|
"num_tokens": 55869848.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 4.854745388031006,
|
|
"epoch": 2.3817748659916615,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004442374549800014,
|
|
"loss": 4.5766,
|
|
"mean_token_accuracy": 0.22536659985780716,
|
|
"num_tokens": 55883794.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 4.938348627090454,
|
|
"epoch": 2.3823704586063132,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044420937136458827,
|
|
"loss": 4.6037,
|
|
"mean_token_accuracy": 0.2235465556383133,
|
|
"num_tokens": 55897626.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 4.876598930358886,
|
|
"epoch": 2.382966051220965,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004441812816799101,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.2200612485408783,
|
|
"num_tokens": 55912519.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 4.872443199157715,
|
|
"epoch": 2.383561643835616,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004441531859269745,
|
|
"loss": 4.5222,
|
|
"mean_token_accuracy": 0.2274884030222893,
|
|
"num_tokens": 55927135.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 4.819071102142334,
|
|
"epoch": 2.384157236450268,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000444125084106789,
|
|
"loss": 4.4906,
|
|
"mean_token_accuracy": 0.2332275316119194,
|
|
"num_tokens": 55939741.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 4.908498811721802,
|
|
"epoch": 2.3847528290649196,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004440969762203618,
|
|
"loss": 4.624,
|
|
"mean_token_accuracy": 0.2267407774925232,
|
|
"num_tokens": 55952408.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 4.969963121414184,
|
|
"epoch": 2.3853484216795713,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000444068862268701,
|
|
"loss": 4.6638,
|
|
"mean_token_accuracy": 0.21871282756328583,
|
|
"num_tokens": 55965536.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 4.894778823852539,
|
|
"epoch": 2.385944014294223,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000444040742252815,
|
|
"loss": 4.5533,
|
|
"mean_token_accuracy": 0.23371966928243637,
|
|
"num_tokens": 55979038.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 4.84032301902771,
|
|
"epoch": 2.3865396069088742,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00044401261617371234,
|
|
"loss": 4.5576,
|
|
"mean_token_accuracy": 0.2257698193192482,
|
|
"num_tokens": 55995249.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 4.9158790588378904,
|
|
"epoch": 2.387135199523526,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00044398448403240213,
|
|
"loss": 4.6665,
|
|
"mean_token_accuracy": 0.2216275751590729,
|
|
"num_tokens": 56011626.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.032799243927002,
|
|
"epoch": 2.3877307921381776,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044395634582989306,
|
|
"loss": 4.7301,
|
|
"mean_token_accuracy": 0.21528594344854354,
|
|
"num_tokens": 56024889.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 4.828405284881592,
|
|
"epoch": 2.388326384752829,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004439282015671946,
|
|
"loss": 4.5199,
|
|
"mean_token_accuracy": 0.23135026693344116,
|
|
"num_tokens": 56041599.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 4.865230321884155,
|
|
"epoch": 2.3889219773674806,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044390005124531626,
|
|
"loss": 4.5597,
|
|
"mean_token_accuracy": 0.22498345822095872,
|
|
"num_tokens": 56054523.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 4.865553474426269,
|
|
"epoch": 2.3895175699821323,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004438718948652676,
|
|
"loss": 4.5764,
|
|
"mean_token_accuracy": 0.22463976591825485,
|
|
"num_tokens": 56067542.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 4.811882019042969,
|
|
"epoch": 2.390113162596784,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004438437324280587,
|
|
"loss": 4.4366,
|
|
"mean_token_accuracy": 0.2316810443997383,
|
|
"num_tokens": 56083391.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 4.866110563278198,
|
|
"epoch": 2.390708755211435,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004438155639346997,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.22455175668001176,
|
|
"num_tokens": 56096987.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 4.790080928802491,
|
|
"epoch": 2.391304347826087,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004437873893862008,
|
|
"loss": 4.4558,
|
|
"mean_token_accuracy": 0.2354924723505974,
|
|
"num_tokens": 56111102.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 4.875319337844848,
|
|
"epoch": 2.3918999404407386,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044375920878357274,
|
|
"loss": 4.4419,
|
|
"mean_token_accuracy": 0.2389090195298195,
|
|
"num_tokens": 56123688.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 4.87097396850586,
|
|
"epoch": 2.3924955330553903,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004437310221278262,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.22388881146907808,
|
|
"num_tokens": 56137977.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 4.786350917816162,
|
|
"epoch": 2.3930911256700416,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004437028294199723,
|
|
"loss": 4.4763,
|
|
"mean_token_accuracy": 0.23837362676858903,
|
|
"num_tokens": 56153090.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 4.825605058670044,
|
|
"epoch": 2.3936867182846933,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044367463066102207,
|
|
"loss": 4.5109,
|
|
"mean_token_accuracy": 0.23129149079322814,
|
|
"num_tokens": 56165991.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 4.791195249557495,
|
|
"epoch": 2.394282310899345,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004436464258519872,
|
|
"loss": 4.5227,
|
|
"mean_token_accuracy": 0.2300104558467865,
|
|
"num_tokens": 56180063.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 4.936437129974365,
|
|
"epoch": 2.394877903513996,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004436182149938792,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.2237844407558441,
|
|
"num_tokens": 56194462.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 4.8650938987731935,
|
|
"epoch": 2.395473496128648,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00044358999808771007,
|
|
"loss": 4.5307,
|
|
"mean_token_accuracy": 0.2252938225865364,
|
|
"num_tokens": 56209278.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 4.842399597167969,
|
|
"epoch": 2.3960690887432996,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004435617751344917,
|
|
"loss": 4.5148,
|
|
"mean_token_accuracy": 0.23047825396060945,
|
|
"num_tokens": 56223145.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 4.8477788925170895,
|
|
"epoch": 2.3966646813579513,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004435335461352366,
|
|
"loss": 4.6176,
|
|
"mean_token_accuracy": 0.2280336797237396,
|
|
"num_tokens": 56237289.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 4.902032709121704,
|
|
"epoch": 2.3972602739726026,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004435053110909572,
|
|
"loss": 4.6585,
|
|
"mean_token_accuracy": 0.22103187292814255,
|
|
"num_tokens": 56252731.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 4.854648113250732,
|
|
"epoch": 2.3978558665872542,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00044347707000266627,
|
|
"loss": 4.5618,
|
|
"mean_token_accuracy": 0.22937051653862,
|
|
"num_tokens": 56265743.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 4.840854454040527,
|
|
"epoch": 2.398451459201906,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044344882287137676,
|
|
"loss": 4.5343,
|
|
"mean_token_accuracy": 0.2259911745786667,
|
|
"num_tokens": 56280308.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 4.851777458190918,
|
|
"epoch": 2.3990470518165576,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004434205696981018,
|
|
"loss": 4.5968,
|
|
"mean_token_accuracy": 0.2270849421620369,
|
|
"num_tokens": 56295181.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 4.968735933303833,
|
|
"epoch": 2.399642644431209,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044339231048385485,
|
|
"loss": 4.572,
|
|
"mean_token_accuracy": 0.22834574580192565,
|
|
"num_tokens": 56307241.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 4.886278200149536,
|
|
"epoch": 2.4002382370458606,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044336404522964963,
|
|
"loss": 4.6083,
|
|
"mean_token_accuracy": 0.22283087223768233,
|
|
"num_tokens": 56320712.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 4.853260231018067,
|
|
"epoch": 2.4008338296605123,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004433357739364998,
|
|
"loss": 4.5356,
|
|
"mean_token_accuracy": 0.2310428351163864,
|
|
"num_tokens": 56333226.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 4.903321695327759,
|
|
"epoch": 2.4014294222751635,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044330749660541943,
|
|
"loss": 4.6472,
|
|
"mean_token_accuracy": 0.2136170521378517,
|
|
"num_tokens": 56347246.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 4.908513975143433,
|
|
"epoch": 2.4020250148898152,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044327921323742276,
|
|
"loss": 4.5766,
|
|
"mean_token_accuracy": 0.23173867762088776,
|
|
"num_tokens": 56361730.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 4.829056453704834,
|
|
"epoch": 2.402620607504467,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044325092383352434,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.22661958932876586,
|
|
"num_tokens": 56378197.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 4.888860034942627,
|
|
"epoch": 2.4032162001191186,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004432226283947388,
|
|
"loss": 4.6063,
|
|
"mean_token_accuracy": 0.2188090816140175,
|
|
"num_tokens": 56391495.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 4.855795001983642,
|
|
"epoch": 2.4038117927337703,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044319432692208115,
|
|
"loss": 4.5216,
|
|
"mean_token_accuracy": 0.23473966866731644,
|
|
"num_tokens": 56405503.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 4.935225582122802,
|
|
"epoch": 2.4044073853484216,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044316601941656655,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.21473909318447112,
|
|
"num_tokens": 56420526.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 4.82901554107666,
|
|
"epoch": 2.4050029779630733,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004431377058792101,
|
|
"loss": 4.4521,
|
|
"mean_token_accuracy": 0.24071079939603807,
|
|
"num_tokens": 56433437.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 4.886039686203003,
|
|
"epoch": 2.405598570577725,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004431093863110276,
|
|
"loss": 4.6786,
|
|
"mean_token_accuracy": 0.21887691617012023,
|
|
"num_tokens": 56447074.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 4.795377492904663,
|
|
"epoch": 2.4061941631923762,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004430810607130347,
|
|
"loss": 4.5305,
|
|
"mean_token_accuracy": 0.22520243972539902,
|
|
"num_tokens": 56462533.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 4.945066738128662,
|
|
"epoch": 2.406789755807028,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044305272908624747,
|
|
"loss": 4.6639,
|
|
"mean_token_accuracy": 0.21961889415979385,
|
|
"num_tokens": 56476914.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 4.93821759223938,
|
|
"epoch": 2.4073853484216796,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00044302439143168213,
|
|
"loss": 4.5966,
|
|
"mean_token_accuracy": 0.22810804843902588,
|
|
"num_tokens": 56492962.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 4.870425462722778,
|
|
"epoch": 2.4079809410363313,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044299604775035497,
|
|
"loss": 4.6194,
|
|
"mean_token_accuracy": 0.22400509119033812,
|
|
"num_tokens": 56506629.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 4.893310689926148,
|
|
"epoch": 2.4085765336509826,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044296769804328274,
|
|
"loss": 4.6957,
|
|
"mean_token_accuracy": 0.2189451903104782,
|
|
"num_tokens": 56520287.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 4.793613576889038,
|
|
"epoch": 2.4091721262656343,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004429393423114824,
|
|
"loss": 4.5295,
|
|
"mean_token_accuracy": 0.22832623422145842,
|
|
"num_tokens": 56534481.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 4.9202981948852536,
|
|
"epoch": 2.409767718880286,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00044291098055597076,
|
|
"loss": 4.6206,
|
|
"mean_token_accuracy": 0.2202541083097458,
|
|
"num_tokens": 56549133.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 4.886923789978027,
|
|
"epoch": 2.4103633114949377,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044288261277776524,
|
|
"loss": 4.5273,
|
|
"mean_token_accuracy": 0.22497609108686448,
|
|
"num_tokens": 56563433.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 4.779503250122071,
|
|
"epoch": 2.410958904109589,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004428542389778834,
|
|
"loss": 4.4876,
|
|
"mean_token_accuracy": 0.22822925597429275,
|
|
"num_tokens": 56577368.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 4.926036262512207,
|
|
"epoch": 2.4115544967242406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044282585915734297,
|
|
"loss": 4.5945,
|
|
"mean_token_accuracy": 0.2175856724381447,
|
|
"num_tokens": 56594500.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 4.8468412399292,
|
|
"epoch": 2.4121500893388923,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004427974733171618,
|
|
"loss": 4.5841,
|
|
"mean_token_accuracy": 0.23150825053453444,
|
|
"num_tokens": 56607951.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 4.822547388076782,
|
|
"epoch": 2.4127456819535436,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004427690814583581,
|
|
"loss": 4.5374,
|
|
"mean_token_accuracy": 0.2293248161673546,
|
|
"num_tokens": 56623195.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 4.887790393829346,
|
|
"epoch": 2.4133412745681952,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004427406835819502,
|
|
"loss": 4.6212,
|
|
"mean_token_accuracy": 0.21895087659358978,
|
|
"num_tokens": 56637731.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 4.915493392944336,
|
|
"epoch": 2.413936867182847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004427122796889567,
|
|
"loss": 4.5632,
|
|
"mean_token_accuracy": 0.22930846810340882,
|
|
"num_tokens": 56651221.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 4.885976791381836,
|
|
"epoch": 2.4145324597974986,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004426838697803965,
|
|
"loss": 4.5906,
|
|
"mean_token_accuracy": 0.22030952274799348,
|
|
"num_tokens": 56665210.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 4.880564594268799,
|
|
"epoch": 2.4151280524121503,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044265545385728847,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.22676781862974166,
|
|
"num_tokens": 56677856.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 4.930343532562256,
|
|
"epoch": 2.4157236450268016,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044262703192065185,
|
|
"loss": 4.6815,
|
|
"mean_token_accuracy": 0.21387600004673005,
|
|
"num_tokens": 56691431.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 4.933754301071167,
|
|
"epoch": 2.4163192376414533,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044259860397150616,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.22169051170349122,
|
|
"num_tokens": 56706939.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 4.849437713623047,
|
|
"epoch": 2.416914830256105,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044257017001087114,
|
|
"loss": 4.5071,
|
|
"mean_token_accuracy": 0.23156590163707733,
|
|
"num_tokens": 56720996.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 4.875651502609253,
|
|
"epoch": 2.4175104228707562,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004425417300397665,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.22166891694068908,
|
|
"num_tokens": 56734890.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 4.930292272567749,
|
|
"epoch": 2.418106015485408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044251328405921236,
|
|
"loss": 4.5899,
|
|
"mean_token_accuracy": 0.23018796890974044,
|
|
"num_tokens": 56747591.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 4.865213298797608,
|
|
"epoch": 2.4187016081000596,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004424848320702291,
|
|
"loss": 4.5976,
|
|
"mean_token_accuracy": 0.22708843946456908,
|
|
"num_tokens": 56759250.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 4.875377750396728,
|
|
"epoch": 2.4192972007147113,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004424563740738373,
|
|
"loss": 4.6217,
|
|
"mean_token_accuracy": 0.21683689802885056,
|
|
"num_tokens": 56775003.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 4.86220760345459,
|
|
"epoch": 2.4198927933293626,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044242791007105764,
|
|
"loss": 4.5261,
|
|
"mean_token_accuracy": 0.23301012963056564,
|
|
"num_tokens": 56788221.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 4.905310869216919,
|
|
"epoch": 2.4204883859440143,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000442399440062911,
|
|
"loss": 4.6374,
|
|
"mean_token_accuracy": 0.22264299988746644,
|
|
"num_tokens": 56803291.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 4.900519561767578,
|
|
"epoch": 2.421083978558666,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044237096405041863,
|
|
"loss": 4.5778,
|
|
"mean_token_accuracy": 0.22295235395431517,
|
|
"num_tokens": 56817550.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 4.97776951789856,
|
|
"epoch": 2.4216795711733177,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044234248203460193,
|
|
"loss": 4.6352,
|
|
"mean_token_accuracy": 0.22032173722982407,
|
|
"num_tokens": 56831573.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 4.875443363189698,
|
|
"epoch": 2.422275163787969,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00044231399401648247,
|
|
"loss": 4.5462,
|
|
"mean_token_accuracy": 0.22150822579860688,
|
|
"num_tokens": 56847286.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 4.863899421691895,
|
|
"epoch": 2.4228707564026206,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044228549999708204,
|
|
"loss": 4.5757,
|
|
"mean_token_accuracy": 0.22385491281747819,
|
|
"num_tokens": 56862680.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 4.845752429962158,
|
|
"epoch": 2.4234663490172723,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004422569999774228,
|
|
"loss": 4.5382,
|
|
"mean_token_accuracy": 0.23297749012708663,
|
|
"num_tokens": 56876813.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 4.991078615188599,
|
|
"epoch": 2.4240619416319236,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044222849395852683,
|
|
"loss": 4.693,
|
|
"mean_token_accuracy": 0.2133200138807297,
|
|
"num_tokens": 56892525.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 4.89896821975708,
|
|
"epoch": 2.4246575342465753,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004421999819414167,
|
|
"loss": 4.5464,
|
|
"mean_token_accuracy": 0.23183876276016235,
|
|
"num_tokens": 56906668.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 4.771290826797485,
|
|
"epoch": 2.425253126861227,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004421714639271151,
|
|
"loss": 4.527,
|
|
"mean_token_accuracy": 0.23293792307376862,
|
|
"num_tokens": 56919365.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 4.876556253433227,
|
|
"epoch": 2.4258487194758787,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004421429399166449,
|
|
"loss": 4.5636,
|
|
"mean_token_accuracy": 0.22687546163797379,
|
|
"num_tokens": 56933790.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 4.886758470535279,
|
|
"epoch": 2.42644431209053,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004421144099110292,
|
|
"loss": 4.529,
|
|
"mean_token_accuracy": 0.23332326114177704,
|
|
"num_tokens": 56947556.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 4.830600595474243,
|
|
"epoch": 2.4270399047051816,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004420858739112913,
|
|
"loss": 4.5102,
|
|
"mean_token_accuracy": 0.22694595903158188,
|
|
"num_tokens": 56960477.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 4.881005573272705,
|
|
"epoch": 2.4276354973198333,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044205733191845473,
|
|
"loss": 4.6614,
|
|
"mean_token_accuracy": 0.22641595900058747,
|
|
"num_tokens": 56974539.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 4.845162677764892,
|
|
"epoch": 2.428231089934485,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004420287839335434,
|
|
"loss": 4.4897,
|
|
"mean_token_accuracy": 0.224897663295269,
|
|
"num_tokens": 56988838.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 4.857963609695434,
|
|
"epoch": 2.4288266825491363,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00044200022995758104,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.22401846647262574,
|
|
"num_tokens": 57004440.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 4.865312814712524,
|
|
"epoch": 2.429422275163788,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044197166999159203,
|
|
"loss": 4.5466,
|
|
"mean_token_accuracy": 0.22521722465753555,
|
|
"num_tokens": 57017936.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 4.969365406036377,
|
|
"epoch": 2.4300178677784396,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004419431040366007,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.21878792196512223,
|
|
"num_tokens": 57032984.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 4.893990230560303,
|
|
"epoch": 2.430613460393091,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044191453209363165,
|
|
"loss": 4.606,
|
|
"mean_token_accuracy": 0.2302045077085495,
|
|
"num_tokens": 57046608.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 4.901612663269043,
|
|
"epoch": 2.4312090530077426,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004418859541637097,
|
|
"loss": 4.6259,
|
|
"mean_token_accuracy": 0.22957899123430253,
|
|
"num_tokens": 57059200.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 4.913552331924438,
|
|
"epoch": 2.4318046456223943,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044185737024785986,
|
|
"loss": 4.5919,
|
|
"mean_token_accuracy": 0.22255027145147324,
|
|
"num_tokens": 57073316.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 4.867716455459595,
|
|
"epoch": 2.432400238237046,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00044182878034710753,
|
|
"loss": 4.5852,
|
|
"mean_token_accuracy": 0.22210745960474015,
|
|
"num_tokens": 57089710.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 4.854584121704102,
|
|
"epoch": 2.4329958308516977,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044180018446247807,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.23129394948482512,
|
|
"num_tokens": 57102770.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 4.885433959960937,
|
|
"epoch": 2.433591423466349,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004417715825949972,
|
|
"loss": 4.5634,
|
|
"mean_token_accuracy": 0.22861934155225755,
|
|
"num_tokens": 57117055.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 4.836786413192749,
|
|
"epoch": 2.4341870160810006,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004417429747456908,
|
|
"loss": 4.5768,
|
|
"mean_token_accuracy": 0.23230966031551362,
|
|
"num_tokens": 57130344.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 4.860322713851929,
|
|
"epoch": 2.4347826086956523,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000441714360915585,
|
|
"loss": 4.5948,
|
|
"mean_token_accuracy": 0.22424041479825974,
|
|
"num_tokens": 57143639.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 4.922972202301025,
|
|
"epoch": 2.4353782013103036,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004416857411057062,
|
|
"loss": 4.7061,
|
|
"mean_token_accuracy": 0.21047521829605104,
|
|
"num_tokens": 57157903.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 4.8806798458099365,
|
|
"epoch": 2.4359737939249553,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00044165711531708073,
|
|
"loss": 4.543,
|
|
"mean_token_accuracy": 0.23041744530200958,
|
|
"num_tokens": 57171224.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 4.895103549957275,
|
|
"epoch": 2.436569386539607,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044162848355073565,
|
|
"loss": 4.5711,
|
|
"mean_token_accuracy": 0.22173301130533218,
|
|
"num_tokens": 57184624.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 4.839400815963745,
|
|
"epoch": 2.4371649791542587,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004415998458076978,
|
|
"loss": 4.6075,
|
|
"mean_token_accuracy": 0.22035420686006546,
|
|
"num_tokens": 57199603.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 4.892491579055786,
|
|
"epoch": 2.43776057176891,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004415712020889943,
|
|
"loss": 4.5907,
|
|
"mean_token_accuracy": 0.22328843921422958,
|
|
"num_tokens": 57214448.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 4.924283695220947,
|
|
"epoch": 2.4383561643835616,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044154255239565256,
|
|
"loss": 4.6424,
|
|
"mean_token_accuracy": 0.21943584233522415,
|
|
"num_tokens": 57229162.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 4.827824974060059,
|
|
"epoch": 2.4389517569982133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004415138967287003,
|
|
"loss": 4.4939,
|
|
"mean_token_accuracy": 0.23912931978702545,
|
|
"num_tokens": 57242208.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 4.876596355438233,
|
|
"epoch": 2.439547349612865,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004414852350891653,
|
|
"loss": 4.5002,
|
|
"mean_token_accuracy": 0.226681624352932,
|
|
"num_tokens": 57254206.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 4.858461093902588,
|
|
"epoch": 2.4401429422275163,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004414565674780756,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.22017192244529724,
|
|
"num_tokens": 57268163.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 4.847522163391114,
|
|
"epoch": 2.440738534842168,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044142789389645944,
|
|
"loss": 4.5578,
|
|
"mean_token_accuracy": 0.22953331470489502,
|
|
"num_tokens": 57282758.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 4.880999803543091,
|
|
"epoch": 2.4413341274568197,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004413992143453453,
|
|
"loss": 4.5679,
|
|
"mean_token_accuracy": 0.2272411599755287,
|
|
"num_tokens": 57295079.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 4.823370742797851,
|
|
"epoch": 2.441929720071471,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000441370528825762,
|
|
"loss": 4.5151,
|
|
"mean_token_accuracy": 0.22657422423362733,
|
|
"num_tokens": 57308664.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 4.7998394012451175,
|
|
"epoch": 2.4425253126861226,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044134183733873827,
|
|
"loss": 4.5118,
|
|
"mean_token_accuracy": 0.23052986413240434,
|
|
"num_tokens": 57321932.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 4.777680587768555,
|
|
"epoch": 2.4431209053007743,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044131313988530325,
|
|
"loss": 4.517,
|
|
"mean_token_accuracy": 0.23856088966131211,
|
|
"num_tokens": 57336395.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 4.943776321411133,
|
|
"epoch": 2.443716497915426,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044128443646648634,
|
|
"loss": 4.6771,
|
|
"mean_token_accuracy": 0.22057481557130815,
|
|
"num_tokens": 57350259.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 4.889054012298584,
|
|
"epoch": 2.4443120905300773,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044125572708331705,
|
|
"loss": 4.5751,
|
|
"mean_token_accuracy": 0.22184690088033676,
|
|
"num_tokens": 57364305.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 4.894467973709107,
|
|
"epoch": 2.444907683144729,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044122701173682514,
|
|
"loss": 4.5834,
|
|
"mean_token_accuracy": 0.2255808964371681,
|
|
"num_tokens": 57378843.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 4.803039264678955,
|
|
"epoch": 2.4455032757593806,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004411982904280407,
|
|
"loss": 4.4863,
|
|
"mean_token_accuracy": 0.23408361673355102,
|
|
"num_tokens": 57392190.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 4.798649168014526,
|
|
"epoch": 2.4460988683740323,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004411695631579936,
|
|
"loss": 4.4905,
|
|
"mean_token_accuracy": 0.23564448058605195,
|
|
"num_tokens": 57405952.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 4.895930814743042,
|
|
"epoch": 2.4466944609886836,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044114082992771457,
|
|
"loss": 4.591,
|
|
"mean_token_accuracy": 0.22029053717851638,
|
|
"num_tokens": 57419678.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 4.91185736656189,
|
|
"epoch": 2.4472900536033353,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00044111209073823416,
|
|
"loss": 4.5868,
|
|
"mean_token_accuracy": 0.22748213559389113,
|
|
"num_tokens": 57434262.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 4.88530011177063,
|
|
"epoch": 2.447885646217987,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000441083345590583,
|
|
"loss": 4.5553,
|
|
"mean_token_accuracy": 0.2359539434313774,
|
|
"num_tokens": 57447039.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 4.872676515579224,
|
|
"epoch": 2.4484812388326382,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004410545944857923,
|
|
"loss": 4.594,
|
|
"mean_token_accuracy": 0.2272389590740204,
|
|
"num_tokens": 57461368.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 4.832567977905273,
|
|
"epoch": 2.44907683144729,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044102583742489337,
|
|
"loss": 4.5534,
|
|
"mean_token_accuracy": 0.22928281873464584,
|
|
"num_tokens": 57475466.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 4.895836210250854,
|
|
"epoch": 2.4496724240619416,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004409970744089175,
|
|
"loss": 4.5934,
|
|
"mean_token_accuracy": 0.22598199248313905,
|
|
"num_tokens": 57488743.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 4.869366693496704,
|
|
"epoch": 2.4502680166765933,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044096830543889653,
|
|
"loss": 4.6104,
|
|
"mean_token_accuracy": 0.22273643910884858,
|
|
"num_tokens": 57502747.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 4.772797966003418,
|
|
"epoch": 2.450863609291245,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044093953051586225,
|
|
"loss": 4.4922,
|
|
"mean_token_accuracy": 0.23393082916736602,
|
|
"num_tokens": 57516994.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 4.882338285446167,
|
|
"epoch": 2.4514592019058963,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004409107496408468,
|
|
"loss": 4.4996,
|
|
"mean_token_accuracy": 0.23660558164119722,
|
|
"num_tokens": 57529995.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 4.798406028747559,
|
|
"epoch": 2.452054794520548,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044088196281488257,
|
|
"loss": 4.5005,
|
|
"mean_token_accuracy": 0.22686369717121124,
|
|
"num_tokens": 57543554.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 4.84909200668335,
|
|
"epoch": 2.4526503871351997,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000440853170039002,
|
|
"loss": 4.5648,
|
|
"mean_token_accuracy": 0.22791268825531005,
|
|
"num_tokens": 57558055.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 4.880374431610107,
|
|
"epoch": 2.453245979749851,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044082437131423785,
|
|
"loss": 4.549,
|
|
"mean_token_accuracy": 0.22561561316251755,
|
|
"num_tokens": 57572981.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 4.896260166168213,
|
|
"epoch": 2.4538415723645026,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044079556664162323,
|
|
"loss": 4.5656,
|
|
"mean_token_accuracy": 0.22493360191583633,
|
|
"num_tokens": 57585955.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 4.894233083724975,
|
|
"epoch": 2.4544371649791543,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004407667560221911,
|
|
"loss": 4.5912,
|
|
"mean_token_accuracy": 0.23109069168567659,
|
|
"num_tokens": 57600879.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 4.875736713409424,
|
|
"epoch": 2.455032757593806,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000440737939456975,
|
|
"loss": 4.5644,
|
|
"mean_token_accuracy": 0.2229878917336464,
|
|
"num_tokens": 57613956.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 4.860066652297974,
|
|
"epoch": 2.4556283502084573,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044070911694700846,
|
|
"loss": 4.637,
|
|
"mean_token_accuracy": 0.22651069462299347,
|
|
"num_tokens": 57626321.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 4.883934497833252,
|
|
"epoch": 2.456223942823109,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004406802884933253,
|
|
"loss": 4.5164,
|
|
"mean_token_accuracy": 0.22707387655973435,
|
|
"num_tokens": 57640669.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 4.830959415435791,
|
|
"epoch": 2.4568195354377607,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004406514540969596,
|
|
"loss": 4.5706,
|
|
"mean_token_accuracy": 0.2291196346282959,
|
|
"num_tokens": 57654917.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 4.904373216629028,
|
|
"epoch": 2.4574151280524124,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044062261375894563,
|
|
"loss": 4.641,
|
|
"mean_token_accuracy": 0.22302378863096237,
|
|
"num_tokens": 57668355.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 4.900738906860352,
|
|
"epoch": 2.4580107206670636,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004405937674803177,
|
|
"loss": 4.5582,
|
|
"mean_token_accuracy": 0.22060364186763765,
|
|
"num_tokens": 57683128.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 4.841205167770386,
|
|
"epoch": 2.4586063132817153,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044056491526211063,
|
|
"loss": 4.5251,
|
|
"mean_token_accuracy": 0.22761744260787964,
|
|
"num_tokens": 57696034.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 4.84939661026001,
|
|
"epoch": 2.459201905896367,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004405360571053592,
|
|
"loss": 4.5874,
|
|
"mean_token_accuracy": 0.2235832154750824,
|
|
"num_tokens": 57711496.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 4.870589637756348,
|
|
"epoch": 2.4597974985110183,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044050719301109856,
|
|
"loss": 4.5351,
|
|
"mean_token_accuracy": 0.22986500859260559,
|
|
"num_tokens": 57724250.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 4.891492223739624,
|
|
"epoch": 2.46039309112567,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000440478322980364,
|
|
"loss": 4.5447,
|
|
"mean_token_accuracy": 0.23304859250783921,
|
|
"num_tokens": 57736979.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 4.885283279418945,
|
|
"epoch": 2.4609886837403216,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044044944701419105,
|
|
"loss": 4.6337,
|
|
"mean_token_accuracy": 0.21231923699378968,
|
|
"num_tokens": 57750745.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 4.895740938186646,
|
|
"epoch": 2.4615842763549733,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004404205651136155,
|
|
"loss": 4.5966,
|
|
"mean_token_accuracy": 0.22593535333871842,
|
|
"num_tokens": 57766414.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 4.905357503890992,
|
|
"epoch": 2.4621798689696246,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004403916772796731,
|
|
"loss": 4.639,
|
|
"mean_token_accuracy": 0.2182316616177559,
|
|
"num_tokens": 57781696.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 4.934223651885986,
|
|
"epoch": 2.4627754615842763,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044036278351340023,
|
|
"loss": 4.6173,
|
|
"mean_token_accuracy": 0.22431463450193406,
|
|
"num_tokens": 57795437.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 4.912436771392822,
|
|
"epoch": 2.463371054198928,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044033388381583324,
|
|
"loss": 4.6076,
|
|
"mean_token_accuracy": 0.22502732425928115,
|
|
"num_tokens": 57808366.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 4.881219053268433,
|
|
"epoch": 2.4639666468135797,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004403049781880086,
|
|
"loss": 4.6147,
|
|
"mean_token_accuracy": 0.2223917528986931,
|
|
"num_tokens": 57821654.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 4.888561868667603,
|
|
"epoch": 2.464562239428231,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004402760666309631,
|
|
"loss": 4.6395,
|
|
"mean_token_accuracy": 0.2204861581325531,
|
|
"num_tokens": 57834897.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 4.773959064483643,
|
|
"epoch": 2.4651578320428826,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004402471491457339,
|
|
"loss": 4.4521,
|
|
"mean_token_accuracy": 0.237661312520504,
|
|
"num_tokens": 57851005.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 4.859804439544678,
|
|
"epoch": 2.4657534246575343,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004402182257333581,
|
|
"loss": 4.5205,
|
|
"mean_token_accuracy": 0.2310831755399704,
|
|
"num_tokens": 57863101.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 4.946809339523315,
|
|
"epoch": 2.4663490172721856,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004401892963948732,
|
|
"loss": 4.6534,
|
|
"mean_token_accuracy": 0.21683279573917388,
|
|
"num_tokens": 57879507.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 4.805143594741821,
|
|
"epoch": 2.4669446098868373,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00044016036113131673,
|
|
"loss": 4.483,
|
|
"mean_token_accuracy": 0.23511119484901427,
|
|
"num_tokens": 57893065.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 4.833800315856934,
|
|
"epoch": 2.467540202501489,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044013141994372673,
|
|
"loss": 4.6219,
|
|
"mean_token_accuracy": 0.22439239472150802,
|
|
"num_tokens": 57906005.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 4.875596761703491,
|
|
"epoch": 2.4681357951161407,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004401024728331411,
|
|
"loss": 4.6023,
|
|
"mean_token_accuracy": 0.2180560439825058,
|
|
"num_tokens": 57920411.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 4.902566194534302,
|
|
"epoch": 2.4687313877307924,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044007351980059826,
|
|
"loss": 4.543,
|
|
"mean_token_accuracy": 0.23331372886896135,
|
|
"num_tokens": 57933230.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 4.73729190826416,
|
|
"epoch": 2.4693269803454436,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004400445608471367,
|
|
"loss": 4.4364,
|
|
"mean_token_accuracy": 0.24126427620649338,
|
|
"num_tokens": 57946923.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 4.810011482238769,
|
|
"epoch": 2.4699225729600953,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044001559597379503,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.233165043592453,
|
|
"num_tokens": 57960545.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 4.929312229156494,
|
|
"epoch": 2.470518165574747,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043998662518161233,
|
|
"loss": 4.5956,
|
|
"mean_token_accuracy": 0.22498399019241333,
|
|
"num_tokens": 57975564.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 4.826607513427734,
|
|
"epoch": 2.4711137581893983,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043995764847162757,
|
|
"loss": 4.5199,
|
|
"mean_token_accuracy": 0.22667265236377715,
|
|
"num_tokens": 57990047.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 4.888105583190918,
|
|
"epoch": 2.47170935080405,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00043992866584488007,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.2172805979847908,
|
|
"num_tokens": 58005850.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 4.872926378250122,
|
|
"epoch": 2.4723049434187017,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004398996773024096,
|
|
"loss": 4.5375,
|
|
"mean_token_accuracy": 0.23066404461860657,
|
|
"num_tokens": 58018473.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 4.895884895324707,
|
|
"epoch": 2.4729005360333534,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004398706828452558,
|
|
"loss": 4.5591,
|
|
"mean_token_accuracy": 0.22812532186508178,
|
|
"num_tokens": 58032893.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 4.750955533981323,
|
|
"epoch": 2.4734961286480046,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004398416824744586,
|
|
"loss": 4.4152,
|
|
"mean_token_accuracy": 0.24079397320747375,
|
|
"num_tokens": 58046031.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 4.81490650177002,
|
|
"epoch": 2.4740917212626563,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043981267619105837,
|
|
"loss": 4.5809,
|
|
"mean_token_accuracy": 0.2286459118127823,
|
|
"num_tokens": 58059589.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 4.961374950408936,
|
|
"epoch": 2.474687313877308,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004397836639960953,
|
|
"loss": 4.6626,
|
|
"mean_token_accuracy": 0.2224809393286705,
|
|
"num_tokens": 58073042.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 4.900942182540893,
|
|
"epoch": 2.4752829064919597,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004397546458906102,
|
|
"loss": 4.6034,
|
|
"mean_token_accuracy": 0.2272923320531845,
|
|
"num_tokens": 58087450.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 4.815643453598023,
|
|
"epoch": 2.475878499106611,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043972562187564383,
|
|
"loss": 4.5573,
|
|
"mean_token_accuracy": 0.22589488476514816,
|
|
"num_tokens": 58101167.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 4.839102697372437,
|
|
"epoch": 2.4764740917212626,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004396965919522373,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.2305302992463112,
|
|
"num_tokens": 58116010.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 4.89480619430542,
|
|
"epoch": 2.4770696843359143,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043966755612143165,
|
|
"loss": 4.5563,
|
|
"mean_token_accuracy": 0.22653389126062393,
|
|
"num_tokens": 58132318.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 4.90176944732666,
|
|
"epoch": 2.4776652769505656,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043963851438426853,
|
|
"loss": 4.6213,
|
|
"mean_token_accuracy": 0.22305260896682738,
|
|
"num_tokens": 58145953.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 4.905824851989746,
|
|
"epoch": 2.4782608695652173,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004396094667417896,
|
|
"loss": 4.5983,
|
|
"mean_token_accuracy": 0.22913058400154113,
|
|
"num_tokens": 58160544.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 4.87578935623169,
|
|
"epoch": 2.478856462179869,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004395804131950368,
|
|
"loss": 4.5672,
|
|
"mean_token_accuracy": 0.23126426637172698,
|
|
"num_tokens": 58174894.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 4.903935718536377,
|
|
"epoch": 2.4794520547945207,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043955135374505207,
|
|
"loss": 4.6627,
|
|
"mean_token_accuracy": 0.21690732836723328,
|
|
"num_tokens": 58187061.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 4.856619358062744,
|
|
"epoch": 2.480047647409172,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004395222883928779,
|
|
"loss": 4.5884,
|
|
"mean_token_accuracy": 0.22172045707702637,
|
|
"num_tokens": 58201815.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 4.866835832595825,
|
|
"epoch": 2.4806432400238236,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00043949321713955677,
|
|
"loss": 4.5114,
|
|
"mean_token_accuracy": 0.23194492906332015,
|
|
"num_tokens": 58216781.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 4.792842388153076,
|
|
"epoch": 2.4812388326384753,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004394641399861313,
|
|
"loss": 4.4607,
|
|
"mean_token_accuracy": 0.2390895590186119,
|
|
"num_tokens": 58229594.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 4.8151716709136965,
|
|
"epoch": 2.481834425253127,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004394350569336445,
|
|
"loss": 4.5196,
|
|
"mean_token_accuracy": 0.2346224531531334,
|
|
"num_tokens": 58243140.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 4.870674133300781,
|
|
"epoch": 2.4824300178677783,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043940596798313963,
|
|
"loss": 4.5775,
|
|
"mean_token_accuracy": 0.22714990079402925,
|
|
"num_tokens": 58256927.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 4.856133890151978,
|
|
"epoch": 2.48302561048243,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043937687313565997,
|
|
"loss": 4.5538,
|
|
"mean_token_accuracy": 0.2334309548139572,
|
|
"num_tokens": 58271768.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 4.817230129241944,
|
|
"epoch": 2.4836212030970817,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004393477723922492,
|
|
"loss": 4.5658,
|
|
"mean_token_accuracy": 0.22932620197534562,
|
|
"num_tokens": 58286263.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 4.901356315612793,
|
|
"epoch": 2.484216795711733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000439318665753951,
|
|
"loss": 4.6041,
|
|
"mean_token_accuracy": 0.22113602608442307,
|
|
"num_tokens": 58299287.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 4.874518013000488,
|
|
"epoch": 2.4848123883263846,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043928955322180944,
|
|
"loss": 4.5245,
|
|
"mean_token_accuracy": 0.2423069193959236,
|
|
"num_tokens": 58312482.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 4.8655839443206785,
|
|
"epoch": 2.4854079809410363,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004392604347968687,
|
|
"loss": 4.5535,
|
|
"mean_token_accuracy": 0.2239435061812401,
|
|
"num_tokens": 58324684.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 4.947835254669189,
|
|
"epoch": 2.486003573555688,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00043923131048017325,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.22342014759778978,
|
|
"num_tokens": 58338342.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 4.979325151443481,
|
|
"epoch": 2.4865991661703397,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043920218027276777,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.22257298976182938,
|
|
"num_tokens": 58352819.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 4.876912546157837,
|
|
"epoch": 2.487194758784991,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043917304417569696,
|
|
"loss": 4.5753,
|
|
"mean_token_accuracy": 0.22662743479013442,
|
|
"num_tokens": 58365952.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 4.868523120880127,
|
|
"epoch": 2.4877903513996427,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043914390219000605,
|
|
"loss": 4.563,
|
|
"mean_token_accuracy": 0.230870521068573,
|
|
"num_tokens": 58378631.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 4.872938728332519,
|
|
"epoch": 2.4883859440142944,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043911475431674025,
|
|
"loss": 4.5961,
|
|
"mean_token_accuracy": 0.22184165716171264,
|
|
"num_tokens": 58390534.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 4.87645583152771,
|
|
"epoch": 2.4889815366289456,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000439085600556945,
|
|
"loss": 4.5422,
|
|
"mean_token_accuracy": 0.21911029368638993,
|
|
"num_tokens": 58404248.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 4.83900728225708,
|
|
"epoch": 2.4895771292435973,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004390564409116661,
|
|
"loss": 4.5769,
|
|
"mean_token_accuracy": 0.22415815889835358,
|
|
"num_tokens": 58417139.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 4.727552652359009,
|
|
"epoch": 2.490172721858249,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004390272753819494,
|
|
"loss": 4.3394,
|
|
"mean_token_accuracy": 0.2416957661509514,
|
|
"num_tokens": 58431131.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 4.85667839050293,
|
|
"epoch": 2.4907683144729007,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000438998103968841,
|
|
"loss": 4.5903,
|
|
"mean_token_accuracy": 0.21973622143268584,
|
|
"num_tokens": 58446378.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 4.8955522060394285,
|
|
"epoch": 2.491363907087552,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043896892667338725,
|
|
"loss": 4.5389,
|
|
"mean_token_accuracy": 0.22775135487318038,
|
|
"num_tokens": 58460441.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 4.826772737503052,
|
|
"epoch": 2.4919594997022037,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043893974349663465,
|
|
"loss": 4.55,
|
|
"mean_token_accuracy": 0.22654869854450227,
|
|
"num_tokens": 58474080.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 4.9320062637329105,
|
|
"epoch": 2.4925550923168553,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004389105544396301,
|
|
"loss": 4.574,
|
|
"mean_token_accuracy": 0.22559189200401306,
|
|
"num_tokens": 58488376.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 4.824117994308471,
|
|
"epoch": 2.493150684931507,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004388813595034204,
|
|
"loss": 4.4654,
|
|
"mean_token_accuracy": 0.23477060794830323,
|
|
"num_tokens": 58501413.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 4.830453824996948,
|
|
"epoch": 2.4937462775461583,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043885215868905283,
|
|
"loss": 4.5776,
|
|
"mean_token_accuracy": 0.22763926386833191,
|
|
"num_tokens": 58517520.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 4.9258016586303714,
|
|
"epoch": 2.49434187016081,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043882295199757464,
|
|
"loss": 4.6066,
|
|
"mean_token_accuracy": 0.2287517100572586,
|
|
"num_tokens": 58533394.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 4.82773609161377,
|
|
"epoch": 2.4949374627754617,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004387937394300336,
|
|
"loss": 4.4964,
|
|
"mean_token_accuracy": 0.23302806466817855,
|
|
"num_tokens": 58547108.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 4.879446029663086,
|
|
"epoch": 2.495533055390113,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004387645209874775,
|
|
"loss": 4.6204,
|
|
"mean_token_accuracy": 0.22494959086179733,
|
|
"num_tokens": 58559612.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 4.875083065032959,
|
|
"epoch": 2.4961286480047646,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043873529667095423,
|
|
"loss": 4.6238,
|
|
"mean_token_accuracy": 0.2225533127784729,
|
|
"num_tokens": 58573357.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 4.854031991958618,
|
|
"epoch": 2.4967242406194163,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00043870606648151205,
|
|
"loss": 4.5373,
|
|
"mean_token_accuracy": 0.22945906817913056,
|
|
"num_tokens": 58588694.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 4.9013337135314945,
|
|
"epoch": 2.497319833234068,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004386768304201995,
|
|
"loss": 4.5888,
|
|
"mean_token_accuracy": 0.2213882863521576,
|
|
"num_tokens": 58600706.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 4.795654821395874,
|
|
"epoch": 2.4979154258487193,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043864758848806515,
|
|
"loss": 4.494,
|
|
"mean_token_accuracy": 0.23063374012708665,
|
|
"num_tokens": 58616314.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 4.8360742092132565,
|
|
"epoch": 2.498511018463371,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004386183406861579,
|
|
"loss": 4.567,
|
|
"mean_token_accuracy": 0.22065166234970093,
|
|
"num_tokens": 58630551.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 4.848541021347046,
|
|
"epoch": 2.4991066110780227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004385890870155267,
|
|
"loss": 4.488,
|
|
"mean_token_accuracy": 0.2331176608800888,
|
|
"num_tokens": 58645375.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 4.8802698135375975,
|
|
"epoch": 2.4997022036926744,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000438559827477221,
|
|
"loss": 4.5944,
|
|
"mean_token_accuracy": 0.22249606847763062,
|
|
"num_tokens": 58659869.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 4.893244123458862,
|
|
"epoch": 2.5002977963073256,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004385305620722902,
|
|
"loss": 4.64,
|
|
"mean_token_accuracy": 0.22912342995405197,
|
|
"num_tokens": 58672387.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 4.847914600372315,
|
|
"epoch": 2.5008933889219773,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000438501290801784,
|
|
"loss": 4.5109,
|
|
"mean_token_accuracy": 0.23119241297245025,
|
|
"num_tokens": 58684579.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 4.919333600997925,
|
|
"epoch": 2.501488981536629,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00043847201366675243,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.2260775610804558,
|
|
"num_tokens": 58700602.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.501488981536629,
|
|
"eval_entropy": 4.683235571526435,
|
|
"eval_loss": 4.639752388000488,
|
|
"eval_mean_token_accuracy": 0.2332399291608214,
|
|
"eval_num_tokens": 58700602.0,
|
|
"eval_runtime": 24.0739,
|
|
"eval_samples_per_second": 1059.777,
|
|
"eval_steps_per_second": 132.509,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 4.926985073089599,
|
|
"epoch": 2.5020845741512803,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004384427306682454,
|
|
"loss": 4.6257,
|
|
"mean_token_accuracy": 0.22496311366558075,
|
|
"num_tokens": 58715390.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 4.907166385650635,
|
|
"epoch": 2.502680166765932,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043841344180731346,
|
|
"loss": 4.613,
|
|
"mean_token_accuracy": 0.22958025485277175,
|
|
"num_tokens": 58728744.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 4.84218921661377,
|
|
"epoch": 2.5032757593805837,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043838414708500704,
|
|
"loss": 4.6296,
|
|
"mean_token_accuracy": 0.2276274800300598,
|
|
"num_tokens": 58740813.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 4.858185148239135,
|
|
"epoch": 2.5038713519952354,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043835484650237683,
|
|
"loss": 4.4475,
|
|
"mean_token_accuracy": 0.23709721267223358,
|
|
"num_tokens": 58755314.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 4.889216518402099,
|
|
"epoch": 2.504466944609887,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000438325540060474,
|
|
"loss": 4.5996,
|
|
"mean_token_accuracy": 0.22885765582323075,
|
|
"num_tokens": 58768775.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 4.809407663345337,
|
|
"epoch": 2.5050625372245383,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004382962277603495,
|
|
"loss": 4.5751,
|
|
"mean_token_accuracy": 0.22198670357465744,
|
|
"num_tokens": 58784017.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 4.857471990585327,
|
|
"epoch": 2.50565812983919,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004382669096030548,
|
|
"loss": 4.5082,
|
|
"mean_token_accuracy": 0.23695261925458908,
|
|
"num_tokens": 58797647.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.016806745529175,
|
|
"epoch": 2.5062537224538417,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004382375855896416,
|
|
"loss": 4.653,
|
|
"mean_token_accuracy": 0.21332966536283493,
|
|
"num_tokens": 58813343.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 4.779447174072265,
|
|
"epoch": 2.506849315068493,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004382082557211615,
|
|
"loss": 4.5296,
|
|
"mean_token_accuracy": 0.22936424762010574,
|
|
"num_tokens": 58827650.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 4.777522802352905,
|
|
"epoch": 2.5074449076831447,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004381789199986667,
|
|
"loss": 4.4958,
|
|
"mean_token_accuracy": 0.22694956213235856,
|
|
"num_tokens": 58842558.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 4.948033475875855,
|
|
"epoch": 2.5080405002977963,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004381495784232093,
|
|
"loss": 4.5988,
|
|
"mean_token_accuracy": 0.22329859733581542,
|
|
"num_tokens": 58856508.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 4.902203893661499,
|
|
"epoch": 2.508636092912448,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00043812023099584193,
|
|
"loss": 4.5249,
|
|
"mean_token_accuracy": 0.23147984594106674,
|
|
"num_tokens": 58870124.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 4.786685132980347,
|
|
"epoch": 2.5092316855270993,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000438090877717617,
|
|
"loss": 4.4529,
|
|
"mean_token_accuracy": 0.2391124576330185,
|
|
"num_tokens": 58883021.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 4.840058469772339,
|
|
"epoch": 2.509827278141751,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004380615185895874,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.23108444958925248,
|
|
"num_tokens": 58897644.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 4.841056442260742,
|
|
"epoch": 2.5104228707564027,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043803215361280627,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.2280863955616951,
|
|
"num_tokens": 58909979.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 4.886591863632202,
|
|
"epoch": 2.5110184633710544,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043800278278832694,
|
|
"loss": 4.5146,
|
|
"mean_token_accuracy": 0.22800950706005096,
|
|
"num_tokens": 58923596.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 4.902657127380371,
|
|
"epoch": 2.5116140559857056,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043797340611720283,
|
|
"loss": 4.6345,
|
|
"mean_token_accuracy": 0.2205516591668129,
|
|
"num_tokens": 58938571.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 4.884707927703857,
|
|
"epoch": 2.5122096486003573,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004379440236004875,
|
|
"loss": 4.5862,
|
|
"mean_token_accuracy": 0.2339065358042717,
|
|
"num_tokens": 58952428.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 4.814919281005859,
|
|
"epoch": 2.512805241215009,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004379146352392351,
|
|
"loss": 4.5385,
|
|
"mean_token_accuracy": 0.22849913090467452,
|
|
"num_tokens": 58967493.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 4.896069145202636,
|
|
"epoch": 2.5134008338296603,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004378852410344995,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.22817918360233308,
|
|
"num_tokens": 58983979.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 4.963620805740357,
|
|
"epoch": 2.513996426444312,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043785584098733523,
|
|
"loss": 4.6672,
|
|
"mean_token_accuracy": 0.21921671479940413,
|
|
"num_tokens": 58998007.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 4.89822826385498,
|
|
"epoch": 2.5145920190589637,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00043782643509879666,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.22183272540569304,
|
|
"num_tokens": 59011206.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 4.892215538024902,
|
|
"epoch": 2.5151876116736154,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043779702336993866,
|
|
"loss": 4.5696,
|
|
"mean_token_accuracy": 0.22645533680915833,
|
|
"num_tokens": 59027627.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 4.807185459136963,
|
|
"epoch": 2.515783204288267,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004377676058018161,
|
|
"loss": 4.499,
|
|
"mean_token_accuracy": 0.22975049018859864,
|
|
"num_tokens": 59041343.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 4.8200994491577145,
|
|
"epoch": 2.5163787969029183,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043773818239548415,
|
|
"loss": 4.6078,
|
|
"mean_token_accuracy": 0.23027001172304154,
|
|
"num_tokens": 59056303.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 4.964636707305909,
|
|
"epoch": 2.51697438951757,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043770875315199816,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.22698282152414323,
|
|
"num_tokens": 59068597.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 4.839831304550171,
|
|
"epoch": 2.5175699821322217,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004376793180724138,
|
|
"loss": 4.5621,
|
|
"mean_token_accuracy": 0.2271113097667694,
|
|
"num_tokens": 59082570.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 4.8110819339752195,
|
|
"epoch": 2.518165574746873,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004376498771577868,
|
|
"loss": 4.5229,
|
|
"mean_token_accuracy": 0.23015276193618775,
|
|
"num_tokens": 59097033.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 4.899882411956787,
|
|
"epoch": 2.5187611673615247,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043762043040917315,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.22409008145332338,
|
|
"num_tokens": 59111876.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 4.936164712905883,
|
|
"epoch": 2.5193567599761764,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043759097782762905,
|
|
"loss": 4.6514,
|
|
"mean_token_accuracy": 0.22287847101688385,
|
|
"num_tokens": 59124552.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 4.904137992858887,
|
|
"epoch": 2.5199523525908276,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043756151941421096,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.22200465500354766,
|
|
"num_tokens": 59136112.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 4.873222541809082,
|
|
"epoch": 2.5205479452054793,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004375320551699755,
|
|
"loss": 4.5317,
|
|
"mean_token_accuracy": 0.23349160701036453,
|
|
"num_tokens": 59147670.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 4.895485162734985,
|
|
"epoch": 2.521143537820131,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00043750258509597947,
|
|
"loss": 4.635,
|
|
"mean_token_accuracy": 0.21787566393613816,
|
|
"num_tokens": 59162519.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 4.931606006622315,
|
|
"epoch": 2.5217391304347827,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043747310919327987,
|
|
"loss": 4.5675,
|
|
"mean_token_accuracy": 0.23366331905126572,
|
|
"num_tokens": 59176482.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 4.870046520233155,
|
|
"epoch": 2.5223347230494344,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004374436274629341,
|
|
"loss": 4.6452,
|
|
"mean_token_accuracy": 0.22697862535715102,
|
|
"num_tokens": 59190023.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 4.889744234085083,
|
|
"epoch": 2.5229303156640857,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043741413990599945,
|
|
"loss": 4.6202,
|
|
"mean_token_accuracy": 0.21427982449531555,
|
|
"num_tokens": 59205110.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 4.848302173614502,
|
|
"epoch": 2.5235259082787374,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004373846465235337,
|
|
"loss": 4.5114,
|
|
"mean_token_accuracy": 0.2310301348567009,
|
|
"num_tokens": 59218208.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 4.890857315063476,
|
|
"epoch": 2.524121500893389,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043735514731659464,
|
|
"loss": 4.6091,
|
|
"mean_token_accuracy": 0.22310724556446077,
|
|
"num_tokens": 59230076.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 4.889851999282837,
|
|
"epoch": 2.5247170935080403,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004373256422862405,
|
|
"loss": 4.601,
|
|
"mean_token_accuracy": 0.22004408687353133,
|
|
"num_tokens": 59244154.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 4.932935810089111,
|
|
"epoch": 2.525312686122692,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004372961314335295,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.2239266201853752,
|
|
"num_tokens": 59258090.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 4.809162139892578,
|
|
"epoch": 2.5259082787373437,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043726661475952005,
|
|
"loss": 4.5086,
|
|
"mean_token_accuracy": 0.2307078242301941,
|
|
"num_tokens": 59272574.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 4.836608839035034,
|
|
"epoch": 2.5265038713519954,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043723709226527104,
|
|
"loss": 4.4709,
|
|
"mean_token_accuracy": 0.22779664546251296,
|
|
"num_tokens": 59288552.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 4.8971484184265135,
|
|
"epoch": 2.527099463966647,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004372075639518413,
|
|
"loss": 4.6224,
|
|
"mean_token_accuracy": 0.2261826753616333,
|
|
"num_tokens": 59301235.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 4.889597463607788,
|
|
"epoch": 2.5276950565812983,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043717802982029,
|
|
"loss": 4.5895,
|
|
"mean_token_accuracy": 0.22690475583076478,
|
|
"num_tokens": 59314676.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 4.88880033493042,
|
|
"epoch": 2.52829064919595,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004371484898716763,
|
|
"loss": 4.5937,
|
|
"mean_token_accuracy": 0.21385786384344102,
|
|
"num_tokens": 59329333.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 4.849575185775757,
|
|
"epoch": 2.5288862418106017,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004371189441070602,
|
|
"loss": 4.5432,
|
|
"mean_token_accuracy": 0.22600036561489106,
|
|
"num_tokens": 59344297.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 4.82045202255249,
|
|
"epoch": 2.529481834425253,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043708939252750094,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.2360813483595848,
|
|
"num_tokens": 59357212.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 4.878141975402832,
|
|
"epoch": 2.5300774270399047,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004370598351340587,
|
|
"loss": 4.5731,
|
|
"mean_token_accuracy": 0.23531631380319595,
|
|
"num_tokens": 59369650.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 4.9472943305969235,
|
|
"epoch": 2.5306730196545564,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004370302719277937,
|
|
"loss": 4.6415,
|
|
"mean_token_accuracy": 0.2224885493516922,
|
|
"num_tokens": 59384040.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 4.8470385551452635,
|
|
"epoch": 2.5312686122692076,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004370007029097664,
|
|
"loss": 4.5751,
|
|
"mean_token_accuracy": 0.22328344583511353,
|
|
"num_tokens": 59399241.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 4.825785493850708,
|
|
"epoch": 2.5318642048838593,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004369711280810372,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.23382875323295593,
|
|
"num_tokens": 59412282.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 4.917511940002441,
|
|
"epoch": 2.532459797498511,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000436941547442667,
|
|
"loss": 4.5747,
|
|
"mean_token_accuracy": 0.2194327548146248,
|
|
"num_tokens": 59425247.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 4.819691133499146,
|
|
"epoch": 2.5330553901131627,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043691196099571676,
|
|
"loss": 4.5332,
|
|
"mean_token_accuracy": 0.22905754745006562,
|
|
"num_tokens": 59439120.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 4.88258376121521,
|
|
"epoch": 2.5336509827278144,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043688236874124775,
|
|
"loss": 4.625,
|
|
"mean_token_accuracy": 0.22787285298109056,
|
|
"num_tokens": 59454214.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 4.902551460266113,
|
|
"epoch": 2.5342465753424657,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043685277068032137,
|
|
"loss": 4.5353,
|
|
"mean_token_accuracy": 0.22967504113912582,
|
|
"num_tokens": 59468782.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 4.8730991840362545,
|
|
"epoch": 2.5348421679571174,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043682316681399933,
|
|
"loss": 4.6335,
|
|
"mean_token_accuracy": 0.2196616053581238,
|
|
"num_tokens": 59484901.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 4.897872066497802,
|
|
"epoch": 2.535437760571769,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004367935571433433,
|
|
"loss": 4.5122,
|
|
"mean_token_accuracy": 0.2334948182106018,
|
|
"num_tokens": 59499104.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 4.950750875473022,
|
|
"epoch": 2.5360333531864203,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043676394166941546,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.21516248285770417,
|
|
"num_tokens": 59512166.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 4.861770963668823,
|
|
"epoch": 2.536628945801072,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004367343203932781,
|
|
"loss": 4.5708,
|
|
"mean_token_accuracy": 0.23017632365226745,
|
|
"num_tokens": 59527382.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 4.987688446044922,
|
|
"epoch": 2.5372245384157237,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004367046933159936,
|
|
"loss": 4.6791,
|
|
"mean_token_accuracy": 0.22722817957401276,
|
|
"num_tokens": 59540431.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 4.865930461883545,
|
|
"epoch": 2.537820131030375,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00043667506043862473,
|
|
"loss": 4.5251,
|
|
"mean_token_accuracy": 0.22590213567018508,
|
|
"num_tokens": 59556239.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 4.799503517150879,
|
|
"epoch": 2.5384157236450267,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043664542176223423,
|
|
"loss": 4.4721,
|
|
"mean_token_accuracy": 0.2333889737725258,
|
|
"num_tokens": 59571810.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 4.860621070861816,
|
|
"epoch": 2.5390113162596784,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043661577728788527,
|
|
"loss": 4.6074,
|
|
"mean_token_accuracy": 0.22849464267492295,
|
|
"num_tokens": 59586007.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 4.904930257797242,
|
|
"epoch": 2.53960690887433,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004365861270166411,
|
|
"loss": 4.5318,
|
|
"mean_token_accuracy": 0.22666636407375335,
|
|
"num_tokens": 59599477.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 4.878209829330444,
|
|
"epoch": 2.5402025014889817,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004365564709495654,
|
|
"loss": 4.542,
|
|
"mean_token_accuracy": 0.2380587324500084,
|
|
"num_tokens": 59612640.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 4.892423868179321,
|
|
"epoch": 2.540798094103633,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004365268090877217,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.229528246819973,
|
|
"num_tokens": 59625234.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 4.825111675262451,
|
|
"epoch": 2.5413936867182847,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000436497141432174,
|
|
"loss": 4.5355,
|
|
"mean_token_accuracy": 0.23175166994333268,
|
|
"num_tokens": 59638390.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 4.885896444320679,
|
|
"epoch": 2.5419892793329364,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004364674679839864,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.230689737200737,
|
|
"num_tokens": 59649707.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 4.888416910171509,
|
|
"epoch": 2.5425848719475876,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004364377887442233,
|
|
"loss": 4.5968,
|
|
"mean_token_accuracy": 0.226800537109375,
|
|
"num_tokens": 59662170.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 4.893464422225952,
|
|
"epoch": 2.5431804645622393,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004364081037139491,
|
|
"loss": 4.6352,
|
|
"mean_token_accuracy": 0.2249199077486992,
|
|
"num_tokens": 59675069.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 4.844336986541748,
|
|
"epoch": 2.543776057176891,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004363784128942288,
|
|
"loss": 4.4795,
|
|
"mean_token_accuracy": 0.2339599534869194,
|
|
"num_tokens": 59688259.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 4.936888265609741,
|
|
"epoch": 2.5443716497915427,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004363487162861271,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.21810967922210694,
|
|
"num_tokens": 59702754.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 4.847635984420776,
|
|
"epoch": 2.5449672424061944,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004363190138907093,
|
|
"loss": 4.5268,
|
|
"mean_token_accuracy": 0.22978056222200394,
|
|
"num_tokens": 59717306.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 4.805173873901367,
|
|
"epoch": 2.5455628350208457,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004362893057090408,
|
|
"loss": 4.553,
|
|
"mean_token_accuracy": 0.2204946905374527,
|
|
"num_tokens": 59731708.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 4.843677806854248,
|
|
"epoch": 2.5461584276354974,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004362595917421871,
|
|
"loss": 4.4933,
|
|
"mean_token_accuracy": 0.23131750375032425,
|
|
"num_tokens": 59745167.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 4.817971134185791,
|
|
"epoch": 2.546754020250149,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00043622987199121404,
|
|
"loss": 4.4203,
|
|
"mean_token_accuracy": 0.23760322481393814,
|
|
"num_tokens": 59759010.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 4.889926528930664,
|
|
"epoch": 2.5473496128648003,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043620014645718766,
|
|
"loss": 4.6229,
|
|
"mean_token_accuracy": 0.21548486799001693,
|
|
"num_tokens": 59772843.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 4.862922096252442,
|
|
"epoch": 2.547945205479452,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043617041514117403,
|
|
"loss": 4.5296,
|
|
"mean_token_accuracy": 0.2287150502204895,
|
|
"num_tokens": 59787612.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 4.849932622909546,
|
|
"epoch": 2.5485407980941037,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004361406780442398,
|
|
"loss": 4.5072,
|
|
"mean_token_accuracy": 0.2324094608426094,
|
|
"num_tokens": 59802899.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 4.962994337081909,
|
|
"epoch": 2.549136390708755,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004361109351674513,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.2176858201622963,
|
|
"num_tokens": 59817768.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 4.917923021316528,
|
|
"epoch": 2.5497319833234067,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043608118651187555,
|
|
"loss": 4.6247,
|
|
"mean_token_accuracy": 0.22268344908952714,
|
|
"num_tokens": 59831680.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 4.89577808380127,
|
|
"epoch": 2.5503275759380584,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043605143207857964,
|
|
"loss": 4.5947,
|
|
"mean_token_accuracy": 0.22625698894262314,
|
|
"num_tokens": 59846065.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 4.848909378051758,
|
|
"epoch": 2.55092316855271,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004360216718686306,
|
|
"loss": 4.4892,
|
|
"mean_token_accuracy": 0.24179550558328627,
|
|
"num_tokens": 59857954.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 4.883067512512207,
|
|
"epoch": 2.5515187611673618,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043599190588309607,
|
|
"loss": 4.5708,
|
|
"mean_token_accuracy": 0.2273808464407921,
|
|
"num_tokens": 59870964.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 4.9604088306427006,
|
|
"epoch": 2.552114353782013,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043596213412304353,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.21753744781017303,
|
|
"num_tokens": 59883420.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 4.864326333999633,
|
|
"epoch": 2.5527099463966647,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043593235658954103,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.2242772787809372,
|
|
"num_tokens": 59896895.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 4.837212371826172,
|
|
"epoch": 2.5533055390113164,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00043590257328365655,
|
|
"loss": 4.5064,
|
|
"mean_token_accuracy": 0.23034160286188127,
|
|
"num_tokens": 59911861.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 4.844911575317383,
|
|
"epoch": 2.5539011316259677,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043587278420645836,
|
|
"loss": 4.4923,
|
|
"mean_token_accuracy": 0.23833144903182985,
|
|
"num_tokens": 59926101.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 4.895536231994629,
|
|
"epoch": 2.5544967242406194,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043584298935901494,
|
|
"loss": 4.5235,
|
|
"mean_token_accuracy": 0.22704419046640395,
|
|
"num_tokens": 59939818.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 4.875039958953858,
|
|
"epoch": 2.555092316855271,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043581318874239504,
|
|
"loss": 4.6066,
|
|
"mean_token_accuracy": 0.2214837059378624,
|
|
"num_tokens": 59953939.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 4.816747093200684,
|
|
"epoch": 2.5556879094699223,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043578338235766763,
|
|
"loss": 4.4562,
|
|
"mean_token_accuracy": 0.24059419929981232,
|
|
"num_tokens": 59966023.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 4.95373215675354,
|
|
"epoch": 2.556283502084574,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004357535702059016,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.22708576470613479,
|
|
"num_tokens": 59978909.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 4.893396997451783,
|
|
"epoch": 2.5568790946992257,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00043572375228816633,
|
|
"loss": 4.595,
|
|
"mean_token_accuracy": 0.22849078923463823,
|
|
"num_tokens": 59993873.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 4.937966394424438,
|
|
"epoch": 2.5574746873138774,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043569392860553146,
|
|
"loss": 4.6446,
|
|
"mean_token_accuracy": 0.21830725073814392,
|
|
"num_tokens": 60010001.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 4.83690824508667,
|
|
"epoch": 2.558070279928529,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00043566409915906664,
|
|
"loss": 4.5125,
|
|
"mean_token_accuracy": 0.23188397139310837,
|
|
"num_tokens": 60026801.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 4.832773065567016,
|
|
"epoch": 2.5586658725431803,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004356342639498418,
|
|
"loss": 4.5798,
|
|
"mean_token_accuracy": 0.22307548224925994,
|
|
"num_tokens": 60041153.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 4.8757771968841555,
|
|
"epoch": 2.559261465157832,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043560442297892703,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.22689546942710875,
|
|
"num_tokens": 60055349.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 4.988231611251831,
|
|
"epoch": 2.5598570577724837,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043557457624739283,
|
|
"loss": 4.6636,
|
|
"mean_token_accuracy": 0.2156881347298622,
|
|
"num_tokens": 60069181.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 4.7854530811309814,
|
|
"epoch": 2.560452650387135,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004355447237563096,
|
|
"loss": 4.4397,
|
|
"mean_token_accuracy": 0.2416374757885933,
|
|
"num_tokens": 60083260.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 4.790687179565429,
|
|
"epoch": 2.5610482430017867,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043551486550674816,
|
|
"loss": 4.553,
|
|
"mean_token_accuracy": 0.22832393944263457,
|
|
"num_tokens": 60095554.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 4.861449384689331,
|
|
"epoch": 2.5616438356164384,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043548500149977946,
|
|
"loss": 4.5484,
|
|
"mean_token_accuracy": 0.23054974228143693,
|
|
"num_tokens": 60110809.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 4.919188022613525,
|
|
"epoch": 2.56223942823109,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043545513173647477,
|
|
"loss": 4.5803,
|
|
"mean_token_accuracy": 0.23106000125408171,
|
|
"num_tokens": 60123356.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 4.8645336627960205,
|
|
"epoch": 2.5628350208457418,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004354252562179053,
|
|
"loss": 4.5905,
|
|
"mean_token_accuracy": 0.22876424789428712,
|
|
"num_tokens": 60136893.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 4.80634617805481,
|
|
"epoch": 2.563430613460393,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043539537494514274,
|
|
"loss": 4.5574,
|
|
"mean_token_accuracy": 0.2310217946767807,
|
|
"num_tokens": 60150367.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 4.917964029312134,
|
|
"epoch": 2.5640262060750447,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004353654879192589,
|
|
"loss": 4.6683,
|
|
"mean_token_accuracy": 0.22651851028203965,
|
|
"num_tokens": 60165142.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 4.901803398132325,
|
|
"epoch": 2.5646217986896964,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004353355951413258,
|
|
"loss": 4.5631,
|
|
"mean_token_accuracy": 0.2249869540333748,
|
|
"num_tokens": 60180351.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 4.8321977138519285,
|
|
"epoch": 2.5652173913043477,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043530569661241546,
|
|
"loss": 4.5531,
|
|
"mean_token_accuracy": 0.23052644431591035,
|
|
"num_tokens": 60193347.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 4.92244234085083,
|
|
"epoch": 2.5658129839189994,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00043527579233360047,
|
|
"loss": 4.5855,
|
|
"mean_token_accuracy": 0.22472635954618453,
|
|
"num_tokens": 60208120.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 4.782607793807983,
|
|
"epoch": 2.566408576533651,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043524588230595346,
|
|
"loss": 4.4537,
|
|
"mean_token_accuracy": 0.2409543812274933,
|
|
"num_tokens": 60221910.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 4.864401817321777,
|
|
"epoch": 2.5670041691483023,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00043521596653054714,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.2247088834643364,
|
|
"num_tokens": 60236504.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 4.8846746444702145,
|
|
"epoch": 2.567599761762954,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004351860450084546,
|
|
"loss": 4.5895,
|
|
"mean_token_accuracy": 0.22140759825706482,
|
|
"num_tokens": 60251546.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 4.882456493377686,
|
|
"epoch": 2.5681953543776057,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004351561177407491,
|
|
"loss": 4.551,
|
|
"mean_token_accuracy": 0.23249933868646622,
|
|
"num_tokens": 60265001.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 4.883697652816773,
|
|
"epoch": 2.5687909469922574,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043512618472850407,
|
|
"loss": 4.5415,
|
|
"mean_token_accuracy": 0.23004311621189116,
|
|
"num_tokens": 60276971.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 4.864464807510376,
|
|
"epoch": 2.569386539606909,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043509624597279313,
|
|
"loss": 4.5943,
|
|
"mean_token_accuracy": 0.22781717032194138,
|
|
"num_tokens": 60291971.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 4.76361346244812,
|
|
"epoch": 2.5699821322215604,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043506630147469006,
|
|
"loss": 4.4412,
|
|
"mean_token_accuracy": 0.23415980190038682,
|
|
"num_tokens": 60308074.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 4.818732976913452,
|
|
"epoch": 2.570577724836212,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00043503635123526914,
|
|
"loss": 4.4686,
|
|
"mean_token_accuracy": 0.23503712564706802,
|
|
"num_tokens": 60320991.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 4.8721014022827145,
|
|
"epoch": 2.5711733174508637,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043500639525560444,
|
|
"loss": 4.5425,
|
|
"mean_token_accuracy": 0.22411130964756013,
|
|
"num_tokens": 60334645.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 4.867046308517456,
|
|
"epoch": 2.571768910065515,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043497643353677045,
|
|
"loss": 4.5635,
|
|
"mean_token_accuracy": 0.23191444277763368,
|
|
"num_tokens": 60347402.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 4.84714035987854,
|
|
"epoch": 2.5723645026801667,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043494646607984195,
|
|
"loss": 4.5513,
|
|
"mean_token_accuracy": 0.22659215927124024,
|
|
"num_tokens": 60362247.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 4.828311204910278,
|
|
"epoch": 2.5729600952948184,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004349164928858938,
|
|
"loss": 4.4848,
|
|
"mean_token_accuracy": 0.23841723799705505,
|
|
"num_tokens": 60375559.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 4.8842720031738285,
|
|
"epoch": 2.5735556879094696,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043488651395600096,
|
|
"loss": 4.5867,
|
|
"mean_token_accuracy": 0.2191849559545517,
|
|
"num_tokens": 60390523.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 4.835341453552246,
|
|
"epoch": 2.5741512805241213,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043485652929123894,
|
|
"loss": 4.5813,
|
|
"mean_token_accuracy": 0.2227875515818596,
|
|
"num_tokens": 60405704.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 4.9055413722991945,
|
|
"epoch": 2.574746873138773,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004348265388926831,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.22512649297714232,
|
|
"num_tokens": 60420221.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 4.901283025741577,
|
|
"epoch": 2.5753424657534247,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004347965427614091,
|
|
"loss": 4.6368,
|
|
"mean_token_accuracy": 0.22078316509723664,
|
|
"num_tokens": 60434408.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 4.862139749526977,
|
|
"epoch": 2.5759380583680764,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043476654089849294,
|
|
"loss": 4.5853,
|
|
"mean_token_accuracy": 0.22467889487743378,
|
|
"num_tokens": 60448529.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 4.846049356460571,
|
|
"epoch": 2.5765336509827277,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004347365333050108,
|
|
"loss": 4.568,
|
|
"mean_token_accuracy": 0.23690906465053557,
|
|
"num_tokens": 60461460.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 4.8981037616729735,
|
|
"epoch": 2.5771292435973794,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043470651998203885,
|
|
"loss": 4.6059,
|
|
"mean_token_accuracy": 0.22982555627822876,
|
|
"num_tokens": 60474634.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 4.906584596633911,
|
|
"epoch": 2.577724836212031,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043467650093065367,
|
|
"loss": 4.5607,
|
|
"mean_token_accuracy": 0.23491017073392867,
|
|
"num_tokens": 60487268.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 4.854431629180908,
|
|
"epoch": 2.5783204288266823,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004346464761519321,
|
|
"loss": 4.5335,
|
|
"mean_token_accuracy": 0.22953828871250154,
|
|
"num_tokens": 60501621.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 4.798818826675415,
|
|
"epoch": 2.578916021441334,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043461644564695096,
|
|
"loss": 4.4187,
|
|
"mean_token_accuracy": 0.23618666231632232,
|
|
"num_tokens": 60513611.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 4.8854574203491214,
|
|
"epoch": 2.5795116140559857,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004345864094167875,
|
|
"loss": 4.5427,
|
|
"mean_token_accuracy": 0.22404351681470872,
|
|
"num_tokens": 60528175.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 4.849441337585449,
|
|
"epoch": 2.5801072066706374,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004345563674625189,
|
|
"loss": 4.5851,
|
|
"mean_token_accuracy": 0.2291160687804222,
|
|
"num_tokens": 60540388.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 4.944777727127075,
|
|
"epoch": 2.580702799285289,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004345263197852229,
|
|
"loss": 4.6586,
|
|
"mean_token_accuracy": 0.2194664239883423,
|
|
"num_tokens": 60555531.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 4.877167749404907,
|
|
"epoch": 2.5812983918999404,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004344962663859771,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.23397776931524278,
|
|
"num_tokens": 60570571.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 4.842975378036499,
|
|
"epoch": 2.581893984514592,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004344662072658597,
|
|
"loss": 4.5604,
|
|
"mean_token_accuracy": 0.22755058407783507,
|
|
"num_tokens": 60585553.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 4.841064357757569,
|
|
"epoch": 2.5824895771292438,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004344361424259486,
|
|
"loss": 4.5386,
|
|
"mean_token_accuracy": 0.23104121237993241,
|
|
"num_tokens": 60599229.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 4.78185076713562,
|
|
"epoch": 2.583085169743895,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043440607186732234,
|
|
"loss": 4.5363,
|
|
"mean_token_accuracy": 0.23037583380937576,
|
|
"num_tokens": 60615864.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 4.893735933303833,
|
|
"epoch": 2.5836807623585467,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043437599559105944,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.2250569835305214,
|
|
"num_tokens": 60630312.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 4.942867660522461,
|
|
"epoch": 2.5842763549731984,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004343459135982387,
|
|
"loss": 4.6124,
|
|
"mean_token_accuracy": 0.2232615604996681,
|
|
"num_tokens": 60646319.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 4.781843519210815,
|
|
"epoch": 2.5848719475878497,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004343158258899391,
|
|
"loss": 4.442,
|
|
"mean_token_accuracy": 0.23895360678434371,
|
|
"num_tokens": 60659645.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 4.77852234840393,
|
|
"epoch": 2.5854675402025014,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004342857324672399,
|
|
"loss": 4.4431,
|
|
"mean_token_accuracy": 0.2355824425816536,
|
|
"num_tokens": 60674115.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 4.823443174362183,
|
|
"epoch": 2.586063132817153,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004342556333312204,
|
|
"loss": 4.5385,
|
|
"mean_token_accuracy": 0.22764570862054825,
|
|
"num_tokens": 60686841.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 4.877101755142212,
|
|
"epoch": 2.5866587254318048,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043422552848296035,
|
|
"loss": 4.5696,
|
|
"mean_token_accuracy": 0.23125226348638533,
|
|
"num_tokens": 60699962.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 4.867270469665527,
|
|
"epoch": 2.5872543180464564,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004341954179235395,
|
|
"loss": 4.5242,
|
|
"mean_token_accuracy": 0.23167950361967088,
|
|
"num_tokens": 60712202.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 4.812998485565186,
|
|
"epoch": 2.5878499106611077,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043416530165403777,
|
|
"loss": 4.5128,
|
|
"mean_token_accuracy": 0.23365990668535233,
|
|
"num_tokens": 60724302.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 4.946837663650513,
|
|
"epoch": 2.5884455032757594,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00043413517967553545,
|
|
"loss": 4.6839,
|
|
"mean_token_accuracy": 0.21440244168043138,
|
|
"num_tokens": 60740181.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 4.803371810913086,
|
|
"epoch": 2.589041095890411,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00043410505198911305,
|
|
"loss": 4.4827,
|
|
"mean_token_accuracy": 0.23008715212345124,
|
|
"num_tokens": 60756907.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 4.781118583679199,
|
|
"epoch": 2.5896366885050623,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004340749185958511,
|
|
"loss": 4.4384,
|
|
"mean_token_accuracy": 0.23578308820724486,
|
|
"num_tokens": 60770566.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 4.92302565574646,
|
|
"epoch": 2.590232281119714,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00043404477949683033,
|
|
"loss": 4.6041,
|
|
"mean_token_accuracy": 0.22763209342956542,
|
|
"num_tokens": 60783869.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 4.868559646606445,
|
|
"epoch": 2.5908278737343657,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043401463469313207,
|
|
"loss": 4.5814,
|
|
"mean_token_accuracy": 0.2251528412103653,
|
|
"num_tokens": 60797138.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 4.90605993270874,
|
|
"epoch": 2.5914234663490174,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00043398448418583736,
|
|
"loss": 4.6436,
|
|
"mean_token_accuracy": 0.21900437027215958,
|
|
"num_tokens": 60812480.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 4.97726526260376,
|
|
"epoch": 2.5920190589636687,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043395432797602764,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.21933623850345613,
|
|
"num_tokens": 60824776.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 4.858622455596924,
|
|
"epoch": 2.5926146515783204,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004339241660647847,
|
|
"loss": 4.5551,
|
|
"mean_token_accuracy": 0.23006672114133836,
|
|
"num_tokens": 60839500.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 4.834133338928223,
|
|
"epoch": 2.593210244192972,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004338939984531903,
|
|
"loss": 4.544,
|
|
"mean_token_accuracy": 0.2228439196944237,
|
|
"num_tokens": 60854766.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 4.892606449127197,
|
|
"epoch": 2.5938058368076238,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00043386382514232647,
|
|
"loss": 4.6206,
|
|
"mean_token_accuracy": 0.21970357447862626,
|
|
"num_tokens": 60870829.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 4.871907377243042,
|
|
"epoch": 2.594401429422275,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004338336461332756,
|
|
"loss": 4.5547,
|
|
"mean_token_accuracy": 0.232086119055748,
|
|
"num_tokens": 60885177.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 4.840619277954102,
|
|
"epoch": 2.5949970220369267,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00043380346142712,
|
|
"loss": 4.5526,
|
|
"mean_token_accuracy": 0.2278283417224884,
|
|
"num_tokens": 60899676.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 4.845364093780518,
|
|
"epoch": 2.5955926146515784,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043377327102494254,
|
|
"loss": 4.5525,
|
|
"mean_token_accuracy": 0.22766095399856567,
|
|
"num_tokens": 60912544.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 4.8509129047393795,
|
|
"epoch": 2.5961882072662297,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043374307492782593,
|
|
"loss": 4.5045,
|
|
"mean_token_accuracy": 0.23288025707006454,
|
|
"num_tokens": 60924975.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 4.853671312332153,
|
|
"epoch": 2.5967837998808814,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004337128731368533,
|
|
"loss": 4.5618,
|
|
"mean_token_accuracy": 0.23430402874946593,
|
|
"num_tokens": 60938382.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 4.7895214557647705,
|
|
"epoch": 2.597379392495533,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043368266565310806,
|
|
"loss": 4.4732,
|
|
"mean_token_accuracy": 0.23285808265209199,
|
|
"num_tokens": 60953775.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 4.852438926696777,
|
|
"epoch": 2.5979749851101848,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004336524524776735,
|
|
"loss": 4.5735,
|
|
"mean_token_accuracy": 0.23667490631341934,
|
|
"num_tokens": 60966323.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 4.820866250991822,
|
|
"epoch": 2.5985705777248365,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00043362223361163355,
|
|
"loss": 4.5248,
|
|
"mean_token_accuracy": 0.22883318811655046,
|
|
"num_tokens": 60981056.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 4.832839632034302,
|
|
"epoch": 2.5991661703394877,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043359200905607187,
|
|
"loss": 4.5292,
|
|
"mean_token_accuracy": 0.2361624538898468,
|
|
"num_tokens": 60996687.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 4.8573983669281,
|
|
"epoch": 2.5997617629541394,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004335617788120728,
|
|
"loss": 4.587,
|
|
"mean_token_accuracy": 0.22538961768150328,
|
|
"num_tokens": 61010769.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 4.8136176586151125,
|
|
"epoch": 2.600357355568791,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004335315428807203,
|
|
"loss": 4.4421,
|
|
"mean_token_accuracy": 0.2428239107131958,
|
|
"num_tokens": 61024463.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 4.870082569122315,
|
|
"epoch": 2.6009529481834424,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043350130126309936,
|
|
"loss": 4.5836,
|
|
"mean_token_accuracy": 0.22029862999916078,
|
|
"num_tokens": 61038222.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 4.85918083190918,
|
|
"epoch": 2.601548540798094,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004334710539602943,
|
|
"loss": 4.5046,
|
|
"mean_token_accuracy": 0.23395790308713912,
|
|
"num_tokens": 61052129.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 4.861561441421509,
|
|
"epoch": 2.6021441334127458,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00043344080097339026,
|
|
"loss": 4.5397,
|
|
"mean_token_accuracy": 0.2344347909092903,
|
|
"num_tokens": 61065631.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 4.874775171279907,
|
|
"epoch": 2.602739726027397,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043341054230347227,
|
|
"loss": 4.5731,
|
|
"mean_token_accuracy": 0.2291690081357956,
|
|
"num_tokens": 61080399.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 4.846048784255982,
|
|
"epoch": 2.6033353186420487,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004333802779516257,
|
|
"loss": 4.5059,
|
|
"mean_token_accuracy": 0.2335888847708702,
|
|
"num_tokens": 61093953.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 4.840673589706421,
|
|
"epoch": 2.6039309112567004,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043335000791893606,
|
|
"loss": 4.4927,
|
|
"mean_token_accuracy": 0.23668755292892457,
|
|
"num_tokens": 61105976.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 4.866870260238647,
|
|
"epoch": 2.604526503871352,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004333197322064891,
|
|
"loss": 4.5879,
|
|
"mean_token_accuracy": 0.2291078820824623,
|
|
"num_tokens": 61121355.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 4.80133810043335,
|
|
"epoch": 2.605122096486004,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043328945081537077,
|
|
"loss": 4.6137,
|
|
"mean_token_accuracy": 0.2276201903820038,
|
|
"num_tokens": 61134345.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 4.9173150062561035,
|
|
"epoch": 2.605717689100655,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004332591637466672,
|
|
"loss": 4.6378,
|
|
"mean_token_accuracy": 0.22118183821439744,
|
|
"num_tokens": 61149103.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 4.920656681060791,
|
|
"epoch": 2.6063132817153067,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004332288710014648,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.22216529846191407,
|
|
"num_tokens": 61163892.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 4.849929475784302,
|
|
"epoch": 2.6069088743299584,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043319857258084996,
|
|
"loss": 4.5432,
|
|
"mean_token_accuracy": 0.2328232392668724,
|
|
"num_tokens": 61176949.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 4.897827625274658,
|
|
"epoch": 2.6075044669446097,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00043316826848590955,
|
|
"loss": 4.5264,
|
|
"mean_token_accuracy": 0.2276506945490837,
|
|
"num_tokens": 61191536.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 4.905785369873047,
|
|
"epoch": 2.6081000595592614,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004331379587177305,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.21913845986127853,
|
|
"num_tokens": 61204679.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 4.832384967803955,
|
|
"epoch": 2.608695652173913,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004331076432774001,
|
|
"loss": 4.5329,
|
|
"mean_token_accuracy": 0.2336338460445404,
|
|
"num_tokens": 61217109.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 4.8921445369720455,
|
|
"epoch": 2.609291244788565,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004330773221660055,
|
|
"loss": 4.5968,
|
|
"mean_token_accuracy": 0.22604207843542098,
|
|
"num_tokens": 61231020.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 4.901525020599365,
|
|
"epoch": 2.6098868374032165,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043304699538463445,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.21841789335012435,
|
|
"num_tokens": 61247108.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 4.93343596458435,
|
|
"epoch": 2.6104824300178677,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004330166629343746,
|
|
"loss": 4.5804,
|
|
"mean_token_accuracy": 0.2290307641029358,
|
|
"num_tokens": 61262728.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 4.817603254318238,
|
|
"epoch": 2.6110780226325194,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043298632481631393,
|
|
"loss": 4.5057,
|
|
"mean_token_accuracy": 0.23197302520275115,
|
|
"num_tokens": 61276918.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 4.842262601852417,
|
|
"epoch": 2.611673615247171,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043295598103154073,
|
|
"loss": 4.5733,
|
|
"mean_token_accuracy": 0.22223419398069383,
|
|
"num_tokens": 61290109.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 4.8615772247314455,
|
|
"epoch": 2.6122692078618224,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043292563158114325,
|
|
"loss": 4.5321,
|
|
"mean_token_accuracy": 0.23037849813699723,
|
|
"num_tokens": 61303841.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 4.911885213851929,
|
|
"epoch": 2.612864800476474,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004328952764662102,
|
|
"loss": 4.6348,
|
|
"mean_token_accuracy": 0.227339905500412,
|
|
"num_tokens": 61320612.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 4.967478942871094,
|
|
"epoch": 2.6134603930911258,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004328649156878303,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.22114201486110688,
|
|
"num_tokens": 61335948.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 4.926539516448974,
|
|
"epoch": 2.614055985705777,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004328345492470924,
|
|
"loss": 4.6116,
|
|
"mean_token_accuracy": 0.22197232395410538,
|
|
"num_tokens": 61350572.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 4.847867250442505,
|
|
"epoch": 2.6146515783204287,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043280417714508605,
|
|
"loss": 4.5094,
|
|
"mean_token_accuracy": 0.23088794350624084,
|
|
"num_tokens": 61365581.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 4.790098667144775,
|
|
"epoch": 2.6152471709350804,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00043277379938290027,
|
|
"loss": 4.5205,
|
|
"mean_token_accuracy": 0.2347265899181366,
|
|
"num_tokens": 61380658.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 4.900379228591919,
|
|
"epoch": 2.615842763549732,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000432743415961625,
|
|
"loss": 4.5154,
|
|
"mean_token_accuracy": 0.23268457502126694,
|
|
"num_tokens": 61393125.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 4.870863342285157,
|
|
"epoch": 2.616438356164384,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004327130268823497,
|
|
"loss": 4.4844,
|
|
"mean_token_accuracy": 0.22885482609272004,
|
|
"num_tokens": 61405988.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 4.892558670043945,
|
|
"epoch": 2.617033948779035,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043268263214616467,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.22018308341503143,
|
|
"num_tokens": 61421177.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 4.785659265518189,
|
|
"epoch": 2.6176295413936868,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00043265223175416,
|
|
"loss": 4.5111,
|
|
"mean_token_accuracy": 0.23032579123973845,
|
|
"num_tokens": 61435395.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 4.800500345230103,
|
|
"epoch": 2.6182251340083385,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00043262182570742605,
|
|
"loss": 4.4392,
|
|
"mean_token_accuracy": 0.2417723909020424,
|
|
"num_tokens": 61449665.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 4.8473669528961185,
|
|
"epoch": 2.6188207266229897,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004325914140070535,
|
|
"loss": 4.5714,
|
|
"mean_token_accuracy": 0.2281421035528183,
|
|
"num_tokens": 61463337.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 4.856076192855835,
|
|
"epoch": 2.6194163192376414,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00043256099665413316,
|
|
"loss": 4.5253,
|
|
"mean_token_accuracy": 0.22642598301172256,
|
|
"num_tokens": 61477085.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 4.874345684051514,
|
|
"epoch": 2.620011911852293,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043253057364975604,
|
|
"loss": 4.5245,
|
|
"mean_token_accuracy": 0.22992274463176726,
|
|
"num_tokens": 61490494.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 4.884130620956421,
|
|
"epoch": 2.6206075044669443,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004325001449950134,
|
|
"loss": 4.6709,
|
|
"mean_token_accuracy": 0.2276637002825737,
|
|
"num_tokens": 61504237.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 4.867599105834961,
|
|
"epoch": 2.621203097081596,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004324697106909966,
|
|
"loss": 4.4622,
|
|
"mean_token_accuracy": 0.23601399213075638,
|
|
"num_tokens": 61517539.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 4.87236967086792,
|
|
"epoch": 2.6217986896962477,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043243927073879733,
|
|
"loss": 4.6287,
|
|
"mean_token_accuracy": 0.22289038002490996,
|
|
"num_tokens": 61531639.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 4.879110097885132,
|
|
"epoch": 2.6223942823108994,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004324088251395074,
|
|
"loss": 4.6497,
|
|
"mean_token_accuracy": 0.2241108685731888,
|
|
"num_tokens": 61545608.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 4.865179252624512,
|
|
"epoch": 2.622989874925551,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043237837389421884,
|
|
"loss": 4.4787,
|
|
"mean_token_accuracy": 0.23577988147735596,
|
|
"num_tokens": 61558908.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 4.803655385971069,
|
|
"epoch": 2.6235854675402024,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043234791700402396,
|
|
"loss": 4.5428,
|
|
"mean_token_accuracy": 0.22765282690525054,
|
|
"num_tokens": 61572344.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 4.877528190612793,
|
|
"epoch": 2.624181060154854,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004323174544700151,
|
|
"loss": 4.5988,
|
|
"mean_token_accuracy": 0.2288050666451454,
|
|
"num_tokens": 61586171.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 4.863048982620239,
|
|
"epoch": 2.624776652769506,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004322869862932848,
|
|
"loss": 4.517,
|
|
"mean_token_accuracy": 0.22886882722377777,
|
|
"num_tokens": 61602954.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 4.855034399032593,
|
|
"epoch": 2.625372245384157,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043225651247492616,
|
|
"loss": 4.5682,
|
|
"mean_token_accuracy": 0.22804927676916123,
|
|
"num_tokens": 61617769.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 4.749316215515137,
|
|
"epoch": 2.6259678379988087,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004322260330160321,
|
|
"loss": 4.4655,
|
|
"mean_token_accuracy": 0.23230959177017213,
|
|
"num_tokens": 61631935.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 4.863440656661988,
|
|
"epoch": 2.6265634306134604,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004321955479176958,
|
|
"loss": 4.5548,
|
|
"mean_token_accuracy": 0.23047178387641906,
|
|
"num_tokens": 61647420.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 4.838272476196289,
|
|
"epoch": 2.627159023228112,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004321650571810109,
|
|
"loss": 4.4108,
|
|
"mean_token_accuracy": 0.2387757956981659,
|
|
"num_tokens": 61660969.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 4.877117156982422,
|
|
"epoch": 2.627754615842764,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043213456080707074,
|
|
"loss": 4.6351,
|
|
"mean_token_accuracy": 0.21918122172355653,
|
|
"num_tokens": 61677889.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 4.862248420715332,
|
|
"epoch": 2.628350208457415,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043210405879696957,
|
|
"loss": 4.5661,
|
|
"mean_token_accuracy": 0.2291559785604477,
|
|
"num_tokens": 61692168.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 4.948465824127197,
|
|
"epoch": 2.6289458010720668,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004320735511518011,
|
|
"loss": 4.6024,
|
|
"mean_token_accuracy": 0.22627157866954803,
|
|
"num_tokens": 61706845.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 4.894543981552124,
|
|
"epoch": 2.6295413936867185,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004320430378726598,
|
|
"loss": 4.5478,
|
|
"mean_token_accuracy": 0.22662356346845627,
|
|
"num_tokens": 61722183.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 4.898062133789063,
|
|
"epoch": 2.6301369863013697,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004320125189606401,
|
|
"loss": 4.6269,
|
|
"mean_token_accuracy": 0.22342548817396163,
|
|
"num_tokens": 61734875.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 4.892816877365112,
|
|
"epoch": 2.6307325789160214,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043198199441683654,
|
|
"loss": 4.5821,
|
|
"mean_token_accuracy": 0.22581943422555922,
|
|
"num_tokens": 61748868.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 4.8104877948760985,
|
|
"epoch": 2.631328171530673,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004319514642423442,
|
|
"loss": 4.5744,
|
|
"mean_token_accuracy": 0.22195099294185638,
|
|
"num_tokens": 61763249.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 4.824511289596558,
|
|
"epoch": 2.6319237641453244,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00043192092843825794,
|
|
"loss": 4.5077,
|
|
"mean_token_accuracy": 0.2290874034166336,
|
|
"num_tokens": 61778278.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 4.894300508499145,
|
|
"epoch": 2.632519356759976,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00043189038700567315,
|
|
"loss": 4.6244,
|
|
"mean_token_accuracy": 0.21966776102781296,
|
|
"num_tokens": 61793173.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 4.866036701202392,
|
|
"epoch": 2.6331149493746278,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004318598399456852,
|
|
"loss": 4.5539,
|
|
"mean_token_accuracy": 0.22515688687562943,
|
|
"num_tokens": 61807549.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 4.891512727737426,
|
|
"epoch": 2.6337105419892795,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004318292872593899,
|
|
"loss": 4.6204,
|
|
"mean_token_accuracy": 0.2267466366291046,
|
|
"num_tokens": 61823302.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 4.872914791107178,
|
|
"epoch": 2.634306134603931,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000431798728947883,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.22785561233758928,
|
|
"num_tokens": 61837035.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 4.856892347335815,
|
|
"epoch": 2.6349017272185824,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004317681650122607,
|
|
"loss": 4.5976,
|
|
"mean_token_accuracy": 0.22943699955940247,
|
|
"num_tokens": 61850848.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 4.8433643817901615,
|
|
"epoch": 2.635497319833234,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043173759545361915,
|
|
"loss": 4.5518,
|
|
"mean_token_accuracy": 0.22685994058847428,
|
|
"num_tokens": 61863907.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 4.914511632919312,
|
|
"epoch": 2.636092912447886,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043170702027305497,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.22311023771762847,
|
|
"num_tokens": 61876920.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 4.8477695941925045,
|
|
"epoch": 2.636688505062537,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043167643947166466,
|
|
"loss": 4.4973,
|
|
"mean_token_accuracy": 0.23035241216421126,
|
|
"num_tokens": 61888837.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 4.821147441864014,
|
|
"epoch": 2.6372840976771887,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004316458530505453,
|
|
"loss": 4.504,
|
|
"mean_token_accuracy": 0.22989293336868286,
|
|
"num_tokens": 61904286.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 4.896985816955566,
|
|
"epoch": 2.6378796902918404,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043161526101079386,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.22227150052785874,
|
|
"num_tokens": 61919199.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 4.854343843460083,
|
|
"epoch": 2.6384752829064917,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004315846633535076,
|
|
"loss": 4.5319,
|
|
"mean_token_accuracy": 0.22529958933591843,
|
|
"num_tokens": 61934821.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 4.915892457962036,
|
|
"epoch": 2.6390708755211434,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004315540600797841,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.22285567820072175,
|
|
"num_tokens": 61950104.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 4.85803804397583,
|
|
"epoch": 2.639666468135795,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000431523451190721,
|
|
"loss": 4.5635,
|
|
"mean_token_accuracy": 0.23122284263372422,
|
|
"num_tokens": 61962800.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 4.863205766677856,
|
|
"epoch": 2.640262060750447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004314928366874162,
|
|
"loss": 4.5524,
|
|
"mean_token_accuracy": 0.23265986889600754,
|
|
"num_tokens": 61976004.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 4.855915307998657,
|
|
"epoch": 2.6408576533650985,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004314622165709678,
|
|
"loss": 4.5261,
|
|
"mean_token_accuracy": 0.23649702221155167,
|
|
"num_tokens": 61989118.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 4.894802904129028,
|
|
"epoch": 2.6414532459797497,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000431431590842474,
|
|
"loss": 4.5665,
|
|
"mean_token_accuracy": 0.23147231042385102,
|
|
"num_tokens": 62000862.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 4.877956771850586,
|
|
"epoch": 2.6420488385944014,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004314009595030335,
|
|
"loss": 4.5957,
|
|
"mean_token_accuracy": 0.22509463131427765,
|
|
"num_tokens": 62014029.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 4.884382009506226,
|
|
"epoch": 2.642644431209053,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043137032255374477,
|
|
"loss": 4.5298,
|
|
"mean_token_accuracy": 0.23328152447938919,
|
|
"num_tokens": 62029583.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 4.888296461105346,
|
|
"epoch": 2.6432400238237044,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004313396799957069,
|
|
"loss": 4.5673,
|
|
"mean_token_accuracy": 0.22348377853631973,
|
|
"num_tokens": 62041741.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 4.784855222702026,
|
|
"epoch": 2.643835616438356,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043130903183001887,
|
|
"loss": 4.4982,
|
|
"mean_token_accuracy": 0.2341577023267746,
|
|
"num_tokens": 62056260.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 4.874172687530518,
|
|
"epoch": 2.6444312090530078,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004312783780577799,
|
|
"loss": 4.5773,
|
|
"mean_token_accuracy": 0.22680604159832002,
|
|
"num_tokens": 62070462.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 4.84076075553894,
|
|
"epoch": 2.6450268016676595,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004312477186800898,
|
|
"loss": 4.5048,
|
|
"mean_token_accuracy": 0.23626556098461152,
|
|
"num_tokens": 62085696.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 4.831060361862183,
|
|
"epoch": 2.645622394282311,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004312170536980479,
|
|
"loss": 4.5,
|
|
"mean_token_accuracy": 0.23668479919433594,
|
|
"num_tokens": 62099455.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 4.818421268463135,
|
|
"epoch": 2.6462179868969624,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043118638311275437,
|
|
"loss": 4.5236,
|
|
"mean_token_accuracy": 0.2329686999320984,
|
|
"num_tokens": 62113219.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 4.94797158241272,
|
|
"epoch": 2.646813579511614,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004311557069253092,
|
|
"loss": 4.6891,
|
|
"mean_token_accuracy": 0.22027634978294372,
|
|
"num_tokens": 62126755.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 4.906444644927978,
|
|
"epoch": 2.647409172126266,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004311250251368128,
|
|
"loss": 4.5344,
|
|
"mean_token_accuracy": 0.23247178941965102,
|
|
"num_tokens": 62139833.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 4.726118373870849,
|
|
"epoch": 2.648004764740917,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043109433774836544,
|
|
"loss": 4.447,
|
|
"mean_token_accuracy": 0.24234373569488527,
|
|
"num_tokens": 62152528.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 4.861474227905274,
|
|
"epoch": 2.6486003573555688,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004310636447610681,
|
|
"loss": 4.6005,
|
|
"mean_token_accuracy": 0.22676015198230742,
|
|
"num_tokens": 62165427.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 4.907225894927978,
|
|
"epoch": 2.6491959499702205,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004310329461760215,
|
|
"loss": 4.6026,
|
|
"mean_token_accuracy": 0.2270619288086891,
|
|
"num_tokens": 62180233.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 4.823527193069458,
|
|
"epoch": 2.6497915425848717,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004310022419943268,
|
|
"loss": 4.4605,
|
|
"mean_token_accuracy": 0.23955039530992508,
|
|
"num_tokens": 62195052.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 4.804245567321777,
|
|
"epoch": 2.6503871351995234,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043097153221708534,
|
|
"loss": 4.5391,
|
|
"mean_token_accuracy": 0.23509407490491868,
|
|
"num_tokens": 62207996.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 4.851650047302246,
|
|
"epoch": 2.650982727814175,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043094081684539866,
|
|
"loss": 4.539,
|
|
"mean_token_accuracy": 0.22952544838190078,
|
|
"num_tokens": 62222174.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 4.8539591312408445,
|
|
"epoch": 2.651578320428827,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004309100958803684,
|
|
"loss": 4.5221,
|
|
"mean_token_accuracy": 0.23184492737054824,
|
|
"num_tokens": 62235649.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 4.760324382781983,
|
|
"epoch": 2.6521739130434785,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004308793693230965,
|
|
"loss": 4.4257,
|
|
"mean_token_accuracy": 0.23733021318912506,
|
|
"num_tokens": 62249040.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 4.864836120605469,
|
|
"epoch": 2.6527695056581297,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043084863717468504,
|
|
"loss": 4.5729,
|
|
"mean_token_accuracy": 0.2263616517186165,
|
|
"num_tokens": 62261893.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 4.873495054244995,
|
|
"epoch": 2.6533650982727814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004308178994362364,
|
|
"loss": 4.5604,
|
|
"mean_token_accuracy": 0.22481882572174072,
|
|
"num_tokens": 62275060.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 4.907353353500366,
|
|
"epoch": 2.653960690887433,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043078715610885297,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.2283306673169136,
|
|
"num_tokens": 62289321.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 4.907612895965576,
|
|
"epoch": 2.6545562835020844,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004307564071936376,
|
|
"loss": 4.6144,
|
|
"mean_token_accuracy": 0.2218483567237854,
|
|
"num_tokens": 62305662.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 4.827468299865723,
|
|
"epoch": 2.655151876116736,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043072565269169325,
|
|
"loss": 4.5562,
|
|
"mean_token_accuracy": 0.2305955097079277,
|
|
"num_tokens": 62318505.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 4.827890253067016,
|
|
"epoch": 2.655747468731388,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043069489260412274,
|
|
"loss": 4.5192,
|
|
"mean_token_accuracy": 0.23202819079160691,
|
|
"num_tokens": 62331659.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 4.824380874633789,
|
|
"epoch": 2.656343061346039,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004306641269320297,
|
|
"loss": 4.4574,
|
|
"mean_token_accuracy": 0.2374780148267746,
|
|
"num_tokens": 62347064.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 4.844267082214356,
|
|
"epoch": 2.6569386539606907,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00043063335567651757,
|
|
"loss": 4.547,
|
|
"mean_token_accuracy": 0.22849064469337463,
|
|
"num_tokens": 62361507.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 4.871939849853516,
|
|
"epoch": 2.6575342465753424,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043060257883868985,
|
|
"loss": 4.5888,
|
|
"mean_token_accuracy": 0.22584993690252303,
|
|
"num_tokens": 62376006.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 4.97983684539795,
|
|
"epoch": 2.658129839189994,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004305717964196507,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.2236545503139496,
|
|
"num_tokens": 62389200.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 4.780693054199219,
|
|
"epoch": 2.658725431804646,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004305410084205042,
|
|
"loss": 4.4385,
|
|
"mean_token_accuracy": 0.24643257707357408,
|
|
"num_tokens": 62400929.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 4.908076190948487,
|
|
"epoch": 2.659321024419297,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043051021484235457,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.22037319093942642,
|
|
"num_tokens": 62416494.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 4.8514937400817875,
|
|
"epoch": 2.6599166170339488,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043047941568630644,
|
|
"loss": 4.5583,
|
|
"mean_token_accuracy": 0.22772953957319259,
|
|
"num_tokens": 62431078.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 4.810244464874268,
|
|
"epoch": 2.6605122096486005,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004304486109534644,
|
|
"loss": 4.4579,
|
|
"mean_token_accuracy": 0.23700518906116486,
|
|
"num_tokens": 62445192.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 4.801055240631103,
|
|
"epoch": 2.6611078022632517,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004304178006449335,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.2352790728211403,
|
|
"num_tokens": 62459654.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 4.821378231048584,
|
|
"epoch": 2.6617033948779034,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004303869847618187,
|
|
"loss": 4.4874,
|
|
"mean_token_accuracy": 0.23818772733211518,
|
|
"num_tokens": 62474054.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 4.8376579761505125,
|
|
"epoch": 2.662298987492555,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004303561633052254,
|
|
"loss": 4.5656,
|
|
"mean_token_accuracy": 0.22785771936178206,
|
|
"num_tokens": 62487729.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 4.873421907424927,
|
|
"epoch": 2.662894580107207,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043032533627625913,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.231545789539814,
|
|
"num_tokens": 62501319.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 4.908824777603149,
|
|
"epoch": 2.6634901727218585,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004302945036760257,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.2186557099223137,
|
|
"num_tokens": 62516653.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 4.981971406936646,
|
|
"epoch": 2.6640857653365098,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004302636655056308,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.22199744880199432,
|
|
"num_tokens": 62529884.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 4.816879510879517,
|
|
"epoch": 2.6646813579511615,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043023282176618067,
|
|
"loss": 4.4294,
|
|
"mean_token_accuracy": 0.23828372210264206,
|
|
"num_tokens": 62543206.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 4.837836074829101,
|
|
"epoch": 2.665276950565813,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004302019724587817,
|
|
"loss": 4.5661,
|
|
"mean_token_accuracy": 0.23382798731327056,
|
|
"num_tokens": 62557722.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 4.850387859344482,
|
|
"epoch": 2.6658725431804644,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004301711175845402,
|
|
"loss": 4.5744,
|
|
"mean_token_accuracy": 0.2263127565383911,
|
|
"num_tokens": 62573527.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 4.883184289932251,
|
|
"epoch": 2.666468135795116,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043014025714456305,
|
|
"loss": 4.5772,
|
|
"mean_token_accuracy": 0.22869160175323486,
|
|
"num_tokens": 62587586.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 4.874354362487793,
|
|
"epoch": 2.667063728409768,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004301093911399571,
|
|
"loss": 4.6398,
|
|
"mean_token_accuracy": 0.21983435600996018,
|
|
"num_tokens": 62599841.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 4.821481847763062,
|
|
"epoch": 2.667659321024419,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043007851957182954,
|
|
"loss": 4.4542,
|
|
"mean_token_accuracy": 0.24261610358953475,
|
|
"num_tokens": 62613635.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 4.850031042098999,
|
|
"epoch": 2.6682549136390707,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043004764244128764,
|
|
"loss": 4.5444,
|
|
"mean_token_accuracy": 0.22533024549484254,
|
|
"num_tokens": 62626840.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 4.831799554824829,
|
|
"epoch": 2.6688505062537224,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043001675974943884,
|
|
"loss": 4.5641,
|
|
"mean_token_accuracy": 0.23936450928449632,
|
|
"num_tokens": 62638161.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 4.838642692565918,
|
|
"epoch": 2.669446098868374,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042998587149739093,
|
|
"loss": 4.4797,
|
|
"mean_token_accuracy": 0.2342745840549469,
|
|
"num_tokens": 62651900.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 4.839907312393189,
|
|
"epoch": 2.670041691483026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004299549776862518,
|
|
"loss": 4.5242,
|
|
"mean_token_accuracy": 0.2269688665866852,
|
|
"num_tokens": 62665871.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 4.87273907661438,
|
|
"epoch": 2.670637284097677,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042992407831712957,
|
|
"loss": 4.5213,
|
|
"mean_token_accuracy": 0.23317767828702926,
|
|
"num_tokens": 62680052.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 4.731499814987183,
|
|
"epoch": 2.671232876712329,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004298931733911325,
|
|
"loss": 4.4348,
|
|
"mean_token_accuracy": 0.24658797383308412,
|
|
"num_tokens": 62693356.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 4.879467630386353,
|
|
"epoch": 2.6718284693269805,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004298622629093692,
|
|
"loss": 4.5416,
|
|
"mean_token_accuracy": 0.2306704878807068,
|
|
"num_tokens": 62708676.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 4.861800956726074,
|
|
"epoch": 2.6724240619416317,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004298313468729482,
|
|
"loss": 4.5834,
|
|
"mean_token_accuracy": 0.2290838599205017,
|
|
"num_tokens": 62722845.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 4.836662006378174,
|
|
"epoch": 2.6730196545562834,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004298004252829787,
|
|
"loss": 4.5715,
|
|
"mean_token_accuracy": 0.2287328377366066,
|
|
"num_tokens": 62738497.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 4.870178604125977,
|
|
"epoch": 2.673615247170935,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004297694981405695,
|
|
"loss": 4.5786,
|
|
"mean_token_accuracy": 0.23006250113248825,
|
|
"num_tokens": 62751635.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 4.846714687347412,
|
|
"epoch": 2.674210839785587,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004297385654468301,
|
|
"loss": 4.5346,
|
|
"mean_token_accuracy": 0.23012688457965852,
|
|
"num_tokens": 62765675.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 4.853402948379516,
|
|
"epoch": 2.674806432400238,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00042970762720287,
|
|
"loss": 4.5735,
|
|
"mean_token_accuracy": 0.2271582826972008,
|
|
"num_tokens": 62780554.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 4.84651665687561,
|
|
"epoch": 2.6754020250148898,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004296766834097988,
|
|
"loss": 4.5698,
|
|
"mean_token_accuracy": 0.225639046728611,
|
|
"num_tokens": 62793863.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 4.887207508087158,
|
|
"epoch": 2.6759976176295415,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004296457340687264,
|
|
"loss": 4.5564,
|
|
"mean_token_accuracy": 0.2300604909658432,
|
|
"num_tokens": 62809184.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 4.806926488876343,
|
|
"epoch": 2.676593210244193,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000429614779180763,
|
|
"loss": 4.4829,
|
|
"mean_token_accuracy": 0.23433296680450438,
|
|
"num_tokens": 62824120.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 4.868081140518188,
|
|
"epoch": 2.6771888028588444,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004295838187470189,
|
|
"loss": 4.6376,
|
|
"mean_token_accuracy": 0.22009809762239457,
|
|
"num_tokens": 62839357.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 4.936398601531982,
|
|
"epoch": 2.677784395473496,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004295528527686046,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.21982816457748414,
|
|
"num_tokens": 62853856.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 4.811123275756836,
|
|
"epoch": 2.678379988088148,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004295218812466306,
|
|
"loss": 4.4482,
|
|
"mean_token_accuracy": 0.2341546893119812,
|
|
"num_tokens": 62866710.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 4.84541335105896,
|
|
"epoch": 2.678975580702799,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042949090418220804,
|
|
"loss": 4.5522,
|
|
"mean_token_accuracy": 0.22703003287315368,
|
|
"num_tokens": 62879703.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 4.85599799156189,
|
|
"epoch": 2.6795711733174508,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000429459921576448,
|
|
"loss": 4.4855,
|
|
"mean_token_accuracy": 0.2324712097644806,
|
|
"num_tokens": 62892759.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 4.779824066162109,
|
|
"epoch": 2.6801667659321025,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042942893343046165,
|
|
"loss": 4.484,
|
|
"mean_token_accuracy": 0.23624908477067946,
|
|
"num_tokens": 62906890.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 4.864571619033813,
|
|
"epoch": 2.680762358546754,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042939793974536045,
|
|
"loss": 4.5753,
|
|
"mean_token_accuracy": 0.22867153584957123,
|
|
"num_tokens": 62921157.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.0215699672698975,
|
|
"epoch": 2.681357951161406,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042936694052225636,
|
|
"loss": 4.6599,
|
|
"mean_token_accuracy": 0.22387049794197084,
|
|
"num_tokens": 62934913.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 4.8187822818756105,
|
|
"epoch": 2.681953543776057,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000429335935762261,
|
|
"loss": 4.49,
|
|
"mean_token_accuracy": 0.22945723533630372,
|
|
"num_tokens": 62950946.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 4.8049421310424805,
|
|
"epoch": 2.682549136390709,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004293049254664865,
|
|
"loss": 4.5537,
|
|
"mean_token_accuracy": 0.23138299137353896,
|
|
"num_tokens": 62965098.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 4.751266288757324,
|
|
"epoch": 2.6831447290053605,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042927390963604534,
|
|
"loss": 4.4079,
|
|
"mean_token_accuracy": 0.243835973739624,
|
|
"num_tokens": 62977116.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 4.954595613479614,
|
|
"epoch": 2.6837403216200117,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004292428882720498,
|
|
"loss": 4.6661,
|
|
"mean_token_accuracy": 0.21726355254650115,
|
|
"num_tokens": 62991735.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 4.903372001647949,
|
|
"epoch": 2.6843359142346634,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004292118613756127,
|
|
"loss": 4.5782,
|
|
"mean_token_accuracy": 0.2194138363003731,
|
|
"num_tokens": 63006605.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 4.76764235496521,
|
|
"epoch": 2.684931506849315,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00042918082894784676,
|
|
"loss": 4.4639,
|
|
"mean_token_accuracy": 0.23300873935222627,
|
|
"num_tokens": 63021090.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 4.888772058486938,
|
|
"epoch": 2.6855270994639664,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004291497909898653,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.2266390800476074,
|
|
"num_tokens": 63035531.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 4.868152236938476,
|
|
"epoch": 2.686122692078618,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042911874750278133,
|
|
"loss": 4.5549,
|
|
"mean_token_accuracy": 0.2345457434654236,
|
|
"num_tokens": 63048208.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 4.800434494018555,
|
|
"epoch": 2.68671828469327,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00042908769848770857,
|
|
"loss": 4.5114,
|
|
"mean_token_accuracy": 0.23275421559810638,
|
|
"num_tokens": 63062769.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 4.801034450531006,
|
|
"epoch": 2.6873138773079215,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004290566439457606,
|
|
"loss": 4.5336,
|
|
"mean_token_accuracy": 0.2293768495321274,
|
|
"num_tokens": 63077581.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 4.8543071269989015,
|
|
"epoch": 2.687909469922573,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042902558387805125,
|
|
"loss": 4.5261,
|
|
"mean_token_accuracy": 0.23157628774642944,
|
|
"num_tokens": 63091541.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 4.789444208145142,
|
|
"epoch": 2.6885050625372244,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004289945182856946,
|
|
"loss": 4.468,
|
|
"mean_token_accuracy": 0.23413208425045012,
|
|
"num_tokens": 63103344.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 4.865107107162475,
|
|
"epoch": 2.689100655151876,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042896344716980507,
|
|
"loss": 4.5478,
|
|
"mean_token_accuracy": 0.22748906016349793,
|
|
"num_tokens": 63118127.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 4.783923864364624,
|
|
"epoch": 2.689696247766528,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004289323705314969,
|
|
"loss": 4.4713,
|
|
"mean_token_accuracy": 0.23725557923316956,
|
|
"num_tokens": 63131739.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 4.878541469573975,
|
|
"epoch": 2.690291840381179,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004289012883718849,
|
|
"loss": 4.5391,
|
|
"mean_token_accuracy": 0.23709927797317504,
|
|
"num_tokens": 63144285.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 4.863165807723999,
|
|
"epoch": 2.6908874329958308,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042887020069208397,
|
|
"loss": 4.555,
|
|
"mean_token_accuracy": 0.2336280405521393,
|
|
"num_tokens": 63158061.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 4.848948192596436,
|
|
"epoch": 2.6914830256104825,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00042883910749320914,
|
|
"loss": 4.5775,
|
|
"mean_token_accuracy": 0.21924899220466615,
|
|
"num_tokens": 63173188.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 4.85169529914856,
|
|
"epoch": 2.692078618225134,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00042880800877637555,
|
|
"loss": 4.5515,
|
|
"mean_token_accuracy": 0.22686527222394942,
|
|
"num_tokens": 63186953.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 4.867895221710205,
|
|
"epoch": 2.6926742108397854,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042877690454269884,
|
|
"loss": 4.4621,
|
|
"mean_token_accuracy": 0.23633046001195906,
|
|
"num_tokens": 63200162.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 4.85741777420044,
|
|
"epoch": 2.693269803454437,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004287457947932946,
|
|
"loss": 4.5521,
|
|
"mean_token_accuracy": 0.2299744725227356,
|
|
"num_tokens": 63215400.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 4.783884859085083,
|
|
"epoch": 2.693865396069089,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004287146795292787,
|
|
"loss": 4.4998,
|
|
"mean_token_accuracy": 0.23479590564966202,
|
|
"num_tokens": 63229555.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 4.9864194869995115,
|
|
"epoch": 2.6944609886837405,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004286835587517671,
|
|
"loss": 4.6574,
|
|
"mean_token_accuracy": 0.2239898756146431,
|
|
"num_tokens": 63246012.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 4.883774089813232,
|
|
"epoch": 2.6950565812983918,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004286524324618761,
|
|
"loss": 4.6064,
|
|
"mean_token_accuracy": 0.22393627911806108,
|
|
"num_tokens": 63261033.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 4.898860216140747,
|
|
"epoch": 2.6956521739130435,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042862130066072225,
|
|
"loss": 4.6045,
|
|
"mean_token_accuracy": 0.22829123139381408,
|
|
"num_tokens": 63276550.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 4.865341472625732,
|
|
"epoch": 2.696247766527695,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000428590163349422,
|
|
"loss": 4.4904,
|
|
"mean_token_accuracy": 0.23169899880886077,
|
|
"num_tokens": 63290355.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 4.850434637069702,
|
|
"epoch": 2.6968433591423464,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042855902052909244,
|
|
"loss": 4.5318,
|
|
"mean_token_accuracy": 0.23270710855722426,
|
|
"num_tokens": 63305065.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 4.860451698303223,
|
|
"epoch": 2.697438951756998,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042852787220085044,
|
|
"loss": 4.5703,
|
|
"mean_token_accuracy": 0.22836415469646454,
|
|
"num_tokens": 63318257.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 4.910464715957642,
|
|
"epoch": 2.69803454437165,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00042849671836581323,
|
|
"loss": 4.6521,
|
|
"mean_token_accuracy": 0.21900299489498137,
|
|
"num_tokens": 63331798.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 4.845616102218628,
|
|
"epoch": 2.6986301369863015,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00042846555902509845,
|
|
"loss": 4.5718,
|
|
"mean_token_accuracy": 0.22679909765720369,
|
|
"num_tokens": 63347863.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 4.894971561431885,
|
|
"epoch": 2.699225729600953,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042843439417982344,
|
|
"loss": 4.543,
|
|
"mean_token_accuracy": 0.2272047683596611,
|
|
"num_tokens": 63361239.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 4.828782176971435,
|
|
"epoch": 2.6998213222156044,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042840322383110626,
|
|
"loss": 4.4536,
|
|
"mean_token_accuracy": 0.24280014187097548,
|
|
"num_tokens": 63375256.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 4.8326021194458,
|
|
"epoch": 2.700416914830256,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004283720479800648,
|
|
"loss": 4.5488,
|
|
"mean_token_accuracy": 0.22689708620309829,
|
|
"num_tokens": 63390051.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 4.799048233032226,
|
|
"epoch": 2.701012507444908,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004283408666278174,
|
|
"loss": 4.4607,
|
|
"mean_token_accuracy": 0.23832439482212067,
|
|
"num_tokens": 63403741.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 4.8672645568847654,
|
|
"epoch": 2.701608100059559,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042830967977548236,
|
|
"loss": 4.4847,
|
|
"mean_token_accuracy": 0.2367929920554161,
|
|
"num_tokens": 63417624.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 4.845545482635498,
|
|
"epoch": 2.702203692674211,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004282784874241785,
|
|
"loss": 4.516,
|
|
"mean_token_accuracy": 0.2372583642601967,
|
|
"num_tokens": 63431139.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 4.813607788085937,
|
|
"epoch": 2.7027992852888625,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042824728957502437,
|
|
"loss": 4.5519,
|
|
"mean_token_accuracy": 0.23944795727729798,
|
|
"num_tokens": 63444193.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 4.842211771011352,
|
|
"epoch": 2.7033948779035137,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004282160862291392,
|
|
"loss": 4.4881,
|
|
"mean_token_accuracy": 0.23841546475887299,
|
|
"num_tokens": 63457489.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 4.811736440658569,
|
|
"epoch": 2.7039904705181654,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004281848773876421,
|
|
"loss": 4.5276,
|
|
"mean_token_accuracy": 0.2267254889011383,
|
|
"num_tokens": 63471262.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 4.9020312309265135,
|
|
"epoch": 2.704586063132817,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042815366305165256,
|
|
"loss": 4.5605,
|
|
"mean_token_accuracy": 0.2215355470776558,
|
|
"num_tokens": 63484843.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 4.792890214920044,
|
|
"epoch": 2.705181655747469,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004281224432222901,
|
|
"loss": 4.4575,
|
|
"mean_token_accuracy": 0.23651760816574097,
|
|
"num_tokens": 63498527.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 4.832864046096802,
|
|
"epoch": 2.7057772483621205,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004280912179006746,
|
|
"loss": 4.5336,
|
|
"mean_token_accuracy": 0.22697917371988297,
|
|
"num_tokens": 63512358.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 4.828949737548828,
|
|
"epoch": 2.7063728409767718,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000428059987087926,
|
|
"loss": 4.5083,
|
|
"mean_token_accuracy": 0.24009348601102828,
|
|
"num_tokens": 63525809.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 4.81783127784729,
|
|
"epoch": 2.7069684335914235,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042802875078516446,
|
|
"loss": 4.5097,
|
|
"mean_token_accuracy": 0.2329895779490471,
|
|
"num_tokens": 63538782.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 4.82491512298584,
|
|
"epoch": 2.707564026206075,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004279975089935106,
|
|
"loss": 4.4757,
|
|
"mean_token_accuracy": 0.22623130977153777,
|
|
"num_tokens": 63552708.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 4.9057478427886965,
|
|
"epoch": 2.7081596188207264,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004279662617140847,
|
|
"loss": 4.6102,
|
|
"mean_token_accuracy": 0.22177822440862655,
|
|
"num_tokens": 63566281.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 4.821102333068848,
|
|
"epoch": 2.708755211435378,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042793500894800776,
|
|
"loss": 4.529,
|
|
"mean_token_accuracy": 0.2301560088992119,
|
|
"num_tokens": 63580983.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 4.810108709335327,
|
|
"epoch": 2.70935080405003,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004279037506964007,
|
|
"loss": 4.5169,
|
|
"mean_token_accuracy": 0.2342434987425804,
|
|
"num_tokens": 63593735.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 4.753465890884399,
|
|
"epoch": 2.7099463966646815,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004278724869603847,
|
|
"loss": 4.3728,
|
|
"mean_token_accuracy": 0.2487647995352745,
|
|
"num_tokens": 63605630.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 4.9286919116973875,
|
|
"epoch": 2.710541989279333,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042784121774108117,
|
|
"loss": 4.6102,
|
|
"mean_token_accuracy": 0.23232532888650895,
|
|
"num_tokens": 63618668.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 4.908023357391357,
|
|
"epoch": 2.7111375818939845,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042780994303961165,
|
|
"loss": 4.6235,
|
|
"mean_token_accuracy": 0.22323066294193267,
|
|
"num_tokens": 63633075.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 4.821076345443726,
|
|
"epoch": 2.711733174508636,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004277786628570979,
|
|
"loss": 4.5367,
|
|
"mean_token_accuracy": 0.2339870423078537,
|
|
"num_tokens": 63645088.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 4.874300909042359,
|
|
"epoch": 2.712328767123288,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000427747377194662,
|
|
"loss": 4.5715,
|
|
"mean_token_accuracy": 0.2286265656352043,
|
|
"num_tokens": 63658640.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 4.7714599609375,
|
|
"epoch": 2.712924359737939,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042771608605342596,
|
|
"loss": 4.4388,
|
|
"mean_token_accuracy": 0.24462903141975403,
|
|
"num_tokens": 63672369.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 4.906185102462769,
|
|
"epoch": 2.713519952352591,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042768478943451223,
|
|
"loss": 4.6711,
|
|
"mean_token_accuracy": 0.2162170395255089,
|
|
"num_tokens": 63687947.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 4.883614349365234,
|
|
"epoch": 2.7141155449672425,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042765348733904337,
|
|
"loss": 4.5351,
|
|
"mean_token_accuracy": 0.23190328031778334,
|
|
"num_tokens": 63701609.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 4.92096357345581,
|
|
"epoch": 2.7147111375818938,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004276221797681421,
|
|
"loss": 4.6163,
|
|
"mean_token_accuracy": 0.22364710569381713,
|
|
"num_tokens": 63716928.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 4.811221361160278,
|
|
"epoch": 2.7153067301965454,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004275908667229314,
|
|
"loss": 4.4673,
|
|
"mean_token_accuracy": 0.23311285227537154,
|
|
"num_tokens": 63731538.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 4.83437213897705,
|
|
"epoch": 2.715902322811197,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00042755954820453433,
|
|
"loss": 4.5425,
|
|
"mean_token_accuracy": 0.23049847781658173,
|
|
"num_tokens": 63746149.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 4.809973907470703,
|
|
"epoch": 2.716497915425849,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00042752822421407443,
|
|
"loss": 4.466,
|
|
"mean_token_accuracy": 0.23807001560926438,
|
|
"num_tokens": 63759254.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 4.88306565284729,
|
|
"epoch": 2.7170935080405005,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042749689475267514,
|
|
"loss": 4.5994,
|
|
"mean_token_accuracy": 0.23622548580169678,
|
|
"num_tokens": 63772040.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 4.8664429664611815,
|
|
"epoch": 2.717689100655152,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042746555982146,
|
|
"loss": 4.5541,
|
|
"mean_token_accuracy": 0.232413586974144,
|
|
"num_tokens": 63784628.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 4.889384126663208,
|
|
"epoch": 2.7182846932698035,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004274342194215533,
|
|
"loss": 4.5775,
|
|
"mean_token_accuracy": 0.2211485430598259,
|
|
"num_tokens": 63799736.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 4.8797472476959225,
|
|
"epoch": 2.718880285884455,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004274028735540789,
|
|
"loss": 4.564,
|
|
"mean_token_accuracy": 0.22344363182783128,
|
|
"num_tokens": 63814704.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 4.831548070907592,
|
|
"epoch": 2.7194758784991064,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004273715222201613,
|
|
"loss": 4.5751,
|
|
"mean_token_accuracy": 0.2299548789858818,
|
|
"num_tokens": 63829081.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 4.849655246734619,
|
|
"epoch": 2.720071471113758,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042734016542092485,
|
|
"loss": 4.5086,
|
|
"mean_token_accuracy": 0.23519693613052367,
|
|
"num_tokens": 63842896.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 4.780557918548584,
|
|
"epoch": 2.72066706372841,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042730880315749445,
|
|
"loss": 4.4496,
|
|
"mean_token_accuracy": 0.243174010515213,
|
|
"num_tokens": 63857255.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 4.818560695648193,
|
|
"epoch": 2.721262656343061,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004272774354309948,
|
|
"loss": 4.5301,
|
|
"mean_token_accuracy": 0.23658776730298997,
|
|
"num_tokens": 63871009.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 4.865215301513672,
|
|
"epoch": 2.721858248957713,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042724606224255117,
|
|
"loss": 4.5747,
|
|
"mean_token_accuracy": 0.2257872626185417,
|
|
"num_tokens": 63885030.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 4.814520359039307,
|
|
"epoch": 2.7224538415723645,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00042721468359328883,
|
|
"loss": 4.4964,
|
|
"mean_token_accuracy": 0.23886209577322007,
|
|
"num_tokens": 63900711.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 4.840835618972778,
|
|
"epoch": 2.723049434187016,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00042718329948433336,
|
|
"loss": 4.4592,
|
|
"mean_token_accuracy": 0.2388080984354019,
|
|
"num_tokens": 63913238.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 4.797008514404297,
|
|
"epoch": 2.723645026801668,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004271519099168103,
|
|
"loss": 4.4817,
|
|
"mean_token_accuracy": 0.23721795231103898,
|
|
"num_tokens": 63928216.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 4.817117977142334,
|
|
"epoch": 2.724240619416319,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004271205148918456,
|
|
"loss": 4.5411,
|
|
"mean_token_accuracy": 0.23256012946367263,
|
|
"num_tokens": 63940904.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 4.892919683456421,
|
|
"epoch": 2.724836212030971,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004270891144105654,
|
|
"loss": 4.4601,
|
|
"mean_token_accuracy": 0.23945943415164947,
|
|
"num_tokens": 63954805.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 4.877027320861816,
|
|
"epoch": 2.7254318046456225,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042705770847409596,
|
|
"loss": 4.5355,
|
|
"mean_token_accuracy": 0.2273740589618683,
|
|
"num_tokens": 63967243.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 4.7918298721313475,
|
|
"epoch": 2.7260273972602738,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004270262970835637,
|
|
"loss": 4.5131,
|
|
"mean_token_accuracy": 0.2308623820543289,
|
|
"num_tokens": 63980652.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 4.9344383716583256,
|
|
"epoch": 2.7266229898749255,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042699488024009537,
|
|
"loss": 4.6189,
|
|
"mean_token_accuracy": 0.22126599699258803,
|
|
"num_tokens": 63997937.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 4.849824714660644,
|
|
"epoch": 2.727218582489577,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042696345794481785,
|
|
"loss": 4.4917,
|
|
"mean_token_accuracy": 0.2349900558590889,
|
|
"num_tokens": 64011199.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 4.863663673400879,
|
|
"epoch": 2.727814175104229,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004269320301988581,
|
|
"loss": 4.5933,
|
|
"mean_token_accuracy": 0.23693519830703735,
|
|
"num_tokens": 64024037.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 4.913475179672242,
|
|
"epoch": 2.7284097677188806,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004269005970033435,
|
|
"loss": 4.5592,
|
|
"mean_token_accuracy": 0.22432425916194915,
|
|
"num_tokens": 64037834.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 4.90305986404419,
|
|
"epoch": 2.729005360333532,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004268691583594014,
|
|
"loss": 4.6011,
|
|
"mean_token_accuracy": 0.22306725829839708,
|
|
"num_tokens": 64051700.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 4.850234460830689,
|
|
"epoch": 2.7296009529481835,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004268377142681596,
|
|
"loss": 4.6157,
|
|
"mean_token_accuracy": 0.22696143239736558,
|
|
"num_tokens": 64065048.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 4.909037923812866,
|
|
"epoch": 2.730196545562835,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042680626473074585,
|
|
"loss": 4.5685,
|
|
"mean_token_accuracy": 0.23337093591690064,
|
|
"num_tokens": 64079736.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 4.863581705093384,
|
|
"epoch": 2.7307921381774864,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042677480974828816,
|
|
"loss": 4.5787,
|
|
"mean_token_accuracy": 0.2317075952887535,
|
|
"num_tokens": 64092794.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 4.840115547180176,
|
|
"epoch": 2.731387730792138,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042674334932191475,
|
|
"loss": 4.5336,
|
|
"mean_token_accuracy": 0.23260879665613174,
|
|
"num_tokens": 64107427.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 4.859932947158813,
|
|
"epoch": 2.73198332340679,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042671188345275423,
|
|
"loss": 4.4785,
|
|
"mean_token_accuracy": 0.23769438415765762,
|
|
"num_tokens": 64121652.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 4.783968591690064,
|
|
"epoch": 2.732578916021441,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00042668041214193514,
|
|
"loss": 4.4634,
|
|
"mean_token_accuracy": 0.2362406000494957,
|
|
"num_tokens": 64137134.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 4.818981456756592,
|
|
"epoch": 2.733174508636093,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004266489353905862,
|
|
"loss": 4.5204,
|
|
"mean_token_accuracy": 0.2307588815689087,
|
|
"num_tokens": 64150305.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 4.845851230621338,
|
|
"epoch": 2.7337701012507445,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004266174531998365,
|
|
"loss": 4.5345,
|
|
"mean_token_accuracy": 0.23054198771715165,
|
|
"num_tokens": 64164230.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 4.84718952178955,
|
|
"epoch": 2.734365693865396,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00042658596557081536,
|
|
"loss": 4.5312,
|
|
"mean_token_accuracy": 0.23017056733369828,
|
|
"num_tokens": 64178374.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 4.8968696117401125,
|
|
"epoch": 2.734961286480048,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042655447250465205,
|
|
"loss": 4.5658,
|
|
"mean_token_accuracy": 0.225212262570858,
|
|
"num_tokens": 64192652.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 4.809517431259155,
|
|
"epoch": 2.735556879094699,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042652297400247625,
|
|
"loss": 4.4691,
|
|
"mean_token_accuracy": 0.2366806909441948,
|
|
"num_tokens": 64205574.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 4.856581020355224,
|
|
"epoch": 2.736152471709351,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004264914700654177,
|
|
"loss": 4.528,
|
|
"mean_token_accuracy": 0.23379205018281937,
|
|
"num_tokens": 64219322.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 4.816513776779175,
|
|
"epoch": 2.7367480643240025,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004264599606946065,
|
|
"loss": 4.4852,
|
|
"mean_token_accuracy": 0.247210031747818,
|
|
"num_tokens": 64232911.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 4.805235576629639,
|
|
"epoch": 2.737343656938654,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004264284458911727,
|
|
"loss": 4.5447,
|
|
"mean_token_accuracy": 0.2307356372475624,
|
|
"num_tokens": 64246651.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 4.880116701126099,
|
|
"epoch": 2.7379392495533055,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042639692565624675,
|
|
"loss": 4.536,
|
|
"mean_token_accuracy": 0.2234654277563095,
|
|
"num_tokens": 64261397.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 4.82397723197937,
|
|
"epoch": 2.738534842167957,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004263653999909593,
|
|
"loss": 4.5073,
|
|
"mean_token_accuracy": 0.23965928852558135,
|
|
"num_tokens": 64274786.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 4.8632659912109375,
|
|
"epoch": 2.7391304347826084,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042633386889644095,
|
|
"loss": 4.5306,
|
|
"mean_token_accuracy": 0.23244561105966569,
|
|
"num_tokens": 64290065.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 4.836436080932617,
|
|
"epoch": 2.73972602739726,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00042630233237382284,
|
|
"loss": 4.5656,
|
|
"mean_token_accuracy": 0.2364175111055374,
|
|
"num_tokens": 64304112.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 4.832255554199219,
|
|
"epoch": 2.740321620011912,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042627079042423607,
|
|
"loss": 4.4728,
|
|
"mean_token_accuracy": 0.23463790416717528,
|
|
"num_tokens": 64316778.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 4.807020854949951,
|
|
"epoch": 2.7409172126265635,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00042623924304881195,
|
|
"loss": 4.5077,
|
|
"mean_token_accuracy": 0.23358167856931686,
|
|
"num_tokens": 64330337.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 4.915528297424316,
|
|
"epoch": 2.741512805241215,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00042620769024868217,
|
|
"loss": 4.6673,
|
|
"mean_token_accuracy": 0.22023663073778152,
|
|
"num_tokens": 64345589.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 4.9142858505249025,
|
|
"epoch": 2.7421083978558665,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042617613202497836,
|
|
"loss": 4.5674,
|
|
"mean_token_accuracy": 0.2190543681383133,
|
|
"num_tokens": 64361746.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 4.899603414535522,
|
|
"epoch": 2.742703990470518,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042614456837883243,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.2237241491675377,
|
|
"num_tokens": 64375415.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 4.900440263748169,
|
|
"epoch": 2.74329958308517,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042611299931137657,
|
|
"loss": 4.6641,
|
|
"mean_token_accuracy": 0.2249986097216606,
|
|
"num_tokens": 64390718.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 4.8548736572265625,
|
|
"epoch": 2.743895175699821,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004260814248237432,
|
|
"loss": 4.4804,
|
|
"mean_token_accuracy": 0.2350762590765953,
|
|
"num_tokens": 64405206.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 4.846575498580933,
|
|
"epoch": 2.744490768314473,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00042604984491706477,
|
|
"loss": 4.518,
|
|
"mean_token_accuracy": 0.2348688319325447,
|
|
"num_tokens": 64419758.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 4.802682733535766,
|
|
"epoch": 2.7450863609291245,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000426018259592474,
|
|
"loss": 4.4792,
|
|
"mean_token_accuracy": 0.23416000306606294,
|
|
"num_tokens": 64435575.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 4.809235954284668,
|
|
"epoch": 2.745681953543776,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042598666885110373,
|
|
"loss": 4.4492,
|
|
"mean_token_accuracy": 0.235120952129364,
|
|
"num_tokens": 64448239.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 4.855081558227539,
|
|
"epoch": 2.746277546158428,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004259550726940872,
|
|
"loss": 4.5212,
|
|
"mean_token_accuracy": 0.23296718895435334,
|
|
"num_tokens": 64461269.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 4.832141876220703,
|
|
"epoch": 2.746873138773079,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042592347112255756,
|
|
"loss": 4.5328,
|
|
"mean_token_accuracy": 0.23061880022287368,
|
|
"num_tokens": 64476081.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 4.766437005996704,
|
|
"epoch": 2.747468731387731,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00042589186413764845,
|
|
"loss": 4.4306,
|
|
"mean_token_accuracy": 0.24454076141119002,
|
|
"num_tokens": 64490278.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 4.874114656448365,
|
|
"epoch": 2.7480643240023825,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042586025174049354,
|
|
"loss": 4.5461,
|
|
"mean_token_accuracy": 0.2302006810903549,
|
|
"num_tokens": 64504056.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 4.829137897491455,
|
|
"epoch": 2.748659916617034,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004258286339322266,
|
|
"loss": 4.4683,
|
|
"mean_token_accuracy": 0.23624743521213531,
|
|
"num_tokens": 64516141.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 4.81819109916687,
|
|
"epoch": 2.7492555092316855,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004257970107139819,
|
|
"loss": 4.5569,
|
|
"mean_token_accuracy": 0.23322177231311797,
|
|
"num_tokens": 64531138.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 4.8591982364654545,
|
|
"epoch": 2.749851101846337,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004257653820868935,
|
|
"loss": 4.5203,
|
|
"mean_token_accuracy": 0.23961235135793685,
|
|
"num_tokens": 64545804.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 4.887569856643677,
|
|
"epoch": 2.7504466944609884,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004257337480520961,
|
|
"loss": 4.5922,
|
|
"mean_token_accuracy": 0.23086408376693726,
|
|
"num_tokens": 64559917.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 4.84059739112854,
|
|
"epoch": 2.75104228707564,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004257021086107241,
|
|
"loss": 4.4985,
|
|
"mean_token_accuracy": 0.23492802083492278,
|
|
"num_tokens": 64571471.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 4.842843818664551,
|
|
"epoch": 2.751637879690292,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004256704637639126,
|
|
"loss": 4.5674,
|
|
"mean_token_accuracy": 0.2301850512623787,
|
|
"num_tokens": 64584655.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 4.938783264160156,
|
|
"epoch": 2.7522334723049435,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004256388135127965,
|
|
"loss": 4.6264,
|
|
"mean_token_accuracy": 0.21177586615085603,
|
|
"num_tokens": 64597150.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 4.93258752822876,
|
|
"epoch": 2.7528290649195952,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004256071578585111,
|
|
"loss": 4.597,
|
|
"mean_token_accuracy": 0.2275615304708481,
|
|
"num_tokens": 64610766.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 4.83165135383606,
|
|
"epoch": 2.7534246575342465,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004255754968021918,
|
|
"loss": 4.4851,
|
|
"mean_token_accuracy": 0.2332117363810539,
|
|
"num_tokens": 64624135.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 4.86894006729126,
|
|
"epoch": 2.754020250148898,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004255438303449742,
|
|
"loss": 4.5936,
|
|
"mean_token_accuracy": 0.2300705388188362,
|
|
"num_tokens": 64637047.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 4.828486633300781,
|
|
"epoch": 2.75461584276355,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042551215848799423,
|
|
"loss": 4.4352,
|
|
"mean_token_accuracy": 0.23555172234773636,
|
|
"num_tokens": 64651823.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 4.844184446334839,
|
|
"epoch": 2.755211435378201,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042548048123238787,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.22952800542116164,
|
|
"num_tokens": 64663700.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 4.856780004501343,
|
|
"epoch": 2.755807027992853,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042544879857929133,
|
|
"loss": 4.5312,
|
|
"mean_token_accuracy": 0.24133591800928117,
|
|
"num_tokens": 64677237.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 4.846324682235718,
|
|
"epoch": 2.7564026206075045,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042541711052984096,
|
|
"loss": 4.4847,
|
|
"mean_token_accuracy": 0.23278932571411132,
|
|
"num_tokens": 64691379.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 4.7629602432250975,
|
|
"epoch": 2.7569982132221558,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042538541708517344,
|
|
"loss": 4.407,
|
|
"mean_token_accuracy": 0.24090753942728044,
|
|
"num_tokens": 64704633.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 4.9416296005249025,
|
|
"epoch": 2.7575938058368075,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042535371824642545,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.212916798889637,
|
|
"num_tokens": 64719591.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 4.961523771286011,
|
|
"epoch": 2.758189398451459,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004253220140147341,
|
|
"loss": 4.6099,
|
|
"mean_token_accuracy": 0.23583859652280809,
|
|
"num_tokens": 64732274.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 4.822484683990479,
|
|
"epoch": 2.758784991066111,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004252903043912365,
|
|
"loss": 4.4732,
|
|
"mean_token_accuracy": 0.23737636655569078,
|
|
"num_tokens": 64745756.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 4.898668479919434,
|
|
"epoch": 2.7593805836807626,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00042525858937707,
|
|
"loss": 4.6394,
|
|
"mean_token_accuracy": 0.22190040796995164,
|
|
"num_tokens": 64761172.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 4.831135416030884,
|
|
"epoch": 2.759976176295414,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004252268689733722,
|
|
"loss": 4.4698,
|
|
"mean_token_accuracy": 0.2311901867389679,
|
|
"num_tokens": 64774917.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 4.846983623504639,
|
|
"epoch": 2.7605717689100655,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00042519514318128086,
|
|
"loss": 4.515,
|
|
"mean_token_accuracy": 0.22632568925619126,
|
|
"num_tokens": 64788046.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 4.853474044799805,
|
|
"epoch": 2.761167361524717,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00042516341200193403,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.2293482691049576,
|
|
"num_tokens": 64802883.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 4.776068258285522,
|
|
"epoch": 2.7617629541393685,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042513167543646975,
|
|
"loss": 4.4459,
|
|
"mean_token_accuracy": 0.23861474096775054,
|
|
"num_tokens": 64816719.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 4.884903144836426,
|
|
"epoch": 2.76235854675402,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042509993348602634,
|
|
"loss": 4.5465,
|
|
"mean_token_accuracy": 0.22651562541723252,
|
|
"num_tokens": 64829622.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 4.893245029449463,
|
|
"epoch": 2.762954139368672,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042506818615174237,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.22927845418453216,
|
|
"num_tokens": 64843847.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 4.826480674743652,
|
|
"epoch": 2.7635497319833235,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004250364334347565,
|
|
"loss": 4.4838,
|
|
"mean_token_accuracy": 0.2298777788877487,
|
|
"num_tokens": 64859968.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 4.889726734161377,
|
|
"epoch": 2.7641453245979752,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00042500467533620773,
|
|
"loss": 4.5198,
|
|
"mean_token_accuracy": 0.2328175574541092,
|
|
"num_tokens": 64874405.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 4.845063304901123,
|
|
"epoch": 2.7647409172126265,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004249729118572352,
|
|
"loss": 4.5567,
|
|
"mean_token_accuracy": 0.2350447356700897,
|
|
"num_tokens": 64887729.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 4.84998836517334,
|
|
"epoch": 2.765336509827278,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042494114299897813,
|
|
"loss": 4.5375,
|
|
"mean_token_accuracy": 0.22822367548942565,
|
|
"num_tokens": 64902727.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 4.8613053321838375,
|
|
"epoch": 2.76593210244193,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004249093687625761,
|
|
"loss": 4.557,
|
|
"mean_token_accuracy": 0.2273403912782669,
|
|
"num_tokens": 64917249.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 4.823974323272705,
|
|
"epoch": 2.766527695056581,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004248775891491686,
|
|
"loss": 4.476,
|
|
"mean_token_accuracy": 0.23223866373300553,
|
|
"num_tokens": 64933397.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 4.888440275192261,
|
|
"epoch": 2.767123287671233,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004248458041598958,
|
|
"loss": 4.5411,
|
|
"mean_token_accuracy": 0.22841559797525407,
|
|
"num_tokens": 64946355.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 4.82898097038269,
|
|
"epoch": 2.7677188802858845,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004248140137958976,
|
|
"loss": 4.5209,
|
|
"mean_token_accuracy": 0.2307184711098671,
|
|
"num_tokens": 64959115.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 4.80607385635376,
|
|
"epoch": 2.768314472900536,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042478221805831437,
|
|
"loss": 4.4745,
|
|
"mean_token_accuracy": 0.2351846531033516,
|
|
"num_tokens": 64973198.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 4.896486473083496,
|
|
"epoch": 2.7689100655151875,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042475041694828644,
|
|
"loss": 4.6017,
|
|
"mean_token_accuracy": 0.22895603477954865,
|
|
"num_tokens": 64983838.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 4.814358949661255,
|
|
"epoch": 2.769505658129839,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042471861046695453,
|
|
"loss": 4.5046,
|
|
"mean_token_accuracy": 0.2318379521369934,
|
|
"num_tokens": 64997739.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 4.7730413436889645,
|
|
"epoch": 2.770101250744491,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004246867986154595,
|
|
"loss": 4.5204,
|
|
"mean_token_accuracy": 0.2367227628827095,
|
|
"num_tokens": 65011443.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 4.941702508926392,
|
|
"epoch": 2.7706968433591426,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004246549813949424,
|
|
"loss": 4.5997,
|
|
"mean_token_accuracy": 0.22124033719301223,
|
|
"num_tokens": 65025713.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 4.87913761138916,
|
|
"epoch": 2.771292435973794,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004246231588065444,
|
|
"loss": 4.4994,
|
|
"mean_token_accuracy": 0.2309613600373268,
|
|
"num_tokens": 65039062.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 4.754719209671021,
|
|
"epoch": 2.7718880285884455,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000424591330851407,
|
|
"loss": 4.4543,
|
|
"mean_token_accuracy": 0.23897564858198167,
|
|
"num_tokens": 65053183.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 4.900100135803223,
|
|
"epoch": 2.772483621203097,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004245594975306718,
|
|
"loss": 4.63,
|
|
"mean_token_accuracy": 0.22553303390741347,
|
|
"num_tokens": 65068151.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 4.819545698165894,
|
|
"epoch": 2.7730792138177485,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042452765884548057,
|
|
"loss": 4.5048,
|
|
"mean_token_accuracy": 0.23435891717672347,
|
|
"num_tokens": 65081231.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 4.92873854637146,
|
|
"epoch": 2.7736748064324,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00042449581479697527,
|
|
"loss": 4.5654,
|
|
"mean_token_accuracy": 0.2233162373304367,
|
|
"num_tokens": 65094224.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 4.879285669326782,
|
|
"epoch": 2.774270399047052,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004244639653862983,
|
|
"loss": 4.5309,
|
|
"mean_token_accuracy": 0.2290731444954872,
|
|
"num_tokens": 65106439.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 4.755163717269897,
|
|
"epoch": 2.7748659916617036,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042443211061459185,
|
|
"loss": 4.451,
|
|
"mean_token_accuracy": 0.24215793162584304,
|
|
"num_tokens": 65118801.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 4.913939523696899,
|
|
"epoch": 2.775461584276355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042440025048299845,
|
|
"loss": 4.5741,
|
|
"mean_token_accuracy": 0.22344851791858672,
|
|
"num_tokens": 65131854.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 4.831999731063843,
|
|
"epoch": 2.7760571768910065,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042436838499266107,
|
|
"loss": 4.4104,
|
|
"mean_token_accuracy": 0.24210689216852188,
|
|
"num_tokens": 65146051.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 4.756537675857544,
|
|
"epoch": 2.776652769505658,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042433651414472255,
|
|
"loss": 4.4738,
|
|
"mean_token_accuracy": 0.2371187537908554,
|
|
"num_tokens": 65161142.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 4.880224514007568,
|
|
"epoch": 2.77724836212031,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042430463794032613,
|
|
"loss": 4.5674,
|
|
"mean_token_accuracy": 0.22830553352832794,
|
|
"num_tokens": 65173891.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 4.92331018447876,
|
|
"epoch": 2.777843954734961,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000424272756380615,
|
|
"loss": 4.6132,
|
|
"mean_token_accuracy": 0.22891238182783127,
|
|
"num_tokens": 65186971.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 4.943950605392456,
|
|
"epoch": 2.778439547349613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004242408694667329,
|
|
"loss": 4.6247,
|
|
"mean_token_accuracy": 0.2202969402074814,
|
|
"num_tokens": 65200622.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 4.813218021392823,
|
|
"epoch": 2.7790351399642645,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004242089771998234,
|
|
"loss": 4.5588,
|
|
"mean_token_accuracy": 0.2365364834666252,
|
|
"num_tokens": 65214600.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 4.825481319427491,
|
|
"epoch": 2.779630732578916,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00042417707958103054,
|
|
"loss": 4.4359,
|
|
"mean_token_accuracy": 0.24119285941123964,
|
|
"num_tokens": 65227347.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 4.8525965213775635,
|
|
"epoch": 2.7802263251935675,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004241451766114984,
|
|
"loss": 4.4902,
|
|
"mean_token_accuracy": 0.23716889023780824,
|
|
"num_tokens": 65241078.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 4.834964752197266,
|
|
"epoch": 2.780821917808219,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042411326829237117,
|
|
"loss": 4.4813,
|
|
"mean_token_accuracy": 0.2329440549015999,
|
|
"num_tokens": 65253851.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 4.901344299316406,
|
|
"epoch": 2.781417510422871,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00042408135462479354,
|
|
"loss": 4.5398,
|
|
"mean_token_accuracy": 0.23260907232761383,
|
|
"num_tokens": 65267970.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 4.8420555114746096,
|
|
"epoch": 2.7820131030375226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004240494356099101,
|
|
"loss": 4.5359,
|
|
"mean_token_accuracy": 0.23120975345373154,
|
|
"num_tokens": 65282804.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 4.824302816390992,
|
|
"epoch": 2.782608695652174,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004240175112488657,
|
|
"loss": 4.5137,
|
|
"mean_token_accuracy": 0.22920838743448257,
|
|
"num_tokens": 65296260.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 4.855774688720703,
|
|
"epoch": 2.7832042882668255,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004239855815428055,
|
|
"loss": 4.4987,
|
|
"mean_token_accuracy": 0.23183181285858154,
|
|
"num_tokens": 65310751.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 4.85989727973938,
|
|
"epoch": 2.7837998808814772,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004239536464928747,
|
|
"loss": 4.5968,
|
|
"mean_token_accuracy": 0.22942357510328293,
|
|
"num_tokens": 65326066.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 4.762788963317871,
|
|
"epoch": 2.7843954734961285,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004239217061002188,
|
|
"loss": 4.4341,
|
|
"mean_token_accuracy": 0.23911699801683425,
|
|
"num_tokens": 65339176.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 4.842779207229614,
|
|
"epoch": 2.78499106611078,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004238897603659834,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.2289945214986801,
|
|
"num_tokens": 65353535.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 4.853712558746338,
|
|
"epoch": 2.785586658725432,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004238578092913144,
|
|
"loss": 4.5256,
|
|
"mean_token_accuracy": 0.2334468349814415,
|
|
"num_tokens": 65367418.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 4.917782497406006,
|
|
"epoch": 2.786182251340083,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004238258528773578,
|
|
"loss": 4.6104,
|
|
"mean_token_accuracy": 0.22393167465925218,
|
|
"num_tokens": 65382082.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 4.885558843612671,
|
|
"epoch": 2.786777843954735,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00042379389112525985,
|
|
"loss": 4.5347,
|
|
"mean_token_accuracy": 0.23800286203622817,
|
|
"num_tokens": 65396350.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 4.883155441284179,
|
|
"epoch": 2.7873734365693865,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004237619240361669,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.2299063175916672,
|
|
"num_tokens": 65408755.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 4.805337715148926,
|
|
"epoch": 2.787969029184038,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042372995161122566,
|
|
"loss": 4.5219,
|
|
"mean_token_accuracy": 0.2344240888953209,
|
|
"num_tokens": 65422881.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 4.927366495132446,
|
|
"epoch": 2.78856462179869,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042369797385158293,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.22420968115329742,
|
|
"num_tokens": 65437332.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 4.807370853424072,
|
|
"epoch": 2.789160214413341,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042366599075838553,
|
|
"loss": 4.4624,
|
|
"mean_token_accuracy": 0.24155545383691787,
|
|
"num_tokens": 65450195.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 4.842518901824951,
|
|
"epoch": 2.789755807027993,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042363400233278077,
|
|
"loss": 4.5416,
|
|
"mean_token_accuracy": 0.22516629993915557,
|
|
"num_tokens": 65464690.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 4.872834873199463,
|
|
"epoch": 2.7903513996426446,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004236020085759161,
|
|
"loss": 4.5485,
|
|
"mean_token_accuracy": 0.22486198395490647,
|
|
"num_tokens": 65480632.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 4.910489416122436,
|
|
"epoch": 2.790946992257296,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042357000948893894,
|
|
"loss": 4.5574,
|
|
"mean_token_accuracy": 0.229511621594429,
|
|
"num_tokens": 65494847.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 4.858185291290283,
|
|
"epoch": 2.7915425848719475,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004235380050729971,
|
|
"loss": 4.577,
|
|
"mean_token_accuracy": 0.22582982927560807,
|
|
"num_tokens": 65507807.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 4.831294775009155,
|
|
"epoch": 2.792138177486599,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004235059953292385,
|
|
"loss": 4.5113,
|
|
"mean_token_accuracy": 0.23490194231271744,
|
|
"num_tokens": 65520047.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 4.831264162063599,
|
|
"epoch": 2.792733770101251,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00042347398025881135,
|
|
"loss": 4.4918,
|
|
"mean_token_accuracy": 0.24037242978811263,
|
|
"num_tokens": 65532546.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 4.757965517044068,
|
|
"epoch": 2.7933293627159026,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004234419598628639,
|
|
"loss": 4.4165,
|
|
"mean_token_accuracy": 0.2394477531313896,
|
|
"num_tokens": 65547657.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 4.803307294845581,
|
|
"epoch": 2.793924955330554,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004234099341425447,
|
|
"loss": 4.4647,
|
|
"mean_token_accuracy": 0.23326809704303741,
|
|
"num_tokens": 65561644.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 4.763795948028564,
|
|
"epoch": 2.7945205479452055,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042337790309900254,
|
|
"loss": 4.4888,
|
|
"mean_token_accuracy": 0.2299646258354187,
|
|
"num_tokens": 65575480.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 4.718370723724365,
|
|
"epoch": 2.7951161405598572,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00042334586673338623,
|
|
"loss": 4.4023,
|
|
"mean_token_accuracy": 0.24346737563610077,
|
|
"num_tokens": 65588562.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 4.813689470291138,
|
|
"epoch": 2.7957117331745085,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042331382504684473,
|
|
"loss": 4.4769,
|
|
"mean_token_accuracy": 0.2351676732301712,
|
|
"num_tokens": 65602758.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 4.890967226028442,
|
|
"epoch": 2.79630732578916,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004232817780405276,
|
|
"loss": 4.5619,
|
|
"mean_token_accuracy": 0.2395457446575165,
|
|
"num_tokens": 65616310.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 4.816812562942505,
|
|
"epoch": 2.796902918403812,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042324972571558414,
|
|
"loss": 4.5584,
|
|
"mean_token_accuracy": 0.23661045879125595,
|
|
"num_tokens": 65630250.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 4.902778291702271,
|
|
"epoch": 2.797498511018463,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042321766807316405,
|
|
"loss": 4.5817,
|
|
"mean_token_accuracy": 0.2247089773416519,
|
|
"num_tokens": 65644224.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 4.8874575138092045,
|
|
"epoch": 2.798094103633115,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004231856051144172,
|
|
"loss": 4.5534,
|
|
"mean_token_accuracy": 0.2342667505145073,
|
|
"num_tokens": 65657801.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 4.881520366668701,
|
|
"epoch": 2.7986896962477665,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004231535368404936,
|
|
"loss": 4.5081,
|
|
"mean_token_accuracy": 0.23425489515066147,
|
|
"num_tokens": 65669567.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 4.870121431350708,
|
|
"epoch": 2.7992852888624182,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004231214632525436,
|
|
"loss": 4.5587,
|
|
"mean_token_accuracy": 0.22685993164777757,
|
|
"num_tokens": 65684858.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 4.806415176391601,
|
|
"epoch": 2.79988088147707,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042308938435171753,
|
|
"loss": 4.4455,
|
|
"mean_token_accuracy": 0.2396983325481415,
|
|
"num_tokens": 65698754.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 4.77959942817688,
|
|
"epoch": 2.800476474091721,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004230573001391659,
|
|
"loss": 4.4589,
|
|
"mean_token_accuracy": 0.23012059330940246,
|
|
"num_tokens": 65713099.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 4.854727172851563,
|
|
"epoch": 2.801072066706373,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042302521061603985,
|
|
"loss": 4.5865,
|
|
"mean_token_accuracy": 0.22658391743898393,
|
|
"num_tokens": 65726828.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 4.9291047096252445,
|
|
"epoch": 2.8016676593210246,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042299311578349003,
|
|
"loss": 4.6133,
|
|
"mean_token_accuracy": 0.22457538098096846,
|
|
"num_tokens": 65741983.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 4.818138599395752,
|
|
"epoch": 2.802263251935676,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042296101564266774,
|
|
"loss": 4.4703,
|
|
"mean_token_accuracy": 0.23969775736331939,
|
|
"num_tokens": 65755071.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 4.888807249069214,
|
|
"epoch": 2.8028588445503275,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004229289101947245,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.2256354108452797,
|
|
"num_tokens": 65767728.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 4.797237062454224,
|
|
"epoch": 2.803454437164979,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00042289679944081164,
|
|
"loss": 4.4306,
|
|
"mean_token_accuracy": 0.24035394936800003,
|
|
"num_tokens": 65780606.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 4.90137505531311,
|
|
"epoch": 2.8040500297796305,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00042286468338208113,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.2221583753824234,
|
|
"num_tokens": 65794646.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 4.9361937046051025,
|
|
"epoch": 2.804645622394282,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042283256201968485,
|
|
"loss": 4.5801,
|
|
"mean_token_accuracy": 0.22545793652534485,
|
|
"num_tokens": 65809057.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 4.90381817817688,
|
|
"epoch": 2.805241215008934,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004228004353547749,
|
|
"loss": 4.5695,
|
|
"mean_token_accuracy": 0.2281576171517372,
|
|
"num_tokens": 65821901.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 4.852563714981079,
|
|
"epoch": 2.8058368076235856,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004227683033885036,
|
|
"loss": 4.5787,
|
|
"mean_token_accuracy": 0.2304189145565033,
|
|
"num_tokens": 65835239.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 4.836330509185791,
|
|
"epoch": 2.8064324002382373,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00042273616612202363,
|
|
"loss": 4.5244,
|
|
"mean_token_accuracy": 0.23083751648664474,
|
|
"num_tokens": 65851116.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 4.863216924667358,
|
|
"epoch": 2.8070279928528885,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004227040235564875,
|
|
"loss": 4.462,
|
|
"mean_token_accuracy": 0.2384291857481003,
|
|
"num_tokens": 65864346.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 4.848590326309204,
|
|
"epoch": 2.80762358546754,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042267187569304825,
|
|
"loss": 4.5302,
|
|
"mean_token_accuracy": 0.23422824144363402,
|
|
"num_tokens": 65877720.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 4.827950525283813,
|
|
"epoch": 2.808219178082192,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004226397225328589,
|
|
"loss": 4.4698,
|
|
"mean_token_accuracy": 0.23583834171295165,
|
|
"num_tokens": 65891187.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 4.869866609573364,
|
|
"epoch": 2.808814770696843,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042260756407707273,
|
|
"loss": 4.5713,
|
|
"mean_token_accuracy": 0.23750094324350357,
|
|
"num_tokens": 65904611.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 4.8760106563568115,
|
|
"epoch": 2.809410363311495,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042257540032684325,
|
|
"loss": 4.5807,
|
|
"mean_token_accuracy": 0.2205899253487587,
|
|
"num_tokens": 65920226.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 4.869102144241333,
|
|
"epoch": 2.8100059559261465,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00042254323128332403,
|
|
"loss": 4.5027,
|
|
"mean_token_accuracy": 0.2396081879734993,
|
|
"num_tokens": 65934212.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 4.85962438583374,
|
|
"epoch": 2.8106015485407982,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004225110569476691,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.23161908388137817,
|
|
"num_tokens": 65948421.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 4.831817293167115,
|
|
"epoch": 2.81119714115545,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042247887732103234,
|
|
"loss": 4.4634,
|
|
"mean_token_accuracy": 0.2371412396430969,
|
|
"num_tokens": 65961247.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 4.880771684646606,
|
|
"epoch": 2.811792733770101,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042244669240456813,
|
|
"loss": 4.6036,
|
|
"mean_token_accuracy": 0.22809817641973495,
|
|
"num_tokens": 65973877.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 4.7937194347381595,
|
|
"epoch": 2.812388326384753,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00042241450219943067,
|
|
"loss": 4.435,
|
|
"mean_token_accuracy": 0.236151222884655,
|
|
"num_tokens": 65987791.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 4.78914098739624,
|
|
"epoch": 2.8129839189994046,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042238230670677473,
|
|
"loss": 4.419,
|
|
"mean_token_accuracy": 0.2344570502638817,
|
|
"num_tokens": 66000469.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 4.845566844940185,
|
|
"epoch": 2.813579511614056,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00042235010592775506,
|
|
"loss": 4.4836,
|
|
"mean_token_accuracy": 0.2387687548995018,
|
|
"num_tokens": 66013894.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 4.877668046951294,
|
|
"epoch": 2.8141751042287075,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004223178998635267,
|
|
"loss": 4.535,
|
|
"mean_token_accuracy": 0.23001203387975694,
|
|
"num_tokens": 66029454.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 4.851301908493042,
|
|
"epoch": 2.8147706968433592,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042228568851524487,
|
|
"loss": 4.5885,
|
|
"mean_token_accuracy": 0.2238723263144493,
|
|
"num_tokens": 66043324.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 4.913832902908325,
|
|
"epoch": 2.8153662894580105,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004222534718840647,
|
|
"loss": 4.59,
|
|
"mean_token_accuracy": 0.22535326033830644,
|
|
"num_tokens": 66056649.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 4.93642897605896,
|
|
"epoch": 2.815961882072662,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000422221249971142,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.23232365101575853,
|
|
"num_tokens": 66069813.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 4.946571159362793,
|
|
"epoch": 2.816557474687314,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00042218902277763254,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.22420538812875748,
|
|
"num_tokens": 66084124.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 4.97406792640686,
|
|
"epoch": 2.8171530673019656,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000422156790304692,
|
|
"loss": 4.6819,
|
|
"mean_token_accuracy": 0.22685838490724564,
|
|
"num_tokens": 66098266.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 4.8841540813446045,
|
|
"epoch": 2.8177486599166173,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042212455255347673,
|
|
"loss": 4.5084,
|
|
"mean_token_accuracy": 0.23991698920726776,
|
|
"num_tokens": 66111053.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 4.8159881114959715,
|
|
"epoch": 2.8183442525312685,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042209230952514287,
|
|
"loss": 4.4762,
|
|
"mean_token_accuracy": 0.2422558233141899,
|
|
"num_tokens": 66123628.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 4.856855773925782,
|
|
"epoch": 2.81893984514592,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004220600612208471,
|
|
"loss": 4.5974,
|
|
"mean_token_accuracy": 0.22455568760633468,
|
|
"num_tokens": 66139342.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 4.849260997772217,
|
|
"epoch": 2.819535437760572,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004220278076417461,
|
|
"loss": 4.498,
|
|
"mean_token_accuracy": 0.2299760177731514,
|
|
"num_tokens": 66151746.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 4.803710269927978,
|
|
"epoch": 2.820131030375223,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042199554878899655,
|
|
"loss": 4.4733,
|
|
"mean_token_accuracy": 0.23477563112974167,
|
|
"num_tokens": 66164707.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 4.856471586227417,
|
|
"epoch": 2.820726622989875,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004219632846637557,
|
|
"loss": 4.5455,
|
|
"mean_token_accuracy": 0.22772152423858644,
|
|
"num_tokens": 66180608.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 4.834376192092895,
|
|
"epoch": 2.8213222156045266,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042193101526718087,
|
|
"loss": 4.5283,
|
|
"mean_token_accuracy": 0.22924882620573045,
|
|
"num_tokens": 66194997.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 4.832655620574951,
|
|
"epoch": 2.821917808219178,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004218987406004293,
|
|
"loss": 4.5017,
|
|
"mean_token_accuracy": 0.23729285299777986,
|
|
"num_tokens": 66209414.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 4.717024946212769,
|
|
"epoch": 2.8225134008338295,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042186646066465883,
|
|
"loss": 4.3896,
|
|
"mean_token_accuracy": 0.24307141155004502,
|
|
"num_tokens": 66223900.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 4.753177213668823,
|
|
"epoch": 2.823108993448481,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004218341754610272,
|
|
"loss": 4.4111,
|
|
"mean_token_accuracy": 0.24543422758579253,
|
|
"num_tokens": 66237583.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 4.835961389541626,
|
|
"epoch": 2.823704586063133,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00042180188499069246,
|
|
"loss": 4.5176,
|
|
"mean_token_accuracy": 0.2333895146846771,
|
|
"num_tokens": 66251563.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 4.943625736236572,
|
|
"epoch": 2.8243001786777846,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00042176958925481276,
|
|
"loss": 4.6336,
|
|
"mean_token_accuracy": 0.23706408739089965,
|
|
"num_tokens": 66266599.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 4.871864748001099,
|
|
"epoch": 2.824895771292436,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00042173728825454647,
|
|
"loss": 4.5613,
|
|
"mean_token_accuracy": 0.2264659360051155,
|
|
"num_tokens": 66281419.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 4.864631986618042,
|
|
"epoch": 2.8254913639070875,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00042170498199105234,
|
|
"loss": 4.5541,
|
|
"mean_token_accuracy": 0.2275899440050125,
|
|
"num_tokens": 66294458.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 4.822345209121704,
|
|
"epoch": 2.8260869565217392,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004216726704654889,
|
|
"loss": 4.4701,
|
|
"mean_token_accuracy": 0.23971909284591675,
|
|
"num_tokens": 66307349.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 4.726570892333984,
|
|
"epoch": 2.8266825491363905,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004216403536790153,
|
|
"loss": 4.3806,
|
|
"mean_token_accuracy": 0.24401048719882965,
|
|
"num_tokens": 66320536.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 4.815203332901001,
|
|
"epoch": 2.827278141751042,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004216080316327907,
|
|
"loss": 4.5259,
|
|
"mean_token_accuracy": 0.2264692887663841,
|
|
"num_tokens": 66334491.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 4.855420780181885,
|
|
"epoch": 2.827873734365694,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004215757043279743,
|
|
"loss": 4.5242,
|
|
"mean_token_accuracy": 0.22770762592554092,
|
|
"num_tokens": 66347962.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 4.884823131561279,
|
|
"epoch": 2.8284693269803456,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00042154337176572576,
|
|
"loss": 4.6469,
|
|
"mean_token_accuracy": 0.22531672120094298,
|
|
"num_tokens": 66361558.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 4.88678240776062,
|
|
"epoch": 2.8290649195949973,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004215110339472047,
|
|
"loss": 4.5172,
|
|
"mean_token_accuracy": 0.22602546513080596,
|
|
"num_tokens": 66374180.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 4.849622201919556,
|
|
"epoch": 2.8296605122096485,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004214786908735711,
|
|
"loss": 4.5249,
|
|
"mean_token_accuracy": 0.2332696035504341,
|
|
"num_tokens": 66387764.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 4.749617290496826,
|
|
"epoch": 2.8302561048243002,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000421446342545985,
|
|
"loss": 4.4009,
|
|
"mean_token_accuracy": 0.24499093741178513,
|
|
"num_tokens": 66401189.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 4.800799036026001,
|
|
"epoch": 2.830851697438952,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042141398896560666,
|
|
"loss": 4.4857,
|
|
"mean_token_accuracy": 0.22713180780410766,
|
|
"num_tokens": 66413020.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 4.821416187286377,
|
|
"epoch": 2.831447290053603,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00042138163013359664,
|
|
"loss": 4.57,
|
|
"mean_token_accuracy": 0.22870421558618545,
|
|
"num_tokens": 66427892.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 4.804522848129272,
|
|
"epoch": 2.832042882668255,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004213492660511155,
|
|
"loss": 4.4732,
|
|
"mean_token_accuracy": 0.2403672903776169,
|
|
"num_tokens": 66441144.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 4.728825473785401,
|
|
"epoch": 2.8326384752829066,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004213168967193242,
|
|
"loss": 4.3921,
|
|
"mean_token_accuracy": 0.24626703709363937,
|
|
"num_tokens": 66455267.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 4.832049322128296,
|
|
"epoch": 2.833234067897558,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042128452213938366,
|
|
"loss": 4.5339,
|
|
"mean_token_accuracy": 0.22777758687734603,
|
|
"num_tokens": 66470781.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 4.858828115463257,
|
|
"epoch": 2.8338296605122095,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004212521423124552,
|
|
"loss": 4.5505,
|
|
"mean_token_accuracy": 0.23217614442110063,
|
|
"num_tokens": 66483507.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 4.8943259716033936,
|
|
"epoch": 2.834425253126861,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004212197572397001,
|
|
"loss": 4.5802,
|
|
"mean_token_accuracy": 0.2281075596809387,
|
|
"num_tokens": 66496060.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 4.884398031234741,
|
|
"epoch": 2.835020845741513,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042118736692228016,
|
|
"loss": 4.4978,
|
|
"mean_token_accuracy": 0.22798266410827636,
|
|
"num_tokens": 66511989.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 4.815479755401611,
|
|
"epoch": 2.8356164383561646,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000421154971361357,
|
|
"loss": 4.4858,
|
|
"mean_token_accuracy": 0.2351115807890892,
|
|
"num_tokens": 66526673.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 4.863908052444458,
|
|
"epoch": 2.836212030970816,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00042112257055809264,
|
|
"loss": 4.4878,
|
|
"mean_token_accuracy": 0.23262586295604706,
|
|
"num_tokens": 66539643.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 4.82307276725769,
|
|
"epoch": 2.8368076235854676,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042109016451364933,
|
|
"loss": 4.5755,
|
|
"mean_token_accuracy": 0.22919601649045945,
|
|
"num_tokens": 66553329.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 4.798067378997803,
|
|
"epoch": 2.8374032162001193,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042105775322918927,
|
|
"loss": 4.4833,
|
|
"mean_token_accuracy": 0.23756733685731887,
|
|
"num_tokens": 66566316.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 4.80418176651001,
|
|
"epoch": 2.8379988088147705,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004210253367058751,
|
|
"loss": 4.4289,
|
|
"mean_token_accuracy": 0.2398652896285057,
|
|
"num_tokens": 66579326.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 4.837030696868896,
|
|
"epoch": 2.838594401429422,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00042099291494486946,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.2297938048839569,
|
|
"num_tokens": 66593287.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 4.798227071762085,
|
|
"epoch": 2.839189994044074,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042096048794733543,
|
|
"loss": 4.4783,
|
|
"mean_token_accuracy": 0.23504788130521775,
|
|
"num_tokens": 66608175.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 4.817229223251343,
|
|
"epoch": 2.839785586658725,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000420928055714436,
|
|
"loss": 4.4504,
|
|
"mean_token_accuracy": 0.23915943801403045,
|
|
"num_tokens": 66621267.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 4.8282983779907225,
|
|
"epoch": 2.840381179273377,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004208956182473344,
|
|
"loss": 4.4755,
|
|
"mean_token_accuracy": 0.23956051617860794,
|
|
"num_tokens": 66635488.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 4.831460952758789,
|
|
"epoch": 2.8409767718880286,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00042086317554719424,
|
|
"loss": 4.5259,
|
|
"mean_token_accuracy": 0.23477635979652406,
|
|
"num_tokens": 66648098.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 4.855752897262573,
|
|
"epoch": 2.8415723645026802,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004208307276151792,
|
|
"loss": 4.4844,
|
|
"mean_token_accuracy": 0.2362018421292305,
|
|
"num_tokens": 66662406.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 4.811969327926636,
|
|
"epoch": 2.842167957117332,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000420798274452453,
|
|
"loss": 4.5266,
|
|
"mean_token_accuracy": 0.23796779215335845,
|
|
"num_tokens": 66677017.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 4.8426038265228275,
|
|
"epoch": 2.842763549731983,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042076581606017964,
|
|
"loss": 4.5583,
|
|
"mean_token_accuracy": 0.23158955425024033,
|
|
"num_tokens": 66689747.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 4.886392641067505,
|
|
"epoch": 2.843359142346635,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042073335243952354,
|
|
"loss": 4.5167,
|
|
"mean_token_accuracy": 0.2357734188437462,
|
|
"num_tokens": 66703900.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 4.887901639938354,
|
|
"epoch": 2.8439547349612866,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042070088359164916,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.22827713191509247,
|
|
"num_tokens": 66718810.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 4.842253494262695,
|
|
"epoch": 2.844550327575938,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042066840951772086,
|
|
"loss": 4.5608,
|
|
"mean_token_accuracy": 0.23186120092868806,
|
|
"num_tokens": 66732522.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 4.818824529647827,
|
|
"epoch": 2.8451459201905895,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004206359302189036,
|
|
"loss": 4.4923,
|
|
"mean_token_accuracy": 0.23218378722667693,
|
|
"num_tokens": 66748403.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 4.839881563186646,
|
|
"epoch": 2.8457415128052412,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004206034456963623,
|
|
"loss": 4.5102,
|
|
"mean_token_accuracy": 0.23831096589565276,
|
|
"num_tokens": 66762308.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 4.972278022766114,
|
|
"epoch": 2.846337105419893,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004205709559512621,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.2275146022439003,
|
|
"num_tokens": 66777731.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 4.852166175842285,
|
|
"epoch": 2.8469326980345446,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004205384609847684,
|
|
"loss": 4.588,
|
|
"mean_token_accuracy": 0.22295902371406556,
|
|
"num_tokens": 66792949.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 4.826029491424561,
|
|
"epoch": 2.847528290649196,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004205059607980467,
|
|
"loss": 4.53,
|
|
"mean_token_accuracy": 0.23704061806201934,
|
|
"num_tokens": 66806476.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 4.911848831176758,
|
|
"epoch": 2.8481238832638476,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004204734553922629,
|
|
"loss": 4.5995,
|
|
"mean_token_accuracy": 0.22269946038722993,
|
|
"num_tokens": 66819797.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 4.840117168426514,
|
|
"epoch": 2.8487194758784993,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00042044094476858266,
|
|
"loss": 4.4755,
|
|
"mean_token_accuracy": 0.23541418164968492,
|
|
"num_tokens": 66835714.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 4.855565214157105,
|
|
"epoch": 2.8493150684931505,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042040842892817227,
|
|
"loss": 4.5003,
|
|
"mean_token_accuracy": 0.22833843380212784,
|
|
"num_tokens": 66849673.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 4.721679544448852,
|
|
"epoch": 2.8499106611078022,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004203759078721979,
|
|
"loss": 4.4075,
|
|
"mean_token_accuracy": 0.2511990383267403,
|
|
"num_tokens": 66863641.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 4.76168794631958,
|
|
"epoch": 2.850506253722454,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004203433816018261,
|
|
"loss": 4.4404,
|
|
"mean_token_accuracy": 0.2437072217464447,
|
|
"num_tokens": 66875943.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 4.7613677978515625,
|
|
"epoch": 2.851101846337105,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00042031085011822356,
|
|
"loss": 4.4267,
|
|
"mean_token_accuracy": 0.238374200463295,
|
|
"num_tokens": 66891324.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 4.858303260803223,
|
|
"epoch": 2.851697438951757,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000420278313422557,
|
|
"loss": 4.5443,
|
|
"mean_token_accuracy": 0.23016287684440612,
|
|
"num_tokens": 66905922.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 4.848030853271484,
|
|
"epoch": 2.8522930315664086,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004202457715159936,
|
|
"loss": 4.4842,
|
|
"mean_token_accuracy": 0.23147520720958709,
|
|
"num_tokens": 66921239.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 4.8449312210083,
|
|
"epoch": 2.8528886241810603,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004202132243997005,
|
|
"loss": 4.5359,
|
|
"mean_token_accuracy": 0.2376118093729019,
|
|
"num_tokens": 66934563.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 4.82995867729187,
|
|
"epoch": 2.853484216795712,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042018067207484524,
|
|
"loss": 4.4875,
|
|
"mean_token_accuracy": 0.23355372548103331,
|
|
"num_tokens": 66948703.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 4.8773314476013185,
|
|
"epoch": 2.854079809410363,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004201481145425952,
|
|
"loss": 4.5447,
|
|
"mean_token_accuracy": 0.23222386240959167,
|
|
"num_tokens": 66962295.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 4.853859186172485,
|
|
"epoch": 2.854675402025015,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004201155518041184,
|
|
"loss": 4.5355,
|
|
"mean_token_accuracy": 0.2334549531340599,
|
|
"num_tokens": 66975309.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 4.769010972976685,
|
|
"epoch": 2.8552709946396666,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042008298386058264,
|
|
"loss": 4.3208,
|
|
"mean_token_accuracy": 0.2501913279294968,
|
|
"num_tokens": 66988728.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 4.880132436752319,
|
|
"epoch": 2.855866587254318,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004200504107131561,
|
|
"loss": 4.5769,
|
|
"mean_token_accuracy": 0.23087082356214522,
|
|
"num_tokens": 67003395.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 4.8158862590789795,
|
|
"epoch": 2.8564621798689696,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004200178323630072,
|
|
"loss": 4.4989,
|
|
"mean_token_accuracy": 0.23621235191822051,
|
|
"num_tokens": 67015563.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 4.8111066818237305,
|
|
"epoch": 2.8570577724836212,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041998524881130446,
|
|
"loss": 4.5562,
|
|
"mean_token_accuracy": 0.2273653745651245,
|
|
"num_tokens": 67028720.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 4.8716284275054935,
|
|
"epoch": 2.857653365098273,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041995266005921656,
|
|
"loss": 4.4968,
|
|
"mean_token_accuracy": 0.22820765525102615,
|
|
"num_tokens": 67042367.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 4.9066554546356205,
|
|
"epoch": 2.858248957712924,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004199200661079124,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.22765980064868926,
|
|
"num_tokens": 67056229.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 4.868706560134887,
|
|
"epoch": 2.858844550327576,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041988746695856115,
|
|
"loss": 4.5228,
|
|
"mean_token_accuracy": 0.23786299377679826,
|
|
"num_tokens": 67070743.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.858844550327576,
|
|
"eval_entropy": 4.628673092399645,
|
|
"eval_loss": 4.5798234939575195,
|
|
"eval_mean_token_accuracy": 0.23973892112744266,
|
|
"eval_num_tokens": 67070743.0,
|
|
"eval_runtime": 24.0924,
|
|
"eval_samples_per_second": 1058.967,
|
|
"eval_steps_per_second": 132.407,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 4.793101453781128,
|
|
"epoch": 2.8594401429422276,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041985486261233204,
|
|
"loss": 4.4479,
|
|
"mean_token_accuracy": 0.23773935586214065,
|
|
"num_tokens": 67085743.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 4.781210088729859,
|
|
"epoch": 2.8600357355568793,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004198222530703944,
|
|
"loss": 4.4961,
|
|
"mean_token_accuracy": 0.2365051031112671,
|
|
"num_tokens": 67100214.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 4.7920139789581295,
|
|
"epoch": 2.8606313281715305,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00041978963833391817,
|
|
"loss": 4.4973,
|
|
"mean_token_accuracy": 0.24029427617788315,
|
|
"num_tokens": 67113756.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 4.784905433654785,
|
|
"epoch": 2.8612269207861822,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041975701840407296,
|
|
"loss": 4.47,
|
|
"mean_token_accuracy": 0.24022151231765748,
|
|
"num_tokens": 67126742.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 4.800309133529663,
|
|
"epoch": 2.861822513400834,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004197243932820288,
|
|
"loss": 4.5182,
|
|
"mean_token_accuracy": 0.2345799446105957,
|
|
"num_tokens": 67142402.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 4.881731700897217,
|
|
"epoch": 2.862418106015485,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000419691762968956,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.23528345823287963,
|
|
"num_tokens": 67154297.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 4.959474754333496,
|
|
"epoch": 2.863013698630137,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041965912746602495,
|
|
"loss": 4.6243,
|
|
"mean_token_accuracy": 0.22483722120523453,
|
|
"num_tokens": 67169293.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 5.064023733139038,
|
|
"epoch": 2.8636092912447886,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004196264867744062,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.21431550085544587,
|
|
"num_tokens": 67183982.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 4.8258452892303465,
|
|
"epoch": 2.8642048838594403,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004195938408952704,
|
|
"loss": 4.4856,
|
|
"mean_token_accuracy": 0.23462871164083482,
|
|
"num_tokens": 67197269.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 4.8726033687591555,
|
|
"epoch": 2.864800476474092,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004195611898297888,
|
|
"loss": 4.549,
|
|
"mean_token_accuracy": 0.22868871837854385,
|
|
"num_tokens": 67210059.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 4.859888219833374,
|
|
"epoch": 2.8653960690887432,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004195285335791323,
|
|
"loss": 4.562,
|
|
"mean_token_accuracy": 0.23139860481023788,
|
|
"num_tokens": 67224081.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 4.800658559799194,
|
|
"epoch": 2.865991661703395,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00041949587214447224,
|
|
"loss": 4.4953,
|
|
"mean_token_accuracy": 0.22802060693502427,
|
|
"num_tokens": 67238443.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 4.748124408721924,
|
|
"epoch": 2.8665872543180466,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004194632055269802,
|
|
"loss": 4.4443,
|
|
"mean_token_accuracy": 0.2438424915075302,
|
|
"num_tokens": 67253765.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 4.874856615066529,
|
|
"epoch": 2.867182846932698,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004194305337278279,
|
|
"loss": 4.5279,
|
|
"mean_token_accuracy": 0.23446561992168427,
|
|
"num_tokens": 67268883.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 4.924755477905274,
|
|
"epoch": 2.8677784395473496,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00041939785674818716,
|
|
"loss": 4.6204,
|
|
"mean_token_accuracy": 0.22614359557628633,
|
|
"num_tokens": 67284545.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 4.837911987304688,
|
|
"epoch": 2.8683740321620013,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041936517458923006,
|
|
"loss": 4.5496,
|
|
"mean_token_accuracy": 0.22726970613002778,
|
|
"num_tokens": 67300984.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 4.91603307723999,
|
|
"epoch": 2.8689696247766525,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004193324872521289,
|
|
"loss": 4.6449,
|
|
"mean_token_accuracy": 0.22459470480680466,
|
|
"num_tokens": 67313982.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 4.806512022018433,
|
|
"epoch": 2.869565217391304,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041929979473805606,
|
|
"loss": 4.403,
|
|
"mean_token_accuracy": 0.24223243892192842,
|
|
"num_tokens": 67325968.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 4.835772705078125,
|
|
"epoch": 2.870160810005956,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004192670970481843,
|
|
"loss": 4.5298,
|
|
"mean_token_accuracy": 0.23719437271356583,
|
|
"num_tokens": 67338870.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 4.725936937332153,
|
|
"epoch": 2.8707564026206076,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004192343941836861,
|
|
"loss": 4.338,
|
|
"mean_token_accuracy": 0.25147135108709334,
|
|
"num_tokens": 67351946.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 4.866654872894287,
|
|
"epoch": 2.8713519952352593,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000419201686145735,
|
|
"loss": 4.5467,
|
|
"mean_token_accuracy": 0.23020472526550292,
|
|
"num_tokens": 67368802.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 4.839614963531494,
|
|
"epoch": 2.8719475878499106,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004191689729355037,
|
|
"loss": 4.5324,
|
|
"mean_token_accuracy": 0.2276088550686836,
|
|
"num_tokens": 67383660.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 4.751908826828003,
|
|
"epoch": 2.8725431804645623,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041913625455416564,
|
|
"loss": 4.4732,
|
|
"mean_token_accuracy": 0.24181035459041594,
|
|
"num_tokens": 67397678.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 4.834235382080078,
|
|
"epoch": 2.873138773079214,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004191035310028947,
|
|
"loss": 4.5089,
|
|
"mean_token_accuracy": 0.23247072249650955,
|
|
"num_tokens": 67412008.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 4.891389274597168,
|
|
"epoch": 2.873734365693865,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004190708022828643,
|
|
"loss": 4.5054,
|
|
"mean_token_accuracy": 0.23867012858390807,
|
|
"num_tokens": 67426235.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 4.874739503860473,
|
|
"epoch": 2.874329958308517,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00041903806839524844,
|
|
"loss": 4.6098,
|
|
"mean_token_accuracy": 0.22395907640457152,
|
|
"num_tokens": 67441823.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 4.7880669116973875,
|
|
"epoch": 2.8749255509231686,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004190053293412213,
|
|
"loss": 4.4663,
|
|
"mean_token_accuracy": 0.24463729113340377,
|
|
"num_tokens": 67456336.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 4.886403656005859,
|
|
"epoch": 2.8755211435378203,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004189725851219571,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.2271299421787262,
|
|
"num_tokens": 67472289.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 4.87114987373352,
|
|
"epoch": 2.876116736152472,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041893983573863044,
|
|
"loss": 4.5177,
|
|
"mean_token_accuracy": 0.24304956793785096,
|
|
"num_tokens": 67488496.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 4.853968811035156,
|
|
"epoch": 2.8767123287671232,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041890708119241585,
|
|
"loss": 4.545,
|
|
"mean_token_accuracy": 0.23796035647392272,
|
|
"num_tokens": 67503170.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 4.834029340744019,
|
|
"epoch": 2.877307921381775,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004188743214844882,
|
|
"loss": 4.4979,
|
|
"mean_token_accuracy": 0.23311890959739684,
|
|
"num_tokens": 67518022.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 4.835097312927246,
|
|
"epoch": 2.8779035139964266,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00041884155661602257,
|
|
"loss": 4.5211,
|
|
"mean_token_accuracy": 0.23502418547868728,
|
|
"num_tokens": 67531856.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 4.841748380661011,
|
|
"epoch": 2.878499106611078,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041880878658819427,
|
|
"loss": 4.5354,
|
|
"mean_token_accuracy": 0.23041969537734985,
|
|
"num_tokens": 67544896.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 4.827758884429931,
|
|
"epoch": 2.8790946992257296,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041877601140217845,
|
|
"loss": 4.4932,
|
|
"mean_token_accuracy": 0.24015310704708098,
|
|
"num_tokens": 67558647.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 4.875018310546875,
|
|
"epoch": 2.8796902918403813,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004187432310591511,
|
|
"loss": 4.5422,
|
|
"mean_token_accuracy": 0.2261686310172081,
|
|
"num_tokens": 67572304.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 4.906844902038574,
|
|
"epoch": 2.8802858844550325,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004187104455602875,
|
|
"loss": 4.5978,
|
|
"mean_token_accuracy": 0.22650453299283982,
|
|
"num_tokens": 67586722.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 4.85185055732727,
|
|
"epoch": 2.8808814770696842,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000418677654906764,
|
|
"loss": 4.4978,
|
|
"mean_token_accuracy": 0.23336181044578552,
|
|
"num_tokens": 67600499.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 4.8733663082122805,
|
|
"epoch": 2.881477069684336,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004186448590997567,
|
|
"loss": 4.5554,
|
|
"mean_token_accuracy": 0.23192697316408156,
|
|
"num_tokens": 67615723.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 4.817930841445923,
|
|
"epoch": 2.8820726622989876,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041861205814044174,
|
|
"loss": 4.4691,
|
|
"mean_token_accuracy": 0.23425636142492295,
|
|
"num_tokens": 67629736.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 4.863938903808593,
|
|
"epoch": 2.8826682549136393,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00041857925202999586,
|
|
"loss": 4.5561,
|
|
"mean_token_accuracy": 0.22601507753133773,
|
|
"num_tokens": 67644458.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 4.781367301940918,
|
|
"epoch": 2.8832638475282906,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004185464407695956,
|
|
"loss": 4.4743,
|
|
"mean_token_accuracy": 0.23909828811883926,
|
|
"num_tokens": 67657219.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 4.767983865737915,
|
|
"epoch": 2.8838594401429423,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004185136243604178,
|
|
"loss": 4.4259,
|
|
"mean_token_accuracy": 0.24539515674114226,
|
|
"num_tokens": 67672048.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 4.860842180252075,
|
|
"epoch": 2.884455032757594,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004184808028036398,
|
|
"loss": 4.5854,
|
|
"mean_token_accuracy": 0.23385871946811676,
|
|
"num_tokens": 67685160.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 4.8415771484375,
|
|
"epoch": 2.885050625372245,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004184479761004386,
|
|
"loss": 4.4946,
|
|
"mean_token_accuracy": 0.2380664974451065,
|
|
"num_tokens": 67698815.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 4.9049585342407225,
|
|
"epoch": 2.885646217986897,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041841514425199175,
|
|
"loss": 4.5707,
|
|
"mean_token_accuracy": 0.2309893399477005,
|
|
"num_tokens": 67711654.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 4.860721683502197,
|
|
"epoch": 2.8862418106015486,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041838230725947683,
|
|
"loss": 4.5406,
|
|
"mean_token_accuracy": 0.22757659405469893,
|
|
"num_tokens": 67726381.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 4.882350158691406,
|
|
"epoch": 2.8868374032162,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041834946512407173,
|
|
"loss": 4.5207,
|
|
"mean_token_accuracy": 0.23783060759305955,
|
|
"num_tokens": 67740197.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 4.845598888397217,
|
|
"epoch": 2.8874329958308516,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004183166178469543,
|
|
"loss": 4.5281,
|
|
"mean_token_accuracy": 0.22888310849666596,
|
|
"num_tokens": 67753960.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 4.8524974346160885,
|
|
"epoch": 2.8880285884455033,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004182837654293029,
|
|
"loss": 4.5216,
|
|
"mean_token_accuracy": 0.23397497236728668,
|
|
"num_tokens": 67768199.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 4.80580153465271,
|
|
"epoch": 2.888624181060155,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041825090787229574,
|
|
"loss": 4.5216,
|
|
"mean_token_accuracy": 0.23432277888059616,
|
|
"num_tokens": 67782518.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 4.809674501419067,
|
|
"epoch": 2.8892197736748066,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004182180451771115,
|
|
"loss": 4.5244,
|
|
"mean_token_accuracy": 0.23061108589172363,
|
|
"num_tokens": 67797858.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 4.834082412719726,
|
|
"epoch": 2.889815366289458,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041818517734492874,
|
|
"loss": 4.5011,
|
|
"mean_token_accuracy": 0.2325191780924797,
|
|
"num_tokens": 67811476.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 4.804698801040649,
|
|
"epoch": 2.8904109589041096,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041815230437692647,
|
|
"loss": 4.5188,
|
|
"mean_token_accuracy": 0.2359963208436966,
|
|
"num_tokens": 67824423.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 4.902306938171387,
|
|
"epoch": 2.8910065515187613,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004181194262742839,
|
|
"loss": 4.52,
|
|
"mean_token_accuracy": 0.23464272618293763,
|
|
"num_tokens": 67837958.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 4.869163274765015,
|
|
"epoch": 2.8916021441334125,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00041808654303818004,
|
|
"loss": 4.5485,
|
|
"mean_token_accuracy": 0.22740192264318465,
|
|
"num_tokens": 67853358.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 4.800021982192993,
|
|
"epoch": 2.8921977367480642,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004180536546697947,
|
|
"loss": 4.4629,
|
|
"mean_token_accuracy": 0.23920533061027527,
|
|
"num_tokens": 67866736.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 4.855188179016113,
|
|
"epoch": 2.892793329362716,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004180207611703073,
|
|
"loss": 4.5338,
|
|
"mean_token_accuracy": 0.2339545875787735,
|
|
"num_tokens": 67879778.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 4.7992840766906735,
|
|
"epoch": 2.8933889219773676,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041798786254089774,
|
|
"loss": 4.4271,
|
|
"mean_token_accuracy": 0.24522390812635422,
|
|
"num_tokens": 67893451.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 4.826423168182373,
|
|
"epoch": 2.8939845145920193,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041795495878274596,
|
|
"loss": 4.5421,
|
|
"mean_token_accuracy": 0.2315526485443115,
|
|
"num_tokens": 67905806.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 4.816096210479737,
|
|
"epoch": 2.8945801072066706,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004179220498970323,
|
|
"loss": 4.5055,
|
|
"mean_token_accuracy": 0.23787413835525512,
|
|
"num_tokens": 67919451.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 4.7787384510040285,
|
|
"epoch": 2.8951756998213223,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041788913588493716,
|
|
"loss": 4.4568,
|
|
"mean_token_accuracy": 0.2422750249505043,
|
|
"num_tokens": 67932985.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 4.816202402114868,
|
|
"epoch": 2.895771292435974,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004178562167476409,
|
|
"loss": 4.5299,
|
|
"mean_token_accuracy": 0.23776986449956894,
|
|
"num_tokens": 67945112.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 4.889164733886719,
|
|
"epoch": 2.8963668850506252,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004178232924863245,
|
|
"loss": 4.5915,
|
|
"mean_token_accuracy": 0.22536783367395402,
|
|
"num_tokens": 67957219.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 4.775556325912476,
|
|
"epoch": 2.896962477665277,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004177903631021688,
|
|
"loss": 4.4748,
|
|
"mean_token_accuracy": 0.23766252398490906,
|
|
"num_tokens": 67970944.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 4.847828722000122,
|
|
"epoch": 2.8975580702799286,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004177574285963549,
|
|
"loss": 4.5249,
|
|
"mean_token_accuracy": 0.22837735563516617,
|
|
"num_tokens": 67985074.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 4.8621293067932125,
|
|
"epoch": 2.89815366289458,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004177244889700642,
|
|
"loss": 4.5472,
|
|
"mean_token_accuracy": 0.2286491647362709,
|
|
"num_tokens": 67999862.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 4.825832796096802,
|
|
"epoch": 2.8987492555092316,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041769154422447813,
|
|
"loss": 4.4586,
|
|
"mean_token_accuracy": 0.2355660542845726,
|
|
"num_tokens": 68013700.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 4.846692514419556,
|
|
"epoch": 2.8993448481238833,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00041765859436077837,
|
|
"loss": 4.5394,
|
|
"mean_token_accuracy": 0.23098389208316802,
|
|
"num_tokens": 68028763.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 4.7769862651824955,
|
|
"epoch": 2.899940440738535,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00041762563938014673,
|
|
"loss": 4.3956,
|
|
"mean_token_accuracy": 0.2444335326552391,
|
|
"num_tokens": 68043695.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 4.870639657974243,
|
|
"epoch": 2.9005360333531867,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004175926792837653,
|
|
"loss": 4.5621,
|
|
"mean_token_accuracy": 0.2275771304965019,
|
|
"num_tokens": 68058743.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 4.7746583938598635,
|
|
"epoch": 2.901131625967838,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004175597140728164,
|
|
"loss": 4.4532,
|
|
"mean_token_accuracy": 0.2353396385908127,
|
|
"num_tokens": 68071029.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 4.779859113693237,
|
|
"epoch": 2.9017272185824896,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004175267437484823,
|
|
"loss": 4.4198,
|
|
"mean_token_accuracy": 0.23837621957063676,
|
|
"num_tokens": 68084570.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 4.85645489692688,
|
|
"epoch": 2.9023228111971413,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041749376831194565,
|
|
"loss": 4.5221,
|
|
"mean_token_accuracy": 0.23025240749120712,
|
|
"num_tokens": 68099203.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 4.880566692352295,
|
|
"epoch": 2.9029184038117926,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004174607877643892,
|
|
"loss": 4.6247,
|
|
"mean_token_accuracy": 0.22461950927972793,
|
|
"num_tokens": 68112441.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 4.886443471908569,
|
|
"epoch": 2.9035139964264443,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041742780210699584,
|
|
"loss": 4.6273,
|
|
"mean_token_accuracy": 0.2322691112756729,
|
|
"num_tokens": 68125174.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 4.86095962524414,
|
|
"epoch": 2.904109589041096,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004173948113409488,
|
|
"loss": 4.543,
|
|
"mean_token_accuracy": 0.2374851644039154,
|
|
"num_tokens": 68139868.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 4.828119707107544,
|
|
"epoch": 2.904705181655747,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004173618154674316,
|
|
"loss": 4.4635,
|
|
"mean_token_accuracy": 0.2348186194896698,
|
|
"num_tokens": 68152913.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 4.846761226654053,
|
|
"epoch": 2.905300774270399,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004173288144876273,
|
|
"loss": 4.5517,
|
|
"mean_token_accuracy": 0.2361970990896225,
|
|
"num_tokens": 68165783.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 4.8857933521270756,
|
|
"epoch": 2.9058963668850506,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004172958084027199,
|
|
"loss": 4.5536,
|
|
"mean_token_accuracy": 0.22929247617721557,
|
|
"num_tokens": 68179967.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 4.876200771331787,
|
|
"epoch": 2.9064919594997023,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004172627972138933,
|
|
"loss": 4.5602,
|
|
"mean_token_accuracy": 0.23023727983236314,
|
|
"num_tokens": 68193799.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 4.8481080532073975,
|
|
"epoch": 2.907087552114354,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041722978092233144,
|
|
"loss": 4.5536,
|
|
"mean_token_accuracy": 0.2274211600422859,
|
|
"num_tokens": 68208933.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 4.807986545562744,
|
|
"epoch": 2.9076831447290052,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041719675952921854,
|
|
"loss": 4.4278,
|
|
"mean_token_accuracy": 0.24473134577274322,
|
|
"num_tokens": 68221732.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 4.828852033615112,
|
|
"epoch": 2.908278737343657,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004171637330357391,
|
|
"loss": 4.5257,
|
|
"mean_token_accuracy": 0.23534891605377198,
|
|
"num_tokens": 68235784.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 4.825180530548096,
|
|
"epoch": 2.9088743299583086,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004171307014430777,
|
|
"loss": 4.4706,
|
|
"mean_token_accuracy": 0.24653336256742478,
|
|
"num_tokens": 68249123.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 4.821222162246704,
|
|
"epoch": 2.90946992257296,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004170976647524192,
|
|
"loss": 4.4441,
|
|
"mean_token_accuracy": 0.24262534081935883,
|
|
"num_tokens": 68261926.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 4.819479656219483,
|
|
"epoch": 2.9100655151876116,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004170646229649484,
|
|
"loss": 4.5316,
|
|
"mean_token_accuracy": 0.23290071040391921,
|
|
"num_tokens": 68275466.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 4.819338178634643,
|
|
"epoch": 2.9106611078022633,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041703157608185057,
|
|
"loss": 4.4557,
|
|
"mean_token_accuracy": 0.24431307017803192,
|
|
"num_tokens": 68290050.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 4.809466028213501,
|
|
"epoch": 2.911256700416915,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000416998524104311,
|
|
"loss": 4.492,
|
|
"mean_token_accuracy": 0.23202220648527144,
|
|
"num_tokens": 68302996.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 4.771133661270142,
|
|
"epoch": 2.9118522930315667,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041696546703351537,
|
|
"loss": 4.4628,
|
|
"mean_token_accuracy": 0.24311632066965103,
|
|
"num_tokens": 68316790.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 4.794195079803467,
|
|
"epoch": 2.912447885646218,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00041693240487064917,
|
|
"loss": 4.4509,
|
|
"mean_token_accuracy": 0.2422123670578003,
|
|
"num_tokens": 68332168.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 4.82102518081665,
|
|
"epoch": 2.9130434782608696,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004168993376168984,
|
|
"loss": 4.4638,
|
|
"mean_token_accuracy": 0.2374982550740242,
|
|
"num_tokens": 68347279.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 4.799539089202881,
|
|
"epoch": 2.9136390708755213,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041686626527344904,
|
|
"loss": 4.4796,
|
|
"mean_token_accuracy": 0.23260839581489562,
|
|
"num_tokens": 68361665.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 4.874814081192016,
|
|
"epoch": 2.9142346634901726,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004168331878414875,
|
|
"loss": 4.5686,
|
|
"mean_token_accuracy": 0.22216822803020478,
|
|
"num_tokens": 68376274.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 4.882202291488648,
|
|
"epoch": 2.9148302561048243,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041680010532220007,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.23347126692533493,
|
|
"num_tokens": 68390793.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 4.850833940505981,
|
|
"epoch": 2.915425848719476,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041676701771677343,
|
|
"loss": 4.4904,
|
|
"mean_token_accuracy": 0.2363382875919342,
|
|
"num_tokens": 68404292.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 4.824847888946533,
|
|
"epoch": 2.916021441334127,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004167339250263943,
|
|
"loss": 4.5401,
|
|
"mean_token_accuracy": 0.23146505802869796,
|
|
"num_tokens": 68419268.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 4.775926733016968,
|
|
"epoch": 2.916617033948779,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004167008272522498,
|
|
"loss": 4.3746,
|
|
"mean_token_accuracy": 0.25325453877449033,
|
|
"num_tokens": 68431665.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 4.7262904167175295,
|
|
"epoch": 2.9172126265634306,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041666772439552703,
|
|
"loss": 4.4924,
|
|
"mean_token_accuracy": 0.23196500837802886,
|
|
"num_tokens": 68445638.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 4.840198040008545,
|
|
"epoch": 2.9178082191780823,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041663461645741336,
|
|
"loss": 4.4973,
|
|
"mean_token_accuracy": 0.23518285900354385,
|
|
"num_tokens": 68458926.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 4.91311559677124,
|
|
"epoch": 2.918403811792734,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041660150343909613,
|
|
"loss": 4.4708,
|
|
"mean_token_accuracy": 0.24028924256563186,
|
|
"num_tokens": 68471215.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 4.797597217559814,
|
|
"epoch": 2.9189994044073853,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041656838534176335,
|
|
"loss": 4.5031,
|
|
"mean_token_accuracy": 0.23514700829982757,
|
|
"num_tokens": 68485940.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 4.859839963912964,
|
|
"epoch": 2.919594997022037,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004165352621666027,
|
|
"loss": 4.6098,
|
|
"mean_token_accuracy": 0.22496084421873092,
|
|
"num_tokens": 68500753.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 4.87523832321167,
|
|
"epoch": 2.9201905896366886,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004165021339148023,
|
|
"loss": 4.5691,
|
|
"mean_token_accuracy": 0.22894095331430436,
|
|
"num_tokens": 68515421.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 4.801388263702393,
|
|
"epoch": 2.92078618225134,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041646900058755045,
|
|
"loss": 4.5305,
|
|
"mean_token_accuracy": 0.22427681535482408,
|
|
"num_tokens": 68529898.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 4.828500890731812,
|
|
"epoch": 2.9213817748659916,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041643586218603556,
|
|
"loss": 4.4579,
|
|
"mean_token_accuracy": 0.2418623223900795,
|
|
"num_tokens": 68544080.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 4.8648984909057615,
|
|
"epoch": 2.9219773674806433,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004164027187114463,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.23242780566215515,
|
|
"num_tokens": 68557879.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 4.909593391418457,
|
|
"epoch": 2.9225729600952945,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004163695701649713,
|
|
"loss": 4.5297,
|
|
"mean_token_accuracy": 0.23462325781583787,
|
|
"num_tokens": 68571963.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 4.903419160842896,
|
|
"epoch": 2.9231685527099462,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004163364165477998,
|
|
"loss": 4.6147,
|
|
"mean_token_accuracy": 0.22849745452404022,
|
|
"num_tokens": 68586082.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 4.778421115875244,
|
|
"epoch": 2.923764145324598,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004163032578611208,
|
|
"loss": 4.4691,
|
|
"mean_token_accuracy": 0.24203493893146516,
|
|
"num_tokens": 68600074.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 4.815400314331055,
|
|
"epoch": 2.9243597379392496,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041627009410612366,
|
|
"loss": 4.4777,
|
|
"mean_token_accuracy": 0.23290377706289292,
|
|
"num_tokens": 68613548.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 4.884516000747681,
|
|
"epoch": 2.9249553305539013,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004162369252839979,
|
|
"loss": 4.5301,
|
|
"mean_token_accuracy": 0.229670187830925,
|
|
"num_tokens": 68627602.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 4.759687709808349,
|
|
"epoch": 2.9255509231685526,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041620375139593335,
|
|
"loss": 4.338,
|
|
"mean_token_accuracy": 0.2487313523888588,
|
|
"num_tokens": 68640660.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 4.788122653961182,
|
|
"epoch": 2.9261465157832043,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004161705724431198,
|
|
"loss": 4.4853,
|
|
"mean_token_accuracy": 0.23956995606422424,
|
|
"num_tokens": 68654312.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 4.835938405990601,
|
|
"epoch": 2.926742108397856,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004161373884267473,
|
|
"loss": 4.4949,
|
|
"mean_token_accuracy": 0.23690484166145326,
|
|
"num_tokens": 68667524.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 4.823982000350952,
|
|
"epoch": 2.9273377010125072,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041610419934800624,
|
|
"loss": 4.4515,
|
|
"mean_token_accuracy": 0.24146812558174133,
|
|
"num_tokens": 68682699.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 4.835312128067017,
|
|
"epoch": 2.927933293627159,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004160710052080869,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.2285111203789711,
|
|
"num_tokens": 68698499.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 4.831078672409058,
|
|
"epoch": 2.9285288862418106,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041603780600818,
|
|
"loss": 4.5074,
|
|
"mean_token_accuracy": 0.23392837792634963,
|
|
"num_tokens": 68713068.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 4.8480916023254395,
|
|
"epoch": 2.9291244788564623,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004160046017494763,
|
|
"loss": 4.4467,
|
|
"mean_token_accuracy": 0.23538999855518342,
|
|
"num_tokens": 68727728.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 4.850634813308716,
|
|
"epoch": 2.929720071471114,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004159713924331668,
|
|
"loss": 4.51,
|
|
"mean_token_accuracy": 0.23306832313537598,
|
|
"num_tokens": 68740906.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 4.892363500595093,
|
|
"epoch": 2.9303156640857653,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041593817806044267,
|
|
"loss": 4.5903,
|
|
"mean_token_accuracy": 0.2263149216771126,
|
|
"num_tokens": 68755003.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 4.880429077148437,
|
|
"epoch": 2.930911256700417,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004159049586324952,
|
|
"loss": 4.5876,
|
|
"mean_token_accuracy": 0.22398093044757844,
|
|
"num_tokens": 68768742.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 4.8801182270050045,
|
|
"epoch": 2.9315068493150687,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000415871734150516,
|
|
"loss": 4.6066,
|
|
"mean_token_accuracy": 0.22668918073177338,
|
|
"num_tokens": 68784637.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 4.960015869140625,
|
|
"epoch": 2.93210244192972,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041583850461569675,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.2259963035583496,
|
|
"num_tokens": 68798443.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 4.9031867504119875,
|
|
"epoch": 2.9326980345443716,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004158052700292292,
|
|
"loss": 4.5364,
|
|
"mean_token_accuracy": 0.2343381628394127,
|
|
"num_tokens": 68811346.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 4.818737745285034,
|
|
"epoch": 2.9332936271590233,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00041577203039230577,
|
|
"loss": 4.4906,
|
|
"mean_token_accuracy": 0.24018259346485138,
|
|
"num_tokens": 68825615.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 4.817808818817139,
|
|
"epoch": 2.9338892197736746,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041573878570611835,
|
|
"loss": 4.4887,
|
|
"mean_token_accuracy": 0.23599823564291,
|
|
"num_tokens": 68840308.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 4.846822357177734,
|
|
"epoch": 2.9344848123883263,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004157055359718595,
|
|
"loss": 4.5782,
|
|
"mean_token_accuracy": 0.22338782399892806,
|
|
"num_tokens": 68854813.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 4.847071361541748,
|
|
"epoch": 2.935080405002978,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004156722811907219,
|
|
"loss": 4.5313,
|
|
"mean_token_accuracy": 0.23033021986484528,
|
|
"num_tokens": 68867887.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 4.874335145950317,
|
|
"epoch": 2.9356759976176297,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004156390213638983,
|
|
"loss": 4.5551,
|
|
"mean_token_accuracy": 0.22827084362506866,
|
|
"num_tokens": 68882577.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 4.82370285987854,
|
|
"epoch": 2.9362715902322813,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004156057564925816,
|
|
"loss": 4.4712,
|
|
"mean_token_accuracy": 0.23879424333572388,
|
|
"num_tokens": 68895774.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 4.851047325134277,
|
|
"epoch": 2.9368671828469326,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004155724865779652,
|
|
"loss": 4.5481,
|
|
"mean_token_accuracy": 0.22949280291795732,
|
|
"num_tokens": 68910033.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 4.806350469589233,
|
|
"epoch": 2.9374627754615843,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004155392116212421,
|
|
"loss": 4.3827,
|
|
"mean_token_accuracy": 0.24457466900348662,
|
|
"num_tokens": 68923599.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 4.766282320022583,
|
|
"epoch": 2.938058368076236,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000415505931623606,
|
|
"loss": 4.4372,
|
|
"mean_token_accuracy": 0.233026222884655,
|
|
"num_tokens": 68937947.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 4.813489055633545,
|
|
"epoch": 2.9386539606908872,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004154726465862506,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.2346588760614395,
|
|
"num_tokens": 68950890.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 4.845812797546387,
|
|
"epoch": 2.939249553305539,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041543935651036976,
|
|
"loss": 4.4256,
|
|
"mean_token_accuracy": 0.24037512838840486,
|
|
"num_tokens": 68964847.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 4.788222408294677,
|
|
"epoch": 2.9398451459201906,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004154060613971576,
|
|
"loss": 4.4369,
|
|
"mean_token_accuracy": 0.23772450238466264,
|
|
"num_tokens": 68978663.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 4.736610269546508,
|
|
"epoch": 2.940440738534842,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004153727612478083,
|
|
"loss": 4.5088,
|
|
"mean_token_accuracy": 0.22892568707466127,
|
|
"num_tokens": 68993141.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 4.828286838531494,
|
|
"epoch": 2.9410363311494936,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004153394560635162,
|
|
"loss": 4.4684,
|
|
"mean_token_accuracy": 0.23974721878767014,
|
|
"num_tokens": 69006960.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 4.837610197067261,
|
|
"epoch": 2.9416319237641453,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00041530614584547594,
|
|
"loss": 4.4721,
|
|
"mean_token_accuracy": 0.2411205440759659,
|
|
"num_tokens": 69020436.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 4.858934450149536,
|
|
"epoch": 2.942227516378797,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004152728305948825,
|
|
"loss": 4.5099,
|
|
"mean_token_accuracy": 0.23395439684391023,
|
|
"num_tokens": 69033648.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 4.819294452667236,
|
|
"epoch": 2.9428231089934487,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004152395103129306,
|
|
"loss": 4.5425,
|
|
"mean_token_accuracy": 0.22813017815351486,
|
|
"num_tokens": 69048555.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 4.858447647094726,
|
|
"epoch": 2.9434187016081,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041520618500081555,
|
|
"loss": 4.5022,
|
|
"mean_token_accuracy": 0.23323518484830857,
|
|
"num_tokens": 69062100.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 4.869324254989624,
|
|
"epoch": 2.9440142942227516,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041517285465973253,
|
|
"loss": 4.5427,
|
|
"mean_token_accuracy": 0.2251915991306305,
|
|
"num_tokens": 69076131.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 4.782312965393066,
|
|
"epoch": 2.9446098868374033,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041513951929087725,
|
|
"loss": 4.4008,
|
|
"mean_token_accuracy": 0.24081622511148454,
|
|
"num_tokens": 69090584.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 4.906894207000732,
|
|
"epoch": 2.9452054794520546,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041510617889544516,
|
|
"loss": 4.6342,
|
|
"mean_token_accuracy": 0.22551233619451522,
|
|
"num_tokens": 69104001.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 4.808641004562378,
|
|
"epoch": 2.9458010720667063,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004150728334746322,
|
|
"loss": 4.5652,
|
|
"mean_token_accuracy": 0.226033578813076,
|
|
"num_tokens": 69121277.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 4.929062080383301,
|
|
"epoch": 2.946396664681358,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041503948302963454,
|
|
"loss": 4.5257,
|
|
"mean_token_accuracy": 0.2368115171790123,
|
|
"num_tokens": 69134802.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 4.831677007675171,
|
|
"epoch": 2.9469922572960097,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041500612756164825,
|
|
"loss": 4.4888,
|
|
"mean_token_accuracy": 0.2291857495903969,
|
|
"num_tokens": 69149133.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 4.874396848678589,
|
|
"epoch": 2.9475878499106614,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00041497276707186983,
|
|
"loss": 4.6432,
|
|
"mean_token_accuracy": 0.22329994142055512,
|
|
"num_tokens": 69163784.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 4.785425853729248,
|
|
"epoch": 2.9481834425253126,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041493940156149577,
|
|
"loss": 4.4351,
|
|
"mean_token_accuracy": 0.23695971220731735,
|
|
"num_tokens": 69177037.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 4.850401401519775,
|
|
"epoch": 2.9487790351399643,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041490603103172297,
|
|
"loss": 4.4734,
|
|
"mean_token_accuracy": 0.24550418853759765,
|
|
"num_tokens": 69189071.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 4.782972717285157,
|
|
"epoch": 2.949374627754616,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004148726554837484,
|
|
"loss": 4.4417,
|
|
"mean_token_accuracy": 0.24016278833150864,
|
|
"num_tokens": 69201998.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 4.823563909530639,
|
|
"epoch": 2.9499702203692673,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041483927491876887,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.24116317480802535,
|
|
"num_tokens": 69215349.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 4.787572574615479,
|
|
"epoch": 2.950565812983919,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004148058893379821,
|
|
"loss": 4.4586,
|
|
"mean_token_accuracy": 0.23724592477083206,
|
|
"num_tokens": 69228244.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 4.792619705200195,
|
|
"epoch": 2.9511614055985707,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004147724987425853,
|
|
"loss": 4.4619,
|
|
"mean_token_accuracy": 0.23700861036777496,
|
|
"num_tokens": 69242988.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 4.8526177406311035,
|
|
"epoch": 2.951756998213222,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041473910313377633,
|
|
"loss": 4.4737,
|
|
"mean_token_accuracy": 0.23968181759119034,
|
|
"num_tokens": 69257722.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 4.897926330566406,
|
|
"epoch": 2.9523525908278736,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00041470570251275285,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.22451627105474473,
|
|
"num_tokens": 69272177.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 4.788710117340088,
|
|
"epoch": 2.9529481834425253,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041467229688071293,
|
|
"loss": 4.4834,
|
|
"mean_token_accuracy": 0.23549754321575164,
|
|
"num_tokens": 69285316.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 4.829472875595092,
|
|
"epoch": 2.953543776057177,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004146388862388549,
|
|
"loss": 4.4708,
|
|
"mean_token_accuracy": 0.24025102257728576,
|
|
"num_tokens": 69299502.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 4.886899089813232,
|
|
"epoch": 2.9541393686718287,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00041460547058837704,
|
|
"loss": 4.5491,
|
|
"mean_token_accuracy": 0.2248254582285881,
|
|
"num_tokens": 69313280.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 4.808387374877929,
|
|
"epoch": 2.95473496128648,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000414572049930478,
|
|
"loss": 4.4776,
|
|
"mean_token_accuracy": 0.23215390145778655,
|
|
"num_tokens": 69326066.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 4.856454086303711,
|
|
"epoch": 2.9553305539011316,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004145386242663563,
|
|
"loss": 4.6076,
|
|
"mean_token_accuracy": 0.23544327467679976,
|
|
"num_tokens": 69340030.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 4.877646780014038,
|
|
"epoch": 2.9559261465157833,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004145051935972111,
|
|
"loss": 4.4842,
|
|
"mean_token_accuracy": 0.2381315529346466,
|
|
"num_tokens": 69355601.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 4.86333966255188,
|
|
"epoch": 2.9565217391304346,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004144717579242414,
|
|
"loss": 4.5322,
|
|
"mean_token_accuracy": 0.22988025099039078,
|
|
"num_tokens": 69369205.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 4.787203359603882,
|
|
"epoch": 2.9571173317450863,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041443831724864656,
|
|
"loss": 4.4024,
|
|
"mean_token_accuracy": 0.24366632401943206,
|
|
"num_tokens": 69383477.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 4.843183326721191,
|
|
"epoch": 2.957712924359738,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041440487157162596,
|
|
"loss": 4.4833,
|
|
"mean_token_accuracy": 0.23530059009790422,
|
|
"num_tokens": 69397175.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 4.8768829822540285,
|
|
"epoch": 2.9583085169743897,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041437142089437927,
|
|
"loss": 4.5518,
|
|
"mean_token_accuracy": 0.23166094720363617,
|
|
"num_tokens": 69410109.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 4.790883779525757,
|
|
"epoch": 2.958904109589041,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004143379652181064,
|
|
"loss": 4.3918,
|
|
"mean_token_accuracy": 0.24559284150600433,
|
|
"num_tokens": 69424552.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 4.775340795516968,
|
|
"epoch": 2.9594997022036926,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041430450454400716,
|
|
"loss": 4.4478,
|
|
"mean_token_accuracy": 0.23797740042209625,
|
|
"num_tokens": 69439312.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 4.884329080581665,
|
|
"epoch": 2.9600952948183443,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004142710388732819,
|
|
"loss": 4.5695,
|
|
"mean_token_accuracy": 0.2299856424331665,
|
|
"num_tokens": 69452207.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 4.88551173210144,
|
|
"epoch": 2.960690887432996,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004142375682071309,
|
|
"loss": 4.5699,
|
|
"mean_token_accuracy": 0.2321224793791771,
|
|
"num_tokens": 69468004.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 4.841141986846924,
|
|
"epoch": 2.9612864800476473,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041420409254675465,
|
|
"loss": 4.5517,
|
|
"mean_token_accuracy": 0.23455004543066024,
|
|
"num_tokens": 69481649.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 4.865327405929565,
|
|
"epoch": 2.961882072662299,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000414170611893354,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.22579987943172455,
|
|
"num_tokens": 69495861.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 4.796579074859619,
|
|
"epoch": 2.9624776652769507,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004141371262481298,
|
|
"loss": 4.4862,
|
|
"mean_token_accuracy": 0.2390761598944664,
|
|
"num_tokens": 69509924.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 4.856772422790527,
|
|
"epoch": 2.963073257891602,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041410363561228316,
|
|
"loss": 4.5576,
|
|
"mean_token_accuracy": 0.22576652467250824,
|
|
"num_tokens": 69523020.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 4.8092855453491214,
|
|
"epoch": 2.9636688505062536,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004140701399870151,
|
|
"loss": 4.5116,
|
|
"mean_token_accuracy": 0.23607417643070222,
|
|
"num_tokens": 69536916.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 4.833775854110717,
|
|
"epoch": 2.9642644431209053,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004140366393735274,
|
|
"loss": 4.5302,
|
|
"mean_token_accuracy": 0.22716784924268724,
|
|
"num_tokens": 69549856.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 4.883171653747558,
|
|
"epoch": 2.964860035735557,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00041400313377302144,
|
|
"loss": 4.5328,
|
|
"mean_token_accuracy": 0.2324698120355606,
|
|
"num_tokens": 69567705.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 4.852353048324585,
|
|
"epoch": 2.9654556283502087,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000413969623186699,
|
|
"loss": 4.4874,
|
|
"mean_token_accuracy": 0.23155560344457626,
|
|
"num_tokens": 69582641.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 4.791726112365723,
|
|
"epoch": 2.96605122096486,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004139361076157622,
|
|
"loss": 4.4598,
|
|
"mean_token_accuracy": 0.23827913999557496,
|
|
"num_tokens": 69595276.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 4.737630939483642,
|
|
"epoch": 2.9666468135795117,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004139025870614131,
|
|
"loss": 4.4439,
|
|
"mean_token_accuracy": 0.23491545021533966,
|
|
"num_tokens": 69608796.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 4.886874389648438,
|
|
"epoch": 2.9672424061941634,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004138690615248541,
|
|
"loss": 4.5727,
|
|
"mean_token_accuracy": 0.23621893674135208,
|
|
"num_tokens": 69622987.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 4.8491496562957765,
|
|
"epoch": 2.9678379988088146,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004138355310072876,
|
|
"loss": 4.5513,
|
|
"mean_token_accuracy": 0.229622919857502,
|
|
"num_tokens": 69637085.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 4.775899362564087,
|
|
"epoch": 2.9684335914234663,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041380199550991635,
|
|
"loss": 4.4604,
|
|
"mean_token_accuracy": 0.23896916657686235,
|
|
"num_tokens": 69651617.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 4.893924903869629,
|
|
"epoch": 2.969029184038118,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004137684550339432,
|
|
"loss": 4.5418,
|
|
"mean_token_accuracy": 0.22984241396188737,
|
|
"num_tokens": 69665879.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 4.865398311614991,
|
|
"epoch": 2.9696247766527692,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004137349095805712,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.22403473556041717,
|
|
"num_tokens": 69679065.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 4.883843231201172,
|
|
"epoch": 2.970220369267421,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004137013591510035,
|
|
"loss": 4.548,
|
|
"mean_token_accuracy": 0.2259882941842079,
|
|
"num_tokens": 69693955.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 4.799565935134888,
|
|
"epoch": 2.9708159618820726,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004136678037464437,
|
|
"loss": 4.4565,
|
|
"mean_token_accuracy": 0.23745371103286744,
|
|
"num_tokens": 69707452.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 4.849902629852295,
|
|
"epoch": 2.9714115544967243,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004136342433680951,
|
|
"loss": 4.6003,
|
|
"mean_token_accuracy": 0.22947757691144943,
|
|
"num_tokens": 69720968.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 4.8139880180358885,
|
|
"epoch": 2.972007147111376,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041360067801716165,
|
|
"loss": 4.4294,
|
|
"mean_token_accuracy": 0.24020012319087983,
|
|
"num_tokens": 69735568.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 4.880717802047729,
|
|
"epoch": 2.9726027397260273,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004135671076948472,
|
|
"loss": 4.6199,
|
|
"mean_token_accuracy": 0.22825566977262496,
|
|
"num_tokens": 69748995.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 4.788748168945313,
|
|
"epoch": 2.973198332340679,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004135335324023559,
|
|
"loss": 4.4096,
|
|
"mean_token_accuracy": 0.23781850188970566,
|
|
"num_tokens": 69760681.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 4.759176445007324,
|
|
"epoch": 2.9737939249553307,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041349995214089207,
|
|
"loss": 4.4225,
|
|
"mean_token_accuracy": 0.2489885538816452,
|
|
"num_tokens": 69774882.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 4.882039499282837,
|
|
"epoch": 2.974389517569982,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041346636691166015,
|
|
"loss": 4.5695,
|
|
"mean_token_accuracy": 0.22684379518032075,
|
|
"num_tokens": 69792133.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 4.807122325897216,
|
|
"epoch": 2.9749851101846336,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004134327767158648,
|
|
"loss": 4.4231,
|
|
"mean_token_accuracy": 0.23995033651590347,
|
|
"num_tokens": 69807032.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 4.82916522026062,
|
|
"epoch": 2.9755807027992853,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004133991815547108,
|
|
"loss": 4.5467,
|
|
"mean_token_accuracy": 0.2350162923336029,
|
|
"num_tokens": 69822831.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 4.777182769775391,
|
|
"epoch": 2.976176295413937,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004133655814294031,
|
|
"loss": 4.4784,
|
|
"mean_token_accuracy": 0.2392943724989891,
|
|
"num_tokens": 69836904.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 4.791684770584107,
|
|
"epoch": 2.9767718880285887,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000413331976341147,
|
|
"loss": 4.438,
|
|
"mean_token_accuracy": 0.2385969802737236,
|
|
"num_tokens": 69852390.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 4.840482997894287,
|
|
"epoch": 2.97736748064324,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041329836629114784,
|
|
"loss": 4.5613,
|
|
"mean_token_accuracy": 0.23246952146291733,
|
|
"num_tokens": 69866267.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 4.771208906173706,
|
|
"epoch": 2.9779630732578917,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004132647512806112,
|
|
"loss": 4.3789,
|
|
"mean_token_accuracy": 0.24196714758872986,
|
|
"num_tokens": 69879264.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 4.776733160018921,
|
|
"epoch": 2.9785586658725434,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004132311313107427,
|
|
"loss": 4.469,
|
|
"mean_token_accuracy": 0.23704368472099305,
|
|
"num_tokens": 69894425.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 4.766748523712158,
|
|
"epoch": 2.9791542584871946,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004131975063827482,
|
|
"loss": 4.4624,
|
|
"mean_token_accuracy": 0.24284646958112716,
|
|
"num_tokens": 69908758.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 4.819109869003296,
|
|
"epoch": 2.9797498511018463,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000413163876497834,
|
|
"loss": 4.4172,
|
|
"mean_token_accuracy": 0.24733535200357437,
|
|
"num_tokens": 69921773.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 4.861061239242554,
|
|
"epoch": 2.980345443716498,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000413130241657206,
|
|
"loss": 4.5505,
|
|
"mean_token_accuracy": 0.2279018685221672,
|
|
"num_tokens": 69934271.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 4.850043106079101,
|
|
"epoch": 2.9809410363311493,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041309660186207093,
|
|
"loss": 4.429,
|
|
"mean_token_accuracy": 0.24196344316005708,
|
|
"num_tokens": 69947809.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 4.807235622406006,
|
|
"epoch": 2.981536628945801,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00041306295711363526,
|
|
"loss": 4.4223,
|
|
"mean_token_accuracy": 0.23665348440408707,
|
|
"num_tokens": 69964136.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 4.785707092285156,
|
|
"epoch": 2.9821322215604527,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00041302930741310585,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.23160127103328704,
|
|
"num_tokens": 69976461.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 4.809480619430542,
|
|
"epoch": 2.9827278141751044,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004129956527616895,
|
|
"loss": 4.4557,
|
|
"mean_token_accuracy": 0.23975914418697358,
|
|
"num_tokens": 69990641.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 4.899850654602051,
|
|
"epoch": 2.983323406789756,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004129619931605935,
|
|
"loss": 4.6095,
|
|
"mean_token_accuracy": 0.22478772848844528,
|
|
"num_tokens": 70003023.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 4.700350570678711,
|
|
"epoch": 2.9839189994044073,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004129283286110251,
|
|
"loss": 4.3212,
|
|
"mean_token_accuracy": 0.24409881681203843,
|
|
"num_tokens": 70015468.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 4.774437046051025,
|
|
"epoch": 2.984514592019059,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041289465911419196,
|
|
"loss": 4.4185,
|
|
"mean_token_accuracy": 0.24269053637981414,
|
|
"num_tokens": 70027601.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 4.844695806503296,
|
|
"epoch": 2.9851101846337107,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004128609846713014,
|
|
"loss": 4.5772,
|
|
"mean_token_accuracy": 0.2304072216153145,
|
|
"num_tokens": 70041589.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 4.783233118057251,
|
|
"epoch": 2.985705777248362,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004128273052835616,
|
|
"loss": 4.4704,
|
|
"mean_token_accuracy": 0.22850197851657866,
|
|
"num_tokens": 70055715.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 4.834902429580689,
|
|
"epoch": 2.9863013698630136,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004127936209521803,
|
|
"loss": 4.4623,
|
|
"mean_token_accuracy": 0.24444739520549774,
|
|
"num_tokens": 70068133.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 4.785319375991821,
|
|
"epoch": 2.9868969624776653,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000412759931678366,
|
|
"loss": 4.4206,
|
|
"mean_token_accuracy": 0.24159908294677734,
|
|
"num_tokens": 70079339.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 4.88501672744751,
|
|
"epoch": 2.9874925550923166,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00041272623746332687,
|
|
"loss": 4.5513,
|
|
"mean_token_accuracy": 0.23560509085655212,
|
|
"num_tokens": 70093633.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 4.81290340423584,
|
|
"epoch": 2.9880881477069683,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004126925383082716,
|
|
"loss": 4.5211,
|
|
"mean_token_accuracy": 0.24357089549303054,
|
|
"num_tokens": 70106781.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 4.748240852355957,
|
|
"epoch": 2.98868374032162,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041265883421440875,
|
|
"loss": 4.3864,
|
|
"mean_token_accuracy": 0.23807304352521896,
|
|
"num_tokens": 70121880.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 4.914955806732178,
|
|
"epoch": 2.9892793329362717,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041262512518294736,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.2195694699883461,
|
|
"num_tokens": 70136862.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 4.802853059768677,
|
|
"epoch": 2.9898749255509234,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041259141121509655,
|
|
"loss": 4.4184,
|
|
"mean_token_accuracy": 0.24268489331007004,
|
|
"num_tokens": 70149989.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 4.729935121536255,
|
|
"epoch": 2.9904705181655746,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004125576923120655,
|
|
"loss": 4.4806,
|
|
"mean_token_accuracy": 0.24056409746408464,
|
|
"num_tokens": 70163278.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 4.8567217826843265,
|
|
"epoch": 2.9910661107802263,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041252396847506374,
|
|
"loss": 4.5338,
|
|
"mean_token_accuracy": 0.23848389387130736,
|
|
"num_tokens": 70178353.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 4.736277866363525,
|
|
"epoch": 2.991661703394878,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041249023970530075,
|
|
"loss": 4.368,
|
|
"mean_token_accuracy": 0.2490224614739418,
|
|
"num_tokens": 70190638.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 4.829479503631592,
|
|
"epoch": 2.9922572960095293,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041245650600398644,
|
|
"loss": 4.5535,
|
|
"mean_token_accuracy": 0.23661288172006606,
|
|
"num_tokens": 70202675.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 4.793118333816528,
|
|
"epoch": 2.992852888624181,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00041242276737233073,
|
|
"loss": 4.5107,
|
|
"mean_token_accuracy": 0.23391687124967575,
|
|
"num_tokens": 70217058.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 4.902760076522827,
|
|
"epoch": 2.9934484812388327,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041238902381154376,
|
|
"loss": 4.596,
|
|
"mean_token_accuracy": 0.22809646129608155,
|
|
"num_tokens": 70231083.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 4.870930147171021,
|
|
"epoch": 2.9940440738534844,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00041235527532283603,
|
|
"loss": 4.49,
|
|
"mean_token_accuracy": 0.22763816267251968,
|
|
"num_tokens": 70245947.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 4.798997592926026,
|
|
"epoch": 2.994639666468136,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004123215219074177,
|
|
"loss": 4.4973,
|
|
"mean_token_accuracy": 0.23089563697576523,
|
|
"num_tokens": 70259434.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 4.823018884658813,
|
|
"epoch": 2.9952352590827873,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00041228776356649975,
|
|
"loss": 4.4446,
|
|
"mean_token_accuracy": 0.24194350689649582,
|
|
"num_tokens": 70274419.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 4.774506568908691,
|
|
"epoch": 2.995830851697439,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041225400030129304,
|
|
"loss": 4.4956,
|
|
"mean_token_accuracy": 0.23237972408533097,
|
|
"num_tokens": 70287949.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 4.8339009284973145,
|
|
"epoch": 2.9964264443120907,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041222023211300837,
|
|
"loss": 4.4806,
|
|
"mean_token_accuracy": 0.24667926877737045,
|
|
"num_tokens": 70300642.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 4.8754363536834715,
|
|
"epoch": 2.997022036926742,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004121864590028571,
|
|
"loss": 4.5178,
|
|
"mean_token_accuracy": 0.23258567303419114,
|
|
"num_tokens": 70314426.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 4.859145402908325,
|
|
"epoch": 2.9976176295413937,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004121526809720506,
|
|
"loss": 4.5471,
|
|
"mean_token_accuracy": 0.22570411562919618,
|
|
"num_tokens": 70329042.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 4.863343858718872,
|
|
"epoch": 2.9982132221560454,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004121188980218004,
|
|
"loss": 4.544,
|
|
"mean_token_accuracy": 0.23336784839630126,
|
|
"num_tokens": 70343194.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 4.803866624832153,
|
|
"epoch": 2.9988088147706966,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004120851101533183,
|
|
"loss": 4.4701,
|
|
"mean_token_accuracy": 0.22958189398050308,
|
|
"num_tokens": 70356953.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 4.8182155132293705,
|
|
"epoch": 2.9994044073853483,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004120513173678162,
|
|
"loss": 4.4186,
|
|
"mean_token_accuracy": 0.2390188530087471,
|
|
"num_tokens": 70369955.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 4.818303918838501,
|
|
"epoch": 3.0,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004120175196665062,
|
|
"loss": 4.5399,
|
|
"mean_token_accuracy": 0.22497672885656356,
|
|
"num_tokens": 70383036.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 4.841366863250732,
|
|
"epoch": 3.0005955926146517,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004119837170506005,
|
|
"loss": 4.4999,
|
|
"mean_token_accuracy": 0.23419786393642425,
|
|
"num_tokens": 70397478.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 4.81650743484497,
|
|
"epoch": 3.001191185229303,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004119499095213116,
|
|
"loss": 4.4416,
|
|
"mean_token_accuracy": 0.23861441016197205,
|
|
"num_tokens": 70411622.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 4.855334663391114,
|
|
"epoch": 3.0017867778439546,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041191609707985215,
|
|
"loss": 4.5016,
|
|
"mean_token_accuracy": 0.23120620101690292,
|
|
"num_tokens": 70426262.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 4.852459287643432,
|
|
"epoch": 3.0023823704586063,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041188227972743487,
|
|
"loss": 4.4495,
|
|
"mean_token_accuracy": 0.2351381540298462,
|
|
"num_tokens": 70440046.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 4.882918834686279,
|
|
"epoch": 3.002977963073258,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004118484574652728,
|
|
"loss": 4.5493,
|
|
"mean_token_accuracy": 0.22847832590341569,
|
|
"num_tokens": 70454940.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 4.909098958969116,
|
|
"epoch": 3.0035735556879093,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00041181463029457905,
|
|
"loss": 4.5122,
|
|
"mean_token_accuracy": 0.2356180340051651,
|
|
"num_tokens": 70468462.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 4.859868955612183,
|
|
"epoch": 3.004169148302561,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041178079821656695,
|
|
"loss": 4.3831,
|
|
"mean_token_accuracy": 0.2400197058916092,
|
|
"num_tokens": 70481248.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 4.80236406326294,
|
|
"epoch": 3.0047647409172127,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041174696123245,
|
|
"loss": 4.4251,
|
|
"mean_token_accuracy": 0.23770939856767653,
|
|
"num_tokens": 70496120.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 4.803331422805786,
|
|
"epoch": 3.0053603335318644,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004117131193434419,
|
|
"loss": 4.4033,
|
|
"mean_token_accuracy": 0.2427815556526184,
|
|
"num_tokens": 70509979.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 4.828064489364624,
|
|
"epoch": 3.0059559261465156,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004116792725507565,
|
|
"loss": 4.3723,
|
|
"mean_token_accuracy": 0.2401679739356041,
|
|
"num_tokens": 70523071.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 4.810996055603027,
|
|
"epoch": 3.0065515187611673,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004116454208556078,
|
|
"loss": 4.4114,
|
|
"mean_token_accuracy": 0.23805825412273407,
|
|
"num_tokens": 70538118.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 4.756220531463623,
|
|
"epoch": 3.007147111375819,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041161156425921004,
|
|
"loss": 4.3498,
|
|
"mean_token_accuracy": 0.24946207106113433,
|
|
"num_tokens": 70551938.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 4.775380373001099,
|
|
"epoch": 3.0077427039904707,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041157770276277754,
|
|
"loss": 4.3438,
|
|
"mean_token_accuracy": 0.24531604647636412,
|
|
"num_tokens": 70566043.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 4.735773611068725,
|
|
"epoch": 3.008338296605122,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041154383636752493,
|
|
"loss": 4.329,
|
|
"mean_token_accuracy": 0.25129450410604476,
|
|
"num_tokens": 70578283.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 4.786367607116699,
|
|
"epoch": 3.0089338892197737,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000411509965074667,
|
|
"loss": 4.4303,
|
|
"mean_token_accuracy": 0.24025928527116774,
|
|
"num_tokens": 70594244.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 4.826435613632202,
|
|
"epoch": 3.0095294818344254,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041147608888541853,
|
|
"loss": 4.3878,
|
|
"mean_token_accuracy": 0.23743189871311188,
|
|
"num_tokens": 70607626.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 4.757103776931762,
|
|
"epoch": 3.0101250744490766,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004114422078009946,
|
|
"loss": 4.3259,
|
|
"mean_token_accuracy": 0.2501170068979263,
|
|
"num_tokens": 70620119.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 4.799637508392334,
|
|
"epoch": 3.0107206670637283,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004114083218226105,
|
|
"loss": 4.423,
|
|
"mean_token_accuracy": 0.24170884490013123,
|
|
"num_tokens": 70635210.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 4.778325748443604,
|
|
"epoch": 3.01131625967838,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041137443095148174,
|
|
"loss": 4.3358,
|
|
"mean_token_accuracy": 0.24873890429735185,
|
|
"num_tokens": 70650122.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 4.755117607116699,
|
|
"epoch": 3.0119118522930317,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041134053518882387,
|
|
"loss": 4.3111,
|
|
"mean_token_accuracy": 0.24730786681175232,
|
|
"num_tokens": 70663639.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 4.7478844165802006,
|
|
"epoch": 3.012507444907683,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004113066345358527,
|
|
"loss": 4.3852,
|
|
"mean_token_accuracy": 0.24503017961978912,
|
|
"num_tokens": 70677211.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 4.874842309951783,
|
|
"epoch": 3.0131030375223347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041127272899378414,
|
|
"loss": 4.5198,
|
|
"mean_token_accuracy": 0.23246921002864837,
|
|
"num_tokens": 70690691.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 4.863989543914795,
|
|
"epoch": 3.0136986301369864,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041123881856383436,
|
|
"loss": 4.3976,
|
|
"mean_token_accuracy": 0.2408418670296669,
|
|
"num_tokens": 70702499.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 4.780087614059449,
|
|
"epoch": 3.014294222751638,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041120490324721967,
|
|
"loss": 4.44,
|
|
"mean_token_accuracy": 0.23476073294878005,
|
|
"num_tokens": 70716529.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 4.820752859115601,
|
|
"epoch": 3.0148898153662893,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004111709830451566,
|
|
"loss": 4.4568,
|
|
"mean_token_accuracy": 0.23564236760139465,
|
|
"num_tokens": 70728705.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 4.96622405052185,
|
|
"epoch": 3.015485407980941,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041113705795886167,
|
|
"loss": 4.6005,
|
|
"mean_token_accuracy": 0.22692212462425232,
|
|
"num_tokens": 70741379.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 4.78663911819458,
|
|
"epoch": 3.0160810005955927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041110312798955186,
|
|
"loss": 4.3867,
|
|
"mean_token_accuracy": 0.24399821013212203,
|
|
"num_tokens": 70754617.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 4.819640445709228,
|
|
"epoch": 3.0166765932102444,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041106919313844417,
|
|
"loss": 4.412,
|
|
"mean_token_accuracy": 0.24599609524011612,
|
|
"num_tokens": 70767712.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 4.890614557266235,
|
|
"epoch": 3.0172721858248956,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004110352534067557,
|
|
"loss": 4.512,
|
|
"mean_token_accuracy": 0.23993792980909348,
|
|
"num_tokens": 70781654.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 4.8791358947753904,
|
|
"epoch": 3.0178677784395473,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041100130879570394,
|
|
"loss": 4.5213,
|
|
"mean_token_accuracy": 0.23441707193851472,
|
|
"num_tokens": 70796402.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 4.732429933547974,
|
|
"epoch": 3.018463371054199,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004109673593065063,
|
|
"loss": 4.2932,
|
|
"mean_token_accuracy": 0.25611309707164764,
|
|
"num_tokens": 70811054.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 4.827420330047607,
|
|
"epoch": 3.0190589636688503,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004109334049403806,
|
|
"loss": 4.4705,
|
|
"mean_token_accuracy": 0.23375643491744996,
|
|
"num_tokens": 70824380.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 4.809354448318482,
|
|
"epoch": 3.019654556283502,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004108994456985446,
|
|
"loss": 4.425,
|
|
"mean_token_accuracy": 0.24814314395189285,
|
|
"num_tokens": 70838338.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 4.861529779434204,
|
|
"epoch": 3.0202501488981537,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004108654815822165,
|
|
"loss": 4.4198,
|
|
"mean_token_accuracy": 0.24643547981977462,
|
|
"num_tokens": 70851206.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 4.849118232727051,
|
|
"epoch": 3.0208457415128054,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004108315125926145,
|
|
"loss": 4.4504,
|
|
"mean_token_accuracy": 0.23856986314058304,
|
|
"num_tokens": 70866838.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 4.905864810943603,
|
|
"epoch": 3.0214413341274566,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000410797538730957,
|
|
"loss": 4.5002,
|
|
"mean_token_accuracy": 0.23918863981962205,
|
|
"num_tokens": 70880379.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 4.854614734649658,
|
|
"epoch": 3.0220369267421083,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00041076355999846256,
|
|
"loss": 4.4945,
|
|
"mean_token_accuracy": 0.23646360635757446,
|
|
"num_tokens": 70892528.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 4.7830949306488035,
|
|
"epoch": 3.02263251935676,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00041072957639634984,
|
|
"loss": 4.3732,
|
|
"mean_token_accuracy": 0.24521708786487578,
|
|
"num_tokens": 70906081.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 4.819280576705933,
|
|
"epoch": 3.0232281119714117,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00041069558792583804,
|
|
"loss": 4.4245,
|
|
"mean_token_accuracy": 0.2408668115735054,
|
|
"num_tokens": 70920447.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 4.793114709854126,
|
|
"epoch": 3.023823704586063,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041066159458814607,
|
|
"loss": 4.4077,
|
|
"mean_token_accuracy": 0.2421740010380745,
|
|
"num_tokens": 70933611.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 4.83515477180481,
|
|
"epoch": 3.0244192972007147,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041062759638449333,
|
|
"loss": 4.4432,
|
|
"mean_token_accuracy": 0.24179895222187042,
|
|
"num_tokens": 70949383.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 4.822231960296631,
|
|
"epoch": 3.0250148898153664,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041059359331609916,
|
|
"loss": 4.3974,
|
|
"mean_token_accuracy": 0.24418267607688904,
|
|
"num_tokens": 70963586.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 4.725216960906982,
|
|
"epoch": 3.025610482430018,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004105595853841833,
|
|
"loss": 4.2908,
|
|
"mean_token_accuracy": 0.25270096212625504,
|
|
"num_tokens": 70977289.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 4.779280710220337,
|
|
"epoch": 3.0262060750446693,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041052557258996553,
|
|
"loss": 4.3708,
|
|
"mean_token_accuracy": 0.2506652906537056,
|
|
"num_tokens": 70990980.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 4.882299757003784,
|
|
"epoch": 3.026801667659321,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004104915549346658,
|
|
"loss": 4.4882,
|
|
"mean_token_accuracy": 0.24300411194562913,
|
|
"num_tokens": 71005780.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 4.832965755462647,
|
|
"epoch": 3.0273972602739727,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004104575324195043,
|
|
"loss": 4.4275,
|
|
"mean_token_accuracy": 0.23794025182724,
|
|
"num_tokens": 71019564.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 4.77410626411438,
|
|
"epoch": 3.027992852888624,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00041042350504570137,
|
|
"loss": 4.3904,
|
|
"mean_token_accuracy": 0.250227726995945,
|
|
"num_tokens": 71032620.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 4.846915292739868,
|
|
"epoch": 3.0285884455032757,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041038947281447745,
|
|
"loss": 4.4402,
|
|
"mean_token_accuracy": 0.2412015676498413,
|
|
"num_tokens": 71047067.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 4.756025695800782,
|
|
"epoch": 3.0291840381179274,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004103554357270533,
|
|
"loss": 4.3644,
|
|
"mean_token_accuracy": 0.24158078134059907,
|
|
"num_tokens": 71059804.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 4.851014089584351,
|
|
"epoch": 3.029779630732579,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004103213937846497,
|
|
"loss": 4.4979,
|
|
"mean_token_accuracy": 0.23228709697723388,
|
|
"num_tokens": 71074264.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 4.807226848602295,
|
|
"epoch": 3.0303752233472303,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004102873469884878,
|
|
"loss": 4.3723,
|
|
"mean_token_accuracy": 0.23964538872241975,
|
|
"num_tokens": 71089177.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 4.769918394088745,
|
|
"epoch": 3.030970815961882,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004102532953397887,
|
|
"loss": 4.3885,
|
|
"mean_token_accuracy": 0.2512555107474327,
|
|
"num_tokens": 71101200.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 4.8025137424469,
|
|
"epoch": 3.0315664085765337,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004102192388397737,
|
|
"loss": 4.4131,
|
|
"mean_token_accuracy": 0.24372094869613647,
|
|
"num_tokens": 71116444.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 4.85400357246399,
|
|
"epoch": 3.0321620011911854,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004101851774896646,
|
|
"loss": 4.4703,
|
|
"mean_token_accuracy": 0.23296654522418975,
|
|
"num_tokens": 71131217.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 4.8118363380432125,
|
|
"epoch": 3.0327575938058366,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000410151111290683,
|
|
"loss": 4.4187,
|
|
"mean_token_accuracy": 0.2442312642931938,
|
|
"num_tokens": 71144849.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 4.7992969989776615,
|
|
"epoch": 3.0333531864204883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041011704024405065,
|
|
"loss": 4.4552,
|
|
"mean_token_accuracy": 0.24034176468849183,
|
|
"num_tokens": 71159211.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 4.8010063648223875,
|
|
"epoch": 3.03394877903514,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041008296435098983,
|
|
"loss": 4.425,
|
|
"mean_token_accuracy": 0.2457820162177086,
|
|
"num_tokens": 71172398.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 4.796756410598755,
|
|
"epoch": 3.0345443716497917,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041004888361272275,
|
|
"loss": 4.3658,
|
|
"mean_token_accuracy": 0.25089556723833084,
|
|
"num_tokens": 71185893.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 4.725970125198364,
|
|
"epoch": 3.035139964264443,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00041001479803047167,
|
|
"loss": 4.366,
|
|
"mean_token_accuracy": 0.24569554328918458,
|
|
"num_tokens": 71198982.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 4.856478214263916,
|
|
"epoch": 3.0357355568790947,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004099807076054594,
|
|
"loss": 4.5034,
|
|
"mean_token_accuracy": 0.24267038702964783,
|
|
"num_tokens": 71212594.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 4.74070143699646,
|
|
"epoch": 3.0363311494937464,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004099466123389086,
|
|
"loss": 4.3425,
|
|
"mean_token_accuracy": 0.24989991784095764,
|
|
"num_tokens": 71227035.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 4.781551694869995,
|
|
"epoch": 3.036926742108398,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00040991251223204217,
|
|
"loss": 4.3706,
|
|
"mean_token_accuracy": 0.2448904573917389,
|
|
"num_tokens": 71241358.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 4.784165620803833,
|
|
"epoch": 3.0375223347230493,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040987840728608335,
|
|
"loss": 4.3779,
|
|
"mean_token_accuracy": 0.24403153508901596,
|
|
"num_tokens": 71256187.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 4.793221569061279,
|
|
"epoch": 3.038117927337701,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00040984429750225534,
|
|
"loss": 4.4393,
|
|
"mean_token_accuracy": 0.24075023531913758,
|
|
"num_tokens": 71271339.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 4.8102803230285645,
|
|
"epoch": 3.0387135199523527,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040981018288178164,
|
|
"loss": 4.4579,
|
|
"mean_token_accuracy": 0.2384659618139267,
|
|
"num_tokens": 71285021.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 4.741739177703858,
|
|
"epoch": 3.039309112567004,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004097760634258858,
|
|
"loss": 4.3732,
|
|
"mean_token_accuracy": 0.24520560801029206,
|
|
"num_tokens": 71298051.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 4.756536865234375,
|
|
"epoch": 3.0399047051816557,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040974193913579174,
|
|
"loss": 4.3614,
|
|
"mean_token_accuracy": 0.24465968906879426,
|
|
"num_tokens": 71311760.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 4.84441819190979,
|
|
"epoch": 3.0405002977963074,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004097078100127234,
|
|
"loss": 4.4792,
|
|
"mean_token_accuracy": 0.2289913222193718,
|
|
"num_tokens": 71328441.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 4.735237312316895,
|
|
"epoch": 3.041095890410959,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040967367605790496,
|
|
"loss": 4.303,
|
|
"mean_token_accuracy": 0.2488623946905136,
|
|
"num_tokens": 71345905.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 4.836341047286988,
|
|
"epoch": 3.0416914830256103,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040963953727256064,
|
|
"loss": 4.5093,
|
|
"mean_token_accuracy": 0.23118268102407455,
|
|
"num_tokens": 71358313.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 4.832771110534668,
|
|
"epoch": 3.042287075640262,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004096053936579151,
|
|
"loss": 4.426,
|
|
"mean_token_accuracy": 0.24086958169937134,
|
|
"num_tokens": 71372382.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 4.761575031280517,
|
|
"epoch": 3.0428826682549137,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040957124521519294,
|
|
"loss": 4.3741,
|
|
"mean_token_accuracy": 0.23915742784738542,
|
|
"num_tokens": 71385893.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 4.801717042922974,
|
|
"epoch": 3.0434782608695654,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000409537091945619,
|
|
"loss": 4.4812,
|
|
"mean_token_accuracy": 0.23454900234937667,
|
|
"num_tokens": 71397939.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 4.780765867233276,
|
|
"epoch": 3.0440738534842167,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004095029338504184,
|
|
"loss": 4.338,
|
|
"mean_token_accuracy": 0.24875971525907517,
|
|
"num_tokens": 71412467.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 4.797774314880371,
|
|
"epoch": 3.0446694460988684,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004094687709308161,
|
|
"loss": 4.4511,
|
|
"mean_token_accuracy": 0.24185614734888078,
|
|
"num_tokens": 71426474.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 4.780684089660644,
|
|
"epoch": 3.04526503871352,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040943460318803774,
|
|
"loss": 4.3584,
|
|
"mean_token_accuracy": 0.24563417285680772,
|
|
"num_tokens": 71440018.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 4.808494663238525,
|
|
"epoch": 3.0458606313281713,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004094004306233087,
|
|
"loss": 4.468,
|
|
"mean_token_accuracy": 0.2347276672720909,
|
|
"num_tokens": 71453569.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 4.8554943084716795,
|
|
"epoch": 3.046456223942823,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004093662532378547,
|
|
"loss": 4.4226,
|
|
"mean_token_accuracy": 0.2423063650727272,
|
|
"num_tokens": 71467522.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 4.8287975788116455,
|
|
"epoch": 3.0470518165574747,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004093320710329017,
|
|
"loss": 4.4035,
|
|
"mean_token_accuracy": 0.24671075791120528,
|
|
"num_tokens": 71480929.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 4.754140090942383,
|
|
"epoch": 3.0476474091721264,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040929788400967566,
|
|
"loss": 4.3517,
|
|
"mean_token_accuracy": 0.247016604244709,
|
|
"num_tokens": 71493996.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 4.755808305740357,
|
|
"epoch": 3.0482430017867777,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000409263692169403,
|
|
"loss": 4.3635,
|
|
"mean_token_accuracy": 0.24076299071311952,
|
|
"num_tokens": 71509350.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 4.856890678405762,
|
|
"epoch": 3.0488385944014293,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040922949551330985,
|
|
"loss": 4.4677,
|
|
"mean_token_accuracy": 0.23997431993484497,
|
|
"num_tokens": 71523095.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 4.77861647605896,
|
|
"epoch": 3.049434187016081,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004091952940426231,
|
|
"loss": 4.3291,
|
|
"mean_token_accuracy": 0.2506276577711105,
|
|
"num_tokens": 71535743.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 4.829520177841187,
|
|
"epoch": 3.0500297796307327,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040916108775856925,
|
|
"loss": 4.4348,
|
|
"mean_token_accuracy": 0.23775566071271897,
|
|
"num_tokens": 71547722.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 4.786174154281616,
|
|
"epoch": 3.050625372245384,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004091268766623753,
|
|
"loss": 4.4928,
|
|
"mean_token_accuracy": 0.2395981192588806,
|
|
"num_tokens": 71561930.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 4.802705574035644,
|
|
"epoch": 3.0512209648600357,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004090926607552684,
|
|
"loss": 4.4392,
|
|
"mean_token_accuracy": 0.23671021461486816,
|
|
"num_tokens": 71575885.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 4.823509645462036,
|
|
"epoch": 3.0518165574746874,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004090584400384758,
|
|
"loss": 4.5149,
|
|
"mean_token_accuracy": 0.2341379776597023,
|
|
"num_tokens": 71590502.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 4.868453168869019,
|
|
"epoch": 3.052412150089339,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040902421451322486,
|
|
"loss": 4.4329,
|
|
"mean_token_accuracy": 0.23937883973121643,
|
|
"num_tokens": 71604876.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 4.872296476364136,
|
|
"epoch": 3.0530077427039903,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004089899841807433,
|
|
"loss": 4.4369,
|
|
"mean_token_accuracy": 0.22698136419057846,
|
|
"num_tokens": 71618476.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 4.810765171051026,
|
|
"epoch": 3.053603335318642,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004089557490422588,
|
|
"loss": 4.385,
|
|
"mean_token_accuracy": 0.2430375874042511,
|
|
"num_tokens": 71630835.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 4.799851989746093,
|
|
"epoch": 3.0541989279332937,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004089215090989994,
|
|
"loss": 4.4325,
|
|
"mean_token_accuracy": 0.24289254993200302,
|
|
"num_tokens": 71645230.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 4.728161716461182,
|
|
"epoch": 3.0547945205479454,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004088872643521933,
|
|
"loss": 4.3435,
|
|
"mean_token_accuracy": 0.24720529168844224,
|
|
"num_tokens": 71659234.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 4.750839519500732,
|
|
"epoch": 3.0553901131625967,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004088530148030687,
|
|
"loss": 4.3664,
|
|
"mean_token_accuracy": 0.24687548130750656,
|
|
"num_tokens": 71673909.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 4.8395849704742435,
|
|
"epoch": 3.0559857057772484,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000408818760452854,
|
|
"loss": 4.4384,
|
|
"mean_token_accuracy": 0.2426376536488533,
|
|
"num_tokens": 71687749.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 4.855147457122802,
|
|
"epoch": 3.0565812983919,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040878450130277797,
|
|
"loss": 4.5308,
|
|
"mean_token_accuracy": 0.23011513203382492,
|
|
"num_tokens": 71701310.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 4.75132565498352,
|
|
"epoch": 3.0571768910065513,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004087502373540694,
|
|
"loss": 4.3265,
|
|
"mean_token_accuracy": 0.2564910531044006,
|
|
"num_tokens": 71715544.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 4.769479560852051,
|
|
"epoch": 3.057772483621203,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040871596860795733,
|
|
"loss": 4.4236,
|
|
"mean_token_accuracy": 0.2438075140118599,
|
|
"num_tokens": 71729822.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 4.7345428466796875,
|
|
"epoch": 3.0583680762358547,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004086816950656708,
|
|
"loss": 4.3799,
|
|
"mean_token_accuracy": 0.24671103358268737,
|
|
"num_tokens": 71745814.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 4.871007108688355,
|
|
"epoch": 3.0589636688505064,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004086474167284393,
|
|
"loss": 4.4848,
|
|
"mean_token_accuracy": 0.24060107171535491,
|
|
"num_tokens": 71760675.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 4.79410753250122,
|
|
"epoch": 3.0595592614651577,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040861313359749217,
|
|
"loss": 4.4811,
|
|
"mean_token_accuracy": 0.2453674241900444,
|
|
"num_tokens": 71774892.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 4.810075807571411,
|
|
"epoch": 3.0601548540798094,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004085788456740593,
|
|
"loss": 4.3953,
|
|
"mean_token_accuracy": 0.24436757415533067,
|
|
"num_tokens": 71788259.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 4.817253303527832,
|
|
"epoch": 3.060750446694461,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004085445529593703,
|
|
"loss": 4.4508,
|
|
"mean_token_accuracy": 0.2412478506565094,
|
|
"num_tokens": 71802968.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 4.874566555023193,
|
|
"epoch": 3.0613460393091128,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00040851025545465537,
|
|
"loss": 4.4367,
|
|
"mean_token_accuracy": 0.23883439898490905,
|
|
"num_tokens": 71817778.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 4.820000076293946,
|
|
"epoch": 3.061941631923764,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004084759531611447,
|
|
"loss": 4.4329,
|
|
"mean_token_accuracy": 0.23985932916402816,
|
|
"num_tokens": 71832554.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 4.870531511306763,
|
|
"epoch": 3.0625372245384157,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040844164608006857,
|
|
"loss": 4.5078,
|
|
"mean_token_accuracy": 0.2367183282971382,
|
|
"num_tokens": 71847505.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 4.790635633468628,
|
|
"epoch": 3.0631328171530674,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004084073342126575,
|
|
"loss": 4.3725,
|
|
"mean_token_accuracy": 0.24321836084127427,
|
|
"num_tokens": 71862187.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 4.835465145111084,
|
|
"epoch": 3.0637284097677187,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040837301756014227,
|
|
"loss": 4.4685,
|
|
"mean_token_accuracy": 0.23182206749916076,
|
|
"num_tokens": 71875070.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 4.8232433795928955,
|
|
"epoch": 3.0643240023823703,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004083386961237538,
|
|
"loss": 4.419,
|
|
"mean_token_accuracy": 0.2443377271294594,
|
|
"num_tokens": 71888843.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 4.834497928619385,
|
|
"epoch": 3.064919594997022,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004083043699047231,
|
|
"loss": 4.4773,
|
|
"mean_token_accuracy": 0.23786348849534988,
|
|
"num_tokens": 71902415.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 4.926025629043579,
|
|
"epoch": 3.0655151876116737,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004082700389042814,
|
|
"loss": 4.4493,
|
|
"mean_token_accuracy": 0.23900820612907409,
|
|
"num_tokens": 71915352.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 4.7975705623626705,
|
|
"epoch": 3.066110780226325,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040823570312366005,
|
|
"loss": 4.3956,
|
|
"mean_token_accuracy": 0.245389986038208,
|
|
"num_tokens": 71928389.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 4.771659660339355,
|
|
"epoch": 3.0667063728409767,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040820136256409064,
|
|
"loss": 4.3965,
|
|
"mean_token_accuracy": 0.2357420951128006,
|
|
"num_tokens": 71943323.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 4.808038759231567,
|
|
"epoch": 3.0673019654556284,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004081670172268049,
|
|
"loss": 4.4215,
|
|
"mean_token_accuracy": 0.24028940945863725,
|
|
"num_tokens": 71958273.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 4.794033765792847,
|
|
"epoch": 3.06789755807028,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00040813266711303486,
|
|
"loss": 4.4296,
|
|
"mean_token_accuracy": 0.23869677931070327,
|
|
"num_tokens": 71972526.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 4.777733373641968,
|
|
"epoch": 3.0684931506849313,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004080983122240125,
|
|
"loss": 4.3878,
|
|
"mean_token_accuracy": 0.24171386808156967,
|
|
"num_tokens": 71987947.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 4.766586351394653,
|
|
"epoch": 3.069088743299583,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00040806395256097,
|
|
"loss": 4.3306,
|
|
"mean_token_accuracy": 0.24551263749599456,
|
|
"num_tokens": 72001209.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 4.732243299484253,
|
|
"epoch": 3.0696843359142347,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040802958812513997,
|
|
"loss": 4.3953,
|
|
"mean_token_accuracy": 0.25261047333478925,
|
|
"num_tokens": 72016196.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 4.833794641494751,
|
|
"epoch": 3.0702799285288864,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004079952189177549,
|
|
"loss": 4.4742,
|
|
"mean_token_accuracy": 0.2435564786195755,
|
|
"num_tokens": 72031920.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 4.820236349105835,
|
|
"epoch": 3.0708755211435377,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00040796084494004747,
|
|
"loss": 4.4463,
|
|
"mean_token_accuracy": 0.24146019220352172,
|
|
"num_tokens": 72044741.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 4.720241403579712,
|
|
"epoch": 3.0714711137581894,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040792646619325086,
|
|
"loss": 4.3666,
|
|
"mean_token_accuracy": 0.24865079075098037,
|
|
"num_tokens": 72059210.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 4.883717966079712,
|
|
"epoch": 3.072066706372841,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004078920826785979,
|
|
"loss": 4.4498,
|
|
"mean_token_accuracy": 0.2450832888484001,
|
|
"num_tokens": 72073590.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 4.814286136627198,
|
|
"epoch": 3.0726622989874928,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000407857694397322,
|
|
"loss": 4.3662,
|
|
"mean_token_accuracy": 0.2483972951769829,
|
|
"num_tokens": 72087052.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 4.774883651733399,
|
|
"epoch": 3.073257891602144,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004078233013506567,
|
|
"loss": 4.3943,
|
|
"mean_token_accuracy": 0.24632259756326674,
|
|
"num_tokens": 72101793.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 4.850345754623413,
|
|
"epoch": 3.0738534842167957,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040778890353983547,
|
|
"loss": 4.4478,
|
|
"mean_token_accuracy": 0.24724046885967255,
|
|
"num_tokens": 72116631.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 4.880142688751221,
|
|
"epoch": 3.0744490768314474,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00040775450096609226,
|
|
"loss": 4.4962,
|
|
"mean_token_accuracy": 0.23249903619289397,
|
|
"num_tokens": 72132604.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 4.756886720657349,
|
|
"epoch": 3.0750446694460987,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004077200936306609,
|
|
"loss": 4.3463,
|
|
"mean_token_accuracy": 0.24725141674280166,
|
|
"num_tokens": 72146629.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 4.817506265640259,
|
|
"epoch": 3.0756402620607504,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004076856815347756,
|
|
"loss": 4.4938,
|
|
"mean_token_accuracy": 0.23395829349756242,
|
|
"num_tokens": 72159839.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 4.804679441452026,
|
|
"epoch": 3.076235854675402,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004076512646796705,
|
|
"loss": 4.4044,
|
|
"mean_token_accuracy": 0.24055605232715607,
|
|
"num_tokens": 72173464.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 4.819541120529175,
|
|
"epoch": 3.0768314472900538,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004076168430665804,
|
|
"loss": 4.4421,
|
|
"mean_token_accuracy": 0.24105482101440429,
|
|
"num_tokens": 72188226.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 4.8479773044586185,
|
|
"epoch": 3.077427039904705,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004075824166967396,
|
|
"loss": 4.4518,
|
|
"mean_token_accuracy": 0.2413791000843048,
|
|
"num_tokens": 72201771.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 4.8557178497314455,
|
|
"epoch": 3.0780226325193567,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040754798557138315,
|
|
"loss": 4.4176,
|
|
"mean_token_accuracy": 0.23601245731115342,
|
|
"num_tokens": 72215576.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 4.769424962997436,
|
|
"epoch": 3.0786182251340084,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000407513549691746,
|
|
"loss": 4.3923,
|
|
"mean_token_accuracy": 0.2515308797359467,
|
|
"num_tokens": 72228237.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 4.748773717880249,
|
|
"epoch": 3.07921381774866,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004074791090590632,
|
|
"loss": 4.2954,
|
|
"mean_token_accuracy": 0.2519258111715317,
|
|
"num_tokens": 72241718.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 4.703347063064575,
|
|
"epoch": 3.0798094103633114,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004074446636745703,
|
|
"loss": 4.3425,
|
|
"mean_token_accuracy": 0.24542823880910875,
|
|
"num_tokens": 72254634.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 4.795396709442139,
|
|
"epoch": 3.080405002977963,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040741021353950246,
|
|
"loss": 4.4817,
|
|
"mean_token_accuracy": 0.2417130008339882,
|
|
"num_tokens": 72269882.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 4.769238996505737,
|
|
"epoch": 3.0810005955926147,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004073757586550957,
|
|
"loss": 4.3254,
|
|
"mean_token_accuracy": 0.250347501039505,
|
|
"num_tokens": 72283520.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 4.850992107391358,
|
|
"epoch": 3.0815961882072664,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004073412990225856,
|
|
"loss": 4.4724,
|
|
"mean_token_accuracy": 0.2412629544734955,
|
|
"num_tokens": 72297340.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 4.75400824546814,
|
|
"epoch": 3.0821917808219177,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040730683464320835,
|
|
"loss": 4.3387,
|
|
"mean_token_accuracy": 0.24916471391916276,
|
|
"num_tokens": 72309765.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 4.848228883743286,
|
|
"epoch": 3.0827873734365694,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004072723655182001,
|
|
"loss": 4.5132,
|
|
"mean_token_accuracy": 0.23349038809537886,
|
|
"num_tokens": 72324971.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 4.864230346679688,
|
|
"epoch": 3.083382966051221,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040723789164879697,
|
|
"loss": 4.4516,
|
|
"mean_token_accuracy": 0.24561405330896377,
|
|
"num_tokens": 72339897.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 4.789153242111206,
|
|
"epoch": 3.0839785586658723,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040720341303623593,
|
|
"loss": 4.3107,
|
|
"mean_token_accuracy": 0.2555934339761734,
|
|
"num_tokens": 72351551.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 4.778189420700073,
|
|
"epoch": 3.084574151280524,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040716892968175325,
|
|
"loss": 4.377,
|
|
"mean_token_accuracy": 0.24613370895385742,
|
|
"num_tokens": 72364018.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 4.829685926437378,
|
|
"epoch": 3.0851697438951757,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004071344415865859,
|
|
"loss": 4.4604,
|
|
"mean_token_accuracy": 0.23239680975675583,
|
|
"num_tokens": 72379019.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 4.758324193954468,
|
|
"epoch": 3.0857653365098274,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004070999487519711,
|
|
"loss": 4.3698,
|
|
"mean_token_accuracy": 0.24624110460281373,
|
|
"num_tokens": 72391424.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 4.772126245498657,
|
|
"epoch": 3.0863609291244787,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004070654511791459,
|
|
"loss": 4.3817,
|
|
"mean_token_accuracy": 0.24230822771787644,
|
|
"num_tokens": 72404334.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 4.815077638626098,
|
|
"epoch": 3.0869565217391304,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040703094886934763,
|
|
"loss": 4.4473,
|
|
"mean_token_accuracy": 0.2377345457673073,
|
|
"num_tokens": 72419495.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 4.7572283267974855,
|
|
"epoch": 3.087552114353782,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00040699644182381394,
|
|
"loss": 4.3763,
|
|
"mean_token_accuracy": 0.24187284409999849,
|
|
"num_tokens": 72431694.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 4.811461544036865,
|
|
"epoch": 3.0881477069684338,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004069619300437825,
|
|
"loss": 4.4512,
|
|
"mean_token_accuracy": 0.2450345516204834,
|
|
"num_tokens": 72445602.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 4.877589559555053,
|
|
"epoch": 3.088743299583085,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004069274135304912,
|
|
"loss": 4.3867,
|
|
"mean_token_accuracy": 0.24574450701475142,
|
|
"num_tokens": 72460484.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 4.755977964401245,
|
|
"epoch": 3.0893388921977367,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000406892892285178,
|
|
"loss": 4.4042,
|
|
"mean_token_accuracy": 0.2379957005381584,
|
|
"num_tokens": 72472811.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 4.732795238494873,
|
|
"epoch": 3.0899344848123884,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004068583663090813,
|
|
"loss": 4.3757,
|
|
"mean_token_accuracy": 0.24076650738716127,
|
|
"num_tokens": 72488275.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 4.864710712432862,
|
|
"epoch": 3.09053007742704,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004068238356034393,
|
|
"loss": 4.5171,
|
|
"mean_token_accuracy": 0.23023789376020432,
|
|
"num_tokens": 72501181.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 4.7921302318573,
|
|
"epoch": 3.0911256700416914,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040678930016949073,
|
|
"loss": 4.336,
|
|
"mean_token_accuracy": 0.25430077910423277,
|
|
"num_tokens": 72514626.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 4.827830457687378,
|
|
"epoch": 3.091721262656343,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040675476000847423,
|
|
"loss": 4.4411,
|
|
"mean_token_accuracy": 0.24308393001556397,
|
|
"num_tokens": 72528907.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 4.866122531890869,
|
|
"epoch": 3.0923168552709948,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00040672021512162864,
|
|
"loss": 4.474,
|
|
"mean_token_accuracy": 0.23395901322364807,
|
|
"num_tokens": 72543719.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 4.8961633205413815,
|
|
"epoch": 3.092912447885646,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004066856655101931,
|
|
"loss": 4.5357,
|
|
"mean_token_accuracy": 0.23563431054353715,
|
|
"num_tokens": 72555992.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 4.816987371444702,
|
|
"epoch": 3.0935080405002977,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004066511111754069,
|
|
"loss": 4.4029,
|
|
"mean_token_accuracy": 0.24684544801712036,
|
|
"num_tokens": 72570748.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 4.778170490264893,
|
|
"epoch": 3.0941036331149494,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004066165521185094,
|
|
"loss": 4.4006,
|
|
"mean_token_accuracy": 0.24240242093801498,
|
|
"num_tokens": 72585108.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 4.717850637435913,
|
|
"epoch": 3.094699225729601,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004065819883407402,
|
|
"loss": 4.3986,
|
|
"mean_token_accuracy": 0.2510637193918228,
|
|
"num_tokens": 72598007.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 4.745287799835205,
|
|
"epoch": 3.0952948183442524,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00040654741984333886,
|
|
"loss": 4.3724,
|
|
"mean_token_accuracy": 0.24701776951551438,
|
|
"num_tokens": 72613587.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 4.817126941680908,
|
|
"epoch": 3.095890410958904,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004065128466275456,
|
|
"loss": 4.4688,
|
|
"mean_token_accuracy": 0.23809205144643783,
|
|
"num_tokens": 72628798.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 4.807615756988525,
|
|
"epoch": 3.0964860035735557,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004064782686946003,
|
|
"loss": 4.4604,
|
|
"mean_token_accuracy": 0.23681236803531647,
|
|
"num_tokens": 72643712.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 4.7832372188568115,
|
|
"epoch": 3.0970815961882074,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004064436860457433,
|
|
"loss": 4.4312,
|
|
"mean_token_accuracy": 0.23846677243709563,
|
|
"num_tokens": 72657777.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 4.89788703918457,
|
|
"epoch": 3.0976771888028587,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000406409098682215,
|
|
"loss": 4.4603,
|
|
"mean_token_accuracy": 0.23983183801174163,
|
|
"num_tokens": 72671414.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 4.792398357391358,
|
|
"epoch": 3.0982727814175104,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040637450660525594,
|
|
"loss": 4.3806,
|
|
"mean_token_accuracy": 0.2452075883746147,
|
|
"num_tokens": 72685956.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 4.7404937744140625,
|
|
"epoch": 3.098868374032162,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000406339909816107,
|
|
"loss": 4.358,
|
|
"mean_token_accuracy": 0.2389398843050003,
|
|
"num_tokens": 72702960.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 4.78660945892334,
|
|
"epoch": 3.099463966646814,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00040630530831600904,
|
|
"loss": 4.4248,
|
|
"mean_token_accuracy": 0.23991691917181016,
|
|
"num_tokens": 72717396.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 4.805073261260986,
|
|
"epoch": 3.100059559261465,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00040627070210620306,
|
|
"loss": 4.3967,
|
|
"mean_token_accuracy": 0.2423383727669716,
|
|
"num_tokens": 72732454.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 4.788006973266602,
|
|
"epoch": 3.1006551518761167,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004062360911879305,
|
|
"loss": 4.4222,
|
|
"mean_token_accuracy": 0.23682251572608948,
|
|
"num_tokens": 72746491.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 4.76541109085083,
|
|
"epoch": 3.1012507444907684,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004062014755624327,
|
|
"loss": 4.3387,
|
|
"mean_token_accuracy": 0.2543055504560471,
|
|
"num_tokens": 72759803.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 4.763391447067261,
|
|
"epoch": 3.1018463371054197,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040616685523095134,
|
|
"loss": 4.3105,
|
|
"mean_token_accuracy": 0.2507737800478935,
|
|
"num_tokens": 72773810.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 4.73336238861084,
|
|
"epoch": 3.1024419297200714,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004061322301947281,
|
|
"loss": 4.3875,
|
|
"mean_token_accuracy": 0.24911706596612931,
|
|
"num_tokens": 72786999.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 4.849783325195313,
|
|
"epoch": 3.103037522334723,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00040609760045500496,
|
|
"loss": 4.5092,
|
|
"mean_token_accuracy": 0.23735456317663192,
|
|
"num_tokens": 72801972.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 4.892773246765136,
|
|
"epoch": 3.1036331149493748,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004060629660130241,
|
|
"loss": 4.4604,
|
|
"mean_token_accuracy": 0.23814246654510499,
|
|
"num_tokens": 72815596.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 4.770318984985352,
|
|
"epoch": 3.104228707564026,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040602832687002774,
|
|
"loss": 4.4207,
|
|
"mean_token_accuracy": 0.24526774734258652,
|
|
"num_tokens": 72830195.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 4.750542497634887,
|
|
"epoch": 3.1048243001786777,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004059936830272583,
|
|
"loss": 4.3984,
|
|
"mean_token_accuracy": 0.23789883852005006,
|
|
"num_tokens": 72844946.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 4.784336757659912,
|
|
"epoch": 3.1054198927933294,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004059590344859584,
|
|
"loss": 4.3739,
|
|
"mean_token_accuracy": 0.2533526733517647,
|
|
"num_tokens": 72857858.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 4.800614309310913,
|
|
"epoch": 3.106015485407981,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040592438124737086,
|
|
"loss": 4.3597,
|
|
"mean_token_accuracy": 0.2486385628581047,
|
|
"num_tokens": 72870192.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 4.765136051177978,
|
|
"epoch": 3.1066110780226324,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004058897233127387,
|
|
"loss": 4.3187,
|
|
"mean_token_accuracy": 0.24376181662082672,
|
|
"num_tokens": 72885203.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 4.815120267868042,
|
|
"epoch": 3.107206670637284,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040585506068330495,
|
|
"loss": 4.4732,
|
|
"mean_token_accuracy": 0.23767591565847396,
|
|
"num_tokens": 72898464.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 4.799475812911988,
|
|
"epoch": 3.1078022632519358,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040582039336031295,
|
|
"loss": 4.4154,
|
|
"mean_token_accuracy": 0.24564177095890044,
|
|
"num_tokens": 72912734.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 4.883196401596069,
|
|
"epoch": 3.1083978558665875,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004057857213450061,
|
|
"loss": 4.4679,
|
|
"mean_token_accuracy": 0.23422443866729736,
|
|
"num_tokens": 72926677.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 4.710399580001831,
|
|
"epoch": 3.1089934484812387,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004057510446386282,
|
|
"loss": 4.2919,
|
|
"mean_token_accuracy": 0.2531758740544319,
|
|
"num_tokens": 72938941.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 4.769179439544677,
|
|
"epoch": 3.1095890410958904,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004057163632424227,
|
|
"loss": 4.3543,
|
|
"mean_token_accuracy": 0.24410042762756348,
|
|
"num_tokens": 72954519.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 4.773994398117066,
|
|
"epoch": 3.110184633710542,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004056816771576339,
|
|
"loss": 4.4004,
|
|
"mean_token_accuracy": 0.24912789911031724,
|
|
"num_tokens": 72967598.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 4.806046438217163,
|
|
"epoch": 3.1107802263251934,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040564698638550584,
|
|
"loss": 4.4485,
|
|
"mean_token_accuracy": 0.23792878687381744,
|
|
"num_tokens": 72983277.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 4.837297105789185,
|
|
"epoch": 3.111375818939845,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040561229092728277,
|
|
"loss": 4.4453,
|
|
"mean_token_accuracy": 0.23974708914756776,
|
|
"num_tokens": 72999128.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 4.753118228912354,
|
|
"epoch": 3.1119714115544967,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004055775907842092,
|
|
"loss": 4.3749,
|
|
"mean_token_accuracy": 0.24639101475477218,
|
|
"num_tokens": 73013721.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 4.779628658294678,
|
|
"epoch": 3.1125670041691484,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004055428859575297,
|
|
"loss": 4.4767,
|
|
"mean_token_accuracy": 0.23651762157678605,
|
|
"num_tokens": 73027826.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 4.773183679580688,
|
|
"epoch": 3.1131625967837997,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004055081764484892,
|
|
"loss": 4.4235,
|
|
"mean_token_accuracy": 0.2432743415236473,
|
|
"num_tokens": 73041085.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 4.774025392532349,
|
|
"epoch": 3.1137581893984514,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004054734622583325,
|
|
"loss": 4.3598,
|
|
"mean_token_accuracy": 0.25028194934129716,
|
|
"num_tokens": 73055692.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 4.80866494178772,
|
|
"epoch": 3.114353782013103,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000405438743388305,
|
|
"loss": 4.4803,
|
|
"mean_token_accuracy": 0.22787687927484512,
|
|
"num_tokens": 73070135.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 4.789136600494385,
|
|
"epoch": 3.114949374627755,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040540401983965173,
|
|
"loss": 4.4463,
|
|
"mean_token_accuracy": 0.2390891656279564,
|
|
"num_tokens": 73086011.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 4.735773754119873,
|
|
"epoch": 3.115544967242406,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040536929161361833,
|
|
"loss": 4.269,
|
|
"mean_token_accuracy": 0.2610223352909088,
|
|
"num_tokens": 73100642.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 4.729992389678955,
|
|
"epoch": 3.1161405598570577,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040533455871145046,
|
|
"loss": 4.3068,
|
|
"mean_token_accuracy": 0.2565107852220535,
|
|
"num_tokens": 73113591.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 4.777115392684936,
|
|
"epoch": 3.1167361524717094,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040529982113439385,
|
|
"loss": 4.4348,
|
|
"mean_token_accuracy": 0.23543930649757386,
|
|
"num_tokens": 73126635.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 4.83378324508667,
|
|
"epoch": 3.117331745086361,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00040526507888369453,
|
|
"loss": 4.4626,
|
|
"mean_token_accuracy": 0.2399812862277031,
|
|
"num_tokens": 73140094.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 4.778267955780029,
|
|
"epoch": 3.1179273377010124,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040523033196059857,
|
|
"loss": 4.379,
|
|
"mean_token_accuracy": 0.24105405509471894,
|
|
"num_tokens": 73152914.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 4.896300840377807,
|
|
"epoch": 3.118522930315664,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004051955803663523,
|
|
"loss": 4.4807,
|
|
"mean_token_accuracy": 0.2379736602306366,
|
|
"num_tokens": 73167273.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 4.857445955276489,
|
|
"epoch": 3.1191185229303158,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004051608241022024,
|
|
"loss": 4.4832,
|
|
"mean_token_accuracy": 0.2365419775247574,
|
|
"num_tokens": 73180986.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 4.742967510223389,
|
|
"epoch": 3.1197141155449675,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040512606316939524,
|
|
"loss": 4.3924,
|
|
"mean_token_accuracy": 0.245764422416687,
|
|
"num_tokens": 73194548.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 4.846279716491699,
|
|
"epoch": 3.1203097081596187,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040509129756917785,
|
|
"loss": 4.4125,
|
|
"mean_token_accuracy": 0.24403838068246841,
|
|
"num_tokens": 73206320.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 4.750808620452881,
|
|
"epoch": 3.1209053007742704,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000405056527302797,
|
|
"loss": 4.3478,
|
|
"mean_token_accuracy": 0.24689513444900513,
|
|
"num_tokens": 73218563.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 4.707005786895752,
|
|
"epoch": 3.121500893388922,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004050217523715002,
|
|
"loss": 4.331,
|
|
"mean_token_accuracy": 0.253333255648613,
|
|
"num_tokens": 73231023.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 4.84223690032959,
|
|
"epoch": 3.1220964860035734,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004049869727765343,
|
|
"loss": 4.452,
|
|
"mean_token_accuracy": 0.24912291169166564,
|
|
"num_tokens": 73244481.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 4.791150522232056,
|
|
"epoch": 3.122692078618225,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040495218851914716,
|
|
"loss": 4.3841,
|
|
"mean_token_accuracy": 0.24240456372499466,
|
|
"num_tokens": 73260755.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 4.7334600448608395,
|
|
"epoch": 3.1232876712328768,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004049173996005863,
|
|
"loss": 4.3895,
|
|
"mean_token_accuracy": 0.2468926265835762,
|
|
"num_tokens": 73273956.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 4.828570556640625,
|
|
"epoch": 3.1238832638475285,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004048826060220996,
|
|
"loss": 4.508,
|
|
"mean_token_accuracy": 0.23117113262414932,
|
|
"num_tokens": 73288446.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 4.872982025146484,
|
|
"epoch": 3.1244788564621797,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004048478077849349,
|
|
"loss": 4.4887,
|
|
"mean_token_accuracy": 0.23467987179756164,
|
|
"num_tokens": 73302522.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 4.9151365756988525,
|
|
"epoch": 3.1250744490768314,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004048130048903404,
|
|
"loss": 4.5021,
|
|
"mean_token_accuracy": 0.23177144825458526,
|
|
"num_tokens": 73315290.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 4.750499057769775,
|
|
"epoch": 3.125670041691483,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040477819733956467,
|
|
"loss": 4.425,
|
|
"mean_token_accuracy": 0.23879117220640184,
|
|
"num_tokens": 73328088.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 4.8286309242248535,
|
|
"epoch": 3.126265634306135,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004047433851338559,
|
|
"loss": 4.582,
|
|
"mean_token_accuracy": 0.22458861023187637,
|
|
"num_tokens": 73342614.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 4.912652921676636,
|
|
"epoch": 3.126861226920786,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00040470856827446285,
|
|
"loss": 4.5077,
|
|
"mean_token_accuracy": 0.23862666487693787,
|
|
"num_tokens": 73357306.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 4.867294645309448,
|
|
"epoch": 3.1274568195354377,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00040467374676263435,
|
|
"loss": 4.431,
|
|
"mean_token_accuracy": 0.23567290753126144,
|
|
"num_tokens": 73369874.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 4.685444164276123,
|
|
"epoch": 3.1280524121500894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040463892059961946,
|
|
"loss": 4.3527,
|
|
"mean_token_accuracy": 0.24449045658111573,
|
|
"num_tokens": 73383576.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 4.815347480773926,
|
|
"epoch": 3.1286480047647407,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004046040897866671,
|
|
"loss": 4.456,
|
|
"mean_token_accuracy": 0.23360365331172944,
|
|
"num_tokens": 73398735.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 4.72355465888977,
|
|
"epoch": 3.1292435973793924,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040456925432502694,
|
|
"loss": 4.2991,
|
|
"mean_token_accuracy": 0.25356577932834623,
|
|
"num_tokens": 73411048.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 4.814213562011719,
|
|
"epoch": 3.129839189994044,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040453441421594823,
|
|
"loss": 4.4578,
|
|
"mean_token_accuracy": 0.23785669654607772,
|
|
"num_tokens": 73425505.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 4.864228677749634,
|
|
"epoch": 3.130434782608696,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040449956946068065,
|
|
"loss": 4.5431,
|
|
"mean_token_accuracy": 0.23231862783432006,
|
|
"num_tokens": 73439812.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 4.873715925216675,
|
|
"epoch": 3.131030375223347,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040446472006047413,
|
|
"loss": 4.361,
|
|
"mean_token_accuracy": 0.24400635063648224,
|
|
"num_tokens": 73455618.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 4.7167651653289795,
|
|
"epoch": 3.1316259678379987,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004044298660165786,
|
|
"loss": 4.3889,
|
|
"mean_token_accuracy": 0.2482347920536995,
|
|
"num_tokens": 73470165.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 4.7898040294647215,
|
|
"epoch": 3.1322215604526504,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004043950073302442,
|
|
"loss": 4.4368,
|
|
"mean_token_accuracy": 0.23759019672870635,
|
|
"num_tokens": 73483100.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 4.777770614624023,
|
|
"epoch": 3.132817153067302,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004043601440027213,
|
|
"loss": 4.3087,
|
|
"mean_token_accuracy": 0.2500914290547371,
|
|
"num_tokens": 73496849.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 4.8110604763031,
|
|
"epoch": 3.1334127456819534,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00040432527603526027,
|
|
"loss": 4.4066,
|
|
"mean_token_accuracy": 0.2480479210615158,
|
|
"num_tokens": 73510656.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 4.773921203613281,
|
|
"epoch": 3.134008338296605,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040429040342911186,
|
|
"loss": 4.4358,
|
|
"mean_token_accuracy": 0.23723650574684144,
|
|
"num_tokens": 73523827.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 4.818146514892578,
|
|
"epoch": 3.1346039309112568,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000404255526185527,
|
|
"loss": 4.4189,
|
|
"mean_token_accuracy": 0.24523766189813614,
|
|
"num_tokens": 73538930.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 4.821829557418823,
|
|
"epoch": 3.1351995235259085,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004042206443057565,
|
|
"loss": 4.4338,
|
|
"mean_token_accuracy": 0.24432320147752762,
|
|
"num_tokens": 73553653.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 4.747297477722168,
|
|
"epoch": 3.1357951161405597,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004041857577910516,
|
|
"loss": 4.3261,
|
|
"mean_token_accuracy": 0.24983796179294587,
|
|
"num_tokens": 73569207.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 4.868878364562988,
|
|
"epoch": 3.1363907087552114,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004041508666426636,
|
|
"loss": 4.4993,
|
|
"mean_token_accuracy": 0.2373395800590515,
|
|
"num_tokens": 73583977.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 4.750488662719727,
|
|
"epoch": 3.136986301369863,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000404115970861844,
|
|
"loss": 4.2761,
|
|
"mean_token_accuracy": 0.24380096793174744,
|
|
"num_tokens": 73596121.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 4.817375183105469,
|
|
"epoch": 3.137581893984515,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040408107044984456,
|
|
"loss": 4.4837,
|
|
"mean_token_accuracy": 0.23397703617811202,
|
|
"num_tokens": 73610861.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 4.798729467391968,
|
|
"epoch": 3.138177486599166,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040404616540791683,
|
|
"loss": 4.394,
|
|
"mean_token_accuracy": 0.24151996225118638,
|
|
"num_tokens": 73623990.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 4.763772201538086,
|
|
"epoch": 3.1387730792138178,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00040401125573731307,
|
|
"loss": 4.4689,
|
|
"mean_token_accuracy": 0.23976316452026367,
|
|
"num_tokens": 73638032.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 4.840383672714234,
|
|
"epoch": 3.1393686718284695,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004039763414392853,
|
|
"loss": 4.3898,
|
|
"mean_token_accuracy": 0.24297226071357728,
|
|
"num_tokens": 73651876.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 4.812295627593994,
|
|
"epoch": 3.1399642644431207,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00040394142251508585,
|
|
"loss": 4.4036,
|
|
"mean_token_accuracy": 0.2522541120648384,
|
|
"num_tokens": 73664450.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 4.797053480148316,
|
|
"epoch": 3.1405598570577724,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004039064989659672,
|
|
"loss": 4.4574,
|
|
"mean_token_accuracy": 0.23768354803323746,
|
|
"num_tokens": 73680207.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 4.849224615097046,
|
|
"epoch": 3.141155449672424,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040387157079318207,
|
|
"loss": 4.4509,
|
|
"mean_token_accuracy": 0.23867253065109253,
|
|
"num_tokens": 73694414.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 4.790272617340088,
|
|
"epoch": 3.141751042287076,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00040383663799798325,
|
|
"loss": 4.3972,
|
|
"mean_token_accuracy": 0.24568919688463212,
|
|
"num_tokens": 73709000.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 4.787754249572754,
|
|
"epoch": 3.142346634901727,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004038017005816237,
|
|
"loss": 4.408,
|
|
"mean_token_accuracy": 0.2326075628399849,
|
|
"num_tokens": 73724444.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 4.786589431762695,
|
|
"epoch": 3.1429422275163788,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004037667585453565,
|
|
"loss": 4.455,
|
|
"mean_token_accuracy": 0.2430336594581604,
|
|
"num_tokens": 73737688.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 4.837621736526489,
|
|
"epoch": 3.1435378201310304,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000403731811890435,
|
|
"loss": 4.4675,
|
|
"mean_token_accuracy": 0.23358642309904099,
|
|
"num_tokens": 73752340.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 4.836310577392578,
|
|
"epoch": 3.144133412745682,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004036968606181129,
|
|
"loss": 4.4668,
|
|
"mean_token_accuracy": 0.2357211634516716,
|
|
"num_tokens": 73767311.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 4.712380743026733,
|
|
"epoch": 3.1447290053603334,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004036619047296435,
|
|
"loss": 4.2875,
|
|
"mean_token_accuracy": 0.2570579633116722,
|
|
"num_tokens": 73781358.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 4.733096885681152,
|
|
"epoch": 3.145324597974985,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004036269442262808,
|
|
"loss": 4.2549,
|
|
"mean_token_accuracy": 0.2537099286913872,
|
|
"num_tokens": 73794618.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 4.699531126022339,
|
|
"epoch": 3.145920190589637,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004035919791092787,
|
|
"loss": 4.3615,
|
|
"mean_token_accuracy": 0.24617473930120468,
|
|
"num_tokens": 73808421.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 4.834623384475708,
|
|
"epoch": 3.146515783204288,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004035570093798914,
|
|
"loss": 4.4527,
|
|
"mean_token_accuracy": 0.23942336887121202,
|
|
"num_tokens": 73823565.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 4.850272083282471,
|
|
"epoch": 3.1471113758189397,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004035220350393732,
|
|
"loss": 4.4567,
|
|
"mean_token_accuracy": 0.24016392827033997,
|
|
"num_tokens": 73837406.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 4.80574140548706,
|
|
"epoch": 3.1477069684335914,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004034870560889787,
|
|
"loss": 4.3969,
|
|
"mean_token_accuracy": 0.24412138313055037,
|
|
"num_tokens": 73853097.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 4.828369855880737,
|
|
"epoch": 3.148302561048243,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004034520725299623,
|
|
"loss": 4.4086,
|
|
"mean_token_accuracy": 0.23496984839439392,
|
|
"num_tokens": 73866413.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 4.858150482177734,
|
|
"epoch": 3.1488981536628944,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004034170843635789,
|
|
"loss": 4.5136,
|
|
"mean_token_accuracy": 0.2398613765835762,
|
|
"num_tokens": 73879406.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 4.862652540206909,
|
|
"epoch": 3.149493746277546,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00040338209159108355,
|
|
"loss": 4.4447,
|
|
"mean_token_accuracy": 0.24146282374858857,
|
|
"num_tokens": 73893507.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 4.879651165008545,
|
|
"epoch": 3.1500893388921978,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004033470942137312,
|
|
"loss": 4.5107,
|
|
"mean_token_accuracy": 0.241882261633873,
|
|
"num_tokens": 73905331.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 4.8286210060119625,
|
|
"epoch": 3.1506849315068495,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004033120922327773,
|
|
"loss": 4.398,
|
|
"mean_token_accuracy": 0.24275858253240584,
|
|
"num_tokens": 73920934.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 4.78909273147583,
|
|
"epoch": 3.1512805241215007,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004032770856494772,
|
|
"loss": 4.4053,
|
|
"mean_token_accuracy": 0.24690084159374237,
|
|
"num_tokens": 73935187.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 4.837828683853149,
|
|
"epoch": 3.1518761167361524,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004032420744650867,
|
|
"loss": 4.4339,
|
|
"mean_token_accuracy": 0.24274222999811174,
|
|
"num_tokens": 73950478.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 4.842225885391235,
|
|
"epoch": 3.152471709350804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040320705868086154,
|
|
"loss": 4.4486,
|
|
"mean_token_accuracy": 0.24395764172077178,
|
|
"num_tokens": 73963987.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 4.786249446868896,
|
|
"epoch": 3.153067301965456,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004031720382980576,
|
|
"loss": 4.3999,
|
|
"mean_token_accuracy": 0.24941567927598954,
|
|
"num_tokens": 73977876.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 4.719261217117309,
|
|
"epoch": 3.153662894580107,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000403137013317931,
|
|
"loss": 4.2979,
|
|
"mean_token_accuracy": 0.24320945590734483,
|
|
"num_tokens": 73992896.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 4.797987985610962,
|
|
"epoch": 3.1542584871947588,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00040310198374173814,
|
|
"loss": 4.4526,
|
|
"mean_token_accuracy": 0.241549289226532,
|
|
"num_tokens": 74007890.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 4.7740014553070065,
|
|
"epoch": 3.1548540798094105,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040306694957073535,
|
|
"loss": 4.302,
|
|
"mean_token_accuracy": 0.24898766577243805,
|
|
"num_tokens": 74022500.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 4.841396951675415,
|
|
"epoch": 3.155449672424062,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040303191080617927,
|
|
"loss": 4.4894,
|
|
"mean_token_accuracy": 0.2358619213104248,
|
|
"num_tokens": 74034843.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 4.831086206436157,
|
|
"epoch": 3.1560452650387134,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004029968674493268,
|
|
"loss": 4.4482,
|
|
"mean_token_accuracy": 0.23509559482336045,
|
|
"num_tokens": 74051968.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 4.766730451583863,
|
|
"epoch": 3.156640857653365,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004029618195014347,
|
|
"loss": 4.3299,
|
|
"mean_token_accuracy": 0.2548037633299828,
|
|
"num_tokens": 74066579.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 4.819347476959228,
|
|
"epoch": 3.157236450268017,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004029267669637603,
|
|
"loss": 4.4019,
|
|
"mean_token_accuracy": 0.24392509311437607,
|
|
"num_tokens": 74079044.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 4.742516374588012,
|
|
"epoch": 3.157832042882668,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040289170983756075,
|
|
"loss": 4.3391,
|
|
"mean_token_accuracy": 0.2414902091026306,
|
|
"num_tokens": 74093885.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 4.812790489196777,
|
|
"epoch": 3.1584276354973198,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040285664812409345,
|
|
"loss": 4.4086,
|
|
"mean_token_accuracy": 0.23897318542003632,
|
|
"num_tokens": 74108941.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 4.816585063934326,
|
|
"epoch": 3.1590232281119714,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004028215818246161,
|
|
"loss": 4.4421,
|
|
"mean_token_accuracy": 0.2383103162050247,
|
|
"num_tokens": 74125426.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 4.783551120758057,
|
|
"epoch": 3.159618820726623,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004027865109403864,
|
|
"loss": 4.3644,
|
|
"mean_token_accuracy": 0.25265926867723465,
|
|
"num_tokens": 74138863.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 4.730223989486694,
|
|
"epoch": 3.1602144133412744,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040275143547266235,
|
|
"loss": 4.3225,
|
|
"mean_token_accuracy": 0.25221732407808306,
|
|
"num_tokens": 74150890.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 4.80444827079773,
|
|
"epoch": 3.160810005955926,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000402716355422702,
|
|
"loss": 4.4346,
|
|
"mean_token_accuracy": 0.24165140390396117,
|
|
"num_tokens": 74162974.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 4.8696356296539305,
|
|
"epoch": 3.161405598570578,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040268127079176364,
|
|
"loss": 4.5017,
|
|
"mean_token_accuracy": 0.23237596601247787,
|
|
"num_tokens": 74175673.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 4.739156055450439,
|
|
"epoch": 3.1620011911852295,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004026461815811057,
|
|
"loss": 4.352,
|
|
"mean_token_accuracy": 0.244962739944458,
|
|
"num_tokens": 74188524.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 4.784078884124756,
|
|
"epoch": 3.1625967837998807,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004026110877919867,
|
|
"loss": 4.3587,
|
|
"mean_token_accuracy": 0.2456026554107666,
|
|
"num_tokens": 74201807.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 4.827562046051026,
|
|
"epoch": 3.1631923764145324,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040257598942566565,
|
|
"loss": 4.4119,
|
|
"mean_token_accuracy": 0.24579299837350846,
|
|
"num_tokens": 74214883.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 4.74412899017334,
|
|
"epoch": 3.163787969029184,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040254088648340107,
|
|
"loss": 4.417,
|
|
"mean_token_accuracy": 0.2449568286538124,
|
|
"num_tokens": 74228145.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 4.840200042724609,
|
|
"epoch": 3.1643835616438354,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004025057789664524,
|
|
"loss": 4.483,
|
|
"mean_token_accuracy": 0.23587937355041505,
|
|
"num_tokens": 74241950.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 4.824079990386963,
|
|
"epoch": 3.164979154258487,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004024706668760787,
|
|
"loss": 4.4485,
|
|
"mean_token_accuracy": 0.23786471486091615,
|
|
"num_tokens": 74256661.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 4.764929962158203,
|
|
"epoch": 3.165574746873139,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004024355502135394,
|
|
"loss": 4.3665,
|
|
"mean_token_accuracy": 0.24585068523883818,
|
|
"num_tokens": 74269459.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 4.765241527557373,
|
|
"epoch": 3.1661703394877905,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040240042898009425,
|
|
"loss": 4.4212,
|
|
"mean_token_accuracy": 0.24545443207025527,
|
|
"num_tokens": 74284489.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 4.861099290847778,
|
|
"epoch": 3.1667659321024417,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004023653031770028,
|
|
"loss": 4.4951,
|
|
"mean_token_accuracy": 0.23521096408367156,
|
|
"num_tokens": 74297571.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 4.896087980270385,
|
|
"epoch": 3.1673615247170934,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040233017280552494,
|
|
"loss": 4.4618,
|
|
"mean_token_accuracy": 0.23728434592485428,
|
|
"num_tokens": 74311924.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 4.7956757068634035,
|
|
"epoch": 3.167957117331745,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004022950378669208,
|
|
"loss": 4.4141,
|
|
"mean_token_accuracy": 0.24427521526813506,
|
|
"num_tokens": 74323821.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 4.7925902843475345,
|
|
"epoch": 3.168552709946397,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00040225989836245064,
|
|
"loss": 4.4356,
|
|
"mean_token_accuracy": 0.2452546089887619,
|
|
"num_tokens": 74338663.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 4.8473108291625975,
|
|
"epoch": 3.169148302561048,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004022247542933749,
|
|
"loss": 4.4391,
|
|
"mean_token_accuracy": 0.23774108439683914,
|
|
"num_tokens": 74354272.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 4.8279317855834964,
|
|
"epoch": 3.1697438951756998,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000402189605660954,
|
|
"loss": 4.4736,
|
|
"mean_token_accuracy": 0.2371262639760971,
|
|
"num_tokens": 74367404.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 4.766849088668823,
|
|
"epoch": 3.1703394877903515,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00040215445246644875,
|
|
"loss": 4.3558,
|
|
"mean_token_accuracy": 0.25099803805351256,
|
|
"num_tokens": 74381276.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 4.724160146713257,
|
|
"epoch": 3.170935080405003,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004021192947111201,
|
|
"loss": 4.3193,
|
|
"mean_token_accuracy": 0.2479011595249176,
|
|
"num_tokens": 74396165.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 4.768697261810303,
|
|
"epoch": 3.1715306730196544,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00040208413239622894,
|
|
"loss": 4.4396,
|
|
"mean_token_accuracy": 0.23817020356655122,
|
|
"num_tokens": 74411015.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 4.788769006729126,
|
|
"epoch": 3.172126265634306,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004020489655230366,
|
|
"loss": 4.4562,
|
|
"mean_token_accuracy": 0.23357754200696945,
|
|
"num_tokens": 74428975.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 4.895149803161621,
|
|
"epoch": 3.172721858248958,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004020137940928045,
|
|
"loss": 4.544,
|
|
"mean_token_accuracy": 0.23614946007728577,
|
|
"num_tokens": 74444084.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 4.712932109832764,
|
|
"epoch": 3.1733174508636095,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004019786181067941,
|
|
"loss": 4.3731,
|
|
"mean_token_accuracy": 0.25660463571548464,
|
|
"num_tokens": 74458446.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 4.77857780456543,
|
|
"epoch": 3.1739130434782608,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040194343756626706,
|
|
"loss": 4.4301,
|
|
"mean_token_accuracy": 0.2393085777759552,
|
|
"num_tokens": 74470688.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 4.856967163085938,
|
|
"epoch": 3.1745086360929125,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00040190825247248544,
|
|
"loss": 4.3851,
|
|
"mean_token_accuracy": 0.2433802843093872,
|
|
"num_tokens": 74483545.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 4.774520683288574,
|
|
"epoch": 3.175104228707564,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000401873062826711,
|
|
"loss": 4.4158,
|
|
"mean_token_accuracy": 0.24518284052610398,
|
|
"num_tokens": 74497168.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 4.783432674407959,
|
|
"epoch": 3.1756998213222154,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00040183786863020617,
|
|
"loss": 4.2979,
|
|
"mean_token_accuracy": 0.24795016199350356,
|
|
"num_tokens": 74509618.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 4.796455192565918,
|
|
"epoch": 3.176295413936867,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040180266988423314,
|
|
"loss": 4.4379,
|
|
"mean_token_accuracy": 0.24132869094610215,
|
|
"num_tokens": 74523268.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 4.77773609161377,
|
|
"epoch": 3.176891006551519,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040176746659005455,
|
|
"loss": 4.332,
|
|
"mean_token_accuracy": 0.2512000069022179,
|
|
"num_tokens": 74538494.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 4.76536865234375,
|
|
"epoch": 3.1774865991661705,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040173225874893305,
|
|
"loss": 4.3989,
|
|
"mean_token_accuracy": 0.2453078031539917,
|
|
"num_tokens": 74551975.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 4.740021085739135,
|
|
"epoch": 3.1780821917808217,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040169704636213143,
|
|
"loss": 4.3661,
|
|
"mean_token_accuracy": 0.25148951411247256,
|
|
"num_tokens": 74566868.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 4.83974061012268,
|
|
"epoch": 3.1786777843954734,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00040166182943091283,
|
|
"loss": 4.5129,
|
|
"mean_token_accuracy": 0.2379620924592018,
|
|
"num_tokens": 74580253.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 4.768677616119385,
|
|
"epoch": 3.179273377010125,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00040162660795654034,
|
|
"loss": 4.3522,
|
|
"mean_token_accuracy": 0.24546058773994445,
|
|
"num_tokens": 74594779.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 4.801374864578247,
|
|
"epoch": 3.179868969624777,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004015913819402773,
|
|
"loss": 4.4571,
|
|
"mean_token_accuracy": 0.23712353855371476,
|
|
"num_tokens": 74609059.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 4.7472044944763185,
|
|
"epoch": 3.180464562239428,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004015561513833872,
|
|
"loss": 4.319,
|
|
"mean_token_accuracy": 0.25322634875774386,
|
|
"num_tokens": 74622349.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 4.8295738697052,
|
|
"epoch": 3.18106015485408,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004015209162871337,
|
|
"loss": 4.4669,
|
|
"mean_token_accuracy": 0.24600453525781632,
|
|
"num_tokens": 74638284.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 4.71922116279602,
|
|
"epoch": 3.1816557474687315,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00040148567665278066,
|
|
"loss": 4.3012,
|
|
"mean_token_accuracy": 0.25725394785404204,
|
|
"num_tokens": 74652782.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 4.7019366264343265,
|
|
"epoch": 3.182251340083383,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040145043248159207,
|
|
"loss": 4.3,
|
|
"mean_token_accuracy": 0.2513487711548805,
|
|
"num_tokens": 74664990.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 4.80848331451416,
|
|
"epoch": 3.1828469326980344,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004014151837748321,
|
|
"loss": 4.4798,
|
|
"mean_token_accuracy": 0.24054927378892899,
|
|
"num_tokens": 74678662.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 4.831474733352661,
|
|
"epoch": 3.183442525312686,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00040137993053376494,
|
|
"loss": 4.3764,
|
|
"mean_token_accuracy": 0.24494238197803497,
|
|
"num_tokens": 74694153.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 4.828972673416137,
|
|
"epoch": 3.184038117927338,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00040134467275965515,
|
|
"loss": 4.4422,
|
|
"mean_token_accuracy": 0.2443040281534195,
|
|
"num_tokens": 74708332.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 4.819380807876587,
|
|
"epoch": 3.184633710541989,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004013094104537674,
|
|
"loss": 4.499,
|
|
"mean_token_accuracy": 0.24005458652973174,
|
|
"num_tokens": 74721626.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 4.7566853046417235,
|
|
"epoch": 3.1852293031566408,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004012741436173665,
|
|
"loss": 4.3562,
|
|
"mean_token_accuracy": 0.24805827289819718,
|
|
"num_tokens": 74732495.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 4.731781959533691,
|
|
"epoch": 3.1858248957712925,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00040123887225171736,
|
|
"loss": 4.3464,
|
|
"mean_token_accuracy": 0.2548341989517212,
|
|
"num_tokens": 74745549.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 4.728405237197876,
|
|
"epoch": 3.186420488385944,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004012035963580851,
|
|
"loss": 4.2971,
|
|
"mean_token_accuracy": 0.25103411376476287,
|
|
"num_tokens": 74759234.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 4.779898357391358,
|
|
"epoch": 3.1870160810005954,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004011683159377351,
|
|
"loss": 4.341,
|
|
"mean_token_accuracy": 0.25112939178943633,
|
|
"num_tokens": 74772209.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 4.814994668960571,
|
|
"epoch": 3.187611673615247,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004011330309919326,
|
|
"loss": 4.4955,
|
|
"mean_token_accuracy": 0.23330143243074417,
|
|
"num_tokens": 74784706.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 4.794592714309692,
|
|
"epoch": 3.188207266229899,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004010977415219435,
|
|
"loss": 4.3768,
|
|
"mean_token_accuracy": 0.2467532128095627,
|
|
"num_tokens": 74800285.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 4.8407752990722654,
|
|
"epoch": 3.1888028588445505,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00040106244752903335,
|
|
"loss": 4.4758,
|
|
"mean_token_accuracy": 0.23497022241353988,
|
|
"num_tokens": 74814134.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 4.789500713348389,
|
|
"epoch": 3.1893984514592018,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040102714901446817,
|
|
"loss": 4.3789,
|
|
"mean_token_accuracy": 0.25215172618627546,
|
|
"num_tokens": 74827172.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 4.7873392581939695,
|
|
"epoch": 3.1899940440738535,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00040099184597951415,
|
|
"loss": 4.3859,
|
|
"mean_token_accuracy": 0.24558547139167786,
|
|
"num_tokens": 74841542.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 4.802748727798462,
|
|
"epoch": 3.190589636688505,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004009565384254374,
|
|
"loss": 4.4527,
|
|
"mean_token_accuracy": 0.24268403202295302,
|
|
"num_tokens": 74855073.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 4.786988687515259,
|
|
"epoch": 3.191185229303157,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004009212263535044,
|
|
"loss": 4.3992,
|
|
"mean_token_accuracy": 0.24067974984645843,
|
|
"num_tokens": 74870099.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 4.82413010597229,
|
|
"epoch": 3.191780821917808,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004008859097649818,
|
|
"loss": 4.5028,
|
|
"mean_token_accuracy": 0.23435718864202498,
|
|
"num_tokens": 74884062.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 4.7913172245025635,
|
|
"epoch": 3.19237641453246,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004008505886611363,
|
|
"loss": 4.3795,
|
|
"mean_token_accuracy": 0.24962908178567886,
|
|
"num_tokens": 74898006.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 4.74765419960022,
|
|
"epoch": 3.1929720071471115,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004008152630432347,
|
|
"loss": 4.2918,
|
|
"mean_token_accuracy": 0.2634320557117462,
|
|
"num_tokens": 74911565.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 4.706830930709839,
|
|
"epoch": 3.1935675997617627,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004007799329125443,
|
|
"loss": 4.3614,
|
|
"mean_token_accuracy": 0.24332184195518494,
|
|
"num_tokens": 74925739.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 4.872382402420044,
|
|
"epoch": 3.1941631923764144,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040074459827033217,
|
|
"loss": 4.5002,
|
|
"mean_token_accuracy": 0.23719798773527145,
|
|
"num_tokens": 74939707.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 4.801838684082031,
|
|
"epoch": 3.194758784991066,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00040070925911786563,
|
|
"loss": 4.4018,
|
|
"mean_token_accuracy": 0.2460734188556671,
|
|
"num_tokens": 74954203.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 4.723313856124878,
|
|
"epoch": 3.195354377605718,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004006739154564126,
|
|
"loss": 4.3345,
|
|
"mean_token_accuracy": 0.25267710238695146,
|
|
"num_tokens": 74967136.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 4.766589212417602,
|
|
"epoch": 3.195949970220369,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00040063856728724033,
|
|
"loss": 4.4003,
|
|
"mean_token_accuracy": 0.23849487751722337,
|
|
"num_tokens": 74980657.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 4.788396787643433,
|
|
"epoch": 3.196545562835021,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004006032146116171,
|
|
"loss": 4.3679,
|
|
"mean_token_accuracy": 0.24732696115970612,
|
|
"num_tokens": 74993468.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 4.8604209423065186,
|
|
"epoch": 3.1971411554496725,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00040056785743081065,
|
|
"loss": 4.4479,
|
|
"mean_token_accuracy": 0.2463352620601654,
|
|
"num_tokens": 75006080.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 4.885102224349976,
|
|
"epoch": 3.197736748064324,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040053249574608935,
|
|
"loss": 4.4807,
|
|
"mean_token_accuracy": 0.24271647334098817,
|
|
"num_tokens": 75020978.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 4.807696342468262,
|
|
"epoch": 3.1983323406789754,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004004971295587216,
|
|
"loss": 4.415,
|
|
"mean_token_accuracy": 0.24475907683372497,
|
|
"num_tokens": 75033856.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 4.800326871871948,
|
|
"epoch": 3.198927933293627,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040046175886997577,
|
|
"loss": 4.3689,
|
|
"mean_token_accuracy": 0.24848927855491637,
|
|
"num_tokens": 75047701.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 4.794340372085571,
|
|
"epoch": 3.199523525908279,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004004263836811207,
|
|
"loss": 4.4436,
|
|
"mean_token_accuracy": 0.23957352340221405,
|
|
"num_tokens": 75062788.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 4.786936330795288,
|
|
"epoch": 3.2001191185229305,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004003910039934251,
|
|
"loss": 4.405,
|
|
"mean_token_accuracy": 0.24844066351652144,
|
|
"num_tokens": 75076588.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 4.819677782058716,
|
|
"epoch": 3.2007147111375818,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040035561980815816,
|
|
"loss": 4.4627,
|
|
"mean_token_accuracy": 0.24008662551641463,
|
|
"num_tokens": 75090690.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 4.808405256271362,
|
|
"epoch": 3.2013103037522335,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004003202311265888,
|
|
"loss": 4.3975,
|
|
"mean_token_accuracy": 0.2414198026061058,
|
|
"num_tokens": 75103274.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 4.776411819458008,
|
|
"epoch": 3.201905896366885,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004002848379499866,
|
|
"loss": 4.4169,
|
|
"mean_token_accuracy": 0.24317652434110643,
|
|
"num_tokens": 75118840.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 4.781536340713501,
|
|
"epoch": 3.202501488981537,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00040024944027962107,
|
|
"loss": 4.393,
|
|
"mean_token_accuracy": 0.24510132968425752,
|
|
"num_tokens": 75133232.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 4.828862047195434,
|
|
"epoch": 3.203097081596188,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004002140381167616,
|
|
"loss": 4.3643,
|
|
"mean_token_accuracy": 0.24610244035720824,
|
|
"num_tokens": 75147093.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 4.77559871673584,
|
|
"epoch": 3.20369267421084,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004001786314626783,
|
|
"loss": 4.4517,
|
|
"mean_token_accuracy": 0.2423919141292572,
|
|
"num_tokens": 75162088.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 4.764816808700561,
|
|
"epoch": 3.2042882668254915,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00040014322031864093,
|
|
"loss": 4.431,
|
|
"mean_token_accuracy": 0.2425870791077614,
|
|
"num_tokens": 75175966.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 4.820158290863037,
|
|
"epoch": 3.2048838594401428,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00040010780468591975,
|
|
"loss": 4.3578,
|
|
"mean_token_accuracy": 0.2489571750164032,
|
|
"num_tokens": 75189043.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 4.802167797088623,
|
|
"epoch": 3.2054794520547945,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040007238456578494,
|
|
"loss": 4.3889,
|
|
"mean_token_accuracy": 0.24683135151863098,
|
|
"num_tokens": 75203105.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 4.733971452713012,
|
|
"epoch": 3.206075044669446,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040003695995950717,
|
|
"loss": 4.3861,
|
|
"mean_token_accuracy": 0.23920916616916657,
|
|
"num_tokens": 75217339.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 4.815876150131226,
|
|
"epoch": 3.206670637284098,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004000015308683569,
|
|
"loss": 4.4461,
|
|
"mean_token_accuracy": 0.24099307954311372,
|
|
"num_tokens": 75230070.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 4.912405109405517,
|
|
"epoch": 3.207266229898749,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039996609729360495,
|
|
"loss": 4.4736,
|
|
"mean_token_accuracy": 0.23108062744140626,
|
|
"num_tokens": 75244611.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 4.717987394332885,
|
|
"epoch": 3.207861822513401,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039993065923652225,
|
|
"loss": 4.3408,
|
|
"mean_token_accuracy": 0.24980918318033218,
|
|
"num_tokens": 75257441.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 4.76868839263916,
|
|
"epoch": 3.2084574151280525,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00039989521669838004,
|
|
"loss": 4.3968,
|
|
"mean_token_accuracy": 0.2511478677392006,
|
|
"num_tokens": 75270074.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 4.861645603179932,
|
|
"epoch": 3.209053007742704,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00039985976968044933,
|
|
"loss": 4.5061,
|
|
"mean_token_accuracy": 0.23216836303472518,
|
|
"num_tokens": 75284962.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 4.878103256225586,
|
|
"epoch": 3.2096486003573554,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003998243181840018,
|
|
"loss": 4.5117,
|
|
"mean_token_accuracy": 0.23571429252624512,
|
|
"num_tokens": 75298362.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 4.810457992553711,
|
|
"epoch": 3.210244192972007,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003997888622103088,
|
|
"loss": 4.4159,
|
|
"mean_token_accuracy": 0.24267754405736924,
|
|
"num_tokens": 75312065.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 4.760893487930298,
|
|
"epoch": 3.210839785586659,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039975340176064237,
|
|
"loss": 4.3148,
|
|
"mean_token_accuracy": 0.25809552520513535,
|
|
"num_tokens": 75324241.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 4.826664447784424,
|
|
"epoch": 3.21143537820131,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039971793683627415,
|
|
"loss": 4.5482,
|
|
"mean_token_accuracy": 0.2351380169391632,
|
|
"num_tokens": 75337415.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 4.822851133346558,
|
|
"epoch": 3.212030970815962,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003996824674384763,
|
|
"loss": 4.3947,
|
|
"mean_token_accuracy": 0.25125523954629897,
|
|
"num_tokens": 75348653.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 4.906450510025024,
|
|
"epoch": 3.2126265634306135,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039964699356852105,
|
|
"loss": 4.5245,
|
|
"mean_token_accuracy": 0.22850839495658876,
|
|
"num_tokens": 75363334.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 4.812639617919922,
|
|
"epoch": 3.213222156045265,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003996115152276809,
|
|
"loss": 4.4647,
|
|
"mean_token_accuracy": 0.23260796517133714,
|
|
"num_tokens": 75377705.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 4.801151752471924,
|
|
"epoch": 3.2138177486599164,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003995760324172283,
|
|
"loss": 4.3899,
|
|
"mean_token_accuracy": 0.2427133947610855,
|
|
"num_tokens": 75390778.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 4.901209497451783,
|
|
"epoch": 3.214413341274568,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039954054513843595,
|
|
"loss": 4.5545,
|
|
"mean_token_accuracy": 0.2330491617321968,
|
|
"num_tokens": 75405375.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 4.790399217605591,
|
|
"epoch": 3.21500893388922,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003995050533925767,
|
|
"loss": 4.3485,
|
|
"mean_token_accuracy": 0.24840985983610153,
|
|
"num_tokens": 75417862.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 4.756039667129516,
|
|
"epoch": 3.2156045265038715,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00039946955718092364,
|
|
"loss": 4.4111,
|
|
"mean_token_accuracy": 0.24612524211406708,
|
|
"num_tokens": 75432577.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 4.832269334793091,
|
|
"epoch": 3.2162001191185228,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039943405650474993,
|
|
"loss": 4.5785,
|
|
"mean_token_accuracy": 0.2335871160030365,
|
|
"num_tokens": 75447426.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 3.2162001191185228,
|
|
"eval_entropy": 4.637276862108595,
|
|
"eval_loss": 4.535953044891357,
|
|
"eval_mean_token_accuracy": 0.2452309182141455,
|
|
"eval_num_tokens": 75447426.0,
|
|
"eval_runtime": 24.3323,
|
|
"eval_samples_per_second": 1048.524,
|
|
"eval_steps_per_second": 131.101,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"entropy": 4.811846446990967,
|
|
"epoch": 3.2167957117331745,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003993985513653289,
|
|
"loss": 4.3477,
|
|
"mean_token_accuracy": 0.24567980766296388,
|
|
"num_tokens": 75462478.0,
|
|
"step": 27005
|
|
},
|
|
{
|
|
"entropy": 4.819065570831299,
|
|
"epoch": 3.217391304347826,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003993630417639341,
|
|
"loss": 4.404,
|
|
"mean_token_accuracy": 0.24605086594820022,
|
|
"num_tokens": 75477858.0,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"entropy": 4.791839551925659,
|
|
"epoch": 3.217986896962478,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00039932752770183925,
|
|
"loss": 4.4216,
|
|
"mean_token_accuracy": 0.24098063856363297,
|
|
"num_tokens": 75491004.0,
|
|
"step": 27015
|
|
},
|
|
{
|
|
"entropy": 4.767690753936767,
|
|
"epoch": 3.218582489577129,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003992920091803181,
|
|
"loss": 4.3661,
|
|
"mean_token_accuracy": 0.24923840612173082,
|
|
"num_tokens": 75505697.0,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"entropy": 4.8182210445404055,
|
|
"epoch": 3.219178082191781,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003992564862006447,
|
|
"loss": 4.4108,
|
|
"mean_token_accuracy": 0.2399127036333084,
|
|
"num_tokens": 75520025.0,
|
|
"step": 27025
|
|
},
|
|
{
|
|
"entropy": 4.81072678565979,
|
|
"epoch": 3.2197736748064325,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00039922095876409306,
|
|
"loss": 4.3807,
|
|
"mean_token_accuracy": 0.2374436751008034,
|
|
"num_tokens": 75533993.0,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"entropy": 4.715099573135376,
|
|
"epoch": 3.220369267421084,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003991854268719377,
|
|
"loss": 4.3399,
|
|
"mean_token_accuracy": 0.24526996463537215,
|
|
"num_tokens": 75547542.0,
|
|
"step": 27035
|
|
},
|
|
{
|
|
"entropy": 4.712669610977173,
|
|
"epoch": 3.2209648600357355,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000399149890525453,
|
|
"loss": 4.3244,
|
|
"mean_token_accuracy": 0.2545383170247078,
|
|
"num_tokens": 75561215.0,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"entropy": 4.792141103744507,
|
|
"epoch": 3.221560452650387,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003991143497259135,
|
|
"loss": 4.3991,
|
|
"mean_token_accuracy": 0.2488876014947891,
|
|
"num_tokens": 75574663.0,
|
|
"step": 27045
|
|
},
|
|
{
|
|
"entropy": 4.779953336715698,
|
|
"epoch": 3.222156045265039,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003990788044745942,
|
|
"loss": 4.4588,
|
|
"mean_token_accuracy": 0.24579974561929702,
|
|
"num_tokens": 75590147.0,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"entropy": 4.799285411834717,
|
|
"epoch": 3.22275163787969,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039904325477276974,
|
|
"loss": 4.3997,
|
|
"mean_token_accuracy": 0.24036941826343536,
|
|
"num_tokens": 75604057.0,
|
|
"step": 27055
|
|
},
|
|
{
|
|
"entropy": 4.8388313293457035,
|
|
"epoch": 3.223347230494342,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003990077006217155,
|
|
"loss": 4.4659,
|
|
"mean_token_accuracy": 0.24425426870584488,
|
|
"num_tokens": 75620067.0,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"entropy": 4.7833295345306395,
|
|
"epoch": 3.2239428231089935,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039897214202270673,
|
|
"loss": 4.3864,
|
|
"mean_token_accuracy": 0.24305396229028703,
|
|
"num_tokens": 75635727.0,
|
|
"step": 27065
|
|
},
|
|
{
|
|
"entropy": 4.778629541397095,
|
|
"epoch": 3.224538415723645,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039893657897701874,
|
|
"loss": 4.4206,
|
|
"mean_token_accuracy": 0.24177156537771224,
|
|
"num_tokens": 75649439.0,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"entropy": 4.768835639953613,
|
|
"epoch": 3.2251340083382964,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003989010114859272,
|
|
"loss": 4.4129,
|
|
"mean_token_accuracy": 0.2374583974480629,
|
|
"num_tokens": 75663390.0,
|
|
"step": 27075
|
|
},
|
|
{
|
|
"entropy": 4.785227680206299,
|
|
"epoch": 3.225729600952948,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039886543955070777,
|
|
"loss": 4.3998,
|
|
"mean_token_accuracy": 0.24189561754465103,
|
|
"num_tokens": 75676841.0,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"entropy": 4.82302451133728,
|
|
"epoch": 3.2263251935676,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003988298631726364,
|
|
"loss": 4.429,
|
|
"mean_token_accuracy": 0.2390461966395378,
|
|
"num_tokens": 75688495.0,
|
|
"step": 27085
|
|
},
|
|
{
|
|
"entropy": 4.7729745388031,
|
|
"epoch": 3.2269207861822515,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039879428235298925,
|
|
"loss": 4.4327,
|
|
"mean_token_accuracy": 0.24132136404514312,
|
|
"num_tokens": 75701819.0,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"entropy": 4.841038656234741,
|
|
"epoch": 3.227516378796903,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003987586970930424,
|
|
"loss": 4.5163,
|
|
"mean_token_accuracy": 0.2327706277370453,
|
|
"num_tokens": 75717101.0,
|
|
"step": 27095
|
|
},
|
|
{
|
|
"entropy": 4.726523923873901,
|
|
"epoch": 3.2281119714115545,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003987231073940723,
|
|
"loss": 4.3464,
|
|
"mean_token_accuracy": 0.24611611366271974,
|
|
"num_tokens": 75730141.0,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"entropy": 4.77917070388794,
|
|
"epoch": 3.228707564026206,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039868751325735556,
|
|
"loss": 4.3444,
|
|
"mean_token_accuracy": 0.2457400903105736,
|
|
"num_tokens": 75742459.0,
|
|
"step": 27105
|
|
},
|
|
{
|
|
"entropy": 4.9138795852661135,
|
|
"epoch": 3.2293031566408574,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003986519146841688,
|
|
"loss": 4.5106,
|
|
"mean_token_accuracy": 0.23099563270807266,
|
|
"num_tokens": 75756540.0,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"entropy": 4.788793754577637,
|
|
"epoch": 3.229898749255509,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000398616311675789,
|
|
"loss": 4.3568,
|
|
"mean_token_accuracy": 0.2490071177482605,
|
|
"num_tokens": 75770539.0,
|
|
"step": 27115
|
|
},
|
|
{
|
|
"entropy": 4.771249771118164,
|
|
"epoch": 3.230494341870161,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039858070423349297,
|
|
"loss": 4.3476,
|
|
"mean_token_accuracy": 0.24507185965776443,
|
|
"num_tokens": 75784308.0,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"entropy": 4.803853702545166,
|
|
"epoch": 3.2310899344848125,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039854509235855796,
|
|
"loss": 4.4026,
|
|
"mean_token_accuracy": 0.23840539455413817,
|
|
"num_tokens": 75798667.0,
|
|
"step": 27125
|
|
},
|
|
{
|
|
"entropy": 4.765840625762939,
|
|
"epoch": 3.2316855270994638,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003985094760522615,
|
|
"loss": 4.3942,
|
|
"mean_token_accuracy": 0.24766535609960555,
|
|
"num_tokens": 75812558.0,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"entropy": 4.780012369155884,
|
|
"epoch": 3.2322811197141155,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003984738553158809,
|
|
"loss": 4.4036,
|
|
"mean_token_accuracy": 0.24365389496088027,
|
|
"num_tokens": 75826517.0,
|
|
"step": 27135
|
|
},
|
|
{
|
|
"entropy": 4.71675705909729,
|
|
"epoch": 3.232876712328767,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003984382301506938,
|
|
"loss": 4.3565,
|
|
"mean_token_accuracy": 0.2481377214193344,
|
|
"num_tokens": 75840130.0,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"entropy": 4.774567461013794,
|
|
"epoch": 3.233472304943419,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003984026005579781,
|
|
"loss": 4.4071,
|
|
"mean_token_accuracy": 0.24315330237150193,
|
|
"num_tokens": 75855003.0,
|
|
"step": 27145
|
|
},
|
|
{
|
|
"entropy": 4.70528998374939,
|
|
"epoch": 3.23406789755807,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003983669665390119,
|
|
"loss": 4.2872,
|
|
"mean_token_accuracy": 0.2554970756173134,
|
|
"num_tokens": 75867775.0,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"entropy": 4.750558710098266,
|
|
"epoch": 3.234663490172722,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039833132809507306,
|
|
"loss": 4.3438,
|
|
"mean_token_accuracy": 0.2496063381433487,
|
|
"num_tokens": 75880996.0,
|
|
"step": 27155
|
|
},
|
|
{
|
|
"entropy": 4.80389289855957,
|
|
"epoch": 3.2352590827873735,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039829568522743996,
|
|
"loss": 4.453,
|
|
"mean_token_accuracy": 0.23665947318077088,
|
|
"num_tokens": 75896616.0,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"entropy": 4.802896022796631,
|
|
"epoch": 3.235854675402025,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003982600379373912,
|
|
"loss": 4.4274,
|
|
"mean_token_accuracy": 0.2354734256863594,
|
|
"num_tokens": 75910086.0,
|
|
"step": 27165
|
|
},
|
|
{
|
|
"entropy": 4.866618537902832,
|
|
"epoch": 3.2364502680166765,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00039822438622620523,
|
|
"loss": 4.5484,
|
|
"mean_token_accuracy": 0.24115811735391618,
|
|
"num_tokens": 75927862.0,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"entropy": 4.842593574523926,
|
|
"epoch": 3.237045860631328,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003981887300951609,
|
|
"loss": 4.3736,
|
|
"mean_token_accuracy": 0.24625469744205475,
|
|
"num_tokens": 75940838.0,
|
|
"step": 27175
|
|
},
|
|
{
|
|
"entropy": 4.777021265029907,
|
|
"epoch": 3.23764145324598,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003981530695455371,
|
|
"loss": 4.399,
|
|
"mean_token_accuracy": 0.24128179401159286,
|
|
"num_tokens": 75954894.0,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"entropy": 4.727947521209717,
|
|
"epoch": 3.2382370458606315,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039811740457861293,
|
|
"loss": 4.3158,
|
|
"mean_token_accuracy": 0.2501344606280327,
|
|
"num_tokens": 75968260.0,
|
|
"step": 27185
|
|
},
|
|
{
|
|
"entropy": 4.759710693359375,
|
|
"epoch": 3.238832638475283,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003980817351956677,
|
|
"loss": 4.3583,
|
|
"mean_token_accuracy": 0.24689568281173707,
|
|
"num_tokens": 75982056.0,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"entropy": 4.833860588073731,
|
|
"epoch": 3.2394282310899345,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003980460613979807,
|
|
"loss": 4.4366,
|
|
"mean_token_accuracy": 0.24628275781869888,
|
|
"num_tokens": 75995754.0,
|
|
"step": 27195
|
|
},
|
|
{
|
|
"entropy": 4.797625160217285,
|
|
"epoch": 3.240023823704586,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039801038318683146,
|
|
"loss": 4.3695,
|
|
"mean_token_accuracy": 0.2396948292851448,
|
|
"num_tokens": 76011275.0,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"entropy": 4.8136513233184814,
|
|
"epoch": 3.2406194163192374,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003979747005634999,
|
|
"loss": 4.4647,
|
|
"mean_token_accuracy": 0.23449814170598984,
|
|
"num_tokens": 76027282.0,
|
|
"step": 27205
|
|
},
|
|
{
|
|
"entropy": 4.847075510025024,
|
|
"epoch": 3.241215008933889,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00039793901352926575,
|
|
"loss": 4.459,
|
|
"mean_token_accuracy": 0.2458688050508499,
|
|
"num_tokens": 76041357.0,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"entropy": 4.82609338760376,
|
|
"epoch": 3.241810601548541,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003979033220854091,
|
|
"loss": 4.444,
|
|
"mean_token_accuracy": 0.23747084587812423,
|
|
"num_tokens": 76057221.0,
|
|
"step": 27215
|
|
},
|
|
{
|
|
"entropy": 4.844176197052002,
|
|
"epoch": 3.2424061941631925,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039786762623320997,
|
|
"loss": 4.4031,
|
|
"mean_token_accuracy": 0.2475363165140152,
|
|
"num_tokens": 76072788.0,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"entropy": 4.7519653797149655,
|
|
"epoch": 3.243001786777844,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039783192597394896,
|
|
"loss": 4.3642,
|
|
"mean_token_accuracy": 0.24701293855905532,
|
|
"num_tokens": 76086637.0,
|
|
"step": 27225
|
|
},
|
|
{
|
|
"entropy": 4.738126182556153,
|
|
"epoch": 3.2435973793924955,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039779622130890654,
|
|
"loss": 4.378,
|
|
"mean_token_accuracy": 0.25040633976459503,
|
|
"num_tokens": 76101365.0,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"entropy": 4.79525580406189,
|
|
"epoch": 3.244192972007147,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003977605122393632,
|
|
"loss": 4.4074,
|
|
"mean_token_accuracy": 0.23509694188833236,
|
|
"num_tokens": 76115494.0,
|
|
"step": 27235
|
|
},
|
|
{
|
|
"entropy": 4.721333074569702,
|
|
"epoch": 3.244788564621799,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003977247987665999,
|
|
"loss": 4.3461,
|
|
"mean_token_accuracy": 0.24988879710435868,
|
|
"num_tokens": 76128416.0,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"entropy": 4.890631771087646,
|
|
"epoch": 3.24538415723645,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003976890808918977,
|
|
"loss": 4.5088,
|
|
"mean_token_accuracy": 0.23808084279298783,
|
|
"num_tokens": 76143870.0,
|
|
"step": 27245
|
|
},
|
|
{
|
|
"entropy": 4.784595966339111,
|
|
"epoch": 3.245979749851102,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039765335861653754,
|
|
"loss": 4.3612,
|
|
"mean_token_accuracy": 0.24190136194229125,
|
|
"num_tokens": 76156415.0,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"entropy": 4.7457287311553955,
|
|
"epoch": 3.2465753424657535,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003976176319418009,
|
|
"loss": 4.4073,
|
|
"mean_token_accuracy": 0.24545470923185347,
|
|
"num_tokens": 76170221.0,
|
|
"step": 27255
|
|
},
|
|
{
|
|
"entropy": 4.829724311828613,
|
|
"epoch": 3.2471709350804048,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0003975819008689691,
|
|
"loss": 4.4462,
|
|
"mean_token_accuracy": 0.23850863724946975,
|
|
"num_tokens": 76186110.0,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"entropy": 4.803352642059326,
|
|
"epoch": 3.2477665276950565,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039754616539932393,
|
|
"loss": 4.4003,
|
|
"mean_token_accuracy": 0.2457006797194481,
|
|
"num_tokens": 76198843.0,
|
|
"step": 27265
|
|
},
|
|
{
|
|
"entropy": 4.854246282577515,
|
|
"epoch": 3.248362120309708,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00039751042553414694,
|
|
"loss": 4.5411,
|
|
"mean_token_accuracy": 0.23379499316215516,
|
|
"num_tokens": 76214056.0,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"entropy": 4.713864469528199,
|
|
"epoch": 3.24895771292436,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00039747468127472027,
|
|
"loss": 4.2967,
|
|
"mean_token_accuracy": 0.25732828825712206,
|
|
"num_tokens": 76228356.0,
|
|
"step": 27275
|
|
},
|
|
{
|
|
"entropy": 4.766296911239624,
|
|
"epoch": 3.249553305539011,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00039743893262232584,
|
|
"loss": 4.3693,
|
|
"mean_token_accuracy": 0.24628807753324508,
|
|
"num_tokens": 76242931.0,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"entropy": 4.775691032409668,
|
|
"epoch": 3.250148898153663,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039740317957824594,
|
|
"loss": 4.3281,
|
|
"mean_token_accuracy": 0.25171963423490523,
|
|
"num_tokens": 76255606.0,
|
|
"step": 27285
|
|
},
|
|
{
|
|
"entropy": 4.832009363174438,
|
|
"epoch": 3.2507444907683145,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039736742214376307,
|
|
"loss": 4.4142,
|
|
"mean_token_accuracy": 0.24484586864709854,
|
|
"num_tokens": 76269710.0,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"entropy": 4.917598581314087,
|
|
"epoch": 3.251340083382966,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003973316603201597,
|
|
"loss": 4.5292,
|
|
"mean_token_accuracy": 0.23257055580615998,
|
|
"num_tokens": 76282949.0,
|
|
"step": 27295
|
|
},
|
|
{
|
|
"entropy": 4.7875267505645756,
|
|
"epoch": 3.2519356759976175,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00039729589410871863,
|
|
"loss": 4.4715,
|
|
"mean_token_accuracy": 0.24001107662916182,
|
|
"num_tokens": 76298920.0,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"entropy": 4.864583110809326,
|
|
"epoch": 3.252531268612269,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003972601235107227,
|
|
"loss": 4.479,
|
|
"mean_token_accuracy": 0.23742151856422425,
|
|
"num_tokens": 76311899.0,
|
|
"step": 27305
|
|
},
|
|
{
|
|
"entropy": 4.919225454330444,
|
|
"epoch": 3.253126861226921,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003972243485274548,
|
|
"loss": 4.5163,
|
|
"mean_token_accuracy": 0.2367126688361168,
|
|
"num_tokens": 76325005.0,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"entropy": 4.848777103424072,
|
|
"epoch": 3.2537224538415725,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0003971885691601983,
|
|
"loss": 4.4691,
|
|
"mean_token_accuracy": 0.24405380487442016,
|
|
"num_tokens": 76340356.0,
|
|
"step": 27315
|
|
},
|
|
{
|
|
"entropy": 4.8180407047271725,
|
|
"epoch": 3.254318046456224,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003971527854102364,
|
|
"loss": 4.4839,
|
|
"mean_token_accuracy": 0.23421872705221175,
|
|
"num_tokens": 76354160.0,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"entropy": 4.78513240814209,
|
|
"epoch": 3.2549136390708755,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00039711699727885285,
|
|
"loss": 4.3644,
|
|
"mean_token_accuracy": 0.2442072093486786,
|
|
"num_tokens": 76369496.0,
|
|
"step": 27325
|
|
},
|
|
{
|
|
"entropy": 4.784386730194091,
|
|
"epoch": 3.255509231685527,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003970812047673311,
|
|
"loss": 4.4258,
|
|
"mean_token_accuracy": 0.23440870642662048,
|
|
"num_tokens": 76382392.0,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"entropy": 4.84304838180542,
|
|
"epoch": 3.256104824300179,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003970454078769551,
|
|
"loss": 4.451,
|
|
"mean_token_accuracy": 0.24053931683301927,
|
|
"num_tokens": 76394626.0,
|
|
"step": 27335
|
|
},
|
|
{
|
|
"entropy": 4.857585287094116,
|
|
"epoch": 3.25670041691483,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039700960660900866,
|
|
"loss": 4.4719,
|
|
"mean_token_accuracy": 0.2331557720899582,
|
|
"num_tokens": 76408604.0,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"entropy": 4.8169862747192385,
|
|
"epoch": 3.257296009529482,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039697380096477596,
|
|
"loss": 4.4084,
|
|
"mean_token_accuracy": 0.24293068200349807,
|
|
"num_tokens": 76422223.0,
|
|
"step": 27345
|
|
},
|
|
{
|
|
"entropy": 4.911411428451538,
|
|
"epoch": 3.2578916021441335,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003969379909455414,
|
|
"loss": 4.5438,
|
|
"mean_token_accuracy": 0.22707614451646804,
|
|
"num_tokens": 76437675.0,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"entropy": 4.800325918197632,
|
|
"epoch": 3.258487194758785,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003969021765525894,
|
|
"loss": 4.4092,
|
|
"mean_token_accuracy": 0.238892038166523,
|
|
"num_tokens": 76451993.0,
|
|
"step": 27355
|
|
},
|
|
{
|
|
"entropy": 4.815458869934082,
|
|
"epoch": 3.2590827873734365,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003968663577872045,
|
|
"loss": 4.4043,
|
|
"mean_token_accuracy": 0.24650684595108033,
|
|
"num_tokens": 76464802.0,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"entropy": 4.887442970275879,
|
|
"epoch": 3.259678379988088,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003968305346506715,
|
|
"loss": 4.4424,
|
|
"mean_token_accuracy": 0.24812009930610657,
|
|
"num_tokens": 76479415.0,
|
|
"step": 27365
|
|
},
|
|
{
|
|
"entropy": 4.839797687530518,
|
|
"epoch": 3.26027397260274,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003967947071442753,
|
|
"loss": 4.4451,
|
|
"mean_token_accuracy": 0.24670174419879914,
|
|
"num_tokens": 76491988.0,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"entropy": 4.816315221786499,
|
|
"epoch": 3.260869565217391,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003967588752693009,
|
|
"loss": 4.4618,
|
|
"mean_token_accuracy": 0.24010412395000458,
|
|
"num_tokens": 76504733.0,
|
|
"step": 27375
|
|
},
|
|
{
|
|
"entropy": 4.83035101890564,
|
|
"epoch": 3.261465157832043,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039672303902703364,
|
|
"loss": 4.3622,
|
|
"mean_token_accuracy": 0.24576579332351683,
|
|
"num_tokens": 76517105.0,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"entropy": 4.724043941497802,
|
|
"epoch": 3.2620607504466945,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039668719841875897,
|
|
"loss": 4.3748,
|
|
"mean_token_accuracy": 0.24554055780172349,
|
|
"num_tokens": 76531574.0,
|
|
"step": 27385
|
|
},
|
|
{
|
|
"entropy": 4.813114595413208,
|
|
"epoch": 3.262656343061346,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003966513534457623,
|
|
"loss": 4.4726,
|
|
"mean_token_accuracy": 0.24193414002656938,
|
|
"num_tokens": 76545788.0,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"entropy": 4.795320081710815,
|
|
"epoch": 3.2632519356759975,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003966155041093293,
|
|
"loss": 4.3823,
|
|
"mean_token_accuracy": 0.2515417903661728,
|
|
"num_tokens": 76557831.0,
|
|
"step": 27395
|
|
},
|
|
{
|
|
"entropy": 4.865707588195801,
|
|
"epoch": 3.263847528290649,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003965796504107461,
|
|
"loss": 4.5329,
|
|
"mean_token_accuracy": 0.23052601367235184,
|
|
"num_tokens": 76572924.0,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"entropy": 4.775178003311157,
|
|
"epoch": 3.264443120905301,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039654379235129836,
|
|
"loss": 4.4092,
|
|
"mean_token_accuracy": 0.2516855627298355,
|
|
"num_tokens": 76586886.0,
|
|
"step": 27405
|
|
},
|
|
{
|
|
"entropy": 4.8676094055175785,
|
|
"epoch": 3.265038713519952,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039650792993227245,
|
|
"loss": 4.4497,
|
|
"mean_token_accuracy": 0.2409730762243271,
|
|
"num_tokens": 76600358.0,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"entropy": 4.791094875335693,
|
|
"epoch": 3.265634306134604,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0003964720631549546,
|
|
"loss": 4.4211,
|
|
"mean_token_accuracy": 0.24240022599697114,
|
|
"num_tokens": 76616393.0,
|
|
"step": 27415
|
|
},
|
|
{
|
|
"entropy": 4.876320266723633,
|
|
"epoch": 3.2662298987492555,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003964361920206314,
|
|
"loss": 4.5358,
|
|
"mean_token_accuracy": 0.23116963654756545,
|
|
"num_tokens": 76630801.0,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"entropy": 4.834768533706665,
|
|
"epoch": 3.266825491363907,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003964003165305894,
|
|
"loss": 4.4692,
|
|
"mean_token_accuracy": 0.2360829383134842,
|
|
"num_tokens": 76643529.0,
|
|
"step": 27425
|
|
},
|
|
{
|
|
"entropy": 4.766444730758667,
|
|
"epoch": 3.267421083978559,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003963644366861155,
|
|
"loss": 4.3311,
|
|
"mean_token_accuracy": 0.2544193401932716,
|
|
"num_tokens": 76656383.0,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"entropy": 4.750172138214111,
|
|
"epoch": 3.26801667659321,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003963285524884964,
|
|
"loss": 4.4293,
|
|
"mean_token_accuracy": 0.24126146733760834,
|
|
"num_tokens": 76670262.0,
|
|
"step": 27435
|
|
},
|
|
{
|
|
"entropy": 4.833969306945801,
|
|
"epoch": 3.268612269207862,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0003962926639390196,
|
|
"loss": 4.377,
|
|
"mean_token_accuracy": 0.24555676132440568,
|
|
"num_tokens": 76686122.0,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"entropy": 4.781801986694336,
|
|
"epoch": 3.2692078618225136,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003962567710389721,
|
|
"loss": 4.4065,
|
|
"mean_token_accuracy": 0.24672878980636598,
|
|
"num_tokens": 76701044.0,
|
|
"step": 27445
|
|
},
|
|
{
|
|
"entropy": 4.8043128490448,
|
|
"epoch": 3.269803454437165,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003962208737896413,
|
|
"loss": 4.4756,
|
|
"mean_token_accuracy": 0.23439310789108275,
|
|
"num_tokens": 76714988.0,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"entropy": 4.859891748428344,
|
|
"epoch": 3.2703990470518165,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039618497219231493,
|
|
"loss": 4.4458,
|
|
"mean_token_accuracy": 0.24456772357225418,
|
|
"num_tokens": 76728913.0,
|
|
"step": 27455
|
|
},
|
|
{
|
|
"entropy": 4.799283409118653,
|
|
"epoch": 3.270994639666468,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003961490662482806,
|
|
"loss": 4.3647,
|
|
"mean_token_accuracy": 0.2446931317448616,
|
|
"num_tokens": 76742572.0,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"entropy": 4.8599649429321286,
|
|
"epoch": 3.27159023228112,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003961131559588263,
|
|
"loss": 4.4661,
|
|
"mean_token_accuracy": 0.24529721438884736,
|
|
"num_tokens": 76756937.0,
|
|
"step": 27465
|
|
},
|
|
{
|
|
"entropy": 4.8040422916412355,
|
|
"epoch": 3.272185824895771,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003960772413252399,
|
|
"loss": 4.4,
|
|
"mean_token_accuracy": 0.2442041665315628,
|
|
"num_tokens": 76770370.0,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"entropy": 4.718371248245239,
|
|
"epoch": 3.272781417510423,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039604132234880983,
|
|
"loss": 4.3698,
|
|
"mean_token_accuracy": 0.24325748085975646,
|
|
"num_tokens": 76785258.0,
|
|
"step": 27475
|
|
},
|
|
{
|
|
"entropy": 4.870261096954346,
|
|
"epoch": 3.2733770101250745,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003960053990308243,
|
|
"loss": 4.4777,
|
|
"mean_token_accuracy": 0.23787967264652252,
|
|
"num_tokens": 76798888.0,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"entropy": 4.807393550872803,
|
|
"epoch": 3.2739726027397262,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039596947137257176,
|
|
"loss": 4.4464,
|
|
"mean_token_accuracy": 0.24075632989406587,
|
|
"num_tokens": 76814766.0,
|
|
"step": 27485
|
|
},
|
|
{
|
|
"entropy": 4.77958869934082,
|
|
"epoch": 3.2745681953543775,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003959335393753411,
|
|
"loss": 4.3477,
|
|
"mean_token_accuracy": 0.2511876091361046,
|
|
"num_tokens": 76828774.0,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"entropy": 4.820512199401856,
|
|
"epoch": 3.275163787969029,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003958976030404209,
|
|
"loss": 4.3852,
|
|
"mean_token_accuracy": 0.24229866713285447,
|
|
"num_tokens": 76842126.0,
|
|
"step": 27495
|
|
},
|
|
{
|
|
"entropy": 4.779028129577637,
|
|
"epoch": 3.275759380583681,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00039586166236910033,
|
|
"loss": 4.4234,
|
|
"mean_token_accuracy": 0.24315306097269057,
|
|
"num_tokens": 76857259.0,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"entropy": 4.73783540725708,
|
|
"epoch": 3.276354973198332,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003958257173626684,
|
|
"loss": 4.3359,
|
|
"mean_token_accuracy": 0.25508349388837814,
|
|
"num_tokens": 76871911.0,
|
|
"step": 27505
|
|
},
|
|
{
|
|
"entropy": 4.815384244918823,
|
|
"epoch": 3.276950565812984,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003957897680224144,
|
|
"loss": 4.4695,
|
|
"mean_token_accuracy": 0.24028127640485764,
|
|
"num_tokens": 76887001.0,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"entropy": 4.706722640991211,
|
|
"epoch": 3.2775461584276355,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039575381434962787,
|
|
"loss": 4.2421,
|
|
"mean_token_accuracy": 0.2561696022748947,
|
|
"num_tokens": 76899023.0,
|
|
"step": 27515
|
|
},
|
|
{
|
|
"entropy": 4.663913011550903,
|
|
"epoch": 3.278141751042287,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003957178563455983,
|
|
"loss": 4.3226,
|
|
"mean_token_accuracy": 0.2528246119618416,
|
|
"num_tokens": 76912438.0,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"entropy": 4.80587100982666,
|
|
"epoch": 3.2787373436569385,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003956818940116156,
|
|
"loss": 4.4561,
|
|
"mean_token_accuracy": 0.2434142753481865,
|
|
"num_tokens": 76926676.0,
|
|
"step": 27525
|
|
},
|
|
{
|
|
"entropy": 4.922595119476318,
|
|
"epoch": 3.27933293627159,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039564592734896945,
|
|
"loss": 4.559,
|
|
"mean_token_accuracy": 0.23856603503227233,
|
|
"num_tokens": 76939728.0,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"entropy": 4.847328138351441,
|
|
"epoch": 3.279928528886242,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003956099563589501,
|
|
"loss": 4.4356,
|
|
"mean_token_accuracy": 0.2447243869304657,
|
|
"num_tokens": 76956121.0,
|
|
"step": 27535
|
|
},
|
|
{
|
|
"entropy": 4.765075588226319,
|
|
"epoch": 3.2805241215008936,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003955739810428477,
|
|
"loss": 4.3847,
|
|
"mean_token_accuracy": 0.24750241488218308,
|
|
"num_tokens": 76969779.0,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"entropy": 4.788105154037476,
|
|
"epoch": 3.281119714115545,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00039553800140195274,
|
|
"loss": 4.4094,
|
|
"mean_token_accuracy": 0.2444858133792877,
|
|
"num_tokens": 76985213.0,
|
|
"step": 27545
|
|
},
|
|
{
|
|
"entropy": 4.802383279800415,
|
|
"epoch": 3.2817153067301965,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039550201743755557,
|
|
"loss": 4.453,
|
|
"mean_token_accuracy": 0.240109121799469,
|
|
"num_tokens": 76998897.0,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"entropy": 4.8901081562042235,
|
|
"epoch": 3.282310899344848,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003954660291509469,
|
|
"loss": 4.5323,
|
|
"mean_token_accuracy": 0.23071039319038392,
|
|
"num_tokens": 77012586.0,
|
|
"step": 27555
|
|
},
|
|
{
|
|
"entropy": 4.759751987457276,
|
|
"epoch": 3.2829064919594995,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039543003654341776,
|
|
"loss": 4.3512,
|
|
"mean_token_accuracy": 0.24578938335180284,
|
|
"num_tokens": 77025765.0,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"entropy": 4.8139890193939205,
|
|
"epoch": 3.283502084574151,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003953940396162589,
|
|
"loss": 4.4652,
|
|
"mean_token_accuracy": 0.23975898176431656,
|
|
"num_tokens": 77039477.0,
|
|
"step": 27565
|
|
},
|
|
{
|
|
"entropy": 4.869364166259766,
|
|
"epoch": 3.284097677188803,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039535803837076165,
|
|
"loss": 4.4749,
|
|
"mean_token_accuracy": 0.24137533754110335,
|
|
"num_tokens": 77053775.0,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"entropy": 4.817768859863281,
|
|
"epoch": 3.2846932698034546,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003953220328082172,
|
|
"loss": 4.4189,
|
|
"mean_token_accuracy": 0.23905895352363588,
|
|
"num_tokens": 77067467.0,
|
|
"step": 27575
|
|
},
|
|
{
|
|
"entropy": 4.752848482131958,
|
|
"epoch": 3.2852888624181062,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039528602292991714,
|
|
"loss": 4.3745,
|
|
"mean_token_accuracy": 0.24679242819547653,
|
|
"num_tokens": 77082027.0,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"entropy": 4.867218017578125,
|
|
"epoch": 3.2858844550327575,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000395250008737153,
|
|
"loss": 4.5586,
|
|
"mean_token_accuracy": 0.23166582584381104,
|
|
"num_tokens": 77097378.0,
|
|
"step": 27585
|
|
},
|
|
{
|
|
"entropy": 4.913396167755127,
|
|
"epoch": 3.286480047647409,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003952139902312165,
|
|
"loss": 4.4627,
|
|
"mean_token_accuracy": 0.24153247028589248,
|
|
"num_tokens": 77109608.0,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"entropy": 4.850388813018799,
|
|
"epoch": 3.287075640262061,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003951779674133997,
|
|
"loss": 4.5098,
|
|
"mean_token_accuracy": 0.23419881314039231,
|
|
"num_tokens": 77123926.0,
|
|
"step": 27595
|
|
},
|
|
{
|
|
"entropy": 4.849264097213745,
|
|
"epoch": 3.287671232876712,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039514194028499456,
|
|
"loss": 4.4679,
|
|
"mean_token_accuracy": 0.23584048300981522,
|
|
"num_tokens": 77138741.0,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"entropy": 4.773609352111817,
|
|
"epoch": 3.288266825491364,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003951059088472934,
|
|
"loss": 4.3766,
|
|
"mean_token_accuracy": 0.24551291465759278,
|
|
"num_tokens": 77152594.0,
|
|
"step": 27605
|
|
},
|
|
{
|
|
"entropy": 4.781574058532715,
|
|
"epoch": 3.2888624181060155,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039506987310158854,
|
|
"loss": 4.4167,
|
|
"mean_token_accuracy": 0.24749124497175218,
|
|
"num_tokens": 77166290.0,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"entropy": 4.809708166122436,
|
|
"epoch": 3.2894580107206672,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039503383304917254,
|
|
"loss": 4.4077,
|
|
"mean_token_accuracy": 0.2386385589838028,
|
|
"num_tokens": 77179481.0,
|
|
"step": 27615
|
|
},
|
|
{
|
|
"entropy": 4.8632269382476805,
|
|
"epoch": 3.2900536033353185,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003949977886913381,
|
|
"loss": 4.4515,
|
|
"mean_token_accuracy": 0.23713550120592117,
|
|
"num_tokens": 77194508.0,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"entropy": 4.819608116149903,
|
|
"epoch": 3.29064919594997,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00039496174002937815,
|
|
"loss": 4.3678,
|
|
"mean_token_accuracy": 0.24671152979135513,
|
|
"num_tokens": 77207411.0,
|
|
"step": 27625
|
|
},
|
|
{
|
|
"entropy": 4.7510138034820555,
|
|
"epoch": 3.291244788564622,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003949256870645856,
|
|
"loss": 4.3617,
|
|
"mean_token_accuracy": 0.24532709866762162,
|
|
"num_tokens": 77221406.0,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"entropy": 4.8863249778747555,
|
|
"epoch": 3.2918403811792736,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003948896297982536,
|
|
"loss": 4.468,
|
|
"mean_token_accuracy": 0.23510740995407103,
|
|
"num_tokens": 77236600.0,
|
|
"step": 27635
|
|
},
|
|
{
|
|
"entropy": 4.79335618019104,
|
|
"epoch": 3.292435973793925,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003948535682316755,
|
|
"loss": 4.4669,
|
|
"mean_token_accuracy": 0.24397406578063965,
|
|
"num_tokens": 77252342.0,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"entropy": 4.817800140380859,
|
|
"epoch": 3.2930315664085765,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003948175023661449,
|
|
"loss": 4.466,
|
|
"mean_token_accuracy": 0.23891518414020538,
|
|
"num_tokens": 77268087.0,
|
|
"step": 27645
|
|
},
|
|
{
|
|
"entropy": 4.8501307487487795,
|
|
"epoch": 3.2936271590232282,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039478143220295526,
|
|
"loss": 4.4258,
|
|
"mean_token_accuracy": 0.24462390840053558,
|
|
"num_tokens": 77280727.0,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"entropy": 4.800592756271362,
|
|
"epoch": 3.2942227516378795,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039474535774340034,
|
|
"loss": 4.4007,
|
|
"mean_token_accuracy": 0.24675310999155045,
|
|
"num_tokens": 77295026.0,
|
|
"step": 27655
|
|
},
|
|
{
|
|
"entropy": 4.810878038406372,
|
|
"epoch": 3.294818344252531,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003947092789887741,
|
|
"loss": 4.4879,
|
|
"mean_token_accuracy": 0.23155614286661147,
|
|
"num_tokens": 77309475.0,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"entropy": 4.756118392944336,
|
|
"epoch": 3.295413936867183,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039467319594037076,
|
|
"loss": 4.377,
|
|
"mean_token_accuracy": 0.24551974534988402,
|
|
"num_tokens": 77323813.0,
|
|
"step": 27665
|
|
},
|
|
{
|
|
"entropy": 4.776002216339111,
|
|
"epoch": 3.2960095294818346,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039463710859948437,
|
|
"loss": 4.4227,
|
|
"mean_token_accuracy": 0.23430014550685882,
|
|
"num_tokens": 77337696.0,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"entropy": 4.794742298126221,
|
|
"epoch": 3.296605122096486,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003946010169674095,
|
|
"loss": 4.3999,
|
|
"mean_token_accuracy": 0.24654654264450074,
|
|
"num_tokens": 77352158.0,
|
|
"step": 27675
|
|
},
|
|
{
|
|
"entropy": 4.799664306640625,
|
|
"epoch": 3.2972007147111375,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039456492104544057,
|
|
"loss": 4.4108,
|
|
"mean_token_accuracy": 0.24020590484142304,
|
|
"num_tokens": 77364725.0,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"entropy": 4.814458847045898,
|
|
"epoch": 3.297796307325789,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039452882083487224,
|
|
"loss": 4.4033,
|
|
"mean_token_accuracy": 0.24158891588449477,
|
|
"num_tokens": 77379403.0,
|
|
"step": 27685
|
|
},
|
|
{
|
|
"entropy": 4.836920261383057,
|
|
"epoch": 3.298391899940441,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039449271633699957,
|
|
"loss": 4.4227,
|
|
"mean_token_accuracy": 0.24240044504404068,
|
|
"num_tokens": 77393079.0,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"entropy": 4.774783706665039,
|
|
"epoch": 3.298987492555092,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00039445660755311736,
|
|
"loss": 4.348,
|
|
"mean_token_accuracy": 0.2488736167550087,
|
|
"num_tokens": 77409423.0,
|
|
"step": 27695
|
|
},
|
|
{
|
|
"entropy": 4.801646184921265,
|
|
"epoch": 3.299583085169744,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039442049448452096,
|
|
"loss": 4.4316,
|
|
"mean_token_accuracy": 0.24088650047779084,
|
|
"num_tokens": 77426065.0,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"entropy": 4.795594835281372,
|
|
"epoch": 3.3001786777843956,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039438437713250547,
|
|
"loss": 4.4098,
|
|
"mean_token_accuracy": 0.2507041335105896,
|
|
"num_tokens": 77438113.0,
|
|
"step": 27705
|
|
},
|
|
{
|
|
"entropy": 4.783589220046997,
|
|
"epoch": 3.300774270399047,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039434825549836654,
|
|
"loss": 4.3977,
|
|
"mean_token_accuracy": 0.240215528011322,
|
|
"num_tokens": 77452602.0,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"entropy": 4.795822477340698,
|
|
"epoch": 3.3013698630136985,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003943121295833998,
|
|
"loss": 4.4038,
|
|
"mean_token_accuracy": 0.23997881412506103,
|
|
"num_tokens": 77467243.0,
|
|
"step": 27715
|
|
},
|
|
{
|
|
"entropy": 4.8328978538513185,
|
|
"epoch": 3.30196545562835,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003942759993889009,
|
|
"loss": 4.3979,
|
|
"mean_token_accuracy": 0.23994633704423904,
|
|
"num_tokens": 77479398.0,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"entropy": 4.840239715576172,
|
|
"epoch": 3.302561048243002,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00039423986491616576,
|
|
"loss": 4.4539,
|
|
"mean_token_accuracy": 0.23731413036584853,
|
|
"num_tokens": 77494304.0,
|
|
"step": 27725
|
|
},
|
|
{
|
|
"entropy": 4.843193483352661,
|
|
"epoch": 3.3031566408576536,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003942037261664906,
|
|
"loss": 4.5031,
|
|
"mean_token_accuracy": 0.2334012821316719,
|
|
"num_tokens": 77509937.0,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"entropy": 4.763671588897705,
|
|
"epoch": 3.303752233472305,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003941675831411717,
|
|
"loss": 4.4165,
|
|
"mean_token_accuracy": 0.24453050792217254,
|
|
"num_tokens": 77524978.0,
|
|
"step": 27735
|
|
},
|
|
{
|
|
"entropy": 4.8654882431030275,
|
|
"epoch": 3.3043478260869565,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039413143584150523,
|
|
"loss": 4.5097,
|
|
"mean_token_accuracy": 0.23740703761577606,
|
|
"num_tokens": 77538497.0,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"entropy": 4.862938451766968,
|
|
"epoch": 3.3049434187016082,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003940952842687879,
|
|
"loss": 4.4917,
|
|
"mean_token_accuracy": 0.23885460942983627,
|
|
"num_tokens": 77552483.0,
|
|
"step": 27745
|
|
},
|
|
{
|
|
"entropy": 4.798424291610718,
|
|
"epoch": 3.3055390113162595,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003940591284243163,
|
|
"loss": 4.3492,
|
|
"mean_token_accuracy": 0.25416424572467805,
|
|
"num_tokens": 77564561.0,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"entropy": 4.708872365951538,
|
|
"epoch": 3.306134603930911,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003940229683093874,
|
|
"loss": 4.3318,
|
|
"mean_token_accuracy": 0.25274782478809354,
|
|
"num_tokens": 77577284.0,
|
|
"step": 27755
|
|
},
|
|
{
|
|
"entropy": 4.83978042602539,
|
|
"epoch": 3.306730196545563,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039398680392529805,
|
|
"loss": 4.4858,
|
|
"mean_token_accuracy": 0.23613717406988144,
|
|
"num_tokens": 77591340.0,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"entropy": 4.8489954471588135,
|
|
"epoch": 3.3073257891602146,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003939506352733456,
|
|
"loss": 4.4754,
|
|
"mean_token_accuracy": 0.23755898773670198,
|
|
"num_tokens": 77605242.0,
|
|
"step": 27765
|
|
},
|
|
{
|
|
"entropy": 4.807187414169311,
|
|
"epoch": 3.307921381774866,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003939144623548273,
|
|
"loss": 4.4237,
|
|
"mean_token_accuracy": 0.24062323123216628,
|
|
"num_tokens": 77617751.0,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"entropy": 4.791181945800782,
|
|
"epoch": 3.3085169743895175,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00039387828517104044,
|
|
"loss": 4.4376,
|
|
"mean_token_accuracy": 0.24213986247777938,
|
|
"num_tokens": 77632763.0,
|
|
"step": 27775
|
|
},
|
|
{
|
|
"entropy": 4.856376886367798,
|
|
"epoch": 3.3091125670041692,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003938421037232828,
|
|
"loss": 4.4436,
|
|
"mean_token_accuracy": 0.24104831367731094,
|
|
"num_tokens": 77646321.0,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"entropy": 4.789501810073853,
|
|
"epoch": 3.309708159618821,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039380591801285226,
|
|
"loss": 4.3579,
|
|
"mean_token_accuracy": 0.24148890972137452,
|
|
"num_tokens": 77659879.0,
|
|
"step": 27785
|
|
},
|
|
{
|
|
"entropy": 4.811961078643799,
|
|
"epoch": 3.310303752233472,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039376972804104653,
|
|
"loss": 4.4531,
|
|
"mean_token_accuracy": 0.2423509657382965,
|
|
"num_tokens": 77672522.0,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"entropy": 4.807698774337768,
|
|
"epoch": 3.310899344848124,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039373353380916376,
|
|
"loss": 4.4579,
|
|
"mean_token_accuracy": 0.23487856537103652,
|
|
"num_tokens": 77687602.0,
|
|
"step": 27795
|
|
},
|
|
{
|
|
"entropy": 4.78606481552124,
|
|
"epoch": 3.3114949374627756,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003936973353185022,
|
|
"loss": 4.4015,
|
|
"mean_token_accuracy": 0.24411144405603408,
|
|
"num_tokens": 77700501.0,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"entropy": 4.814654541015625,
|
|
"epoch": 3.312090530077427,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0003936611325703602,
|
|
"loss": 4.4289,
|
|
"mean_token_accuracy": 0.24011509865522385,
|
|
"num_tokens": 77714901.0,
|
|
"step": 27805
|
|
},
|
|
{
|
|
"entropy": 4.79863657951355,
|
|
"epoch": 3.3126861226920785,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003936249255660363,
|
|
"loss": 4.3019,
|
|
"mean_token_accuracy": 0.25089172273874283,
|
|
"num_tokens": 77728243.0,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"entropy": 4.827978658676147,
|
|
"epoch": 3.31328171530673,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003935887143068292,
|
|
"loss": 4.4125,
|
|
"mean_token_accuracy": 0.25029492378234863,
|
|
"num_tokens": 77740726.0,
|
|
"step": 27815
|
|
},
|
|
{
|
|
"entropy": 4.706410074234009,
|
|
"epoch": 3.313877307921382,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003935524987940376,
|
|
"loss": 4.2863,
|
|
"mean_token_accuracy": 0.25027120262384417,
|
|
"num_tokens": 77753218.0,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"entropy": 4.775123500823975,
|
|
"epoch": 3.314472900536033,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003935162790289608,
|
|
"loss": 4.3806,
|
|
"mean_token_accuracy": 0.24888475686311723,
|
|
"num_tokens": 77765766.0,
|
|
"step": 27825
|
|
},
|
|
{
|
|
"entropy": 4.774979734420777,
|
|
"epoch": 3.315068493150685,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039348005501289775,
|
|
"loss": 4.4403,
|
|
"mean_token_accuracy": 0.239623960852623,
|
|
"num_tokens": 77779956.0,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"entropy": 4.7303032875061035,
|
|
"epoch": 3.3156640857653366,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00039344382674714773,
|
|
"loss": 4.328,
|
|
"mean_token_accuracy": 0.2511750191450119,
|
|
"num_tokens": 77795364.0,
|
|
"step": 27835
|
|
},
|
|
{
|
|
"entropy": 4.908004379272461,
|
|
"epoch": 3.3162596783799883,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039340759423301026,
|
|
"loss": 4.5448,
|
|
"mean_token_accuracy": 0.23628686219453812,
|
|
"num_tokens": 77809944.0,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"entropy": 4.815680503845215,
|
|
"epoch": 3.3168552709946395,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039337135747178476,
|
|
"loss": 4.4229,
|
|
"mean_token_accuracy": 0.23306018859148026,
|
|
"num_tokens": 77822963.0,
|
|
"step": 27845
|
|
},
|
|
{
|
|
"entropy": 4.746547603607178,
|
|
"epoch": 3.317450863609291,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003933351164647713,
|
|
"loss": 4.3686,
|
|
"mean_token_accuracy": 0.24425335079431534,
|
|
"num_tokens": 77837380.0,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"entropy": 4.851466846466065,
|
|
"epoch": 3.318046456223943,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003932988712132696,
|
|
"loss": 4.4839,
|
|
"mean_token_accuracy": 0.24500854015350343,
|
|
"num_tokens": 77851558.0,
|
|
"step": 27855
|
|
},
|
|
{
|
|
"entropy": 4.894737386703492,
|
|
"epoch": 3.3186420488385946,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039326262171857963,
|
|
"loss": 4.4697,
|
|
"mean_token_accuracy": 0.23442662507295609,
|
|
"num_tokens": 77867674.0,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"entropy": 4.771296691894531,
|
|
"epoch": 3.319237641453246,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00039322636798200174,
|
|
"loss": 4.3651,
|
|
"mean_token_accuracy": 0.25194336026906966,
|
|
"num_tokens": 77881121.0,
|
|
"step": 27865
|
|
},
|
|
{
|
|
"entropy": 4.824480772018433,
|
|
"epoch": 3.3198332340678975,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039319011000483615,
|
|
"loss": 4.5377,
|
|
"mean_token_accuracy": 0.23345817774534225,
|
|
"num_tokens": 77895293.0,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"entropy": 4.740913534164429,
|
|
"epoch": 3.3204288266825492,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039315384778838364,
|
|
"loss": 4.3238,
|
|
"mean_token_accuracy": 0.254258693754673,
|
|
"num_tokens": 77909410.0,
|
|
"step": 27875
|
|
},
|
|
{
|
|
"entropy": 4.734993934631348,
|
|
"epoch": 3.321024419297201,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003931175813339447,
|
|
"loss": 4.3344,
|
|
"mean_token_accuracy": 0.2469314604997635,
|
|
"num_tokens": 77925014.0,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"entropy": 4.85869460105896,
|
|
"epoch": 3.321620011911852,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039308131064282016,
|
|
"loss": 4.5634,
|
|
"mean_token_accuracy": 0.22854650765657425,
|
|
"num_tokens": 77939312.0,
|
|
"step": 27885
|
|
},
|
|
{
|
|
"entropy": 4.763597774505615,
|
|
"epoch": 3.322215604526504,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00039304503571631095,
|
|
"loss": 4.239,
|
|
"mean_token_accuracy": 0.2573072716593742,
|
|
"num_tokens": 77953062.0,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"entropy": 4.708873224258423,
|
|
"epoch": 3.3228111971411556,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003930087565557183,
|
|
"loss": 4.3507,
|
|
"mean_token_accuracy": 0.2537884533405304,
|
|
"num_tokens": 77965401.0,
|
|
"step": 27895
|
|
},
|
|
{
|
|
"entropy": 4.742206287384033,
|
|
"epoch": 3.323406789755807,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00039297247316234335,
|
|
"loss": 4.3838,
|
|
"mean_token_accuracy": 0.24623445123434068,
|
|
"num_tokens": 77980755.0,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"entropy": 4.876486825942993,
|
|
"epoch": 3.3240023823704585,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003929361855374876,
|
|
"loss": 4.4342,
|
|
"mean_token_accuracy": 0.23953837901353836,
|
|
"num_tokens": 77994028.0,
|
|
"step": 27905
|
|
},
|
|
{
|
|
"entropy": 4.855444049835205,
|
|
"epoch": 3.3245979749851102,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039289989368245263,
|
|
"loss": 4.4209,
|
|
"mean_token_accuracy": 0.24684132635593414,
|
|
"num_tokens": 78006431.0,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"entropy": 4.769939994812011,
|
|
"epoch": 3.325193567599762,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039286359759854023,
|
|
"loss": 4.4267,
|
|
"mean_token_accuracy": 0.2431538388133049,
|
|
"num_tokens": 78020515.0,
|
|
"step": 27915
|
|
},
|
|
{
|
|
"entropy": 4.8451563835144045,
|
|
"epoch": 3.325789160214413,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003928272972870522,
|
|
"loss": 4.4117,
|
|
"mean_token_accuracy": 0.2503505453467369,
|
|
"num_tokens": 78033466.0,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"entropy": 4.873320055007935,
|
|
"epoch": 3.326384752829065,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003927909927492906,
|
|
"loss": 4.4933,
|
|
"mean_token_accuracy": 0.2319117084145546,
|
|
"num_tokens": 78049312.0,
|
|
"step": 27925
|
|
},
|
|
{
|
|
"entropy": 4.791367244720459,
|
|
"epoch": 3.3269803454437166,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003927546839865576,
|
|
"loss": 4.4577,
|
|
"mean_token_accuracy": 0.23942837566137315,
|
|
"num_tokens": 78063621.0,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"entropy": 4.8235913753509525,
|
|
"epoch": 3.3275759380583683,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003927183710001555,
|
|
"loss": 4.4474,
|
|
"mean_token_accuracy": 0.24409058392047883,
|
|
"num_tokens": 78078051.0,
|
|
"step": 27935
|
|
},
|
|
{
|
|
"entropy": 4.784062147140503,
|
|
"epoch": 3.3281715306730195,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003926820537913868,
|
|
"loss": 4.3755,
|
|
"mean_token_accuracy": 0.24279857724905013,
|
|
"num_tokens": 78090856.0,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"entropy": 4.6868468761444095,
|
|
"epoch": 3.328767123287671,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003926457323615543,
|
|
"loss": 4.2755,
|
|
"mean_token_accuracy": 0.25514958053827286,
|
|
"num_tokens": 78103117.0,
|
|
"step": 27945
|
|
},
|
|
{
|
|
"entropy": 4.784412574768067,
|
|
"epoch": 3.329362715902323,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003926094067119605,
|
|
"loss": 4.418,
|
|
"mean_token_accuracy": 0.240533547103405,
|
|
"num_tokens": 78115753.0,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"entropy": 4.775800895690918,
|
|
"epoch": 3.329958308516974,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003925730768439086,
|
|
"loss": 4.4112,
|
|
"mean_token_accuracy": 0.23887597918510436,
|
|
"num_tokens": 78128490.0,
|
|
"step": 27955
|
|
},
|
|
{
|
|
"entropy": 4.691694688796997,
|
|
"epoch": 3.330553901131626,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003925367427587016,
|
|
"loss": 4.3332,
|
|
"mean_token_accuracy": 0.24618915170431138,
|
|
"num_tokens": 78141752.0,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"entropy": 4.7789306640625,
|
|
"epoch": 3.3311494937462776,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003925004044576428,
|
|
"loss": 4.4052,
|
|
"mean_token_accuracy": 0.24753628075122833,
|
|
"num_tokens": 78155335.0,
|
|
"step": 27965
|
|
},
|
|
{
|
|
"entropy": 4.734844827651978,
|
|
"epoch": 3.3317450863609293,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00039246406194203535,
|
|
"loss": 4.3764,
|
|
"mean_token_accuracy": 0.25841181725263596,
|
|
"num_tokens": 78168637.0,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"entropy": 4.815714550018311,
|
|
"epoch": 3.332340678975581,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00039242771521318315,
|
|
"loss": 4.4256,
|
|
"mean_token_accuracy": 0.2515336647629738,
|
|
"num_tokens": 78182564.0,
|
|
"step": 27975
|
|
},
|
|
{
|
|
"entropy": 4.73459677696228,
|
|
"epoch": 3.332936271590232,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00039239136427238967,
|
|
"loss": 4.3183,
|
|
"mean_token_accuracy": 0.2594480410218239,
|
|
"num_tokens": 78196096.0,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"entropy": 4.735301113128662,
|
|
"epoch": 3.333531864204884,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039235500912095886,
|
|
"loss": 4.334,
|
|
"mean_token_accuracy": 0.2513437241315842,
|
|
"num_tokens": 78211229.0,
|
|
"step": 27985
|
|
},
|
|
{
|
|
"entropy": 4.802818632125854,
|
|
"epoch": 3.3341274568195356,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00039231864976019466,
|
|
"loss": 4.4548,
|
|
"mean_token_accuracy": 0.2362417384982109,
|
|
"num_tokens": 78229452.0,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"entropy": 4.854534721374511,
|
|
"epoch": 3.334723049434187,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003922822861914012,
|
|
"loss": 4.4644,
|
|
"mean_token_accuracy": 0.23489675521850586,
|
|
"num_tokens": 78244087.0,
|
|
"step": 27995
|
|
},
|
|
{
|
|
"entropy": 4.810452842712403,
|
|
"epoch": 3.3353186420488385,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0003922459184158828,
|
|
"loss": 4.5152,
|
|
"mean_token_accuracy": 0.23522577285766602,
|
|
"num_tokens": 78258341.0,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"entropy": 4.829465246200561,
|
|
"epoch": 3.3359142346634902,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000392209546434944,
|
|
"loss": 4.402,
|
|
"mean_token_accuracy": 0.24784977734088898,
|
|
"num_tokens": 78270096.0,
|
|
"step": 28005
|
|
},
|
|
{
|
|
"entropy": 4.788179540634156,
|
|
"epoch": 3.336509827278142,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003921731702498893,
|
|
"loss": 4.4416,
|
|
"mean_token_accuracy": 0.2452860653400421,
|
|
"num_tokens": 78283444.0,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"entropy": 4.751328420639038,
|
|
"epoch": 3.337105419892793,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00039213678986202357,
|
|
"loss": 4.3888,
|
|
"mean_token_accuracy": 0.24601346999406815,
|
|
"num_tokens": 78298505.0,
|
|
"step": 28015
|
|
},
|
|
{
|
|
"entropy": 4.9009260654449465,
|
|
"epoch": 3.337701012507445,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00039210040527265164,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.23041732907295226,
|
|
"num_tokens": 78314467.0,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"entropy": 4.886048269271851,
|
|
"epoch": 3.3382966051220966,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003920640164830785,
|
|
"loss": 4.4912,
|
|
"mean_token_accuracy": 0.23616471141576767,
|
|
"num_tokens": 78329114.0,
|
|
"step": 28025
|
|
},
|
|
{
|
|
"entropy": 4.808170318603516,
|
|
"epoch": 3.3388921977367483,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00039202762349460933,
|
|
"loss": 4.4117,
|
|
"mean_token_accuracy": 0.24342803061008453,
|
|
"num_tokens": 78343897.0,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"entropy": 4.7722431182861325,
|
|
"epoch": 3.3394877903513995,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00039199122630854976,
|
|
"loss": 4.3965,
|
|
"mean_token_accuracy": 0.25158770233392713,
|
|
"num_tokens": 78356732.0,
|
|
"step": 28035
|
|
},
|
|
{
|
|
"entropy": 4.774852275848389,
|
|
"epoch": 3.3400833829660512,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00039195482492620506,
|
|
"loss": 4.3655,
|
|
"mean_token_accuracy": 0.23728516846895217,
|
|
"num_tokens": 78370122.0,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"entropy": 4.783718204498291,
|
|
"epoch": 3.340678975580703,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003919184193488809,
|
|
"loss": 4.3198,
|
|
"mean_token_accuracy": 0.24608540087938308,
|
|
"num_tokens": 78383642.0,
|
|
"step": 28045
|
|
},
|
|
{
|
|
"entropy": 4.801359605789185,
|
|
"epoch": 3.341274568195354,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003918820095778832,
|
|
"loss": 4.3856,
|
|
"mean_token_accuracy": 0.2462697669863701,
|
|
"num_tokens": 78397335.0,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"entropy": 4.713674116134643,
|
|
"epoch": 3.341870160810006,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003918455956145178,
|
|
"loss": 4.3602,
|
|
"mean_token_accuracy": 0.24719761461019515,
|
|
"num_tokens": 78411881.0,
|
|
"step": 28055
|
|
},
|
|
{
|
|
"entropy": 4.748007774353027,
|
|
"epoch": 3.3424657534246576,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039180917746009085,
|
|
"loss": 4.3587,
|
|
"mean_token_accuracy": 0.25359513610601425,
|
|
"num_tokens": 78424993.0,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"entropy": 4.681986379623413,
|
|
"epoch": 3.3430613460393093,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003917727551159087,
|
|
"loss": 4.3182,
|
|
"mean_token_accuracy": 0.2533546626567841,
|
|
"num_tokens": 78437992.0,
|
|
"step": 28065
|
|
},
|
|
{
|
|
"entropy": 4.845908880233765,
|
|
"epoch": 3.3436569386539605,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003917363285832777,
|
|
"loss": 4.4745,
|
|
"mean_token_accuracy": 0.23510278463363649,
|
|
"num_tokens": 78452303.0,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"entropy": 4.822172069549561,
|
|
"epoch": 3.344252531268612,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003916998978635044,
|
|
"loss": 4.3951,
|
|
"mean_token_accuracy": 0.24309561252593995,
|
|
"num_tokens": 78466219.0,
|
|
"step": 28075
|
|
},
|
|
{
|
|
"entropy": 4.841880750656128,
|
|
"epoch": 3.344848123883264,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003916634629578953,
|
|
"loss": 4.4857,
|
|
"mean_token_accuracy": 0.23657372444868088,
|
|
"num_tokens": 78478738.0,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"entropy": 4.715886211395263,
|
|
"epoch": 3.3454437164979156,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039162702386775773,
|
|
"loss": 4.3801,
|
|
"mean_token_accuracy": 0.25095484107732774,
|
|
"num_tokens": 78492286.0,
|
|
"step": 28085
|
|
},
|
|
{
|
|
"entropy": 4.771911382675171,
|
|
"epoch": 3.346039309112567,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003915905805943983,
|
|
"loss": 4.3699,
|
|
"mean_token_accuracy": 0.2384594663977623,
|
|
"num_tokens": 78507820.0,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"entropy": 4.819495916366577,
|
|
"epoch": 3.3466349017272186,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003915541331391243,
|
|
"loss": 4.4084,
|
|
"mean_token_accuracy": 0.2513041391968727,
|
|
"num_tokens": 78520483.0,
|
|
"step": 28095
|
|
},
|
|
{
|
|
"entropy": 4.655571413040161,
|
|
"epoch": 3.3472304943418703,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003915176815032431,
|
|
"loss": 4.268,
|
|
"mean_token_accuracy": 0.25919887125492097,
|
|
"num_tokens": 78534208.0,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"entropy": 4.730915307998657,
|
|
"epoch": 3.3478260869565215,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00039148122568806215,
|
|
"loss": 4.3714,
|
|
"mean_token_accuracy": 0.247807015478611,
|
|
"num_tokens": 78549034.0,
|
|
"step": 28105
|
|
},
|
|
{
|
|
"entropy": 4.867380905151367,
|
|
"epoch": 3.348421679571173,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039144476569488896,
|
|
"loss": 4.4072,
|
|
"mean_token_accuracy": 0.2469192162156105,
|
|
"num_tokens": 78563147.0,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"entropy": 4.782218551635742,
|
|
"epoch": 3.349017272185825,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003914083015250314,
|
|
"loss": 4.4771,
|
|
"mean_token_accuracy": 0.24000260084867478,
|
|
"num_tokens": 78577923.0,
|
|
"step": 28115
|
|
},
|
|
{
|
|
"entropy": 4.732664155960083,
|
|
"epoch": 3.3496128648004766,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039137183317979724,
|
|
"loss": 4.3366,
|
|
"mean_token_accuracy": 0.2580944836139679,
|
|
"num_tokens": 78589758.0,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"entropy": 4.784263038635254,
|
|
"epoch": 3.3502084574151283,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003913353606604947,
|
|
"loss": 4.3796,
|
|
"mean_token_accuracy": 0.24618062674999236,
|
|
"num_tokens": 78601849.0,
|
|
"step": 28125
|
|
},
|
|
{
|
|
"entropy": 4.81989312171936,
|
|
"epoch": 3.3508040500297795,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00039129888396843187,
|
|
"loss": 4.4574,
|
|
"mean_token_accuracy": 0.23964973539113998,
|
|
"num_tokens": 78614691.0,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"entropy": 4.722729778289795,
|
|
"epoch": 3.3513996426444312,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039126240310491725,
|
|
"loss": 4.3111,
|
|
"mean_token_accuracy": 0.25569515228271483,
|
|
"num_tokens": 78628846.0,
|
|
"step": 28135
|
|
},
|
|
{
|
|
"entropy": 4.821070051193237,
|
|
"epoch": 3.351995235259083,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00039122591807125924,
|
|
"loss": 4.4201,
|
|
"mean_token_accuracy": 0.24719275832176207,
|
|
"num_tokens": 78643278.0,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"entropy": 4.7544036388397215,
|
|
"epoch": 3.352590827873734,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00039118942886876647,
|
|
"loss": 4.3123,
|
|
"mean_token_accuracy": 0.25503764748573304,
|
|
"num_tokens": 78657650.0,
|
|
"step": 28145
|
|
},
|
|
{
|
|
"entropy": 4.719218683242798,
|
|
"epoch": 3.353186420488386,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003911529354987478,
|
|
"loss": 4.347,
|
|
"mean_token_accuracy": 0.24827049672603607,
|
|
"num_tokens": 78672496.0,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"entropy": 4.706994485855103,
|
|
"epoch": 3.3537820131030376,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003911164379625122,
|
|
"loss": 4.3691,
|
|
"mean_token_accuracy": 0.24658943116664886,
|
|
"num_tokens": 78686232.0,
|
|
"step": 28155
|
|
},
|
|
{
|
|
"entropy": 4.794610023498535,
|
|
"epoch": 3.3543776057176893,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003910799362613688,
|
|
"loss": 4.428,
|
|
"mean_token_accuracy": 0.24669234156608583,
|
|
"num_tokens": 78702141.0,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"entropy": 4.776057720184326,
|
|
"epoch": 3.3549731983323405,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039104343039662675,
|
|
"loss": 4.3912,
|
|
"mean_token_accuracy": 0.2533385202288628,
|
|
"num_tokens": 78714876.0,
|
|
"step": 28165
|
|
},
|
|
{
|
|
"entropy": 4.835677528381348,
|
|
"epoch": 3.3555687909469922,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039100692036959564,
|
|
"loss": 4.4489,
|
|
"mean_token_accuracy": 0.23948899954557418,
|
|
"num_tokens": 78728920.0,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"entropy": 4.685890865325928,
|
|
"epoch": 3.356164383561644,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003909704061815848,
|
|
"loss": 4.3111,
|
|
"mean_token_accuracy": 0.25833147913217547,
|
|
"num_tokens": 78743960.0,
|
|
"step": 28175
|
|
},
|
|
{
|
|
"entropy": 4.806468677520752,
|
|
"epoch": 3.3567599761762956,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003909338878339041,
|
|
"loss": 4.497,
|
|
"mean_token_accuracy": 0.23065468221902846,
|
|
"num_tokens": 78758039.0,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"entropy": 4.891583108901978,
|
|
"epoch": 3.357355568790947,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039089736532786336,
|
|
"loss": 4.5057,
|
|
"mean_token_accuracy": 0.23911290466785431,
|
|
"num_tokens": 78772634.0,
|
|
"step": 28185
|
|
},
|
|
{
|
|
"entropy": 4.740127754211426,
|
|
"epoch": 3.3579511614055986,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003908608386647725,
|
|
"loss": 4.3344,
|
|
"mean_token_accuracy": 0.24530139416456223,
|
|
"num_tokens": 78786354.0,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"entropy": 4.741527509689331,
|
|
"epoch": 3.3585467540202503,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039082430784594173,
|
|
"loss": 4.369,
|
|
"mean_token_accuracy": 0.2508601829409599,
|
|
"num_tokens": 78798851.0,
|
|
"step": 28195
|
|
},
|
|
{
|
|
"entropy": 4.707811403274536,
|
|
"epoch": 3.3591423466349015,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003907877728726814,
|
|
"loss": 4.3984,
|
|
"mean_token_accuracy": 0.24630616158246993,
|
|
"num_tokens": 78812576.0,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"entropy": 4.776282596588135,
|
|
"epoch": 3.359737939249553,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00039075123374630194,
|
|
"loss": 4.3836,
|
|
"mean_token_accuracy": 0.25524702072143557,
|
|
"num_tokens": 78825296.0,
|
|
"step": 28205
|
|
},
|
|
{
|
|
"entropy": 4.800040292739868,
|
|
"epoch": 3.360333531864205,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039071469046811396,
|
|
"loss": 4.3705,
|
|
"mean_token_accuracy": 0.2463463217020035,
|
|
"num_tokens": 78840940.0,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"entropy": 4.799200582504272,
|
|
"epoch": 3.3609291244788566,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00039067814303942806,
|
|
"loss": 4.4279,
|
|
"mean_token_accuracy": 0.2410166546702385,
|
|
"num_tokens": 78853914.0,
|
|
"step": 28215
|
|
},
|
|
{
|
|
"entropy": 4.730961179733276,
|
|
"epoch": 3.361524717093508,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003906415914615553,
|
|
"loss": 4.3825,
|
|
"mean_token_accuracy": 0.2487489864230156,
|
|
"num_tokens": 78869417.0,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"entropy": 4.774725103378296,
|
|
"epoch": 3.3621203097081596,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003906050357358067,
|
|
"loss": 4.3523,
|
|
"mean_token_accuracy": 0.24626027643680573,
|
|
"num_tokens": 78883831.0,
|
|
"step": 28225
|
|
},
|
|
{
|
|
"entropy": 4.822626733779908,
|
|
"epoch": 3.3627159023228113,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00039056847586349335,
|
|
"loss": 4.4588,
|
|
"mean_token_accuracy": 0.2374795064330101,
|
|
"num_tokens": 78898341.0,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"entropy": 4.850362110137939,
|
|
"epoch": 3.363311494937463,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003905319118459268,
|
|
"loss": 4.3885,
|
|
"mean_token_accuracy": 0.2515096992254257,
|
|
"num_tokens": 78910384.0,
|
|
"step": 28235
|
|
},
|
|
{
|
|
"entropy": 4.773040771484375,
|
|
"epoch": 3.363907087552114,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003904953436844183,
|
|
"loss": 4.4238,
|
|
"mean_token_accuracy": 0.23657240420579911,
|
|
"num_tokens": 78924688.0,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"entropy": 4.803785181045532,
|
|
"epoch": 3.364502680166766,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00039045877138027963,
|
|
"loss": 4.4627,
|
|
"mean_token_accuracy": 0.23841402679681778,
|
|
"num_tokens": 78939226.0,
|
|
"step": 28245
|
|
},
|
|
{
|
|
"entropy": 4.797795915603638,
|
|
"epoch": 3.3650982727814176,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003904221949348226,
|
|
"loss": 4.3556,
|
|
"mean_token_accuracy": 0.2466673195362091,
|
|
"num_tokens": 78954181.0,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"entropy": 4.811429834365844,
|
|
"epoch": 3.365693865396069,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003903856143493591,
|
|
"loss": 4.3869,
|
|
"mean_token_accuracy": 0.2466812774538994,
|
|
"num_tokens": 78968316.0,
|
|
"step": 28255
|
|
},
|
|
{
|
|
"entropy": 4.721120071411133,
|
|
"epoch": 3.3662894580107205,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039034902962520123,
|
|
"loss": 4.3684,
|
|
"mean_token_accuracy": 0.25020863562822343,
|
|
"num_tokens": 78984161.0,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"entropy": 4.7421080589294435,
|
|
"epoch": 3.3668850506253722,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00039031244076366116,
|
|
"loss": 4.3918,
|
|
"mean_token_accuracy": 0.24926343858242034,
|
|
"num_tokens": 79000176.0,
|
|
"step": 28265
|
|
},
|
|
{
|
|
"entropy": 4.766800737380981,
|
|
"epoch": 3.367480643240024,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039027584776605136,
|
|
"loss": 4.3849,
|
|
"mean_token_accuracy": 0.2419150561094284,
|
|
"num_tokens": 79013244.0,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"entropy": 4.715028238296509,
|
|
"epoch": 3.3680762358546756,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003902392506336843,
|
|
"loss": 4.3188,
|
|
"mean_token_accuracy": 0.24413536936044694,
|
|
"num_tokens": 79027769.0,
|
|
"step": 28275
|
|
},
|
|
{
|
|
"entropy": 4.92712368965149,
|
|
"epoch": 3.368671828469327,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039020264936787276,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.22485593855381011,
|
|
"num_tokens": 79042411.0,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"entropy": 4.912181329727173,
|
|
"epoch": 3.3692674210839786,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003901660439699294,
|
|
"loss": 4.4496,
|
|
"mean_token_accuracy": 0.23912166953086852,
|
|
"num_tokens": 79054408.0,
|
|
"step": 28285
|
|
},
|
|
{
|
|
"entropy": 4.81598162651062,
|
|
"epoch": 3.3698630136986303,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039012943444116725,
|
|
"loss": 4.4513,
|
|
"mean_token_accuracy": 0.24420538544654846,
|
|
"num_tokens": 79068066.0,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"entropy": 4.742448377609253,
|
|
"epoch": 3.3704586063132815,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00039009282078289963,
|
|
"loss": 4.4159,
|
|
"mean_token_accuracy": 0.24309022128582,
|
|
"num_tokens": 79081948.0,
|
|
"step": 28295
|
|
},
|
|
{
|
|
"entropy": 4.748645448684693,
|
|
"epoch": 3.3710541989279332,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003900562029964396,
|
|
"loss": 4.2945,
|
|
"mean_token_accuracy": 0.260996051132679,
|
|
"num_tokens": 79094109.0,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"entropy": 4.759379911422729,
|
|
"epoch": 3.371649791542585,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00039001958108310066,
|
|
"loss": 4.3452,
|
|
"mean_token_accuracy": 0.2506631791591644,
|
|
"num_tokens": 79108365.0,
|
|
"step": 28305
|
|
},
|
|
{
|
|
"entropy": 4.622799634933472,
|
|
"epoch": 3.3722453841572366,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038998295504419627,
|
|
"loss": 4.2126,
|
|
"mean_token_accuracy": 0.2644208803772926,
|
|
"num_tokens": 79120458.0,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"entropy": 4.743785953521728,
|
|
"epoch": 3.372840976771888,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003899463248810403,
|
|
"loss": 4.381,
|
|
"mean_token_accuracy": 0.24524833559989928,
|
|
"num_tokens": 79133843.0,
|
|
"step": 28315
|
|
},
|
|
{
|
|
"entropy": 4.771577501296997,
|
|
"epoch": 3.3734365693865396,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00038990969059494654,
|
|
"loss": 4.361,
|
|
"mean_token_accuracy": 0.24635191708803178,
|
|
"num_tokens": 79148511.0,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"entropy": 4.80914454460144,
|
|
"epoch": 3.3740321620011913,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038987305218722904,
|
|
"loss": 4.445,
|
|
"mean_token_accuracy": 0.2500111237168312,
|
|
"num_tokens": 79161559.0,
|
|
"step": 28325
|
|
},
|
|
{
|
|
"entropy": 4.83264856338501,
|
|
"epoch": 3.374627754615843,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003898364096592018,
|
|
"loss": 4.4208,
|
|
"mean_token_accuracy": 0.23172805458307266,
|
|
"num_tokens": 79176404.0,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"entropy": 4.801163959503174,
|
|
"epoch": 3.375223347230494,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038979976301217934,
|
|
"loss": 4.4129,
|
|
"mean_token_accuracy": 0.24201138764619828,
|
|
"num_tokens": 79189686.0,
|
|
"step": 28335
|
|
},
|
|
{
|
|
"entropy": 4.804040718078613,
|
|
"epoch": 3.375818939845146,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003897631122474761,
|
|
"loss": 4.3967,
|
|
"mean_token_accuracy": 0.24530216455459594,
|
|
"num_tokens": 79203604.0,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"entropy": 4.794249057769775,
|
|
"epoch": 3.3764145324597976,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00038972645736640654,
|
|
"loss": 4.4092,
|
|
"mean_token_accuracy": 0.24515757858753204,
|
|
"num_tokens": 79216191.0,
|
|
"step": 28345
|
|
},
|
|
{
|
|
"entropy": 4.812794876098633,
|
|
"epoch": 3.377010125074449,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038968979837028555,
|
|
"loss": 4.479,
|
|
"mean_token_accuracy": 0.24607163816690444,
|
|
"num_tokens": 79230386.0,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"entropy": 4.772590208053589,
|
|
"epoch": 3.3776057176891006,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00038965313526042797,
|
|
"loss": 4.3518,
|
|
"mean_token_accuracy": 0.24599184095859528,
|
|
"num_tokens": 79245302.0,
|
|
"step": 28355
|
|
},
|
|
{
|
|
"entropy": 4.7274693012237545,
|
|
"epoch": 3.3782013103037523,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00038961646803814873,
|
|
"loss": 4.3208,
|
|
"mean_token_accuracy": 0.258550101518631,
|
|
"num_tokens": 79258134.0,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"entropy": 4.752446556091309,
|
|
"epoch": 3.378796902918404,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003895797967047632,
|
|
"loss": 4.3302,
|
|
"mean_token_accuracy": 0.25604108572006223,
|
|
"num_tokens": 79271939.0,
|
|
"step": 28365
|
|
},
|
|
{
|
|
"entropy": 4.720610523223877,
|
|
"epoch": 3.379392495533055,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003895431212615867,
|
|
"loss": 4.349,
|
|
"mean_token_accuracy": 0.2524352088570595,
|
|
"num_tokens": 79285165.0,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"entropy": 4.821830606460571,
|
|
"epoch": 3.379988088147707,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003895064417099346,
|
|
"loss": 4.4938,
|
|
"mean_token_accuracy": 0.2431863471865654,
|
|
"num_tokens": 79299084.0,
|
|
"step": 28375
|
|
},
|
|
{
|
|
"entropy": 4.875012350082398,
|
|
"epoch": 3.3805836807623586,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003894697580511226,
|
|
"loss": 4.4488,
|
|
"mean_token_accuracy": 0.23916580080986022,
|
|
"num_tokens": 79313633.0,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"entropy": 4.860861873626709,
|
|
"epoch": 3.3811792733770103,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00038943307028646665,
|
|
"loss": 4.4613,
|
|
"mean_token_accuracy": 0.24455275386571884,
|
|
"num_tokens": 79328553.0,
|
|
"step": 28385
|
|
},
|
|
{
|
|
"entropy": 4.782514190673828,
|
|
"epoch": 3.3817748659916615,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003893963784172824,
|
|
"loss": 4.4294,
|
|
"mean_token_accuracy": 0.24190270602703096,
|
|
"num_tokens": 79343364.0,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"entropy": 4.830332803726196,
|
|
"epoch": 3.3823704586063132,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003893596824448861,
|
|
"loss": 4.4575,
|
|
"mean_token_accuracy": 0.2434788390994072,
|
|
"num_tokens": 79357474.0,
|
|
"step": 28395
|
|
},
|
|
{
|
|
"entropy": 4.7593653202056885,
|
|
"epoch": 3.382966051220965,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038932298237059394,
|
|
"loss": 4.3841,
|
|
"mean_token_accuracy": 0.2458254724740982,
|
|
"num_tokens": 79370512.0,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"entropy": 4.843710565567017,
|
|
"epoch": 3.383561643835616,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038928627819572213,
|
|
"loss": 4.4534,
|
|
"mean_token_accuracy": 0.23680139034986497,
|
|
"num_tokens": 79382839.0,
|
|
"step": 28405
|
|
},
|
|
{
|
|
"entropy": 4.81341872215271,
|
|
"epoch": 3.384157236450268,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003892495699215875,
|
|
"loss": 4.4217,
|
|
"mean_token_accuracy": 0.24515187591314316,
|
|
"num_tokens": 79395216.0,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"entropy": 4.746179246902466,
|
|
"epoch": 3.3847528290649196,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038921285754950645,
|
|
"loss": 4.328,
|
|
"mean_token_accuracy": 0.24752278178930281,
|
|
"num_tokens": 79407901.0,
|
|
"step": 28415
|
|
},
|
|
{
|
|
"entropy": 4.7717937469482425,
|
|
"epoch": 3.3853484216795713,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000389176141080796,
|
|
"loss": 4.369,
|
|
"mean_token_accuracy": 0.25154962837696077,
|
|
"num_tokens": 79420635.0,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"entropy": 4.794589948654175,
|
|
"epoch": 3.385944014294223,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000389139420516773,
|
|
"loss": 4.3654,
|
|
"mean_token_accuracy": 0.24194719791412353,
|
|
"num_tokens": 79434233.0,
|
|
"step": 28425
|
|
},
|
|
{
|
|
"entropy": 4.750098085403442,
|
|
"epoch": 3.3865396069088742,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038910269585875446,
|
|
"loss": 4.3399,
|
|
"mean_token_accuracy": 0.24400077164173126,
|
|
"num_tokens": 79446347.0,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"entropy": 4.801591539382935,
|
|
"epoch": 3.387135199523526,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003890659671080579,
|
|
"loss": 4.4062,
|
|
"mean_token_accuracy": 0.24493536353111267,
|
|
"num_tokens": 79461908.0,
|
|
"step": 28435
|
|
},
|
|
{
|
|
"entropy": 4.763952159881592,
|
|
"epoch": 3.3877307921381776,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038902923426600047,
|
|
"loss": 4.345,
|
|
"mean_token_accuracy": 0.24181989580392838,
|
|
"num_tokens": 79474299.0,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"entropy": 4.764033699035645,
|
|
"epoch": 3.388326384752829,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003889924973338998,
|
|
"loss": 4.3922,
|
|
"mean_token_accuracy": 0.24761046022176741,
|
|
"num_tokens": 79487984.0,
|
|
"step": 28445
|
|
},
|
|
{
|
|
"entropy": 4.766359853744507,
|
|
"epoch": 3.3889219773674806,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038895575631307355,
|
|
"loss": 4.412,
|
|
"mean_token_accuracy": 0.24322417825460435,
|
|
"num_tokens": 79502483.0,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"entropy": 4.904546785354614,
|
|
"epoch": 3.3895175699821323,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003889190112048397,
|
|
"loss": 4.4781,
|
|
"mean_token_accuracy": 0.24494799375534057,
|
|
"num_tokens": 79516662.0,
|
|
"step": 28455
|
|
},
|
|
{
|
|
"entropy": 4.704093313217163,
|
|
"epoch": 3.390113162596784,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003888822620105161,
|
|
"loss": 4.3274,
|
|
"mean_token_accuracy": 0.2528680384159088,
|
|
"num_tokens": 79529956.0,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"entropy": 4.768643474578857,
|
|
"epoch": 3.390708755211435,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038884550873142084,
|
|
"loss": 4.4326,
|
|
"mean_token_accuracy": 0.24751046150922776,
|
|
"num_tokens": 79544131.0,
|
|
"step": 28465
|
|
},
|
|
{
|
|
"entropy": 4.798229074478149,
|
|
"epoch": 3.391304347826087,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003888087513688724,
|
|
"loss": 4.4564,
|
|
"mean_token_accuracy": 0.24164637923240662,
|
|
"num_tokens": 79559593.0,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"entropy": 4.80020661354065,
|
|
"epoch": 3.3918999404407386,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000388771989924189,
|
|
"loss": 4.3657,
|
|
"mean_token_accuracy": 0.24969368278980256,
|
|
"num_tokens": 79572843.0,
|
|
"step": 28475
|
|
},
|
|
{
|
|
"entropy": 4.856994867324829,
|
|
"epoch": 3.3924955330553903,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003887352243986894,
|
|
"loss": 4.4903,
|
|
"mean_token_accuracy": 0.24127780348062516,
|
|
"num_tokens": 79588207.0,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"entropy": 4.7183980464935305,
|
|
"epoch": 3.3930911256700416,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003886984547936921,
|
|
"loss": 4.3231,
|
|
"mean_token_accuracy": 0.2559518426656723,
|
|
"num_tokens": 79602490.0,
|
|
"step": 28485
|
|
},
|
|
{
|
|
"entropy": 4.791283750534058,
|
|
"epoch": 3.3936867182846933,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003886616811105162,
|
|
"loss": 4.3615,
|
|
"mean_token_accuracy": 0.24524053633213044,
|
|
"num_tokens": 79618382.0,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"entropy": 4.768812084197998,
|
|
"epoch": 3.394282310899345,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00038862490335048064,
|
|
"loss": 4.3566,
|
|
"mean_token_accuracy": 0.24152295142412186,
|
|
"num_tokens": 79634962.0,
|
|
"step": 28495
|
|
},
|
|
{
|
|
"entropy": 4.7849232196807865,
|
|
"epoch": 3.394877903513996,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038858812151490435,
|
|
"loss": 4.4109,
|
|
"mean_token_accuracy": 0.2462003856897354,
|
|
"num_tokens": 79649325.0,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"entropy": 4.69215955734253,
|
|
"epoch": 3.395473496128648,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000388551335605107,
|
|
"loss": 4.3154,
|
|
"mean_token_accuracy": 0.24963009655475615,
|
|
"num_tokens": 79661651.0,
|
|
"step": 28505
|
|
},
|
|
{
|
|
"entropy": 4.789693212509155,
|
|
"epoch": 3.3960690887432996,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00038851454562240773,
|
|
"loss": 4.4076,
|
|
"mean_token_accuracy": 0.25035971254110334,
|
|
"num_tokens": 79675567.0,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"entropy": 4.843389892578125,
|
|
"epoch": 3.3966646813579513,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003884777515681264,
|
|
"loss": 4.4514,
|
|
"mean_token_accuracy": 0.23753579556941987,
|
|
"num_tokens": 79690091.0,
|
|
"step": 28515
|
|
},
|
|
{
|
|
"entropy": 4.821670007705689,
|
|
"epoch": 3.3972602739726026,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00038844095344358254,
|
|
"loss": 4.4411,
|
|
"mean_token_accuracy": 0.2406662419438362,
|
|
"num_tokens": 79706171.0,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"entropy": 4.738582897186279,
|
|
"epoch": 3.3978558665872542,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00038840415125009623,
|
|
"loss": 4.3558,
|
|
"mean_token_accuracy": 0.24615718722343444,
|
|
"num_tokens": 79721371.0,
|
|
"step": 28525
|
|
},
|
|
{
|
|
"entropy": 4.880258989334107,
|
|
"epoch": 3.398451459201906,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003883673449889873,
|
|
"loss": 4.4957,
|
|
"mean_token_accuracy": 0.23646678775548935,
|
|
"num_tokens": 79735083.0,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"entropy": 4.807406997680664,
|
|
"epoch": 3.3990470518165576,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000388330534661576,
|
|
"loss": 4.468,
|
|
"mean_token_accuracy": 0.24401642084121705,
|
|
"num_tokens": 79750095.0,
|
|
"step": 28535
|
|
},
|
|
{
|
|
"entropy": 4.746306037902832,
|
|
"epoch": 3.399642644431209,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003882937202691828,
|
|
"loss": 4.3567,
|
|
"mean_token_accuracy": 0.24945542961359024,
|
|
"num_tokens": 79762685.0,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"entropy": 4.822926712036133,
|
|
"epoch": 3.4002382370458606,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00038825690181312793,
|
|
"loss": 4.4359,
|
|
"mean_token_accuracy": 0.2443309247493744,
|
|
"num_tokens": 79775142.0,
|
|
"step": 28545
|
|
},
|
|
{
|
|
"entropy": 4.784904861450196,
|
|
"epoch": 3.4008338296605123,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003882200792947322,
|
|
"loss": 4.3832,
|
|
"mean_token_accuracy": 0.23715304881334304,
|
|
"num_tokens": 79791189.0,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"entropy": 4.785731172561645,
|
|
"epoch": 3.4014294222751635,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0003881832527153163,
|
|
"loss": 4.2973,
|
|
"mean_token_accuracy": 0.25276957750320433,
|
|
"num_tokens": 79803743.0,
|
|
"step": 28555
|
|
},
|
|
{
|
|
"entropy": 4.857995986938477,
|
|
"epoch": 3.4020250148898152,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003881464220762012,
|
|
"loss": 4.4571,
|
|
"mean_token_accuracy": 0.2344738781452179,
|
|
"num_tokens": 79819952.0,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"entropy": 4.8188232421875,
|
|
"epoch": 3.402620607504467,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003881095873787079,
|
|
"loss": 4.4228,
|
|
"mean_token_accuracy": 0.23839259892702103,
|
|
"num_tokens": 79832809.0,
|
|
"step": 28565
|
|
},
|
|
{
|
|
"entropy": 4.784341335296631,
|
|
"epoch": 3.4032162001191186,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00038807274862415756,
|
|
"loss": 4.4059,
|
|
"mean_token_accuracy": 0.2515587851405144,
|
|
"num_tokens": 79848369.0,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"entropy": 4.82908034324646,
|
|
"epoch": 3.4038117927337703,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00038803590581387156,
|
|
"loss": 4.3978,
|
|
"mean_token_accuracy": 0.24303909689188002,
|
|
"num_tokens": 79862298.0,
|
|
"step": 28575
|
|
},
|
|
{
|
|
"entropy": 4.791672039031982,
|
|
"epoch": 3.4044073853484216,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038799905894917143,
|
|
"loss": 4.4102,
|
|
"mean_token_accuracy": 0.24373553991317748,
|
|
"num_tokens": 79875800.0,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"entropy": 4.818418502807617,
|
|
"epoch": 3.4050029779630733,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003879622080313788,
|
|
"loss": 4.4521,
|
|
"mean_token_accuracy": 0.24268707185983657,
|
|
"num_tokens": 79889176.0,
|
|
"step": 28585
|
|
},
|
|
{
|
|
"entropy": 4.767510604858399,
|
|
"epoch": 3.405598570577725,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038792535306181536,
|
|
"loss": 4.3206,
|
|
"mean_token_accuracy": 0.2553145051002502,
|
|
"num_tokens": 79901801.0,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"entropy": 4.90285472869873,
|
|
"epoch": 3.4061941631923762,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003878884940418032,
|
|
"loss": 4.506,
|
|
"mean_token_accuracy": 0.23631419539451598,
|
|
"num_tokens": 79915451.0,
|
|
"step": 28595
|
|
},
|
|
{
|
|
"entropy": 4.82772421836853,
|
|
"epoch": 3.406789755807028,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00038785163097266424,
|
|
"loss": 4.4617,
|
|
"mean_token_accuracy": 0.240449421107769,
|
|
"num_tokens": 79928632.0,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"entropy": 4.743516540527343,
|
|
"epoch": 3.4073853484216796,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038781476385572075,
|
|
"loss": 4.3437,
|
|
"mean_token_accuracy": 0.2512801691889763,
|
|
"num_tokens": 79940292.0,
|
|
"step": 28605
|
|
},
|
|
{
|
|
"entropy": 4.762499094009399,
|
|
"epoch": 3.4079809410363313,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003877778926922952,
|
|
"loss": 4.3981,
|
|
"mean_token_accuracy": 0.2483108952641487,
|
|
"num_tokens": 79955544.0,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"entropy": 4.759169292449951,
|
|
"epoch": 3.4085765336509826,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003877410174837099,
|
|
"loss": 4.3616,
|
|
"mean_token_accuracy": 0.251052325963974,
|
|
"num_tokens": 79969688.0,
|
|
"step": 28615
|
|
},
|
|
{
|
|
"entropy": 4.8921098709106445,
|
|
"epoch": 3.4091721262656343,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00038770413823128764,
|
|
"loss": 4.4865,
|
|
"mean_token_accuracy": 0.23416720628738402,
|
|
"num_tokens": 79984016.0,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"entropy": 4.85396900177002,
|
|
"epoch": 3.409767718880286,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00038766725493635123,
|
|
"loss": 4.5039,
|
|
"mean_token_accuracy": 0.23011019080877304,
|
|
"num_tokens": 80000237.0,
|
|
"step": 28625
|
|
},
|
|
{
|
|
"entropy": 4.8321120262146,
|
|
"epoch": 3.4103633114949377,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038763036760022356,
|
|
"loss": 4.4429,
|
|
"mean_token_accuracy": 0.2497226506471634,
|
|
"num_tokens": 80013520.0,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"entropy": 4.739975881576538,
|
|
"epoch": 3.410958904109589,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.00038759347622422774,
|
|
"loss": 4.3769,
|
|
"mean_token_accuracy": 0.2546906709671021,
|
|
"num_tokens": 80027660.0,
|
|
"step": 28635
|
|
},
|
|
{
|
|
"entropy": 4.801723194122315,
|
|
"epoch": 3.4115544967242406,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003875565808096869,
|
|
"loss": 4.4205,
|
|
"mean_token_accuracy": 0.2489562600851059,
|
|
"num_tokens": 80041062.0,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"entropy": 4.749373197555542,
|
|
"epoch": 3.4121500893388923,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003875196813579246,
|
|
"loss": 4.3698,
|
|
"mean_token_accuracy": 0.24325964897871016,
|
|
"num_tokens": 80053940.0,
|
|
"step": 28645
|
|
},
|
|
{
|
|
"entropy": 4.832703590393066,
|
|
"epoch": 3.4127456819535436,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003874827778702643,
|
|
"loss": 4.4351,
|
|
"mean_token_accuracy": 0.2424188271164894,
|
|
"num_tokens": 80067097.0,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"entropy": 4.778190565109253,
|
|
"epoch": 3.4133412745681952,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003874458703480296,
|
|
"loss": 4.4263,
|
|
"mean_token_accuracy": 0.2464842364192009,
|
|
"num_tokens": 80081294.0,
|
|
"step": 28655
|
|
},
|
|
{
|
|
"entropy": 4.764107656478882,
|
|
"epoch": 3.413936867182847,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038740895879254433,
|
|
"loss": 4.3701,
|
|
"mean_token_accuracy": 0.24628763049840927,
|
|
"num_tokens": 80095117.0,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"entropy": 4.808184385299683,
|
|
"epoch": 3.4145324597974986,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00038737204320513254,
|
|
"loss": 4.404,
|
|
"mean_token_accuracy": 0.24138575941324233,
|
|
"num_tokens": 80110519.0,
|
|
"step": 28665
|
|
},
|
|
{
|
|
"entropy": 4.777184057235718,
|
|
"epoch": 3.4151280524121503,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003873351235871181,
|
|
"loss": 4.3902,
|
|
"mean_token_accuracy": 0.24552237391471862,
|
|
"num_tokens": 80124824.0,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"entropy": 4.8203939437866214,
|
|
"epoch": 3.4157236450268016,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00038729819993982566,
|
|
"loss": 4.4427,
|
|
"mean_token_accuracy": 0.24190025627613068,
|
|
"num_tokens": 80137976.0,
|
|
"step": 28675
|
|
},
|
|
{
|
|
"entropy": 4.824670934677124,
|
|
"epoch": 3.4163192376414533,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003872612722645792,
|
|
"loss": 4.4413,
|
|
"mean_token_accuracy": 0.244223053753376,
|
|
"num_tokens": 80151686.0,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"entropy": 4.785607862472534,
|
|
"epoch": 3.416914830256105,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038722434056270356,
|
|
"loss": 4.3997,
|
|
"mean_token_accuracy": 0.24320320039987564,
|
|
"num_tokens": 80166550.0,
|
|
"step": 28685
|
|
},
|
|
{
|
|
"entropy": 4.728652286529541,
|
|
"epoch": 3.4175104228707562,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003871874048355233,
|
|
"loss": 4.3305,
|
|
"mean_token_accuracy": 0.2511701837182045,
|
|
"num_tokens": 80179197.0,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"entropy": 4.7468485832214355,
|
|
"epoch": 3.418106015485408,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00038715046508436306,
|
|
"loss": 4.3472,
|
|
"mean_token_accuracy": 0.2481576144695282,
|
|
"num_tokens": 80193364.0,
|
|
"step": 28695
|
|
},
|
|
{
|
|
"entropy": 4.8086248397827145,
|
|
"epoch": 3.4187016081000596,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038711352131054813,
|
|
"loss": 4.4601,
|
|
"mean_token_accuracy": 0.23858631998300553,
|
|
"num_tokens": 80207826.0,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"entropy": 4.7905144691467285,
|
|
"epoch": 3.4192972007147113,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003870765735154034,
|
|
"loss": 4.3768,
|
|
"mean_token_accuracy": 0.2514320135116577,
|
|
"num_tokens": 80220079.0,
|
|
"step": 28705
|
|
},
|
|
{
|
|
"entropy": 4.811188650131226,
|
|
"epoch": 3.4198927933293626,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003870396217002542,
|
|
"loss": 4.4102,
|
|
"mean_token_accuracy": 0.24744724482297897,
|
|
"num_tokens": 80232865.0,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"entropy": 4.766029787063599,
|
|
"epoch": 3.4204883859440143,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038700266586642597,
|
|
"loss": 4.4001,
|
|
"mean_token_accuracy": 0.24804145991802215,
|
|
"num_tokens": 80246381.0,
|
|
"step": 28715
|
|
},
|
|
{
|
|
"entropy": 4.813641691207886,
|
|
"epoch": 3.421083978558666,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003869657060152443,
|
|
"loss": 4.502,
|
|
"mean_token_accuracy": 0.2363559514284134,
|
|
"num_tokens": 80261688.0,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"entropy": 4.738937520980835,
|
|
"epoch": 3.4216795711733177,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003869287421480347,
|
|
"loss": 4.26,
|
|
"mean_token_accuracy": 0.26486887186765673,
|
|
"num_tokens": 80275782.0,
|
|
"step": 28725
|
|
},
|
|
{
|
|
"entropy": 4.751482915878296,
|
|
"epoch": 3.422275163787969,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003868917742661231,
|
|
"loss": 4.3847,
|
|
"mean_token_accuracy": 0.25099640488624575,
|
|
"num_tokens": 80290877.0,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"entropy": 4.74449520111084,
|
|
"epoch": 3.4228707564026206,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038685480237083547,
|
|
"loss": 4.3345,
|
|
"mean_token_accuracy": 0.2589446514844894,
|
|
"num_tokens": 80304239.0,
|
|
"step": 28735
|
|
},
|
|
{
|
|
"entropy": 4.682726097106934,
|
|
"epoch": 3.4234663490172723,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000386817826463498,
|
|
"loss": 4.2438,
|
|
"mean_token_accuracy": 0.2675758346915245,
|
|
"num_tokens": 80319224.0,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"entropy": 4.717236852645874,
|
|
"epoch": 3.4240619416319236,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003867808465454368,
|
|
"loss": 4.36,
|
|
"mean_token_accuracy": 0.24404603987932205,
|
|
"num_tokens": 80333250.0,
|
|
"step": 28745
|
|
},
|
|
{
|
|
"entropy": 4.775151872634888,
|
|
"epoch": 3.4246575342465753,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003867438626179785,
|
|
"loss": 4.4407,
|
|
"mean_token_accuracy": 0.2451443463563919,
|
|
"num_tokens": 80347929.0,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"entropy": 4.807559967041016,
|
|
"epoch": 3.425253126861227,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00038670687468244947,
|
|
"loss": 4.3779,
|
|
"mean_token_accuracy": 0.25159376561641694,
|
|
"num_tokens": 80362731.0,
|
|
"step": 28755
|
|
},
|
|
{
|
|
"entropy": 4.771134233474731,
|
|
"epoch": 3.4258487194758787,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003866698827401765,
|
|
"loss": 4.4339,
|
|
"mean_token_accuracy": 0.23867589235305786,
|
|
"num_tokens": 80376366.0,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"entropy": 4.7820594787597654,
|
|
"epoch": 3.42644431209053,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003866328867924864,
|
|
"loss": 4.3985,
|
|
"mean_token_accuracy": 0.2461097627878189,
|
|
"num_tokens": 80389483.0,
|
|
"step": 28765
|
|
},
|
|
{
|
|
"entropy": 4.725534963607788,
|
|
"epoch": 3.4270399047051816,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003865958868407061,
|
|
"loss": 4.3122,
|
|
"mean_token_accuracy": 0.252581912279129,
|
|
"num_tokens": 80401129.0,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"entropy": 4.74785041809082,
|
|
"epoch": 3.4276354973198333,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003865588828861629,
|
|
"loss": 4.5055,
|
|
"mean_token_accuracy": 0.2462083727121353,
|
|
"num_tokens": 80413498.0,
|
|
"step": 28775
|
|
},
|
|
{
|
|
"entropy": 4.809371280670166,
|
|
"epoch": 3.428231089934485,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003865218749301838,
|
|
"loss": 4.3829,
|
|
"mean_token_accuracy": 0.24415990263223647,
|
|
"num_tokens": 80427971.0,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"entropy": 4.785028123855591,
|
|
"epoch": 3.4288266825491363,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003864848629740965,
|
|
"loss": 4.4373,
|
|
"mean_token_accuracy": 0.2393994688987732,
|
|
"num_tokens": 80441648.0,
|
|
"step": 28785
|
|
},
|
|
{
|
|
"entropy": 4.758919715881348,
|
|
"epoch": 3.429422275163788,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038644784701922835,
|
|
"loss": 4.3239,
|
|
"mean_token_accuracy": 0.24463005512952804,
|
|
"num_tokens": 80454099.0,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"entropy": 4.874612331390381,
|
|
"epoch": 3.4300178677784396,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038641082706690716,
|
|
"loss": 4.5187,
|
|
"mean_token_accuracy": 0.2427385374903679,
|
|
"num_tokens": 80468091.0,
|
|
"step": 28795
|
|
},
|
|
{
|
|
"entropy": 4.815976762771607,
|
|
"epoch": 3.430613460393091,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00038637380311846075,
|
|
"loss": 4.3706,
|
|
"mean_token_accuracy": 0.24298965483903884,
|
|
"num_tokens": 80480643.0,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"entropy": 4.904421663284301,
|
|
"epoch": 3.4312090530077426,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003863367751752171,
|
|
"loss": 4.58,
|
|
"mean_token_accuracy": 0.22574420422315597,
|
|
"num_tokens": 80493633.0,
|
|
"step": 28805
|
|
},
|
|
{
|
|
"entropy": 4.860826444625855,
|
|
"epoch": 3.4318046456223943,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003862997432385043,
|
|
"loss": 4.455,
|
|
"mean_token_accuracy": 0.241801917552948,
|
|
"num_tokens": 80508268.0,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"entropy": 4.736325645446778,
|
|
"epoch": 3.432400238237046,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003862627073096508,
|
|
"loss": 4.3185,
|
|
"mean_token_accuracy": 0.2553770899772644,
|
|
"num_tokens": 80521579.0,
|
|
"step": 28815
|
|
},
|
|
{
|
|
"entropy": 4.798646354675293,
|
|
"epoch": 3.4329958308516977,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003862256673899848,
|
|
"loss": 4.4059,
|
|
"mean_token_accuracy": 0.24409022629261018,
|
|
"num_tokens": 80534950.0,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"entropy": 4.809395885467529,
|
|
"epoch": 3.433591423466349,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003861886234808349,
|
|
"loss": 4.4605,
|
|
"mean_token_accuracy": 0.24281534254550935,
|
|
"num_tokens": 80548970.0,
|
|
"step": 28825
|
|
},
|
|
{
|
|
"entropy": 4.797947978973388,
|
|
"epoch": 3.4341870160810006,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00038615157558353,
|
|
"loss": 4.3472,
|
|
"mean_token_accuracy": 0.24674547463655472,
|
|
"num_tokens": 80563387.0,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"entropy": 4.827268362045288,
|
|
"epoch": 3.4347826086956523,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038611452369939864,
|
|
"loss": 4.4934,
|
|
"mean_token_accuracy": 0.23676319271326066,
|
|
"num_tokens": 80576939.0,
|
|
"step": 28835
|
|
},
|
|
{
|
|
"entropy": 4.7489217758178714,
|
|
"epoch": 3.4353782013103036,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003860774678297701,
|
|
"loss": 4.3871,
|
|
"mean_token_accuracy": 0.2413552939891815,
|
|
"num_tokens": 80591245.0,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"entropy": 4.8466424465179445,
|
|
"epoch": 3.4359737939249553,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00038604040797597335,
|
|
"loss": 4.4671,
|
|
"mean_token_accuracy": 0.23076062053442,
|
|
"num_tokens": 80604440.0,
|
|
"step": 28845
|
|
},
|
|
{
|
|
"entropy": 4.7229479312896725,
|
|
"epoch": 3.436569386539607,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003860033441393377,
|
|
"loss": 4.3122,
|
|
"mean_token_accuracy": 0.259015329182148,
|
|
"num_tokens": 80618803.0,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"entropy": 4.747756719589233,
|
|
"epoch": 3.4371649791542587,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038596627632119255,
|
|
"loss": 4.3484,
|
|
"mean_token_accuracy": 0.2470596358180046,
|
|
"num_tokens": 80633099.0,
|
|
"step": 28855
|
|
},
|
|
{
|
|
"entropy": 4.769489717483521,
|
|
"epoch": 3.43776057176891,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003859292045228676,
|
|
"loss": 4.3776,
|
|
"mean_token_accuracy": 0.25029055029153824,
|
|
"num_tokens": 80646494.0,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"entropy": 4.76742639541626,
|
|
"epoch": 3.4383561643835616,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038589212874569237,
|
|
"loss": 4.3554,
|
|
"mean_token_accuracy": 0.2554210990667343,
|
|
"num_tokens": 80662053.0,
|
|
"step": 28865
|
|
},
|
|
{
|
|
"entropy": 4.724194049835205,
|
|
"epoch": 3.4389517569982133,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0003858550489909967,
|
|
"loss": 4.2545,
|
|
"mean_token_accuracy": 0.25499277561903,
|
|
"num_tokens": 80675632.0,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"entropy": 4.77264928817749,
|
|
"epoch": 3.439547349612865,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003858179652601108,
|
|
"loss": 4.4364,
|
|
"mean_token_accuracy": 0.24155695587396622,
|
|
"num_tokens": 80691156.0,
|
|
"step": 28875
|
|
},
|
|
{
|
|
"entropy": 4.780932283401489,
|
|
"epoch": 3.4401429422275163,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003857808775543646,
|
|
"loss": 4.4277,
|
|
"mean_token_accuracy": 0.24597822725772858,
|
|
"num_tokens": 80704278.0,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"entropy": 4.843939018249512,
|
|
"epoch": 3.440738534842168,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003857437858750884,
|
|
"loss": 4.4347,
|
|
"mean_token_accuracy": 0.23990151882171631,
|
|
"num_tokens": 80718981.0,
|
|
"step": 28885
|
|
},
|
|
{
|
|
"entropy": 4.745156955718994,
|
|
"epoch": 3.4413341274568197,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00038570669022361273,
|
|
"loss": 4.3607,
|
|
"mean_token_accuracy": 0.24943193942308425,
|
|
"num_tokens": 80733483.0,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"entropy": 4.731619024276734,
|
|
"epoch": 3.441929720071471,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000385669590601268,
|
|
"loss": 4.3819,
|
|
"mean_token_accuracy": 0.24672045260667802,
|
|
"num_tokens": 80746834.0,
|
|
"step": 28895
|
|
},
|
|
{
|
|
"entropy": 4.803303289413452,
|
|
"epoch": 3.4425253126861226,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003856324870093851,
|
|
"loss": 4.3932,
|
|
"mean_token_accuracy": 0.24729582220315932,
|
|
"num_tokens": 80761728.0,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"entropy": 4.781686210632325,
|
|
"epoch": 3.4431209053007743,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00038559537944929465,
|
|
"loss": 4.3671,
|
|
"mean_token_accuracy": 0.2430396005511284,
|
|
"num_tokens": 80776138.0,
|
|
"step": 28905
|
|
},
|
|
{
|
|
"entropy": 4.690334892272949,
|
|
"epoch": 3.443716497915426,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0003855582679223279,
|
|
"loss": 4.2873,
|
|
"mean_token_accuracy": 0.2594291791319847,
|
|
"num_tokens": 80792088.0,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"entropy": 4.785591650009155,
|
|
"epoch": 3.4443120905300773,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00038552115242981573,
|
|
"loss": 4.4751,
|
|
"mean_token_accuracy": 0.23985066562891005,
|
|
"num_tokens": 80807516.0,
|
|
"step": 28915
|
|
},
|
|
{
|
|
"entropy": 4.776434707641601,
|
|
"epoch": 3.444907683144729,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00038548403297308955,
|
|
"loss": 4.3499,
|
|
"mean_token_accuracy": 0.25180527567863464,
|
|
"num_tokens": 80821394.0,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"entropy": 4.818357276916504,
|
|
"epoch": 3.4455032757593806,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038544690955348077,
|
|
"loss": 4.4635,
|
|
"mean_token_accuracy": 0.23871086090803145,
|
|
"num_tokens": 80835231.0,
|
|
"step": 28925
|
|
},
|
|
{
|
|
"entropy": 4.881836700439453,
|
|
"epoch": 3.4460988683740323,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038540978217232086,
|
|
"loss": 4.5195,
|
|
"mean_token_accuracy": 0.22954975366592406,
|
|
"num_tokens": 80848680.0,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"entropy": 4.806451749801636,
|
|
"epoch": 3.4466944609886836,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003853726508309416,
|
|
"loss": 4.4462,
|
|
"mean_token_accuracy": 0.24229174703359604,
|
|
"num_tokens": 80862966.0,
|
|
"step": 28935
|
|
},
|
|
{
|
|
"entropy": 4.814884853363037,
|
|
"epoch": 3.4472900536033353,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003853355155306748,
|
|
"loss": 4.454,
|
|
"mean_token_accuracy": 0.23702566474676132,
|
|
"num_tokens": 80879028.0,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"entropy": 4.686403608322143,
|
|
"epoch": 3.447885646217987,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038529837627285246,
|
|
"loss": 4.2814,
|
|
"mean_token_accuracy": 0.2549467712640762,
|
|
"num_tokens": 80893505.0,
|
|
"step": 28945
|
|
},
|
|
{
|
|
"entropy": 4.8748575210571286,
|
|
"epoch": 3.4484812388326382,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003852612330588067,
|
|
"loss": 4.4721,
|
|
"mean_token_accuracy": 0.23555505275726318,
|
|
"num_tokens": 80908100.0,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"entropy": 4.772454929351807,
|
|
"epoch": 3.44907683144729,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00038522408588986985,
|
|
"loss": 4.4038,
|
|
"mean_token_accuracy": 0.2452249765396118,
|
|
"num_tokens": 80921652.0,
|
|
"step": 28955
|
|
},
|
|
{
|
|
"entropy": 4.751867628097534,
|
|
"epoch": 3.4496724240619416,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003851869347673742,
|
|
"loss": 4.3999,
|
|
"mean_token_accuracy": 0.2417986810207367,
|
|
"num_tokens": 80934087.0,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"entropy": 4.741327142715454,
|
|
"epoch": 3.4502680166765933,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038514977969265234,
|
|
"loss": 4.2949,
|
|
"mean_token_accuracy": 0.2541873618960381,
|
|
"num_tokens": 80947112.0,
|
|
"step": 28965
|
|
},
|
|
{
|
|
"entropy": 4.812667560577393,
|
|
"epoch": 3.450863609291245,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003851126206670369,
|
|
"loss": 4.5003,
|
|
"mean_token_accuracy": 0.23424229472875596,
|
|
"num_tokens": 80958918.0,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"entropy": 4.788296508789062,
|
|
"epoch": 3.4514592019058963,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00038507545769186094,
|
|
"loss": 4.4235,
|
|
"mean_token_accuracy": 0.24646183401346206,
|
|
"num_tokens": 80973694.0,
|
|
"step": 28975
|
|
},
|
|
{
|
|
"entropy": 4.7497645854949955,
|
|
"epoch": 3.452054794520548,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0003850382907684572,
|
|
"loss": 4.3371,
|
|
"mean_token_accuracy": 0.24653341323137284,
|
|
"num_tokens": 80988417.0,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"entropy": 4.837302112579346,
|
|
"epoch": 3.4526503871351997,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00038500111989815894,
|
|
"loss": 4.3962,
|
|
"mean_token_accuracy": 0.24573962539434432,
|
|
"num_tokens": 81001672.0,
|
|
"step": 28985
|
|
},
|
|
{
|
|
"entropy": 4.862812662124634,
|
|
"epoch": 3.453245979749851,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00038496394508229925,
|
|
"loss": 4.4969,
|
|
"mean_token_accuracy": 0.23608110696077347,
|
|
"num_tokens": 81017049.0,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"entropy": 4.822233009338379,
|
|
"epoch": 3.4538415723645026,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00038492676632221175,
|
|
"loss": 4.4323,
|
|
"mean_token_accuracy": 0.247769495844841,
|
|
"num_tokens": 81031516.0,
|
|
"step": 28995
|
|
},
|
|
{
|
|
"entropy": 4.838186311721802,
|
|
"epoch": 3.4544371649791543,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00038488958361922984,
|
|
"loss": 4.4502,
|
|
"mean_token_accuracy": 0.23942428231239318,
|
|
"num_tokens": 81045894.0,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"entropy": 4.7792271137237545,
|
|
"epoch": 3.455032757593806,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00038485239697468715,
|
|
"loss": 4.4898,
|
|
"mean_token_accuracy": 0.23931564688682555,
|
|
"num_tokens": 81063143.0,
|
|
"step": 29005
|
|
},
|
|
{
|
|
"entropy": 4.793621015548706,
|
|
"epoch": 3.4556283502084573,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003848152063899177,
|
|
"loss": 4.3288,
|
|
"mean_token_accuracy": 0.24942028373479844,
|
|
"num_tokens": 81077050.0,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"entropy": 4.818116044998169,
|
|
"epoch": 3.456223942823109,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038477801186625533,
|
|
"loss": 4.3873,
|
|
"mean_token_accuracy": 0.25014942735433576,
|
|
"num_tokens": 81091942.0,
|
|
"step": 29015
|
|
},
|
|
{
|
|
"entropy": 4.809658336639404,
|
|
"epoch": 3.4568195354377607,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038474081340503414,
|
|
"loss": 4.4423,
|
|
"mean_token_accuracy": 0.2377608075737953,
|
|
"num_tokens": 81104984.0,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"entropy": 4.792799711227417,
|
|
"epoch": 3.4574151280524124,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0003847036110075884,
|
|
"loss": 4.4448,
|
|
"mean_token_accuracy": 0.2409555658698082,
|
|
"num_tokens": 81121241.0,
|
|
"step": 29025
|
|
},
|
|
{
|
|
"entropy": 4.817486906051636,
|
|
"epoch": 3.4580107206670636,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00038466640467525254,
|
|
"loss": 4.4212,
|
|
"mean_token_accuracy": 0.2449526309967041,
|
|
"num_tokens": 81135350.0,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"entropy": 4.8387171745300295,
|
|
"epoch": 3.4586063132817153,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00038462919440936094,
|
|
"loss": 4.4511,
|
|
"mean_token_accuracy": 0.24715524464845656,
|
|
"num_tokens": 81148192.0,
|
|
"step": 29035
|
|
},
|
|
{
|
|
"entropy": 4.799556112289428,
|
|
"epoch": 3.459201905896367,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00038459198021124853,
|
|
"loss": 4.3958,
|
|
"mean_token_accuracy": 0.2483133554458618,
|
|
"num_tokens": 81162324.0,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"entropy": 4.7659882545471195,
|
|
"epoch": 3.4597974985110183,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003845547620822498,
|
|
"loss": 4.3897,
|
|
"mean_token_accuracy": 0.2524033963680267,
|
|
"num_tokens": 81175978.0,
|
|
"step": 29045
|
|
},
|
|
{
|
|
"entropy": 4.7287554264068605,
|
|
"epoch": 3.46039309112567,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00038451754002370004,
|
|
"loss": 4.3068,
|
|
"mean_token_accuracy": 0.2547963261604309,
|
|
"num_tokens": 81188316.0,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"entropy": 4.707996797561646,
|
|
"epoch": 3.4609886837403216,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003844803140369342,
|
|
"loss": 4.3271,
|
|
"mean_token_accuracy": 0.2522635906934738,
|
|
"num_tokens": 81202037.0,
|
|
"step": 29055
|
|
},
|
|
{
|
|
"entropy": 4.856210374832154,
|
|
"epoch": 3.4615842763549733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003844430841232873,
|
|
"loss": 4.5053,
|
|
"mean_token_accuracy": 0.2362519085407257,
|
|
"num_tokens": 81215957.0,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"entropy": 4.849500703811645,
|
|
"epoch": 3.4621798689696246,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003844058502840951,
|
|
"loss": 4.4833,
|
|
"mean_token_accuracy": 0.23850267827510835,
|
|
"num_tokens": 81230415.0,
|
|
"step": 29065
|
|
},
|
|
{
|
|
"entropy": 4.78666090965271,
|
|
"epoch": 3.4627754615842763,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003843686125206928,
|
|
"loss": 4.3689,
|
|
"mean_token_accuracy": 0.24880080074071884,
|
|
"num_tokens": 81241519.0,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"entropy": 4.735047817230225,
|
|
"epoch": 3.463371054198928,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003843313708344163,
|
|
"loss": 4.3312,
|
|
"mean_token_accuracy": 0.2523442506790161,
|
|
"num_tokens": 81254466.0,
|
|
"step": 29075
|
|
},
|
|
{
|
|
"entropy": 4.832787656784058,
|
|
"epoch": 3.4639666468135797,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003842941252266013,
|
|
"loss": 4.4924,
|
|
"mean_token_accuracy": 0.23848651200532914,
|
|
"num_tokens": 81268014.0,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"entropy": 4.8562945365905765,
|
|
"epoch": 3.464562239428231,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003842568756985837,
|
|
"loss": 4.4715,
|
|
"mean_token_accuracy": 0.24358444213867186,
|
|
"num_tokens": 81283567.0,
|
|
"step": 29085
|
|
},
|
|
{
|
|
"entropy": 4.818210172653198,
|
|
"epoch": 3.4651578320428826,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00038421962225169954,
|
|
"loss": 4.427,
|
|
"mean_token_accuracy": 0.2396508425474167,
|
|
"num_tokens": 81298373.0,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"entropy": 4.767684507369995,
|
|
"epoch": 3.4657534246575343,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003841823648872852,
|
|
"loss": 4.3705,
|
|
"mean_token_accuracy": 0.24649859666824342,
|
|
"num_tokens": 81312560.0,
|
|
"step": 29095
|
|
},
|
|
{
|
|
"entropy": 4.768068456649781,
|
|
"epoch": 3.4663490172721856,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003841451036066769,
|
|
"loss": 4.3902,
|
|
"mean_token_accuracy": 0.24586798697710038,
|
|
"num_tokens": 81325279.0,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"entropy": 4.764687967300415,
|
|
"epoch": 3.4669446098868373,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00038410783841121124,
|
|
"loss": 4.3423,
|
|
"mean_token_accuracy": 0.24806736707687377,
|
|
"num_tokens": 81339847.0,
|
|
"step": 29105
|
|
},
|
|
{
|
|
"entropy": 4.836872291564942,
|
|
"epoch": 3.467540202501489,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003840705693022248,
|
|
"loss": 4.4791,
|
|
"mean_token_accuracy": 0.24024665504693984,
|
|
"num_tokens": 81352479.0,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"entropy": 4.746706771850586,
|
|
"epoch": 3.4681357951161407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003840332962810543,
|
|
"loss": 4.3615,
|
|
"mean_token_accuracy": 0.24849707186222075,
|
|
"num_tokens": 81364708.0,
|
|
"step": 29115
|
|
},
|
|
{
|
|
"entropy": 4.666823863983154,
|
|
"epoch": 3.4687313877307924,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003839960193490368,
|
|
"loss": 4.2852,
|
|
"mean_token_accuracy": 0.25602707266807556,
|
|
"num_tokens": 81378245.0,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"entropy": 4.832547616958618,
|
|
"epoch": 3.4693269803454436,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003839587385075093,
|
|
"loss": 4.4432,
|
|
"mean_token_accuracy": 0.2381943166255951,
|
|
"num_tokens": 81392493.0,
|
|
"step": 29125
|
|
},
|
|
{
|
|
"entropy": 4.79042615890503,
|
|
"epoch": 3.4699225729600953,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000383921453757809,
|
|
"loss": 4.4029,
|
|
"mean_token_accuracy": 0.247467739880085,
|
|
"num_tokens": 81407157.0,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"entropy": 4.784522438049317,
|
|
"epoch": 3.470518165574747,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003838841651012733,
|
|
"loss": 4.3691,
|
|
"mean_token_accuracy": 0.25048479437828064,
|
|
"num_tokens": 81420036.0,
|
|
"step": 29135
|
|
},
|
|
{
|
|
"entropy": 4.8034529209136965,
|
|
"epoch": 3.4711137581893983,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00038384687253923956,
|
|
"loss": 4.493,
|
|
"mean_token_accuracy": 0.24541191458702089,
|
|
"num_tokens": 81434715.0,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"entropy": 4.8560975074768065,
|
|
"epoch": 3.47170935080405,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00038380957607304553,
|
|
"loss": 4.4251,
|
|
"mean_token_accuracy": 0.24444044530391693,
|
|
"num_tokens": 81448505.0,
|
|
"step": 29145
|
|
},
|
|
{
|
|
"entropy": 4.769432783126831,
|
|
"epoch": 3.4723049434187017,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003837722757040289,
|
|
"loss": 4.3742,
|
|
"mean_token_accuracy": 0.24713025540113448,
|
|
"num_tokens": 81461997.0,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"entropy": 4.736823701858521,
|
|
"epoch": 3.4729005360333534,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038373497143352764,
|
|
"loss": 4.422,
|
|
"mean_token_accuracy": 0.2451208531856537,
|
|
"num_tokens": 81475878.0,
|
|
"step": 29155
|
|
},
|
|
{
|
|
"entropy": 4.812538909912109,
|
|
"epoch": 3.4734961286480046,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003836976632628797,
|
|
"loss": 4.4519,
|
|
"mean_token_accuracy": 0.24223184138536452,
|
|
"num_tokens": 81489115.0,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"entropy": 4.85396671295166,
|
|
"epoch": 3.4740917212626563,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00038366035119342327,
|
|
"loss": 4.4869,
|
|
"mean_token_accuracy": 0.239462211728096,
|
|
"num_tokens": 81503969.0,
|
|
"step": 29165
|
|
},
|
|
{
|
|
"entropy": 4.7918372631073,
|
|
"epoch": 3.474687313877308,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003836230352264968,
|
|
"loss": 4.3909,
|
|
"mean_token_accuracy": 0.24785963892936708,
|
|
"num_tokens": 81517740.0,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"entropy": 4.711308193206787,
|
|
"epoch": 3.4752829064919597,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003835857153634385,
|
|
"loss": 4.2794,
|
|
"mean_token_accuracy": 0.2525432899594307,
|
|
"num_tokens": 81531497.0,
|
|
"step": 29175
|
|
},
|
|
{
|
|
"entropy": 4.8099915981292725,
|
|
"epoch": 3.475878499106611,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00038354839160558736,
|
|
"loss": 4.4114,
|
|
"mean_token_accuracy": 0.244362972676754,
|
|
"num_tokens": 81546871.0,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"entropy": 4.797192049026489,
|
|
"epoch": 3.4764740917212626,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003835110639542817,
|
|
"loss": 4.3936,
|
|
"mean_token_accuracy": 0.2420945569872856,
|
|
"num_tokens": 81561845.0,
|
|
"step": 29185
|
|
},
|
|
{
|
|
"entropy": 4.808348369598389,
|
|
"epoch": 3.4770696843359143,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00038347373241086075,
|
|
"loss": 4.4242,
|
|
"mean_token_accuracy": 0.2511287420988083,
|
|
"num_tokens": 81576258.0,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"entropy": 4.798850440979004,
|
|
"epoch": 3.4776652769505656,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00038343639697666337,
|
|
"loss": 4.4251,
|
|
"mean_token_accuracy": 0.2455781042575836,
|
|
"num_tokens": 81591414.0,
|
|
"step": 29195
|
|
},
|
|
{
|
|
"entropy": 4.743184280395508,
|
|
"epoch": 3.4782608695652173,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003833990576530287,
|
|
"loss": 4.296,
|
|
"mean_token_accuracy": 0.25879954397678373,
|
|
"num_tokens": 81603565.0,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"entropy": 4.748832845687867,
|
|
"epoch": 3.478856462179869,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003833617144412961,
|
|
"loss": 4.3481,
|
|
"mean_token_accuracy": 0.24677981287240983,
|
|
"num_tokens": 81618204.0,
|
|
"step": 29205
|
|
},
|
|
{
|
|
"entropy": 4.744263982772827,
|
|
"epoch": 3.4794520547945207,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000383324367342805,
|
|
"loss": 4.3895,
|
|
"mean_token_accuracy": 0.24891225695610047,
|
|
"num_tokens": 81630157.0,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"entropy": 4.7212395668029785,
|
|
"epoch": 3.480047647409172,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003832870163588949,
|
|
"loss": 4.3704,
|
|
"mean_token_accuracy": 0.24818326830863952,
|
|
"num_tokens": 81643608.0,
|
|
"step": 29215
|
|
},
|
|
{
|
|
"entropy": 4.813976526260376,
|
|
"epoch": 3.4806432400238236,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038324966149090557,
|
|
"loss": 4.4138,
|
|
"mean_token_accuracy": 0.24765202403068542,
|
|
"num_tokens": 81657411.0,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"entropy": 4.752273368835449,
|
|
"epoch": 3.4812388326384753,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000383212302740177,
|
|
"loss": 4.3554,
|
|
"mean_token_accuracy": 0.2509397387504578,
|
|
"num_tokens": 81670448.0,
|
|
"step": 29225
|
|
},
|
|
{
|
|
"entropy": 4.771467685699463,
|
|
"epoch": 3.481834425253127,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000383174940108049,
|
|
"loss": 4.4158,
|
|
"mean_token_accuracy": 0.2443507730960846,
|
|
"num_tokens": 81681996.0,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"entropy": 4.71423373222351,
|
|
"epoch": 3.4824300178677783,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003831375735958618,
|
|
"loss": 4.3083,
|
|
"mean_token_accuracy": 0.26131960898637774,
|
|
"num_tokens": 81695096.0,
|
|
"step": 29235
|
|
},
|
|
{
|
|
"entropy": 4.722962760925293,
|
|
"epoch": 3.48302561048243,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003831002032049557,
|
|
"loss": 4.3381,
|
|
"mean_token_accuracy": 0.2543421357870102,
|
|
"num_tokens": 81708504.0,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"entropy": 4.874344968795777,
|
|
"epoch": 3.4836212030970817,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038306282893667097,
|
|
"loss": 4.4471,
|
|
"mean_token_accuracy": 0.23807919025421143,
|
|
"num_tokens": 81722893.0,
|
|
"step": 29245
|
|
},
|
|
{
|
|
"entropy": 4.827772569656372,
|
|
"epoch": 3.484216795711733,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038302545079234833,
|
|
"loss": 4.4315,
|
|
"mean_token_accuracy": 0.23950205445289613,
|
|
"num_tokens": 81737029.0,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"entropy": 4.751695442199707,
|
|
"epoch": 3.4848123883263846,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003829880687733284,
|
|
"loss": 4.4155,
|
|
"mean_token_accuracy": 0.24681039452552794,
|
|
"num_tokens": 81749751.0,
|
|
"step": 29255
|
|
},
|
|
{
|
|
"entropy": 4.832977199554444,
|
|
"epoch": 3.4854079809410363,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0003829506828809521,
|
|
"loss": 4.4707,
|
|
"mean_token_accuracy": 0.2420685976743698,
|
|
"num_tokens": 81765109.0,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"entropy": 4.809509563446045,
|
|
"epoch": 3.486003573555688,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038291329311656013,
|
|
"loss": 4.4381,
|
|
"mean_token_accuracy": 0.24430502206087112,
|
|
"num_tokens": 81781098.0,
|
|
"step": 29265
|
|
},
|
|
{
|
|
"entropy": 4.775773382186889,
|
|
"epoch": 3.4865991661703397,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003828758994814939,
|
|
"loss": 4.3102,
|
|
"mean_token_accuracy": 0.25131590366363527,
|
|
"num_tokens": 81792569.0,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"entropy": 4.710330200195313,
|
|
"epoch": 3.487194758784991,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003828385019770946,
|
|
"loss": 4.4012,
|
|
"mean_token_accuracy": 0.24606603682041167,
|
|
"num_tokens": 81807913.0,
|
|
"step": 29275
|
|
},
|
|
{
|
|
"entropy": 4.820809745788575,
|
|
"epoch": 3.4877903513996427,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00038280110060470355,
|
|
"loss": 4.4173,
|
|
"mean_token_accuracy": 0.2420044168829918,
|
|
"num_tokens": 81819981.0,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"entropy": 4.840263795852661,
|
|
"epoch": 3.4883859440142944,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00038276369536566224,
|
|
"loss": 4.4514,
|
|
"mean_token_accuracy": 0.24213438332080842,
|
|
"num_tokens": 81834238.0,
|
|
"step": 29285
|
|
},
|
|
{
|
|
"entropy": 4.768301296234131,
|
|
"epoch": 3.4889815366289456,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00038272628626131246,
|
|
"loss": 4.377,
|
|
"mean_token_accuracy": 0.24744569212198259,
|
|
"num_tokens": 81848952.0,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"entropy": 4.769392824172973,
|
|
"epoch": 3.4895771292435973,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003826888732929959,
|
|
"loss": 4.3991,
|
|
"mean_token_accuracy": 0.2408041775226593,
|
|
"num_tokens": 81862367.0,
|
|
"step": 29295
|
|
},
|
|
{
|
|
"entropy": 4.832153081893921,
|
|
"epoch": 3.490172721858249,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00038265145646205453,
|
|
"loss": 4.3744,
|
|
"mean_token_accuracy": 0.24742707908153533,
|
|
"num_tokens": 81875567.0,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"entropy": 4.755547523498535,
|
|
"epoch": 3.4907683144729007,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00038261403576983044,
|
|
"loss": 4.4207,
|
|
"mean_token_accuracy": 0.2407107874751091,
|
|
"num_tokens": 81891162.0,
|
|
"step": 29305
|
|
},
|
|
{
|
|
"entropy": 4.690163946151733,
|
|
"epoch": 3.491363907087552,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003825766112176659,
|
|
"loss": 4.2755,
|
|
"mean_token_accuracy": 0.2641467094421387,
|
|
"num_tokens": 81905537.0,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"entropy": 4.826464891433716,
|
|
"epoch": 3.4919594997022037,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003825391828069032,
|
|
"loss": 4.4051,
|
|
"mean_token_accuracy": 0.24426545649766923,
|
|
"num_tokens": 81918301.0,
|
|
"step": 29315
|
|
},
|
|
{
|
|
"entropy": 4.77934193611145,
|
|
"epoch": 3.4925550923168553,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0003825017505388849,
|
|
"loss": 4.4331,
|
|
"mean_token_accuracy": 0.24666097909212112,
|
|
"num_tokens": 81934085.0,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"entropy": 4.815784168243408,
|
|
"epoch": 3.493150684931507,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003824643144149535,
|
|
"loss": 4.4402,
|
|
"mean_token_accuracy": 0.24269829094409942,
|
|
"num_tokens": 81947642.0,
|
|
"step": 29325
|
|
},
|
|
{
|
|
"entropy": 4.751755666732788,
|
|
"epoch": 3.4937462775461583,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00038242687443645196,
|
|
"loss": 4.3001,
|
|
"mean_token_accuracy": 0.258463029563427,
|
|
"num_tokens": 81960341.0,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"entropy": 4.8422609806060795,
|
|
"epoch": 3.49434187016081,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003823894306047231,
|
|
"loss": 4.4873,
|
|
"mean_token_accuracy": 0.2387832969427109,
|
|
"num_tokens": 81974415.0,
|
|
"step": 29335
|
|
},
|
|
{
|
|
"entropy": 4.816203927993774,
|
|
"epoch": 3.4949374627754617,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00038235198292110997,
|
|
"loss": 4.4455,
|
|
"mean_token_accuracy": 0.24756014198064805,
|
|
"num_tokens": 81988051.0,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"entropy": 4.808395862579346,
|
|
"epoch": 3.495533055390113,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00038231453138695573,
|
|
"loss": 4.4642,
|
|
"mean_token_accuracy": 0.24802320152521135,
|
|
"num_tokens": 82003654.0,
|
|
"step": 29345
|
|
},
|
|
{
|
|
"entropy": 4.834208726882935,
|
|
"epoch": 3.4961286480047646,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0003822770760036037,
|
|
"loss": 4.4125,
|
|
"mean_token_accuracy": 0.2420259892940521,
|
|
"num_tokens": 82019166.0,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"entropy": 4.749674844741821,
|
|
"epoch": 3.4967242406194163,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00038223961677239746,
|
|
"loss": 4.3555,
|
|
"mean_token_accuracy": 0.2569729253649712,
|
|
"num_tokens": 82034055.0,
|
|
"step": 29355
|
|
},
|
|
{
|
|
"entropy": 4.815714120864868,
|
|
"epoch": 3.497319833234068,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003822021536946804,
|
|
"loss": 4.4763,
|
|
"mean_token_accuracy": 0.24008371233940123,
|
|
"num_tokens": 82046282.0,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"entropy": 4.879299736022949,
|
|
"epoch": 3.4979154258487193,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038216468677179644,
|
|
"loss": 4.4957,
|
|
"mean_token_accuracy": 0.2440239816904068,
|
|
"num_tokens": 82059442.0,
|
|
"step": 29365
|
|
},
|
|
{
|
|
"entropy": 4.850062131881714,
|
|
"epoch": 3.498511018463371,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003821272160050894,
|
|
"loss": 4.4155,
|
|
"mean_token_accuracy": 0.24262211173772813,
|
|
"num_tokens": 82074727.0,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"entropy": 4.8125035762786865,
|
|
"epoch": 3.4991066110780227,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003820897413959034,
|
|
"loss": 4.354,
|
|
"mean_token_accuracy": 0.2504424139857292,
|
|
"num_tokens": 82087289.0,
|
|
"step": 29375
|
|
},
|
|
{
|
|
"entropy": 4.7793052196502686,
|
|
"epoch": 3.4997022036926744,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003820522629455824,
|
|
"loss": 4.3815,
|
|
"mean_token_accuracy": 0.24733553677797318,
|
|
"num_tokens": 82101443.0,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"entropy": 4.718859767913818,
|
|
"epoch": 3.5002977963073256,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003820147806554708,
|
|
"loss": 4.3245,
|
|
"mean_token_accuracy": 0.25204467177391054,
|
|
"num_tokens": 82116698.0,
|
|
"step": 29385
|
|
},
|
|
{
|
|
"entropy": 4.846873188018799,
|
|
"epoch": 3.5008933889219773,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00038197729452691304,
|
|
"loss": 4.4804,
|
|
"mean_token_accuracy": 0.23466752022504805,
|
|
"num_tokens": 82133184.0,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"entropy": 4.869242906570435,
|
|
"epoch": 3.501488981536629,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003819398045612536,
|
|
"loss": 4.4337,
|
|
"mean_token_accuracy": 0.24701888710260392,
|
|
"num_tokens": 82147523.0,
|
|
"step": 29395
|
|
},
|
|
{
|
|
"entropy": 4.738665676116943,
|
|
"epoch": 3.5020845741512803,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038190231075983734,
|
|
"loss": 4.3597,
|
|
"mean_token_accuracy": 0.2531085342168808,
|
|
"num_tokens": 82159154.0,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"entropy": 4.740139436721802,
|
|
"epoch": 3.502680166765932,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038186481312400887,
|
|
"loss": 4.3272,
|
|
"mean_token_accuracy": 0.25174291580915453,
|
|
"num_tokens": 82172043.0,
|
|
"step": 29405
|
|
},
|
|
{
|
|
"entropy": 4.77804126739502,
|
|
"epoch": 3.5032757593805837,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038182731165511334,
|
|
"loss": 4.4058,
|
|
"mean_token_accuracy": 0.24439468681812287,
|
|
"num_tokens": 82185068.0,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"entropy": 4.827327919006348,
|
|
"epoch": 3.5038713519952354,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0003817898063544959,
|
|
"loss": 4.4682,
|
|
"mean_token_accuracy": 0.24716438204050065,
|
|
"num_tokens": 82198920.0,
|
|
"step": 29415
|
|
},
|
|
{
|
|
"entropy": 4.87840723991394,
|
|
"epoch": 3.504466944609887,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00038175229722350174,
|
|
"loss": 4.4404,
|
|
"mean_token_accuracy": 0.2321089908480644,
|
|
"num_tokens": 82212742.0,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"entropy": 4.747947931289673,
|
|
"epoch": 3.5050625372245383,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0003817147842634762,
|
|
"loss": 4.3744,
|
|
"mean_token_accuracy": 0.24593228995800018,
|
|
"num_tokens": 82227170.0,
|
|
"step": 29425
|
|
},
|
|
{
|
|
"entropy": 4.79638261795044,
|
|
"epoch": 3.50565812983919,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003816772674757649,
|
|
"loss": 4.4209,
|
|
"mean_token_accuracy": 0.24765381813049317,
|
|
"num_tokens": 82239898.0,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"entropy": 4.860724544525146,
|
|
"epoch": 3.5062537224538417,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00038163974686171345,
|
|
"loss": 4.4592,
|
|
"mean_token_accuracy": 0.2415317788720131,
|
|
"num_tokens": 82253944.0,
|
|
"step": 29435
|
|
},
|
|
{
|
|
"entropy": 4.794533681869507,
|
|
"epoch": 3.506849315068493,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003816022224226676,
|
|
"loss": 4.4109,
|
|
"mean_token_accuracy": 0.2441830664873123,
|
|
"num_tokens": 82266682.0,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"entropy": 4.7782958984375,
|
|
"epoch": 3.5074449076831447,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003815646941599734,
|
|
"loss": 4.3843,
|
|
"mean_token_accuracy": 0.24584104716777802,
|
|
"num_tokens": 82279659.0,
|
|
"step": 29445
|
|
},
|
|
{
|
|
"entropy": 4.843901538848877,
|
|
"epoch": 3.5080405002977963,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00038152716207497697,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.23854208439588548,
|
|
"num_tokens": 82294057.0,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"entropy": 4.847921562194824,
|
|
"epoch": 3.508636092912448,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003814896261690243,
|
|
"loss": 4.4354,
|
|
"mean_token_accuracy": 0.24477644115686417,
|
|
"num_tokens": 82307024.0,
|
|
"step": 29455
|
|
},
|
|
{
|
|
"entropy": 4.7484337329864506,
|
|
"epoch": 3.5092316855270993,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000381452086443462,
|
|
"loss": 4.2958,
|
|
"mean_token_accuracy": 0.2572549283504486,
|
|
"num_tokens": 82320264.0,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"entropy": 4.757162761688233,
|
|
"epoch": 3.509827278141751,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0003814145428996363,
|
|
"loss": 4.3995,
|
|
"mean_token_accuracy": 0.2481740340590477,
|
|
"num_tokens": 82334276.0,
|
|
"step": 29465
|
|
},
|
|
{
|
|
"entropy": 4.786420679092407,
|
|
"epoch": 3.5104228707564027,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003813769955388941,
|
|
"loss": 4.4412,
|
|
"mean_token_accuracy": 0.2432885080575943,
|
|
"num_tokens": 82349467.0,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"entropy": 4.779375648498535,
|
|
"epoch": 3.5110184633710544,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00038133944436258196,
|
|
"loss": 4.3275,
|
|
"mean_token_accuracy": 0.25272945016622544,
|
|
"num_tokens": 82363864.0,
|
|
"step": 29475
|
|
},
|
|
{
|
|
"entropy": 4.770548629760742,
|
|
"epoch": 3.5116140559857056,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003813018893720468,
|
|
"loss": 4.3395,
|
|
"mean_token_accuracy": 0.25105291306972505,
|
|
"num_tokens": 82375329.0,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"entropy": 4.707975625991821,
|
|
"epoch": 3.5122096486003573,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003812643305686358,
|
|
"loss": 4.3248,
|
|
"mean_token_accuracy": 0.25535465180873873,
|
|
"num_tokens": 82388960.0,
|
|
"step": 29485
|
|
},
|
|
{
|
|
"entropy": 4.787388944625855,
|
|
"epoch": 3.512805241215009,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000381226767953696,
|
|
"loss": 4.4153,
|
|
"mean_token_accuracy": 0.24629338830709457,
|
|
"num_tokens": 82402314.0,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"entropy": 4.732888889312744,
|
|
"epoch": 3.5134008338296603,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003811892015285748,
|
|
"loss": 4.3814,
|
|
"mean_token_accuracy": 0.2514752984046936,
|
|
"num_tokens": 82417544.0,
|
|
"step": 29495
|
|
},
|
|
{
|
|
"entropy": 4.767721128463745,
|
|
"epoch": 3.513996426444312,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00038115163129461943,
|
|
"loss": 4.3849,
|
|
"mean_token_accuracy": 0.24489706605672837,
|
|
"num_tokens": 82432173.0,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"entropy": 4.8303920269012455,
|
|
"epoch": 3.5145920190589637,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00038111405725317784,
|
|
"loss": 4.4161,
|
|
"mean_token_accuracy": 0.24064921885728835,
|
|
"num_tokens": 82445967.0,
|
|
"step": 29505
|
|
},
|
|
{
|
|
"entropy": 4.771405744552612,
|
|
"epoch": 3.5151876116736154,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003810764794055974,
|
|
"loss": 4.3983,
|
|
"mean_token_accuracy": 0.2509349584579468,
|
|
"num_tokens": 82461740.0,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"entropy": 4.836655139923096,
|
|
"epoch": 3.515783204288267,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003810388977532262,
|
|
"loss": 4.4217,
|
|
"mean_token_accuracy": 0.24158397316932678,
|
|
"num_tokens": 82475238.0,
|
|
"step": 29515
|
|
},
|
|
{
|
|
"entropy": 4.817225551605224,
|
|
"epoch": 3.5163787969029183,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0003810013122974122,
|
|
"loss": 4.4775,
|
|
"mean_token_accuracy": 0.23232460767030716,
|
|
"num_tokens": 82490620.0,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"entropy": 4.791823244094848,
|
|
"epoch": 3.51697438951757,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00038096372303950333,
|
|
"loss": 4.3713,
|
|
"mean_token_accuracy": 0.2469705194234848,
|
|
"num_tokens": 82505162.0,
|
|
"step": 29525
|
|
},
|
|
{
|
|
"entropy": 4.710621500015259,
|
|
"epoch": 3.5175699821322217,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003809261299808481,
|
|
"loss": 4.29,
|
|
"mean_token_accuracy": 0.25555932223796846,
|
|
"num_tokens": 82518699.0,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"entropy": 4.8914330959320065,
|
|
"epoch": 3.518165574746873,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00038088853312279473,
|
|
"loss": 4.5487,
|
|
"mean_token_accuracy": 0.23740618377923967,
|
|
"num_tokens": 82533360.0,
|
|
"step": 29535
|
|
},
|
|
{
|
|
"entropy": 4.795813131332397,
|
|
"epoch": 3.5187611673615247,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0003808509324666919,
|
|
"loss": 4.3312,
|
|
"mean_token_accuracy": 0.25232878178358076,
|
|
"num_tokens": 82549495.0,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"entropy": 4.764744615554809,
|
|
"epoch": 3.5193567599761764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003808133280138882,
|
|
"loss": 4.4063,
|
|
"mean_token_accuracy": 0.2447350099682808,
|
|
"num_tokens": 82565150.0,
|
|
"step": 29545
|
|
},
|
|
{
|
|
"entropy": 4.756431198120117,
|
|
"epoch": 3.5199523525908276,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0003807757197657325,
|
|
"loss": 4.3829,
|
|
"mean_token_accuracy": 0.24185733497142792,
|
|
"num_tokens": 82580979.0,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"entropy": 4.777141904830932,
|
|
"epoch": 3.5205479452054793,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003807381077235737,
|
|
"loss": 4.4319,
|
|
"mean_token_accuracy": 0.25151543915271757,
|
|
"num_tokens": 82595262.0,
|
|
"step": 29555
|
|
},
|
|
{
|
|
"entropy": 4.770010852813721,
|
|
"epoch": 3.521143537820131,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003807004918887608,
|
|
"loss": 4.3977,
|
|
"mean_token_accuracy": 0.24795491993427277,
|
|
"num_tokens": 82608700.0,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"entropy": 4.861059951782226,
|
|
"epoch": 3.5217391304347827,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003806628722626433,
|
|
"loss": 4.4462,
|
|
"mean_token_accuracy": 0.24448077976703644,
|
|
"num_tokens": 82622619.0,
|
|
"step": 29565
|
|
},
|
|
{
|
|
"entropy": 4.905704402923584,
|
|
"epoch": 3.5223347230494344,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003806252488465703,
|
|
"loss": 4.526,
|
|
"mean_token_accuracy": 0.23846938759088515,
|
|
"num_tokens": 82635105.0,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"entropy": 4.758580923080444,
|
|
"epoch": 3.5229303156640857,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0003805876216418914,
|
|
"loss": 4.4402,
|
|
"mean_token_accuracy": 0.24457681626081468,
|
|
"num_tokens": 82650059.0,
|
|
"step": 29575
|
|
},
|
|
{
|
|
"entropy": 4.86756534576416,
|
|
"epoch": 3.5235259082787374,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000380549990649956,
|
|
"loss": 4.3915,
|
|
"mean_token_accuracy": 0.2444167897105217,
|
|
"num_tokens": 82665454.0,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"entropy": 4.760664272308349,
|
|
"epoch": 3.524121500893389,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038051235587211417,
|
|
"loss": 4.3698,
|
|
"mean_token_accuracy": 0.2555003061890602,
|
|
"num_tokens": 82679744.0,
|
|
"step": 29585
|
|
},
|
|
{
|
|
"entropy": 4.617368936538696,
|
|
"epoch": 3.5247170935080403,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003804747173097157,
|
|
"loss": 4.2583,
|
|
"mean_token_accuracy": 0.26247545927762983,
|
|
"num_tokens": 82693028.0,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"entropy": 4.848039627075195,
|
|
"epoch": 3.525312686122692,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003804370749641106,
|
|
"loss": 4.4509,
|
|
"mean_token_accuracy": 0.2415560379624367,
|
|
"num_tokens": 82705866.0,
|
|
"step": 29595
|
|
},
|
|
{
|
|
"entropy": 4.7688991069793705,
|
|
"epoch": 3.5259082787373437,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038039942883664904,
|
|
"loss": 4.366,
|
|
"mean_token_accuracy": 0.2458485931158066,
|
|
"num_tokens": 82719334.0,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"entropy": 4.797002935409546,
|
|
"epoch": 3.5265038713519954,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00038036177892868133,
|
|
"loss": 4.3895,
|
|
"mean_token_accuracy": 0.23912933468818665,
|
|
"num_tokens": 82735637.0,
|
|
"step": 29605
|
|
},
|
|
{
|
|
"entropy": 4.793107652664185,
|
|
"epoch": 3.527099463966647,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000380324125241558,
|
|
"loss": 4.4087,
|
|
"mean_token_accuracy": 0.24632110595703124,
|
|
"num_tokens": 82749523.0,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"entropy": 4.801804733276367,
|
|
"epoch": 3.5276950565812983,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038028646777662947,
|
|
"loss": 4.4425,
|
|
"mean_token_accuracy": 0.24981988072395325,
|
|
"num_tokens": 82763702.0,
|
|
"step": 29615
|
|
},
|
|
{
|
|
"entropy": 4.700007152557373,
|
|
"epoch": 3.52829064919595,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0003802488065352465,
|
|
"loss": 4.2781,
|
|
"mean_token_accuracy": 0.25812435150146484,
|
|
"num_tokens": 82778112.0,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"entropy": 4.756571102142334,
|
|
"epoch": 3.5288862418106017,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00038021114151876,
|
|
"loss": 4.3809,
|
|
"mean_token_accuracy": 0.24728307425975798,
|
|
"num_tokens": 82792235.0,
|
|
"step": 29625
|
|
},
|
|
{
|
|
"entropy": 4.881325626373291,
|
|
"epoch": 3.529481834425253,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00038017347272852086,
|
|
"loss": 4.4873,
|
|
"mean_token_accuracy": 0.23623089641332626,
|
|
"num_tokens": 82806512.0,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"entropy": 4.823066902160645,
|
|
"epoch": 3.5300774270399047,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003801358001658804,
|
|
"loss": 4.461,
|
|
"mean_token_accuracy": 0.24562804847955705,
|
|
"num_tokens": 82819842.0,
|
|
"step": 29635
|
|
},
|
|
{
|
|
"entropy": 4.755245018005371,
|
|
"epoch": 3.5306730196545564,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00038009812383218956,
|
|
"loss": 4.3449,
|
|
"mean_token_accuracy": 0.25483925044536593,
|
|
"num_tokens": 82834559.0,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"entropy": 4.787827444076538,
|
|
"epoch": 3.5312686122692076,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00038006044372880006,
|
|
"loss": 4.3878,
|
|
"mean_token_accuracy": 0.24447617828845977,
|
|
"num_tokens": 82848869.0,
|
|
"step": 29645
|
|
},
|
|
{
|
|
"entropy": 4.752560091018677,
|
|
"epoch": 3.5318642048838593,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038002275985706316,
|
|
"loss": 4.3221,
|
|
"mean_token_accuracy": 0.24744414538145065,
|
|
"num_tokens": 82862011.0,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"entropy": 4.703907299041748,
|
|
"epoch": 3.532459797498511,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00037998507221833066,
|
|
"loss": 4.3505,
|
|
"mean_token_accuracy": 0.25284478813409805,
|
|
"num_tokens": 82876373.0,
|
|
"step": 29655
|
|
},
|
|
{
|
|
"entropy": 4.720309543609619,
|
|
"epoch": 3.5330553901131627,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00037994738081395426,
|
|
"loss": 4.3648,
|
|
"mean_token_accuracy": 0.24523140639066696,
|
|
"num_tokens": 82890520.0,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"entropy": 4.817366456985473,
|
|
"epoch": 3.5336509827278144,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000379909685645286,
|
|
"loss": 4.3873,
|
|
"mean_token_accuracy": 0.24630404263734818,
|
|
"num_tokens": 82903561.0,
|
|
"step": 29665
|
|
},
|
|
{
|
|
"entropy": 4.74019341468811,
|
|
"epoch": 3.5342465753424657,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037987198671367783,
|
|
"loss": 4.3939,
|
|
"mean_token_accuracy": 0.24612123370170594,
|
|
"num_tokens": 82915660.0,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"entropy": 4.857523202896118,
|
|
"epoch": 3.5348421679571174,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0003798342840204821,
|
|
"loss": 4.457,
|
|
"mean_token_accuracy": 0.23801897913217546,
|
|
"num_tokens": 82931134.0,
|
|
"step": 29675
|
|
},
|
|
{
|
|
"entropy": 4.755500650405883,
|
|
"epoch": 3.535437760571769,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000379796577567051,
|
|
"loss": 4.3308,
|
|
"mean_token_accuracy": 0.2495166167616844,
|
|
"num_tokens": 82948400.0,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"entropy": 4.745766878128052,
|
|
"epoch": 3.5360333531864203,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000379758867354737,
|
|
"loss": 4.3975,
|
|
"mean_token_accuracy": 0.2532802581787109,
|
|
"num_tokens": 82962028.0,
|
|
"step": 29685
|
|
},
|
|
{
|
|
"entropy": 4.749495267868042,
|
|
"epoch": 3.536628945801072,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00037972115338489275,
|
|
"loss": 4.3335,
|
|
"mean_token_accuracy": 0.24545668959617614,
|
|
"num_tokens": 82977264.0,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"entropy": 4.846315813064575,
|
|
"epoch": 3.5372245384157237,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0003796834356588711,
|
|
"loss": 4.4874,
|
|
"mean_token_accuracy": 0.24164749234914779,
|
|
"num_tokens": 82991401.0,
|
|
"step": 29695
|
|
},
|
|
{
|
|
"entropy": 4.820199823379516,
|
|
"epoch": 3.537820131030375,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037964571417802473,
|
|
"loss": 4.5028,
|
|
"mean_token_accuracy": 0.23297007828950883,
|
|
"num_tokens": 83004095.0,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"entropy": 4.720700693130493,
|
|
"epoch": 3.5384157236450267,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003796079889437068,
|
|
"loss": 4.3112,
|
|
"mean_token_accuracy": 0.2542742595076561,
|
|
"num_tokens": 83017242.0,
|
|
"step": 29705
|
|
},
|
|
{
|
|
"entropy": 4.76373257637024,
|
|
"epoch": 3.5390113162596784,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00037957025995727036,
|
|
"loss": 4.345,
|
|
"mean_token_accuracy": 0.2529569149017334,
|
|
"num_tokens": 83031092.0,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"entropy": 4.748532915115357,
|
|
"epoch": 3.53960690887433,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00037953252722006873,
|
|
"loss": 4.3662,
|
|
"mean_token_accuracy": 0.25032746493816377,
|
|
"num_tokens": 83046008.0,
|
|
"step": 29715
|
|
},
|
|
{
|
|
"entropy": 4.916044759750366,
|
|
"epoch": 3.5402025014889817,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0003794947907334553,
|
|
"loss": 4.5427,
|
|
"mean_token_accuracy": 0.23243168294429778,
|
|
"num_tokens": 83060004.0,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"entropy": 4.878021574020385,
|
|
"epoch": 3.540798094103633,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003794570504987836,
|
|
"loss": 4.4292,
|
|
"mean_token_accuracy": 0.23657530993223191,
|
|
"num_tokens": 83074460.0,
|
|
"step": 29725
|
|
},
|
|
{
|
|
"entropy": 4.826827621459961,
|
|
"epoch": 3.5413936867182847,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037941930651740736,
|
|
"loss": 4.4367,
|
|
"mean_token_accuracy": 0.2470392942428589,
|
|
"num_tokens": 83088589.0,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"entropy": 4.762472772598267,
|
|
"epoch": 3.5419892793329364,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00037938155879068037,
|
|
"loss": 4.3933,
|
|
"mean_token_accuracy": 0.25163906067609787,
|
|
"num_tokens": 83104305.0,
|
|
"step": 29735
|
|
},
|
|
{
|
|
"entropy": 4.819248008728027,
|
|
"epoch": 3.5425848719475876,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003793438073199565,
|
|
"loss": 4.4481,
|
|
"mean_token_accuracy": 0.24493790417909622,
|
|
"num_tokens": 83119003.0,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"entropy": 4.781117343902588,
|
|
"epoch": 3.5431804645622393,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00037930605210659003,
|
|
"loss": 4.4601,
|
|
"mean_token_accuracy": 0.24954416006803512,
|
|
"num_tokens": 83132410.0,
|
|
"step": 29745
|
|
},
|
|
{
|
|
"entropy": 4.823826837539673,
|
|
"epoch": 3.543776057176891,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00037926829315193506,
|
|
"loss": 4.3747,
|
|
"mean_token_accuracy": 0.25560774505138395,
|
|
"num_tokens": 83145174.0,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"entropy": 4.758699083328247,
|
|
"epoch": 3.5443716497915427,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00037923053045734595,
|
|
"loss": 4.3654,
|
|
"mean_token_accuracy": 0.2566588088870049,
|
|
"num_tokens": 83158856.0,
|
|
"step": 29755
|
|
},
|
|
{
|
|
"entropy": 4.774213743209839,
|
|
"epoch": 3.5449672424061944,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003791927640241771,
|
|
"loss": 4.3652,
|
|
"mean_token_accuracy": 0.24523860216140747,
|
|
"num_tokens": 83172067.0,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"entropy": 4.722863674163818,
|
|
"epoch": 3.5455628350208457,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00037915499385378327,
|
|
"loss": 4.3317,
|
|
"mean_token_accuracy": 0.24720735996961593,
|
|
"num_tokens": 83184690.0,
|
|
"step": 29765
|
|
},
|
|
{
|
|
"entropy": 4.724143362045288,
|
|
"epoch": 3.5461584276354974,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00037911721994751907,
|
|
"loss": 4.4156,
|
|
"mean_token_accuracy": 0.24719146341085435,
|
|
"num_tokens": 83198153.0,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"entropy": 4.886318111419678,
|
|
"epoch": 3.546754020250149,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00037907944230673957,
|
|
"loss": 4.4346,
|
|
"mean_token_accuracy": 0.24318316727876663,
|
|
"num_tokens": 83213117.0,
|
|
"step": 29775
|
|
},
|
|
{
|
|
"entropy": 4.788671970367432,
|
|
"epoch": 3.5473496128648003,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037904166093279964,
|
|
"loss": 4.3884,
|
|
"mean_token_accuracy": 0.2525982841849327,
|
|
"num_tokens": 83226439.0,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"entropy": 4.712046384811401,
|
|
"epoch": 3.547945205479452,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037900387582705453,
|
|
"loss": 4.2651,
|
|
"mean_token_accuracy": 0.26568988859653475,
|
|
"num_tokens": 83238261.0,
|
|
"step": 29785
|
|
},
|
|
{
|
|
"entropy": 4.867302513122558,
|
|
"epoch": 3.5485407980941037,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0003789660869908595,
|
|
"loss": 4.5408,
|
|
"mean_token_accuracy": 0.22988368272781373,
|
|
"num_tokens": 83254542.0,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"entropy": 4.803576278686523,
|
|
"epoch": 3.549136390708755,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00037892829442556986,
|
|
"loss": 4.4113,
|
|
"mean_token_accuracy": 0.24568598419427873,
|
|
"num_tokens": 83270270.0,
|
|
"step": 29795
|
|
},
|
|
{
|
|
"entropy": 4.841852903366089,
|
|
"epoch": 3.5497319833234067,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003788904981325414,
|
|
"loss": 4.5189,
|
|
"mean_token_accuracy": 0.23777078241109847,
|
|
"num_tokens": 83283363.0,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"entropy": 4.786399841308594,
|
|
"epoch": 3.5503275759380584,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00037885269811312975,
|
|
"loss": 4.3737,
|
|
"mean_token_accuracy": 0.24311235845088958,
|
|
"num_tokens": 83296479.0,
|
|
"step": 29805
|
|
},
|
|
{
|
|
"entropy": 4.877291965484619,
|
|
"epoch": 3.55092316855271,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00037881489436869054,
|
|
"loss": 4.5291,
|
|
"mean_token_accuracy": 0.2297930523753166,
|
|
"num_tokens": 83312190.0,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"entropy": 4.920561265945435,
|
|
"epoch": 3.5515187611673618,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003787770869005799,
|
|
"loss": 4.5236,
|
|
"mean_token_accuracy": 0.23463923186063768,
|
|
"num_tokens": 83325256.0,
|
|
"step": 29815
|
|
},
|
|
{
|
|
"entropy": 4.8116107940673825,
|
|
"epoch": 3.552114353782013,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0003787392757101539,
|
|
"loss": 4.3978,
|
|
"mean_token_accuracy": 0.24182338863611222,
|
|
"num_tokens": 83339800.0,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"entropy": 4.748401117324829,
|
|
"epoch": 3.5527099463966647,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003787014607987687,
|
|
"loss": 4.3594,
|
|
"mean_token_accuracy": 0.2509281724691391,
|
|
"num_tokens": 83351223.0,
|
|
"step": 29825
|
|
},
|
|
{
|
|
"entropy": 4.731678104400634,
|
|
"epoch": 3.5533055390113164,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0003786636421677807,
|
|
"loss": 4.357,
|
|
"mean_token_accuracy": 0.2523745134472847,
|
|
"num_tokens": 83363772.0,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"entropy": 4.806447124481201,
|
|
"epoch": 3.5539011316259677,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0003786258198185465,
|
|
"loss": 4.4178,
|
|
"mean_token_accuracy": 0.24339055567979812,
|
|
"num_tokens": 83377065.0,
|
|
"step": 29835
|
|
},
|
|
{
|
|
"entropy": 4.768439769744873,
|
|
"epoch": 3.5544967242406194,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003785879937524225,
|
|
"loss": 4.3932,
|
|
"mean_token_accuracy": 0.23451109677553178,
|
|
"num_tokens": 83390799.0,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"entropy": 4.7517022609710695,
|
|
"epoch": 3.555092316855271,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037855016397076574,
|
|
"loss": 4.3667,
|
|
"mean_token_accuracy": 0.24611034840345383,
|
|
"num_tokens": 83404779.0,
|
|
"step": 29845
|
|
},
|
|
{
|
|
"entropy": 4.744570302963257,
|
|
"epoch": 3.5556879094699223,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0003785123304749329,
|
|
"loss": 4.343,
|
|
"mean_token_accuracy": 0.2519821926951408,
|
|
"num_tokens": 83420066.0,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"entropy": 4.832146501541137,
|
|
"epoch": 3.556283502084574,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000378474493266281,
|
|
"loss": 4.4507,
|
|
"mean_token_accuracy": 0.24094126224517823,
|
|
"num_tokens": 83434000.0,
|
|
"step": 29855
|
|
},
|
|
{
|
|
"entropy": 4.712611484527588,
|
|
"epoch": 3.5568790946992257,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003784366523461674,
|
|
"loss": 4.2968,
|
|
"mean_token_accuracy": 0.2620610460639,
|
|
"num_tokens": 83447222.0,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"entropy": 4.8064412593841555,
|
|
"epoch": 3.5574746873138774,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0003783988077159491,
|
|
"loss": 4.4652,
|
|
"mean_token_accuracy": 0.2378348872065544,
|
|
"num_tokens": 83461749.0,
|
|
"step": 29865
|
|
},
|
|
{
|
|
"entropy": 4.829790306091309,
|
|
"epoch": 3.558070279928529,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0003783609593769838,
|
|
"loss": 4.4614,
|
|
"mean_token_accuracy": 0.2407524049282074,
|
|
"num_tokens": 83474988.0,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"entropy": 4.775653076171875,
|
|
"epoch": 3.5586658725431803,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00037832310733062883,
|
|
"loss": 4.3759,
|
|
"mean_token_accuracy": 0.2467888429760933,
|
|
"num_tokens": 83488333.0,
|
|
"step": 29875
|
|
},
|
|
{
|
|
"entropy": 4.854892158508301,
|
|
"epoch": 3.559261465157832,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00037828525157824214,
|
|
"loss": 4.5013,
|
|
"mean_token_accuracy": 0.23953614085912706,
|
|
"num_tokens": 83502976.0,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"entropy": 4.775830316543579,
|
|
"epoch": 3.5598570577724837,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00037824739212118124,
|
|
"loss": 4.3264,
|
|
"mean_token_accuracy": 0.2592546552419662,
|
|
"num_tokens": 83516892.0,
|
|
"step": 29885
|
|
},
|
|
{
|
|
"entropy": 4.77017297744751,
|
|
"epoch": 3.560452650387135,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0003782095289608044,
|
|
"loss": 4.4035,
|
|
"mean_token_accuracy": 0.24859634339809417,
|
|
"num_tokens": 83531231.0,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"entropy": 4.8509684085845945,
|
|
"epoch": 3.5610482430017867,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00037817166209846954,
|
|
"loss": 4.4973,
|
|
"mean_token_accuracy": 0.23938008248806,
|
|
"num_tokens": 83545745.0,
|
|
"step": 29895
|
|
},
|
|
{
|
|
"entropy": 4.821801996231079,
|
|
"epoch": 3.5616438356164384,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003781337915355348,
|
|
"loss": 4.3754,
|
|
"mean_token_accuracy": 0.2438103049993515,
|
|
"num_tokens": 83559973.0,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"entropy": 4.66869478225708,
|
|
"epoch": 3.56223942823109,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003780959172733588,
|
|
"loss": 4.274,
|
|
"mean_token_accuracy": 0.261724691092968,
|
|
"num_tokens": 83573532.0,
|
|
"step": 29905
|
|
},
|
|
{
|
|
"entropy": 4.763007402420044,
|
|
"epoch": 3.5628350208457418,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00037805803931329976,
|
|
"loss": 4.4207,
|
|
"mean_token_accuracy": 0.2423779308795929,
|
|
"num_tokens": 83587496.0,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"entropy": 4.837070417404175,
|
|
"epoch": 3.563430613460393,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003780201576567164,
|
|
"loss": 4.3796,
|
|
"mean_token_accuracy": 0.2456320583820343,
|
|
"num_tokens": 83600765.0,
|
|
"step": 29915
|
|
},
|
|
{
|
|
"entropy": 4.8161827564239506,
|
|
"epoch": 3.5640262060750447,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00037798227230496754,
|
|
"loss": 4.4168,
|
|
"mean_token_accuracy": 0.24049310833215715,
|
|
"num_tokens": 83614835.0,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"entropy": 4.858139896392823,
|
|
"epoch": 3.5646217986896964,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037794438325941207,
|
|
"loss": 4.4829,
|
|
"mean_token_accuracy": 0.24116022884845734,
|
|
"num_tokens": 83627583.0,
|
|
"step": 29925
|
|
},
|
|
{
|
|
"entropy": 4.784737682342529,
|
|
"epoch": 3.5652173913043477,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003779064905214088,
|
|
"loss": 4.4042,
|
|
"mean_token_accuracy": 0.2460481733083725,
|
|
"num_tokens": 83643275.0,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"entropy": 4.7107171535491945,
|
|
"epoch": 3.5658129839189994,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003778685940923171,
|
|
"loss": 4.287,
|
|
"mean_token_accuracy": 0.2579903170466423,
|
|
"num_tokens": 83656783.0,
|
|
"step": 29935
|
|
},
|
|
{
|
|
"entropy": 4.805788946151734,
|
|
"epoch": 3.566408576533651,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00037783069397349624,
|
|
"loss": 4.4313,
|
|
"mean_token_accuracy": 0.23836339712142945,
|
|
"num_tokens": 83671663.0,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"entropy": 4.8138336658477785,
|
|
"epoch": 3.5670041691483023,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037779279016630555,
|
|
"loss": 4.4612,
|
|
"mean_token_accuracy": 0.24232489317655564,
|
|
"num_tokens": 83684158.0,
|
|
"step": 29945
|
|
},
|
|
{
|
|
"entropy": 4.7463593006134035,
|
|
"epoch": 3.567599761762954,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003777548826721046,
|
|
"loss": 4.3822,
|
|
"mean_token_accuracy": 0.24959650188684462,
|
|
"num_tokens": 83698518.0,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"entropy": 4.778213977813721,
|
|
"epoch": 3.5681953543776057,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000377716971492253,
|
|
"loss": 4.3689,
|
|
"mean_token_accuracy": 0.24444948136806488,
|
|
"num_tokens": 83713607.0,
|
|
"step": 29955
|
|
},
|
|
{
|
|
"entropy": 4.738386535644532,
|
|
"epoch": 3.5687909469922574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037767905662811074,
|
|
"loss": 4.2603,
|
|
"mean_token_accuracy": 0.2548457637429237,
|
|
"num_tokens": 83726486.0,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"entropy": 4.739310932159424,
|
|
"epoch": 3.569386539606909,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00037764113808103766,
|
|
"loss": 4.3722,
|
|
"mean_token_accuracy": 0.2449069619178772,
|
|
"num_tokens": 83739823.0,
|
|
"step": 29965
|
|
},
|
|
{
|
|
"entropy": 4.756053733825683,
|
|
"epoch": 3.5699821322215604,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00037760321585239375,
|
|
"loss": 4.3948,
|
|
"mean_token_accuracy": 0.2544577419757843,
|
|
"num_tokens": 83753307.0,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"entropy": 4.872998237609863,
|
|
"epoch": 3.570577724836212,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037756528994353945,
|
|
"loss": 4.4907,
|
|
"mean_token_accuracy": 0.24489355385303496,
|
|
"num_tokens": 83767901.0,
|
|
"step": 29975
|
|
},
|
|
{
|
|
"entropy": 4.7389391422271725,
|
|
"epoch": 3.5711733174508637,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00037752736035583486,
|
|
"loss": 4.3403,
|
|
"mean_token_accuracy": 0.2557230994105339,
|
|
"num_tokens": 83783468.0,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"entropy": 4.800101375579834,
|
|
"epoch": 3.571768910065515,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003774894270906405,
|
|
"loss": 4.3746,
|
|
"mean_token_accuracy": 0.24840098917484282,
|
|
"num_tokens": 83796510.0,
|
|
"step": 29985
|
|
},
|
|
{
|
|
"entropy": 4.80941367149353,
|
|
"epoch": 3.5723645026801667,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003774514901493172,
|
|
"loss": 4.4462,
|
|
"mean_token_accuracy": 0.24507949948310853,
|
|
"num_tokens": 83810292.0,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"entropy": 4.784249210357666,
|
|
"epoch": 3.5729600952948184,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037741354953322546,
|
|
"loss": 4.3885,
|
|
"mean_token_accuracy": 0.2498642697930336,
|
|
"num_tokens": 83824524.0,
|
|
"step": 29995
|
|
},
|
|
{
|
|
"entropy": 4.876415252685547,
|
|
"epoch": 3.5735556879094696,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0003773756052437262,
|
|
"loss": 4.4409,
|
|
"mean_token_accuracy": 0.2439899116754532,
|
|
"num_tokens": 83839788.0,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 3.5735556879094696,
|
|
"eval_entropy": 4.584945871986939,
|
|
"eval_loss": 4.485484600067139,
|
|
"eval_mean_token_accuracy": 0.2511307996081708,
|
|
"eval_num_tokens": 83839788.0,
|
|
"eval_runtime": 24.1512,
|
|
"eval_samples_per_second": 1056.387,
|
|
"eval_steps_per_second": 132.085,
|
|
"step": 30000
|
|
}
|
|
],
|
|
"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": 1.49078390846976e+17,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|