7107a07762
Model: fpadovani/urd-arab-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.357355568790947,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.930814170837403,
|
|
"epoch": 0.0005955926146515784,
|
|
"grad_norm": 16.625,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.4167,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 14043.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.930934953689575,
|
|
"epoch": 0.0011911852293031567,
|
|
"grad_norm": 17.75,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.379,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 27431.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.9491476058959964,
|
|
"epoch": 0.001786777843954735,
|
|
"grad_norm": 17.875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.329,
|
|
"mean_token_accuracy": 0.00018347387667745353,
|
|
"num_tokens": 41546.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.993091201782226,
|
|
"epoch": 0.0023823704586063135,
|
|
"grad_norm": 20.625,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.1411,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 55610.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.118336009979248,
|
|
"epoch": 0.0029779630732578916,
|
|
"grad_norm": 21.75,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.6646,
|
|
"mean_token_accuracy": 6.816632812842727e-05,
|
|
"num_tokens": 67719.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.474337196350097,
|
|
"epoch": 0.00357355568790947,
|
|
"grad_norm": 30.25,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.1064,
|
|
"mean_token_accuracy": 0.00011789437266997992,
|
|
"num_tokens": 82309.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.435689878463745,
|
|
"epoch": 0.004169148302561048,
|
|
"grad_norm": 18.625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 11.8501,
|
|
"mean_token_accuracy": 4.861448833253235e-05,
|
|
"num_tokens": 95752.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.319789028167724,
|
|
"epoch": 0.004764740917212627,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.9137,
|
|
"mean_token_accuracy": 0.0005631551030091941,
|
|
"num_tokens": 109473.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.729671287536622,
|
|
"epoch": 0.005360333531864205,
|
|
"grad_norm": 2.984375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.7917,
|
|
"mean_token_accuracy": 0.00835633766837418,
|
|
"num_tokens": 124193.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.742140769958496,
|
|
"epoch": 0.005955926146515783,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.6127,
|
|
"mean_token_accuracy": 0.01253411192446947,
|
|
"num_tokens": 136870.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.72428617477417,
|
|
"epoch": 0.006551518761167362,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.4405,
|
|
"mean_token_accuracy": 0.012474751565605402,
|
|
"num_tokens": 150613.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.684938621520995,
|
|
"epoch": 0.00714711137581894,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.2731,
|
|
"mean_token_accuracy": 0.012535067927092313,
|
|
"num_tokens": 164213.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.724059772491454,
|
|
"epoch": 0.007742703990470518,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.1137,
|
|
"mean_token_accuracy": 0.012889985833317042,
|
|
"num_tokens": 177408.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.737416172027588,
|
|
"epoch": 0.008338296605122097,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 10.0167,
|
|
"mean_token_accuracy": 0.016255142353475093,
|
|
"num_tokens": 190273.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.733052158355713,
|
|
"epoch": 0.008933889219773675,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.9276,
|
|
"mean_token_accuracy": 0.020910577662289143,
|
|
"num_tokens": 203323.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.725570011138917,
|
|
"epoch": 0.009529481834425254,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.8741,
|
|
"mean_token_accuracy": 0.01995530426502228,
|
|
"num_tokens": 218647.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.725209617614746,
|
|
"epoch": 0.01012507444907683,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.7652,
|
|
"mean_token_accuracy": 0.024607140198349954,
|
|
"num_tokens": 232910.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.721164894104003,
|
|
"epoch": 0.01072066706372841,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.6469,
|
|
"mean_token_accuracy": 0.030704791098833083,
|
|
"num_tokens": 246683.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.704849815368652,
|
|
"epoch": 0.011316259678379988,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.5264,
|
|
"mean_token_accuracy": 0.02491922862827778,
|
|
"num_tokens": 260150.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.682201194763184,
|
|
"epoch": 0.011911852293031567,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.4318,
|
|
"mean_token_accuracy": 0.021196888480335473,
|
|
"num_tokens": 273788.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.659872341156007,
|
|
"epoch": 0.012507444907683145,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2861,
|
|
"mean_token_accuracy": 0.029328163340687753,
|
|
"num_tokens": 287625.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.632499027252198,
|
|
"epoch": 0.013103037522334724,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1897,
|
|
"mean_token_accuracy": 0.03203366734087467,
|
|
"num_tokens": 302938.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.594201469421387,
|
|
"epoch": 0.0136986301369863,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.0455,
|
|
"mean_token_accuracy": 0.03484860137104988,
|
|
"num_tokens": 316905.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.538117980957031,
|
|
"epoch": 0.01429422275163788,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8813,
|
|
"mean_token_accuracy": 0.0357183400541544,
|
|
"num_tokens": 331131.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.47524003982544,
|
|
"epoch": 0.014889815366289458,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7829,
|
|
"mean_token_accuracy": 0.033022386766970155,
|
|
"num_tokens": 344995.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.404957103729249,
|
|
"epoch": 0.015485407980941036,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6273,
|
|
"mean_token_accuracy": 0.036685516312718394,
|
|
"num_tokens": 361057.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.323211097717286,
|
|
"epoch": 0.016081000595592615,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.4986,
|
|
"mean_token_accuracy": 0.03400989808142185,
|
|
"num_tokens": 375037.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.220504856109619,
|
|
"epoch": 0.016676593210244194,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3809,
|
|
"mean_token_accuracy": 0.034114895388484,
|
|
"num_tokens": 389797.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.096634578704833,
|
|
"epoch": 0.017272185824895772,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2767,
|
|
"mean_token_accuracy": 0.031545726023614405,
|
|
"num_tokens": 403743.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 9.95783576965332,
|
|
"epoch": 0.01786777843954735,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1678,
|
|
"mean_token_accuracy": 0.03068047184497118,
|
|
"num_tokens": 417337.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.782308101654053,
|
|
"epoch": 0.01846337105419893,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.982,
|
|
"mean_token_accuracy": 0.035417051427066325,
|
|
"num_tokens": 430106.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.577162837982177,
|
|
"epoch": 0.019058963668850508,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9343,
|
|
"mean_token_accuracy": 0.03450303077697754,
|
|
"num_tokens": 444654.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.363965129852295,
|
|
"epoch": 0.019654556283502083,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8736,
|
|
"mean_token_accuracy": 0.02943610493093729,
|
|
"num_tokens": 457837.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.135973644256591,
|
|
"epoch": 0.02025014889815366,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7257,
|
|
"mean_token_accuracy": 0.03390593882650137,
|
|
"num_tokens": 472006.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.896466922760009,
|
|
"epoch": 0.02084574151280524,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6716,
|
|
"mean_token_accuracy": 0.03380203507840633,
|
|
"num_tokens": 486155.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.67120819091797,
|
|
"epoch": 0.02144133412745682,
|
|
"grad_norm": 0.58203125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.7149,
|
|
"mean_token_accuracy": 0.03578196074813604,
|
|
"num_tokens": 501152.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.502655220031738,
|
|
"epoch": 0.022036926742108397,
|
|
"grad_norm": 0.65234375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.6346,
|
|
"mean_token_accuracy": 0.03523296993225813,
|
|
"num_tokens": 514856.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.348474788665772,
|
|
"epoch": 0.022632519356759976,
|
|
"grad_norm": 0.6328125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.6222,
|
|
"mean_token_accuracy": 0.035581219382584094,
|
|
"num_tokens": 529356.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.230454540252685,
|
|
"epoch": 0.023228111971411555,
|
|
"grad_norm": 0.58203125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.5873,
|
|
"mean_token_accuracy": 0.03212651666253805,
|
|
"num_tokens": 542876.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.147227382659912,
|
|
"epoch": 0.023823704586063133,
|
|
"grad_norm": 0.490234375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.5732,
|
|
"mean_token_accuracy": 0.035758920945227146,
|
|
"num_tokens": 557245.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.095999717712402,
|
|
"epoch": 0.024419297200714712,
|
|
"grad_norm": 0.58203125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.5073,
|
|
"mean_token_accuracy": 0.03651750274002552,
|
|
"num_tokens": 571458.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.050759887695312,
|
|
"epoch": 0.02501488981536629,
|
|
"grad_norm": 0.47265625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.5066,
|
|
"mean_token_accuracy": 0.03243191316723824,
|
|
"num_tokens": 588000.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.013091421127319,
|
|
"epoch": 0.02561048243001787,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.5562,
|
|
"mean_token_accuracy": 0.0339569590985775,
|
|
"num_tokens": 602302.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.969041728973389,
|
|
"epoch": 0.026206075044669448,
|
|
"grad_norm": 0.671875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.5942,
|
|
"mean_token_accuracy": 0.03409683294594288,
|
|
"num_tokens": 616708.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.94416618347168,
|
|
"epoch": 0.026801667659321026,
|
|
"grad_norm": 0.546875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.4634,
|
|
"mean_token_accuracy": 0.0323529377579689,
|
|
"num_tokens": 629236.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.921618127822876,
|
|
"epoch": 0.0273972602739726,
|
|
"grad_norm": 0.59765625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.5542,
|
|
"mean_token_accuracy": 0.030759461037814618,
|
|
"num_tokens": 642934.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.902442789077758,
|
|
"epoch": 0.02799285288862418,
|
|
"grad_norm": 0.640625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.4437,
|
|
"mean_token_accuracy": 0.035265585593879226,
|
|
"num_tokens": 656008.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.861639022827148,
|
|
"epoch": 0.02858844550327576,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.6688,
|
|
"mean_token_accuracy": 0.034444690495729444,
|
|
"num_tokens": 668843.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.883711433410644,
|
|
"epoch": 0.029184038117927337,
|
|
"grad_norm": 0.6171875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.571,
|
|
"mean_token_accuracy": 0.03377729225903749,
|
|
"num_tokens": 681883.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.923669385910034,
|
|
"epoch": 0.029779630732578916,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.5543,
|
|
"mean_token_accuracy": 0.0359426986426115,
|
|
"num_tokens": 694282.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.89340558052063,
|
|
"epoch": 0.030375223347230494,
|
|
"grad_norm": 0.60546875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4795,
|
|
"mean_token_accuracy": 0.03754743784666061,
|
|
"num_tokens": 708158.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.8842583179473875,
|
|
"epoch": 0.030970815961882073,
|
|
"grad_norm": 0.64453125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.4866,
|
|
"mean_token_accuracy": 0.03875179141759873,
|
|
"num_tokens": 722083.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.977138090133667,
|
|
"epoch": 0.03156640857653365,
|
|
"grad_norm": 0.640625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.496,
|
|
"mean_token_accuracy": 0.041106514260172845,
|
|
"num_tokens": 737806.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.9657190322875975,
|
|
"epoch": 0.03216200119118523,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.3861,
|
|
"mean_token_accuracy": 0.042757176980376246,
|
|
"num_tokens": 754100.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.942463493347168,
|
|
"epoch": 0.03275759380583681,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.4886,
|
|
"mean_token_accuracy": 0.040197388455271724,
|
|
"num_tokens": 769128.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.981670141220093,
|
|
"epoch": 0.03335318642048839,
|
|
"grad_norm": 0.6953125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.4943,
|
|
"mean_token_accuracy": 0.045960443839430806,
|
|
"num_tokens": 781259.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.896102476119995,
|
|
"epoch": 0.033948779035139966,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.3953,
|
|
"mean_token_accuracy": 0.04786432795226574,
|
|
"num_tokens": 796152.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.966923093795776,
|
|
"epoch": 0.034544371649791544,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.4398,
|
|
"mean_token_accuracy": 0.05151117071509361,
|
|
"num_tokens": 809686.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.934781837463379,
|
|
"epoch": 0.03513996426444312,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.3937,
|
|
"mean_token_accuracy": 0.05039183758199215,
|
|
"num_tokens": 824500.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.844818496704102,
|
|
"epoch": 0.0357355568790947,
|
|
"grad_norm": 0.67578125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.3402,
|
|
"mean_token_accuracy": 0.04793580211699009,
|
|
"num_tokens": 840643.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.877313280105591,
|
|
"epoch": 0.03633114949374628,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.3912,
|
|
"mean_token_accuracy": 0.05205256342887878,
|
|
"num_tokens": 853207.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.869196844100952,
|
|
"epoch": 0.03692674210839786,
|
|
"grad_norm": 0.73046875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.4454,
|
|
"mean_token_accuracy": 0.049079485982656476,
|
|
"num_tokens": 867735.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.893518781661987,
|
|
"epoch": 0.03752233472304944,
|
|
"grad_norm": 0.70703125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.3504,
|
|
"mean_token_accuracy": 0.05559028312563896,
|
|
"num_tokens": 881237.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.824286365509034,
|
|
"epoch": 0.038117927337701016,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.367,
|
|
"mean_token_accuracy": 0.05415560603141785,
|
|
"num_tokens": 894288.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.8115541458129885,
|
|
"epoch": 0.03871351995235259,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.3186,
|
|
"mean_token_accuracy": 0.05349941030144691,
|
|
"num_tokens": 907492.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.801938915252686,
|
|
"epoch": 0.039309112567004166,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.2421,
|
|
"mean_token_accuracy": 0.05915445201098919,
|
|
"num_tokens": 922255.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.784055852890015,
|
|
"epoch": 0.039904705181655745,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.2892,
|
|
"mean_token_accuracy": 0.053931834548711775,
|
|
"num_tokens": 937055.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.726195573806763,
|
|
"epoch": 0.04050029779630732,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.188,
|
|
"mean_token_accuracy": 0.05952785350382328,
|
|
"num_tokens": 951248.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.7162572860717775,
|
|
"epoch": 0.0410958904109589,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.1886,
|
|
"mean_token_accuracy": 0.06354545056819916,
|
|
"num_tokens": 965211.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.6900331497192385,
|
|
"epoch": 0.04169148302561048,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.1642,
|
|
"mean_token_accuracy": 0.062313458696007726,
|
|
"num_tokens": 979787.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.696742391586303,
|
|
"epoch": 0.04228707564026206,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.1587,
|
|
"mean_token_accuracy": 0.06508125178515911,
|
|
"num_tokens": 993412.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.69320273399353,
|
|
"epoch": 0.04288266825491364,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.1597,
|
|
"mean_token_accuracy": 0.07009457275271416,
|
|
"num_tokens": 1006819.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.641013479232788,
|
|
"epoch": 0.043478260869565216,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.139,
|
|
"mean_token_accuracy": 0.06649906449019909,
|
|
"num_tokens": 1022287.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.629658365249634,
|
|
"epoch": 0.044073853484216795,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.1324,
|
|
"mean_token_accuracy": 0.07035545893013477,
|
|
"num_tokens": 1034908.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.643279647827148,
|
|
"epoch": 0.04466944609886837,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.1701,
|
|
"mean_token_accuracy": 0.06597472541034222,
|
|
"num_tokens": 1051506.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.592386913299561,
|
|
"epoch": 0.04526503871351995,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.0495,
|
|
"mean_token_accuracy": 0.06537603698670864,
|
|
"num_tokens": 1066382.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.59307894706726,
|
|
"epoch": 0.04586063132817153,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.1083,
|
|
"mean_token_accuracy": 0.06889445632696152,
|
|
"num_tokens": 1082030.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.642332267761231,
|
|
"epoch": 0.04645622394282311,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.1244,
|
|
"mean_token_accuracy": 0.07188902460038663,
|
|
"num_tokens": 1095926.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.552314281463623,
|
|
"epoch": 0.04705181655747469,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.0076,
|
|
"mean_token_accuracy": 0.07692514657974243,
|
|
"num_tokens": 1110579.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.550763702392578,
|
|
"epoch": 0.047647409172126266,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.057,
|
|
"mean_token_accuracy": 0.07238596305251122,
|
|
"num_tokens": 1124001.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.585630941390991,
|
|
"epoch": 0.048243001786777845,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.0771,
|
|
"mean_token_accuracy": 0.07235280349850655,
|
|
"num_tokens": 1138316.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.512993621826172,
|
|
"epoch": 0.048838594401429423,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9804,
|
|
"mean_token_accuracy": 0.0787552185356617,
|
|
"num_tokens": 1150055.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.550870418548584,
|
|
"epoch": 0.049434187016081,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.0764,
|
|
"mean_token_accuracy": 0.07361177429556846,
|
|
"num_tokens": 1163645.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.537073230743408,
|
|
"epoch": 0.05002977963073258,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9307,
|
|
"mean_token_accuracy": 0.08229006081819534,
|
|
"num_tokens": 1176660.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.527930688858032,
|
|
"epoch": 0.05062537224538416,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.0167,
|
|
"mean_token_accuracy": 0.07370237298309804,
|
|
"num_tokens": 1193169.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.4409411430358885,
|
|
"epoch": 0.05122096486003574,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.9707,
|
|
"mean_token_accuracy": 0.07518848553299903,
|
|
"num_tokens": 1208484.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.529849243164063,
|
|
"epoch": 0.051816557474687316,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.0021,
|
|
"mean_token_accuracy": 0.07936362251639366,
|
|
"num_tokens": 1222925.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.530001974105835,
|
|
"epoch": 0.052412150089338895,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.9287,
|
|
"mean_token_accuracy": 0.08345810249447823,
|
|
"num_tokens": 1237949.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.440493488311768,
|
|
"epoch": 0.053007742703990474,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.9377,
|
|
"mean_token_accuracy": 0.0861880637705326,
|
|
"num_tokens": 1251535.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.432596206665039,
|
|
"epoch": 0.05360333531864205,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8614,
|
|
"mean_token_accuracy": 0.09000310897827149,
|
|
"num_tokens": 1265453.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.3850061893463135,
|
|
"epoch": 0.054198927933293624,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.883,
|
|
"mean_token_accuracy": 0.08198810368776321,
|
|
"num_tokens": 1280662.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.402025270462036,
|
|
"epoch": 0.0547945205479452,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.945,
|
|
"mean_token_accuracy": 0.0770284455269575,
|
|
"num_tokens": 1294980.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.329999589920044,
|
|
"epoch": 0.05539011316259678,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.805,
|
|
"mean_token_accuracy": 0.08324572592973709,
|
|
"num_tokens": 1309686.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.372046089172363,
|
|
"epoch": 0.05598570577724836,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.794,
|
|
"mean_token_accuracy": 0.08914539813995362,
|
|
"num_tokens": 1324815.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.337932395935058,
|
|
"epoch": 0.05658129839189994,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.8414,
|
|
"mean_token_accuracy": 0.08996991142630577,
|
|
"num_tokens": 1337829.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.276449060440063,
|
|
"epoch": 0.05717689100655152,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.8563,
|
|
"mean_token_accuracy": 0.0883386842906475,
|
|
"num_tokens": 1352163.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.33621392250061,
|
|
"epoch": 0.057772483621203095,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7701,
|
|
"mean_token_accuracy": 0.08845470175147056,
|
|
"num_tokens": 1364954.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.307647562026977,
|
|
"epoch": 0.058368076235854674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.8157,
|
|
"mean_token_accuracy": 0.08340756595134735,
|
|
"num_tokens": 1379414.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.2946351051330565,
|
|
"epoch": 0.05896366885050625,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.7092,
|
|
"mean_token_accuracy": 0.08904855772852897,
|
|
"num_tokens": 1393515.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.166852378845215,
|
|
"epoch": 0.05955926146515783,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6882,
|
|
"mean_token_accuracy": 0.09408702999353409,
|
|
"num_tokens": 1408986.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.191372203826904,
|
|
"epoch": 0.06015485407980941,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7165,
|
|
"mean_token_accuracy": 0.08943552300333976,
|
|
"num_tokens": 1423176.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.353649234771728,
|
|
"epoch": 0.06075044669446099,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.8398,
|
|
"mean_token_accuracy": 0.09024247303605079,
|
|
"num_tokens": 1436802.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.23568754196167,
|
|
"epoch": 0.06134603930911257,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7068,
|
|
"mean_token_accuracy": 0.09397510960698127,
|
|
"num_tokens": 1449212.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.229180955886841,
|
|
"epoch": 0.061941631923764146,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.7693,
|
|
"mean_token_accuracy": 0.09169242009520531,
|
|
"num_tokens": 1463357.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.265628623962402,
|
|
"epoch": 0.06253722453841572,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.7525,
|
|
"mean_token_accuracy": 0.09015973433852195,
|
|
"num_tokens": 1477494.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.205424404144287,
|
|
"epoch": 0.0631328171530673,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6818,
|
|
"mean_token_accuracy": 0.09626985341310501,
|
|
"num_tokens": 1491687.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.081217479705811,
|
|
"epoch": 0.06372840976771887,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6132,
|
|
"mean_token_accuracy": 0.09427964016795158,
|
|
"num_tokens": 1506656.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.22808575630188,
|
|
"epoch": 0.06432400238237046,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6698,
|
|
"mean_token_accuracy": 0.09833893999457359,
|
|
"num_tokens": 1519336.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.212263393402099,
|
|
"epoch": 0.06491959499702203,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.7991,
|
|
"mean_token_accuracy": 0.09189821183681487,
|
|
"num_tokens": 1535204.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.111486864089966,
|
|
"epoch": 0.06551518761167362,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.6043,
|
|
"mean_token_accuracy": 0.10303139835596084,
|
|
"num_tokens": 1547876.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.151664209365845,
|
|
"epoch": 0.06611078022632519,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.7128,
|
|
"mean_token_accuracy": 0.09272770434617997,
|
|
"num_tokens": 1560315.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.1699254512786865,
|
|
"epoch": 0.06670637284097677,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.7602,
|
|
"mean_token_accuracy": 0.09424815848469734,
|
|
"num_tokens": 1576379.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.220321846008301,
|
|
"epoch": 0.06730196545562835,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.6408,
|
|
"mean_token_accuracy": 0.0926160991191864,
|
|
"num_tokens": 1590480.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.07102780342102,
|
|
"epoch": 0.06789755807027993,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.703,
|
|
"mean_token_accuracy": 0.09206220582127571,
|
|
"num_tokens": 1605328.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.1097441673278805,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6425,
|
|
"mean_token_accuracy": 0.1003260225057602,
|
|
"num_tokens": 1619814.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.085073232650757,
|
|
"epoch": 0.06908874329958309,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.5538,
|
|
"mean_token_accuracy": 0.09950781464576722,
|
|
"num_tokens": 1632561.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.082305765151977,
|
|
"epoch": 0.06968433591423466,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6551,
|
|
"mean_token_accuracy": 0.09661801382899285,
|
|
"num_tokens": 1645669.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.117526912689209,
|
|
"epoch": 0.07027992852888625,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5938,
|
|
"mean_token_accuracy": 0.09815755933523178,
|
|
"num_tokens": 1660479.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.989982414245605,
|
|
"epoch": 0.07087552114353782,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6183,
|
|
"mean_token_accuracy": 0.10322244465351105,
|
|
"num_tokens": 1673966.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.9893852233886715,
|
|
"epoch": 0.0714711137581894,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.5064,
|
|
"mean_token_accuracy": 0.10409865230321884,
|
|
"num_tokens": 1688866.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.006651830673218,
|
|
"epoch": 0.07206670637284097,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.5253,
|
|
"mean_token_accuracy": 0.10221413522958755,
|
|
"num_tokens": 1703810.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.084087467193603,
|
|
"epoch": 0.07266229898749256,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.726,
|
|
"mean_token_accuracy": 0.09800749719142914,
|
|
"num_tokens": 1719308.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.085141658782959,
|
|
"epoch": 0.07325789160214413,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.5164,
|
|
"mean_token_accuracy": 0.10650407746434212,
|
|
"num_tokens": 1734508.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.996237087249756,
|
|
"epoch": 0.07385348421679572,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4823,
|
|
"mean_token_accuracy": 0.10844174847006798,
|
|
"num_tokens": 1745999.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.891753721237182,
|
|
"epoch": 0.07444907683144729,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.4833,
|
|
"mean_token_accuracy": 0.10262857228517533,
|
|
"num_tokens": 1761083.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.933672142028809,
|
|
"epoch": 0.07504466944609887,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4377,
|
|
"mean_token_accuracy": 0.10970923900604249,
|
|
"num_tokens": 1774948.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.065245723724365,
|
|
"epoch": 0.07564026206075045,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5462,
|
|
"mean_token_accuracy": 0.10084090903401374,
|
|
"num_tokens": 1787897.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.849849843978882,
|
|
"epoch": 0.07623585467540203,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.447,
|
|
"mean_token_accuracy": 0.10135650783777236,
|
|
"num_tokens": 1801208.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.905785322189331,
|
|
"epoch": 0.0768314472900536,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4399,
|
|
"mean_token_accuracy": 0.10623147189617158,
|
|
"num_tokens": 1815439.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.934341907501221,
|
|
"epoch": 0.07742703990470517,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4706,
|
|
"mean_token_accuracy": 0.10109811723232269,
|
|
"num_tokens": 1828177.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.9069075107574465,
|
|
"epoch": 0.07802263251935676,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.4401,
|
|
"mean_token_accuracy": 0.10964255481958389,
|
|
"num_tokens": 1844854.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.850523233413696,
|
|
"epoch": 0.07861822513400833,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.4589,
|
|
"mean_token_accuracy": 0.10506043657660484,
|
|
"num_tokens": 1858245.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.912349796295166,
|
|
"epoch": 0.07921381774865992,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5421,
|
|
"mean_token_accuracy": 0.09892791137099266,
|
|
"num_tokens": 1872167.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.98550853729248,
|
|
"epoch": 0.07980941036331149,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4915,
|
|
"mean_token_accuracy": 0.10364059209823609,
|
|
"num_tokens": 1885376.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.929462909698486,
|
|
"epoch": 0.08040500297796307,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5236,
|
|
"mean_token_accuracy": 0.10212516784667969,
|
|
"num_tokens": 1899318.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.881788492202759,
|
|
"epoch": 0.08100059559261465,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5513,
|
|
"mean_token_accuracy": 0.09749151393771172,
|
|
"num_tokens": 1914028.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.9367156505584715,
|
|
"epoch": 0.08159618820726623,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4879,
|
|
"mean_token_accuracy": 0.10404472425580025,
|
|
"num_tokens": 1927653.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.8751222610473635,
|
|
"epoch": 0.0821917808219178,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4722,
|
|
"mean_token_accuracy": 0.10491280928254128,
|
|
"num_tokens": 1941397.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.844230985641479,
|
|
"epoch": 0.08278737343656939,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4394,
|
|
"mean_token_accuracy": 0.11292621716856957,
|
|
"num_tokens": 1955941.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.873829555511475,
|
|
"epoch": 0.08338296605122096,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.4411,
|
|
"mean_token_accuracy": 0.11104056984186172,
|
|
"num_tokens": 1970440.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.8488373279571535,
|
|
"epoch": 0.08397855866587255,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.3716,
|
|
"mean_token_accuracy": 0.10946704521775245,
|
|
"num_tokens": 1985770.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.880035781860352,
|
|
"epoch": 0.08457415128052412,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5109,
|
|
"mean_token_accuracy": 0.10345830023288727,
|
|
"num_tokens": 1999314.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.829602193832398,
|
|
"epoch": 0.0851697438951757,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.3619,
|
|
"mean_token_accuracy": 0.11096959337592124,
|
|
"num_tokens": 2014578.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.770991659164428,
|
|
"epoch": 0.08576533650982728,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4632,
|
|
"mean_token_accuracy": 0.10845699012279511,
|
|
"num_tokens": 2027650.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.815863227844238,
|
|
"epoch": 0.08636092912447886,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.3974,
|
|
"mean_token_accuracy": 0.10836413204669952,
|
|
"num_tokens": 2042215.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.819264030456543,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.4312,
|
|
"mean_token_accuracy": 0.10930703803896905,
|
|
"num_tokens": 2055818.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.765752077102661,
|
|
"epoch": 0.08755211435378202,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.3629,
|
|
"mean_token_accuracy": 0.10484683290123939,
|
|
"num_tokens": 2069040.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.779899024963379,
|
|
"epoch": 0.08814770696843359,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.3655,
|
|
"mean_token_accuracy": 0.11239994913339615,
|
|
"num_tokens": 2085085.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.81702184677124,
|
|
"epoch": 0.08874329958308518,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.4548,
|
|
"mean_token_accuracy": 0.10735387653112412,
|
|
"num_tokens": 2100780.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.8485040187835695,
|
|
"epoch": 0.08933889219773675,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.4447,
|
|
"mean_token_accuracy": 0.10719722360372544,
|
|
"num_tokens": 2116317.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.7829875469207765,
|
|
"epoch": 0.08993448481238833,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3759,
|
|
"mean_token_accuracy": 0.10919374153017998,
|
|
"num_tokens": 2130865.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.765843772888184,
|
|
"epoch": 0.0905300774270399,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4189,
|
|
"mean_token_accuracy": 0.10919043198227882,
|
|
"num_tokens": 2145791.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.7471170902252195,
|
|
"epoch": 0.09112567004169149,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.335,
|
|
"mean_token_accuracy": 0.11494111120700837,
|
|
"num_tokens": 2158750.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.8053412437438965,
|
|
"epoch": 0.09172126265634306,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4184,
|
|
"mean_token_accuracy": 0.10531997457146644,
|
|
"num_tokens": 2175026.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.626815366744995,
|
|
"epoch": 0.09231685527099463,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.10479198396205902,
|
|
"num_tokens": 2189597.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.871908044815063,
|
|
"epoch": 0.09291244788564622,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5028,
|
|
"mean_token_accuracy": 0.10715138986706733,
|
|
"num_tokens": 2203663.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.708221340179444,
|
|
"epoch": 0.09350804050029779,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.309,
|
|
"mean_token_accuracy": 0.1115417167544365,
|
|
"num_tokens": 2218784.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.721556663513184,
|
|
"epoch": 0.09410363311494938,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.3204,
|
|
"mean_token_accuracy": 0.11020497232675552,
|
|
"num_tokens": 2233256.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.72320671081543,
|
|
"epoch": 0.09469922572960095,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.345,
|
|
"mean_token_accuracy": 0.11311636269092559,
|
|
"num_tokens": 2247689.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.660076570510864,
|
|
"epoch": 0.09529481834425253,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.2075,
|
|
"mean_token_accuracy": 0.1183502845466137,
|
|
"num_tokens": 2261158.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.607417726516724,
|
|
"epoch": 0.0958904109589041,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.1543,
|
|
"mean_token_accuracy": 0.12614388689398764,
|
|
"num_tokens": 2274013.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.712612342834473,
|
|
"epoch": 0.09648600357355569,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4276,
|
|
"mean_token_accuracy": 0.11010882630944252,
|
|
"num_tokens": 2287471.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.5407732963562015,
|
|
"epoch": 0.09708159618820726,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.11724651902914048,
|
|
"num_tokens": 2302536.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.797843170166016,
|
|
"epoch": 0.09767718880285885,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.4347,
|
|
"mean_token_accuracy": 0.11103935763239861,
|
|
"num_tokens": 2315235.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.734398555755615,
|
|
"epoch": 0.09827278141751042,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4861,
|
|
"mean_token_accuracy": 0.10722489356994629,
|
|
"num_tokens": 2329010.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.720923137664795,
|
|
"epoch": 0.098868374032162,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3117,
|
|
"mean_token_accuracy": 0.11377218067646026,
|
|
"num_tokens": 2342862.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.66477599143982,
|
|
"epoch": 0.09946396664681358,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.1728,
|
|
"mean_token_accuracy": 0.1223041906952858,
|
|
"num_tokens": 2354680.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.641294670104981,
|
|
"epoch": 0.10005955926146516,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.2917,
|
|
"mean_token_accuracy": 0.11401325613260269,
|
|
"num_tokens": 2369251.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.591806840896607,
|
|
"epoch": 0.10065515187611673,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3274,
|
|
"mean_token_accuracy": 0.11739440113306046,
|
|
"num_tokens": 2382880.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.586479949951172,
|
|
"epoch": 0.10125074449076832,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2035,
|
|
"mean_token_accuracy": 0.11815706938505173,
|
|
"num_tokens": 2397627.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.688563108444214,
|
|
"epoch": 0.10184633710541989,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.2696,
|
|
"mean_token_accuracy": 0.1177187018096447,
|
|
"num_tokens": 2411923.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.6933588027954105,
|
|
"epoch": 0.10244192972007148,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3613,
|
|
"mean_token_accuracy": 0.1067679412662983,
|
|
"num_tokens": 2426253.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.608582544326782,
|
|
"epoch": 0.10303752233472305,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2902,
|
|
"mean_token_accuracy": 0.11663747504353524,
|
|
"num_tokens": 2440887.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.677258396148682,
|
|
"epoch": 0.10363311494937463,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2558,
|
|
"mean_token_accuracy": 0.11874346956610679,
|
|
"num_tokens": 2453556.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.6070856094360355,
|
|
"epoch": 0.1042287075640262,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.288,
|
|
"mean_token_accuracy": 0.11727045178413391,
|
|
"num_tokens": 2467374.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.571826696395874,
|
|
"epoch": 0.10482430017867779,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.11710346788167954,
|
|
"num_tokens": 2481106.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.581917428970337,
|
|
"epoch": 0.10541989279332936,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.1906,
|
|
"mean_token_accuracy": 0.1213937483727932,
|
|
"num_tokens": 2495431.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.537778902053833,
|
|
"epoch": 0.10601548540798095,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.2675,
|
|
"mean_token_accuracy": 0.11115022003650665,
|
|
"num_tokens": 2511312.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.616943073272705,
|
|
"epoch": 0.10661107802263252,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2159,
|
|
"mean_token_accuracy": 0.11556814685463905,
|
|
"num_tokens": 2524960.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.626460790634155,
|
|
"epoch": 0.1072066706372841,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2737,
|
|
"mean_token_accuracy": 0.11773282811045646,
|
|
"num_tokens": 2537965.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.6072300434112545,
|
|
"epoch": 0.10780226325193568,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2788,
|
|
"mean_token_accuracy": 0.11970137506723404,
|
|
"num_tokens": 2550802.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.591081953048706,
|
|
"epoch": 0.10839785586658725,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2862,
|
|
"mean_token_accuracy": 0.11800834238529205,
|
|
"num_tokens": 2565844.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.595367097854615,
|
|
"epoch": 0.10899344848123883,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2565,
|
|
"mean_token_accuracy": 0.11649239212274551,
|
|
"num_tokens": 2580049.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.482936382293701,
|
|
"epoch": 0.1095890410958904,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.1448,
|
|
"mean_token_accuracy": 0.12193809524178505,
|
|
"num_tokens": 2594516.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.511714839935303,
|
|
"epoch": 0.11018463371054199,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2034,
|
|
"mean_token_accuracy": 0.11656689867377282,
|
|
"num_tokens": 2610528.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.501130628585815,
|
|
"epoch": 0.11078022632519356,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2033,
|
|
"mean_token_accuracy": 0.11759555637836457,
|
|
"num_tokens": 2624357.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.434783506393432,
|
|
"epoch": 0.11137581893984515,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.101,
|
|
"mean_token_accuracy": 0.12296189963817597,
|
|
"num_tokens": 2640422.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.440039587020874,
|
|
"epoch": 0.11197141155449672,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.0936,
|
|
"mean_token_accuracy": 0.12058185562491416,
|
|
"num_tokens": 2653573.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.473729467391967,
|
|
"epoch": 0.1125670041691483,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1081,
|
|
"mean_token_accuracy": 0.12454278320074082,
|
|
"num_tokens": 2667746.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.414681053161621,
|
|
"epoch": 0.11316259678379988,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1161,
|
|
"mean_token_accuracy": 0.12352227419614792,
|
|
"num_tokens": 2681158.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.527306318283081,
|
|
"epoch": 0.11375818939845146,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2165,
|
|
"mean_token_accuracy": 0.11906958743929863,
|
|
"num_tokens": 2693093.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.525028371810913,
|
|
"epoch": 0.11435378201310303,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2047,
|
|
"mean_token_accuracy": 0.11837840005755425,
|
|
"num_tokens": 2704664.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.366198587417602,
|
|
"epoch": 0.11494937462775462,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.0602,
|
|
"mean_token_accuracy": 0.11995950192213059,
|
|
"num_tokens": 2718495.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.491328144073487,
|
|
"epoch": 0.11554496724240619,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.12504696175456048,
|
|
"num_tokens": 2731529.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.353138732910156,
|
|
"epoch": 0.11614055985705778,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.0651,
|
|
"mean_token_accuracy": 0.12829754576087,
|
|
"num_tokens": 2745382.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.522163438796997,
|
|
"epoch": 0.11673615247170935,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.162,
|
|
"mean_token_accuracy": 0.12371505424380302,
|
|
"num_tokens": 2758291.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.374239492416382,
|
|
"epoch": 0.11733174508636093,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.0693,
|
|
"mean_token_accuracy": 0.1308108687400818,
|
|
"num_tokens": 2771179.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.463430023193359,
|
|
"epoch": 0.1179273377010125,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.138,
|
|
"mean_token_accuracy": 0.12384373098611831,
|
|
"num_tokens": 2784172.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.536656045913697,
|
|
"epoch": 0.11852293031566409,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2009,
|
|
"mean_token_accuracy": 0.12257609069347382,
|
|
"num_tokens": 2798402.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.3584379196167,
|
|
"epoch": 0.11911852293031566,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.12082507088780403,
|
|
"num_tokens": 2813371.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.415217399597168,
|
|
"epoch": 0.11971411554496725,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999974174771,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.1270086333155632,
|
|
"num_tokens": 2825837.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.527797079086303,
|
|
"epoch": 0.12030970815961882,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999999869259778,
|
|
"loss": 6.1476,
|
|
"mean_token_accuracy": 0.11767676174640655,
|
|
"num_tokens": 2837988.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.3425514698028564,
|
|
"epoch": 0.1209053007742704,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999999683640947,
|
|
"loss": 6.0479,
|
|
"mean_token_accuracy": 0.12839874923229216,
|
|
"num_tokens": 2851396.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.329852104187012,
|
|
"epoch": 0.12150089338892198,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999417318286,
|
|
"loss": 6.1058,
|
|
"mean_token_accuracy": 0.12663584053516388,
|
|
"num_tokens": 2863958.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.465506744384766,
|
|
"epoch": 0.12209648600357356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999070291805,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.1186541423201561,
|
|
"num_tokens": 2876179.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.492192602157592,
|
|
"epoch": 0.12269207861822513,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999998642561514,
|
|
"loss": 6.1945,
|
|
"mean_token_accuracy": 0.120078806579113,
|
|
"num_tokens": 2890023.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.381492853164673,
|
|
"epoch": 0.1232876712328767,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999998134127432,
|
|
"loss": 6.0571,
|
|
"mean_token_accuracy": 0.1269380420446396,
|
|
"num_tokens": 2902345.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.41484808921814,
|
|
"epoch": 0.12388326384752829,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999997544989574,
|
|
"loss": 6.1925,
|
|
"mean_token_accuracy": 0.11679442450404168,
|
|
"num_tokens": 2916310.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.308828401565552,
|
|
"epoch": 0.12447885646217986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999996875147963,
|
|
"loss": 5.9935,
|
|
"mean_token_accuracy": 0.12981754839420317,
|
|
"num_tokens": 2928523.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.489779281616211,
|
|
"epoch": 0.12507444907683143,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999996124602621,
|
|
"loss": 6.1935,
|
|
"mean_token_accuracy": 0.12208816781640053,
|
|
"num_tokens": 2943367.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.367865753173828,
|
|
"epoch": 0.12567004169148302,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999995293353578,
|
|
"loss": 6.1091,
|
|
"mean_token_accuracy": 0.12408217713236809,
|
|
"num_tokens": 2956995.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.370166778564453,
|
|
"epoch": 0.1262656343061346,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999994381400862,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.1243286520242691,
|
|
"num_tokens": 2971380.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.33416519165039,
|
|
"epoch": 0.1268612269207862,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999993388744504,
|
|
"loss": 6.0895,
|
|
"mean_token_accuracy": 0.12192660868167877,
|
|
"num_tokens": 2986048.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.452546739578247,
|
|
"epoch": 0.12745681953543775,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004999992315384543,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.1280795730650425,
|
|
"num_tokens": 2997058.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.352313089370727,
|
|
"epoch": 0.12805241215008933,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999991161321014,
|
|
"loss": 6.086,
|
|
"mean_token_accuracy": 0.12010991722345352,
|
|
"num_tokens": 3011844.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.341938829421997,
|
|
"epoch": 0.12864800476474092,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999989926553962,
|
|
"loss": 6.0724,
|
|
"mean_token_accuracy": 0.12632107511162757,
|
|
"num_tokens": 3024648.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.301097774505616,
|
|
"epoch": 0.1292435973793925,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499998861108343,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.12609847411513328,
|
|
"num_tokens": 3038533.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.328859663009643,
|
|
"epoch": 0.12983918999404406,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999987214909464,
|
|
"loss": 5.9667,
|
|
"mean_token_accuracy": 0.1258576452732086,
|
|
"num_tokens": 3052531.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.359162616729736,
|
|
"epoch": 0.13043478260869565,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999985738032115,
|
|
"loss": 6.0929,
|
|
"mean_token_accuracy": 0.12015311568975448,
|
|
"num_tokens": 3066526.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.303039121627807,
|
|
"epoch": 0.13103037522334723,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999984180451436,
|
|
"loss": 6.0107,
|
|
"mean_token_accuracy": 0.12698210626840592,
|
|
"num_tokens": 3080729.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.366794204711914,
|
|
"epoch": 0.13162596783799882,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999982542167483,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.12779821902513505,
|
|
"num_tokens": 3093776.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.242038297653198,
|
|
"epoch": 0.13222156045265038,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999980823180314,
|
|
"loss": 5.995,
|
|
"mean_token_accuracy": 0.1289702907204628,
|
|
"num_tokens": 3107005.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.390946006774902,
|
|
"epoch": 0.13281715306730196,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499997902348999,
|
|
"loss": 6.2139,
|
|
"mean_token_accuracy": 0.123123649507761,
|
|
"num_tokens": 3120840.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.329113721847534,
|
|
"epoch": 0.13341274568195355,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004999977143096578,
|
|
"loss": 6.0003,
|
|
"mean_token_accuracy": 0.13599837496876716,
|
|
"num_tokens": 3134894.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.4248573780059814,
|
|
"epoch": 0.13400833829660513,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999975182000143,
|
|
"loss": 6.1723,
|
|
"mean_token_accuracy": 0.11902732923626899,
|
|
"num_tokens": 3146917.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.3331897258758545,
|
|
"epoch": 0.1346039309112567,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999973140200759,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.12749992683529854,
|
|
"num_tokens": 3162161.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.29176082611084,
|
|
"epoch": 0.13519952352590828,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999971017698495,
|
|
"loss": 5.997,
|
|
"mean_token_accuracy": 0.12809050157666207,
|
|
"num_tokens": 3176627.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.290631914138794,
|
|
"epoch": 0.13579511614055986,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999968814493428,
|
|
"loss": 6.0509,
|
|
"mean_token_accuracy": 0.12325706332921982,
|
|
"num_tokens": 3190139.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.129739570617676,
|
|
"epoch": 0.13639070875521145,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999966530585639,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.1336134321987629,
|
|
"num_tokens": 3202312.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.335797929763794,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999964165975209,
|
|
"loss": 6.013,
|
|
"mean_token_accuracy": 0.12452457398176194,
|
|
"num_tokens": 3219052.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.199960422515869,
|
|
"epoch": 0.1375818939845146,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999961720662221,
|
|
"loss": 5.93,
|
|
"mean_token_accuracy": 0.13772231340408325,
|
|
"num_tokens": 3233706.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.329391717910767,
|
|
"epoch": 0.13817748659916618,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999959194646766,
|
|
"loss": 6.1365,
|
|
"mean_token_accuracy": 0.12410388141870499,
|
|
"num_tokens": 3249947.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.254737424850464,
|
|
"epoch": 0.13877307921381773,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999956587928932,
|
|
"loss": 5.9511,
|
|
"mean_token_accuracy": 0.13368401676416397,
|
|
"num_tokens": 3264308.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.237644338607788,
|
|
"epoch": 0.13936867182846932,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999953900508814,
|
|
"loss": 5.9313,
|
|
"mean_token_accuracy": 0.13862481266260146,
|
|
"num_tokens": 3277171.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.216887712478638,
|
|
"epoch": 0.1399642644431209,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999951132386507,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.1251385323703289,
|
|
"num_tokens": 3290445.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.230327320098877,
|
|
"epoch": 0.1405598570577725,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999948283562111,
|
|
"loss": 5.9128,
|
|
"mean_token_accuracy": 0.13102139234542848,
|
|
"num_tokens": 3304850.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.208104801177979,
|
|
"epoch": 0.14115544967242405,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499994535403573,
|
|
"loss": 5.991,
|
|
"mean_token_accuracy": 0.12939597889781,
|
|
"num_tokens": 3318765.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.284398698806763,
|
|
"epoch": 0.14175104228707563,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999942343807465,
|
|
"loss": 5.9608,
|
|
"mean_token_accuracy": 0.12530108392238617,
|
|
"num_tokens": 3330403.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.280538749694824,
|
|
"epoch": 0.14234663490172722,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999939252877428,
|
|
"loss": 5.9603,
|
|
"mean_token_accuracy": 0.13062661439180373,
|
|
"num_tokens": 3346420.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.3126036643981935,
|
|
"epoch": 0.1429422275163788,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999936081245727,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.12489332854747773,
|
|
"num_tokens": 3361853.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.11865086555481,
|
|
"epoch": 0.14353782013103036,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999932828912478,
|
|
"loss": 5.9865,
|
|
"mean_token_accuracy": 0.12948045805096625,
|
|
"num_tokens": 3375907.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.311586666107178,
|
|
"epoch": 0.14413341274568195,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999929495877796,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.12694947198033332,
|
|
"num_tokens": 3390151.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.227874851226806,
|
|
"epoch": 0.14472900536033353,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999926082141801,
|
|
"loss": 5.9907,
|
|
"mean_token_accuracy": 0.12592855468392372,
|
|
"num_tokens": 3405151.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.297283744812011,
|
|
"epoch": 0.14532459797498512,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999922587704616,
|
|
"loss": 6.0123,
|
|
"mean_token_accuracy": 0.1289777062833309,
|
|
"num_tokens": 3420510.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.134367656707764,
|
|
"epoch": 0.14592019058963668,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999919012566366,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.13303905054926873,
|
|
"num_tokens": 3435162.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.3096319198608395,
|
|
"epoch": 0.14651578320428826,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999915356727179,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.12648904845118522,
|
|
"num_tokens": 3450923.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.178441858291626,
|
|
"epoch": 0.14711137581893985,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999911620187186,
|
|
"loss": 5.9686,
|
|
"mean_token_accuracy": 0.13010273054242133,
|
|
"num_tokens": 3464575.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.18217191696167,
|
|
"epoch": 0.14770696843359143,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999907802946521,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.1358582466840744,
|
|
"num_tokens": 3477494.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.332776260375977,
|
|
"epoch": 0.148302561048243,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999903905005323,
|
|
"loss": 6.1045,
|
|
"mean_token_accuracy": 0.12159235775470734,
|
|
"num_tokens": 3492314.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.201799583435059,
|
|
"epoch": 0.14889815366289458,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999899926363729,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.13536160737276076,
|
|
"num_tokens": 3504913.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.3105498313903805,
|
|
"epoch": 0.14949374627754616,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999895867021882,
|
|
"loss": 6.0594,
|
|
"mean_token_accuracy": 0.12324824780225754,
|
|
"num_tokens": 3519758.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.208724546432495,
|
|
"epoch": 0.15008933889219775,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999891726979928,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.13799096569418906,
|
|
"num_tokens": 3531268.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.255499744415284,
|
|
"epoch": 0.1506849315068493,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999887506238018,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.12254432216286659,
|
|
"num_tokens": 3546560.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.149677562713623,
|
|
"epoch": 0.1512805241215009,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049998832047963,
|
|
"loss": 5.9394,
|
|
"mean_token_accuracy": 0.13916889131069182,
|
|
"num_tokens": 3560602.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.181966352462768,
|
|
"epoch": 0.15187611673615248,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999878822654929,
|
|
"loss": 5.9171,
|
|
"mean_token_accuracy": 0.12628751248121262,
|
|
"num_tokens": 3575611.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.153938150405883,
|
|
"epoch": 0.15247170935080406,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999874359814064,
|
|
"loss": 5.8903,
|
|
"mean_token_accuracy": 0.12943542823195459,
|
|
"num_tokens": 3589933.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.186302137374878,
|
|
"epoch": 0.15306730196545562,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999869816273863,
|
|
"loss": 5.934,
|
|
"mean_token_accuracy": 0.13333622738718987,
|
|
"num_tokens": 3602513.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.212094688415528,
|
|
"epoch": 0.1536628945801072,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999865192034489,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.12433857470750809,
|
|
"num_tokens": 3615488.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.194716072082519,
|
|
"epoch": 0.1542584871947588,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499986048709611,
|
|
"loss": 5.8549,
|
|
"mean_token_accuracy": 0.13235142156481744,
|
|
"num_tokens": 3629292.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.013790655136108,
|
|
"epoch": 0.15485407980941035,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999855701458893,
|
|
"loss": 5.8692,
|
|
"mean_token_accuracy": 0.1351253107190132,
|
|
"num_tokens": 3647010.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.201636695861817,
|
|
"epoch": 0.15544967242406194,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999850835123009,
|
|
"loss": 5.8879,
|
|
"mean_token_accuracy": 0.13833648189902306,
|
|
"num_tokens": 3661994.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.199787235260009,
|
|
"epoch": 0.15604526503871352,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999845888088635,
|
|
"loss": 5.9376,
|
|
"mean_token_accuracy": 0.13500029519200324,
|
|
"num_tokens": 3676789.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.177236413955688,
|
|
"epoch": 0.1566408576533651,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999840860355946,
|
|
"loss": 5.8763,
|
|
"mean_token_accuracy": 0.13209234178066254,
|
|
"num_tokens": 3689598.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.1664684295654295,
|
|
"epoch": 0.15723645026801666,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999835751925124,
|
|
"loss": 5.9715,
|
|
"mean_token_accuracy": 0.13493691980838776,
|
|
"num_tokens": 3703597.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.142622280120849,
|
|
"epoch": 0.15783204288266825,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999830562796351,
|
|
"loss": 5.9335,
|
|
"mean_token_accuracy": 0.13459465578198432,
|
|
"num_tokens": 3717312.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.146435022354126,
|
|
"epoch": 0.15842763549731984,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999825292969814,
|
|
"loss": 5.8716,
|
|
"mean_token_accuracy": 0.13243480250239373,
|
|
"num_tokens": 3731677.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.192383813858032,
|
|
"epoch": 0.15902322811197142,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999819942445703,
|
|
"loss": 5.9646,
|
|
"mean_token_accuracy": 0.13210354819893838,
|
|
"num_tokens": 3746648.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.061094045639038,
|
|
"epoch": 0.15961882072662298,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999814511224207,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.13954348489642143,
|
|
"num_tokens": 3760859.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.125566244125366,
|
|
"epoch": 0.16021441334127456,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999808999305523,
|
|
"loss": 5.812,
|
|
"mean_token_accuracy": 0.14403728321194648,
|
|
"num_tokens": 3774743.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.11449089050293,
|
|
"epoch": 0.16081000595592615,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999803406689848,
|
|
"loss": 5.8883,
|
|
"mean_token_accuracy": 0.13627953380346297,
|
|
"num_tokens": 3789566.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.175709247589111,
|
|
"epoch": 0.16140559857057774,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999797733377384,
|
|
"loss": 5.8704,
|
|
"mean_token_accuracy": 0.13867518082261085,
|
|
"num_tokens": 3802875.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.023449468612671,
|
|
"epoch": 0.1620011911852293,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999791979368332,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.13548058420419692,
|
|
"num_tokens": 3816197.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.078633451461792,
|
|
"epoch": 0.16259678379988088,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999786144662899,
|
|
"loss": 5.8745,
|
|
"mean_token_accuracy": 0.13849861174821854,
|
|
"num_tokens": 3829196.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.281984329223633,
|
|
"epoch": 0.16319237641453246,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999780229261295,
|
|
"loss": 5.9806,
|
|
"mean_token_accuracy": 0.13247482031583785,
|
|
"num_tokens": 3842618.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.129805183410644,
|
|
"epoch": 0.16378796902918405,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999774233163734,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.1349676601588726,
|
|
"num_tokens": 3854833.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.222629356384277,
|
|
"epoch": 0.1643835616438356,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999768156370428,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.1408792868256569,
|
|
"num_tokens": 3867971.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.116525554656983,
|
|
"epoch": 0.1649791542584872,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999761998881596,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.137498077750206,
|
|
"num_tokens": 3881555.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.07482943534851,
|
|
"epoch": 0.16557474687313878,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999755760697459,
|
|
"loss": 5.8279,
|
|
"mean_token_accuracy": 0.13793229386210443,
|
|
"num_tokens": 3894717.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.133864688873291,
|
|
"epoch": 0.16617033948779036,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499974944181824,
|
|
"loss": 5.8423,
|
|
"mean_token_accuracy": 0.13098374754190445,
|
|
"num_tokens": 3909381.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.084359836578369,
|
|
"epoch": 0.16676593210244192,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999743042244167,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.140174800157547,
|
|
"num_tokens": 3923828.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.032461881637573,
|
|
"epoch": 0.1673615247170935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499973656197547,
|
|
"loss": 5.771,
|
|
"mean_token_accuracy": 0.145071642100811,
|
|
"num_tokens": 3936901.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.1170196533203125,
|
|
"epoch": 0.1679571173317451,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999730001012379,
|
|
"loss": 5.8664,
|
|
"mean_token_accuracy": 0.14042325764894487,
|
|
"num_tokens": 3949052.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.060851192474365,
|
|
"epoch": 0.16855270994639668,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999723359355131,
|
|
"loss": 5.9055,
|
|
"mean_token_accuracy": 0.13427708745002748,
|
|
"num_tokens": 3963099.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.181085157394409,
|
|
"epoch": 0.16914830256104824,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999716637003965,
|
|
"loss": 5.8284,
|
|
"mean_token_accuracy": 0.1343017265200615,
|
|
"num_tokens": 3977598.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.14753737449646,
|
|
"epoch": 0.16974389517569982,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499970983395912,
|
|
"loss": 5.9807,
|
|
"mean_token_accuracy": 0.13452064618468285,
|
|
"num_tokens": 3989995.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.169982481002807,
|
|
"epoch": 0.1703394877903514,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999702950220841,
|
|
"loss": 5.8672,
|
|
"mean_token_accuracy": 0.13851600810885428,
|
|
"num_tokens": 4002971.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.030078363418579,
|
|
"epoch": 0.17093508040500296,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999695985789376,
|
|
"loss": 5.7973,
|
|
"mean_token_accuracy": 0.13650505170226096,
|
|
"num_tokens": 4017380.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.066078996658325,
|
|
"epoch": 0.17153067301965455,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999688940664972,
|
|
"loss": 5.8719,
|
|
"mean_token_accuracy": 0.1359370768070221,
|
|
"num_tokens": 4031125.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.0827854633331295,
|
|
"epoch": 0.17212626563430614,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999681814847884,
|
|
"loss": 5.8571,
|
|
"mean_token_accuracy": 0.13307401165366173,
|
|
"num_tokens": 4046416.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.133123397827148,
|
|
"epoch": 0.17272185824895772,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999674608338367,
|
|
"loss": 5.9017,
|
|
"mean_token_accuracy": 0.13661788851022721,
|
|
"num_tokens": 4061024.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.135586833953857,
|
|
"epoch": 0.17331745086360928,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999667321136681,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.14357046857476236,
|
|
"num_tokens": 4074753.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 5.990246534347534,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999659953243085,
|
|
"loss": 5.797,
|
|
"mean_token_accuracy": 0.13705897554755211,
|
|
"num_tokens": 4089954.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.075388431549072,
|
|
"epoch": 0.17450863609291245,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999652504657844,
|
|
"loss": 5.8001,
|
|
"mean_token_accuracy": 0.14036204069852828,
|
|
"num_tokens": 4105220.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.045007419586182,
|
|
"epoch": 0.17510422870756404,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999644975381226,
|
|
"loss": 5.8138,
|
|
"mean_token_accuracy": 0.13910319581627845,
|
|
"num_tokens": 4117578.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.073321771621704,
|
|
"epoch": 0.1756998213222156,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00049996373654135,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.13800777047872542,
|
|
"num_tokens": 4131113.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.925372457504272,
|
|
"epoch": 0.17629541393686718,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999629674754939,
|
|
"loss": 5.6924,
|
|
"mean_token_accuracy": 0.14459261149168015,
|
|
"num_tokens": 4145029.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.07428207397461,
|
|
"epoch": 0.17689100655151876,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999621903405819,
|
|
"loss": 5.8448,
|
|
"mean_token_accuracy": 0.13987531289458274,
|
|
"num_tokens": 4157227.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.997102546691894,
|
|
"epoch": 0.17748659916617035,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999614051366421,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.13752183616161345,
|
|
"num_tokens": 4171172.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.102160787582397,
|
|
"epoch": 0.1780821917808219,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999606118637022,
|
|
"loss": 5.7613,
|
|
"mean_token_accuracy": 0.14721178859472275,
|
|
"num_tokens": 4184219.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.924183893203735,
|
|
"epoch": 0.1786777843954735,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999598105217911,
|
|
"loss": 5.7174,
|
|
"mean_token_accuracy": 0.1472506955265999,
|
|
"num_tokens": 4199317.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.155888223648072,
|
|
"epoch": 0.17927337701012508,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999590011109373,
|
|
"loss": 5.8777,
|
|
"mean_token_accuracy": 0.13627814128994942,
|
|
"num_tokens": 4213905.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.982195091247559,
|
|
"epoch": 0.17986896962477666,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049995818363117,
|
|
"loss": 5.7864,
|
|
"mean_token_accuracy": 0.13483413383364679,
|
|
"num_tokens": 4228123.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.075154113769531,
|
|
"epoch": 0.18046456223942822,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999573580825182,
|
|
"loss": 5.7709,
|
|
"mean_token_accuracy": 0.1384432390332222,
|
|
"num_tokens": 4243024.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.969430923461914,
|
|
"epoch": 0.1810601548540798,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999565244650119,
|
|
"loss": 5.7606,
|
|
"mean_token_accuracy": 0.140154667198658,
|
|
"num_tokens": 4259061.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.091729736328125,
|
|
"epoch": 0.1816557474687314,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999556827786807,
|
|
"loss": 5.9387,
|
|
"mean_token_accuracy": 0.13430257365107537,
|
|
"num_tokens": 4273010.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.062456846237183,
|
|
"epoch": 0.18225134008338298,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999548330235549,
|
|
"loss": 5.742,
|
|
"mean_token_accuracy": 0.146440476924181,
|
|
"num_tokens": 4286515.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.001115512847901,
|
|
"epoch": 0.18284693269803454,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999539751996651,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.14425970166921614,
|
|
"num_tokens": 4300125.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.929234790802002,
|
|
"epoch": 0.18344252531268612,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499953109307042,
|
|
"loss": 5.7329,
|
|
"mean_token_accuracy": 0.14257181733846663,
|
|
"num_tokens": 4313962.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.009220933914184,
|
|
"epoch": 0.1840381179273377,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999522353457165,
|
|
"loss": 5.7773,
|
|
"mean_token_accuracy": 0.14214551225304603,
|
|
"num_tokens": 4328776.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.074196243286133,
|
|
"epoch": 0.18463371054198927,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999513533157201,
|
|
"loss": 5.8145,
|
|
"mean_token_accuracy": 0.14416868686676027,
|
|
"num_tokens": 4340933.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.015391874313354,
|
|
"epoch": 0.18522930315664085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999504632170844,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.1347845658659935,
|
|
"num_tokens": 4355463.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.059228897094727,
|
|
"epoch": 0.18582489577129244,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999495650498413,
|
|
"loss": 5.8178,
|
|
"mean_token_accuracy": 0.13992976918816566,
|
|
"num_tokens": 4369717.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.047009229660034,
|
|
"epoch": 0.18642048838594402,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999486588140231,
|
|
"loss": 5.8022,
|
|
"mean_token_accuracy": 0.14501721635460854,
|
|
"num_tokens": 4383713.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.9465508460998535,
|
|
"epoch": 0.18701608100059558,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999477445096623,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.14647423028945922,
|
|
"num_tokens": 4396487.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.122650671005249,
|
|
"epoch": 0.18761167361524717,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999468221367916,
|
|
"loss": 5.8341,
|
|
"mean_token_accuracy": 0.14547718539834023,
|
|
"num_tokens": 4408762.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.873108673095703,
|
|
"epoch": 0.18820726622989875,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999458916954442,
|
|
"loss": 5.7273,
|
|
"mean_token_accuracy": 0.1382825143635273,
|
|
"num_tokens": 4422871.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.047405529022217,
|
|
"epoch": 0.18880285884455034,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999449531856532,
|
|
"loss": 5.7817,
|
|
"mean_token_accuracy": 0.14346812292933464,
|
|
"num_tokens": 4436399.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.917907571792602,
|
|
"epoch": 0.1893984514592019,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999440066074526,
|
|
"loss": 5.6556,
|
|
"mean_token_accuracy": 0.14324021935462952,
|
|
"num_tokens": 4450799.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.888736343383789,
|
|
"epoch": 0.18999404407385348,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999430519608762,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.15139601975679398,
|
|
"num_tokens": 4464567.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.085984420776367,
|
|
"epoch": 0.19058963668850507,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999420892459584,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.14648282527923584,
|
|
"num_tokens": 4478461.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.837108373641968,
|
|
"epoch": 0.19118522930315665,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999411184627334,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.1408247545361519,
|
|
"num_tokens": 4493252.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.07178521156311,
|
|
"epoch": 0.1917808219178082,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999401396112364,
|
|
"loss": 5.8169,
|
|
"mean_token_accuracy": 0.14276161938905715,
|
|
"num_tokens": 4507716.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.958076238632202,
|
|
"epoch": 0.1923764145324598,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499939152691502,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.14387270733714103,
|
|
"num_tokens": 4520903.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.988181114196777,
|
|
"epoch": 0.19297200714711138,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999381577035663,
|
|
"loss": 5.7701,
|
|
"mean_token_accuracy": 0.14710289984941483,
|
|
"num_tokens": 4534939.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.944279718399048,
|
|
"epoch": 0.19356759976176297,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999371546474643,
|
|
"loss": 5.7416,
|
|
"mean_token_accuracy": 0.14387295618653298,
|
|
"num_tokens": 4547502.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.982019662857056,
|
|
"epoch": 0.19416319237641452,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999361435232324,
|
|
"loss": 5.6404,
|
|
"mean_token_accuracy": 0.15546864569187163,
|
|
"num_tokens": 4560531.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.956538581848145,
|
|
"epoch": 0.1947587849910661,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999351243309069,
|
|
"loss": 5.7186,
|
|
"mean_token_accuracy": 0.14406703263521195,
|
|
"num_tokens": 4573678.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.920241498947144,
|
|
"epoch": 0.1953543776057177,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999340970705241,
|
|
"loss": 5.5925,
|
|
"mean_token_accuracy": 0.15064503699541093,
|
|
"num_tokens": 4586313.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.922688674926758,
|
|
"epoch": 0.19594997022036928,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999330617421209,
|
|
"loss": 5.7249,
|
|
"mean_token_accuracy": 0.1432578146457672,
|
|
"num_tokens": 4600030.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.94793381690979,
|
|
"epoch": 0.19654556283502084,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999320183457346,
|
|
"loss": 5.7895,
|
|
"mean_token_accuracy": 0.14367235824465752,
|
|
"num_tokens": 4613289.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.999211740493775,
|
|
"epoch": 0.19714115544967242,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999309668814024,
|
|
"loss": 5.6714,
|
|
"mean_token_accuracy": 0.14725829809904098,
|
|
"num_tokens": 4626642.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.994658041000366,
|
|
"epoch": 0.197736748064324,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999299073491623,
|
|
"loss": 5.7717,
|
|
"mean_token_accuracy": 0.14237359762191773,
|
|
"num_tokens": 4639750.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.911065006256104,
|
|
"epoch": 0.1983323406789756,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999288397490519,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.14523659348487855,
|
|
"num_tokens": 4656894.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.863076972961426,
|
|
"epoch": 0.19892793329362715,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999277640811099,
|
|
"loss": 5.6135,
|
|
"mean_token_accuracy": 0.14550506547093392,
|
|
"num_tokens": 4670229.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.932292318344116,
|
|
"epoch": 0.19952352590827874,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999266803453747,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.14489086717367172,
|
|
"num_tokens": 4683754.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.861297369003296,
|
|
"epoch": 0.20011911852293032,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999255885418852,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.14351495504379272,
|
|
"num_tokens": 4697824.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.084273195266723,
|
|
"epoch": 0.20071471113758188,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999244886706804,
|
|
"loss": 5.7063,
|
|
"mean_token_accuracy": 0.1476170912384987,
|
|
"num_tokens": 4711004.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.9069945335388185,
|
|
"epoch": 0.20131030375223347,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999233807318001,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.1482615776360035,
|
|
"num_tokens": 4724992.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.955147361755371,
|
|
"epoch": 0.20190589636688505,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999222647252837,
|
|
"loss": 5.7651,
|
|
"mean_token_accuracy": 0.1488338366150856,
|
|
"num_tokens": 4737770.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.919939708709717,
|
|
"epoch": 0.20250148898153664,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999211406511714,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.15138266682624818,
|
|
"num_tokens": 4753807.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.810354232788086,
|
|
"epoch": 0.2030970815961882,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999200085095035,
|
|
"loss": 5.6172,
|
|
"mean_token_accuracy": 0.1507824957370758,
|
|
"num_tokens": 4766294.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.82021746635437,
|
|
"epoch": 0.20369267421083978,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999188683003207,
|
|
"loss": 5.6385,
|
|
"mean_token_accuracy": 0.14985886216163635,
|
|
"num_tokens": 4780143.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.9594724655151365,
|
|
"epoch": 0.20428826682549137,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999177200236635,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.14395827203989028,
|
|
"num_tokens": 4793717.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.042572021484375,
|
|
"epoch": 0.20488385944014295,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999165636795736,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.14551655277609826,
|
|
"num_tokens": 4808925.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.785923480987549,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999153992680923,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.15120129138231278,
|
|
"num_tokens": 4821439.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.983820247650146,
|
|
"epoch": 0.2060750446694461,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999142267892612,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.15296397656202315,
|
|
"num_tokens": 4835511.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.789422559738159,
|
|
"epoch": 0.20667063728409768,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999130462431224,
|
|
"loss": 5.6129,
|
|
"mean_token_accuracy": 0.15730532854795456,
|
|
"num_tokens": 4849500.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.890871191024781,
|
|
"epoch": 0.20726622989874927,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999118576297185,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.1478873685002327,
|
|
"num_tokens": 4863372.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.977503395080566,
|
|
"epoch": 0.20786182251340082,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999106609490918,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.14098284542560577,
|
|
"num_tokens": 4876643.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.937208986282348,
|
|
"epoch": 0.2084574151280524,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999094562012855,
|
|
"loss": 5.7161,
|
|
"mean_token_accuracy": 0.14677354469895362,
|
|
"num_tokens": 4890274.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.811558246612549,
|
|
"epoch": 0.209053007742704,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999082433863426,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.15926780849695205,
|
|
"num_tokens": 4905643.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.868651819229126,
|
|
"epoch": 0.20964860035735558,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999070225043068,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.14219833314418792,
|
|
"num_tokens": 4920106.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.908795642852783,
|
|
"epoch": 0.21024419297200714,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999057935552217,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.14921227991580963,
|
|
"num_tokens": 4934498.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.898429441452026,
|
|
"epoch": 0.21083978558665872,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999045565391313,
|
|
"loss": 5.7174,
|
|
"mean_token_accuracy": 0.14658699333667755,
|
|
"num_tokens": 4947562.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.948586416244507,
|
|
"epoch": 0.2114353782013103,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999033114560803,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.14664072990417482,
|
|
"num_tokens": 4962375.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.960314416885376,
|
|
"epoch": 0.2120309708159619,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999020583061132,
|
|
"loss": 5.7365,
|
|
"mean_token_accuracy": 0.14642444998025894,
|
|
"num_tokens": 4975683.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.8760178565979,
|
|
"epoch": 0.21262656343061345,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999007970892749,
|
|
"loss": 5.7235,
|
|
"mean_token_accuracy": 0.1489431828260422,
|
|
"num_tokens": 4989662.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.928982782363891,
|
|
"epoch": 0.21322215604526504,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998995278056107,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.15458934381604195,
|
|
"num_tokens": 5003778.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.874552202224732,
|
|
"epoch": 0.21381774865991662,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998982504551661,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.14478579238057138,
|
|
"num_tokens": 5016556.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.859337520599365,
|
|
"epoch": 0.2144133412745682,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998969650379869,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.1535716950893402,
|
|
"num_tokens": 5029732.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.76890459060669,
|
|
"epoch": 0.21500893388921977,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004998956715541192,
|
|
"loss": 5.5411,
|
|
"mean_token_accuracy": 0.15743917003273963,
|
|
"num_tokens": 5042123.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.881715488433838,
|
|
"epoch": 0.21560452650387135,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998943700036095,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.15229580849409102,
|
|
"num_tokens": 5055537.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.8458868026733395,
|
|
"epoch": 0.21620011911852294,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998930603865042,
|
|
"loss": 5.6726,
|
|
"mean_token_accuracy": 0.1492104411125183,
|
|
"num_tokens": 5068795.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.950700092315674,
|
|
"epoch": 0.2167957117331745,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998917427028507,
|
|
"loss": 5.6803,
|
|
"mean_token_accuracy": 0.14506942629814149,
|
|
"num_tokens": 5083149.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.83851842880249,
|
|
"epoch": 0.21739130434782608,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998904169526959,
|
|
"loss": 5.5948,
|
|
"mean_token_accuracy": 0.15276345163583754,
|
|
"num_tokens": 5096879.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.853925323486328,
|
|
"epoch": 0.21798689696247767,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998890831360876,
|
|
"loss": 5.5712,
|
|
"mean_token_accuracy": 0.15716206580400466,
|
|
"num_tokens": 5110692.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.880740547180176,
|
|
"epoch": 0.21858248957712925,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998877412530735,
|
|
"loss": 5.6759,
|
|
"mean_token_accuracy": 0.1477023884654045,
|
|
"num_tokens": 5125981.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.859289455413818,
|
|
"epoch": 0.2191780821917808,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998863913037017,
|
|
"loss": 5.6223,
|
|
"mean_token_accuracy": 0.14958753809332848,
|
|
"num_tokens": 5138755.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.9917884349823,
|
|
"epoch": 0.2197736748064324,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998850332880208,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.13919250220060347,
|
|
"num_tokens": 5154208.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.93279767036438,
|
|
"epoch": 0.22036926742108398,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998836672060795,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.14053081423044206,
|
|
"num_tokens": 5169633.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.888271522521973,
|
|
"epoch": 0.22096486003573557,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998822930579264,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.14142198786139487,
|
|
"num_tokens": 5186213.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.9545313835144045,
|
|
"epoch": 0.22156045265038712,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998809108436112,
|
|
"loss": 5.7081,
|
|
"mean_token_accuracy": 0.1471554718911648,
|
|
"num_tokens": 5201171.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.805160427093506,
|
|
"epoch": 0.2221560452650387,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998795205631834,
|
|
"loss": 5.6259,
|
|
"mean_token_accuracy": 0.15711353570222855,
|
|
"num_tokens": 5216669.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.035808753967285,
|
|
"epoch": 0.2227516378796903,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998781222166929,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.14197402000427245,
|
|
"num_tokens": 5229774.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.918375253677368,
|
|
"epoch": 0.22334723049434188,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998767158041897,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.14612481221556664,
|
|
"num_tokens": 5241862.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.854528999328613,
|
|
"epoch": 0.22394282310899344,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998753013257242,
|
|
"loss": 5.6276,
|
|
"mean_token_accuracy": 0.154552099108696,
|
|
"num_tokens": 5255768.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.871614646911621,
|
|
"epoch": 0.22453841572364502,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998738787813475,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.15562250316143036,
|
|
"num_tokens": 5268472.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.7948620319366455,
|
|
"epoch": 0.2251340083382966,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998724481711103,
|
|
"loss": 5.5361,
|
|
"mean_token_accuracy": 0.15973934084177016,
|
|
"num_tokens": 5284309.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.914908027648925,
|
|
"epoch": 0.2257296009529482,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499871009495064,
|
|
"loss": 5.6846,
|
|
"mean_token_accuracy": 0.14368400871753692,
|
|
"num_tokens": 5298559.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.86197681427002,
|
|
"epoch": 0.22632519356759975,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998695627532601,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.15339628010988235,
|
|
"num_tokens": 5312024.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.799851751327514,
|
|
"epoch": 0.22692078618225134,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998681079457507,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.14799990355968476,
|
|
"num_tokens": 5326848.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.785066413879394,
|
|
"epoch": 0.22751637879690292,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499866645072588,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.15455202460289003,
|
|
"num_tokens": 5341382.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.909482479095459,
|
|
"epoch": 0.2281119714115545,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998651741338242,
|
|
"loss": 5.7301,
|
|
"mean_token_accuracy": 0.1493678107857704,
|
|
"num_tokens": 5355477.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.780251502990723,
|
|
"epoch": 0.22870756402620607,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998636951295122,
|
|
"loss": 5.6028,
|
|
"mean_token_accuracy": 0.14676975458860397,
|
|
"num_tokens": 5369271.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.912346458435058,
|
|
"epoch": 0.22930315664085765,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998622080597052,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.14607542753219604,
|
|
"num_tokens": 5385016.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.7787182331085205,
|
|
"epoch": 0.22989874925550924,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998607129244563,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.1482226386666298,
|
|
"num_tokens": 5398838.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.8631453037261965,
|
|
"epoch": 0.23049434187016082,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998592097238192,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.15687993317842483,
|
|
"num_tokens": 5413297.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.908843994140625,
|
|
"epoch": 0.23108993448481238,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998576984578479,
|
|
"loss": 5.734,
|
|
"mean_token_accuracy": 0.1465668722987175,
|
|
"num_tokens": 5428013.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.842571640014649,
|
|
"epoch": 0.23168552709946397,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998561791265966,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.15798842012882233,
|
|
"num_tokens": 5442252.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.863111114501953,
|
|
"epoch": 0.23228111971411555,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998546517301196,
|
|
"loss": 5.6263,
|
|
"mean_token_accuracy": 0.1506134569644928,
|
|
"num_tokens": 5455919.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.824723243713379,
|
|
"epoch": 0.2328767123287671,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499853116268472,
|
|
"loss": 5.5972,
|
|
"mean_token_accuracy": 0.15163710564374924,
|
|
"num_tokens": 5469615.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.78403263092041,
|
|
"epoch": 0.2334723049434187,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998515727417086,
|
|
"loss": 5.5777,
|
|
"mean_token_accuracy": 0.1515430822968483,
|
|
"num_tokens": 5483955.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.882195043563843,
|
|
"epoch": 0.23406789755807028,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998500211498848,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.14697863012552262,
|
|
"num_tokens": 5498304.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.84442982673645,
|
|
"epoch": 0.23466349017272187,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998484614930566,
|
|
"loss": 5.5352,
|
|
"mean_token_accuracy": 0.15370398461818696,
|
|
"num_tokens": 5512674.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.875718069076538,
|
|
"epoch": 0.23525908278737342,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998468937712794,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.1451726473867893,
|
|
"num_tokens": 5527553.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.7593348026275635,
|
|
"epoch": 0.235854675402025,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998453179846098,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.16111078709363938,
|
|
"num_tokens": 5539818.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.771800756454468,
|
|
"epoch": 0.2364502680166766,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998437341331043,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.1472565457224846,
|
|
"num_tokens": 5554619.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.819460201263428,
|
|
"epoch": 0.23704586063132818,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998421422168195,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.15597962886095046,
|
|
"num_tokens": 5568539.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.782457685470581,
|
|
"epoch": 0.23764145324597974,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998405422358126,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.1590198189020157,
|
|
"num_tokens": 5581476.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.759257555007935,
|
|
"epoch": 0.23823704586063132,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998389341901411,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.15764866173267364,
|
|
"num_tokens": 5593774.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.869300508499146,
|
|
"epoch": 0.2388326384752829,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998373180798626,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.1508452832698822,
|
|
"num_tokens": 5606425.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.843395853042603,
|
|
"epoch": 0.2394282310899345,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998356939050351,
|
|
"loss": 5.6154,
|
|
"mean_token_accuracy": 0.1481335297226906,
|
|
"num_tokens": 5620472.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.713233566284179,
|
|
"epoch": 0.24002382370458605,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998340616657168,
|
|
"loss": 5.571,
|
|
"mean_token_accuracy": 0.1501559741795063,
|
|
"num_tokens": 5634744.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.865204477310181,
|
|
"epoch": 0.24061941631923764,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998324213619661,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.15888553559780122,
|
|
"num_tokens": 5648555.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.6331220149993895,
|
|
"epoch": 0.24121500893388922,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998307729938423,
|
|
"loss": 5.408,
|
|
"mean_token_accuracy": 0.16249011605978012,
|
|
"num_tokens": 5661780.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.835843849182129,
|
|
"epoch": 0.2418106015485408,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499829116561404,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.14600757211446763,
|
|
"num_tokens": 5674713.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.833654689788818,
|
|
"epoch": 0.24240619416319237,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998274520647109,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.15434815287590026,
|
|
"num_tokens": 5689152.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.848890066146851,
|
|
"epoch": 0.24300178677784395,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998257795038227,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.15140494406223298,
|
|
"num_tokens": 5704097.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.820264863967895,
|
|
"epoch": 0.24359737939249554,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998240988787992,
|
|
"loss": 5.6295,
|
|
"mean_token_accuracy": 0.15269548892974855,
|
|
"num_tokens": 5716579.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.80458984375,
|
|
"epoch": 0.24419297200714712,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998224101897009,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.15557244569063186,
|
|
"num_tokens": 5731114.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.8610326766967775,
|
|
"epoch": 0.24478856462179868,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998207134365883,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.14772013574838638,
|
|
"num_tokens": 5744843.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.812155294418335,
|
|
"epoch": 0.24538415723645027,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998190086195223,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.1433685004711151,
|
|
"num_tokens": 5759277.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.846189212799072,
|
|
"epoch": 0.24597974985110185,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998172957385638,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.14597747176885606,
|
|
"num_tokens": 5774754.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.854474449157715,
|
|
"epoch": 0.2465753424657534,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998155747937746,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.15177480429410933,
|
|
"num_tokens": 5788524.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.777294778823853,
|
|
"epoch": 0.247170935080405,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998138457852162,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.15807356238365172,
|
|
"num_tokens": 5800617.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.708472728729248,
|
|
"epoch": 0.24776652769505658,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998121087129507,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.16315317004919053,
|
|
"num_tokens": 5812433.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.805622100830078,
|
|
"epoch": 0.24836212030970817,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998103635770404,
|
|
"loss": 5.5297,
|
|
"mean_token_accuracy": 0.1630118742585182,
|
|
"num_tokens": 5825507.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.7305450439453125,
|
|
"epoch": 0.24895771292435973,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998086103775478,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.15464060008525848,
|
|
"num_tokens": 5841214.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.807388496398926,
|
|
"epoch": 0.2495533055390113,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998068491145359,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.15406294167041779,
|
|
"num_tokens": 5854788.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.716540718078614,
|
|
"epoch": 0.25014889815366287,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998050797880678,
|
|
"loss": 5.5064,
|
|
"mean_token_accuracy": 0.1597963571548462,
|
|
"num_tokens": 5870241.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.7547094345092775,
|
|
"epoch": 0.25074449076831445,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998033023982071,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.15717919915914536,
|
|
"num_tokens": 5883245.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.774991798400879,
|
|
"epoch": 0.25134008338296604,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998015169450174,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.15454900562763213,
|
|
"num_tokens": 5896103.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.76882643699646,
|
|
"epoch": 0.2519356759976176,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997997234285627,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.15321445912122728,
|
|
"num_tokens": 5909633.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.737154722213745,
|
|
"epoch": 0.2525312686122692,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997979218489076,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.15896177142858506,
|
|
"num_tokens": 5924211.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.750363540649414,
|
|
"epoch": 0.2531268612269208,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997961122061164,
|
|
"loss": 5.5113,
|
|
"mean_token_accuracy": 0.15694990754127502,
|
|
"num_tokens": 5937484.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.749356079101562,
|
|
"epoch": 0.2537224538415724,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997942945002543,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.1634616881608963,
|
|
"num_tokens": 5951224.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.765405607223511,
|
|
"epoch": 0.25431804645622397,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997924687313862,
|
|
"loss": 5.5152,
|
|
"mean_token_accuracy": 0.1565602719783783,
|
|
"num_tokens": 5964762.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.769849967956543,
|
|
"epoch": 0.2549136390708755,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004997906348995777,
|
|
"loss": 5.6265,
|
|
"mean_token_accuracy": 0.14467998296022416,
|
|
"num_tokens": 5978215.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.75273904800415,
|
|
"epoch": 0.2555092316855271,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997887930048947,
|
|
"loss": 5.5208,
|
|
"mean_token_accuracy": 0.1585681065917015,
|
|
"num_tokens": 5992951.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.83434648513794,
|
|
"epoch": 0.25610482430017867,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997869430474033,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.1532045155763626,
|
|
"num_tokens": 6005853.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.734776163101197,
|
|
"epoch": 0.25670041691483025,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997850850271696,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.15563962906599044,
|
|
"num_tokens": 6021502.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.760023355484009,
|
|
"epoch": 0.25729600952948184,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997832189442604,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.14632335305213928,
|
|
"num_tokens": 6038098.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.760441493988037,
|
|
"epoch": 0.2578916021441334,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997813447987426,
|
|
"loss": 5.6461,
|
|
"mean_token_accuracy": 0.15183507204055785,
|
|
"num_tokens": 6053957.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.808081865310669,
|
|
"epoch": 0.258487194758785,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997794625906834,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.151631598174572,
|
|
"num_tokens": 6069018.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.735133171081543,
|
|
"epoch": 0.2590827873734366,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997775723201504,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.15588141679763795,
|
|
"num_tokens": 6085202.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.74224271774292,
|
|
"epoch": 0.2596783799880881,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997756739872112,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.15963026583194734,
|
|
"num_tokens": 6098351.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.7959226131439205,
|
|
"epoch": 0.2602739726027397,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997737675919344,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.1592527598142624,
|
|
"num_tokens": 6111322.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.684843349456787,
|
|
"epoch": 0.2608695652173913,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997718531343877,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.1607907608151436,
|
|
"num_tokens": 6124438.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.807793426513672,
|
|
"epoch": 0.2614651578320429,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997699306146402,
|
|
"loss": 5.5325,
|
|
"mean_token_accuracy": 0.15616532564163207,
|
|
"num_tokens": 6139409.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.766112232208252,
|
|
"epoch": 0.26206075044669447,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997680000327607,
|
|
"loss": 5.5768,
|
|
"mean_token_accuracy": 0.15187618434429168,
|
|
"num_tokens": 6156678.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.81320858001709,
|
|
"epoch": 0.26265634306134605,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997660613888185,
|
|
"loss": 5.6322,
|
|
"mean_token_accuracy": 0.15070387125015258,
|
|
"num_tokens": 6171149.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.718372964859009,
|
|
"epoch": 0.26325193567599764,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997641146828831,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.16186487227678298,
|
|
"num_tokens": 6184179.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.725496625900268,
|
|
"epoch": 0.26384752829064917,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997621599150244,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.1599770426750183,
|
|
"num_tokens": 6197564.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.776312685012817,
|
|
"epoch": 0.26444312090530075,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997601970853124,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.15219161361455918,
|
|
"num_tokens": 6211018.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.686135387420654,
|
|
"epoch": 0.26503871351995234,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997582261938177,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.1594506174325943,
|
|
"num_tokens": 6223129.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.83850622177124,
|
|
"epoch": 0.2656343061346039,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997562472406107,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.15561751872301102,
|
|
"num_tokens": 6238236.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.684722995758056,
|
|
"epoch": 0.2662298987492555,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997542602257626,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.15514500215649604,
|
|
"num_tokens": 6251285.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.687035131454468,
|
|
"epoch": 0.2668254913639071,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997522651493447,
|
|
"loss": 5.487,
|
|
"mean_token_accuracy": 0.1623363599181175,
|
|
"num_tokens": 6266221.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.7185444831848145,
|
|
"epoch": 0.2674210839785587,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997502620114284,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.16145272701978683,
|
|
"num_tokens": 6278991.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.683774805068969,
|
|
"epoch": 0.26801667659321027,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997482508120856,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.16056784987449646,
|
|
"num_tokens": 6293095.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.654379177093506,
|
|
"epoch": 0.2686122692078618,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997462315513884,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.1590845227241516,
|
|
"num_tokens": 6306162.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.794221353530884,
|
|
"epoch": 0.2692078618225134,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997442042294095,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.15907941162586212,
|
|
"num_tokens": 6318636.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.645574855804443,
|
|
"epoch": 0.26980345443716497,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997421688462213,
|
|
"loss": 5.4966,
|
|
"mean_token_accuracy": 0.1574823960661888,
|
|
"num_tokens": 6332815.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.69795789718628,
|
|
"epoch": 0.27039904705181655,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997401254018969,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.16259774714708328,
|
|
"num_tokens": 6346887.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.656126308441162,
|
|
"epoch": 0.27099463966646814,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997380738965096,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.15526608750224113,
|
|
"num_tokens": 6360688.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.727518606185913,
|
|
"epoch": 0.2715902322811197,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499736014330133,
|
|
"loss": 5.4506,
|
|
"mean_token_accuracy": 0.16166550517082215,
|
|
"num_tokens": 6376560.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.77340669631958,
|
|
"epoch": 0.2721858248957713,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997339467028409,
|
|
"loss": 5.5886,
|
|
"mean_token_accuracy": 0.15267962366342544,
|
|
"num_tokens": 6390434.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.639683723449707,
|
|
"epoch": 0.2727814175104229,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997318710147076,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.1705484703183174,
|
|
"num_tokens": 6403585.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.757227802276612,
|
|
"epoch": 0.2733770101250744,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997297872658075,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.15438172817230225,
|
|
"num_tokens": 6414663.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.747932052612304,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997276954562152,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.16165455877780915,
|
|
"num_tokens": 6428655.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.691848421096802,
|
|
"epoch": 0.2745681953543776,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499725595586006,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.15874576568603516,
|
|
"num_tokens": 6443494.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.780502653121948,
|
|
"epoch": 0.2751637879690292,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499723487655255,
|
|
"loss": 5.5171,
|
|
"mean_token_accuracy": 0.1548047885298729,
|
|
"num_tokens": 6456078.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.680557155609131,
|
|
"epoch": 0.27575938058368077,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997213716640378,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.15409818589687346,
|
|
"num_tokens": 6469805.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.638623476028442,
|
|
"epoch": 0.27635497319833235,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997192476124306,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.16045788824558258,
|
|
"num_tokens": 6484209.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.720003318786621,
|
|
"epoch": 0.27695056581298394,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997171155005091,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.16009475886821747,
|
|
"num_tokens": 6498471.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.6884801387786865,
|
|
"epoch": 0.27754615842763547,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997149753283502,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.1510870337486267,
|
|
"num_tokens": 6513558.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.750243854522705,
|
|
"epoch": 0.27814175104228706,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997128270960304,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.15534038990736007,
|
|
"num_tokens": 6527538.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.681467199325562,
|
|
"epoch": 0.27873734365693864,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004997106708036268,
|
|
"loss": 5.4044,
|
|
"mean_token_accuracy": 0.16420497447252275,
|
|
"num_tokens": 6542188.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.737585878372192,
|
|
"epoch": 0.2793329362715902,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499708506451217,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.15870639830827712,
|
|
"num_tokens": 6557774.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.725549411773682,
|
|
"epoch": 0.2799285288862418,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997063340388783,
|
|
"loss": 5.5047,
|
|
"mean_token_accuracy": 0.1591295287013054,
|
|
"num_tokens": 6571868.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.66669020652771,
|
|
"epoch": 0.2805241215008934,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004997041535666888,
|
|
"loss": 5.5046,
|
|
"mean_token_accuracy": 0.16267810761928558,
|
|
"num_tokens": 6585534.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.744427156448364,
|
|
"epoch": 0.281119714115545,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997019650347266,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.15984203517436982,
|
|
"num_tokens": 6599855.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.659567928314209,
|
|
"epoch": 0.28171530673019657,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996997684430703,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.15913976728916168,
|
|
"num_tokens": 6615496.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.757647752761841,
|
|
"epoch": 0.2823108993448481,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996975637917986,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.15786412060260774,
|
|
"num_tokens": 6629993.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.606914806365967,
|
|
"epoch": 0.2829064919594997,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996953510809906,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.16335108876228333,
|
|
"num_tokens": 6644076.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.617101430892944,
|
|
"epoch": 0.28350208457415127,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996931303107258,
|
|
"loss": 5.4125,
|
|
"mean_token_accuracy": 0.1685549348592758,
|
|
"num_tokens": 6656924.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.610404968261719,
|
|
"epoch": 0.28409767718880286,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996909014810837,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.15931935012340545,
|
|
"num_tokens": 6670350.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.737998008728027,
|
|
"epoch": 0.28469326980345444,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996886645921442,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.16411933153867722,
|
|
"num_tokens": 6683174.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.722575998306274,
|
|
"epoch": 0.285288862418106,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996864196439877,
|
|
"loss": 5.5207,
|
|
"mean_token_accuracy": 0.1614995777606964,
|
|
"num_tokens": 6699648.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.692573165893554,
|
|
"epoch": 0.2858844550327576,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996841666366947,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.15927475988864898,
|
|
"num_tokens": 6712174.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.653959178924561,
|
|
"epoch": 0.2864800476474092,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996819055703458,
|
|
"loss": 5.4756,
|
|
"mean_token_accuracy": 0.1557614453136921,
|
|
"num_tokens": 6725376.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.5309672355651855,
|
|
"epoch": 0.2870756402620607,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996796364450224,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.17544015496969223,
|
|
"num_tokens": 6738177.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.676974773406982,
|
|
"epoch": 0.2876712328767123,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996773592608057,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.1570800721645355,
|
|
"num_tokens": 6751521.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.694453525543213,
|
|
"epoch": 0.2882668254913639,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996750740177775,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.15885785073041916,
|
|
"num_tokens": 6765901.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.619515609741211,
|
|
"epoch": 0.2888624181060155,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996727807160196,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.1706821084022522,
|
|
"num_tokens": 6778473.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.733613109588623,
|
|
"epoch": 0.28945801072066707,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004996704793556144,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.14786985665559768,
|
|
"num_tokens": 6792067.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.691383790969849,
|
|
"epoch": 0.29005360333531865,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996681699366443,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.16579745709896088,
|
|
"num_tokens": 6807534.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.590576267242431,
|
|
"epoch": 0.29064919594997024,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996658524591924,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.16009370386600494,
|
|
"num_tokens": 6821600.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.729387331008911,
|
|
"epoch": 0.2912447885646218,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996635269233415,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.16830949485301971,
|
|
"num_tokens": 6835044.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.6157289981842045,
|
|
"epoch": 0.29184038117927336,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996611933291752,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.15535762757062913,
|
|
"num_tokens": 6847745.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.692510461807251,
|
|
"epoch": 0.29243597379392494,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996588516767772,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.16661667376756667,
|
|
"num_tokens": 6861403.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.610689783096314,
|
|
"epoch": 0.2930315664085765,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996565019662315,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.16217046603560448,
|
|
"num_tokens": 6874418.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.793422508239746,
|
|
"epoch": 0.2936271590232281,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996541441976223,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.15529351979494094,
|
|
"num_tokens": 6890166.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.652487850189209,
|
|
"epoch": 0.2942227516378797,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996517783710342,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.15386532098054886,
|
|
"num_tokens": 6904569.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.693504858016968,
|
|
"epoch": 0.2948183442525313,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996494044865521,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.16156764328479767,
|
|
"num_tokens": 6918562.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.711939144134521,
|
|
"epoch": 0.29541393686718287,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004996470225442611,
|
|
"loss": 5.4817,
|
|
"mean_token_accuracy": 0.15454793199896813,
|
|
"num_tokens": 6934751.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.656792163848877,
|
|
"epoch": 0.2960095294818344,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996446325442466,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.16370049118995667,
|
|
"num_tokens": 6947669.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.824085998535156,
|
|
"epoch": 0.296605122096486,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004996422344865945,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.15432622879743577,
|
|
"num_tokens": 6959993.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.608792734146118,
|
|
"epoch": 0.29720071471113757,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996398283713907,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.16161959767341613,
|
|
"num_tokens": 6974637.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.6103503704071045,
|
|
"epoch": 0.29779630732578916,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996374141987215,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.17203344255685807,
|
|
"num_tokens": 6989182.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.601393842697144,
|
|
"epoch": 0.29839189994044074,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996349919686733,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.16592477560043334,
|
|
"num_tokens": 7003681.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.620221138000488,
|
|
"epoch": 0.2989874925550923,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996325616813334,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.16927724331617355,
|
|
"num_tokens": 7017919.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.668755769729614,
|
|
"epoch": 0.2995830851697439,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996301233367886,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.15672117918729783,
|
|
"num_tokens": 7033405.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.583414888381958,
|
|
"epoch": 0.3001786777843955,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004996276769351265,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.16647372990846634,
|
|
"num_tokens": 7046938.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.68247618675232,
|
|
"epoch": 0.30077427039904703,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996252224764349,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.15755810290575029,
|
|
"num_tokens": 7059708.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.599438667297363,
|
|
"epoch": 0.3013698630136986,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004996227599608018,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.16436849236488343,
|
|
"num_tokens": 7074554.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.615538120269775,
|
|
"epoch": 0.3019654556283502,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004996202893883156,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.1633124217391014,
|
|
"num_tokens": 7089654.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.664164066314697,
|
|
"epoch": 0.3025610482430018,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996178107590648,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.15866321474313735,
|
|
"num_tokens": 7103137.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.571569728851318,
|
|
"epoch": 0.30315664085765337,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996153240731381,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.170277501642704,
|
|
"num_tokens": 7114857.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.685733318328857,
|
|
"epoch": 0.30375223347230496,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996128293306251,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.15823855698108674,
|
|
"num_tokens": 7128243.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.60353684425354,
|
|
"epoch": 0.30434782608695654,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996103265316152,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.16011096984148027,
|
|
"num_tokens": 7142505.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.574767923355102,
|
|
"epoch": 0.3049434187016081,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996078156761979,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.16808079183101654,
|
|
"num_tokens": 7157877.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.66445107460022,
|
|
"epoch": 0.30553901131625966,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996052967644636,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.15935673713684081,
|
|
"num_tokens": 7170819.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.624619102478027,
|
|
"epoch": 0.30613460393091124,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996027697965024,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.16764672398567199,
|
|
"num_tokens": 7183013.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.624931812286377,
|
|
"epoch": 0.3067301965455628,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499600234772405,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.1584194555878639,
|
|
"num_tokens": 7196530.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.803409290313721,
|
|
"epoch": 0.3073257891602144,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995976916922624,
|
|
"loss": 5.5174,
|
|
"mean_token_accuracy": 0.15356251150369643,
|
|
"num_tokens": 7210657.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.562406587600708,
|
|
"epoch": 0.307921381774866,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004995951405561658,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.1599239155650139,
|
|
"num_tokens": 7224450.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.611307907104492,
|
|
"epoch": 0.3085169743895176,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995925813642068,
|
|
"loss": 5.4337,
|
|
"mean_token_accuracy": 0.16787374764680862,
|
|
"num_tokens": 7238767.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.665083408355713,
|
|
"epoch": 0.30911256700416917,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995900141164768,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.16733885556459427,
|
|
"num_tokens": 7253326.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.554730796813965,
|
|
"epoch": 0.3097081596188207,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004995874388130683,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.16792593598365785,
|
|
"num_tokens": 7268256.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.6270942211151125,
|
|
"epoch": 0.3103037522334723,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995848554540734,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.16549789309501647,
|
|
"num_tokens": 7281561.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.620613431930542,
|
|
"epoch": 0.31089934484812387,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499582264039585,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.16193209886550902,
|
|
"num_tokens": 7294302.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.61934986114502,
|
|
"epoch": 0.31149493746277546,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499579664569696,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.16470654010772706,
|
|
"num_tokens": 7309257.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.594733762741089,
|
|
"epoch": 0.31209053007742704,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995770570444996,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.16754524707794188,
|
|
"num_tokens": 7322797.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.58003568649292,
|
|
"epoch": 0.3126861226920786,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004995744414640892,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.1701003834605217,
|
|
"num_tokens": 7336913.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.659595012664795,
|
|
"epoch": 0.3132817153067302,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995718178285587,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.166141539812088,
|
|
"num_tokens": 7350267.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.628715658187867,
|
|
"epoch": 0.3138773079213818,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995691861380022,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.17088788449764253,
|
|
"num_tokens": 7365592.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.612440729141236,
|
|
"epoch": 0.31447290053603333,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995665463925142,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.17181715220212937,
|
|
"num_tokens": 7380045.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.6453581809997555,
|
|
"epoch": 0.3150684931506849,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995638985921893,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.16612079590559006,
|
|
"num_tokens": 7392487.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.66465916633606,
|
|
"epoch": 0.3156640857653365,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995612427371224,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.15476237386465072,
|
|
"num_tokens": 7405578.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.6685933589935305,
|
|
"epoch": 0.3162596783799881,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499558578827409,
|
|
"loss": 5.3893,
|
|
"mean_token_accuracy": 0.16497644335031508,
|
|
"num_tokens": 7418940.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.597129678726196,
|
|
"epoch": 0.31685527099463967,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995559068631444,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.16862670332193375,
|
|
"num_tokens": 7432688.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.663164901733398,
|
|
"epoch": 0.31745086360929126,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995532268444244,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.15491555035114288,
|
|
"num_tokens": 7446238.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.713318824768066,
|
|
"epoch": 0.31804645622394284,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995505387713453,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.1582308754324913,
|
|
"num_tokens": 7460781.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.6887444972991945,
|
|
"epoch": 0.3186420488385944,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995478426440037,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.1570764347910881,
|
|
"num_tokens": 7475041.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.651510286331177,
|
|
"epoch": 0.31923764145324596,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995451384624959,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.15209561437368393,
|
|
"num_tokens": 7491027.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.737888288497925,
|
|
"epoch": 0.31983323406789754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995424262269191,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.15689847469329835,
|
|
"num_tokens": 7503070.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.545493078231812,
|
|
"epoch": 0.32042882668254913,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995397059373704,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.166213496029377,
|
|
"num_tokens": 7515553.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.516410255432129,
|
|
"epoch": 0.3210244192972007,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995369775939478,
|
|
"loss": 5.334,
|
|
"mean_token_accuracy": 0.16750890761613846,
|
|
"num_tokens": 7529603.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.685449600219727,
|
|
"epoch": 0.3216200119118523,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995342411967487,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.16326793283224106,
|
|
"num_tokens": 7543320.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.610023260116577,
|
|
"epoch": 0.3222156045265039,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995314967458715,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.15878843814134597,
|
|
"num_tokens": 7556413.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.662295913696289,
|
|
"epoch": 0.32281119714115547,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995287442414145,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.1669587939977646,
|
|
"num_tokens": 7570427.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.6275365352630615,
|
|
"epoch": 0.323406789755807,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995259836834767,
|
|
"loss": 5.4886,
|
|
"mean_token_accuracy": 0.16144248992204666,
|
|
"num_tokens": 7585143.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.722830390930175,
|
|
"epoch": 0.3240023823704586,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995232150721568,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.16559174209833144,
|
|
"num_tokens": 7597429.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.454201507568359,
|
|
"epoch": 0.32459797498511017,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995204384075542,
|
|
"loss": 5.2701,
|
|
"mean_token_accuracy": 0.17763542830944062,
|
|
"num_tokens": 7610203.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.625760793685913,
|
|
"epoch": 0.32519356759976176,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995176536897685,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.16095541268587113,
|
|
"num_tokens": 7625343.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.627835273742676,
|
|
"epoch": 0.32578916021441334,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995148609188997,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.16819330155849457,
|
|
"num_tokens": 7637850.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.541169357299805,
|
|
"epoch": 0.32638475282906493,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995120600950479,
|
|
"loss": 5.3556,
|
|
"mean_token_accuracy": 0.16982422769069672,
|
|
"num_tokens": 7651877.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.702938222885132,
|
|
"epoch": 0.3269803454437165,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995092512183134,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.15641891360282897,
|
|
"num_tokens": 7666457.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.534969091415405,
|
|
"epoch": 0.3275759380583681,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004995064342887972,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.16628559976816176,
|
|
"num_tokens": 7678979.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.57575101852417,
|
|
"epoch": 0.32817153067301963,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995036093066001,
|
|
"loss": 5.33,
|
|
"mean_token_accuracy": 0.16701254695653917,
|
|
"num_tokens": 7692357.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.6921913623809814,
|
|
"epoch": 0.3287671232876712,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995007762718237,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.16096125543117523,
|
|
"num_tokens": 7707537.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.5510852336883545,
|
|
"epoch": 0.3293627159023228,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994979351845693,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.17132228910923003,
|
|
"num_tokens": 7719737.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.566894817352295,
|
|
"epoch": 0.3299583085169744,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994950860449392,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.1679743781685829,
|
|
"num_tokens": 7734612.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.683651638031006,
|
|
"epoch": 0.33055390113162597,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004994922288530353,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.1574023813009262,
|
|
"num_tokens": 7749109.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.529888391494751,
|
|
"epoch": 0.33114949374627756,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994893636089601,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.1658666491508484,
|
|
"num_tokens": 7761972.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.602976703643799,
|
|
"epoch": 0.33174508636092914,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994864903128164,
|
|
"loss": 5.4233,
|
|
"mean_token_accuracy": 0.15958732664585112,
|
|
"num_tokens": 7777769.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.623035573959351,
|
|
"epoch": 0.33234067897558073,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994836089647073,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.16498465538024903,
|
|
"num_tokens": 7792576.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.501369333267212,
|
|
"epoch": 0.33293627159023226,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004994807195647362,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.16465005427598953,
|
|
"num_tokens": 7805997.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.538904047012329,
|
|
"epoch": 0.33353186420488384,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994778221130066,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.16367123275995255,
|
|
"num_tokens": 7819548.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.5802665710449215,
|
|
"epoch": 0.33412745681953543,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994749166096226,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.16447833478450774,
|
|
"num_tokens": 7832786.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.607454586029053,
|
|
"epoch": 0.334723049434187,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994720030546882,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.1597932130098343,
|
|
"num_tokens": 7847524.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.5271384716033936,
|
|
"epoch": 0.3353186420488386,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994690814483081,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.171538744866848,
|
|
"num_tokens": 7861783.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.555627012252808,
|
|
"epoch": 0.3359142346634902,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994661517905869,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.1623458221554756,
|
|
"num_tokens": 7875671.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.640743923187256,
|
|
"epoch": 0.33650982727814177,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994632140816299,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.16768883168697357,
|
|
"num_tokens": 7890624.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.560923671722412,
|
|
"epoch": 0.33710541989279336,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994602683215424,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.16181447505950927,
|
|
"num_tokens": 7904296.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.5300528049469,
|
|
"epoch": 0.3377010125074449,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049945731451043,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.16830001771450043,
|
|
"num_tokens": 7918588.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.510066986083984,
|
|
"epoch": 0.33829660512209647,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994543526483985,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.17027873545885086,
|
|
"num_tokens": 7933087.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.589756488800049,
|
|
"epoch": 0.33889219773674806,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004994513827355546,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.16768360435962676,
|
|
"num_tokens": 7945477.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.614036130905151,
|
|
"epoch": 0.33948779035139964,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994484047720043,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.15274825766682626,
|
|
"num_tokens": 7961488.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.625618028640747,
|
|
"epoch": 0.34008338296605123,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994454187578547,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.17579563111066818,
|
|
"num_tokens": 7974533.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.5334639072418215,
|
|
"epoch": 0.3406789755807028,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994424246932129,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.16355580389499663,
|
|
"num_tokens": 7988481.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.5664245128631595,
|
|
"epoch": 0.3412745681953544,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994394225781863,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.1667862430214882,
|
|
"num_tokens": 8003589.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.530544567108154,
|
|
"epoch": 0.34187016081000593,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994364124128825,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.16983226537704468,
|
|
"num_tokens": 8017560.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.5746856212615965,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004994333941974094,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.16409531384706497,
|
|
"num_tokens": 8032339.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.560096645355225,
|
|
"epoch": 0.3430613460393091,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004994303679318754,
|
|
"loss": 5.4204,
|
|
"mean_token_accuracy": 0.16137190610170365,
|
|
"num_tokens": 8047634.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.619360399246216,
|
|
"epoch": 0.3436569386539607,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004994273336163891,
|
|
"loss": 5.3841,
|
|
"mean_token_accuracy": 0.16237827986478806,
|
|
"num_tokens": 8061267.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.500016403198242,
|
|
"epoch": 0.34425253126861227,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994242912510591,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.1678288221359253,
|
|
"num_tokens": 8076225.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.625662899017334,
|
|
"epoch": 0.34484812388326386,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994212408359948,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.1694784641265869,
|
|
"num_tokens": 8089997.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.5583420753479,
|
|
"epoch": 0.34544371649791544,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004994181823713054,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.17125595957040787,
|
|
"num_tokens": 8102739.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.584038639068604,
|
|
"epoch": 0.34603930911256703,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994151158571006,
|
|
"loss": 5.4956,
|
|
"mean_token_accuracy": 0.1619663342833519,
|
|
"num_tokens": 8115435.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.578685283660889,
|
|
"epoch": 0.34663490172721856,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994120412934906,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.16590591147542,
|
|
"num_tokens": 8129833.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.586967706680298,
|
|
"epoch": 0.34723049434187014,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.1695588394999504,
|
|
"num_tokens": 8144316.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.548436164855957,
|
|
"epoch": 0.34782608695652173,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994058680184959,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.16426207274198532,
|
|
"num_tokens": 8158927.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.628516483306885,
|
|
"epoch": 0.3484216795711733,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994027693073327,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.16862507164478302,
|
|
"num_tokens": 8172297.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.60341796875,
|
|
"epoch": 0.3490172721858249,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993996625472071,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.16386872231960298,
|
|
"num_tokens": 8184985.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.642530727386474,
|
|
"epoch": 0.3496128648004765,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993965477382304,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.16768093705177306,
|
|
"num_tokens": 8198936.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.512491226196289,
|
|
"epoch": 0.35020845741512807,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993934248805143,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.16670797020196915,
|
|
"num_tokens": 8213538.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.6335100650787355,
|
|
"epoch": 0.35080405002977966,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004993902939741709,
|
|
"loss": 5.4455,
|
|
"mean_token_accuracy": 0.16404985934495925,
|
|
"num_tokens": 8226794.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.516642761230469,
|
|
"epoch": 0.3513996426444312,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993871550193126,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.16991336792707443,
|
|
"num_tokens": 8241671.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.532778930664063,
|
|
"epoch": 0.3519952352590828,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993840080160519,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.1677089139819145,
|
|
"num_tokens": 8255079.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.602738666534424,
|
|
"epoch": 0.35259082787373436,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993808529645016,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.1690721958875656,
|
|
"num_tokens": 8267958.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.529457139968872,
|
|
"epoch": 0.35318642048838594,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993776898647749,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.15847480446100234,
|
|
"num_tokens": 8281082.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.572062015533447,
|
|
"epoch": 0.35378201310303753,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993745187169852,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.16842308640480042,
|
|
"num_tokens": 8292675.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.474595403671264,
|
|
"epoch": 0.3543776057176891,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004993713395212464,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.17008770853281022,
|
|
"num_tokens": 8304481.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.551436233520508,
|
|
"epoch": 0.3549731983323407,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004993681522776725,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.16411831080913544,
|
|
"num_tokens": 8318529.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.614675807952881,
|
|
"epoch": 0.35556879094699223,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004993649569863778,
|
|
"loss": 5.3942,
|
|
"mean_token_accuracy": 0.16421158984303474,
|
|
"num_tokens": 8333181.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.498898363113403,
|
|
"epoch": 0.3561643835616438,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993617536474768,
|
|
"loss": 5.2767,
|
|
"mean_token_accuracy": 0.1807217612862587,
|
|
"num_tokens": 8346036.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.49157862663269,
|
|
"epoch": 0.3567599761762954,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004993585422610845,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.17009854316711426,
|
|
"num_tokens": 8361037.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.599612188339234,
|
|
"epoch": 0.357355568790947,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004993553228273161,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.16624198853969574,
|
|
"num_tokens": 8374802.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.357355568790947,
|
|
"eval_entropy": 5.324107903597123,
|
|
"eval_loss": 5.312887191772461,
|
|
"eval_mean_token_accuracy": 0.17884539870726276,
|
|
"eval_num_tokens": 8374802.0,
|
|
"eval_runtime": 19.0482,
|
|
"eval_samples_per_second": 1339.395,
|
|
"eval_steps_per_second": 167.47,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 83940,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 2222324889845760.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|