7107a07762
Model: fpadovani/urd-arab-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 Source: Original Platform
42112 lines
1.1 MiB
42112 lines
1.1 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.501488981536629,
|
|
"eval_steps": 3000,
|
|
"global_step": 21000,
|
|
"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
|
|
},
|
|
{
|
|
"entropy": 5.504523706436157,
|
|
"epoch": 0.3579511614055986,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499352095346287,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.1773324653506279,
|
|
"num_tokens": 8389127.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.653847742080688,
|
|
"epoch": 0.35854675402025016,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993488598181131,
|
|
"loss": 5.4527,
|
|
"mean_token_accuracy": 0.15407529845833778,
|
|
"num_tokens": 8403358.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.562090158462524,
|
|
"epoch": 0.35914234663490174,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004993456162429103,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.16840836703777312,
|
|
"num_tokens": 8418693.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.557594060897827,
|
|
"epoch": 0.35973793924955333,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993423646207951,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.17382775396108627,
|
|
"num_tokens": 8429968.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.530175733566284,
|
|
"epoch": 0.36033353186420486,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499339104951884,
|
|
"loss": 5.3431,
|
|
"mean_token_accuracy": 0.1667601391673088,
|
|
"num_tokens": 8443700.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.585377502441406,
|
|
"epoch": 0.36092912447885644,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004993358372362939,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.16528983861207963,
|
|
"num_tokens": 8457919.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.588597583770752,
|
|
"epoch": 0.36152471709350803,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004993325614741421,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.16814952492713928,
|
|
"num_tokens": 8472787.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.546421098709106,
|
|
"epoch": 0.3621203097081596,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004993292776655461,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.17282703518867493,
|
|
"num_tokens": 8484235.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.452932596206665,
|
|
"epoch": 0.3627159023228112,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993259858106236,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.17634237557649612,
|
|
"num_tokens": 8496971.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.534565401077271,
|
|
"epoch": 0.3633114949374628,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993226859094927,
|
|
"loss": 5.334,
|
|
"mean_token_accuracy": 0.17172078788280487,
|
|
"num_tokens": 8510531.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.555890417098999,
|
|
"epoch": 0.36390708755211437,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004993193779622719,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.16886600553989412,
|
|
"num_tokens": 8522492.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.592002248764038,
|
|
"epoch": 0.36450268016676596,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004993160619690796,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.16994454115629196,
|
|
"num_tokens": 8537119.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.45992522239685,
|
|
"epoch": 0.3650982727814175,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993127379300349,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.17288872301578523,
|
|
"num_tokens": 8549899.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.5834204196929935,
|
|
"epoch": 0.3656938653960691,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499309405845257,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.15655851662158965,
|
|
"num_tokens": 8563604.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.653063535690308,
|
|
"epoch": 0.36628945801072066,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993060657148654,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.16795894205570222,
|
|
"num_tokens": 8577948.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.528710556030274,
|
|
"epoch": 0.36688505062537224,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00049930271753898,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.17339263260364532,
|
|
"num_tokens": 8591750.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.58987398147583,
|
|
"epoch": 0.36748064324002383,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992993613177208,
|
|
"loss": 5.3273,
|
|
"mean_token_accuracy": 0.1703854039311409,
|
|
"num_tokens": 8604091.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.448946285247803,
|
|
"epoch": 0.3680762358546754,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004992959970512082,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.17441565990448,
|
|
"num_tokens": 8617314.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.421458768844604,
|
|
"epoch": 0.368671828469327,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992926247395627,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.17659326493740082,
|
|
"num_tokens": 8630050.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.441833782196045,
|
|
"epoch": 0.36926742108397853,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004992892443829057,
|
|
"loss": 5.3034,
|
|
"mean_token_accuracy": 0.17432785481214524,
|
|
"num_tokens": 8643462.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.470647573471069,
|
|
"epoch": 0.3698630136986301,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499285855981358,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.17231116443872452,
|
|
"num_tokens": 8657207.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.572486543655396,
|
|
"epoch": 0.3704586063132817,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992824595350414,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.17450466454029084,
|
|
"num_tokens": 8671129.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.579818344116211,
|
|
"epoch": 0.3710541989279333,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992790550440775,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.175332710146904,
|
|
"num_tokens": 8684308.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.437342262268066,
|
|
"epoch": 0.3716497915425849,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992756425085887,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.17211799919605256,
|
|
"num_tokens": 8697651.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.540539789199829,
|
|
"epoch": 0.37224538415723646,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004992722219286972,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.1629774361848831,
|
|
"num_tokens": 8714559.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.622084093093872,
|
|
"epoch": 0.37284097677188804,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992687933045258,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.17317133396863937,
|
|
"num_tokens": 8729999.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.4910510063171385,
|
|
"epoch": 0.37343656938653963,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992653566361974,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.17395152598619462,
|
|
"num_tokens": 8742503.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.519348812103272,
|
|
"epoch": 0.37403216200119116,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992619119238351,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.16655327677726744,
|
|
"num_tokens": 8755034.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.524391126632691,
|
|
"epoch": 0.37462775461584275,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000499258459167563,
|
|
"loss": 5.3478,
|
|
"mean_token_accuracy": 0.17010837346315383,
|
|
"num_tokens": 8770410.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.533599901199341,
|
|
"epoch": 0.37522334723049433,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992549983675043,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.1769703060388565,
|
|
"num_tokens": 8784020.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.488097429275513,
|
|
"epoch": 0.3758189398451459,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992515295237835,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.17155248895287514,
|
|
"num_tokens": 8797763.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.509059953689575,
|
|
"epoch": 0.3764145324597975,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499248052636525,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.1777146726846695,
|
|
"num_tokens": 8810306.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.44479193687439,
|
|
"epoch": 0.3770101250744491,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992445677058534,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.17329318970441818,
|
|
"num_tokens": 8822345.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.545683765411377,
|
|
"epoch": 0.3776057176891007,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004992410747318938,
|
|
"loss": 5.3528,
|
|
"mean_token_accuracy": 0.16775246411561967,
|
|
"num_tokens": 8836024.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.507455730438233,
|
|
"epoch": 0.37820131030375226,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992375737147715,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.169485142827034,
|
|
"num_tokens": 8849994.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.509756660461425,
|
|
"epoch": 0.3787969029184038,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992340646546118,
|
|
"loss": 5.2767,
|
|
"mean_token_accuracy": 0.17721723914146423,
|
|
"num_tokens": 8863867.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.451604175567627,
|
|
"epoch": 0.3793924955330554,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499230547551541,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.17159224599599837,
|
|
"num_tokens": 8878077.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.511496353149414,
|
|
"epoch": 0.37998808814770696,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004992270224056849,
|
|
"loss": 5.3221,
|
|
"mean_token_accuracy": 0.16856638044118882,
|
|
"num_tokens": 8892729.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.493692827224732,
|
|
"epoch": 0.38058368076235854,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992234892171702,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.1764099881052971,
|
|
"num_tokens": 8906242.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.499857997894287,
|
|
"epoch": 0.38117927337701013,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004992199479861235,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.16584230959415436,
|
|
"num_tokens": 8919814.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.49078950881958,
|
|
"epoch": 0.3817748659916617,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004992163987126717,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.17567045837640763,
|
|
"num_tokens": 8934345.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.469553852081299,
|
|
"epoch": 0.3823704586063133,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992128413969423,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.17588595300912857,
|
|
"num_tokens": 8947825.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.55420069694519,
|
|
"epoch": 0.3829660512209649,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992092760390628,
|
|
"loss": 5.4284,
|
|
"mean_token_accuracy": 0.1664010375738144,
|
|
"num_tokens": 8962270.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.523141145706177,
|
|
"epoch": 0.3835616438356164,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992057026391612,
|
|
"loss": 5.2917,
|
|
"mean_token_accuracy": 0.17372822165489196,
|
|
"num_tokens": 8974453.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.541723537445068,
|
|
"epoch": 0.384157236450268,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992021211973655,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.1666663333773613,
|
|
"num_tokens": 8991689.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.558318996429444,
|
|
"epoch": 0.3847528290649196,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991985317138043,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.1748742088675499,
|
|
"num_tokens": 9005783.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.477128410339356,
|
|
"epoch": 0.3853484216795712,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004991949341886063,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.16816703379154205,
|
|
"num_tokens": 9019733.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.463809633255005,
|
|
"epoch": 0.38594401429422276,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004991913286219004,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.17063444554805757,
|
|
"num_tokens": 9035131.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.540193033218384,
|
|
"epoch": 0.38653960690887434,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991877150138162,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.17725360840559007,
|
|
"num_tokens": 9047954.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.450523900985718,
|
|
"epoch": 0.38713519952352593,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991840933644831,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.17834202349185943,
|
|
"num_tokens": 9059945.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.516718769073487,
|
|
"epoch": 0.38773079213817746,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499180463674031,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.1747880756855011,
|
|
"num_tokens": 9074128.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.48166036605835,
|
|
"epoch": 0.38832638475282905,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004991768259425903,
|
|
"loss": 5.4114,
|
|
"mean_token_accuracy": 0.17040577977895738,
|
|
"num_tokens": 9086760.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.571305131912231,
|
|
"epoch": 0.38892197736748063,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004991731801702914,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.16743518710136412,
|
|
"num_tokens": 9100632.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.533093738555908,
|
|
"epoch": 0.3895175699821322,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991695263572648,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.16504896879196168,
|
|
"num_tokens": 9115092.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.420135593414306,
|
|
"epoch": 0.3901131625967838,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991658645036419,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.18088019043207168,
|
|
"num_tokens": 9127473.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.51769323348999,
|
|
"epoch": 0.3907087552114354,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991621946095539,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.17103094160556792,
|
|
"num_tokens": 9141028.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.502821779251098,
|
|
"epoch": 0.391304347826087,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991585166751325,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.17616523057222366,
|
|
"num_tokens": 9154526.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.53980016708374,
|
|
"epoch": 0.39189994044073856,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991548307005094,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.1677374616265297,
|
|
"num_tokens": 9167220.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.526500844955445,
|
|
"epoch": 0.3924955330553901,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004991511366858172,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.17052534446120263,
|
|
"num_tokens": 9181648.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.499467897415161,
|
|
"epoch": 0.3930911256700417,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991474346311879,
|
|
"loss": 5.186,
|
|
"mean_token_accuracy": 0.18327035903930664,
|
|
"num_tokens": 9194714.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.397356224060059,
|
|
"epoch": 0.39368671828469326,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991437245367547,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.16969424039125441,
|
|
"num_tokens": 9211467.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.678962278366089,
|
|
"epoch": 0.39428231089934485,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991400064026506,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.16078380048274993,
|
|
"num_tokens": 9226409.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.491414976119995,
|
|
"epoch": 0.39487790351399643,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991362802290089,
|
|
"loss": 5.2566,
|
|
"mean_token_accuracy": 0.17088149338960648,
|
|
"num_tokens": 9240476.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.447879981994629,
|
|
"epoch": 0.395473496128648,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991325460159631,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.17435861080884935,
|
|
"num_tokens": 9254020.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.455914306640625,
|
|
"epoch": 0.3960690887432996,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004991288037636474,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.17692663073539733,
|
|
"num_tokens": 9269150.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.550675678253174,
|
|
"epoch": 0.3966646813579512,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991250534721959,
|
|
"loss": 5.4621,
|
|
"mean_token_accuracy": 0.15861991345882415,
|
|
"num_tokens": 9285184.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.508290195465088,
|
|
"epoch": 0.3972602739726027,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004991212951417431,
|
|
"loss": 5.2732,
|
|
"mean_token_accuracy": 0.18077291846275328,
|
|
"num_tokens": 9298622.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.567737007141114,
|
|
"epoch": 0.3978558665872543,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004991175287724239,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.16661519706249237,
|
|
"num_tokens": 9314653.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.497212028503418,
|
|
"epoch": 0.3984514592019059,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991137543643733,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.17750592529773712,
|
|
"num_tokens": 9328428.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.534097290039062,
|
|
"epoch": 0.3990470518165575,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004991099719177268,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.16878652125597,
|
|
"num_tokens": 9341250.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.508481788635254,
|
|
"epoch": 0.39964264443120906,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004991061814326198,
|
|
"loss": 5.2543,
|
|
"mean_token_accuracy": 0.17515599876642227,
|
|
"num_tokens": 9355706.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.629912090301514,
|
|
"epoch": 0.40023823704586065,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991023829091887,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.16176478564739227,
|
|
"num_tokens": 9368562.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.532537794113159,
|
|
"epoch": 0.40083382966051223,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004990985763475694,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.16469235718250275,
|
|
"num_tokens": 9383484.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.380288028717041,
|
|
"epoch": 0.40142942227516376,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004990947617478984,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.18112877756357193,
|
|
"num_tokens": 9397364.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.400164794921875,
|
|
"epoch": 0.40202501488981535,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004990909391103127,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.17644066065549852,
|
|
"num_tokens": 9411738.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.465491104125976,
|
|
"epoch": 0.40262060750446693,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004990871084349494,
|
|
"loss": 5.2154,
|
|
"mean_token_accuracy": 0.17861545234918594,
|
|
"num_tokens": 9426660.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.516983270645142,
|
|
"epoch": 0.4032162001191185,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004990832697219459,
|
|
"loss": 5.2746,
|
|
"mean_token_accuracy": 0.16800158768892287,
|
|
"num_tokens": 9440878.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.496309852600097,
|
|
"epoch": 0.4038117927337701,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990794229714398,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.1711987301707268,
|
|
"num_tokens": 9455174.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.430727624893189,
|
|
"epoch": 0.4044073853484217,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990755681835693,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.17757174372673035,
|
|
"num_tokens": 9467936.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.437943696975708,
|
|
"epoch": 0.4050029779630733,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004990717053584723,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.17058937549591063,
|
|
"num_tokens": 9482529.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.489191246032715,
|
|
"epoch": 0.40559857057772486,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004990678344962876,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.17237125784158708,
|
|
"num_tokens": 9497141.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.5955078125,
|
|
"epoch": 0.4061941631923764,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990639555971539,
|
|
"loss": 5.354,
|
|
"mean_token_accuracy": 0.16431059688329697,
|
|
"num_tokens": 9509878.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.384750509262085,
|
|
"epoch": 0.406789755807028,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004990600686612106,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.17743294984102248,
|
|
"num_tokens": 9522720.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.4489542007446286,
|
|
"epoch": 0.40738534842167956,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990561736885968,
|
|
"loss": 5.3043,
|
|
"mean_token_accuracy": 0.1772517666220665,
|
|
"num_tokens": 9536418.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.497792053222656,
|
|
"epoch": 0.40798094103633115,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990522706794523,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.18019660860300063,
|
|
"num_tokens": 9552336.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.494215202331543,
|
|
"epoch": 0.40857653365098273,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990483596339174,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.17481288462877273,
|
|
"num_tokens": 9565676.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.35205717086792,
|
|
"epoch": 0.4091721262656343,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004990444405521318,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.18299626260995866,
|
|
"num_tokens": 9579361.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.413522338867187,
|
|
"epoch": 0.4097677188802859,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990405134342366,
|
|
"loss": 5.2207,
|
|
"mean_token_accuracy": 0.176656311750412,
|
|
"num_tokens": 9591779.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.465343475341797,
|
|
"epoch": 0.4103633114949375,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990365782803724,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.1722876861691475,
|
|
"num_tokens": 9608353.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.436408662796021,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990326350906803,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.17406587451696395,
|
|
"num_tokens": 9623236.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.43439564704895,
|
|
"epoch": 0.4115544967242406,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990286838653019,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.17022293210029601,
|
|
"num_tokens": 9635746.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.395553970336914,
|
|
"epoch": 0.4121500893388922,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004990247246043789,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.17702321857213973,
|
|
"num_tokens": 9650458.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.469908809661865,
|
|
"epoch": 0.4127456819535438,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004990207573080533,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.17951687276363373,
|
|
"num_tokens": 9665486.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.51123743057251,
|
|
"epoch": 0.41334127456819536,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004990167819764672,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.16876161694526673,
|
|
"num_tokens": 9679977.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.511188745498657,
|
|
"epoch": 0.41393686718284695,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004990127986097636,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.1703689679503441,
|
|
"num_tokens": 9695092.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.347048997879028,
|
|
"epoch": 0.41453245979749853,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499008807208085,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.18218721598386764,
|
|
"num_tokens": 9707836.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.531648635864258,
|
|
"epoch": 0.4151280524121501,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990048077715746,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.1670540988445282,
|
|
"num_tokens": 9721936.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.438021564483643,
|
|
"epoch": 0.41572364502680165,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990008003003762,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.1823842465877533,
|
|
"num_tokens": 9734876.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.445828008651733,
|
|
"epoch": 0.41631923764145323,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004989967847946331,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.1645902529358864,
|
|
"num_tokens": 9748870.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.6073973178863525,
|
|
"epoch": 0.4169148302561048,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004989927612544895,
|
|
"loss": 5.3268,
|
|
"mean_token_accuracy": 0.1696002960205078,
|
|
"num_tokens": 9763605.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.499495029449463,
|
|
"epoch": 0.4175104228707564,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989887296800899,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.17259501814842224,
|
|
"num_tokens": 9779312.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.428809118270874,
|
|
"epoch": 0.418106015485408,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989846900715786,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.16444026827812194,
|
|
"num_tokens": 9791770.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.478866720199585,
|
|
"epoch": 0.4187016081000596,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989806424291008,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.17432912141084672,
|
|
"num_tokens": 9807341.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.47484130859375,
|
|
"epoch": 0.41929720071471116,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989765867528014,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.17365871816873552,
|
|
"num_tokens": 9821829.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.330928754806519,
|
|
"epoch": 0.4198927933293627,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989725230428262,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.18658216744661332,
|
|
"num_tokens": 9836554.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.485716915130615,
|
|
"epoch": 0.4204883859440143,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989684512993205,
|
|
"loss": 5.2582,
|
|
"mean_token_accuracy": 0.18167788535356522,
|
|
"num_tokens": 9849904.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.449398851394653,
|
|
"epoch": 0.42108397855866586,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004989643715224307,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.17559571117162703,
|
|
"num_tokens": 9863935.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.430984449386597,
|
|
"epoch": 0.42167957117331745,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004989602837123031,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.17416692078113555,
|
|
"num_tokens": 9878230.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.42053337097168,
|
|
"epoch": 0.42227516378796903,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989561878690842,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.1819121167063713,
|
|
"num_tokens": 9891411.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.344071674346924,
|
|
"epoch": 0.4228707564026206,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000498952083992921,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.17915465980768203,
|
|
"num_tokens": 9904891.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.42699966430664,
|
|
"epoch": 0.4234663490172722,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989479720839605,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.17122799158096313,
|
|
"num_tokens": 9918920.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.457906007766724,
|
|
"epoch": 0.4240619416319238,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004989438521423506,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.17930842638015748,
|
|
"num_tokens": 9932975.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.412199592590332,
|
|
"epoch": 0.4246575342465753,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989397241682387,
|
|
"loss": 5.2697,
|
|
"mean_token_accuracy": 0.176967653632164,
|
|
"num_tokens": 9946704.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.406197786331177,
|
|
"epoch": 0.4252531268612269,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000498935588161773,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.1737269788980484,
|
|
"num_tokens": 9961729.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.504418277740479,
|
|
"epoch": 0.4258487194758785,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004989314441231019,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.17251337468624114,
|
|
"num_tokens": 9976980.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.504780960083008,
|
|
"epoch": 0.4264443120905301,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989272920523741,
|
|
"loss": 5.254,
|
|
"mean_token_accuracy": 0.1716462790966034,
|
|
"num_tokens": 9991963.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.449224662780762,
|
|
"epoch": 0.42703990470518166,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004989231319497382,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.1751016616821289,
|
|
"num_tokens": 10005323.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.408845376968384,
|
|
"epoch": 0.42763549731983325,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989189638153437,
|
|
"loss": 5.1936,
|
|
"mean_token_accuracy": 0.18045521527528763,
|
|
"num_tokens": 10018352.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.405736637115479,
|
|
"epoch": 0.42823108993448483,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004989147876493401,
|
|
"loss": 5.2259,
|
|
"mean_token_accuracy": 0.17859551459550857,
|
|
"num_tokens": 10032371.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.517723846435547,
|
|
"epoch": 0.4288266825491364,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989106034518771,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.17126883566379547,
|
|
"num_tokens": 10044221.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.4738462448120115,
|
|
"epoch": 0.42942227516378795,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004989064112231049,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.17219431549310685,
|
|
"num_tokens": 10057475.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.478409481048584,
|
|
"epoch": 0.43001786777843953,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004989022109631736,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.17937839776277542,
|
|
"num_tokens": 10072272.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.463757419586182,
|
|
"epoch": 0.4306134603930911,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004988980026722341,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.16646866500377655,
|
|
"num_tokens": 10086757.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.493578147888184,
|
|
"epoch": 0.4312090530077427,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988937863504373,
|
|
"loss": 5.2989,
|
|
"mean_token_accuracy": 0.1656480222940445,
|
|
"num_tokens": 10100471.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.548541069030762,
|
|
"epoch": 0.4318046456223943,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988895619979344,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.17451075464487076,
|
|
"num_tokens": 10112764.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.471344041824341,
|
|
"epoch": 0.4324002382370459,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000498885329614877,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.18120261430740356,
|
|
"num_tokens": 10125830.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.285438537597656,
|
|
"epoch": 0.43299583085169746,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988810892014168,
|
|
"loss": 5.192,
|
|
"mean_token_accuracy": 0.18470473140478133,
|
|
"num_tokens": 10140007.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.464161491394043,
|
|
"epoch": 0.433591423466349,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988768407577058,
|
|
"loss": 5.2139,
|
|
"mean_token_accuracy": 0.18329060524702073,
|
|
"num_tokens": 10154508.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.451922225952148,
|
|
"epoch": 0.4341870160810006,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988725842838968,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.18227056562900543,
|
|
"num_tokens": 10167832.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.447620010375976,
|
|
"epoch": 0.43478260869565216,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498868319780142,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.17347651720046997,
|
|
"num_tokens": 10182421.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.388653373718261,
|
|
"epoch": 0.43537820131030375,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988640472465947,
|
|
"loss": 5.1814,
|
|
"mean_token_accuracy": 0.18340695053339004,
|
|
"num_tokens": 10196210.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.433486461639404,
|
|
"epoch": 0.43597379392495533,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004988597666834078,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.17672632932662963,
|
|
"num_tokens": 10210930.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.447716569900512,
|
|
"epoch": 0.4365693865396069,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004988554780907353,
|
|
"loss": 5.209,
|
|
"mean_token_accuracy": 0.17999767810106276,
|
|
"num_tokens": 10225758.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.459556674957275,
|
|
"epoch": 0.4371649791542585,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988511814687306,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.1789574459195137,
|
|
"num_tokens": 10239924.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.45181303024292,
|
|
"epoch": 0.4377605717689101,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004988468768175479,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.17841825783252716,
|
|
"num_tokens": 10254713.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.450264739990234,
|
|
"epoch": 0.4383561643835616,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988425641373418,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.1699953243136406,
|
|
"num_tokens": 10270335.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.417951583862305,
|
|
"epoch": 0.4389517569982132,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988382434282668,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.17859781831502913,
|
|
"num_tokens": 10286368.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.503134155273438,
|
|
"epoch": 0.4395473496128648,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000498833914690478,
|
|
"loss": 5.2765,
|
|
"mean_token_accuracy": 0.1666211262345314,
|
|
"num_tokens": 10302073.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.3756622791290285,
|
|
"epoch": 0.4401429422275164,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004988295779241306,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.18852665275335312,
|
|
"num_tokens": 10317741.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.463269662857056,
|
|
"epoch": 0.44073853484216796,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004988252331293802,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.1729907587170601,
|
|
"num_tokens": 10331439.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.519346475601196,
|
|
"epoch": 0.44133412745681955,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988208803063827,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.16675825864076615,
|
|
"num_tokens": 10345107.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.497174167633057,
|
|
"epoch": 0.44192972007147113,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004988165194552939,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.1763206422328949,
|
|
"num_tokens": 10360078.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.4186278820037845,
|
|
"epoch": 0.4425253126861227,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004988121505762706,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.17349922955036162,
|
|
"num_tokens": 10373221.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.4956518650054935,
|
|
"epoch": 0.44312090530077425,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004988077736694693,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.16975481510162355,
|
|
"num_tokens": 10386200.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.405879306793213,
|
|
"epoch": 0.44371649791542583,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988033887350471,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.17643922865390776,
|
|
"num_tokens": 10398680.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.475712585449219,
|
|
"epoch": 0.4443120905300774,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004987989957731611,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.17309290021657944,
|
|
"num_tokens": 10414483.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.482502889633179,
|
|
"epoch": 0.444907683144729,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004987945947839691,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.17647774666547775,
|
|
"num_tokens": 10428962.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.560481452941895,
|
|
"epoch": 0.4455032757593806,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498790185767629,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.17228059396147727,
|
|
"num_tokens": 10442273.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.553908109664917,
|
|
"epoch": 0.4460988683740322,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004987857687242986,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.17345699965953826,
|
|
"num_tokens": 10456610.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.337998104095459,
|
|
"epoch": 0.44669446098868376,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004987813436541366,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.17825863063335418,
|
|
"num_tokens": 10470144.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.462057161331177,
|
|
"epoch": 0.4472900536033353,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987769105573016,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.18721976578235627,
|
|
"num_tokens": 10483866.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.435852193832398,
|
|
"epoch": 0.4478856462179869,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987724694339526,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.1813330054283142,
|
|
"num_tokens": 10497350.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.401251745223999,
|
|
"epoch": 0.44848123883263846,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987680202842491,
|
|
"loss": 5.2647,
|
|
"mean_token_accuracy": 0.17907270640134812,
|
|
"num_tokens": 10510808.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.410561609268188,
|
|
"epoch": 0.44907683144729005,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987635631083505,
|
|
"loss": 5.0955,
|
|
"mean_token_accuracy": 0.18220418691635132,
|
|
"num_tokens": 10525965.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.459945726394653,
|
|
"epoch": 0.44967242406194163,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004987590979064167,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.17401321083307267,
|
|
"num_tokens": 10539900.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.451573276519776,
|
|
"epoch": 0.4502680166765932,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004987546246786078,
|
|
"loss": 5.3051,
|
|
"mean_token_accuracy": 0.17250088304281236,
|
|
"num_tokens": 10553653.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.354863882064819,
|
|
"epoch": 0.4508636092912448,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004987501434250844,
|
|
"loss": 5.185,
|
|
"mean_token_accuracy": 0.17886309772729875,
|
|
"num_tokens": 10568202.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.363522291183472,
|
|
"epoch": 0.4514592019058964,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000498745654146007,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.18388983756303787,
|
|
"num_tokens": 10581290.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.381134271621704,
|
|
"epoch": 0.4520547945205479,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000498741156841537,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.18084201067686081,
|
|
"num_tokens": 10596697.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.454072713851929,
|
|
"epoch": 0.4526503871351995,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987366515118353,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.17724405229091644,
|
|
"num_tokens": 10610052.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.406693458557129,
|
|
"epoch": 0.4532459797498511,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004987321381570638,
|
|
"loss": 5.1987,
|
|
"mean_token_accuracy": 0.18197130262851716,
|
|
"num_tokens": 10624268.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.337955665588379,
|
|
"epoch": 0.4538415723645027,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004987276167773842,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.18395244628190993,
|
|
"num_tokens": 10636463.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.419845104217529,
|
|
"epoch": 0.45443716497915426,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987230873729588,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.1791321575641632,
|
|
"num_tokens": 10649566.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.411997222900391,
|
|
"epoch": 0.45503275759380585,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049871854994395,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.17639743089675902,
|
|
"num_tokens": 10661373.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.360568475723267,
|
|
"epoch": 0.45562835020845743,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004987140044905205,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.18040407747030257,
|
|
"num_tokens": 10677008.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.463270759582519,
|
|
"epoch": 0.456223942823109,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987094510128335,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.18028978854417801,
|
|
"num_tokens": 10690497.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.387830209732056,
|
|
"epoch": 0.45681953543776055,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004987048895110522,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.18052594661712645,
|
|
"num_tokens": 10705315.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.3848429203033445,
|
|
"epoch": 0.45741512805241213,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004987003199853401,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.18569260686635972,
|
|
"num_tokens": 10718536.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.425768804550171,
|
|
"epoch": 0.4580107206670637,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004986957424358613,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.17248504608869553,
|
|
"num_tokens": 10735402.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.455077743530273,
|
|
"epoch": 0.4586063132817153,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049869115686278,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.17963045835494995,
|
|
"num_tokens": 10748809.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.291566371917725,
|
|
"epoch": 0.4592019058963669,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986865632662606,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.18188143372535706,
|
|
"num_tokens": 10761935.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.407263994216919,
|
|
"epoch": 0.4597974985110185,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004986819616464678,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.17161599099636077,
|
|
"num_tokens": 10778252.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.536478281021118,
|
|
"epoch": 0.46039309112567006,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004986773520035667,
|
|
"loss": 5.369,
|
|
"mean_token_accuracy": 0.17348424196243287,
|
|
"num_tokens": 10792606.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.44503812789917,
|
|
"epoch": 0.46098868374032165,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004986727343377227,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.17564860582351685,
|
|
"num_tokens": 10805433.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.38973035812378,
|
|
"epoch": 0.4615842763549732,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986681086491014,
|
|
"loss": 5.2438,
|
|
"mean_token_accuracy": 0.1775559201836586,
|
|
"num_tokens": 10818648.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.405978059768676,
|
|
"epoch": 0.46217986896962476,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004986634749378686,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.17992064654827117,
|
|
"num_tokens": 10833089.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.386883735656738,
|
|
"epoch": 0.46277546158427635,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986588332041908,
|
|
"loss": 5.1692,
|
|
"mean_token_accuracy": 0.18023942708969115,
|
|
"num_tokens": 10847850.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.445439863204956,
|
|
"epoch": 0.46337105419892793,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004986541834482342,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.17605786323547362,
|
|
"num_tokens": 10861354.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.460016536712646,
|
|
"epoch": 0.4639666468135795,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004986495256701657,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.16894470155239105,
|
|
"num_tokens": 10877986.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.349572610855103,
|
|
"epoch": 0.4645622394282311,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986448598701523,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.18420587629079818,
|
|
"num_tokens": 10891253.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.422088575363159,
|
|
"epoch": 0.4651578320428827,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986401860483615,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.177257764339447,
|
|
"num_tokens": 10905916.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.378653717041016,
|
|
"epoch": 0.4657534246575342,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986355042049608,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.18282263427972795,
|
|
"num_tokens": 10920038.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.375914716720581,
|
|
"epoch": 0.4663490172721858,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004986308143401181,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.18440732806921006,
|
|
"num_tokens": 10933161.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.385863161087036,
|
|
"epoch": 0.4669446098868374,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004986261164540018,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.17684833109378814,
|
|
"num_tokens": 10946573.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.420489740371704,
|
|
"epoch": 0.467540202501489,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004986214105467801,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.1764943853020668,
|
|
"num_tokens": 10960727.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.475333166122437,
|
|
"epoch": 0.46813579511614056,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004986166966186223,
|
|
"loss": 5.2586,
|
|
"mean_token_accuracy": 0.17300828397274018,
|
|
"num_tokens": 10973298.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.437486410140991,
|
|
"epoch": 0.46873138773079215,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986119746696969,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.17683133184909822,
|
|
"num_tokens": 10988214.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.4991988182067875,
|
|
"epoch": 0.46932698034544373,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986072447001736,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.17713205516338348,
|
|
"num_tokens": 11003526.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.443651914596558,
|
|
"epoch": 0.4699225729600953,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004986025067102221,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.16945464611053468,
|
|
"num_tokens": 11019600.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.372118949890137,
|
|
"epoch": 0.47051816557474685,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985977607000121,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.18064777106046676,
|
|
"num_tokens": 11032591.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.340700483322143,
|
|
"epoch": 0.47111375818939843,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985930066697141,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.18015246540308,
|
|
"num_tokens": 11045724.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.426395130157471,
|
|
"epoch": 0.47170935080405,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004985882446194984,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.1719123438000679,
|
|
"num_tokens": 11059149.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.37501859664917,
|
|
"epoch": 0.4723049434187016,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000498583474549536,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.1719416782259941,
|
|
"num_tokens": 11073489.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.415882778167725,
|
|
"epoch": 0.4729005360333532,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985786964599978,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.17780339866876602,
|
|
"num_tokens": 11086535.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.314735031127929,
|
|
"epoch": 0.4734961286480048,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004985739103510553,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.1835525944828987,
|
|
"num_tokens": 11100142.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.3323729038238525,
|
|
"epoch": 0.47409172126265636,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004985691162228802,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.19121087342500687,
|
|
"num_tokens": 11113364.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.504801177978516,
|
|
"epoch": 0.47468731387730795,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985643140756442,
|
|
"loss": 5.2685,
|
|
"mean_token_accuracy": 0.17476556897163392,
|
|
"num_tokens": 11127127.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.4617955684661865,
|
|
"epoch": 0.4752829064919595,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049855950390952,
|
|
"loss": 5.2001,
|
|
"mean_token_accuracy": 0.17798593938350676,
|
|
"num_tokens": 11139788.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.396760749816894,
|
|
"epoch": 0.47587849910661106,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004985546857246797,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.17533749639987944,
|
|
"num_tokens": 11156470.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.394761610031128,
|
|
"epoch": 0.47647409172126265,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004985498595212964,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.18325577527284623,
|
|
"num_tokens": 11168923.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.378653860092163,
|
|
"epoch": 0.47706968433591423,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985450252995431,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.18289474546909332,
|
|
"num_tokens": 11181328.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.491535997390747,
|
|
"epoch": 0.4776652769505658,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004985401830595932,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.17148307859897613,
|
|
"num_tokens": 11197800.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.518416118621826,
|
|
"epoch": 0.4782608695652174,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985353328016204,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.17990812957286834,
|
|
"num_tokens": 11209862.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.354816961288452,
|
|
"epoch": 0.478856462179869,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004985304745257986,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.17843100428581238,
|
|
"num_tokens": 11223433.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.492253971099854,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985256082323022,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.1737961947917938,
|
|
"num_tokens": 11236975.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.349940395355224,
|
|
"epoch": 0.4800476474091721,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004985207339213057,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.1750365063548088,
|
|
"num_tokens": 11250277.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.397316408157349,
|
|
"epoch": 0.4806432400238237,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985158515929837,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.18069482296705247,
|
|
"num_tokens": 11264990.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.502514934539795,
|
|
"epoch": 0.4812388326384753,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004985109612475116,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.17538685202598572,
|
|
"num_tokens": 11277496.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.420845413208008,
|
|
"epoch": 0.48183442525312686,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004985060628850648,
|
|
"loss": 5.2702,
|
|
"mean_token_accuracy": 0.17813128978013992,
|
|
"num_tokens": 11290263.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.3939567565917965,
|
|
"epoch": 0.48243001786777845,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004985011565058189,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.18240702748298646,
|
|
"num_tokens": 11305611.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.481168270111084,
|
|
"epoch": 0.48302561048243003,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004984962421099498,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.1746520832180977,
|
|
"num_tokens": 11321216.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.411353349685669,
|
|
"epoch": 0.4836212030970816,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498491319697634,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.1857217565178871,
|
|
"num_tokens": 11335029.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.32309398651123,
|
|
"epoch": 0.48421679571173315,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000498486389269048,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.17848790884017945,
|
|
"num_tokens": 11349301.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.469196367263794,
|
|
"epoch": 0.48481238832638474,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984814508243685,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.1781415417790413,
|
|
"num_tokens": 11364561.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.34276819229126,
|
|
"epoch": 0.4854079809410363,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004984765043637727,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.1835410252213478,
|
|
"num_tokens": 11379470.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.391331672668457,
|
|
"epoch": 0.4860035735556879,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000498471549887438,
|
|
"loss": 5.1851,
|
|
"mean_token_accuracy": 0.18035566210746765,
|
|
"num_tokens": 11393433.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.331994915008545,
|
|
"epoch": 0.4865991661703395,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984665873955422,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.18213555961847305,
|
|
"num_tokens": 11406673.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.3302874088287355,
|
|
"epoch": 0.4871947587849911,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004984616168882632,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.18401360362768174,
|
|
"num_tokens": 11420395.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.461697959899903,
|
|
"epoch": 0.48779035139964266,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004984566383657794,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.1796843484044075,
|
|
"num_tokens": 11432866.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.350088882446289,
|
|
"epoch": 0.48838594401429425,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984516518282692,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.17782287746667863,
|
|
"num_tokens": 11447062.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.378855609893799,
|
|
"epoch": 0.4889815366289458,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004984466572759117,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.18548077642917632,
|
|
"num_tokens": 11461255.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.4743170738220215,
|
|
"epoch": 0.48957712924359736,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004984416547088858,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.17700682282447816,
|
|
"num_tokens": 11475711.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.408509540557861,
|
|
"epoch": 0.49017272185824895,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984366441273711,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.17547389417886733,
|
|
"num_tokens": 11491199.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.413048601150512,
|
|
"epoch": 0.49076831447290054,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004984316255315472,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.18458717167377472,
|
|
"num_tokens": 11504365.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.42731122970581,
|
|
"epoch": 0.4913639070875521,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984265989215942,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.16969735622406007,
|
|
"num_tokens": 11517969.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.400035381317139,
|
|
"epoch": 0.4919594997022037,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.0004984215642976923,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.17709336876869203,
|
|
"num_tokens": 11533203.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.402977991104126,
|
|
"epoch": 0.4925550923168553,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004984165216600224,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.17979006171226503,
|
|
"num_tokens": 11547820.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.425424098968506,
|
|
"epoch": 0.4931506849315068,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004984114710087648,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.18383354544639588,
|
|
"num_tokens": 11561591.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.3444990634918215,
|
|
"epoch": 0.4937462775461584,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004984064123441011,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.1771566241979599,
|
|
"num_tokens": 11576722.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.4565346240997314,
|
|
"epoch": 0.49434187016081,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004984013456662127,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.1775720477104187,
|
|
"num_tokens": 11590455.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.448108577728272,
|
|
"epoch": 0.4949374627754616,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004983962709752812,
|
|
"loss": 5.2123,
|
|
"mean_token_accuracy": 0.1778811439871788,
|
|
"num_tokens": 11605495.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.3837755680084225,
|
|
"epoch": 0.49553305539011316,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983911882714886,
|
|
"loss": 5.1908,
|
|
"mean_token_accuracy": 0.1828569382429123,
|
|
"num_tokens": 11619692.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.398835611343384,
|
|
"epoch": 0.49612864800476475,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004983860975550174,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.1811256691813469,
|
|
"num_tokens": 11633806.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.372111892700195,
|
|
"epoch": 0.49672424061941634,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004983809988260501,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.19019066840410231,
|
|
"num_tokens": 11649871.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.340040969848633,
|
|
"epoch": 0.4973198332340679,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004983758920847696,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.18091800808906555,
|
|
"num_tokens": 11661472.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.295851755142212,
|
|
"epoch": 0.49791542584871945,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004983707773313589,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.18488455712795257,
|
|
"num_tokens": 11674689.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.291795921325684,
|
|
"epoch": 0.49851101846337104,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004983656545660016,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.19727823436260222,
|
|
"num_tokens": 11687867.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.311141681671143,
|
|
"epoch": 0.4991066110780226,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004983605237888815,
|
|
"loss": 5.0975,
|
|
"mean_token_accuracy": 0.18359908312559128,
|
|
"num_tokens": 11704611.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.381280374526978,
|
|
"epoch": 0.4997022036926742,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004983553850001826,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.18190955221652985,
|
|
"num_tokens": 11719448.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.360610008239746,
|
|
"epoch": 0.5002977963073257,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983502382000892,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.1821006640791893,
|
|
"num_tokens": 11731160.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.3960349559783936,
|
|
"epoch": 0.5008933889219773,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004983450833887859,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.1835642486810684,
|
|
"num_tokens": 11744319.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.355774402618408,
|
|
"epoch": 0.5014889815366289,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004983399205664575,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.18385220170021058,
|
|
"num_tokens": 11757861.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.375676441192627,
|
|
"epoch": 0.5020845741512805,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004983347497332894,
|
|
"loss": 5.099,
|
|
"mean_token_accuracy": 0.18466894924640656,
|
|
"num_tokens": 11770707.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.3535175800323485,
|
|
"epoch": 0.5026801667659321,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004983295708894668,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.18802412003278732,
|
|
"num_tokens": 11785155.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.395015621185303,
|
|
"epoch": 0.5032757593805837,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004983243840351757,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.1816991686820984,
|
|
"num_tokens": 11798532.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.294522428512574,
|
|
"epoch": 0.5038713519952353,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004983191891706021,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.1819404810667038,
|
|
"num_tokens": 11812708.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.370300388336181,
|
|
"epoch": 0.5044669446098868,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004983139862959322,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.17646192014217377,
|
|
"num_tokens": 11828844.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.371694135665893,
|
|
"epoch": 0.5050625372245384,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004983087754113527,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.1806330621242523,
|
|
"num_tokens": 11845070.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.311435270309448,
|
|
"epoch": 0.50565812983919,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004983035565170505,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.18790811151266099,
|
|
"num_tokens": 11858299.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.381554174423218,
|
|
"epoch": 0.5062537224538416,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982983296132128,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.18355477303266526,
|
|
"num_tokens": 11873805.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.306122922897339,
|
|
"epoch": 0.5068493150684932,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004982930947000271,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.1724663570523262,
|
|
"num_tokens": 11888304.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.3913490772247314,
|
|
"epoch": 0.5074449076831448,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004982878517776812,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.1833187460899353,
|
|
"num_tokens": 11901914.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.3774196147918705,
|
|
"epoch": 0.5080405002977963,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498282600846363,
|
|
"loss": 5.1855,
|
|
"mean_token_accuracy": 0.18499902933835982,
|
|
"num_tokens": 11913225.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.336227607727051,
|
|
"epoch": 0.5086360929124479,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498277341906261,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.18356177657842637,
|
|
"num_tokens": 11927200.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.347063493728638,
|
|
"epoch": 0.5092316855270994,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004982720749575637,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.18288348615169525,
|
|
"num_tokens": 11939826.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.365194177627563,
|
|
"epoch": 0.509827278141751,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004982668000004602,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.18635171502828599,
|
|
"num_tokens": 11951983.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.418434095382691,
|
|
"epoch": 0.5104228707564026,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004982615170351395,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.17496707439422607,
|
|
"num_tokens": 11965642.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.34821720123291,
|
|
"epoch": 0.5110184633710542,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004982562260617912,
|
|
"loss": 5.2435,
|
|
"mean_token_accuracy": 0.17255653142929078,
|
|
"num_tokens": 11981472.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.368606996536255,
|
|
"epoch": 0.5116140559857058,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004982509270806052,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.18220441788434982,
|
|
"num_tokens": 11995739.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.462830018997193,
|
|
"epoch": 0.5122096486003573,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982456200917712,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.176616108417511,
|
|
"num_tokens": 12007850.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.411269950866699,
|
|
"epoch": 0.5128052412150089,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00049824030509548,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.1907610520720482,
|
|
"num_tokens": 12022893.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.360086679458618,
|
|
"epoch": 0.5134008338296605,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498234982091922,
|
|
"loss": 5.1809,
|
|
"mean_token_accuracy": 0.18792386054992677,
|
|
"num_tokens": 12035520.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.304580926895142,
|
|
"epoch": 0.5139964264443121,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004982296510812879,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.18127159029245377,
|
|
"num_tokens": 12047938.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.366024780273437,
|
|
"epoch": 0.5145920190589637,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004982243120637694,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.17741145193576813,
|
|
"num_tokens": 12061236.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.3376422882080075,
|
|
"epoch": 0.5151876116736153,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004982189650395577,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.18770092576742173,
|
|
"num_tokens": 12074427.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.3394263744354244,
|
|
"epoch": 0.5157832042882668,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004982136100088447,
|
|
"loss": 5.1243,
|
|
"mean_token_accuracy": 0.18907763063907623,
|
|
"num_tokens": 12088128.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.4335160732269285,
|
|
"epoch": 0.5163787969029184,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004982082469718224,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.1720768094062805,
|
|
"num_tokens": 12100938.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.345817613601684,
|
|
"epoch": 0.51697438951757,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004982028759286831,
|
|
"loss": 5.1357,
|
|
"mean_token_accuracy": 0.1845109209418297,
|
|
"num_tokens": 12113464.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.354687881469727,
|
|
"epoch": 0.5175699821322216,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004981974968796197,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.17695156782865523,
|
|
"num_tokens": 12129113.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.397428560256958,
|
|
"epoch": 0.5181655747468732,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981921098248249,
|
|
"loss": 5.2519,
|
|
"mean_token_accuracy": 0.17520484924316407,
|
|
"num_tokens": 12142024.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.424976873397827,
|
|
"epoch": 0.5187611673615247,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.000498186714764492,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.1788182258605957,
|
|
"num_tokens": 12157889.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.401285028457641,
|
|
"epoch": 0.5193567599761763,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004981813116988145,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.17771369963884354,
|
|
"num_tokens": 12171527.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.369123554229736,
|
|
"epoch": 0.5199523525908278,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004981759006279864,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.17832735776901246,
|
|
"num_tokens": 12186453.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.276954698562622,
|
|
"epoch": 0.5205479452054794,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004981704815522014,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.1799240991473198,
|
|
"num_tokens": 12201401.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.336610221862793,
|
|
"epoch": 0.521143537820131,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004981650544716542,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.1777276188135147,
|
|
"num_tokens": 12215219.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.400670957565308,
|
|
"epoch": 0.5217391304347826,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004981596193865393,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.17499773651361467,
|
|
"num_tokens": 12229932.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.334597826004028,
|
|
"epoch": 0.5223347230494342,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981541762970517,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.188652803003788,
|
|
"num_tokens": 12241718.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.432035350799561,
|
|
"epoch": 0.5229303156640858,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981487252033866,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.17703877240419388,
|
|
"num_tokens": 12256395.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.3418543338775635,
|
|
"epoch": 0.5235259082787374,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004981432661057396,
|
|
"loss": 5.0652,
|
|
"mean_token_accuracy": 0.18941047340631484,
|
|
"num_tokens": 12269966.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.3853747844696045,
|
|
"epoch": 0.5241215008933889,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004981377990043064,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.17666574120521544,
|
|
"num_tokens": 12284410.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.248237466812133,
|
|
"epoch": 0.5247170935080405,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004981323238992831,
|
|
"loss": 5.0172,
|
|
"mean_token_accuracy": 0.190936478972435,
|
|
"num_tokens": 12298931.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.333182621002197,
|
|
"epoch": 0.5253126861226921,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004981268407908662,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.18727773129940034,
|
|
"num_tokens": 12313857.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.326207828521729,
|
|
"epoch": 0.5259082787373437,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004981213496792523,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.18813281804323195,
|
|
"num_tokens": 12327732.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.331199884414673,
|
|
"epoch": 0.5265038713519953,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981158505646383,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.18382711708545685,
|
|
"num_tokens": 12341754.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.342618417739868,
|
|
"epoch": 0.5270994639666469,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981103434472216,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.18141558915376663,
|
|
"num_tokens": 12355656.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.288913822174072,
|
|
"epoch": 0.5276950565812983,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981048283271997,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.18948088735342025,
|
|
"num_tokens": 12368346.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.319597959518433,
|
|
"epoch": 0.5282906491959499,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004980993052047701,
|
|
"loss": 5.128,
|
|
"mean_token_accuracy": 0.17983518242836,
|
|
"num_tokens": 12381844.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.433142042160034,
|
|
"epoch": 0.5288862418106015,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004980937740801313,
|
|
"loss": 5.2505,
|
|
"mean_token_accuracy": 0.17256402224302292,
|
|
"num_tokens": 12395432.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.326618003845215,
|
|
"epoch": 0.5294818344252531,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004980882349534816,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.17884818762540816,
|
|
"num_tokens": 12408897.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.313967180252075,
|
|
"epoch": 0.5300774270399047,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980826878250195,
|
|
"loss": 5.1052,
|
|
"mean_token_accuracy": 0.1866842970252037,
|
|
"num_tokens": 12421480.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.390976095199585,
|
|
"epoch": 0.5306730196545563,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004980771326949442,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.1760936826467514,
|
|
"num_tokens": 12436931.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.346206188201904,
|
|
"epoch": 0.5312686122692079,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004980715695634549,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.1828779920935631,
|
|
"num_tokens": 12451687.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.336434745788575,
|
|
"epoch": 0.5318642048838594,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004980659984307511,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.18571032583713531,
|
|
"num_tokens": 12464338.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.375011920928955,
|
|
"epoch": 0.532459797498511,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004980604192970325,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.18247899264097214,
|
|
"num_tokens": 12482520.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.477635526657105,
|
|
"epoch": 0.5330553901131626,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004980548321624993,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.1796797677874565,
|
|
"num_tokens": 12495791.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.281922435760498,
|
|
"epoch": 0.5336509827278142,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498049237027352,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.18044036626815796,
|
|
"num_tokens": 12509963.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.386615800857544,
|
|
"epoch": 0.5342465753424658,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004980436338917914,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.1813435047864914,
|
|
"num_tokens": 12522825.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.377624130249023,
|
|
"epoch": 0.5348421679571174,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000498038022756018,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.18387425392866136,
|
|
"num_tokens": 12536097.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.292933368682862,
|
|
"epoch": 0.535437760571769,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004980324036202335,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.19418380856513978,
|
|
"num_tokens": 12551441.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.363208198547364,
|
|
"epoch": 0.5360333531864205,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004980267764846393,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.18742390125989913,
|
|
"num_tokens": 12566271.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.410250043869018,
|
|
"epoch": 0.5366289458010721,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004980211413494373,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.18530384153127671,
|
|
"num_tokens": 12580585.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.26597228050232,
|
|
"epoch": 0.5372245384157236,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004980154982148296,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.1947075054049492,
|
|
"num_tokens": 12592389.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.233290386199951,
|
|
"epoch": 0.5378201310303752,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004980098470810185,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.19874578565359116,
|
|
"num_tokens": 12606487.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.308344984054566,
|
|
"epoch": 0.5384157236450268,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004980041879482068,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.18965509980916978,
|
|
"num_tokens": 12621036.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.307169389724732,
|
|
"epoch": 0.5390113162596784,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004979985208165975,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.18871429711580276,
|
|
"num_tokens": 12634911.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.29555025100708,
|
|
"epoch": 0.5396069088743299,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004979928456863937,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.19091595858335494,
|
|
"num_tokens": 12649165.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.327419137954712,
|
|
"epoch": 0.5402025014889815,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979871625577991,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.18464012295007706,
|
|
"num_tokens": 12663803.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.338599395751953,
|
|
"epoch": 0.5407980941036331,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004979814714310177,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.183014377951622,
|
|
"num_tokens": 12676336.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.249287748336792,
|
|
"epoch": 0.5413936867182847,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004979757723062533,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.18926156014204026,
|
|
"num_tokens": 12689619.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.29856276512146,
|
|
"epoch": 0.5419892793329363,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979700651837107,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.18330489844083786,
|
|
"num_tokens": 12703964.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.398951768875122,
|
|
"epoch": 0.5425848719475879,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979643500635942,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.182154643535614,
|
|
"num_tokens": 12716832.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.318705940246582,
|
|
"epoch": 0.5431804645622395,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004979586269461089,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.19125055223703386,
|
|
"num_tokens": 12729665.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.316912984848022,
|
|
"epoch": 0.543776057176891,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004979528958314604,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.18553293943405152,
|
|
"num_tokens": 12743576.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.248009777069091,
|
|
"epoch": 0.5443716497915426,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004979471567198539,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.18719419091939926,
|
|
"num_tokens": 12758511.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.284886264801026,
|
|
"epoch": 0.5449672424061942,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979414096114953,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.18700873255729675,
|
|
"num_tokens": 12771694.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.337162733078003,
|
|
"epoch": 0.5455628350208458,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000497935654506591,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.1798368662595749,
|
|
"num_tokens": 12786367.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.264929866790771,
|
|
"epoch": 0.5461584276354973,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000497929891405347,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.19360989928245545,
|
|
"num_tokens": 12801177.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.384415960311889,
|
|
"epoch": 0.5467540202501489,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004979241203079705,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.1744415670633316,
|
|
"num_tokens": 12817347.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.432735443115234,
|
|
"epoch": 0.5473496128648004,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004979183412146681,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.18087000995874405,
|
|
"num_tokens": 12830304.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.255253314971924,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979125541256474,
|
|
"loss": 5.0174,
|
|
"mean_token_accuracy": 0.19406490474939347,
|
|
"num_tokens": 12843813.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.32857027053833,
|
|
"epoch": 0.5485407980941036,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004979067590411157,
|
|
"loss": 5.2029,
|
|
"mean_token_accuracy": 0.17924811244010924,
|
|
"num_tokens": 12857989.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.37745041847229,
|
|
"epoch": 0.5491363907087552,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000497900955961281,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.18549373298883437,
|
|
"num_tokens": 12871529.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.299321842193604,
|
|
"epoch": 0.5497319833234068,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004978951448863514,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.18333496451377868,
|
|
"num_tokens": 12884907.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.312129306793213,
|
|
"epoch": 0.5503275759380584,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004978893258165354,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.18713537007570266,
|
|
"num_tokens": 12898403.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.338302564620972,
|
|
"epoch": 0.55092316855271,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004978834987520417,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.18272190392017365,
|
|
"num_tokens": 12913982.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.31809024810791,
|
|
"epoch": 0.5515187611673615,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004978776636930792,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.18271613717079163,
|
|
"num_tokens": 12928826.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.263760328292847,
|
|
"epoch": 0.5521143537820131,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004978718206398574,
|
|
"loss": 5.1135,
|
|
"mean_token_accuracy": 0.18286098539829254,
|
|
"num_tokens": 12941905.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.349569272994995,
|
|
"epoch": 0.5527099463966647,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004978659695925856,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.1862290918827057,
|
|
"num_tokens": 12955522.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.3778736114501955,
|
|
"epoch": 0.5533055390113163,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004978601105514739,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.18458685427904128,
|
|
"num_tokens": 12968491.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.282912683486939,
|
|
"epoch": 0.5539011316259679,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004978542435167324,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.1839528352022171,
|
|
"num_tokens": 12983258.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.322308111190796,
|
|
"epoch": 0.5544967242406195,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978483684885716,
|
|
"loss": 5.1466,
|
|
"mean_token_accuracy": 0.18625638484954835,
|
|
"num_tokens": 12996271.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.391269826889038,
|
|
"epoch": 0.5550923168552709,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004978424854672021,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.18536857068538665,
|
|
"num_tokens": 13010920.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.242734766006469,
|
|
"epoch": 0.5556879094699225,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004978365944528349,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.19349264204502106,
|
|
"num_tokens": 13023499.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.326134061813354,
|
|
"epoch": 0.5562835020845741,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004978306954456814,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.18411154747009278,
|
|
"num_tokens": 13040510.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.348765754699707,
|
|
"epoch": 0.5568790946992257,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004978247884459532,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.19509867280721666,
|
|
"num_tokens": 13053708.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.292072820663452,
|
|
"epoch": 0.5574746873138773,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004978188734538621,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.18618395924568176,
|
|
"num_tokens": 13068666.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.297101640701294,
|
|
"epoch": 0.5580702799285289,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004978129504696203,
|
|
"loss": 5.0721,
|
|
"mean_token_accuracy": 0.184037546813488,
|
|
"num_tokens": 13082549.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.464348030090332,
|
|
"epoch": 0.5586658725431805,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978070194934402,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.17674349546432494,
|
|
"num_tokens": 13096685.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.318595314025879,
|
|
"epoch": 0.559261465157832,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004978010805255347,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.18393055498600006,
|
|
"num_tokens": 13110187.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.22731761932373,
|
|
"epoch": 0.5598570577724836,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977951335661165,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.18744331151247023,
|
|
"num_tokens": 13124105.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.398666334152222,
|
|
"epoch": 0.5604526503871352,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004977891786153992,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.1836570531129837,
|
|
"num_tokens": 13139675.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.338856887817383,
|
|
"epoch": 0.5610482430017868,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004977832156735963,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.1826365500688553,
|
|
"num_tokens": 13154105.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.229065322875977,
|
|
"epoch": 0.5616438356164384,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004977772447409217,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.18953980952501298,
|
|
"num_tokens": 13168473.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.361047649383545,
|
|
"epoch": 0.56223942823109,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004977712658175894,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.18757959604263305,
|
|
"num_tokens": 13182873.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.2741364479064945,
|
|
"epoch": 0.5628350208457416,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004977652789038142,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.18117690235376357,
|
|
"num_tokens": 13196894.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.300452947616577,
|
|
"epoch": 0.5634306134603931,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977592839998105,
|
|
"loss": 5.1145,
|
|
"mean_token_accuracy": 0.1844866842031479,
|
|
"num_tokens": 13212285.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.409982824325562,
|
|
"epoch": 0.5640262060750447,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004977532811057936,
|
|
"loss": 5.1228,
|
|
"mean_token_accuracy": 0.18170470297336577,
|
|
"num_tokens": 13227272.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.3273820877075195,
|
|
"epoch": 0.5646217986896962,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004977472702219786,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.18836157470941545,
|
|
"num_tokens": 13241544.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.262960052490234,
|
|
"epoch": 0.5652173913043478,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004977412513485812,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.18137868195772172,
|
|
"num_tokens": 13255605.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.3655212879180905,
|
|
"epoch": 0.5658129839189994,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004977352244858172,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.188253515958786,
|
|
"num_tokens": 13269143.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.335684061050415,
|
|
"epoch": 0.566408576533651,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004977291896339029,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.192444109916687,
|
|
"num_tokens": 13284316.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.245979976654053,
|
|
"epoch": 0.5670041691483025,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977231467930546,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.1953254222869873,
|
|
"num_tokens": 13297714.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.304807233810425,
|
|
"epoch": 0.5675997617629541,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004977170959634893,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.18302944004535676,
|
|
"num_tokens": 13311759.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.221931600570679,
|
|
"epoch": 0.5681953543776057,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977110371454239,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.18989023864269255,
|
|
"num_tokens": 13325966.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.336720180511475,
|
|
"epoch": 0.5687909469922573,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004977049703390755,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.18615473210811614,
|
|
"num_tokens": 13340939.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.3345701694488525,
|
|
"epoch": 0.5693865396069089,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004976988955446622,
|
|
"loss": 5.2158,
|
|
"mean_token_accuracy": 0.1850939840078354,
|
|
"num_tokens": 13354400.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.501184177398682,
|
|
"epoch": 0.5699821322215605,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004976928127624013,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.17180499881505967,
|
|
"num_tokens": 13368819.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.2898355484008786,
|
|
"epoch": 0.570577724836212,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004976867219925116,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.194341841340065,
|
|
"num_tokens": 13381106.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.331715059280396,
|
|
"epoch": 0.5711733174508636,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000497680623235211,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.18656556606292723,
|
|
"num_tokens": 13394718.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.358362483978271,
|
|
"epoch": 0.5717689100655152,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004976745164907185,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.18393243700265885,
|
|
"num_tokens": 13408416.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.325113964080811,
|
|
"epoch": 0.5723645026801668,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004976684017592533,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.1798110619187355,
|
|
"num_tokens": 13422287.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.350599479675293,
|
|
"epoch": 0.5729600952948184,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004976622790410345,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.18608130812644957,
|
|
"num_tokens": 13438080.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.33511209487915,
|
|
"epoch": 0.5735556879094699,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004976561483362818,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.1797863408923149,
|
|
"num_tokens": 13454781.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.304973220825195,
|
|
"epoch": 0.5741512805241215,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000497650009645215,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.18030023723840713,
|
|
"num_tokens": 13467021.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.277446937561035,
|
|
"epoch": 0.574746873138773,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976438629680543,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.18845548778772353,
|
|
"num_tokens": 13479125.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.272354936599731,
|
|
"epoch": 0.5753424657534246,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004976377083050204,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.19556739777326584,
|
|
"num_tokens": 13493444.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.360541152954101,
|
|
"epoch": 0.5759380583680762,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004976315456563339,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.18694202452898026,
|
|
"num_tokens": 13508261.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.337416458129883,
|
|
"epoch": 0.5765336509827278,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004976253750222157,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.18485014140605927,
|
|
"num_tokens": 13521371.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.307542085647583,
|
|
"epoch": 0.5771292435973794,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004976191964028874,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.18434630036354066,
|
|
"num_tokens": 13536944.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.345064449310303,
|
|
"epoch": 0.577724836212031,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004976130097985703,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.18826042115688324,
|
|
"num_tokens": 13552281.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.321694850921631,
|
|
"epoch": 0.5783204288266826,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004976068152094867,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.18491527140140535,
|
|
"num_tokens": 13567376.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.4058403968811035,
|
|
"epoch": 0.5789160214413341,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004976006126358584,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.17675745934247972,
|
|
"num_tokens": 13580688.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.3274452686309814,
|
|
"epoch": 0.5795116140559857,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004975944020779082,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.18648908287286758,
|
|
"num_tokens": 13594823.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.292813348770141,
|
|
"epoch": 0.5801072066706373,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004975881835358586,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.19072499871253967,
|
|
"num_tokens": 13606702.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.323752737045288,
|
|
"epoch": 0.5807027992852889,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004975819570099328,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.18786547034978868,
|
|
"num_tokens": 13620651.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.258793067932129,
|
|
"epoch": 0.5812983918999405,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000497575722500354,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.1933680698275566,
|
|
"num_tokens": 13633192.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.218072414398193,
|
|
"epoch": 0.5818939845145921,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000497569480007346,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.18774635791778566,
|
|
"num_tokens": 13647082.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.2966231346130375,
|
|
"epoch": 0.5824895771292437,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004975632295311327,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.1909986898303032,
|
|
"num_tokens": 13662753.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.27412109375,
|
|
"epoch": 0.5830851697438951,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975569710719382,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.18980183005332946,
|
|
"num_tokens": 13678548.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.337112617492676,
|
|
"epoch": 0.5836807623585467,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975507046299869,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.18484079837799072,
|
|
"num_tokens": 13690969.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.328014707565307,
|
|
"epoch": 0.5842763549731983,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004975444302055038,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.18875147700309752,
|
|
"num_tokens": 13704519.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.267178106307983,
|
|
"epoch": 0.5848719475878499,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004975381477987136,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.18831533044576645,
|
|
"num_tokens": 13719664.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.30739951133728,
|
|
"epoch": 0.5854675402025015,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004975318574098422,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.19231267273426056,
|
|
"num_tokens": 13733527.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.363993167877197,
|
|
"epoch": 0.586063132817153,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004975255590391147,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.18890826106071473,
|
|
"num_tokens": 13747788.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.302137231826782,
|
|
"epoch": 0.5866587254318046,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975192526867572,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.18822885304689407,
|
|
"num_tokens": 13761389.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.282014989852906,
|
|
"epoch": 0.5872543180464562,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004975129383529959,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.1893123835325241,
|
|
"num_tokens": 13774153.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.276796579360962,
|
|
"epoch": 0.5878499106611078,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004975066160380573,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.18843629211187363,
|
|
"num_tokens": 13788167.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.306083822250367,
|
|
"epoch": 0.5884455032757594,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004975002857421681,
|
|
"loss": 5.0503,
|
|
"mean_token_accuracy": 0.1954532966017723,
|
|
"num_tokens": 13801190.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.281638336181641,
|
|
"epoch": 0.589041095890411,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004974939474655554,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.18895162045955657,
|
|
"num_tokens": 13815744.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.32926344871521,
|
|
"epoch": 0.5896366885050626,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004974876012084468,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.19358201771974565,
|
|
"num_tokens": 13829329.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.356852436065674,
|
|
"epoch": 0.5902322811197142,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974812469710694,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.18719965517520903,
|
|
"num_tokens": 13842401.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.267741584777832,
|
|
"epoch": 0.5908278737343657,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004974748847536516,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.18107263892889022,
|
|
"num_tokens": 13857156.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.257267951965332,
|
|
"epoch": 0.5914234663490173,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004974685145564213,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.1879847139120102,
|
|
"num_tokens": 13870863.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.387854528427124,
|
|
"epoch": 0.5920190589636688,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974621363796071,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.18297118395566941,
|
|
"num_tokens": 13886121.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.401101303100586,
|
|
"epoch": 0.5926146515783204,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974557502234378,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.18656743913888932,
|
|
"num_tokens": 13898928.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.337077045440674,
|
|
"epoch": 0.593210244192972,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004974493560881423,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.18620624542236328,
|
|
"num_tokens": 13911648.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.320045042037964,
|
|
"epoch": 0.5938058368076236,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004974429539739502,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.1797662854194641,
|
|
"num_tokens": 13924705.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.2995924949646,
|
|
"epoch": 0.5944014294222751,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004974365438810911,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.18246831893920898,
|
|
"num_tokens": 13939495.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.287857723236084,
|
|
"epoch": 0.5949970220369267,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974301258097948,
|
|
"loss": 5.0495,
|
|
"mean_token_accuracy": 0.19224149882793426,
|
|
"num_tokens": 13952236.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.362414264678955,
|
|
"epoch": 0.5955926146515783,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004974236997602915,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.18654642701148988,
|
|
"num_tokens": 13967699.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.385529041290283,
|
|
"epoch": 0.5961882072662299,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004974172657328116,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.18504815697669982,
|
|
"num_tokens": 13980619.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.242889642715454,
|
|
"epoch": 0.5967837998808815,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497410823727586,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.18375581204891206,
|
|
"num_tokens": 13995965.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.285166883468628,
|
|
"epoch": 0.5973793924955331,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000497404373744846,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.1867982938885689,
|
|
"num_tokens": 14010325.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.372513055801392,
|
|
"epoch": 0.5979749851101847,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004973979157848227,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.18112455755472184,
|
|
"num_tokens": 14025368.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.2272053241729735,
|
|
"epoch": 0.5985705777248362,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004973914498477475,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.18892043828964233,
|
|
"num_tokens": 14039609.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.3455727100372314,
|
|
"epoch": 0.5991661703394878,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004973849759338527,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.18381206393241883,
|
|
"num_tokens": 14053680.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.435503625869751,
|
|
"epoch": 0.5997617629541394,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004973784940433706,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.18110530376434325,
|
|
"num_tokens": 14067262.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.242698717117309,
|
|
"epoch": 0.600357355568791,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004973720041765332,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.18773505985736846,
|
|
"num_tokens": 14080821.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.326541376113892,
|
|
"epoch": 0.6009529481834425,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004973655063335736,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.18176350593566895,
|
|
"num_tokens": 14093586.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.275772047042847,
|
|
"epoch": 0.6015485407980941,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000497359000514725,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.1942247360944748,
|
|
"num_tokens": 14108138.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.273860263824463,
|
|
"epoch": 0.6021441334127456,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004973524867202205,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.18716853260993957,
|
|
"num_tokens": 14122495.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.199629783630371,
|
|
"epoch": 0.6027397260273972,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004973459649502939,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.19232825487852095,
|
|
"num_tokens": 14136838.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.290495586395264,
|
|
"epoch": 0.6033353186420488,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004973394352051789,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.191631717979908,
|
|
"num_tokens": 14150910.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.327006673812866,
|
|
"epoch": 0.6039309112567004,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00049733289748511,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.18818621039390565,
|
|
"num_tokens": 14164116.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.295506334304809,
|
|
"epoch": 0.604526503871352,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004973263517903213,
|
|
"loss": 4.9861,
|
|
"mean_token_accuracy": 0.20130750238895417,
|
|
"num_tokens": 14178549.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.274371480941772,
|
|
"epoch": 0.6051220964860036,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004973197981210481,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.19356632679700853,
|
|
"num_tokens": 14191625.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.268049669265747,
|
|
"epoch": 0.6057176891006552,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004973132364775252,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.18876909017562865,
|
|
"num_tokens": 14205396.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.239681148529053,
|
|
"epoch": 0.6063132817153067,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004973066668599879,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.1882330909371376,
|
|
"num_tokens": 14216957.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.371358346939087,
|
|
"epoch": 0.6069088743299583,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004973000892686719,
|
|
"loss": 5.0728,
|
|
"mean_token_accuracy": 0.18767688125371934,
|
|
"num_tokens": 14232891.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.307251882553101,
|
|
"epoch": 0.6075044669446099,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004972935037038131,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.19542305469512938,
|
|
"num_tokens": 14245628.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.221906757354736,
|
|
"epoch": 0.6081000595592615,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004972869101656478,
|
|
"loss": 5.0653,
|
|
"mean_token_accuracy": 0.19175480157136918,
|
|
"num_tokens": 14260164.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.3775773525238035,
|
|
"epoch": 0.6086956521739131,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972803086544125,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.18299226015806197,
|
|
"num_tokens": 14274828.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.322595310211182,
|
|
"epoch": 0.6092912447885647,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972736991703439,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.18462182134389876,
|
|
"num_tokens": 14287779.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.2907520771026615,
|
|
"epoch": 0.6098868374032163,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004972670817136791,
|
|
"loss": 5.0837,
|
|
"mean_token_accuracy": 0.18469851166009904,
|
|
"num_tokens": 14300946.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.265849828720093,
|
|
"epoch": 0.6104824300178677,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004972604562846554,
|
|
"loss": 5.0043,
|
|
"mean_token_accuracy": 0.19170174300670623,
|
|
"num_tokens": 14314944.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.342233610153198,
|
|
"epoch": 0.6110780226325193,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972538228835106,
|
|
"loss": 5.1177,
|
|
"mean_token_accuracy": 0.18638357967138292,
|
|
"num_tokens": 14330069.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.309694242477417,
|
|
"epoch": 0.6116736152471709,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004972471815104825,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.18415531218051912,
|
|
"num_tokens": 14344262.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.291870021820069,
|
|
"epoch": 0.6122692078618225,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004972405321658094,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.1862774133682251,
|
|
"num_tokens": 14358358.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.267843103408813,
|
|
"epoch": 0.6128648004764741,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004972338748497297,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.19755438566207886,
|
|
"num_tokens": 14371520.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.2251979351043705,
|
|
"epoch": 0.6134603930911257,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972272095624822,
|
|
"loss": 4.9384,
|
|
"mean_token_accuracy": 0.20251286178827285,
|
|
"num_tokens": 14384901.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.189097356796265,
|
|
"epoch": 0.6140559857057772,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000497220536304306,
|
|
"loss": 4.9478,
|
|
"mean_token_accuracy": 0.20562216341495515,
|
|
"num_tokens": 14397740.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.256771373748779,
|
|
"epoch": 0.6146515783204288,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004972138550754405,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.18695269525051117,
|
|
"num_tokens": 14412850.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.381332540512085,
|
|
"epoch": 0.6152471709350804,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004972071658761254,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.18321346193552018,
|
|
"num_tokens": 14426174.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.302031946182251,
|
|
"epoch": 0.615842763549732,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004972004687066005,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.18186050206422805,
|
|
"num_tokens": 14442736.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.3441712856292725,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004971937635671061,
|
|
"loss": 5.0935,
|
|
"mean_token_accuracy": 0.18732459098100662,
|
|
"num_tokens": 14459631.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.242708492279053,
|
|
"epoch": 0.6170339487790352,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004971870504578825,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.18648074120283126,
|
|
"num_tokens": 14472896.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.267556381225586,
|
|
"epoch": 0.6176295413936868,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004971803293791708,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.18363955169916152,
|
|
"num_tokens": 14487959.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.18598747253418,
|
|
"epoch": 0.6182251340083383,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004971736003312119,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.19469079971313477,
|
|
"num_tokens": 14501420.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.267638111114502,
|
|
"epoch": 0.6188207266229899,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004971668633142472,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.1950201004743576,
|
|
"num_tokens": 14514800.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.339569902420044,
|
|
"epoch": 0.6194163192376414,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004971601183285183,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.179900361597538,
|
|
"num_tokens": 14530254.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.37944450378418,
|
|
"epoch": 0.620011911852293,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004971533653742672,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.18368457555770873,
|
|
"num_tokens": 14545635.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.2463775157928465,
|
|
"epoch": 0.6206075044669446,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000497146604451736,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.18645368814468383,
|
|
"num_tokens": 14558672.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.190332317352295,
|
|
"epoch": 0.6212030970815962,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004971398355611674,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.18812876641750337,
|
|
"num_tokens": 14571706.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.313739013671875,
|
|
"epoch": 0.6217986896962477,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000497133058702804,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.188061685860157,
|
|
"num_tokens": 14584732.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.291232872009277,
|
|
"epoch": 0.6223942823108993,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000497126273876889,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.192041277885437,
|
|
"num_tokens": 14598883.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.287946081161499,
|
|
"epoch": 0.6229898749255509,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004971194810836657,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.18967678099870683,
|
|
"num_tokens": 14613202.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.373216342926026,
|
|
"epoch": 0.6235854675402025,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004971126803233778,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.18106554299592972,
|
|
"num_tokens": 14627267.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.30979814529419,
|
|
"epoch": 0.6241810601548541,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004971058715962691,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.18988630026578904,
|
|
"num_tokens": 14640300.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.2569245338439945,
|
|
"epoch": 0.6247766527695057,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000497099054902584,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.18281649351119994,
|
|
"num_tokens": 14655029.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.354593801498413,
|
|
"epoch": 0.6253722453841573,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004970922302425669,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.1874535173177719,
|
|
"num_tokens": 14669321.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.25976824760437,
|
|
"epoch": 0.6259678379988088,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004970853976164624,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.1960184618830681,
|
|
"num_tokens": 14682280.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.311201000213623,
|
|
"epoch": 0.6265634306134604,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497078557024516,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.19802143275737763,
|
|
"num_tokens": 14693761.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.290307664871216,
|
|
"epoch": 0.627159023228112,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004970717084669728,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.18947107195854188,
|
|
"num_tokens": 14706024.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.285837936401367,
|
|
"epoch": 0.6277546158427636,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004970648519440785,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.18500043004751204,
|
|
"num_tokens": 14721273.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.261366844177246,
|
|
"epoch": 0.6283502084574152,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004970579874560789,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.18455203920602797,
|
|
"num_tokens": 14737033.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.290789270401001,
|
|
"epoch": 0.6289458010720667,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004970511150032205,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.18884081691503524,
|
|
"num_tokens": 14751881.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.2421314239501955,
|
|
"epoch": 0.6295413936867182,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004970442345857495,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.19180212765932084,
|
|
"num_tokens": 14764866.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.350847816467285,
|
|
"epoch": 0.6301369863013698,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970373462039128,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.18925783634185792,
|
|
"num_tokens": 14777703.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.267268657684326,
|
|
"epoch": 0.6307325789160214,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004970304498579576,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.1927807718515396,
|
|
"num_tokens": 14792819.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.169047403335571,
|
|
"epoch": 0.631328171530673,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004970235455481312,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.19723652452230453,
|
|
"num_tokens": 14806612.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.247286987304688,
|
|
"epoch": 0.6319237641453246,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970166332746811,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.19824519753456116,
|
|
"num_tokens": 14820313.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.355741500854492,
|
|
"epoch": 0.6325193567599762,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004970097130378554,
|
|
"loss": 5.1174,
|
|
"mean_token_accuracy": 0.18773682564496993,
|
|
"num_tokens": 14832874.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.289426946640015,
|
|
"epoch": 0.6331149493746278,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004970027848379023,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.19114599972963334,
|
|
"num_tokens": 14845021.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.298947954177857,
|
|
"epoch": 0.6337105419892793,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004969958486750702,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.1900929629802704,
|
|
"num_tokens": 14860928.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.34732232093811,
|
|
"epoch": 0.6343061346039309,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000496988904549608,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.19776032269001007,
|
|
"num_tokens": 14874709.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.3082374095916744,
|
|
"epoch": 0.6349017272185825,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004969819524617647,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.17894596755504608,
|
|
"num_tokens": 14888323.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.2797017097473145,
|
|
"epoch": 0.6354973198332341,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004969749924117896,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.18447374701499938,
|
|
"num_tokens": 14901410.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.29444522857666,
|
|
"epoch": 0.6360929124478857,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004969680243999325,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.18881284892559053,
|
|
"num_tokens": 14915335.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.311003971099853,
|
|
"epoch": 0.6366885050625373,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004969610484264433,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.18364232033491135,
|
|
"num_tokens": 14931549.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.238314485549926,
|
|
"epoch": 0.6372840976771889,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004969540644915721,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.19179584830999374,
|
|
"num_tokens": 14943745.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.326440286636353,
|
|
"epoch": 0.6378796902918403,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004969470725955695,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.18694547563791275,
|
|
"num_tokens": 14957662.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.326256608963012,
|
|
"epoch": 0.6384752829064919,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004969400727386864,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.17875856012105942,
|
|
"num_tokens": 14970175.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.280163526535034,
|
|
"epoch": 0.6390708755211435,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969330649211737,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.1831430658698082,
|
|
"num_tokens": 14983901.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.398005485534668,
|
|
"epoch": 0.6396664681357951,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969260491432826,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.18423172682523728,
|
|
"num_tokens": 14997637.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.2718092918396,
|
|
"epoch": 0.6402620607504467,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004969190254052651,
|
|
"loss": 5.0848,
|
|
"mean_token_accuracy": 0.17836270332336426,
|
|
"num_tokens": 15014576.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.318856954574585,
|
|
"epoch": 0.6408576533650983,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004969119937073731,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.1834678590297699,
|
|
"num_tokens": 15031049.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.252246952056884,
|
|
"epoch": 0.6414532459797498,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004969049540498585,
|
|
"loss": 5.0394,
|
|
"mean_token_accuracy": 0.19357677698135375,
|
|
"num_tokens": 15044632.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.193923044204712,
|
|
"epoch": 0.6420488385944014,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004968979064329741,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.1925104796886444,
|
|
"num_tokens": 15057500.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.325106143951416,
|
|
"epoch": 0.642644431209053,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004968908508569725,
|
|
"loss": 5.0942,
|
|
"mean_token_accuracy": 0.1867637261748314,
|
|
"num_tokens": 15070994.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.222676134109497,
|
|
"epoch": 0.6432400238237046,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004968837873221069,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.18503739386796952,
|
|
"num_tokens": 15085824.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.247950220108033,
|
|
"epoch": 0.6438356164383562,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004968767158286306,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.1901594191789627,
|
|
"num_tokens": 15101263.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.292113304138184,
|
|
"epoch": 0.6444312090530078,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004968696363767972,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.19729039520025254,
|
|
"num_tokens": 15113830.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.347804546356201,
|
|
"epoch": 0.6450268016676594,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004968625489668607,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.1861426681280136,
|
|
"num_tokens": 15128427.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.265256357192993,
|
|
"epoch": 0.6456223942823109,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004968554535990754,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.19307721257209778,
|
|
"num_tokens": 15143790.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.248657321929931,
|
|
"epoch": 0.6462179868969625,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004968483502736956,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.18485984057188035,
|
|
"num_tokens": 15157533.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.243309164047242,
|
|
"epoch": 0.646813579511614,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004968412389909762,
|
|
"loss": 4.9828,
|
|
"mean_token_accuracy": 0.18990262001752853,
|
|
"num_tokens": 15172164.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.27074031829834,
|
|
"epoch": 0.6474091721262656,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968341197511722,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.19355926513671876,
|
|
"num_tokens": 15184334.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.2285261154174805,
|
|
"epoch": 0.6480047647409172,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004968269925545391,
|
|
"loss": 5.0277,
|
|
"mean_token_accuracy": 0.19238440245389937,
|
|
"num_tokens": 15198783.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.251455545425415,
|
|
"epoch": 0.6486003573555688,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004968198574013323,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.19222124367952348,
|
|
"num_tokens": 15214153.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.342940473556519,
|
|
"epoch": 0.6491959499702203,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004968127142918081,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.182593996822834,
|
|
"num_tokens": 15229029.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.288835668563843,
|
|
"epoch": 0.6497915425848719,
|
|
"grad_norm": 0.75,
|
|
"learning_rate": 0.0004968055632262223,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.18840956687927246,
|
|
"num_tokens": 15244724.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.281258916854858,
|
|
"epoch": 0.6503871351995235,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004967984042048317,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.1861490324139595,
|
|
"num_tokens": 15258703.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.377297496795654,
|
|
"epoch": 0.6509827278141751,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004967912372278928,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.1820966199040413,
|
|
"num_tokens": 15272281.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.267626237869263,
|
|
"epoch": 0.6515783204288267,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000496784062295663,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.18922995030879974,
|
|
"num_tokens": 15286657.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.299370670318604,
|
|
"epoch": 0.6521739130434783,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004967768794083994,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.19198830276727677,
|
|
"num_tokens": 15300416.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.278030681610107,
|
|
"epoch": 0.6527695056581299,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967696885663597,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.19082478880882264,
|
|
"num_tokens": 15313945.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.1918495178222654,
|
|
"epoch": 0.6533650982727814,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000496762489769802,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.19632806479930878,
|
|
"num_tokens": 15328995.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.264467096328735,
|
|
"epoch": 0.653960690887433,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004967552830189842,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.19462988376617432,
|
|
"num_tokens": 15342588.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.273479700088501,
|
|
"epoch": 0.6545562835020846,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004967480683141651,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.1963807076215744,
|
|
"num_tokens": 15357411.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.181907033920288,
|
|
"epoch": 0.6551518761167362,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000496740845655603,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.19349863082170488,
|
|
"num_tokens": 15371968.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.25212516784668,
|
|
"epoch": 0.6557474687313878,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004967336150435576,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.18986750096082688,
|
|
"num_tokens": 15387186.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.244566965103149,
|
|
"epoch": 0.6563430613460393,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967263764782878,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.19642722457647324,
|
|
"num_tokens": 15398842.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.2688453674316404,
|
|
"epoch": 0.6569386539606908,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004967191299600535,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.18934263586997985,
|
|
"num_tokens": 15411687.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.168119478225708,
|
|
"epoch": 0.6575342465753424,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004967118754891144,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.1981848046183586,
|
|
"num_tokens": 15425868.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.321026134490967,
|
|
"epoch": 0.658129839189994,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004967046130657309,
|
|
"loss": 5.1337,
|
|
"mean_token_accuracy": 0.1804911270737648,
|
|
"num_tokens": 15439489.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.332544374465942,
|
|
"epoch": 0.6587254318046456,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004966973426901634,
|
|
"loss": 5.1222,
|
|
"mean_token_accuracy": 0.1913837358355522,
|
|
"num_tokens": 15453067.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.206445837020874,
|
|
"epoch": 0.6593210244192972,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004966900643626726,
|
|
"loss": 4.9598,
|
|
"mean_token_accuracy": 0.19637186974287033,
|
|
"num_tokens": 15465357.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.243476390838623,
|
|
"epoch": 0.6599166170339488,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004966827780835197,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.19123535752296447,
|
|
"num_tokens": 15479657.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.493918085098267,
|
|
"epoch": 0.6605122096486004,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004966754838529659,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.17709000259637833,
|
|
"num_tokens": 15495245.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.294262027740478,
|
|
"epoch": 0.6611078022632519,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000496668181671273,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.1921727776527405,
|
|
"num_tokens": 15507788.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.233879947662354,
|
|
"epoch": 0.6617033948779035,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004966608715387029,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.18628320395946502,
|
|
"num_tokens": 15521970.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.285766077041626,
|
|
"epoch": 0.6622989874925551,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004966535534555175,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.19533409029245377,
|
|
"num_tokens": 15534720.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.264064073562622,
|
|
"epoch": 0.6628945801072067,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004966462274219797,
|
|
"loss": 5.0938,
|
|
"mean_token_accuracy": 0.18742941617965697,
|
|
"num_tokens": 15549345.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.321471405029297,
|
|
"epoch": 0.6634901727218583,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000496638893438352,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.18999270498752593,
|
|
"num_tokens": 15562838.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.336755752563477,
|
|
"epoch": 0.6640857653365099,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004966315515048977,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.19182344526052475,
|
|
"num_tokens": 15575044.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.238848161697388,
|
|
"epoch": 0.6646813579511615,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004966242016218799,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.1946866512298584,
|
|
"num_tokens": 15591912.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.306922769546508,
|
|
"epoch": 0.6652769505658129,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004966168437895624,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.18743124455213547,
|
|
"num_tokens": 15606903.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.236415243148803,
|
|
"epoch": 0.6658725431804645,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004966094780082089,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.1967455968260765,
|
|
"num_tokens": 15620885.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.322501182556152,
|
|
"epoch": 0.6664681357951161,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004966021042780837,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.18818866908550264,
|
|
"num_tokens": 15634927.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.264331865310669,
|
|
"epoch": 0.6670637284097677,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004965947225994516,
|
|
"loss": 5.0727,
|
|
"mean_token_accuracy": 0.19072187840938568,
|
|
"num_tokens": 15649369.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.269458532333374,
|
|
"epoch": 0.6676593210244193,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004965873329725769,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.17978961020708084,
|
|
"num_tokens": 15665288.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.2741748809814455,
|
|
"epoch": 0.6682549136390709,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004965799353977248,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.19320162683725356,
|
|
"num_tokens": 15679117.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.208561372756958,
|
|
"epoch": 0.6688505062537224,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004965725298751608,
|
|
"loss": 4.9435,
|
|
"mean_token_accuracy": 0.2003881424665451,
|
|
"num_tokens": 15692177.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.3116758346557615,
|
|
"epoch": 0.669446098868374,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004965651164051504,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.200613334774971,
|
|
"num_tokens": 15706047.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.258336973190308,
|
|
"epoch": 0.6700416914830256,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004965576949879594,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.1864259272813797,
|
|
"num_tokens": 15721191.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.295834875106811,
|
|
"epoch": 0.6706372840976772,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004965502656238543,
|
|
"loss": 5.0764,
|
|
"mean_token_accuracy": 0.18373899459838866,
|
|
"num_tokens": 15735569.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.247524690628052,
|
|
"epoch": 0.6712328767123288,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004965428283131013,
|
|
"loss": 4.995,
|
|
"mean_token_accuracy": 0.195026995241642,
|
|
"num_tokens": 15749125.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.207850217819214,
|
|
"epoch": 0.6718284693269804,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004965353830559671,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.1935933068394661,
|
|
"num_tokens": 15765641.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.307414150238037,
|
|
"epoch": 0.672424061941632,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004965279298527192,
|
|
"loss": 5.0948,
|
|
"mean_token_accuracy": 0.18444264382123948,
|
|
"num_tokens": 15780816.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.3150101661682125,
|
|
"epoch": 0.6730196545562835,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004965204687036244,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.1835220530629158,
|
|
"num_tokens": 15795123.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.253581762313843,
|
|
"epoch": 0.6736152471709351,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004965129996089507,
|
|
"loss": 5.025,
|
|
"mean_token_accuracy": 0.19557120501995087,
|
|
"num_tokens": 15808428.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.321144390106201,
|
|
"epoch": 0.6742108397855867,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004965055225689658,
|
|
"loss": 5.1503,
|
|
"mean_token_accuracy": 0.1824200063943863,
|
|
"num_tokens": 15820618.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.266052722930908,
|
|
"epoch": 0.6748064324002382,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004964980375839379,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.19926946461200715,
|
|
"num_tokens": 15833431.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.252100610733033,
|
|
"epoch": 0.6754020250148898,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964905446541355,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.199505116045475,
|
|
"num_tokens": 15845629.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.331709337234497,
|
|
"epoch": 0.6759976176295414,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964830437798276,
|
|
"loss": 5.1027,
|
|
"mean_token_accuracy": 0.1810487002134323,
|
|
"num_tokens": 15859464.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.2029050350189205,
|
|
"epoch": 0.6765932102441929,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004964755349612829,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.20364129096269606,
|
|
"num_tokens": 15873207.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.273396635055542,
|
|
"epoch": 0.6771888028588445,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004964680181987709,
|
|
"loss": 5.0447,
|
|
"mean_token_accuracy": 0.1895923063158989,
|
|
"num_tokens": 15888856.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.222301054000854,
|
|
"epoch": 0.6777843954734961,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000496460493492561,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.19774415493011474,
|
|
"num_tokens": 15901841.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.279787015914917,
|
|
"epoch": 0.6783799880881477,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004964529608429234,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.19503959864377976,
|
|
"num_tokens": 15914960.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.192133903503418,
|
|
"epoch": 0.6789755807027993,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004964454202501282,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.19498180598020554,
|
|
"num_tokens": 15929466.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.32805323600769,
|
|
"epoch": 0.6795711733174509,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004964378717144458,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.18622483164072037,
|
|
"num_tokens": 15943934.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.2692914485931395,
|
|
"epoch": 0.6801667659321025,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496430315236147,
|
|
"loss": 5.0523,
|
|
"mean_token_accuracy": 0.1980827271938324,
|
|
"num_tokens": 15956214.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.258679342269898,
|
|
"epoch": 0.680762358546754,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004964227508155027,
|
|
"loss": 5.0085,
|
|
"mean_token_accuracy": 0.18469200581312178,
|
|
"num_tokens": 15970943.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.295328521728516,
|
|
"epoch": 0.6813579511614056,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004964151784527844,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.18483902513980865,
|
|
"num_tokens": 15985539.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.233646202087402,
|
|
"epoch": 0.6819535437760572,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964075981482637,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.20117942094802857,
|
|
"num_tokens": 15998622.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.227403926849365,
|
|
"epoch": 0.6825491363907088,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004964000099022124,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.1949496239423752,
|
|
"num_tokens": 16013820.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.376773118972778,
|
|
"epoch": 0.6831447290053604,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963924137149027,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.18095397502183913,
|
|
"num_tokens": 16026615.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.308851432800293,
|
|
"epoch": 0.6837403216200119,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004963848095866072,
|
|
"loss": 5.0875,
|
|
"mean_token_accuracy": 0.1890351504087448,
|
|
"num_tokens": 16039921.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.132941818237304,
|
|
"epoch": 0.6843359142346634,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004963771975175984,
|
|
"loss": 4.9211,
|
|
"mean_token_accuracy": 0.2011510670185089,
|
|
"num_tokens": 16054790.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.212114048004151,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004963695775081495,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.18952561020851136,
|
|
"num_tokens": 16069778.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.220016288757324,
|
|
"epoch": 0.6855270994639666,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004963619495585338,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.19416166692972184,
|
|
"num_tokens": 16086472.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.274522066116333,
|
|
"epoch": 0.6861226920786182,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004963543136690247,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.18789082020521164,
|
|
"num_tokens": 16100743.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.210842180252075,
|
|
"epoch": 0.6867182846932698,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004963466698398965,
|
|
"loss": 4.99,
|
|
"mean_token_accuracy": 0.19347046613693236,
|
|
"num_tokens": 16114894.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.2474284172058105,
|
|
"epoch": 0.6873138773079214,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004963390180714231,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.1936781108379364,
|
|
"num_tokens": 16129232.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.267042016983032,
|
|
"epoch": 0.687909469922573,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000496331358363879,
|
|
"loss": 4.9404,
|
|
"mean_token_accuracy": 0.19571829587221146,
|
|
"num_tokens": 16142983.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.263561630249024,
|
|
"epoch": 0.6885050625372245,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004963236907175388,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.1890594929456711,
|
|
"num_tokens": 16157195.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.225505447387695,
|
|
"epoch": 0.6891006551518761,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004963160151326778,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.19163466840982438,
|
|
"num_tokens": 16171240.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.329293966293335,
|
|
"epoch": 0.6896962477665277,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004963083316095712,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.18515958338975907,
|
|
"num_tokens": 16186313.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.2782454013824465,
|
|
"epoch": 0.6902918403811793,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963006401484945,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.1855359449982643,
|
|
"num_tokens": 16201394.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.19909086227417,
|
|
"epoch": 0.6908874329958309,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004962929407497236,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.1956307038664818,
|
|
"num_tokens": 16214917.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.249820423126221,
|
|
"epoch": 0.6914830256104825,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004962852334135348,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.19452162235975265,
|
|
"num_tokens": 16228700.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.205440425872803,
|
|
"epoch": 0.6920786182251341,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004962775181402044,
|
|
"loss": 4.8974,
|
|
"mean_token_accuracy": 0.2022468104958534,
|
|
"num_tokens": 16240262.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.207813882827759,
|
|
"epoch": 0.6926742108397855,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004962697949300093,
|
|
"loss": 4.9595,
|
|
"mean_token_accuracy": 0.19471850842237473,
|
|
"num_tokens": 16254830.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.2083488464355465,
|
|
"epoch": 0.6932698034544371,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004962620637832263,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.20220405906438826,
|
|
"num_tokens": 16267547.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.215187120437622,
|
|
"epoch": 0.6938653960690887,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004962543247001329,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.19601463228464128,
|
|
"num_tokens": 16281223.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.276646423339844,
|
|
"epoch": 0.6944609886837403,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004962465776810066,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.19119674265384673,
|
|
"num_tokens": 16295366.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.312460851669312,
|
|
"epoch": 0.6950565812983919,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004962388227261253,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.19316454082727433,
|
|
"num_tokens": 16310081.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.319116258621216,
|
|
"epoch": 0.6956521739130435,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004962310598357672,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.1877794086933136,
|
|
"num_tokens": 16324544.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.33834228515625,
|
|
"epoch": 0.696247766527695,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004962232890102106,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.19095985144376754,
|
|
"num_tokens": 16339128.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.22356948852539,
|
|
"epoch": 0.6968433591423466,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004962155102497342,
|
|
"loss": 4.9871,
|
|
"mean_token_accuracy": 0.19575985372066498,
|
|
"num_tokens": 16351997.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.213065338134766,
|
|
"epoch": 0.6974389517569982,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004962077235546173,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.19867926388978957,
|
|
"num_tokens": 16365075.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.195607900619507,
|
|
"epoch": 0.6980345443716498,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004961999289251389,
|
|
"loss": 4.9964,
|
|
"mean_token_accuracy": 0.20640301406383516,
|
|
"num_tokens": 16378635.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.243032693862915,
|
|
"epoch": 0.6986301369863014,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004961921263615788,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.2027442216873169,
|
|
"num_tokens": 16392224.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.192925024032593,
|
|
"epoch": 0.699225729600953,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004961843158642167,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.1963099405169487,
|
|
"num_tokens": 16407830.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.177820110321045,
|
|
"epoch": 0.6998213222156046,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004961764974333328,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.19690936654806138,
|
|
"num_tokens": 16421576.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.304880428314209,
|
|
"epoch": 0.7004169148302561,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004961686710692076,
|
|
"loss": 5.0777,
|
|
"mean_token_accuracy": 0.19389348328113556,
|
|
"num_tokens": 16436548.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.251643657684326,
|
|
"epoch": 0.7010125074449077,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004961608367721217,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.18878477513790132,
|
|
"num_tokens": 16451435.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.276120376586914,
|
|
"epoch": 0.7016081000595593,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004961529945423563,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.18928759694099426,
|
|
"num_tokens": 16465786.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.289232349395752,
|
|
"epoch": 0.7022036926742108,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004961451443801924,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.19101280570030213,
|
|
"num_tokens": 16479832.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.247342538833618,
|
|
"epoch": 0.7027992852888624,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004961372862859119,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.20071283727884293,
|
|
"num_tokens": 16491824.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.236342191696167,
|
|
"epoch": 0.703394877903514,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004961294202597962,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.19119400382041932,
|
|
"num_tokens": 16507273.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.228244638442993,
|
|
"epoch": 0.7039904705181655,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004961215463021281,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.19366009831428527,
|
|
"num_tokens": 16521041.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.254487085342407,
|
|
"epoch": 0.7045860631328171,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004961136644131894,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.19704702645540237,
|
|
"num_tokens": 16534837.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.276070165634155,
|
|
"epoch": 0.7051816557474687,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004961057745932633,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.19341509640216828,
|
|
"num_tokens": 16549183.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.21911768913269,
|
|
"epoch": 0.7057772483621203,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004960978768426323,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.19222921878099442,
|
|
"num_tokens": 16562044.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.298666048049927,
|
|
"epoch": 0.7063728409767719,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00049608997116158,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.18796951174736024,
|
|
"num_tokens": 16577014.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.270325613021851,
|
|
"epoch": 0.7069684335914235,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00049608205755039,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.20204018503427507,
|
|
"num_tokens": 16588289.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.223482847213745,
|
|
"epoch": 0.7075640262060751,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004960741360093459,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.18865396380424498,
|
|
"num_tokens": 16602433.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.341929197311401,
|
|
"epoch": 0.7081596188207266,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004960662065387322,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.18707696944475175,
|
|
"num_tokens": 16618178.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.338521909713745,
|
|
"epoch": 0.7087552114353782,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000496058269138833,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.1945318728685379,
|
|
"num_tokens": 16634090.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.198310232162475,
|
|
"epoch": 0.7093508040500298,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004960503238099331,
|
|
"loss": 4.9443,
|
|
"mean_token_accuracy": 0.2026712641119957,
|
|
"num_tokens": 16646713.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.215253162384033,
|
|
"epoch": 0.7099463966646814,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004960423705523175,
|
|
"loss": 4.978,
|
|
"mean_token_accuracy": 0.19276022166013718,
|
|
"num_tokens": 16659172.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.26342282295227,
|
|
"epoch": 0.710541989279333,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004960344093662714,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.19340185225009918,
|
|
"num_tokens": 16672592.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.262936353683472,
|
|
"epoch": 0.7111375818939845,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004960264402520804,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.1867918014526367,
|
|
"num_tokens": 16687026.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.22091760635376,
|
|
"epoch": 0.711733174508636,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004960184632100304,
|
|
"loss": 4.9209,
|
|
"mean_token_accuracy": 0.20684377402067183,
|
|
"num_tokens": 16699489.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.23095293045044,
|
|
"epoch": 0.7123287671232876,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004960104782404075,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.19487977474927903,
|
|
"num_tokens": 16713821.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.319440698623657,
|
|
"epoch": 0.7129243597379392,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004960024853434982,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.19367949813604354,
|
|
"num_tokens": 16727271.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.274638319015503,
|
|
"epoch": 0.7135199523525908,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000495994484519589,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.19416755437850952,
|
|
"num_tokens": 16740387.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.193914413452148,
|
|
"epoch": 0.7141155449672424,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004959864757689669,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.19212597757577896,
|
|
"num_tokens": 16756131.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.207724571228027,
|
|
"epoch": 0.714711137581894,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004959784590919192,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.19890668988227844,
|
|
"num_tokens": 16768781.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.714711137581894,
|
|
"eval_entropy": 5.041748077368662,
|
|
"eval_loss": 4.973918437957764,
|
|
"eval_mean_token_accuracy": 0.20530051143845796,
|
|
"eval_num_tokens": 16768781.0,
|
|
"eval_runtime": 18.4319,
|
|
"eval_samples_per_second": 1384.175,
|
|
"eval_steps_per_second": 173.069,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.313890695571899,
|
|
"epoch": 0.7153067301965456,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004959704344887335,
|
|
"loss": 5.0547,
|
|
"mean_token_accuracy": 0.19012281596660613,
|
|
"num_tokens": 16782933.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.245557260513306,
|
|
"epoch": 0.7159023228111971,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004959624019596976,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.1960408493876457,
|
|
"num_tokens": 16795999.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.287603378295898,
|
|
"epoch": 0.7164979154258487,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004959543615050996,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.19529915750026702,
|
|
"num_tokens": 16809042.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.256368827819824,
|
|
"epoch": 0.7170935080405003,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004959463131252278,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.19385978281497956,
|
|
"num_tokens": 16820896.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.2617021083831785,
|
|
"epoch": 0.7176891006551519,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004959382568203711,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.1864404559135437,
|
|
"num_tokens": 16834418.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.193333339691162,
|
|
"epoch": 0.7182846932698035,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004959301925908184,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.197181998193264,
|
|
"num_tokens": 16848818.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.2972633838653564,
|
|
"epoch": 0.7188802858844551,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004959221204368588,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.1941531479358673,
|
|
"num_tokens": 16863145.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.255667781829834,
|
|
"epoch": 0.7194758784991067,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004959140403587819,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.18803129494190216,
|
|
"num_tokens": 16876342.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.247892236709594,
|
|
"epoch": 0.7200714711137582,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004959059523568778,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.18704271614551543,
|
|
"num_tokens": 16892113.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.346061420440674,
|
|
"epoch": 0.7206670637284097,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004958978564314361,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.19460833668708802,
|
|
"num_tokens": 16906103.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.216146469116211,
|
|
"epoch": 0.7212626563430613,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004958897525827476,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.19465346932411193,
|
|
"num_tokens": 16921655.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.22554497718811,
|
|
"epoch": 0.7218582489577129,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004958816408111027,
|
|
"loss": 5.01,
|
|
"mean_token_accuracy": 0.19605536311864852,
|
|
"num_tokens": 16936143.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.190352439880371,
|
|
"epoch": 0.7224538415723645,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004958735211167926,
|
|
"loss": 4.9861,
|
|
"mean_token_accuracy": 0.19656968861818314,
|
|
"num_tokens": 16950232.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.229558610916138,
|
|
"epoch": 0.7230494341870161,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004958653935001083,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.19739560633897782,
|
|
"num_tokens": 16963407.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.223942565917969,
|
|
"epoch": 0.7236450268016676,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004958572579613415,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.1986496478319168,
|
|
"num_tokens": 16975758.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.257091808319092,
|
|
"epoch": 0.7242406194163192,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000495849114500784,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.19636190682649612,
|
|
"num_tokens": 16989496.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.25351128578186,
|
|
"epoch": 0.7248362120309708,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004958409631187278,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.19271715730428696,
|
|
"num_tokens": 17002790.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.276073551177978,
|
|
"epoch": 0.7254318046456224,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004958328038154652,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.19676563739776612,
|
|
"num_tokens": 17016384.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.251778507232666,
|
|
"epoch": 0.726027397260274,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004958246365912891,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.20254836678504945,
|
|
"num_tokens": 17031331.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.26299295425415,
|
|
"epoch": 0.7266229898749256,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004958164614464923,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.19192450046539306,
|
|
"num_tokens": 17043820.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.175413322448731,
|
|
"epoch": 0.7272185824895772,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.20446360409259795,
|
|
"num_tokens": 17057826.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.216018772125244,
|
|
"epoch": 0.7278141751042287,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004958000873962099,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.19328736513853073,
|
|
"num_tokens": 17073410.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.251501369476318,
|
|
"epoch": 0.7284097677188803,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004957918884913115,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.196573606133461,
|
|
"num_tokens": 17086705.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.286893653869629,
|
|
"epoch": 0.7290053603335319,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004957836816669672,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.189536888897419,
|
|
"num_tokens": 17100787.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.22686071395874,
|
|
"epoch": 0.7296009529481834,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004957754669234711,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.19498735964298247,
|
|
"num_tokens": 17116381.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.126053810119629,
|
|
"epoch": 0.730196545562835,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495767244261118,
|
|
"loss": 4.9443,
|
|
"mean_token_accuracy": 0.20307367891073227,
|
|
"num_tokens": 17129214.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.298078346252441,
|
|
"epoch": 0.7307921381774866,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004957590136802028,
|
|
"loss": 5.0643,
|
|
"mean_token_accuracy": 0.19485459327697754,
|
|
"num_tokens": 17143033.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.220994138717652,
|
|
"epoch": 0.7313877307921381,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004957507751810207,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.19101704359054567,
|
|
"num_tokens": 17156325.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.253524208068848,
|
|
"epoch": 0.7319833234067897,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004957425287638673,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.19157552272081374,
|
|
"num_tokens": 17173031.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.236788988113403,
|
|
"epoch": 0.7325789160214413,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004957342744290381,
|
|
"loss": 5.0082,
|
|
"mean_token_accuracy": 0.19147226065397263,
|
|
"num_tokens": 17186579.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.151167106628418,
|
|
"epoch": 0.7331745086360929,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004957260121768296,
|
|
"loss": 4.9148,
|
|
"mean_token_accuracy": 0.2050897017121315,
|
|
"num_tokens": 17200987.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.236871671676636,
|
|
"epoch": 0.7337701012507445,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004957177420075377,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.2020905628800392,
|
|
"num_tokens": 17215429.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.1915594100952145,
|
|
"epoch": 0.7343656938653961,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004957094639214594,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.20174178034067153,
|
|
"num_tokens": 17229460.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.2357635498046875,
|
|
"epoch": 0.7349612864800477,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004957011779188915,
|
|
"loss": 5.0043,
|
|
"mean_token_accuracy": 0.19210758209228515,
|
|
"num_tokens": 17243399.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.147185516357422,
|
|
"epoch": 0.7355568790946992,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004956928840001312,
|
|
"loss": 4.8905,
|
|
"mean_token_accuracy": 0.19683880358934402,
|
|
"num_tokens": 17258028.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.147904920578003,
|
|
"epoch": 0.7361524717093508,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004956845821654758,
|
|
"loss": 4.9116,
|
|
"mean_token_accuracy": 0.20454588979482652,
|
|
"num_tokens": 17271666.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.288060283660888,
|
|
"epoch": 0.7367480643240024,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004956762724152234,
|
|
"loss": 5.0545,
|
|
"mean_token_accuracy": 0.18782139718532562,
|
|
"num_tokens": 17285423.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.268111848831177,
|
|
"epoch": 0.737343656938654,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004956679547496719,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.18980278819799423,
|
|
"num_tokens": 17299134.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.279369449615478,
|
|
"epoch": 0.7379392495533056,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004956596291691197,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.19268375486135483,
|
|
"num_tokens": 17311835.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.285842561721802,
|
|
"epoch": 0.7385348421679571,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004956512956738652,
|
|
"loss": 5.0419,
|
|
"mean_token_accuracy": 0.19235637187957763,
|
|
"num_tokens": 17324943.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.262370586395264,
|
|
"epoch": 0.7391304347826086,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004956429542642075,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.18325200974941253,
|
|
"num_tokens": 17339710.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.312359094619751,
|
|
"epoch": 0.7397260273972602,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004956346049404459,
|
|
"loss": 5.0306,
|
|
"mean_token_accuracy": 0.1959820106625557,
|
|
"num_tokens": 17353391.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.228341674804687,
|
|
"epoch": 0.7403216200119118,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004956262477028797,
|
|
"loss": 5.0193,
|
|
"mean_token_accuracy": 0.19141646027565,
|
|
"num_tokens": 17367811.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.218722677230835,
|
|
"epoch": 0.7409172126265634,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004956178825518087,
|
|
"loss": 5.0212,
|
|
"mean_token_accuracy": 0.1960410565137863,
|
|
"num_tokens": 17380323.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.2607005596160885,
|
|
"epoch": 0.741512805241215,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004956095094875329,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.20446429401636124,
|
|
"num_tokens": 17394650.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.250370121002197,
|
|
"epoch": 0.7421083978558666,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004956011285103528,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.200028432905674,
|
|
"num_tokens": 17408461.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.27189884185791,
|
|
"epoch": 0.7427039904705182,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004955927396205689,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.19704937934875488,
|
|
"num_tokens": 17422086.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.236105060577392,
|
|
"epoch": 0.7432995830851697,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000495584342818482,
|
|
"loss": 4.9871,
|
|
"mean_token_accuracy": 0.2036873757839203,
|
|
"num_tokens": 17436845.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.155274391174316,
|
|
"epoch": 0.7438951756998213,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004955759381043934,
|
|
"loss": 4.9151,
|
|
"mean_token_accuracy": 0.1985413044691086,
|
|
"num_tokens": 17451783.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.350344467163086,
|
|
"epoch": 0.7444907683144729,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004955675254786045,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.17879049181938172,
|
|
"num_tokens": 17466310.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.228491020202637,
|
|
"epoch": 0.7450863609291245,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004955591049414171,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.19769092053174972,
|
|
"num_tokens": 17481595.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.253096199035644,
|
|
"epoch": 0.7456819535437761,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004955506764931332,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.1991863414645195,
|
|
"num_tokens": 17496947.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.242966365814209,
|
|
"epoch": 0.7462775461584277,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004955422401340553,
|
|
"loss": 4.9382,
|
|
"mean_token_accuracy": 0.19870818108320237,
|
|
"num_tokens": 17509772.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.208853530883789,
|
|
"epoch": 0.7468731387730793,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004955337958644857,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.19495915174484252,
|
|
"num_tokens": 17522819.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.236962175369262,
|
|
"epoch": 0.7474687313877308,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004955253436847273,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.19658604264259338,
|
|
"num_tokens": 17536524.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.224010848999024,
|
|
"epoch": 0.7480643240023823,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004955168835950835,
|
|
"loss": 4.965,
|
|
"mean_token_accuracy": 0.19878460019826888,
|
|
"num_tokens": 17549033.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.223360919952393,
|
|
"epoch": 0.7486599166170339,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004955084155958576,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.1960088223218918,
|
|
"num_tokens": 17562615.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.1995251178741455,
|
|
"epoch": 0.7492555092316855,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004954999396873534,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.19340447187423707,
|
|
"num_tokens": 17576388.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.204186201095581,
|
|
"epoch": 0.7498511018463371,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004954914558698748,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.20574136227369308,
|
|
"num_tokens": 17588275.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.183174133300781,
|
|
"epoch": 0.7504466944609887,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004954829641437261,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.19972068816423416,
|
|
"num_tokens": 17601534.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.244009494781494,
|
|
"epoch": 0.7510422870756402,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004954744645092121,
|
|
"loss": 4.9624,
|
|
"mean_token_accuracy": 0.19543291330337526,
|
|
"num_tokens": 17614801.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.238858222961426,
|
|
"epoch": 0.7516378796902918,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004954659569666375,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.20598389208316803,
|
|
"num_tokens": 17628056.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.162618732452392,
|
|
"epoch": 0.7522334723049434,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004954574415163075,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.19398632645606995,
|
|
"num_tokens": 17642676.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.220286798477173,
|
|
"epoch": 0.752829064919595,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004954489181585275,
|
|
"loss": 4.9645,
|
|
"mean_token_accuracy": 0.19994464963674546,
|
|
"num_tokens": 17655911.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.236740589141846,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004954403868936032,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.1934132069349289,
|
|
"num_tokens": 17669386.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.288609838485717,
|
|
"epoch": 0.7540202501488982,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004954318477218406,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.19728015661239623,
|
|
"num_tokens": 17683426.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.356310319900513,
|
|
"epoch": 0.7546158427635498,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000495423300643546,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.18000272214412688,
|
|
"num_tokens": 17697188.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.24656047821045,
|
|
"epoch": 0.7552114353782013,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004954147456590262,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.19575938135385512,
|
|
"num_tokens": 17711302.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.274896335601807,
|
|
"epoch": 0.7558070279928529,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004954061827685877,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.1991220235824585,
|
|
"num_tokens": 17725173.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.2344471454620365,
|
|
"epoch": 0.7564026206075045,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004953976119725378,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.19012053310871124,
|
|
"num_tokens": 17740770.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.257531404495239,
|
|
"epoch": 0.756998213222156,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004953890332711839,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.19161965399980546,
|
|
"num_tokens": 17754077.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.236436891555786,
|
|
"epoch": 0.7575938058368076,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004953804466648337,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.1974656328558922,
|
|
"num_tokens": 17768572.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.232912683486939,
|
|
"epoch": 0.7581893984514592,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004953718521537952,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.19388171583414077,
|
|
"num_tokens": 17783678.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.2367500305175785,
|
|
"epoch": 0.7587849910661107,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004953632497383766,
|
|
"loss": 5.0117,
|
|
"mean_token_accuracy": 0.1882649764418602,
|
|
"num_tokens": 17796453.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.2102912902832035,
|
|
"epoch": 0.7593805836807623,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004953546394188867,
|
|
"loss": 4.9903,
|
|
"mean_token_accuracy": 0.19316976219415666,
|
|
"num_tokens": 17810459.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.199485015869141,
|
|
"epoch": 0.7599761762954139,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000495346021195634,
|
|
"loss": 4.9452,
|
|
"mean_token_accuracy": 0.1976654350757599,
|
|
"num_tokens": 17822976.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.270958948135376,
|
|
"epoch": 0.7605717689100655,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004953373950689279,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.19287413954734803,
|
|
"num_tokens": 17836842.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.219940137863159,
|
|
"epoch": 0.7611673615247171,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004953287610390775,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.19589110910892488,
|
|
"num_tokens": 17849300.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.197756910324097,
|
|
"epoch": 0.7617629541393687,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004953201191063928,
|
|
"loss": 4.9482,
|
|
"mean_token_accuracy": 0.20569814294576644,
|
|
"num_tokens": 17862526.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.234637022018433,
|
|
"epoch": 0.7623585467540203,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004953114692711837,
|
|
"loss": 4.9392,
|
|
"mean_token_accuracy": 0.19683305472135543,
|
|
"num_tokens": 17874895.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.351198387145996,
|
|
"epoch": 0.7629541393686718,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004953028115337603,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.18872247040271758,
|
|
"num_tokens": 17888898.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.275505781173706,
|
|
"epoch": 0.7635497319833234,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004952941458944333,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.19684648215770723,
|
|
"num_tokens": 17902185.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.212680244445801,
|
|
"epoch": 0.764145324597975,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004952854723535134,
|
|
"loss": 5.0407,
|
|
"mean_token_accuracy": 0.19405684173107146,
|
|
"num_tokens": 17917309.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.292424011230469,
|
|
"epoch": 0.7647409172126266,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004952767909113118,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.18623896241188048,
|
|
"num_tokens": 17931147.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.2509864330291744,
|
|
"epoch": 0.7653365098272782,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004952681015681398,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.19457871317863465,
|
|
"num_tokens": 17944792.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.240945720672608,
|
|
"epoch": 0.7659321024419298,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004952594043243092,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.19307603240013121,
|
|
"num_tokens": 17958580.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.254747772216797,
|
|
"epoch": 0.7665276950565812,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004952506991801319,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.19729479104280473,
|
|
"num_tokens": 17972245.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.217161798477173,
|
|
"epoch": 0.7671232876712328,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004952419861359201,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.20097014605998992,
|
|
"num_tokens": 17987082.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.281825304031372,
|
|
"epoch": 0.7677188802858844,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004952332651919864,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.196898852288723,
|
|
"num_tokens": 18001477.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.267430400848388,
|
|
"epoch": 0.768314472900536,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004952245363486435,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.19692141562700272,
|
|
"num_tokens": 18014553.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.213688087463379,
|
|
"epoch": 0.7689100655151876,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004952157996062046,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.19314685165882112,
|
|
"num_tokens": 18027454.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.229483366012573,
|
|
"epoch": 0.7695056581298392,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000495207054964983,
|
|
"loss": 5.028,
|
|
"mean_token_accuracy": 0.19735330641269683,
|
|
"num_tokens": 18040632.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.174659967422485,
|
|
"epoch": 0.7701012507444908,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004951983024252924,
|
|
"loss": 4.9364,
|
|
"mean_token_accuracy": 0.20677314549684525,
|
|
"num_tokens": 18053859.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.19487247467041,
|
|
"epoch": 0.7706968433591423,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004951895419874466,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.1979288101196289,
|
|
"num_tokens": 18067734.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.2400572299957275,
|
|
"epoch": 0.7712924359737939,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00049518077365176,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.19198224693536758,
|
|
"num_tokens": 18083831.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.2484739303588865,
|
|
"epoch": 0.7718880285884455,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000495171997418547,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.20254883915185928,
|
|
"num_tokens": 18097085.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.227088212966919,
|
|
"epoch": 0.7724836212030971,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004951632132881225,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.2043430894613266,
|
|
"num_tokens": 18111311.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.242480659484864,
|
|
"epoch": 0.7730792138177487,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004951544212608015,
|
|
"loss": 4.978,
|
|
"mean_token_accuracy": 0.19956133663654327,
|
|
"num_tokens": 18126622.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.28610634803772,
|
|
"epoch": 0.7736748064324003,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004951456213368994,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.1988889068365097,
|
|
"num_tokens": 18138074.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.185953140258789,
|
|
"epoch": 0.7742703990470519,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004951368135167316,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.2016700193285942,
|
|
"num_tokens": 18150865.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.175633811950684,
|
|
"epoch": 0.7748659916617034,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004951279978006143,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.2048206552863121,
|
|
"num_tokens": 18163779.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.194139909744263,
|
|
"epoch": 0.7754615842763549,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004951191741888638,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.1920811727643013,
|
|
"num_tokens": 18177924.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.332524538040161,
|
|
"epoch": 0.7760571768910065,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004951103426817961,
|
|
"loss": 5.0794,
|
|
"mean_token_accuracy": 0.1860789477825165,
|
|
"num_tokens": 18191818.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.250522756576538,
|
|
"epoch": 0.7766527695056581,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004951015032797286,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.19232677519321442,
|
|
"num_tokens": 18205681.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.196157360076905,
|
|
"epoch": 0.7772483621203097,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004950926559829778,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.19033485502004624,
|
|
"num_tokens": 18220420.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.163662004470825,
|
|
"epoch": 0.7778439547349613,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004950838007918615,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.20483670234680176,
|
|
"num_tokens": 18233891.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.210063457489014,
|
|
"epoch": 0.7784395473496128,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000495074937706697,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.19820671677589416,
|
|
"num_tokens": 18246671.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.176687812805175,
|
|
"epoch": 0.7790351399642644,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004950660667278023,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.1949735924601555,
|
|
"num_tokens": 18260351.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.171747779846191,
|
|
"epoch": 0.779630732578916,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004950571878554956,
|
|
"loss": 4.9168,
|
|
"mean_token_accuracy": 0.2090547576546669,
|
|
"num_tokens": 18275475.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.229822111129761,
|
|
"epoch": 0.7802263251935676,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004950483010900953,
|
|
"loss": 5.021,
|
|
"mean_token_accuracy": 0.1890003874897957,
|
|
"num_tokens": 18289598.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.191414928436279,
|
|
"epoch": 0.7808219178082192,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004950394064319203,
|
|
"loss": 4.8955,
|
|
"mean_token_accuracy": 0.20110878497362136,
|
|
"num_tokens": 18302118.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.286186599731446,
|
|
"epoch": 0.7814175104228708,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004950305038812895,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.1940566450357437,
|
|
"num_tokens": 18316462.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.218073558807373,
|
|
"epoch": 0.7820131030375224,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004950215934385223,
|
|
"loss": 4.9384,
|
|
"mean_token_accuracy": 0.20610519498586655,
|
|
"num_tokens": 18328241.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.227169466018677,
|
|
"epoch": 0.782608695652174,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004950126751039382,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.1960917666554451,
|
|
"num_tokens": 18341580.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.220258092880249,
|
|
"epoch": 0.7832042882668255,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004950037488778572,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.19299762398004533,
|
|
"num_tokens": 18354996.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.2296185970306395,
|
|
"epoch": 0.7837998808814771,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004949948147605996,
|
|
"loss": 4.9952,
|
|
"mean_token_accuracy": 0.1980782702565193,
|
|
"num_tokens": 18369284.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.290348911285401,
|
|
"epoch": 0.7843954734961287,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004949858727524855,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.19346099942922593,
|
|
"num_tokens": 18383008.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.250885820388794,
|
|
"epoch": 0.7849910661107802,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004949769228538359,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.19770067930221558,
|
|
"num_tokens": 18396676.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.166311311721802,
|
|
"epoch": 0.7855866587254318,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004949679650649717,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.19133253246545792,
|
|
"num_tokens": 18411155.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.183766508102417,
|
|
"epoch": 0.7861822513400833,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004949589993862143,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.19767880588769912,
|
|
"num_tokens": 18425793.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.157757186889649,
|
|
"epoch": 0.7867778439547349,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004949500258178851,
|
|
"loss": 4.9108,
|
|
"mean_token_accuracy": 0.20680391937494277,
|
|
"num_tokens": 18438920.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.221579074859619,
|
|
"epoch": 0.7873734365693865,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004949410443603062,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.18938832432031633,
|
|
"num_tokens": 18454440.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.261292409896851,
|
|
"epoch": 0.7879690291840381,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004949320550137996,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.1941392943263054,
|
|
"num_tokens": 18469269.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.274663877487183,
|
|
"epoch": 0.7885646217986897,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004949230577786877,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.18626997470855713,
|
|
"num_tokens": 18484071.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.244982051849365,
|
|
"epoch": 0.7891602144133413,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004949140526552934,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.193590746819973,
|
|
"num_tokens": 18498647.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.258627462387085,
|
|
"epoch": 0.7897558070279929,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004949050396439395,
|
|
"loss": 4.9953,
|
|
"mean_token_accuracy": 0.19717811048030853,
|
|
"num_tokens": 18513406.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.1929131031036375,
|
|
"epoch": 0.7903513996426444,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004948960187449495,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.19698793888092042,
|
|
"num_tokens": 18528150.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.279631280899048,
|
|
"epoch": 0.790946992257296,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004948869899586467,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.1833077073097229,
|
|
"num_tokens": 18542402.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.2759575843811035,
|
|
"epoch": 0.7915425848719476,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004948779532853552,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.18903296142816545,
|
|
"num_tokens": 18557156.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.187373399734497,
|
|
"epoch": 0.7921381774865992,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004948689087253989,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.20532598197460175,
|
|
"num_tokens": 18570544.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.24799075126648,
|
|
"epoch": 0.7927337701012508,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004948598562791025,
|
|
"loss": 5.0356,
|
|
"mean_token_accuracy": 0.19691961258649826,
|
|
"num_tokens": 18583755.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.220971345901489,
|
|
"epoch": 0.7933293627159024,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004948507959467905,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.19516967833042145,
|
|
"num_tokens": 18596991.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.243996334075928,
|
|
"epoch": 0.7939249553305538,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004948417277287877,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.1944785237312317,
|
|
"num_tokens": 18611206.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.30399603843689,
|
|
"epoch": 0.7945205479452054,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004948326516254197,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.1917933315038681,
|
|
"num_tokens": 18626567.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.335937118530273,
|
|
"epoch": 0.795116140559857,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000494823567637012,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.18980808258056642,
|
|
"num_tokens": 18641515.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.238548803329468,
|
|
"epoch": 0.7957117331745086,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004948144757638902,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.19614880084991454,
|
|
"num_tokens": 18656622.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.2198200702667235,
|
|
"epoch": 0.7963073257891602,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004948053760063806,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.19848720729351044,
|
|
"num_tokens": 18669919.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.193484592437744,
|
|
"epoch": 0.7969029184038118,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004947962683648095,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.2065558910369873,
|
|
"num_tokens": 18683254.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.201970624923706,
|
|
"epoch": 0.7974985110184634,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004947871528395038,
|
|
"loss": 4.9424,
|
|
"mean_token_accuracy": 0.19787162989377977,
|
|
"num_tokens": 18697611.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.2578284740448,
|
|
"epoch": 0.798094103633115,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00049477802943079,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.19779613763093948,
|
|
"num_tokens": 18711363.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.224925374984741,
|
|
"epoch": 0.7986896962477665,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004947688981389958,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.195338936150074,
|
|
"num_tokens": 18725641.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.209351396560669,
|
|
"epoch": 0.7992852888624181,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004947597589644484,
|
|
"loss": 5.0006,
|
|
"mean_token_accuracy": 0.1966038629412651,
|
|
"num_tokens": 18739724.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.203993797302246,
|
|
"epoch": 0.7998808814770697,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004947506119074759,
|
|
"loss": 4.916,
|
|
"mean_token_accuracy": 0.20244602411985396,
|
|
"num_tokens": 18755257.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.254049396514892,
|
|
"epoch": 0.8004764740917213,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004947414569684062,
|
|
"loss": 4.9726,
|
|
"mean_token_accuracy": 0.19627052843570708,
|
|
"num_tokens": 18770300.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.158795690536499,
|
|
"epoch": 0.8010720667063729,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004947322941475677,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.20374849885702134,
|
|
"num_tokens": 18781939.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.201802492141724,
|
|
"epoch": 0.8016676593210245,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004947231234452891,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.19272928833961486,
|
|
"num_tokens": 18794851.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.174449491500854,
|
|
"epoch": 0.802263251935676,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004947139448618994,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.1976815566420555,
|
|
"num_tokens": 18810776.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.19357385635376,
|
|
"epoch": 0.8028588445503275,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004947047583977276,
|
|
"loss": 4.9185,
|
|
"mean_token_accuracy": 0.2047879159450531,
|
|
"num_tokens": 18825602.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.278327703475952,
|
|
"epoch": 0.8034544371649791,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004946955640531033,
|
|
"loss": 5.0363,
|
|
"mean_token_accuracy": 0.19233814030885696,
|
|
"num_tokens": 18840284.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.1930032730102536,
|
|
"epoch": 0.8040500297796307,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004946863618283565,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.19921063184738158,
|
|
"num_tokens": 18853372.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.2031471729278564,
|
|
"epoch": 0.8046456223942823,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004946771517238169,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.195361690223217,
|
|
"num_tokens": 18867320.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.272561883926391,
|
|
"epoch": 0.8052412150089339,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004946679337398151,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.1923861414194107,
|
|
"num_tokens": 18881441.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.194640111923218,
|
|
"epoch": 0.8058368076235854,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004946587078766818,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.19871903508901595,
|
|
"num_tokens": 18895225.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.270473051071167,
|
|
"epoch": 0.806432400238237,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004946494741347476,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.19545858353376389,
|
|
"num_tokens": 18909834.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.22183084487915,
|
|
"epoch": 0.8070279928528886,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004946402325143439,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.19898949265480043,
|
|
"num_tokens": 18922304.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.226222085952759,
|
|
"epoch": 0.8076235854675402,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004946309830158024,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.19586487859487534,
|
|
"num_tokens": 18935959.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.275166273117065,
|
|
"epoch": 0.8082191780821918,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004946217256394544,
|
|
"loss": 4.9475,
|
|
"mean_token_accuracy": 0.1978494107723236,
|
|
"num_tokens": 18950468.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.187729215621948,
|
|
"epoch": 0.8088147706968434,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004946124603856322,
|
|
"loss": 4.9302,
|
|
"mean_token_accuracy": 0.20428735613822938,
|
|
"num_tokens": 18966015.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.187413930892944,
|
|
"epoch": 0.809410363311495,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004946031872546683,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.19645809531211852,
|
|
"num_tokens": 18980689.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.2232287406921385,
|
|
"epoch": 0.8100059559261465,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000494593906246895,
|
|
"loss": 4.9467,
|
|
"mean_token_accuracy": 0.19833593368530272,
|
|
"num_tokens": 18994111.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.253461933135986,
|
|
"epoch": 0.8106015485407981,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004945846173626453,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.1915527805685997,
|
|
"num_tokens": 19006845.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.102130508422851,
|
|
"epoch": 0.8111971411554497,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004945753206022525,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.2026818349957466,
|
|
"num_tokens": 19021182.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.119801950454712,
|
|
"epoch": 0.8117927337701013,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004945660159660499,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.20574050694704055,
|
|
"num_tokens": 19034850.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.156879663467407,
|
|
"epoch": 0.8123883263847528,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004945567034543712,
|
|
"loss": 4.9625,
|
|
"mean_token_accuracy": 0.19564699828624726,
|
|
"num_tokens": 19047405.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.186093187332153,
|
|
"epoch": 0.8129839189994044,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004945473830675507,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.19549231976270676,
|
|
"num_tokens": 19061475.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.269990491867065,
|
|
"epoch": 0.813579511614056,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945380548059224,
|
|
"loss": 4.955,
|
|
"mean_token_accuracy": 0.19739711731672288,
|
|
"num_tokens": 19077312.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.284447097778321,
|
|
"epoch": 0.8141751042287075,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004945287186698211,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.196418796479702,
|
|
"num_tokens": 19091066.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.1753651142120365,
|
|
"epoch": 0.8147706968433591,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004945193746595815,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.19640980660915375,
|
|
"num_tokens": 19105081.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.226230049133301,
|
|
"epoch": 0.8153662894580107,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004945100227755389,
|
|
"loss": 5.0035,
|
|
"mean_token_accuracy": 0.19250698685646056,
|
|
"num_tokens": 19119223.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.2444275379180905,
|
|
"epoch": 0.8159618820726623,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004945006630180288,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.19720785915851594,
|
|
"num_tokens": 19132704.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.163217306137085,
|
|
"epoch": 0.8165574746873139,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004944912953873865,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.19969214051961898,
|
|
"num_tokens": 19147882.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.190442991256714,
|
|
"epoch": 0.8171530673019655,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004944819198839486,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.19937245547771454,
|
|
"num_tokens": 19160815.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.17026572227478,
|
|
"epoch": 0.817748659916617,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000494472536508051,
|
|
"loss": 4.9253,
|
|
"mean_token_accuracy": 0.19624848365783693,
|
|
"num_tokens": 19175654.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.153588008880615,
|
|
"epoch": 0.8183442525312686,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004944631452600303,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.20589463412761688,
|
|
"num_tokens": 19189428.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.150795316696167,
|
|
"epoch": 0.8189398451459202,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004944537461402234,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.20777377337217331,
|
|
"num_tokens": 19203050.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.1590831756591795,
|
|
"epoch": 0.8195354377605718,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004944443391489676,
|
|
"loss": 4.9033,
|
|
"mean_token_accuracy": 0.20656412839889526,
|
|
"num_tokens": 19216875.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.140744924545288,
|
|
"epoch": 0.8201310303752234,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004944349242865999,
|
|
"loss": 4.8814,
|
|
"mean_token_accuracy": 0.20422403514385223,
|
|
"num_tokens": 19231423.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.178452873229981,
|
|
"epoch": 0.820726622989875,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004944255015534585,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.19136395901441575,
|
|
"num_tokens": 19245360.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.176740264892578,
|
|
"epoch": 0.8213222156045265,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000494416070949881,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.1939812645316124,
|
|
"num_tokens": 19261233.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.179486227035523,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004944066324762058,
|
|
"loss": 4.8352,
|
|
"mean_token_accuracy": 0.20505842119455336,
|
|
"num_tokens": 19274656.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.208062553405762,
|
|
"epoch": 0.8225134008338296,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004943971861327713,
|
|
"loss": 4.9845,
|
|
"mean_token_accuracy": 0.20033636838197708,
|
|
"num_tokens": 19290243.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.184555101394653,
|
|
"epoch": 0.8231089934484812,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004943877319199167,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.20203078240156175,
|
|
"num_tokens": 19303314.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.25859260559082,
|
|
"epoch": 0.8237045860631328,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004943782698379807,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.1967867374420166,
|
|
"num_tokens": 19317856.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.225908422470093,
|
|
"epoch": 0.8243001786777844,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004943687998873029,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.1996067926287651,
|
|
"num_tokens": 19332876.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.264829635620117,
|
|
"epoch": 0.824895771292436,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004943593220682229,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.19916828125715255,
|
|
"num_tokens": 19345938.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.198520231246948,
|
|
"epoch": 0.8254913639070875,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004943498363810807,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.20096887052059173,
|
|
"num_tokens": 19359439.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.197078514099121,
|
|
"epoch": 0.8260869565217391,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004943403428262164,
|
|
"loss": 4.927,
|
|
"mean_token_accuracy": 0.1983810320496559,
|
|
"num_tokens": 19374440.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.2000243186950685,
|
|
"epoch": 0.8266825491363907,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004943308414039708,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.19840652048587798,
|
|
"num_tokens": 19386937.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.221543884277343,
|
|
"epoch": 0.8272781417510423,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004943213321146843,
|
|
"loss": 4.9552,
|
|
"mean_token_accuracy": 0.19773127138614655,
|
|
"num_tokens": 19401077.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.263700199127197,
|
|
"epoch": 0.8278737343656939,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004943118149586984,
|
|
"loss": 5.0748,
|
|
"mean_token_accuracy": 0.1942123457789421,
|
|
"num_tokens": 19416093.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.257858657836914,
|
|
"epoch": 0.8284693269803455,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004943022899363542,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.19796085953712464,
|
|
"num_tokens": 19428961.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.194193124771118,
|
|
"epoch": 0.8290649195949971,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942927570479934,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.1998603105545044,
|
|
"num_tokens": 19442909.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.084754371643067,
|
|
"epoch": 0.8296605122096486,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004942832162939581,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.20469870269298554,
|
|
"num_tokens": 19457702.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.200575447082519,
|
|
"epoch": 0.8302561048243002,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004942736676745902,
|
|
"loss": 4.9756,
|
|
"mean_token_accuracy": 0.19211914837360383,
|
|
"num_tokens": 19471662.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.190879869461059,
|
|
"epoch": 0.8308516974389517,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004942641111902324,
|
|
"loss": 4.9243,
|
|
"mean_token_accuracy": 0.20491006523370742,
|
|
"num_tokens": 19486109.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.173599481582642,
|
|
"epoch": 0.8314472900536033,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004942545468412275,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.19535935670137405,
|
|
"num_tokens": 19501600.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.179930782318115,
|
|
"epoch": 0.8320428826682549,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004942449746279184,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.19809613525867462,
|
|
"num_tokens": 19515721.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.25024676322937,
|
|
"epoch": 0.8326384752829065,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004942353945506485,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.19599954932928085,
|
|
"num_tokens": 19530536.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.211724328994751,
|
|
"epoch": 0.833234067897558,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942258066097617,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.20121758729219436,
|
|
"num_tokens": 19542976.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.1772066116333,
|
|
"epoch": 0.8338296605122096,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004942162108056015,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.20356553196907043,
|
|
"num_tokens": 19557884.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.195683336257934,
|
|
"epoch": 0.8344252531268612,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004942066071385122,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.20158070772886277,
|
|
"num_tokens": 19572438.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.250618267059326,
|
|
"epoch": 0.8350208457415128,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004941969956088383,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.19092175960540772,
|
|
"num_tokens": 19586114.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.126167869567871,
|
|
"epoch": 0.8356164383561644,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004941873762169246,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.20391568541526794,
|
|
"num_tokens": 19600338.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.235204648971558,
|
|
"epoch": 0.836212030970816,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004941777489631161,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.19510669857263566,
|
|
"num_tokens": 19613049.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.179143190383911,
|
|
"epoch": 0.8368076235854676,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004941681138477582,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.20509544909000396,
|
|
"num_tokens": 19626685.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.209314966201783,
|
|
"epoch": 0.8374032162001191,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004941584708711962,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.20257640033960342,
|
|
"num_tokens": 19642114.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.230994081497192,
|
|
"epoch": 0.8379988088147707,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004941488200337763,
|
|
"loss": 4.9315,
|
|
"mean_token_accuracy": 0.20642898678779603,
|
|
"num_tokens": 19655505.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.182041168212891,
|
|
"epoch": 0.8385944014294223,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004941391613358444,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.195048788189888,
|
|
"num_tokens": 19671845.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.199954509735107,
|
|
"epoch": 0.8391899940440739,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004941294947777473,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.20698976814746856,
|
|
"num_tokens": 19683578.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.194951057434082,
|
|
"epoch": 0.8397855866587254,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004941198203598314,
|
|
"loss": 4.957,
|
|
"mean_token_accuracy": 0.20136092156171798,
|
|
"num_tokens": 19697974.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.158334541320801,
|
|
"epoch": 0.840381179273377,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004941101380824438,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.2090238317847252,
|
|
"num_tokens": 19713024.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.2471624374389645,
|
|
"epoch": 0.8409767718880286,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004941004479459318,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.1891821950674057,
|
|
"num_tokens": 19726562.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.197494459152222,
|
|
"epoch": 0.8415723645026801,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000494090749950643,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.20092622488737105,
|
|
"num_tokens": 19741838.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.225650882720947,
|
|
"epoch": 0.8421679571173317,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004940810440969253,
|
|
"loss": 4.9018,
|
|
"mean_token_accuracy": 0.19776152968406677,
|
|
"num_tokens": 19754852.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.14455132484436,
|
|
"epoch": 0.8427635497319833,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004940713303851265,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.21060265749692916,
|
|
"num_tokens": 19767355.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.0800426483154295,
|
|
"epoch": 0.8433591423466349,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004940616088155954,
|
|
"loss": 4.8863,
|
|
"mean_token_accuracy": 0.19781294763088225,
|
|
"num_tokens": 19780861.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.150558280944824,
|
|
"epoch": 0.8439547349612865,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004940518793886807,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.1977229505777359,
|
|
"num_tokens": 19793802.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.286704015731812,
|
|
"epoch": 0.8445503275759381,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004940421421047311,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.18992689847946168,
|
|
"num_tokens": 19810748.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.201115131378174,
|
|
"epoch": 0.8451459201905897,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000494032396964096,
|
|
"loss": 4.9496,
|
|
"mean_token_accuracy": 0.19507500380277634,
|
|
"num_tokens": 19826046.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.174026727676392,
|
|
"epoch": 0.8457415128052412,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000494022643967125,
|
|
"loss": 4.9272,
|
|
"mean_token_accuracy": 0.19786983132362365,
|
|
"num_tokens": 19839591.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.191043186187744,
|
|
"epoch": 0.8463371054198928,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004940128831141679,
|
|
"loss": 4.9384,
|
|
"mean_token_accuracy": 0.20353737771511077,
|
|
"num_tokens": 19852560.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.215848159790039,
|
|
"epoch": 0.8469326980345444,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004940031144055747,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.1993735834956169,
|
|
"num_tokens": 19867663.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.1568732261657715,
|
|
"epoch": 0.847528290649196,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004939933378416959,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.20010240375995636,
|
|
"num_tokens": 19883761.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.200322818756104,
|
|
"epoch": 0.8481238832638476,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004939835534228821,
|
|
"loss": 4.9605,
|
|
"mean_token_accuracy": 0.1938878983259201,
|
|
"num_tokens": 19897205.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.321979808807373,
|
|
"epoch": 0.848719475878499,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004939737611494842,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.191355599462986,
|
|
"num_tokens": 19912563.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.219370937347412,
|
|
"epoch": 0.8493150684931506,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004939639610218536,
|
|
"loss": 4.9486,
|
|
"mean_token_accuracy": 0.19734373092651367,
|
|
"num_tokens": 19926308.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.143039846420288,
|
|
"epoch": 0.8499106611078022,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004939541530403419,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.20476730912923813,
|
|
"num_tokens": 19939372.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.243761587142944,
|
|
"epoch": 0.8505062537224538,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004939443372053004,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.19902985841035842,
|
|
"num_tokens": 19952755.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.185356140136719,
|
|
"epoch": 0.8511018463371054,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004939345135170818,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.20194488018751144,
|
|
"num_tokens": 19965678.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.196139192581176,
|
|
"epoch": 0.851697438951757,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000493924681976038,
|
|
"loss": 4.9437,
|
|
"mean_token_accuracy": 0.2041453018784523,
|
|
"num_tokens": 19979022.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.2096381187438965,
|
|
"epoch": 0.8522930315664086,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004939148425825219,
|
|
"loss": 4.8807,
|
|
"mean_token_accuracy": 0.20381091088056563,
|
|
"num_tokens": 19991861.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.145027446746826,
|
|
"epoch": 0.8528886241810602,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004939049953368863,
|
|
"loss": 4.9048,
|
|
"mean_token_accuracy": 0.2007173627614975,
|
|
"num_tokens": 20004444.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.139266633987427,
|
|
"epoch": 0.8534842167957117,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004938951402394844,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.20842663794755936,
|
|
"num_tokens": 20018302.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.156631565093994,
|
|
"epoch": 0.8540798094103633,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004938852772906697,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.2095871940255165,
|
|
"num_tokens": 20031193.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.142639684677124,
|
|
"epoch": 0.8546754020250149,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004938754064907961,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.205288627743721,
|
|
"num_tokens": 20044883.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.237454032897949,
|
|
"epoch": 0.8552709946396665,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004938655278402175,
|
|
"loss": 5.002,
|
|
"mean_token_accuracy": 0.19401786625385284,
|
|
"num_tokens": 20058024.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.272576999664307,
|
|
"epoch": 0.8558665872543181,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004938556413392882,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.19195224493741989,
|
|
"num_tokens": 20072622.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.202688407897949,
|
|
"epoch": 0.8564621798689697,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004938457469883629,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.20383676290512084,
|
|
"num_tokens": 20086774.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.217047595977784,
|
|
"epoch": 0.8570577724836212,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004938358447877966,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.19284874200820923,
|
|
"num_tokens": 20102435.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.226665210723877,
|
|
"epoch": 0.8576533650982728,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004938259347379442,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.2000731647014618,
|
|
"num_tokens": 20115860.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.15633807182312,
|
|
"epoch": 0.8582489577129243,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004938160168391614,
|
|
"loss": 4.9193,
|
|
"mean_token_accuracy": 0.20516918748617172,
|
|
"num_tokens": 20130910.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.144200801849365,
|
|
"epoch": 0.8588445503275759,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004938060910918038,
|
|
"loss": 4.8379,
|
|
"mean_token_accuracy": 0.2057316169142723,
|
|
"num_tokens": 20143093.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.14917106628418,
|
|
"epoch": 0.8594401429422275,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004937961574962274,
|
|
"loss": 4.933,
|
|
"mean_token_accuracy": 0.199495305120945,
|
|
"num_tokens": 20157637.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.233995628356934,
|
|
"epoch": 0.8600357355568791,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004937862160527887,
|
|
"loss": 5.0208,
|
|
"mean_token_accuracy": 0.19563516080379487,
|
|
"num_tokens": 20170455.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.174675321578979,
|
|
"epoch": 0.8606313281715307,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004937762667618441,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.20732314884662628,
|
|
"num_tokens": 20186452.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.183922529220581,
|
|
"epoch": 0.8612269207861822,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004937663096237505,
|
|
"loss": 4.9532,
|
|
"mean_token_accuracy": 0.2031957194209099,
|
|
"num_tokens": 20199754.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.202494049072266,
|
|
"epoch": 0.8618225134008338,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004937563446388652,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.1951001614332199,
|
|
"num_tokens": 20215765.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.236445617675781,
|
|
"epoch": 0.8624181060154854,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004937463718075453,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.19351110756397247,
|
|
"num_tokens": 20229225.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.16055998802185,
|
|
"epoch": 0.863013698630137,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004937363911301488,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.20316509753465653,
|
|
"num_tokens": 20242729.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.221871662139892,
|
|
"epoch": 0.8636092912447886,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004937264026070336,
|
|
"loss": 4.9144,
|
|
"mean_token_accuracy": 0.20396992564201355,
|
|
"num_tokens": 20252914.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.119789075851441,
|
|
"epoch": 0.8642048838594402,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000493716406238558,
|
|
"loss": 4.8289,
|
|
"mean_token_accuracy": 0.21363402307033538,
|
|
"num_tokens": 20265611.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.248425769805908,
|
|
"epoch": 0.8648004764740918,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004937064020250804,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.19304792135953902,
|
|
"num_tokens": 20279808.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.112802934646607,
|
|
"epoch": 0.8653960690887433,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004936963899669599,
|
|
"loss": 4.9046,
|
|
"mean_token_accuracy": 0.21182684153318404,
|
|
"num_tokens": 20295028.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.19658465385437,
|
|
"epoch": 0.8659916617033949,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004936863700645554,
|
|
"loss": 4.9093,
|
|
"mean_token_accuracy": 0.20723917037248613,
|
|
"num_tokens": 20308780.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.3057116031646725,
|
|
"epoch": 0.8665872543180465,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004936763423182264,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.1955184668302536,
|
|
"num_tokens": 20322513.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.315117979049683,
|
|
"epoch": 0.867182846932698,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004936663067283325,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.19142100661993028,
|
|
"num_tokens": 20336457.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.251580333709716,
|
|
"epoch": 0.8677784395473496,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004936562632952337,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.204435995221138,
|
|
"num_tokens": 20349063.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.242055892944336,
|
|
"epoch": 0.8683740321620012,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004936462120192903,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.19686673134565352,
|
|
"num_tokens": 20361832.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.119455623626709,
|
|
"epoch": 0.8689696247766527,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004936361529008627,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.207675901055336,
|
|
"num_tokens": 20376291.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.100206422805786,
|
|
"epoch": 0.8695652173913043,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004936260859403119,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.20781948715448378,
|
|
"num_tokens": 20389654.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.281002473831177,
|
|
"epoch": 0.8701608100059559,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004936160111379987,
|
|
"loss": 5.0008,
|
|
"mean_token_accuracy": 0.19634274691343306,
|
|
"num_tokens": 20403782.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.2350830078125,
|
|
"epoch": 0.8707564026206075,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004936059284942848,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.21461202949285507,
|
|
"num_tokens": 20416547.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.218772029876709,
|
|
"epoch": 0.8713519952352591,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004935958380095316,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.18681780993938446,
|
|
"num_tokens": 20430831.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.154837417602539,
|
|
"epoch": 0.8719475878499107,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000493585739684101,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.20065713673830032,
|
|
"num_tokens": 20445905.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.2428586959838865,
|
|
"epoch": 0.8725431804645623,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004935756335183554,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.19477982223033904,
|
|
"num_tokens": 20461506.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.2439109802246096,
|
|
"epoch": 0.8731387730792138,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004935655195126572,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.2032554864883423,
|
|
"num_tokens": 20474753.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.2102876663208,
|
|
"epoch": 0.8737343656938654,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004935553976673692,
|
|
"loss": 4.9502,
|
|
"mean_token_accuracy": 0.20263940393924712,
|
|
"num_tokens": 20489877.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.123287916183472,
|
|
"epoch": 0.874329958308517,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004935452679828545,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.20947035849094392,
|
|
"num_tokens": 20503693.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.19082989692688,
|
|
"epoch": 0.8749255509231686,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004935351304594763,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.19590176343917848,
|
|
"num_tokens": 20519188.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.195393228530884,
|
|
"epoch": 0.8755211435378202,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004935249850975983,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.19099701195955276,
|
|
"num_tokens": 20535218.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.165136432647705,
|
|
"epoch": 0.8761167361524718,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004935148318975843,
|
|
"loss": 4.9085,
|
|
"mean_token_accuracy": 0.20871033221483232,
|
|
"num_tokens": 20548037.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.183838748931885,
|
|
"epoch": 0.8767123287671232,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004935046708597986,
|
|
"loss": 4.959,
|
|
"mean_token_accuracy": 0.1991287961602211,
|
|
"num_tokens": 20562248.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.217296314239502,
|
|
"epoch": 0.8773079213817748,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004934945019846057,
|
|
"loss": 5.0065,
|
|
"mean_token_accuracy": 0.1968469500541687,
|
|
"num_tokens": 20577796.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.192312240600586,
|
|
"epoch": 0.8779035139964264,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004934843252723702,
|
|
"loss": 4.9366,
|
|
"mean_token_accuracy": 0.20320193320512772,
|
|
"num_tokens": 20591413.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.183933162689209,
|
|
"epoch": 0.878499106611078,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004934741407234572,
|
|
"loss": 4.9601,
|
|
"mean_token_accuracy": 0.20014556050300597,
|
|
"num_tokens": 20606648.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.310555791854858,
|
|
"epoch": 0.8790946992257296,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000493463948338232,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.1992385908961296,
|
|
"num_tokens": 20620531.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.222958707809449,
|
|
"epoch": 0.8796902918403812,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004934537481170602,
|
|
"loss": 4.9454,
|
|
"mean_token_accuracy": 0.19808440804481506,
|
|
"num_tokens": 20636639.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.1746210098266605,
|
|
"epoch": 0.8802858844550328,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004934435400603077,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.19616561979055405,
|
|
"num_tokens": 20648799.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.1259603023529055,
|
|
"epoch": 0.8808814770696843,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004934333241683404,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.20880354791879654,
|
|
"num_tokens": 20662612.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.1939445495605465,
|
|
"epoch": 0.8814770696843359,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004934231004415251,
|
|
"loss": 4.9306,
|
|
"mean_token_accuracy": 0.2053857773542404,
|
|
"num_tokens": 20676382.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.1708900928497314,
|
|
"epoch": 0.8820726622989875,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004934128688802282,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.20347366034984588,
|
|
"num_tokens": 20691659.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.198373222351075,
|
|
"epoch": 0.8826682549136391,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004934026294848168,
|
|
"loss": 4.9429,
|
|
"mean_token_accuracy": 0.20474757850170136,
|
|
"num_tokens": 20705276.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.23359375,
|
|
"epoch": 0.8832638475282907,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004933923822556583,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.20139704048633575,
|
|
"num_tokens": 20719632.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.222641277313232,
|
|
"epoch": 0.8838594401429423,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049338212719312,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.19771241545677185,
|
|
"num_tokens": 20733190.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.204409790039063,
|
|
"epoch": 0.8844550327575939,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00049337186429757,
|
|
"loss": 5.0617,
|
|
"mean_token_accuracy": 0.19113123714923858,
|
|
"num_tokens": 20749019.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.24530725479126,
|
|
"epoch": 0.8850506253722454,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004933615935693762,
|
|
"loss": 4.882,
|
|
"mean_token_accuracy": 0.20122056752443312,
|
|
"num_tokens": 20762731.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.149179172515869,
|
|
"epoch": 0.8856462179868969,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004933513150089069,
|
|
"loss": 4.9526,
|
|
"mean_token_accuracy": 0.19772725850343703,
|
|
"num_tokens": 20775599.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.178813028335571,
|
|
"epoch": 0.8862418106015485,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004933410286165311,
|
|
"loss": 4.8662,
|
|
"mean_token_accuracy": 0.21296440362930297,
|
|
"num_tokens": 20788945.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.153425216674805,
|
|
"epoch": 0.8868374032162001,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004933307343926177,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.20397458225488663,
|
|
"num_tokens": 20803079.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.136587524414063,
|
|
"epoch": 0.8874329958308517,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004933204323375358,
|
|
"loss": 4.8578,
|
|
"mean_token_accuracy": 0.2016685426235199,
|
|
"num_tokens": 20816321.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.1141492366790775,
|
|
"epoch": 0.8880285884455033,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000493310122451655,
|
|
"loss": 4.882,
|
|
"mean_token_accuracy": 0.20431207716464997,
|
|
"num_tokens": 20830095.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.181095552444458,
|
|
"epoch": 0.8886241810601548,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004932998047353449,
|
|
"loss": 4.9054,
|
|
"mean_token_accuracy": 0.20596170127391816,
|
|
"num_tokens": 20845022.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.2052695751190186,
|
|
"epoch": 0.8892197736748064,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004932894791889759,
|
|
"loss": 4.9437,
|
|
"mean_token_accuracy": 0.21047252267599106,
|
|
"num_tokens": 20857851.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.188587999343872,
|
|
"epoch": 0.889815366289458,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004932791458129181,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.2098463460803032,
|
|
"num_tokens": 20870343.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.249913072586059,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004932688046075422,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.1921821653842926,
|
|
"num_tokens": 20883805.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.200862884521484,
|
|
"epoch": 0.8910065515187612,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004932584555732192,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.19443014711141587,
|
|
"num_tokens": 20898160.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.167494392395019,
|
|
"epoch": 0.8916021441334128,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004932480987103204,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.20095734894275666,
|
|
"num_tokens": 20912528.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.244489336013794,
|
|
"epoch": 0.8921977367480644,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004932377340192169,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.19706807434558868,
|
|
"num_tokens": 20925603.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.114873218536377,
|
|
"epoch": 0.8927933293627159,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004932273615002809,
|
|
"loss": 4.8507,
|
|
"mean_token_accuracy": 0.20646660327911376,
|
|
"num_tokens": 20937319.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.114079856872559,
|
|
"epoch": 0.8933889219773675,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004932169811538843,
|
|
"loss": 4.881,
|
|
"mean_token_accuracy": 0.20121762305498123,
|
|
"num_tokens": 20952963.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.2189850330352785,
|
|
"epoch": 0.8939845145920191,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004932065929803993,
|
|
"loss": 4.9271,
|
|
"mean_token_accuracy": 0.20091308951377868,
|
|
"num_tokens": 20966696.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.171426820755005,
|
|
"epoch": 0.8945801072066706,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004931961969801985,
|
|
"loss": 4.9286,
|
|
"mean_token_accuracy": 0.20093297958374023,
|
|
"num_tokens": 20981093.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.177992582321167,
|
|
"epoch": 0.8951756998213222,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000493185793153655,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.2003267765045166,
|
|
"num_tokens": 20997069.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.1724700927734375,
|
|
"epoch": 0.8957712924359738,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004931753815011419,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.21557454019784927,
|
|
"num_tokens": 21010123.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.2213465690612795,
|
|
"epoch": 0.8963668850506253,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004931649620230325,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.1982094570994377,
|
|
"num_tokens": 21024774.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.20386323928833,
|
|
"epoch": 0.8969624776652769,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004931545347197006,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.20229129642248153,
|
|
"num_tokens": 21039533.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.159692621231079,
|
|
"epoch": 0.8975580702799285,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004931440995915203,
|
|
"loss": 4.8977,
|
|
"mean_token_accuracy": 0.20701258033514022,
|
|
"num_tokens": 21053593.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.224324083328247,
|
|
"epoch": 0.8981536628945801,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004931336566388658,
|
|
"loss": 4.8943,
|
|
"mean_token_accuracy": 0.2041863963007927,
|
|
"num_tokens": 21064659.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.1039862632751465,
|
|
"epoch": 0.8987492555092317,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004931232058621117,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.21007396429777145,
|
|
"num_tokens": 21078815.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.086712312698364,
|
|
"epoch": 0.8993448481238833,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004931127472616328,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.20999844521284103,
|
|
"num_tokens": 21093415.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.252542448043823,
|
|
"epoch": 0.8999404407385349,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004931022808378044,
|
|
"loss": 4.945,
|
|
"mean_token_accuracy": 0.1973043665289879,
|
|
"num_tokens": 21108347.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.206389379501343,
|
|
"epoch": 0.9005360333531864,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004930918065910018,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.19522498100996016,
|
|
"num_tokens": 21122647.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.160792875289917,
|
|
"epoch": 0.901131625967838,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004930813245216005,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.20371284186840058,
|
|
"num_tokens": 21136465.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.23701844215393,
|
|
"epoch": 0.9017272185824896,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004930708346299769,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.1972338527441025,
|
|
"num_tokens": 21152047.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.168750190734864,
|
|
"epoch": 0.9023228111971412,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004930603369165069,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.20251699537038803,
|
|
"num_tokens": 21166355.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.176753664016724,
|
|
"epoch": 0.9029184038117928,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004930498313815672,
|
|
"loss": 4.8576,
|
|
"mean_token_accuracy": 0.20514662116765975,
|
|
"num_tokens": 21180676.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.147077131271362,
|
|
"epoch": 0.9035139964264444,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004930393180255345,
|
|
"loss": 4.9258,
|
|
"mean_token_accuracy": 0.2021421566605568,
|
|
"num_tokens": 21193091.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.212683963775635,
|
|
"epoch": 0.9041095890410958,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000493028796848786,
|
|
"loss": 4.9424,
|
|
"mean_token_accuracy": 0.20019227117300034,
|
|
"num_tokens": 21208072.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.151427793502807,
|
|
"epoch": 0.9047051816557474,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004930182678516992,
|
|
"loss": 4.8656,
|
|
"mean_token_accuracy": 0.20790144205093383,
|
|
"num_tokens": 21220249.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.128323173522949,
|
|
"epoch": 0.905300774270399,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004930077310346515,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.21145258694887162,
|
|
"num_tokens": 21233609.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.14946813583374,
|
|
"epoch": 0.9058963668850506,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004929971863980209,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.19934533089399337,
|
|
"num_tokens": 21247083.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.141020059585571,
|
|
"epoch": 0.9064919594997022,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004929866339421857,
|
|
"loss": 4.8998,
|
|
"mean_token_accuracy": 0.19907359629869462,
|
|
"num_tokens": 21260614.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.246790075302124,
|
|
"epoch": 0.9070875521143538,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004929760736675243,
|
|
"loss": 4.9018,
|
|
"mean_token_accuracy": 0.20408432483673095,
|
|
"num_tokens": 21275823.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.136869716644287,
|
|
"epoch": 0.9076831447290054,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004929655055744157,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.20603823363780976,
|
|
"num_tokens": 21288787.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.140333032608032,
|
|
"epoch": 0.9082787373436569,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004929549296632387,
|
|
"loss": 4.9624,
|
|
"mean_token_accuracy": 0.1937859132885933,
|
|
"num_tokens": 21304060.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.137907981872559,
|
|
"epoch": 0.9088743299583085,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004929443459343728,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.21058847308158873,
|
|
"num_tokens": 21317116.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.135432624816895,
|
|
"epoch": 0.9094699225729601,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004929337543881975,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.20557257980108262,
|
|
"num_tokens": 21330894.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.180467748641968,
|
|
"epoch": 0.9100655151876117,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004929231550250927,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.2037023201584816,
|
|
"num_tokens": 21344933.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.193316221237183,
|
|
"epoch": 0.9106611078022633,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004929125478454389,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.1956772729754448,
|
|
"num_tokens": 21358675.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.177977609634399,
|
|
"epoch": 0.9112567004169149,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004929019328496161,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.19668956249952316,
|
|
"num_tokens": 21373611.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.173390960693359,
|
|
"epoch": 0.9118522930315665,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004928913100380053,
|
|
"loss": 4.8386,
|
|
"mean_token_accuracy": 0.21380106657743453,
|
|
"num_tokens": 21387292.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.222535705566406,
|
|
"epoch": 0.912447885646218,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004928806794109875,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.1949174463748932,
|
|
"num_tokens": 21400950.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.237725305557251,
|
|
"epoch": 0.9130434782608695,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000492870040968944,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.19785772413015365,
|
|
"num_tokens": 21414625.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.134331226348877,
|
|
"epoch": 0.9136390708755211,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004928593947122564,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.21167535483837127,
|
|
"num_tokens": 21430408.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.188184309005737,
|
|
"epoch": 0.9142346634901727,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004928487406413065,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.2023768365383148,
|
|
"num_tokens": 21444921.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.182950067520141,
|
|
"epoch": 0.9148302561048243,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004928380787564764,
|
|
"loss": 4.9642,
|
|
"mean_token_accuracy": 0.1997913211584091,
|
|
"num_tokens": 21458541.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.159980773925781,
|
|
"epoch": 0.9154258487194759,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004928274090581486,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.2052391842007637,
|
|
"num_tokens": 21472117.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.169700956344604,
|
|
"epoch": 0.9160214413341274,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004928167315467059,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.2038397714495659,
|
|
"num_tokens": 21484983.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.185782241821289,
|
|
"epoch": 0.916617033948779,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004928060462225312,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.20135005414485932,
|
|
"num_tokens": 21498786.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.150549459457397,
|
|
"epoch": 0.9172126265634306,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004927953530860077,
|
|
"loss": 4.8709,
|
|
"mean_token_accuracy": 0.20191349983215331,
|
|
"num_tokens": 21513482.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.169084072113037,
|
|
"epoch": 0.9178082191780822,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004927846521375189,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.20204687416553496,
|
|
"num_tokens": 21528648.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.158945560455322,
|
|
"epoch": 0.9184038117927338,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004927739433774489,
|
|
"loss": 4.8648,
|
|
"mean_token_accuracy": 0.20773633271455766,
|
|
"num_tokens": 21541490.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.089977359771728,
|
|
"epoch": 0.9189994044073854,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004927632268061815,
|
|
"loss": 4.8641,
|
|
"mean_token_accuracy": 0.20510826855897904,
|
|
"num_tokens": 21557156.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.131033229827881,
|
|
"epoch": 0.919594997022037,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004927525024241013,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.20958006531000137,
|
|
"num_tokens": 21571697.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.131120252609253,
|
|
"epoch": 0.9201905896366885,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004927417702315928,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.20465663820505142,
|
|
"num_tokens": 21585936.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.168517208099365,
|
|
"epoch": 0.9207861822513401,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004927310302290411,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.19797697216272353,
|
|
"num_tokens": 21601003.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.129728889465332,
|
|
"epoch": 0.9213817748659917,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004927202824168313,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.20895304530858994,
|
|
"num_tokens": 21616018.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.219531059265137,
|
|
"epoch": 0.9219773674806433,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000492709526795349,
|
|
"loss": 4.9427,
|
|
"mean_token_accuracy": 0.20302734673023223,
|
|
"num_tokens": 21628548.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.236133098602295,
|
|
"epoch": 0.9225729600952948,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00049269876336498,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.19700684100389482,
|
|
"num_tokens": 21643637.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.135596132278442,
|
|
"epoch": 0.9231685527099464,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004926879921261101,
|
|
"loss": 4.8646,
|
|
"mean_token_accuracy": 0.20729771256446838,
|
|
"num_tokens": 21658189.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.196467781066895,
|
|
"epoch": 0.9237641453245979,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004926772130791261,
|
|
"loss": 4.9631,
|
|
"mean_token_accuracy": 0.19533421695232392,
|
|
"num_tokens": 21673023.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.239789533615112,
|
|
"epoch": 0.9243597379392495,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004926664262244143,
|
|
"loss": 4.9605,
|
|
"mean_token_accuracy": 0.19980762153863907,
|
|
"num_tokens": 21687417.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.159991931915283,
|
|
"epoch": 0.9249553305539011,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004926556315623617,
|
|
"loss": 4.9618,
|
|
"mean_token_accuracy": 0.20308748334646226,
|
|
"num_tokens": 21700679.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.213489532470703,
|
|
"epoch": 0.9255509231685527,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004926448290933555,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.20665492862462997,
|
|
"num_tokens": 21715832.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.145826816558838,
|
|
"epoch": 0.9261465157832043,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004926340188177831,
|
|
"loss": 4.8941,
|
|
"mean_token_accuracy": 0.2037758097052574,
|
|
"num_tokens": 21730193.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.225900888442993,
|
|
"epoch": 0.9267421083978559,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004926232007360324,
|
|
"loss": 4.9831,
|
|
"mean_token_accuracy": 0.20186328440904616,
|
|
"num_tokens": 21743177.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.092954158782959,
|
|
"epoch": 0.9273377010125075,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004926123748484911,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.21815144568681716,
|
|
"num_tokens": 21757379.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.113038110733032,
|
|
"epoch": 0.927933293627159,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000492601541155548,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.20746953934431075,
|
|
"num_tokens": 21769872.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.230046510696411,
|
|
"epoch": 0.9285288862418106,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004925906996575912,
|
|
"loss": 4.9195,
|
|
"mean_token_accuracy": 0.20158937126398085,
|
|
"num_tokens": 21784367.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.109302425384522,
|
|
"epoch": 0.9291244788564622,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004925798503550099,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.21196796745061874,
|
|
"num_tokens": 21797896.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.0936198234558105,
|
|
"epoch": 0.9297200714711138,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004925689932481931,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.20395442843437195,
|
|
"num_tokens": 21810668.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.160853910446167,
|
|
"epoch": 0.9303156640857654,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004925581283375303,
|
|
"loss": 4.9371,
|
|
"mean_token_accuracy": 0.20145956575870513,
|
|
"num_tokens": 21824923.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.162323665618897,
|
|
"epoch": 0.930911256700417,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004925472556234111,
|
|
"loss": 4.9117,
|
|
"mean_token_accuracy": 0.20034001916646957,
|
|
"num_tokens": 21839967.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.156509113311768,
|
|
"epoch": 0.9315068493150684,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004925363751062256,
|
|
"loss": 4.893,
|
|
"mean_token_accuracy": 0.21004895567893983,
|
|
"num_tokens": 21852254.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.142991542816162,
|
|
"epoch": 0.93210244192972,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000492525486786364,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.19620302319526672,
|
|
"num_tokens": 21865227.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.2314129829406735,
|
|
"epoch": 0.9326980345443716,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004925145906642169,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.19770905524492263,
|
|
"num_tokens": 21880235.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.152101802825928,
|
|
"epoch": 0.9332936271590232,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004925036867401751,
|
|
"loss": 4.8684,
|
|
"mean_token_accuracy": 0.21156338304281236,
|
|
"num_tokens": 21892514.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.167354583740234,
|
|
"epoch": 0.9338892197736748,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004924927750146296,
|
|
"loss": 4.9488,
|
|
"mean_token_accuracy": 0.201300211250782,
|
|
"num_tokens": 21907212.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.128619384765625,
|
|
"epoch": 0.9344848123883264,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004924818554879718,
|
|
"loss": 4.803,
|
|
"mean_token_accuracy": 0.21054368019104003,
|
|
"num_tokens": 21920627.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.177452659606933,
|
|
"epoch": 0.935080405002978,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004924709281605938,
|
|
"loss": 4.9224,
|
|
"mean_token_accuracy": 0.20415157824754715,
|
|
"num_tokens": 21933557.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.199985599517822,
|
|
"epoch": 0.9356759976176295,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004924599930328869,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.20511766970157624,
|
|
"num_tokens": 21948122.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.155661010742188,
|
|
"epoch": 0.9362715902322811,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004924490501052437,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.20870193392038344,
|
|
"num_tokens": 21961925.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.227665901184082,
|
|
"epoch": 0.9368671828469327,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004924380993780566,
|
|
"loss": 4.9953,
|
|
"mean_token_accuracy": 0.19945377856492996,
|
|
"num_tokens": 21976825.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.130494451522827,
|
|
"epoch": 0.9374627754615843,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004924271408517185,
|
|
"loss": 4.9018,
|
|
"mean_token_accuracy": 0.2027468502521515,
|
|
"num_tokens": 21989599.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.197911357879638,
|
|
"epoch": 0.9380583680762359,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004924161745266222,
|
|
"loss": 4.9224,
|
|
"mean_token_accuracy": 0.2063490316271782,
|
|
"num_tokens": 22002921.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.117190551757813,
|
|
"epoch": 0.9386539606908875,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004924052004031613,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.20760558545589447,
|
|
"num_tokens": 22015933.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.0915440082550045,
|
|
"epoch": 0.939249553305539,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004923942184817293,
|
|
"loss": 4.8275,
|
|
"mean_token_accuracy": 0.2097380131483078,
|
|
"num_tokens": 22029769.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.154109907150269,
|
|
"epoch": 0.9398451459201906,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004923832287627202,
|
|
"loss": 4.926,
|
|
"mean_token_accuracy": 0.19839970171451568,
|
|
"num_tokens": 22044025.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.130391407012939,
|
|
"epoch": 0.9404407385348421,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004923722312465281,
|
|
"loss": 4.8306,
|
|
"mean_token_accuracy": 0.20729864984750748,
|
|
"num_tokens": 22057875.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.130284166336059,
|
|
"epoch": 0.9410363311494937,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004923612259335476,
|
|
"loss": 4.8081,
|
|
"mean_token_accuracy": 0.20912522822618484,
|
|
"num_tokens": 22070995.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.122770357131958,
|
|
"epoch": 0.9416319237641453,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004923502128241732,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.20335273891687394,
|
|
"num_tokens": 22086429.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.052299642562867,
|
|
"epoch": 0.9422275163787969,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004923391919188001,
|
|
"loss": 4.7839,
|
|
"mean_token_accuracy": 0.21197172850370408,
|
|
"num_tokens": 22101146.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.140118885040283,
|
|
"epoch": 0.9428231089934485,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004923281632178236,
|
|
"loss": 4.8642,
|
|
"mean_token_accuracy": 0.21286741644144058,
|
|
"num_tokens": 22113103.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.148571634292603,
|
|
"epoch": 0.9434187016081,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004923171267216392,
|
|
"loss": 4.8631,
|
|
"mean_token_accuracy": 0.2038659781217575,
|
|
"num_tokens": 22126540.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.121250963211059,
|
|
"epoch": 0.9440142942227516,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004923060824306428,
|
|
"loss": 4.9001,
|
|
"mean_token_accuracy": 0.19790467321872712,
|
|
"num_tokens": 22141219.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.189825057983398,
|
|
"epoch": 0.9446098868374032,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004922950303452306,
|
|
"loss": 4.9704,
|
|
"mean_token_accuracy": 0.19676323384046554,
|
|
"num_tokens": 22156178.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.1505598545074465,
|
|
"epoch": 0.9452054794520548,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004922839704657988,
|
|
"loss": 4.8092,
|
|
"mean_token_accuracy": 0.20919700860977172,
|
|
"num_tokens": 22168981.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.173435926437378,
|
|
"epoch": 0.9458010720667064,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004922729027927444,
|
|
"loss": 4.858,
|
|
"mean_token_accuracy": 0.20743221938610076,
|
|
"num_tokens": 22182288.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.1875604629516605,
|
|
"epoch": 0.946396664681358,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004922618273264642,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.19997060894966126,
|
|
"num_tokens": 22197564.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.161518812179565,
|
|
"epoch": 0.9469922572960096,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004922507440673555,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.1902603894472122,
|
|
"num_tokens": 22212030.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.191466808319092,
|
|
"epoch": 0.9475878499106611,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004922396530158159,
|
|
"loss": 4.9046,
|
|
"mean_token_accuracy": 0.19261828809976578,
|
|
"num_tokens": 22226941.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.170515537261963,
|
|
"epoch": 0.9481834425253127,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004922285541722431,
|
|
"loss": 4.9137,
|
|
"mean_token_accuracy": 0.2043929323554039,
|
|
"num_tokens": 22241129.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.1403172492980955,
|
|
"epoch": 0.9487790351399643,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004922174475370352,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.20051785856485366,
|
|
"num_tokens": 22256298.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.139975881576538,
|
|
"epoch": 0.9493746277546159,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004922063331105907,
|
|
"loss": 4.878,
|
|
"mean_token_accuracy": 0.20726433098316194,
|
|
"num_tokens": 22270128.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.234405994415283,
|
|
"epoch": 0.9499702203692674,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004921952108933083,
|
|
"loss": 4.9554,
|
|
"mean_token_accuracy": 0.19809087812900544,
|
|
"num_tokens": 22284847.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.0821973323822025,
|
|
"epoch": 0.950565812983919,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004921840808855865,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.21232864558696746,
|
|
"num_tokens": 22300010.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.113724231719971,
|
|
"epoch": 0.9511614055985705,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004921729430878252,
|
|
"loss": 4.8574,
|
|
"mean_token_accuracy": 0.21107297837734224,
|
|
"num_tokens": 22313339.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.171497631072998,
|
|
"epoch": 0.9517569982132221,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004921617975004233,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.19861940741539003,
|
|
"num_tokens": 22327659.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.220788812637329,
|
|
"epoch": 0.9523525908278737,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004921506441237809,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.2001410648226738,
|
|
"num_tokens": 22343910.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.0376060009002686,
|
|
"epoch": 0.9529481834425253,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004921394829582979,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.21131607443094252,
|
|
"num_tokens": 22359705.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.137473249435425,
|
|
"epoch": 0.9535437760571769,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004921283140043748,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.20236312448978425,
|
|
"num_tokens": 22373446.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.191259384155273,
|
|
"epoch": 0.9541393686718285,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004921171372624121,
|
|
"loss": 4.9056,
|
|
"mean_token_accuracy": 0.20399160534143448,
|
|
"num_tokens": 22386628.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.173376941680909,
|
|
"epoch": 0.95473496128648,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004921059527328106,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.20108542144298552,
|
|
"num_tokens": 22400084.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.151824331283569,
|
|
"epoch": 0.9553305539011316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004920947604159716,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.2020645558834076,
|
|
"num_tokens": 22414135.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.140155887603759,
|
|
"epoch": 0.9559261465157832,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004920835603122965,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.20570904910564422,
|
|
"num_tokens": 22427738.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.168469047546386,
|
|
"epoch": 0.9565217391304348,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004920723524221871,
|
|
"loss": 4.9284,
|
|
"mean_token_accuracy": 0.20862699300050735,
|
|
"num_tokens": 22440024.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.150033283233642,
|
|
"epoch": 0.9571173317450864,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004920611367460453,
|
|
"loss": 4.8202,
|
|
"mean_token_accuracy": 0.21285234093666078,
|
|
"num_tokens": 22453948.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.220550966262818,
|
|
"epoch": 0.957712924359738,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004920499132842734,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.20136776566505432,
|
|
"num_tokens": 22465613.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.138388824462891,
|
|
"epoch": 0.9583085169743896,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004920386820372741,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.19648492187261582,
|
|
"num_tokens": 22478702.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.1773984909057615,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004920274430054502,
|
|
"loss": 4.9576,
|
|
"mean_token_accuracy": 0.20093554258346558,
|
|
"num_tokens": 22490947.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.099131965637207,
|
|
"epoch": 0.9594997022036926,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004920161961892047,
|
|
"loss": 4.8889,
|
|
"mean_token_accuracy": 0.202164663374424,
|
|
"num_tokens": 22506308.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.265158176422119,
|
|
"epoch": 0.9600952948183442,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004920049415889411,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.19947466850280762,
|
|
"num_tokens": 22522045.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.11003794670105,
|
|
"epoch": 0.9606908874329958,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004919936792050631,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.20477987676858903,
|
|
"num_tokens": 22536183.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.107207584381103,
|
|
"epoch": 0.9612864800476474,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004919824090379747,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.2019120067358017,
|
|
"num_tokens": 22548239.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.185073137283325,
|
|
"epoch": 0.961882072662299,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00049197113108808,
|
|
"loss": 4.9073,
|
|
"mean_token_accuracy": 0.20826930403709412,
|
|
"num_tokens": 22563467.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.139787864685059,
|
|
"epoch": 0.9624776652769506,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004919598453557836,
|
|
"loss": 4.89,
|
|
"mean_token_accuracy": 0.20454525500535964,
|
|
"num_tokens": 22577446.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.144203138351441,
|
|
"epoch": 0.9630732578916021,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004919485518414902,
|
|
"loss": 4.8417,
|
|
"mean_token_accuracy": 0.2084780976176262,
|
|
"num_tokens": 22591044.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.100666856765747,
|
|
"epoch": 0.9636688505062537,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004919372505456051,
|
|
"loss": 4.8695,
|
|
"mean_token_accuracy": 0.20638136863708495,
|
|
"num_tokens": 22604872.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.171467208862305,
|
|
"epoch": 0.9642644431209053,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004919259414685336,
|
|
"loss": 4.9499,
|
|
"mean_token_accuracy": 0.19789250046014786,
|
|
"num_tokens": 22620138.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.211587858200073,
|
|
"epoch": 0.9648600357355569,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004919146246106812,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.20072329342365264,
|
|
"num_tokens": 22635580.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.168636274337769,
|
|
"epoch": 0.9654556283502085,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004919032999724539,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.21022566854953767,
|
|
"num_tokens": 22650223.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.089344644546509,
|
|
"epoch": 0.9660512209648601,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004918919675542579,
|
|
"loss": 4.8159,
|
|
"mean_token_accuracy": 0.21292904913425445,
|
|
"num_tokens": 22664899.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.1833117485046385,
|
|
"epoch": 0.9666468135795117,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004918806273564996,
|
|
"loss": 4.8903,
|
|
"mean_token_accuracy": 0.2064916267991066,
|
|
"num_tokens": 22680052.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.1585564613342285,
|
|
"epoch": 0.9672424061941632,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000491869279379586,
|
|
"loss": 4.8266,
|
|
"mean_token_accuracy": 0.21529081463813782,
|
|
"num_tokens": 22693740.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.0844961643219,
|
|
"epoch": 0.9678379988088148,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004918579236239238,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.2172262355685234,
|
|
"num_tokens": 22707795.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.207188892364502,
|
|
"epoch": 0.9684335914234663,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004918465600899205,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.20862368643283843,
|
|
"num_tokens": 22720296.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.185635805130005,
|
|
"epoch": 0.9690291840381179,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004918351887779837,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.20637147575616838,
|
|
"num_tokens": 22733680.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.106030607223511,
|
|
"epoch": 0.9696247766527695,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004918238096885213,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.20991733819246292,
|
|
"num_tokens": 22746202.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.169045782089233,
|
|
"epoch": 0.9702203692674211,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004918124228219412,
|
|
"loss": 4.8823,
|
|
"mean_token_accuracy": 0.20171044617891312,
|
|
"num_tokens": 22759547.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.174850130081177,
|
|
"epoch": 0.9708159618820726,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004918010281786522,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.20426854640245437,
|
|
"num_tokens": 22772593.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.145639514923095,
|
|
"epoch": 0.9714115544967242,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004917896257590627,
|
|
"loss": 4.9152,
|
|
"mean_token_accuracy": 0.20570519864559172,
|
|
"num_tokens": 22786482.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.143901300430298,
|
|
"epoch": 0.9720071471113758,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004917782155635817,
|
|
"loss": 4.8745,
|
|
"mean_token_accuracy": 0.2031828925013542,
|
|
"num_tokens": 22800582.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.169395446777344,
|
|
"epoch": 0.9726027397260274,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004917667975926187,
|
|
"loss": 4.9014,
|
|
"mean_token_accuracy": 0.2019306406378746,
|
|
"num_tokens": 22813661.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.199574422836304,
|
|
"epoch": 0.973198332340679,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004917553718465832,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.21097655594348907,
|
|
"num_tokens": 22827648.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.180054140090943,
|
|
"epoch": 0.9737939249553306,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004917439383258848,
|
|
"loss": 4.969,
|
|
"mean_token_accuracy": 0.19981744438409804,
|
|
"num_tokens": 22843345.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.208468389511109,
|
|
"epoch": 0.9743895175699822,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004917324970309337,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.2014692783355713,
|
|
"num_tokens": 22857474.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.1444275856018065,
|
|
"epoch": 0.9749851101846337,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004917210479621404,
|
|
"loss": 4.8773,
|
|
"mean_token_accuracy": 0.21017157286405563,
|
|
"num_tokens": 22870233.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.168971872329712,
|
|
"epoch": 0.9755807027992853,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004917095911199155,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.20469366610050202,
|
|
"num_tokens": 22885616.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.135917806625367,
|
|
"epoch": 0.9761762954139369,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00049169812650467,
|
|
"loss": 4.8428,
|
|
"mean_token_accuracy": 0.21661810725927352,
|
|
"num_tokens": 22899553.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.120583534240723,
|
|
"epoch": 0.9767718880285885,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004916866541168148,
|
|
"loss": 4.8222,
|
|
"mean_token_accuracy": 0.20923354774713515,
|
|
"num_tokens": 22912671.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.206519651412964,
|
|
"epoch": 0.97736748064324,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004916751739567617,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.1954212635755539,
|
|
"num_tokens": 22926112.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.142909383773803,
|
|
"epoch": 0.9779630732578916,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 0.0004916636860249225,
|
|
"loss": 4.8083,
|
|
"mean_token_accuracy": 0.22121331393718718,
|
|
"num_tokens": 22940348.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.091591310501099,
|
|
"epoch": 0.9785586658725431,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000491652190321709,
|
|
"loss": 4.9432,
|
|
"mean_token_accuracy": 0.2039811372756958,
|
|
"num_tokens": 22953347.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.19566502571106,
|
|
"epoch": 0.9791542584871947,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004916406868475338,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.18632267862558366,
|
|
"num_tokens": 22967963.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.205854749679565,
|
|
"epoch": 0.9797498511018463,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004916291756028094,
|
|
"loss": 4.8887,
|
|
"mean_token_accuracy": 0.19927141964435577,
|
|
"num_tokens": 22985611.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.15804443359375,
|
|
"epoch": 0.9803454437164979,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004916176565879487,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.20035916119813918,
|
|
"num_tokens": 22999210.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.1641459465026855,
|
|
"epoch": 0.9809410363311495,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004916061298033648,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.20353958904743194,
|
|
"num_tokens": 23012315.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.146068954467774,
|
|
"epoch": 0.9815366289458011,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004915945952494713,
|
|
"loss": 4.8955,
|
|
"mean_token_accuracy": 0.20492046177387238,
|
|
"num_tokens": 23025886.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.118735504150391,
|
|
"epoch": 0.9821322215604527,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004915830529266818,
|
|
"loss": 4.7875,
|
|
"mean_token_accuracy": 0.21191224902868272,
|
|
"num_tokens": 23040308.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.151578617095947,
|
|
"epoch": 0.9827278141751042,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004915715028354102,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.2065846651792526,
|
|
"num_tokens": 23053608.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.19239239692688,
|
|
"epoch": 0.9833234067897558,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004915599449760711,
|
|
"loss": 4.8838,
|
|
"mean_token_accuracy": 0.21130586862564088,
|
|
"num_tokens": 23068153.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.1373237609863285,
|
|
"epoch": 0.9839189994044074,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004915483793490788,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.20041715055704118,
|
|
"num_tokens": 23081334.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.15984959602356,
|
|
"epoch": 0.984514592019059,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004915368059548482,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.1981048420071602,
|
|
"num_tokens": 23095943.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.179400157928467,
|
|
"epoch": 0.9851101846337106,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004915252247937944,
|
|
"loss": 4.8534,
|
|
"mean_token_accuracy": 0.2055879920721054,
|
|
"num_tokens": 23110311.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.186139059066773,
|
|
"epoch": 0.9857057772483622,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000491513635866333,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.20667112171649932,
|
|
"num_tokens": 23123783.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.178050231933594,
|
|
"epoch": 0.9863013698630136,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004915020391728792,
|
|
"loss": 4.9872,
|
|
"mean_token_accuracy": 0.20367335379123688,
|
|
"num_tokens": 23139147.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.155344295501709,
|
|
"epoch": 0.9868969624776652,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004914904347138495,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.2081715539097786,
|
|
"num_tokens": 23153216.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.106193113327026,
|
|
"epoch": 0.9874925550923168,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004914788224896599,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.2105048656463623,
|
|
"num_tokens": 23166263.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.094871759414673,
|
|
"epoch": 0.9880881477069684,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004914672025007269,
|
|
"loss": 4.8467,
|
|
"mean_token_accuracy": 0.20345101356506348,
|
|
"num_tokens": 23182093.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.129582214355469,
|
|
"epoch": 0.98868374032162,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004914555747474673,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.20541125237941743,
|
|
"num_tokens": 23195492.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.236596965789795,
|
|
"epoch": 0.9892793329362716,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004914439392302981,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.1982062503695488,
|
|
"num_tokens": 23208333.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.175382518768311,
|
|
"epoch": 0.9898749255509232,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004914322959496367,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.20490623861551285,
|
|
"num_tokens": 23223265.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.143275213241577,
|
|
"epoch": 0.9904705181655747,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004914206449059008,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.20889676362276077,
|
|
"num_tokens": 23237534.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.12363829612732,
|
|
"epoch": 0.9910661107802263,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004914089860995084,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.2044193148612976,
|
|
"num_tokens": 23252038.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.145361757278442,
|
|
"epoch": 0.9916617033948779,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004913973195308772,
|
|
"loss": 4.9047,
|
|
"mean_token_accuracy": 0.20208573192358018,
|
|
"num_tokens": 23265728.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.194819545745849,
|
|
"epoch": 0.9922572960095295,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004913856452004262,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.20181659162044524,
|
|
"num_tokens": 23278282.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.116386556625367,
|
|
"epoch": 0.9928528886241811,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004913739631085739,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.2121524393558502,
|
|
"num_tokens": 23293041.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.142052888870239,
|
|
"epoch": 0.9934484812388327,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004913622732557394,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.2083202287554741,
|
|
"num_tokens": 23307307.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.195662975311279,
|
|
"epoch": 0.9940440738534843,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913505756423418,
|
|
"loss": 4.9418,
|
|
"mean_token_accuracy": 0.1993076264858246,
|
|
"num_tokens": 23324064.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.13206114768982,
|
|
"epoch": 0.9946396664681358,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004913388702688009,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.2090326204895973,
|
|
"num_tokens": 23338498.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.105178546905518,
|
|
"epoch": 0.9952352590827874,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004913271571355365,
|
|
"loss": 4.8358,
|
|
"mean_token_accuracy": 0.2085870996117592,
|
|
"num_tokens": 23352252.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.18420090675354,
|
|
"epoch": 0.9958308516974389,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004913154362429686,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.19440813064575196,
|
|
"num_tokens": 23366220.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.14540319442749,
|
|
"epoch": 0.9964264443120905,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004913037075915178,
|
|
"loss": 4.8386,
|
|
"mean_token_accuracy": 0.2095992758870125,
|
|
"num_tokens": 23378926.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.181989908218384,
|
|
"epoch": 0.9970220369267421,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004912919711816047,
|
|
"loss": 4.9014,
|
|
"mean_token_accuracy": 0.202271930873394,
|
|
"num_tokens": 23391252.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.122814559936524,
|
|
"epoch": 0.9976176295413937,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004912802270136503,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.20503441244363785,
|
|
"num_tokens": 23403812.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.187450408935547,
|
|
"epoch": 0.9982132221560452,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004912684750880757,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.2050313338637352,
|
|
"num_tokens": 23417536.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.240493583679199,
|
|
"epoch": 0.9988088147706968,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004912567154053025,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.20314064621925354,
|
|
"num_tokens": 23431897.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.155682229995728,
|
|
"epoch": 0.9994044073853484,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004912449479657526,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.2052952915430069,
|
|
"num_tokens": 23446561.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.070127534866333,
|
|
"epoch": 1.0,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004912331727698481,
|
|
"loss": 4.8581,
|
|
"mean_token_accuracy": 0.2062658980488777,
|
|
"num_tokens": 23461012.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.138813114166259,
|
|
"epoch": 1.0005955926146515,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004912213898180111,
|
|
"loss": 4.7927,
|
|
"mean_token_accuracy": 0.21029384583234786,
|
|
"num_tokens": 23473208.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.216282749176026,
|
|
"epoch": 1.0011911852293032,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004912095991106644,
|
|
"loss": 4.8772,
|
|
"mean_token_accuracy": 0.20366016030311584,
|
|
"num_tokens": 23487450.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.184504604339599,
|
|
"epoch": 1.0017867778439546,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004911978006482311,
|
|
"loss": 4.9172,
|
|
"mean_token_accuracy": 0.20066119134426116,
|
|
"num_tokens": 23500630.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.176157665252686,
|
|
"epoch": 1.0023823704586063,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004911859944311341,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.20801374316215515,
|
|
"num_tokens": 23513999.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.199293756484986,
|
|
"epoch": 1.0029779630732578,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000491174180459797,
|
|
"loss": 4.8832,
|
|
"mean_token_accuracy": 0.20216892063617706,
|
|
"num_tokens": 23529046.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.22356219291687,
|
|
"epoch": 1.0035735556879095,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004911623587346434,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.20714361369609832,
|
|
"num_tokens": 23545040.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.1354498863220215,
|
|
"epoch": 1.004169148302561,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004911505292560977,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.20984240025281906,
|
|
"num_tokens": 23558019.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.128421783447266,
|
|
"epoch": 1.0047647409172127,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004911386920245837,
|
|
"loss": 4.8358,
|
|
"mean_token_accuracy": 0.20819839239120483,
|
|
"num_tokens": 23571263.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.1692524433135985,
|
|
"epoch": 1.0053603335318642,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004911268470405263,
|
|
"loss": 4.8617,
|
|
"mean_token_accuracy": 0.20826758593320846,
|
|
"num_tokens": 23584992.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.066988325119018,
|
|
"epoch": 1.0059559261465159,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004911149943043504,
|
|
"loss": 4.6861,
|
|
"mean_token_accuracy": 0.22212384194135665,
|
|
"num_tokens": 23597751.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.090288591384888,
|
|
"epoch": 1.0065515187611673,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000491103133816481,
|
|
"loss": 4.8447,
|
|
"mean_token_accuracy": 0.21272822916507722,
|
|
"num_tokens": 23613045.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.157129287719727,
|
|
"epoch": 1.007147111375819,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004910912655773436,
|
|
"loss": 4.8111,
|
|
"mean_token_accuracy": 0.2078084632754326,
|
|
"num_tokens": 23626785.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.147101736068725,
|
|
"epoch": 1.0077427039904705,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004910793895873637,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.21254142224788666,
|
|
"num_tokens": 23640496.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.172559356689453,
|
|
"epoch": 1.0083382966051222,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004910675058469675,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.20700593143701554,
|
|
"num_tokens": 23652604.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.127598667144776,
|
|
"epoch": 1.0089338892197737,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004910556143565812,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.20883881002664567,
|
|
"num_tokens": 23666326.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.092582178115845,
|
|
"epoch": 1.0095294818344251,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004910437151166312,
|
|
"loss": 4.7656,
|
|
"mean_token_accuracy": 0.20856189131736755,
|
|
"num_tokens": 23680728.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.066568326950073,
|
|
"epoch": 1.0101250744490768,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004910318081275445,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.21278895437717438,
|
|
"num_tokens": 23694326.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.159813690185547,
|
|
"epoch": 1.0107206670637283,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000491019893389748,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.2057343080639839,
|
|
"num_tokens": 23709459.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.143509244918823,
|
|
"epoch": 1.01131625967838,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004910079709036692,
|
|
"loss": 4.8594,
|
|
"mean_token_accuracy": 0.20517559647560119,
|
|
"num_tokens": 23725227.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.174915504455567,
|
|
"epoch": 1.0119118522930315,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004909960406697358,
|
|
"loss": 4.9061,
|
|
"mean_token_accuracy": 0.20066791772842407,
|
|
"num_tokens": 23738733.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.166104555130005,
|
|
"epoch": 1.0125074449076832,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004909841026883755,
|
|
"loss": 4.8557,
|
|
"mean_token_accuracy": 0.20205041468143464,
|
|
"num_tokens": 23753189.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.206087493896485,
|
|
"epoch": 1.0131030375223347,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004909721569600166,
|
|
"loss": 4.8533,
|
|
"mean_token_accuracy": 0.20892948061227798,
|
|
"num_tokens": 23766665.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.154427814483642,
|
|
"epoch": 1.0136986301369864,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004909602034850875,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.21215418577194214,
|
|
"num_tokens": 23780190.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.082206678390503,
|
|
"epoch": 1.0142942227516378,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004909482422640172,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.21402974426746368,
|
|
"num_tokens": 23794652.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.132416105270385,
|
|
"epoch": 1.0148898153662895,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004909362732972344,
|
|
"loss": 4.7941,
|
|
"mean_token_accuracy": 0.20658524483442306,
|
|
"num_tokens": 23810423.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.13685712814331,
|
|
"epoch": 1.015485407980941,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004909242965851688,
|
|
"loss": 4.8135,
|
|
"mean_token_accuracy": 0.21229182779788972,
|
|
"num_tokens": 23823676.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.1011253833770756,
|
|
"epoch": 1.0160810005955927,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004909123121282495,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.2105905219912529,
|
|
"num_tokens": 23836703.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.003394079208374,
|
|
"epoch": 1.0166765932102442,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004909003199269068,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.21504827439785004,
|
|
"num_tokens": 23850804.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.176595735549927,
|
|
"epoch": 1.0172721858248959,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004908883199815705,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.2049652636051178,
|
|
"num_tokens": 23864893.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.136459255218506,
|
|
"epoch": 1.0178677784395473,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004908763122926712,
|
|
"loss": 4.7684,
|
|
"mean_token_accuracy": 0.20551982074975966,
|
|
"num_tokens": 23878268.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.10177698135376,
|
|
"epoch": 1.018463371054199,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004908642968606396,
|
|
"loss": 4.7761,
|
|
"mean_token_accuracy": 0.211183163523674,
|
|
"num_tokens": 23892398.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.051022720336914,
|
|
"epoch": 1.0190589636688505,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004908522736859068,
|
|
"loss": 4.7071,
|
|
"mean_token_accuracy": 0.21554582417011262,
|
|
"num_tokens": 23907268.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.1465315341949465,
|
|
"epoch": 1.019654556283502,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004908402427689037,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.21144466549158097,
|
|
"num_tokens": 23921484.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.034311532974243,
|
|
"epoch": 1.0202501488981537,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004908282041100621,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.21745063215494156,
|
|
"num_tokens": 23934312.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.1466833591461185,
|
|
"epoch": 1.0208457415128052,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004908161577098137,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.20310075283050538,
|
|
"num_tokens": 23946866.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.128697109222412,
|
|
"epoch": 1.0214413341274569,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004908041035685907,
|
|
"loss": 4.8139,
|
|
"mean_token_accuracy": 0.2119651973247528,
|
|
"num_tokens": 23960582.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.132839965820312,
|
|
"epoch": 1.0220369267421083,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004907920416868253,
|
|
"loss": 4.8176,
|
|
"mean_token_accuracy": 0.20396367460489273,
|
|
"num_tokens": 23976130.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.17964882850647,
|
|
"epoch": 1.02263251935676,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004907799720649502,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.20460424274206163,
|
|
"num_tokens": 23989740.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.126927709579467,
|
|
"epoch": 1.0232281119714115,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004907678947033984,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.2095361277461052,
|
|
"num_tokens": 24005840.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.17985692024231,
|
|
"epoch": 1.0238237045860632,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004907558096026031,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.20556285679340364,
|
|
"num_tokens": 24019861.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.1436186790466305,
|
|
"epoch": 1.0244192972007147,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004907437167629976,
|
|
"loss": 4.7925,
|
|
"mean_token_accuracy": 0.21151459813117982,
|
|
"num_tokens": 24034741.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.151778030395508,
|
|
"epoch": 1.0250148898153664,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004907316161850158,
|
|
"loss": 4.8604,
|
|
"mean_token_accuracy": 0.20032909214496614,
|
|
"num_tokens": 24048905.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.094139146804809,
|
|
"epoch": 1.0256104824300178,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004907195078690916,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.20486340671777725,
|
|
"num_tokens": 24064937.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.104985094070434,
|
|
"epoch": 1.0262060750446695,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004907073918156595,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.21135835945606232,
|
|
"num_tokens": 24080293.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.224298477172852,
|
|
"epoch": 1.026801667659321,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004906952680251539,
|
|
"loss": 4.8731,
|
|
"mean_token_accuracy": 0.204022878408432,
|
|
"num_tokens": 24092048.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.1068422317504885,
|
|
"epoch": 1.0273972602739727,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004906831364980098,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.21063403487205506,
|
|
"num_tokens": 24106446.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.092778968811035,
|
|
"epoch": 1.0279928528886242,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004906709972346623,
|
|
"loss": 4.829,
|
|
"mean_token_accuracy": 0.20791480988264083,
|
|
"num_tokens": 24120867.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.13624587059021,
|
|
"epoch": 1.0285884455032757,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004906588502355467,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.21009235829114914,
|
|
"num_tokens": 24135139.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.075651979446411,
|
|
"epoch": 1.0291840381179274,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004906466955010988,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.21506182700395585,
|
|
"num_tokens": 24147649.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.0850231647491455,
|
|
"epoch": 1.0297796307325788,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004906345330317546,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.2156852275133133,
|
|
"num_tokens": 24162408.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.133837604522705,
|
|
"epoch": 1.0303752233472305,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004906223628279502,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.2128289073705673,
|
|
"num_tokens": 24175011.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.1190205097198485,
|
|
"epoch": 1.030970815961882,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004906101848901224,
|
|
"loss": 4.7668,
|
|
"mean_token_accuracy": 0.20752097815275192,
|
|
"num_tokens": 24187832.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.137272930145263,
|
|
"epoch": 1.0315664085765337,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004905979992187076,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.20723040401935577,
|
|
"num_tokens": 24202347.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.127494812011719,
|
|
"epoch": 1.0321620011911852,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004905858058141433,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.2151472434401512,
|
|
"num_tokens": 24216988.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.144544363021851,
|
|
"epoch": 1.0327575938058369,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004905736046768665,
|
|
"loss": 4.8342,
|
|
"mean_token_accuracy": 0.20514188557863236,
|
|
"num_tokens": 24231091.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.119000005722046,
|
|
"epoch": 1.0333531864204883,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004905613958073151,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.21235317587852479,
|
|
"num_tokens": 24244684.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.041586399078369,
|
|
"epoch": 1.03394877903514,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000490549179205927,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.21712538301944734,
|
|
"num_tokens": 24259637.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.114613962173462,
|
|
"epoch": 1.0345443716497915,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004905369548731402,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.19975724518299104,
|
|
"num_tokens": 24274046.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.172807598114014,
|
|
"epoch": 1.0351399642644432,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004905247228093933,
|
|
"loss": 4.8924,
|
|
"mean_token_accuracy": 0.20453329384326935,
|
|
"num_tokens": 24288266.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.100952005386352,
|
|
"epoch": 1.0357355568790947,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000490512483015125,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.20122157484292985,
|
|
"num_tokens": 24303029.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.017348766326904,
|
|
"epoch": 1.0363311494937464,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004905002354907743,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.2311531126499176,
|
|
"num_tokens": 24315369.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.225590467453003,
|
|
"epoch": 1.0369267421083979,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004904879802367806,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.20815024971961976,
|
|
"num_tokens": 24327049.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.183346843719482,
|
|
"epoch": 1.0375223347230493,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004904757172535833,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.20634782463312148,
|
|
"num_tokens": 24341797.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.092668056488037,
|
|
"epoch": 1.038117927337701,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004904634465416226,
|
|
"loss": 4.8491,
|
|
"mean_token_accuracy": 0.2014106571674347,
|
|
"num_tokens": 24357560.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.138264274597168,
|
|
"epoch": 1.0387135199523525,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004904511681013382,
|
|
"loss": 4.7794,
|
|
"mean_token_accuracy": 0.20823070108890535,
|
|
"num_tokens": 24371856.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.173141002655029,
|
|
"epoch": 1.0393091125670042,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004904388819331707,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.21101521402597428,
|
|
"num_tokens": 24384494.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.203754043579101,
|
|
"epoch": 1.0399047051816557,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004904265880375609,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.2087449088692665,
|
|
"num_tokens": 24398901.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.085235071182251,
|
|
"epoch": 1.0405002977963074,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004904142864149496,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.20378551334142686,
|
|
"num_tokens": 24413900.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.147413444519043,
|
|
"epoch": 1.0410958904109588,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000490401977065778,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.2099375069141388,
|
|
"num_tokens": 24427764.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.119725751876831,
|
|
"epoch": 1.0416914830256105,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004903896599904878,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.21138669550418854,
|
|
"num_tokens": 24442510.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.199914073944091,
|
|
"epoch": 1.042287075640262,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004903773351895206,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.2088031142950058,
|
|
"num_tokens": 24457119.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.159385299682617,
|
|
"epoch": 1.0428826682549137,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004903650026633187,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.203310626745224,
|
|
"num_tokens": 24470232.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.126715230941772,
|
|
"epoch": 1.0434782608695652,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004903526624123243,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.21211189180612564,
|
|
"num_tokens": 24484886.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.138202333450318,
|
|
"epoch": 1.0440738534842169,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00049034031443698,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.20580998957157134,
|
|
"num_tokens": 24499682.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.15484585762024,
|
|
"epoch": 1.0446694460988684,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004903279587377287,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.21023864448070526,
|
|
"num_tokens": 24514812.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.183528327941895,
|
|
"epoch": 1.04526503871352,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004903155953150137,
|
|
"loss": 4.7981,
|
|
"mean_token_accuracy": 0.209485225379467,
|
|
"num_tokens": 24527723.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.09554352760315,
|
|
"epoch": 1.0458606313281715,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004903032241692784,
|
|
"loss": 4.7807,
|
|
"mean_token_accuracy": 0.21643899828195573,
|
|
"num_tokens": 24542082.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.112549066543579,
|
|
"epoch": 1.046456223942823,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004902908453009664,
|
|
"loss": 4.7696,
|
|
"mean_token_accuracy": 0.20846424698829652,
|
|
"num_tokens": 24556854.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.032196998596191,
|
|
"epoch": 1.0470518165574747,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004902784587105218,
|
|
"loss": 4.6628,
|
|
"mean_token_accuracy": 0.21990129500627517,
|
|
"num_tokens": 24570927.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.107818984985352,
|
|
"epoch": 1.0476474091721262,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000490266064398389,
|
|
"loss": 4.775,
|
|
"mean_token_accuracy": 0.21337322592735292,
|
|
"num_tokens": 24584458.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.096448659896851,
|
|
"epoch": 1.0482430017867779,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004902536623650125,
|
|
"loss": 4.718,
|
|
"mean_token_accuracy": 0.21747942119836808,
|
|
"num_tokens": 24597576.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.039991664886474,
|
|
"epoch": 1.0488385944014293,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004902412526108371,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.21844386756420137,
|
|
"num_tokens": 24613022.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.183021354675293,
|
|
"epoch": 1.049434187016081,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004902288351363079,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.20556181222200393,
|
|
"num_tokens": 24627730.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.065745496749878,
|
|
"epoch": 1.0500297796307325,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004902164099418703,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.2147128850221634,
|
|
"num_tokens": 24642870.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.219315767288208,
|
|
"epoch": 1.0506253722453842,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00049020397702797,
|
|
"loss": 4.9291,
|
|
"mean_token_accuracy": 0.20059290081262587,
|
|
"num_tokens": 24658416.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.145761871337891,
|
|
"epoch": 1.0512209648600357,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000490191536395053,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.20804867446422576,
|
|
"num_tokens": 24673294.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.014398193359375,
|
|
"epoch": 1.0518165574746874,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004901790880435655,
|
|
"loss": 4.7572,
|
|
"mean_token_accuracy": 0.2120633065700531,
|
|
"num_tokens": 24687841.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.109115839004517,
|
|
"epoch": 1.0524121500893389,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004901666319739537,
|
|
"loss": 4.6754,
|
|
"mean_token_accuracy": 0.2193242758512497,
|
|
"num_tokens": 24701489.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.108572387695313,
|
|
"epoch": 1.0530077427039906,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004901541681866649,
|
|
"loss": 4.7637,
|
|
"mean_token_accuracy": 0.21108277440071105,
|
|
"num_tokens": 24714312.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.081126356124878,
|
|
"epoch": 1.053603335318642,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004901416966821459,
|
|
"loss": 4.7562,
|
|
"mean_token_accuracy": 0.2104330077767372,
|
|
"num_tokens": 24728982.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.137008714675903,
|
|
"epoch": 1.0541989279332937,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000490129217460844,
|
|
"loss": 4.8043,
|
|
"mean_token_accuracy": 0.21663427203893662,
|
|
"num_tokens": 24744374.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.201541233062744,
|
|
"epoch": 1.0547945205479452,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004901167305232068,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.19659553468227386,
|
|
"num_tokens": 24759129.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.135098457336426,
|
|
"epoch": 1.0553901131625967,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004901042358696823,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.21131441444158555,
|
|
"num_tokens": 24772154.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.057092714309692,
|
|
"epoch": 1.0559857057772484,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004900917335007186,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.21486336290836333,
|
|
"num_tokens": 24785961.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.114371490478516,
|
|
"epoch": 1.0565812983918998,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004900792234167642,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.21809787452220916,
|
|
"num_tokens": 24797337.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.179401016235351,
|
|
"epoch": 1.0571768910065515,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004900667056182676,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.20549160838127137,
|
|
"num_tokens": 24811023.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.1551713943481445,
|
|
"epoch": 1.057772483621203,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004900541801056781,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.2057827115058899,
|
|
"num_tokens": 24823951.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.098555326461792,
|
|
"epoch": 1.0583680762358547,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004900416468794446,
|
|
"loss": 4.7708,
|
|
"mean_token_accuracy": 0.20761974304914474,
|
|
"num_tokens": 24838856.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.170796871185303,
|
|
"epoch": 1.0589636688505062,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004900291059400171,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.20616501867771148,
|
|
"num_tokens": 24853539.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.157054901123047,
|
|
"epoch": 1.0595592614651579,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000490016557287845,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.215354286134243,
|
|
"num_tokens": 24866385.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.108547258377075,
|
|
"epoch": 1.0601548540798094,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004900040009233787,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.20210982412099837,
|
|
"num_tokens": 24880168.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.12911434173584,
|
|
"epoch": 1.060750446694461,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004899914368470685,
|
|
"loss": 4.7869,
|
|
"mean_token_accuracy": 0.21187651455402373,
|
|
"num_tokens": 24893673.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.172240304946899,
|
|
"epoch": 1.0613460393091125,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004899788650593648,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.20732207149267196,
|
|
"num_tokens": 24907950.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.163798761367798,
|
|
"epoch": 1.0619416319237642,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004899662855607189,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.2171337828040123,
|
|
"num_tokens": 24921443.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.113023996353149,
|
|
"epoch": 1.0625372245384157,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004899536983515819,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.20986804664134978,
|
|
"num_tokens": 24935485.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.102256870269775,
|
|
"epoch": 1.0631328171530674,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004899411034324051,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.20706371665000917,
|
|
"num_tokens": 24950372.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.038030767440796,
|
|
"epoch": 1.0637284097677189,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004899285008036406,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.20937495082616805,
|
|
"num_tokens": 24964360.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.091169452667236,
|
|
"epoch": 1.0643240023823703,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048991589046574,
|
|
"loss": 4.7466,
|
|
"mean_token_accuracy": 0.22248387187719346,
|
|
"num_tokens": 24979101.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.149181985855103,
|
|
"epoch": 1.064919594997022,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004899032724191559,
|
|
"loss": 4.8037,
|
|
"mean_token_accuracy": 0.20824328660964966,
|
|
"num_tokens": 24994350.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.064204359054566,
|
|
"epoch": 1.0655151876116735,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004898906466643409,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.2156625956296921,
|
|
"num_tokens": 25007343.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.213231086730957,
|
|
"epoch": 1.0661107802263252,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004898780132017478,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.19968572556972503,
|
|
"num_tokens": 25020191.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.086263990402221,
|
|
"epoch": 1.0667063728409767,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004898653720318296,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.20833426117897033,
|
|
"num_tokens": 25034910.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.138117980957031,
|
|
"epoch": 1.0673019654556284,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048985272315504,
|
|
"loss": 4.8043,
|
|
"mean_token_accuracy": 0.21070942282676697,
|
|
"num_tokens": 25048958.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.195279169082641,
|
|
"epoch": 1.0678975580702799,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004898400665718325,
|
|
"loss": 4.8879,
|
|
"mean_token_accuracy": 0.20562794059515,
|
|
"num_tokens": 25065752.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.122239065170288,
|
|
"epoch": 1.0684931506849316,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004898274022826611,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.22069545984268188,
|
|
"num_tokens": 25078569.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.088910675048828,
|
|
"epoch": 1.069088743299583,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004898147302879801,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.21561240553855895,
|
|
"num_tokens": 25093973.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.086549758911133,
|
|
"epoch": 1.0696843359142347,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004898020505882441,
|
|
"loss": 4.7219,
|
|
"mean_token_accuracy": 0.21272779107093812,
|
|
"num_tokens": 25109338.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.080607318878174,
|
|
"epoch": 1.0702799285288862,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004897893631839076,
|
|
"loss": 4.7974,
|
|
"mean_token_accuracy": 0.2102585643529892,
|
|
"num_tokens": 25124902.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.122834062576294,
|
|
"epoch": 1.070875521143538,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000489776668075426,
|
|
"loss": 4.7487,
|
|
"mean_token_accuracy": 0.21668126285076142,
|
|
"num_tokens": 25138982.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.116102790832519,
|
|
"epoch": 1.0714711137581894,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004897639652632544,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.2124329015612602,
|
|
"num_tokens": 25152684.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.100784015655518,
|
|
"epoch": 1.072066706372841,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004897512547478487,
|
|
"loss": 4.7783,
|
|
"mean_token_accuracy": 0.2098769724369049,
|
|
"num_tokens": 25167275.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.072066706372841,
|
|
"eval_entropy": 4.8975390982852085,
|
|
"eval_loss": 4.816634654998779,
|
|
"eval_mean_token_accuracy": 0.21961654885715826,
|
|
"eval_num_tokens": 25167275.0,
|
|
"eval_runtime": 18.4152,
|
|
"eval_samples_per_second": 1385.43,
|
|
"eval_steps_per_second": 173.226,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.16540002822876,
|
|
"epoch": 1.0726622989874925,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004897385365296645,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.21491356641054155,
|
|
"num_tokens": 25178117.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.078837442398071,
|
|
"epoch": 1.073257891602144,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004897258106091582,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.2198787063360214,
|
|
"num_tokens": 25191002.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.016154146194458,
|
|
"epoch": 1.0738534842167957,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004897130769867862,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.22024079412221909,
|
|
"num_tokens": 25204749.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.111913776397705,
|
|
"epoch": 1.0744490768314472,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004897003356630052,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.20652114748954772,
|
|
"num_tokens": 25219324.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.09404616355896,
|
|
"epoch": 1.0750446694460989,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004896875866382723,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.21282534748315812,
|
|
"num_tokens": 25234032.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.140444421768189,
|
|
"epoch": 1.0756402620607504,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004896748299130447,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.21394070833921433,
|
|
"num_tokens": 25245922.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.188923692703247,
|
|
"epoch": 1.076235854675402,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048966206548778,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.20531648993492127,
|
|
"num_tokens": 25257614.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.029330205917359,
|
|
"epoch": 1.0768314472900535,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000489649293362936,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.220835542678833,
|
|
"num_tokens": 25271705.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.142241430282593,
|
|
"epoch": 1.0774270399047052,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004896365135389709,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.20908144265413284,
|
|
"num_tokens": 25286963.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.116881418228149,
|
|
"epoch": 1.0780226325193567,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000489623726016343,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.20688092708587646,
|
|
"num_tokens": 25301953.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.141439390182495,
|
|
"epoch": 1.0786182251340084,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000489610930795511,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.21847102046012878,
|
|
"num_tokens": 25314417.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.200575065612793,
|
|
"epoch": 1.0792138177486599,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000489598127876934,
|
|
"loss": 4.8288,
|
|
"mean_token_accuracy": 0.21232869923114778,
|
|
"num_tokens": 25327555.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.039005184173584,
|
|
"epoch": 1.0798094103633116,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004895853172610709,
|
|
"loss": 4.8107,
|
|
"mean_token_accuracy": 0.20905042737722396,
|
|
"num_tokens": 25342840.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.104830265045166,
|
|
"epoch": 1.080405002977963,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004895724989483814,
|
|
"loss": 4.7435,
|
|
"mean_token_accuracy": 0.21740988940000533,
|
|
"num_tokens": 25354922.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.1597717761993405,
|
|
"epoch": 1.0810005955926147,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004895596729393252,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.210628542304039,
|
|
"num_tokens": 25370331.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.077929353713989,
|
|
"epoch": 1.0815961882072662,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004895468392343623,
|
|
"loss": 4.7572,
|
|
"mean_token_accuracy": 0.21291482597589492,
|
|
"num_tokens": 25383392.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.059962129592895,
|
|
"epoch": 1.0821917808219177,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004895339978339534,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.2167042762041092,
|
|
"num_tokens": 25395613.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.1479034423828125,
|
|
"epoch": 1.0827873734365694,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004895211487385586,
|
|
"loss": 4.7759,
|
|
"mean_token_accuracy": 0.20892425626516342,
|
|
"num_tokens": 25409141.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.117047309875488,
|
|
"epoch": 1.0833829660512209,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000489508291948639,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.20413924157619476,
|
|
"num_tokens": 25423128.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.063171768188477,
|
|
"epoch": 1.0839785586658726,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004894954274646557,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.20208020508289337,
|
|
"num_tokens": 25437641.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.0647937774658205,
|
|
"epoch": 1.084574151280524,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004894825552870703,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.20633695721626283,
|
|
"num_tokens": 25452719.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.098248434066773,
|
|
"epoch": 1.0851697438951757,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004894696754163442,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.2121065989136696,
|
|
"num_tokens": 25466239.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.114010906219482,
|
|
"epoch": 1.0857653365098272,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004894567878529397,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.21417551189661027,
|
|
"num_tokens": 25478477.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.1610918045043945,
|
|
"epoch": 1.086360929124479,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004894438925973189,
|
|
"loss": 4.8729,
|
|
"mean_token_accuracy": 0.19705216586589813,
|
|
"num_tokens": 25492525.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.185461235046387,
|
|
"epoch": 1.0869565217391304,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004894309896499443,
|
|
"loss": 4.9146,
|
|
"mean_token_accuracy": 0.20964380651712416,
|
|
"num_tokens": 25507725.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.177495050430298,
|
|
"epoch": 1.087552114353782,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004894180790112787,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.21045794785022737,
|
|
"num_tokens": 25522716.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.108553123474121,
|
|
"epoch": 1.0881477069684335,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004894051606817851,
|
|
"loss": 4.777,
|
|
"mean_token_accuracy": 0.21488006860017778,
|
|
"num_tokens": 25536805.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.061162090301513,
|
|
"epoch": 1.0887432995830852,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004893922346619272,
|
|
"loss": 4.7209,
|
|
"mean_token_accuracy": 0.21867688596248627,
|
|
"num_tokens": 25550253.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.104697275161743,
|
|
"epoch": 1.0893388921977367,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004893793009521684,
|
|
"loss": 4.8839,
|
|
"mean_token_accuracy": 0.2054370313882828,
|
|
"num_tokens": 25564975.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.172736883163452,
|
|
"epoch": 1.0899344848123884,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004893663595529725,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.21317766904830932,
|
|
"num_tokens": 25578467.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.1094322681427,
|
|
"epoch": 1.09053007742704,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000489353410464804,
|
|
"loss": 4.7912,
|
|
"mean_token_accuracy": 0.20879195183515548,
|
|
"num_tokens": 25591931.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.002699756622315,
|
|
"epoch": 1.0911256700416916,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004893404536881271,
|
|
"loss": 4.6243,
|
|
"mean_token_accuracy": 0.2147970974445343,
|
|
"num_tokens": 25605553.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.0797161102294925,
|
|
"epoch": 1.091721262656343,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004893274892234066,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.21428321301937103,
|
|
"num_tokens": 25620946.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.119762754440307,
|
|
"epoch": 1.0923168552709945,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004893145170711075,
|
|
"loss": 4.8296,
|
|
"mean_token_accuracy": 0.21233490258455276,
|
|
"num_tokens": 25633704.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.083192634582519,
|
|
"epoch": 1.0929124478856462,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004893015372316953,
|
|
"loss": 4.7661,
|
|
"mean_token_accuracy": 0.2123695805668831,
|
|
"num_tokens": 25646770.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.080183744430542,
|
|
"epoch": 1.0935080405002977,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004892885497056353,
|
|
"loss": 4.7997,
|
|
"mean_token_accuracy": 0.2059437394142151,
|
|
"num_tokens": 25660440.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.129262065887451,
|
|
"epoch": 1.0941036331149494,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004892755544933934,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.20603895634412767,
|
|
"num_tokens": 25673730.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.02286810874939,
|
|
"epoch": 1.0946992257296009,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004892625515954357,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.21705514192581177,
|
|
"num_tokens": 25688300.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.164815902709961,
|
|
"epoch": 1.0952948183442526,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004892495410122288,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.20383615791797638,
|
|
"num_tokens": 25702158.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.170638656616211,
|
|
"epoch": 1.095890410958904,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004892365227442392,
|
|
"loss": 4.8614,
|
|
"mean_token_accuracy": 0.20585092157125473,
|
|
"num_tokens": 25715505.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.098015356063843,
|
|
"epoch": 1.0964860035735557,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004892234967919337,
|
|
"loss": 4.7757,
|
|
"mean_token_accuracy": 0.21333049684762956,
|
|
"num_tokens": 25729566.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.114918994903564,
|
|
"epoch": 1.0970815961882072,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004892104631557797,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.2175240248441696,
|
|
"num_tokens": 25742777.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.15191535949707,
|
|
"epoch": 1.097677188802859,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004891974218362448,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.2017412781715393,
|
|
"num_tokens": 25757689.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.168026447296143,
|
|
"epoch": 1.0982727814175104,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004891843728337965,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.20952672362327576,
|
|
"num_tokens": 25770699.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.161900568008423,
|
|
"epoch": 1.098868374032162,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004891713161489031,
|
|
"loss": 4.8809,
|
|
"mean_token_accuracy": 0.20774952620267867,
|
|
"num_tokens": 25782692.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.080398273468018,
|
|
"epoch": 1.0994639666468136,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004891582517820328,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.21044551581144333,
|
|
"num_tokens": 25798900.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.148919773101807,
|
|
"epoch": 1.1000595592614653,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004891451797336541,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.2115256354212761,
|
|
"num_tokens": 25814443.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.184782838821411,
|
|
"epoch": 1.1006551518761167,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004891321000042361,
|
|
"loss": 4.8202,
|
|
"mean_token_accuracy": 0.21107107996940613,
|
|
"num_tokens": 25830620.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.046825885772705,
|
|
"epoch": 1.1012507444907684,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004891190125942478,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.21163716316223144,
|
|
"num_tokens": 25845364.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.062483549118042,
|
|
"epoch": 1.10184633710542,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004891059175041586,
|
|
"loss": 4.6637,
|
|
"mean_token_accuracy": 0.2189219370484352,
|
|
"num_tokens": 25858418.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.104993438720703,
|
|
"epoch": 1.1024419297200714,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004890928147344383,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.2159407243132591,
|
|
"num_tokens": 25870669.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.171875905990601,
|
|
"epoch": 1.103037522334723,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004890797042855569,
|
|
"loss": 4.8425,
|
|
"mean_token_accuracy": 0.20708916187286378,
|
|
"num_tokens": 25883785.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.189558696746826,
|
|
"epoch": 1.1036331149493745,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004890665861579845,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.20777952820062637,
|
|
"num_tokens": 25895566.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.174317979812622,
|
|
"epoch": 1.1042287075640262,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890534603521917,
|
|
"loss": 4.8372,
|
|
"mean_token_accuracy": 0.20915231704711915,
|
|
"num_tokens": 25908751.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.052730083465576,
|
|
"epoch": 1.1048243001786777,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004890403268686494,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.21950893551111222,
|
|
"num_tokens": 25922070.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.055852651596069,
|
|
"epoch": 1.1054198927933294,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004890271857078285,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.21853601783514023,
|
|
"num_tokens": 25935772.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.143687438964844,
|
|
"epoch": 1.106015485407981,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004890140368702003,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.21519884914159776,
|
|
"num_tokens": 25950443.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.079981803894043,
|
|
"epoch": 1.1066110780226326,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004890008803562368,
|
|
"loss": 4.7264,
|
|
"mean_token_accuracy": 0.2133280262351036,
|
|
"num_tokens": 25964585.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 4.987684440612793,
|
|
"epoch": 1.107206670637284,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 4.7016,
|
|
"mean_token_accuracy": 0.21636242270469666,
|
|
"num_tokens": 25977952.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.164033222198486,
|
|
"epoch": 1.1078022632519358,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004889745443011909,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.20726708471775054,
|
|
"num_tokens": 25993164.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.140723705291748,
|
|
"epoch": 1.1083978558665872,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004889613647610532,
|
|
"loss": 4.7814,
|
|
"mean_token_accuracy": 0.20881174206733705,
|
|
"num_tokens": 26007710.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.175624656677246,
|
|
"epoch": 1.108993448481239,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004889481775464692,
|
|
"loss": 4.8223,
|
|
"mean_token_accuracy": 0.20682681649923323,
|
|
"num_tokens": 26023311.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.158775043487549,
|
|
"epoch": 1.1095890410958904,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000488934982657912,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.209122134745121,
|
|
"num_tokens": 26037485.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 4.994678926467896,
|
|
"epoch": 1.110184633710542,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004889217800958548,
|
|
"loss": 4.6982,
|
|
"mean_token_accuracy": 0.214284984767437,
|
|
"num_tokens": 26053621.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.137152099609375,
|
|
"epoch": 1.1107802263251936,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004889085698607711,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.20987987518310547,
|
|
"num_tokens": 26066724.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.132687759399414,
|
|
"epoch": 1.111375818939845,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004888953519531349,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.20737578123807907,
|
|
"num_tokens": 26080818.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.186780023574829,
|
|
"epoch": 1.1119714115544967,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048888212637342,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.20567422807216645,
|
|
"num_tokens": 26096455.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.076623821258545,
|
|
"epoch": 1.1125670041691482,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004888688931221012,
|
|
"loss": 4.7759,
|
|
"mean_token_accuracy": 0.21223370730876923,
|
|
"num_tokens": 26113194.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.110510730743409,
|
|
"epoch": 1.1131625967838,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004888556521996529,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.20956113189458847,
|
|
"num_tokens": 26127489.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.159948205947876,
|
|
"epoch": 1.1137581893984514,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048884240360655,
|
|
"loss": 4.7657,
|
|
"mean_token_accuracy": 0.21548998206853867,
|
|
"num_tokens": 26140008.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.129664134979248,
|
|
"epoch": 1.114353782013103,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004888291473432678,
|
|
"loss": 4.8224,
|
|
"mean_token_accuracy": 0.20485147088766098,
|
|
"num_tokens": 26154849.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.108830118179322,
|
|
"epoch": 1.1149493746277546,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004888158834102816,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.2039340168237686,
|
|
"num_tokens": 26168600.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.123218774795532,
|
|
"epoch": 1.1155449672424063,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004888026118080675,
|
|
"loss": 4.8233,
|
|
"mean_token_accuracy": 0.21038224548101425,
|
|
"num_tokens": 26182933.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.157085609436035,
|
|
"epoch": 1.1161405598570577,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004887893325371013,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.20603585690259935,
|
|
"num_tokens": 26198152.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.025686645507813,
|
|
"epoch": 1.1167361524717094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004887760455978592,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.2211693912744522,
|
|
"num_tokens": 26212395.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.111611938476562,
|
|
"epoch": 1.117331745086361,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000488762750990818,
|
|
"loss": 4.761,
|
|
"mean_token_accuracy": 0.22104687094688416,
|
|
"num_tokens": 26226188.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.153337049484253,
|
|
"epoch": 1.1179273377010126,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004887494487164546,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.20817349702119828,
|
|
"num_tokens": 26242259.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.0928527355194095,
|
|
"epoch": 1.118522930315664,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004887361387752459,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.2107127994298935,
|
|
"num_tokens": 26256458.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.138862562179566,
|
|
"epoch": 1.1191185229303158,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004887228211676694,
|
|
"loss": 4.8065,
|
|
"mean_token_accuracy": 0.21230117231607437,
|
|
"num_tokens": 26270575.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.081882286071777,
|
|
"epoch": 1.1197141155449672,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004887094958942029,
|
|
"loss": 4.6768,
|
|
"mean_token_accuracy": 0.2188928559422493,
|
|
"num_tokens": 26283770.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.063848161697388,
|
|
"epoch": 1.1203097081596187,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004886961629553242,
|
|
"loss": 4.6875,
|
|
"mean_token_accuracy": 0.22074328362941742,
|
|
"num_tokens": 26296563.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.054387474060059,
|
|
"epoch": 1.1209053007742704,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004886828223515115,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.21863000988960266,
|
|
"num_tokens": 26310473.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.133524227142334,
|
|
"epoch": 1.121500893388922,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004886694740832434,
|
|
"loss": 4.8398,
|
|
"mean_token_accuracy": 0.2123277962207794,
|
|
"num_tokens": 26324953.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.136531352996826,
|
|
"epoch": 1.1220964860035736,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004886561181509988,
|
|
"loss": 4.7691,
|
|
"mean_token_accuracy": 0.210523621737957,
|
|
"num_tokens": 26337561.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.102759075164795,
|
|
"epoch": 1.122692078618225,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004886427545552567,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.21943832635879518,
|
|
"num_tokens": 26350953.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.030993223190308,
|
|
"epoch": 1.1232876712328768,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004886293832964961,
|
|
"loss": 4.724,
|
|
"mean_token_accuracy": 0.2130439817905426,
|
|
"num_tokens": 26365829.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.0886389255523685,
|
|
"epoch": 1.1238832638475282,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000488616004375197,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.21220109909772872,
|
|
"num_tokens": 26380938.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.081142234802246,
|
|
"epoch": 1.12447885646218,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000488602617791839,
|
|
"loss": 4.7272,
|
|
"mean_token_accuracy": 0.21321851015090942,
|
|
"num_tokens": 26394799.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.088978004455567,
|
|
"epoch": 1.1250744490768314,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004885892235469026,
|
|
"loss": 4.7568,
|
|
"mean_token_accuracy": 0.21017563194036484,
|
|
"num_tokens": 26408898.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.134984397888184,
|
|
"epoch": 1.125670041691483,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000488575821640868,
|
|
"loss": 4.7965,
|
|
"mean_token_accuracy": 0.21436019390821456,
|
|
"num_tokens": 26423104.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.1516509532928465,
|
|
"epoch": 1.1262656343061346,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004885624120742158,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.2098564863204956,
|
|
"num_tokens": 26437583.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.106500482559204,
|
|
"epoch": 1.1268612269207863,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004885489948474272,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.2165507271885872,
|
|
"num_tokens": 26449959.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.147189521789551,
|
|
"epoch": 1.1274568195354377,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004885355699609834,
|
|
"loss": 4.8616,
|
|
"mean_token_accuracy": 0.19820286333560944,
|
|
"num_tokens": 26461519.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.045877075195312,
|
|
"epoch": 1.1280524121500894,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004885221374153657,
|
|
"loss": 4.6828,
|
|
"mean_token_accuracy": 0.2153364509344101,
|
|
"num_tokens": 26474620.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.178341674804687,
|
|
"epoch": 1.128648004764741,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004885086972110563,
|
|
"loss": 4.8325,
|
|
"mean_token_accuracy": 0.20684239268302917,
|
|
"num_tokens": 26490599.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.143666458129883,
|
|
"epoch": 1.1292435973793924,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000488495249348537,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.21760233342647553,
|
|
"num_tokens": 26504071.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.1450025081634525,
|
|
"epoch": 1.129839189994044,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004884817938282902,
|
|
"loss": 4.8405,
|
|
"mean_token_accuracy": 0.2029558777809143,
|
|
"num_tokens": 26516308.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.076809883117676,
|
|
"epoch": 1.1304347826086956,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004884683306507987,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.22212740331888198,
|
|
"num_tokens": 26529271.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.077942609786987,
|
|
"epoch": 1.1310303752233473,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000488454859816545,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.2091490775346756,
|
|
"num_tokens": 26544514.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.065841007232666,
|
|
"epoch": 1.1316259678379987,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004884413813260127,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.21030309051275253,
|
|
"num_tokens": 26559582.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.100552225112915,
|
|
"epoch": 1.1322215604526504,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004884278951796851,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.21597006618976594,
|
|
"num_tokens": 26574002.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.086867427825927,
|
|
"epoch": 1.132817153067302,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004884144013780459,
|
|
"loss": 4.7509,
|
|
"mean_token_accuracy": 0.2222162202000618,
|
|
"num_tokens": 26587708.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.133012342453003,
|
|
"epoch": 1.1334127456819536,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004884008999215792,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.212900248169899,
|
|
"num_tokens": 26601548.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.102998065948486,
|
|
"epoch": 1.134008338296605,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000488387390810769,
|
|
"loss": 4.7402,
|
|
"mean_token_accuracy": 0.21425114423036576,
|
|
"num_tokens": 26615037.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.1633227348327635,
|
|
"epoch": 1.1346039309112568,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004883738740461001,
|
|
"loss": 4.8781,
|
|
"mean_token_accuracy": 0.20410791486501695,
|
|
"num_tokens": 26630510.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.081027221679688,
|
|
"epoch": 1.1351995235259082,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004883603496280573,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.21040312200784683,
|
|
"num_tokens": 26645720.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.076631546020508,
|
|
"epoch": 1.13579511614056,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004883468175571256,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.21235255599021913,
|
|
"num_tokens": 26658412.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.142853212356568,
|
|
"epoch": 1.1363907087552114,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004883332778337905,
|
|
"loss": 4.8081,
|
|
"mean_token_accuracy": 0.21551200300455092,
|
|
"num_tokens": 26672930.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.044628286361695,
|
|
"epoch": 1.1369863013698631,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004883197304585376,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.2250182405114174,
|
|
"num_tokens": 26688151.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.084400606155396,
|
|
"epoch": 1.1375818939845146,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004883061754318528,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.21559267044067382,
|
|
"num_tokens": 26701920.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.108040142059326,
|
|
"epoch": 1.138177486599166,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004882926127542222,
|
|
"loss": 4.8107,
|
|
"mean_token_accuracy": 0.207529316842556,
|
|
"num_tokens": 26717355.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.166854047775269,
|
|
"epoch": 1.1387730792138178,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004882790424261325,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.2052867203950882,
|
|
"num_tokens": 26734026.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.016953659057617,
|
|
"epoch": 1.1393686718284692,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004882654644480702,
|
|
"loss": 4.6772,
|
|
"mean_token_accuracy": 0.22186008840799332,
|
|
"num_tokens": 26748570.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.111245965957641,
|
|
"epoch": 1.139964264443121,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004882518788205225,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.2110672891139984,
|
|
"num_tokens": 26762227.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.070897722244263,
|
|
"epoch": 1.1405598570577724,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048823828554397664,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.21668891608715057,
|
|
"num_tokens": 26776884.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.128597927093506,
|
|
"epoch": 1.141155449672424,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004882246846189202,
|
|
"loss": 4.793,
|
|
"mean_token_accuracy": 0.20949785858392717,
|
|
"num_tokens": 26790470.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.0097963333129885,
|
|
"epoch": 1.1417510422870756,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00048821107604584096,
|
|
"loss": 4.6589,
|
|
"mean_token_accuracy": 0.22852914780378342,
|
|
"num_tokens": 26805188.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.108630800247193,
|
|
"epoch": 1.1423466349017273,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004881974598252271,
|
|
"loss": 4.7774,
|
|
"mean_token_accuracy": 0.20938942730426788,
|
|
"num_tokens": 26819680.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.061063528060913,
|
|
"epoch": 1.1429422275163788,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000488183835957567,
|
|
"loss": 4.7385,
|
|
"mean_token_accuracy": 0.21934699267148972,
|
|
"num_tokens": 26834138.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.03578667640686,
|
|
"epoch": 1.1435378201310304,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048817020444334936,
|
|
"loss": 4.7112,
|
|
"mean_token_accuracy": 0.21584356427192689,
|
|
"num_tokens": 26847147.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.102898740768433,
|
|
"epoch": 1.144133412745682,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048815656528306304,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.2205371156334877,
|
|
"num_tokens": 26860491.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.080540704727173,
|
|
"epoch": 1.1447290053603336,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004881429184771973,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.21511513590812684,
|
|
"num_tokens": 26875702.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.044608211517334,
|
|
"epoch": 1.145324597974985,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004881292640262416,
|
|
"loss": 4.7045,
|
|
"mean_token_accuracy": 0.2159467324614525,
|
|
"num_tokens": 26890724.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.0813416004180905,
|
|
"epoch": 1.1459201905896368,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004881156019306857,
|
|
"loss": 4.727,
|
|
"mean_token_accuracy": 0.2158544182777405,
|
|
"num_tokens": 26904920.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.118503856658935,
|
|
"epoch": 1.1465157832042883,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004881019321910198,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.20514730364084244,
|
|
"num_tokens": 26920289.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.0882219791412355,
|
|
"epoch": 1.1471113758189397,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048808825480773396,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.20562069863080978,
|
|
"num_tokens": 26932942.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 4.986104917526245,
|
|
"epoch": 1.1477069684335914,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004880745697813189,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.2242564857006073,
|
|
"num_tokens": 26948215.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.068514966964722,
|
|
"epoch": 1.148302561048243,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004880608771122654,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.21425673812627793,
|
|
"num_tokens": 26961402.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.093816328048706,
|
|
"epoch": 1.1488981536628946,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048804717680106475,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.21878189444541932,
|
|
"num_tokens": 26974476.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.077834224700927,
|
|
"epoch": 1.149493746277546,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004880334688482082,
|
|
"loss": 4.724,
|
|
"mean_token_accuracy": 0.22361875474452972,
|
|
"num_tokens": 26987384.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.177525472640991,
|
|
"epoch": 1.1500893388921978,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004880197532541875,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.20169489085674286,
|
|
"num_tokens": 27002829.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.087194776535034,
|
|
"epoch": 1.1506849315068493,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004880060300194947,
|
|
"loss": 4.6988,
|
|
"mean_token_accuracy": 0.2117103233933449,
|
|
"num_tokens": 27016638.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.076683759689331,
|
|
"epoch": 1.151280524121501,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004879922991446218,
|
|
"loss": 4.7372,
|
|
"mean_token_accuracy": 0.21307769566774368,
|
|
"num_tokens": 27030412.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.045311737060547,
|
|
"epoch": 1.1518761167361524,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048797856063006144,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.2172710344195366,
|
|
"num_tokens": 27043563.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.049429082870484,
|
|
"epoch": 1.1524717093508041,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048796481447630646,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.21865667700767516,
|
|
"num_tokens": 27058344.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.157071447372436,
|
|
"epoch": 1.1530673019654556,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048795106068384985,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.21219955384731293,
|
|
"num_tokens": 27071273.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.088050842285156,
|
|
"epoch": 1.1536628945801073,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004879372992531849,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.2154638111591339,
|
|
"num_tokens": 27085478.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.018187236785889,
|
|
"epoch": 1.1542584871947588,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004879235301848052,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.21499646455049515,
|
|
"num_tokens": 27098457.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.154622220993042,
|
|
"epoch": 1.1548540798094105,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004879097534792047,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.20623774081468582,
|
|
"num_tokens": 27113563.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.188105821609497,
|
|
"epoch": 1.155449672424062,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004878959691368776,
|
|
"loss": 4.7855,
|
|
"mean_token_accuracy": 0.21461879163980485,
|
|
"num_tokens": 27126221.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.128426218032837,
|
|
"epoch": 1.1560452650387134,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004878821771583181,
|
|
"loss": 4.772,
|
|
"mean_token_accuracy": 0.21516907066106797,
|
|
"num_tokens": 27137897.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.0430961608886715,
|
|
"epoch": 1.156640857653365,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048786837754402114,
|
|
"loss": 4.6824,
|
|
"mean_token_accuracy": 0.218320032954216,
|
|
"num_tokens": 27152880.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.100685358047485,
|
|
"epoch": 1.1572364502680166,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004878545702944815,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.21372529715299607,
|
|
"num_tokens": 27167204.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.033062076568603,
|
|
"epoch": 1.1578320428826683,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048784075541019454,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.2195582538843155,
|
|
"num_tokens": 27182732.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.126903772354126,
|
|
"epoch": 1.1584276354973198,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004878269328916557,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.203693950176239,
|
|
"num_tokens": 27198354.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.179881191253662,
|
|
"epoch": 1.1590232281119714,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004878131027393609,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.2040960505604744,
|
|
"num_tokens": 27212040.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.145464706420898,
|
|
"epoch": 1.159618820726623,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.000487799264953806,
|
|
"loss": 4.8176,
|
|
"mean_token_accuracy": 0.2112979143857956,
|
|
"num_tokens": 27225597.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.11765947341919,
|
|
"epoch": 1.1602144133412746,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048778541953548753,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.21296810656785964,
|
|
"num_tokens": 27240395.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.095719575881958,
|
|
"epoch": 1.160810005955926,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000487771566484902,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.21267236173152923,
|
|
"num_tokens": 27253457.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.081818914413452,
|
|
"epoch": 1.1614055985705778,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048775770580254636,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.21242358535528183,
|
|
"num_tokens": 27266406.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.136696529388428,
|
|
"epoch": 1.1620011911852293,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048774383748891774,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.21443676948547363,
|
|
"num_tokens": 27280366.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.103785705566406,
|
|
"epoch": 1.162596783799881,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048772996154451356,
|
|
"loss": 4.76,
|
|
"mean_token_accuracy": 0.21665974855422973,
|
|
"num_tokens": 27293471.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.103191614151001,
|
|
"epoch": 1.1631923764145324,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004877160779698315,
|
|
"loss": 4.6879,
|
|
"mean_token_accuracy": 0.21827892810106278,
|
|
"num_tokens": 27308564.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.0485834121704105,
|
|
"epoch": 1.1637879690291841,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048770218676536957,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.21421089619398118,
|
|
"num_tokens": 27321949.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.0509419441223145,
|
|
"epoch": 1.1643835616438356,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048768828793162614,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.21626509726047516,
|
|
"num_tokens": 27335422.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.135927343368531,
|
|
"epoch": 1.164979154258487,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004876743814690995,
|
|
"loss": 4.799,
|
|
"mean_token_accuracy": 0.21587759554386138,
|
|
"num_tokens": 27348607.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.088861036300659,
|
|
"epoch": 1.1655747468731388,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004876604673782887,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.215619321167469,
|
|
"num_tokens": 27364034.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.184890460968018,
|
|
"epoch": 1.1661703394877905,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004876465456596926,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.21061232537031174,
|
|
"num_tokens": 27378053.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.107333946228027,
|
|
"epoch": 1.166765932102442,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048763261631381075,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.2092966228723526,
|
|
"num_tokens": 27391871.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.13832278251648,
|
|
"epoch": 1.1673615247170934,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004876186793411426,
|
|
"loss": 4.8694,
|
|
"mean_token_accuracy": 0.20379515141248702,
|
|
"num_tokens": 27405472.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.081336116790771,
|
|
"epoch": 1.1679571173317451,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048760473474218814,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.2151399150490761,
|
|
"num_tokens": 27418757.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.051310014724732,
|
|
"epoch": 1.1685527099463966,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048759078251744747,
|
|
"loss": 4.6827,
|
|
"mean_token_accuracy": 0.21864848285913469,
|
|
"num_tokens": 27431375.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.078908634185791,
|
|
"epoch": 1.1691483025610483,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048757682266742115,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.2180253893136978,
|
|
"num_tokens": 27444739.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.132732725143432,
|
|
"epoch": 1.1697438951756998,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004875628551926098,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.21311752796173095,
|
|
"num_tokens": 27458580.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.138022184371948,
|
|
"epoch": 1.1703394877903515,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004875488800935144,
|
|
"loss": 4.7948,
|
|
"mean_token_accuracy": 0.20555733144283295,
|
|
"num_tokens": 27471844.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.081372499465942,
|
|
"epoch": 1.170935080405003,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004875348973706363,
|
|
"loss": 4.763,
|
|
"mean_token_accuracy": 0.21034434586763381,
|
|
"num_tokens": 27485777.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.111505222320557,
|
|
"epoch": 1.1715306730196546,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000487520907024477,
|
|
"loss": 4.7971,
|
|
"mean_token_accuracy": 0.20683573931455612,
|
|
"num_tokens": 27501350.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.063177251815796,
|
|
"epoch": 1.172126265634306,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048750690905553833,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.21999795883893966,
|
|
"num_tokens": 27514788.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.131145763397217,
|
|
"epoch": 1.1727218582489578,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004874929034643223,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.20356326550245285,
|
|
"num_tokens": 27531024.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.134463357925415,
|
|
"epoch": 1.1733174508636093,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004874788902513314,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.21034822911024093,
|
|
"num_tokens": 27545606.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.09910306930542,
|
|
"epoch": 1.1739130434782608,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004874648694170681,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.21900229752063752,
|
|
"num_tokens": 27561640.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.146020030975341,
|
|
"epoch": 1.1745086360929125,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048745084096203536,
|
|
"loss": 4.8114,
|
|
"mean_token_accuracy": 0.2147976979613304,
|
|
"num_tokens": 27574933.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.059779310226441,
|
|
"epoch": 1.1751042287075641,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004874368048867364,
|
|
"loss": 4.7067,
|
|
"mean_token_accuracy": 0.2142910361289978,
|
|
"num_tokens": 27589493.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.146832704544067,
|
|
"epoch": 1.1756998213222156,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048742276119167463,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.21688163727521897,
|
|
"num_tokens": 27603290.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.120478630065918,
|
|
"epoch": 1.176295413936867,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048740870987735383,
|
|
"loss": 4.7996,
|
|
"mean_token_accuracy": 0.21577620804309844,
|
|
"num_tokens": 27616792.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.155629348754883,
|
|
"epoch": 1.1768910065515188,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004873946509442779,
|
|
"loss": 4.8367,
|
|
"mean_token_accuracy": 0.21179769337177276,
|
|
"num_tokens": 27632646.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.053051710128784,
|
|
"epoch": 1.1774865991661703,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004873805843929512,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.21222757399082184,
|
|
"num_tokens": 27647433.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.091515445709229,
|
|
"epoch": 1.178082191780822,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004873665102238783,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.21350331008434295,
|
|
"num_tokens": 27661456.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.139657306671142,
|
|
"epoch": 1.1786777843954734,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048735242843756394,
|
|
"loss": 4.8709,
|
|
"mean_token_accuracy": 0.20826115608215331,
|
|
"num_tokens": 27676109.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.135034513473511,
|
|
"epoch": 1.1792733770101251,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004873383390345132,
|
|
"loss": 4.8117,
|
|
"mean_token_accuracy": 0.2041277527809143,
|
|
"num_tokens": 27690575.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.092693948745728,
|
|
"epoch": 1.1798689696247766,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048732424201523156,
|
|
"loss": 4.7928,
|
|
"mean_token_accuracy": 0.2088407337665558,
|
|
"num_tokens": 27704318.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.165721702575683,
|
|
"epoch": 1.1804645622394283,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004873101373802245,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.20128200352191924,
|
|
"num_tokens": 27719946.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.132372951507568,
|
|
"epoch": 1.1810601548540798,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004872960251299981,
|
|
"loss": 4.8189,
|
|
"mean_token_accuracy": 0.21174192428588867,
|
|
"num_tokens": 27734338.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.032425785064698,
|
|
"epoch": 1.1816557474687315,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048728190526505834,
|
|
"loss": 4.7015,
|
|
"mean_token_accuracy": 0.21193702071905135,
|
|
"num_tokens": 27750074.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.11120228767395,
|
|
"epoch": 1.182251340083383,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048726777778591184,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.2111811637878418,
|
|
"num_tokens": 27762879.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.122042465209961,
|
|
"epoch": 1.1828469326980344,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004872536426930653,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.21627118438482285,
|
|
"num_tokens": 27774492.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.0946883201599125,
|
|
"epoch": 1.1834425253126861,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004872394999870256,
|
|
"loss": 4.8078,
|
|
"mean_token_accuracy": 0.21357118040323259,
|
|
"num_tokens": 27789988.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.123398017883301,
|
|
"epoch": 1.1840381179273378,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048722534966830027,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.20778115093708038,
|
|
"num_tokens": 27806217.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.052970123291016,
|
|
"epoch": 1.1846337105419893,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048721119173739667,
|
|
"loss": 4.7107,
|
|
"mean_token_accuracy": 0.21850267201662063,
|
|
"num_tokens": 27821265.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.1031074047088625,
|
|
"epoch": 1.1852293031566408,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048719702619482255,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.20979789644479752,
|
|
"num_tokens": 27833977.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.056207323074341,
|
|
"epoch": 1.1858248957712925,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048718285304108613,
|
|
"loss": 4.653,
|
|
"mean_token_accuracy": 0.22439760714769363,
|
|
"num_tokens": 27847341.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.063553762435913,
|
|
"epoch": 1.186420488385944,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004871686722766958,
|
|
"loss": 4.6931,
|
|
"mean_token_accuracy": 0.22202793657779693,
|
|
"num_tokens": 27861364.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.0527318000793455,
|
|
"epoch": 1.1870160810005956,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048715448390216015,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.21167261451482772,
|
|
"num_tokens": 27875226.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.0647729396820065,
|
|
"epoch": 1.187611673615247,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048714028791798817,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.21608517020940782,
|
|
"num_tokens": 27887966.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.207310914993286,
|
|
"epoch": 1.1882072662298988,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004871260843246889,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.20955295860767365,
|
|
"num_tokens": 27903083.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.117490434646607,
|
|
"epoch": 1.1888028588445503,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048711187312277187,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.2152729332447052,
|
|
"num_tokens": 27916277.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.002702045440674,
|
|
"epoch": 1.189398451459202,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048709765431274686,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.20835181176662446,
|
|
"num_tokens": 27932543.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.1494362354278564,
|
|
"epoch": 1.1899940440738535,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004870834278951238,
|
|
"loss": 4.7903,
|
|
"mean_token_accuracy": 0.21532005220651626,
|
|
"num_tokens": 27948425.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.112181520462036,
|
|
"epoch": 1.1905896366885051,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004870691938704131,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.21978810727596282,
|
|
"num_tokens": 27962175.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.043657875061035,
|
|
"epoch": 1.1911852293031566,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004870549522391252,
|
|
"loss": 4.8093,
|
|
"mean_token_accuracy": 0.2035306841135025,
|
|
"num_tokens": 27976027.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.00992784500122,
|
|
"epoch": 1.191780821917808,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048704070300177094,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.21701682060956956,
|
|
"num_tokens": 27990532.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.1067304611206055,
|
|
"epoch": 1.1923764145324598,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048702644615886137,
|
|
"loss": 4.7419,
|
|
"mean_token_accuracy": 0.21428163945674897,
|
|
"num_tokens": 28004591.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.110615015029907,
|
|
"epoch": 1.1929720071471115,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004870121817109079,
|
|
"loss": 4.8086,
|
|
"mean_token_accuracy": 0.21344692409038543,
|
|
"num_tokens": 28019634.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.107333660125732,
|
|
"epoch": 1.193567599761763,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048699790965842224,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.21205149888992308,
|
|
"num_tokens": 28035388.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.135132884979248,
|
|
"epoch": 1.1941631923764144,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004869836300019162,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.2107624813914299,
|
|
"num_tokens": 28049666.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.075716161727906,
|
|
"epoch": 1.1947587849910661,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004869693427419021,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.2140372946858406,
|
|
"num_tokens": 28065059.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 4.977325868606568,
|
|
"epoch": 1.1953543776057176,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004869550478788922,
|
|
"loss": 4.5635,
|
|
"mean_token_accuracy": 0.2333416685461998,
|
|
"num_tokens": 28077567.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.081180286407471,
|
|
"epoch": 1.1959499702203693,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048694074541339946,
|
|
"loss": 4.7186,
|
|
"mean_token_accuracy": 0.21873088628053666,
|
|
"num_tokens": 28089741.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.147770023345947,
|
|
"epoch": 1.1965455628350208,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048692643534593665,
|
|
"loss": 4.841,
|
|
"mean_token_accuracy": 0.20877935737371445,
|
|
"num_tokens": 28104962.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.049217271804809,
|
|
"epoch": 1.1971411554496725,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004869121176770173,
|
|
"loss": 4.7032,
|
|
"mean_token_accuracy": 0.2168010115623474,
|
|
"num_tokens": 28119754.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.085090398788452,
|
|
"epoch": 1.197736748064324,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048689779240715484,
|
|
"loss": 4.6851,
|
|
"mean_token_accuracy": 0.2180337652564049,
|
|
"num_tokens": 28133638.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.052976608276367,
|
|
"epoch": 1.1983323406789756,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048688345953686296,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.21606846600770951,
|
|
"num_tokens": 28146706.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.169551944732666,
|
|
"epoch": 1.1989279332936271,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048686911906665597,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.20502034276723863,
|
|
"num_tokens": 28159104.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.070777702331543,
|
|
"epoch": 1.1995235259082788,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048685477099704816,
|
|
"loss": 4.773,
|
|
"mean_token_accuracy": 0.21599237471818925,
|
|
"num_tokens": 28173317.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.042007923126221,
|
|
"epoch": 1.2001191185229303,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048684041532855415,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.2159523159265518,
|
|
"num_tokens": 28186946.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.08794150352478,
|
|
"epoch": 1.2007147111375818,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004868260520616889,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.20968615412712097,
|
|
"num_tokens": 28201416.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.126212453842163,
|
|
"epoch": 1.2013103037522335,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048681168119696757,
|
|
"loss": 4.7827,
|
|
"mean_token_accuracy": 0.21534298062324525,
|
|
"num_tokens": 28215608.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.059923791885376,
|
|
"epoch": 1.2019058963668852,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004867973027349056,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.20928678214550017,
|
|
"num_tokens": 28228046.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.083116483688355,
|
|
"epoch": 1.2025014889815366,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004867829166760188,
|
|
"loss": 4.7352,
|
|
"mean_token_accuracy": 0.21275541186332703,
|
|
"num_tokens": 28241287.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.05580883026123,
|
|
"epoch": 1.2030970815961881,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048676852302082305,
|
|
"loss": 4.7203,
|
|
"mean_token_accuracy": 0.21977683901786804,
|
|
"num_tokens": 28253600.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.007792806625366,
|
|
"epoch": 1.2036926742108398,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004867541217698347,
|
|
"loss": 4.6578,
|
|
"mean_token_accuracy": 0.21573266237974167,
|
|
"num_tokens": 28266324.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.13236894607544,
|
|
"epoch": 1.2042882668254913,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00048673971292357025,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.2158218115568161,
|
|
"num_tokens": 28281222.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.069007539749146,
|
|
"epoch": 1.204883859440143,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004867252964825467,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.2117045685648918,
|
|
"num_tokens": 28296529.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.035825157165528,
|
|
"epoch": 1.2054794520547945,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048671087244728093,
|
|
"loss": 4.6817,
|
|
"mean_token_accuracy": 0.22802362889051436,
|
|
"num_tokens": 28311620.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 4.981909513473511,
|
|
"epoch": 1.2060750446694462,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048669644081829035,
|
|
"loss": 4.6195,
|
|
"mean_token_accuracy": 0.22713734954595566,
|
|
"num_tokens": 28324762.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.113273859024048,
|
|
"epoch": 1.2066706372840976,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048668200159609267,
|
|
"loss": 4.8247,
|
|
"mean_token_accuracy": 0.2073280081152916,
|
|
"num_tokens": 28338856.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.0097596645355225,
|
|
"epoch": 1.2072662298987493,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048666755478120576,
|
|
"loss": 4.5524,
|
|
"mean_token_accuracy": 0.2304200991988182,
|
|
"num_tokens": 28352171.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.081250858306885,
|
|
"epoch": 1.2078618225134008,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048665310037414777,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.21585011035203933,
|
|
"num_tokens": 28365027.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.056905126571655,
|
|
"epoch": 1.2084574151280525,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004866386383754373,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.21971324384212493,
|
|
"num_tokens": 28378495.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.02812647819519,
|
|
"epoch": 1.209053007742704,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004866241687855929,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.20700015872716904,
|
|
"num_tokens": 28392708.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.049591779708862,
|
|
"epoch": 1.2096486003573557,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048660969160513367,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.2216326951980591,
|
|
"num_tokens": 28406041.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.1067972660064695,
|
|
"epoch": 1.2102441929720071,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004865952068345788,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.20287846475839616,
|
|
"num_tokens": 28421522.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.093909168243409,
|
|
"epoch": 1.2108397855866588,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048658071447444794,
|
|
"loss": 4.7807,
|
|
"mean_token_accuracy": 0.2116684526205063,
|
|
"num_tokens": 28437974.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.145810556411743,
|
|
"epoch": 1.2114353782013103,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004865662145252609,
|
|
"loss": 4.7769,
|
|
"mean_token_accuracy": 0.20843886733055114,
|
|
"num_tokens": 28452111.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.079491519927979,
|
|
"epoch": 1.2120309708159618,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048655170698753774,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.21377092748880386,
|
|
"num_tokens": 28466008.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.080013942718506,
|
|
"epoch": 1.2126265634306135,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048653719186179874,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.2209400102496147,
|
|
"num_tokens": 28478610.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.029927539825439,
|
|
"epoch": 1.213222156045265,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004865226691485646,
|
|
"loss": 4.6977,
|
|
"mean_token_accuracy": 0.21987060606479644,
|
|
"num_tokens": 28493372.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.114395332336426,
|
|
"epoch": 1.2138177486599167,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048650813884835634,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.21036521941423417,
|
|
"num_tokens": 28507704.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.080484771728516,
|
|
"epoch": 1.2144133412745681,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004864936009616949,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.21261926740407944,
|
|
"num_tokens": 28522249.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.133411693572998,
|
|
"epoch": 1.2150089338892198,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000486479055489102,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.21258241236209868,
|
|
"num_tokens": 28534285.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.050037431716919,
|
|
"epoch": 1.2156045265038713,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004864645024310991,
|
|
"loss": 4.7301,
|
|
"mean_token_accuracy": 0.21558472663164138,
|
|
"num_tokens": 28547932.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.097560214996338,
|
|
"epoch": 1.216200119118523,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004864499417882084,
|
|
"loss": 4.724,
|
|
"mean_token_accuracy": 0.21598902195692063,
|
|
"num_tokens": 28559853.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.044958257675171,
|
|
"epoch": 1.2167957117331745,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000486435373560952,
|
|
"loss": 4.7611,
|
|
"mean_token_accuracy": 0.21336128264665605,
|
|
"num_tokens": 28573048.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.146153211593628,
|
|
"epoch": 1.2173913043478262,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048642079774985255,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.20427530705928804,
|
|
"num_tokens": 28586481.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.135902452468872,
|
|
"epoch": 1.2179868969624776,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048640621435543286,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.20943422317504884,
|
|
"num_tokens": 28601003.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.138334703445435,
|
|
"epoch": 1.2185824895771293,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000486391623378216,
|
|
"loss": 4.7495,
|
|
"mean_token_accuracy": 0.21705090403556823,
|
|
"num_tokens": 28614290.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.211790275573731,
|
|
"epoch": 1.2191780821917808,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004863770248187253,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.20962463915348054,
|
|
"num_tokens": 28627604.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.167331886291504,
|
|
"epoch": 1.2197736748064325,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004863624186774844,
|
|
"loss": 4.8168,
|
|
"mean_token_accuracy": 0.2144093096256256,
|
|
"num_tokens": 28640957.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.010699510574341,
|
|
"epoch": 1.220369267421084,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004863478049550171,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.21878811419010163,
|
|
"num_tokens": 28654664.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.09139609336853,
|
|
"epoch": 1.2209648600357355,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048633318365184783,
|
|
"loss": 4.7116,
|
|
"mean_token_accuracy": 0.217777019739151,
|
|
"num_tokens": 28669584.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.085193920135498,
|
|
"epoch": 1.2215604526503872,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048631855476850074,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.21023824959993362,
|
|
"num_tokens": 28684253.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.00111403465271,
|
|
"epoch": 1.2221560452650386,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048630391830550076,
|
|
"loss": 4.6262,
|
|
"mean_token_accuracy": 0.2257951721549034,
|
|
"num_tokens": 28698164.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.039229059219361,
|
|
"epoch": 1.2227516378796903,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004862892742633727,
|
|
"loss": 4.7221,
|
|
"mean_token_accuracy": 0.21854661256074906,
|
|
"num_tokens": 28712054.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.124612522125244,
|
|
"epoch": 1.2233472304943418,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000486274622642642,
|
|
"loss": 4.8174,
|
|
"mean_token_accuracy": 0.20729428380727768,
|
|
"num_tokens": 28725243.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.11459698677063,
|
|
"epoch": 1.2239428231089935,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048625996344383405,
|
|
"loss": 4.8005,
|
|
"mean_token_accuracy": 0.20908929258584977,
|
|
"num_tokens": 28740584.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.142807245254517,
|
|
"epoch": 1.224538415723645,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004862452966674747,
|
|
"loss": 4.7913,
|
|
"mean_token_accuracy": 0.21542464792728425,
|
|
"num_tokens": 28753390.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.079797649383545,
|
|
"epoch": 1.2251340083382967,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004862306223140901,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.21328348517417908,
|
|
"num_tokens": 28766479.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.121115207672119,
|
|
"epoch": 1.2257296009529481,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004862159403842064,
|
|
"loss": 4.7697,
|
|
"mean_token_accuracy": 0.21106517165899277,
|
|
"num_tokens": 28778670.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.1013960361480715,
|
|
"epoch": 1.2263251935675998,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048620125087835045,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.20734815597534179,
|
|
"num_tokens": 28790774.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.153951358795166,
|
|
"epoch": 1.2269207861822513,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004861865537970489,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.21644166260957717,
|
|
"num_tokens": 28805743.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.134754657745361,
|
|
"epoch": 1.227516378796903,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004861718491408291,
|
|
"loss": 4.8342,
|
|
"mean_token_accuracy": 0.2086245000362396,
|
|
"num_tokens": 28822125.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.116240835189819,
|
|
"epoch": 1.2281119714115545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004861571369102184,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.21362287700176238,
|
|
"num_tokens": 28835718.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.07932071685791,
|
|
"epoch": 1.2287075640262062,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004861424171057445,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.21104440242052078,
|
|
"num_tokens": 28848874.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.084657859802246,
|
|
"epoch": 1.2293031566408577,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004861276897279354,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.21691497415304184,
|
|
"num_tokens": 28861915.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.067553472518921,
|
|
"epoch": 1.2298987492555091,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004861129547773194,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.20715005993843078,
|
|
"num_tokens": 28875500.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.2000977993011475,
|
|
"epoch": 1.2304943418701608,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048609821225442494,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.213006192445755,
|
|
"num_tokens": 28888480.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.1459697723388675,
|
|
"epoch": 1.2310899344848123,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004860834621597808,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.21102100908756255,
|
|
"num_tokens": 28904680.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.071827030181884,
|
|
"epoch": 1.231685527099464,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048606870449391604,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.2156597703695297,
|
|
"num_tokens": 28919201.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.037603378295898,
|
|
"epoch": 1.2322811197141155,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004860539392573601,
|
|
"loss": 4.6471,
|
|
"mean_token_accuracy": 0.2233708918094635,
|
|
"num_tokens": 28930934.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.060216903686523,
|
|
"epoch": 1.2328767123287672,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048603916645064256,
|
|
"loss": 4.7419,
|
|
"mean_token_accuracy": 0.21683550179004668,
|
|
"num_tokens": 28942837.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.110366773605347,
|
|
"epoch": 1.2334723049434186,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048602438607429313,
|
|
"loss": 4.7418,
|
|
"mean_token_accuracy": 0.21320353597402572,
|
|
"num_tokens": 28956449.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.0842485427856445,
|
|
"epoch": 1.2340678975580703,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048600959812884217,
|
|
"loss": 4.7611,
|
|
"mean_token_accuracy": 0.21026803851127623,
|
|
"num_tokens": 28969654.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.106632947921753,
|
|
"epoch": 1.2346634901727218,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004859948026148199,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.20317149311304092,
|
|
"num_tokens": 28985242.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.126336193084716,
|
|
"epoch": 1.2352590827873735,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048597999953275717,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.20987137854099275,
|
|
"num_tokens": 29001167.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.091632127761841,
|
|
"epoch": 1.235854675402025,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048596518888318485,
|
|
"loss": 4.7179,
|
|
"mean_token_accuracy": 0.21769358664751054,
|
|
"num_tokens": 29015379.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.059624576568604,
|
|
"epoch": 1.2364502680166767,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048595037066663434,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.21201508939266206,
|
|
"num_tokens": 29029596.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.031740808486939,
|
|
"epoch": 1.2370458606313282,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004859355448836369,
|
|
"loss": 4.6654,
|
|
"mean_token_accuracy": 0.21774423122406006,
|
|
"num_tokens": 29043259.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.086722707748413,
|
|
"epoch": 1.2376414532459799,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00048592071153472446,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.21941217482089997,
|
|
"num_tokens": 29056084.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.100697565078735,
|
|
"epoch": 1.2382370458606313,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048590587062042907,
|
|
"loss": 4.7116,
|
|
"mean_token_accuracy": 0.22170991450548172,
|
|
"num_tokens": 29069785.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.050120449066162,
|
|
"epoch": 1.2388326384752828,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004858910221412829,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.22896369695663452,
|
|
"num_tokens": 29083751.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.081870412826538,
|
|
"epoch": 1.2394282310899345,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004858761660978188,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.2115928426384926,
|
|
"num_tokens": 29097398.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.144118213653565,
|
|
"epoch": 1.240023823704586,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004858613024905694,
|
|
"loss": 4.791,
|
|
"mean_token_accuracy": 0.20825098305940629,
|
|
"num_tokens": 29111787.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.109205722808838,
|
|
"epoch": 1.2406194163192377,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004858464313200679,
|
|
"loss": 4.7584,
|
|
"mean_token_accuracy": 0.21495575904846193,
|
|
"num_tokens": 29127130.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.079181432723999,
|
|
"epoch": 1.2412150089338891,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004858315525868478,
|
|
"loss": 4.7058,
|
|
"mean_token_accuracy": 0.21577922254800797,
|
|
"num_tokens": 29140343.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.129450798034668,
|
|
"epoch": 1.2418106015485408,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004858166662914426,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.2096116855740547,
|
|
"num_tokens": 29153710.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.104081869125366,
|
|
"epoch": 1.2424061941631923,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004858017724343864,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.21167834252119064,
|
|
"num_tokens": 29167736.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.079645490646362,
|
|
"epoch": 1.243001786777844,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048578687101621346,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.21494364142417907,
|
|
"num_tokens": 29179789.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.081763505935669,
|
|
"epoch": 1.2435973793924955,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000485771962037458,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.20713549852371216,
|
|
"num_tokens": 29192449.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.074944019317627,
|
|
"epoch": 1.2441929720071472,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048575704549865505,
|
|
"loss": 4.7673,
|
|
"mean_token_accuracy": 0.21694255173206328,
|
|
"num_tokens": 29203863.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.071632146835327,
|
|
"epoch": 1.2447885646217987,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048574212140033965,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.20983763933181762,
|
|
"num_tokens": 29217937.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.08571457862854,
|
|
"epoch": 1.2453841572364504,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048572718974304683,
|
|
"loss": 4.6598,
|
|
"mean_token_accuracy": 0.22010882198810577,
|
|
"num_tokens": 29231706.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.074212455749512,
|
|
"epoch": 1.2459797498511018,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048571225052731245,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.22098939269781112,
|
|
"num_tokens": 29242552.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.03963189125061,
|
|
"epoch": 1.2465753424657535,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048569730375367217,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.2184157758951187,
|
|
"num_tokens": 29256770.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.1189305782318115,
|
|
"epoch": 1.247170935080405,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048568234942266217,
|
|
"loss": 4.7492,
|
|
"mean_token_accuracy": 0.21805519610643387,
|
|
"num_tokens": 29270711.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.225402164459228,
|
|
"epoch": 1.2477665276950565,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048566738753481886,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.20152891129255296,
|
|
"num_tokens": 29285410.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.178777170181275,
|
|
"epoch": 1.2483621203097082,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004856524180906789,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.21808849424123763,
|
|
"num_tokens": 29299126.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.130902338027954,
|
|
"epoch": 1.2489577129243596,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048563744109077916,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.2111866906285286,
|
|
"num_tokens": 29313261.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.052660179138184,
|
|
"epoch": 1.2495533055390113,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004856224565356569,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.2183852195739746,
|
|
"num_tokens": 29327618.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.090760993957519,
|
|
"epoch": 1.2501488981536628,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048560746442584965,
|
|
"loss": 4.8035,
|
|
"mean_token_accuracy": 0.2148297354578972,
|
|
"num_tokens": 29342055.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.004829216003418,
|
|
"epoch": 1.2507444907683145,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000485592464761895,
|
|
"loss": 4.6521,
|
|
"mean_token_accuracy": 0.21892470270395278,
|
|
"num_tokens": 29355943.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.102649784088134,
|
|
"epoch": 1.251340083382966,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004855774575443311,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.21382016986608504,
|
|
"num_tokens": 29368462.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.113299894332886,
|
|
"epoch": 1.2519356759976177,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004855624427736961,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.20888904929161073,
|
|
"num_tokens": 29384441.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.147354793548584,
|
|
"epoch": 1.2525312686122692,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004855474204505287,
|
|
"loss": 4.8344,
|
|
"mean_token_accuracy": 0.2076205775141716,
|
|
"num_tokens": 29397802.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.060034227371216,
|
|
"epoch": 1.2531268612269209,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048553239057536757,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.22377095371484756,
|
|
"num_tokens": 29411999.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.098827171325683,
|
|
"epoch": 1.2537224538415723,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048551735314875203,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.2173004388809204,
|
|
"num_tokens": 29424844.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.097791385650635,
|
|
"epoch": 1.254318046456224,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004855023081712212,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.21769099533557892,
|
|
"num_tokens": 29438245.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.0678955078125,
|
|
"epoch": 1.2549136390708755,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004854872556433149,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.207384292781353,
|
|
"num_tokens": 29453304.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 4.989389324188233,
|
|
"epoch": 1.2555092316855272,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004854721955655729,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.2219428226351738,
|
|
"num_tokens": 29466662.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.07050256729126,
|
|
"epoch": 1.2561048243001787,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048545712793853554,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.21763503551483154,
|
|
"num_tokens": 29480953.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.094119596481323,
|
|
"epoch": 1.2567004169148301,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004854420527627431,
|
|
"loss": 4.7704,
|
|
"mean_token_accuracy": 0.2083369567990303,
|
|
"num_tokens": 29495630.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.12077898979187,
|
|
"epoch": 1.2572960095294818,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048542697003873636,
|
|
"loss": 4.7433,
|
|
"mean_token_accuracy": 0.21619222611188887,
|
|
"num_tokens": 29509426.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 4.944429206848144,
|
|
"epoch": 1.2578916021441335,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048541187976705645,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.21560807824134826,
|
|
"num_tokens": 29521836.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.119189596176147,
|
|
"epoch": 1.258487194758785,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004853967819482445,
|
|
"loss": 4.7935,
|
|
"mean_token_accuracy": 0.20696403086185455,
|
|
"num_tokens": 29536825.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.124304008483887,
|
|
"epoch": 1.2590827873734365,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000485381676582842,
|
|
"loss": 4.7799,
|
|
"mean_token_accuracy": 0.21297565400600432,
|
|
"num_tokens": 29549972.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.046988916397095,
|
|
"epoch": 1.2596783799880882,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048536656367139085,
|
|
"loss": 4.6856,
|
|
"mean_token_accuracy": 0.22065961956977845,
|
|
"num_tokens": 29563521.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.074641370773316,
|
|
"epoch": 1.2602739726027397,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048535144321443317,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.22144710421562194,
|
|
"num_tokens": 29576915.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.082714176177978,
|
|
"epoch": 1.2608695652173914,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048533631521251115,
|
|
"loss": 4.7651,
|
|
"mean_token_accuracy": 0.21498289555311204,
|
|
"num_tokens": 29590660.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.08029146194458,
|
|
"epoch": 1.2614651578320428,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004853211796661675,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.214959080517292,
|
|
"num_tokens": 29606364.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.109196472167969,
|
|
"epoch": 1.2620607504466945,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004853060365759451,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.22088099271059036,
|
|
"num_tokens": 29621361.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.044472169876099,
|
|
"epoch": 1.262656343061346,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00048529088594238714,
|
|
"loss": 4.7422,
|
|
"mean_token_accuracy": 0.2129343941807747,
|
|
"num_tokens": 29634945.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.0952962875366214,
|
|
"epoch": 1.2632519356759977,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004852757277660369,
|
|
"loss": 4.7235,
|
|
"mean_token_accuracy": 0.22488274723291396,
|
|
"num_tokens": 29649080.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.135135459899902,
|
|
"epoch": 1.2638475282906492,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048526056204743827,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.20314518362283707,
|
|
"num_tokens": 29663469.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.055833959579468,
|
|
"epoch": 1.2644431209053009,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048524538878713517,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.21202257722616197,
|
|
"num_tokens": 29676163.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.08028473854065,
|
|
"epoch": 1.2650387135199523,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004852302079856718,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.2208072066307068,
|
|
"num_tokens": 29690237.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.168832063674927,
|
|
"epoch": 1.2656343061346038,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004852150196435927,
|
|
"loss": 4.7789,
|
|
"mean_token_accuracy": 0.21574588418006896,
|
|
"num_tokens": 29704924.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.0343633651733395,
|
|
"epoch": 1.2662298987492555,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048519982376144254,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.22950420826673507,
|
|
"num_tokens": 29718855.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.1242899894714355,
|
|
"epoch": 1.2668254913639072,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048518462033976653,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.20929691344499587,
|
|
"num_tokens": 29732402.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.113747215270996,
|
|
"epoch": 1.2674210839785587,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048516940937910996,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.21022236496210098,
|
|
"num_tokens": 29747767.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.147992944717407,
|
|
"epoch": 1.2680166765932102,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004851541908800184,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.21343968212604522,
|
|
"num_tokens": 29759178.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.0815348625183105,
|
|
"epoch": 1.2686122692078619,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048513896484303763,
|
|
"loss": 4.7123,
|
|
"mean_token_accuracy": 0.21593091785907745,
|
|
"num_tokens": 29773164.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.051130723953247,
|
|
"epoch": 1.2692078618225133,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048512373126871383,
|
|
"loss": 4.635,
|
|
"mean_token_accuracy": 0.2216097295284271,
|
|
"num_tokens": 29786783.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.131823635101318,
|
|
"epoch": 1.269803454437165,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004851084901575935,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.2141844466328621,
|
|
"num_tokens": 29800920.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.059316110610962,
|
|
"epoch": 1.2703990470518165,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048509324151022325,
|
|
"loss": 4.6686,
|
|
"mean_token_accuracy": 0.21852324306964874,
|
|
"num_tokens": 29815100.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.027430486679077,
|
|
"epoch": 1.2709946396664682,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048507798532715005,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.21172737926244736,
|
|
"num_tokens": 29827513.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.127364444732666,
|
|
"epoch": 1.2715902322811197,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000485062721608921,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.21122190207242966,
|
|
"num_tokens": 29840111.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.113210964202881,
|
|
"epoch": 1.2721858248957714,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004850474503560837,
|
|
"loss": 4.7495,
|
|
"mean_token_accuracy": 0.21547822952270507,
|
|
"num_tokens": 29854007.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.083609104156494,
|
|
"epoch": 1.2727814175104228,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004850321715691858,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.21844643950462342,
|
|
"num_tokens": 29868743.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.094195365905762,
|
|
"epoch": 1.2733770101250745,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048501688524877555,
|
|
"loss": 4.7076,
|
|
"mean_token_accuracy": 0.21845536381006242,
|
|
"num_tokens": 29882958.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.040835285186768,
|
|
"epoch": 1.273972602739726,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000485001591395401,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.21432363092899323,
|
|
"num_tokens": 29898769.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.019916629791259,
|
|
"epoch": 1.2745681953543775,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004849862900096108,
|
|
"loss": 4.6734,
|
|
"mean_token_accuracy": 0.22355999797582626,
|
|
"num_tokens": 29914149.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.014545488357544,
|
|
"epoch": 1.2751637879690292,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048497098109195387,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.2208660811185837,
|
|
"num_tokens": 29927092.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.060800504684448,
|
|
"epoch": 1.2757593805836809,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048495566464297913,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.22182293534278869,
|
|
"num_tokens": 29942033.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.178141117095947,
|
|
"epoch": 1.2763549731983324,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004849403406632361,
|
|
"loss": 4.8082,
|
|
"mean_token_accuracy": 0.21190335899591445,
|
|
"num_tokens": 29954987.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.039294147491455,
|
|
"epoch": 1.2769505658129838,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004849250091532744,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.22427250891923906,
|
|
"num_tokens": 29968227.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.061319160461426,
|
|
"epoch": 1.2775461584276355,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048490967011364394,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.2230926588177681,
|
|
"num_tokens": 29981234.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.181216192245484,
|
|
"epoch": 1.278141751042287,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048489432354489496,
|
|
"loss": 4.8682,
|
|
"mean_token_accuracy": 0.21379023790359497,
|
|
"num_tokens": 29994420.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.088354301452637,
|
|
"epoch": 1.2787373436569387,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048487896944757777,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.2180277317762375,
|
|
"num_tokens": 30007241.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.076921796798706,
|
|
"epoch": 1.2793329362715902,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004848636078222433,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.21463209986686707,
|
|
"num_tokens": 30021804.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.123570919036865,
|
|
"epoch": 1.2799285288862419,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004848482386694424,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.21716968566179276,
|
|
"num_tokens": 30035782.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.066223573684693,
|
|
"epoch": 1.2805241215008933,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048483286198972627,
|
|
"loss": 4.7326,
|
|
"mean_token_accuracy": 0.21022755205631255,
|
|
"num_tokens": 30051157.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.056766080856323,
|
|
"epoch": 1.281119714115545,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004848174777836466,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.21699768900871277,
|
|
"num_tokens": 30066360.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.129126405715942,
|
|
"epoch": 1.2817153067301965,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004848020860517552,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.21094697266817092,
|
|
"num_tokens": 30079714.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.065632915496826,
|
|
"epoch": 1.2823108993448482,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000484786686794604,
|
|
"loss": 4.7067,
|
|
"mean_token_accuracy": 0.22101722955703734,
|
|
"num_tokens": 30091880.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.079112958908081,
|
|
"epoch": 1.2829064919594997,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048477128001274557,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.2205980733036995,
|
|
"num_tokens": 30105211.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.072791337966919,
|
|
"epoch": 1.2835020845741512,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048475586570673223,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.21840990632772445,
|
|
"num_tokens": 30121064.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.029682970046997,
|
|
"epoch": 1.2840976771888029,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004847404438771172,
|
|
"loss": 4.7169,
|
|
"mean_token_accuracy": 0.21642858237028123,
|
|
"num_tokens": 30135347.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.034801006317139,
|
|
"epoch": 1.2846932698034546,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048472501452445334,
|
|
"loss": 4.7111,
|
|
"mean_token_accuracy": 0.2166202187538147,
|
|
"num_tokens": 30149652.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.1654585838317875,
|
|
"epoch": 1.285288862418106,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004847095776492942,
|
|
"loss": 4.8288,
|
|
"mean_token_accuracy": 0.20724356770515442,
|
|
"num_tokens": 30165003.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.130265617370606,
|
|
"epoch": 1.2858844550327575,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048469413325219355,
|
|
"loss": 4.8609,
|
|
"mean_token_accuracy": 0.2137702375650406,
|
|
"num_tokens": 30179567.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.038681507110596,
|
|
"epoch": 1.2864800476474092,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048467868133370527,
|
|
"loss": 4.6537,
|
|
"mean_token_accuracy": 0.21994829028844834,
|
|
"num_tokens": 30193773.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.04768967628479,
|
|
"epoch": 1.2870756402620607,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048466322189438354,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.2203361228108406,
|
|
"num_tokens": 30208233.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.131940126419067,
|
|
"epoch": 1.2876712328767124,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048464775493478303,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.2112637147307396,
|
|
"num_tokens": 30223136.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.112301683425903,
|
|
"epoch": 1.2882668254913638,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048463228045545837,
|
|
"loss": 4.7292,
|
|
"mean_token_accuracy": 0.22494020611047744,
|
|
"num_tokens": 30236549.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.023993682861328,
|
|
"epoch": 1.2888624181060155,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048461679845696466,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.21532781273126603,
|
|
"num_tokens": 30251870.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.071002054214477,
|
|
"epoch": 1.289458010720667,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004846013089398572,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.21584085673093795,
|
|
"num_tokens": 30266649.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.041169023513794,
|
|
"epoch": 1.2900536033353187,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048458581190469153,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.2266119346022606,
|
|
"num_tokens": 30279811.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.058982515335083,
|
|
"epoch": 1.2906491959499702,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004845703073520236,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.21801775991916655,
|
|
"num_tokens": 30291950.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.034642124176026,
|
|
"epoch": 1.2912447885646219,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004845547952824095,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.22108678370714188,
|
|
"num_tokens": 30304289.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.053299140930176,
|
|
"epoch": 1.2918403811792734,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048453927569640557,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.21525705754756927,
|
|
"num_tokens": 30318182.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.071677112579346,
|
|
"epoch": 1.2924359737939248,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048452374859456855,
|
|
"loss": 4.7436,
|
|
"mean_token_accuracy": 0.22393852919340135,
|
|
"num_tokens": 30330470.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.089022874832153,
|
|
"epoch": 1.2930315664085765,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004845082139774553,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.2226005971431732,
|
|
"num_tokens": 30345544.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.09156231880188,
|
|
"epoch": 1.2936271590232282,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004844926718456231,
|
|
"loss": 4.7609,
|
|
"mean_token_accuracy": 0.22597862780094147,
|
|
"num_tokens": 30358952.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.060569953918457,
|
|
"epoch": 1.2942227516378797,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004844771221996293,
|
|
"loss": 4.7173,
|
|
"mean_token_accuracy": 0.22091517001390457,
|
|
"num_tokens": 30372652.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.080519580841065,
|
|
"epoch": 1.2948183442525312,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004844615650400318,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.2123303234577179,
|
|
"num_tokens": 30385439.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.068361902236939,
|
|
"epoch": 1.2954139368671829,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048444600036738844,
|
|
"loss": 4.7295,
|
|
"mean_token_accuracy": 0.21759775578975676,
|
|
"num_tokens": 30399006.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.085919427871704,
|
|
"epoch": 1.2960095294818343,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048443042818225766,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.21927937716245652,
|
|
"num_tokens": 30412143.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.120971775054931,
|
|
"epoch": 1.296605122096486,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048441484848519786,
|
|
"loss": 4.776,
|
|
"mean_token_accuracy": 0.21683505028486252,
|
|
"num_tokens": 30424874.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.139245223999024,
|
|
"epoch": 1.2972007147111375,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048439926127676796,
|
|
"loss": 4.7905,
|
|
"mean_token_accuracy": 0.21421439498662947,
|
|
"num_tokens": 30438938.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.105907964706421,
|
|
"epoch": 1.2977963073257892,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048438366655752707,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.21552451848983764,
|
|
"num_tokens": 30453470.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.095156049728393,
|
|
"epoch": 1.2983918999404407,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004843680643280345,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.21584622114896773,
|
|
"num_tokens": 30466463.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.115495395660401,
|
|
"epoch": 1.2989874925550924,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004843524545888498,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.22219110876321793,
|
|
"num_tokens": 30481241.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.068651962280273,
|
|
"epoch": 1.2995830851697439,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000484336837340533,
|
|
"loss": 4.676,
|
|
"mean_token_accuracy": 0.21753981113433837,
|
|
"num_tokens": 30493346.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.01164059638977,
|
|
"epoch": 1.3001786777843956,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048432121258364417,
|
|
"loss": 4.7525,
|
|
"mean_token_accuracy": 0.21819172352552413,
|
|
"num_tokens": 30510073.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.122398948669433,
|
|
"epoch": 1.300774270399047,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004843055803187438,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.2135274514555931,
|
|
"num_tokens": 30524480.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.1599937915802006,
|
|
"epoch": 1.3013698630136985,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048428994054639256,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.20841917842626573,
|
|
"num_tokens": 30539502.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.081346035003662,
|
|
"epoch": 1.3019654556283502,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004842742932671514,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.20980944335460663,
|
|
"num_tokens": 30553974.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.062034463882446,
|
|
"epoch": 1.302561048243002,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004842586384815817,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.21450783610343932,
|
|
"num_tokens": 30567445.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.043261098861694,
|
|
"epoch": 1.3031566408576534,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004842429761902448,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.2152729019522667,
|
|
"num_tokens": 30581835.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.033901166915894,
|
|
"epoch": 1.3037522334723048,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048422730639370256,
|
|
"loss": 4.6625,
|
|
"mean_token_accuracy": 0.21844639182090758,
|
|
"num_tokens": 30595851.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.068371391296386,
|
|
"epoch": 1.3043478260869565,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004842116290925171,
|
|
"loss": 4.7002,
|
|
"mean_token_accuracy": 0.2250771254301071,
|
|
"num_tokens": 30610732.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.088637399673462,
|
|
"epoch": 1.3049434187016082,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004841959442872505,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.21550360023975373,
|
|
"num_tokens": 30624836.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.0092360496521,
|
|
"epoch": 1.3055390113162597,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004841802519784656,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.2195701703429222,
|
|
"num_tokens": 30638860.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.036838436126709,
|
|
"epoch": 1.3061346039309112,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048416455216672525,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.2189900442957878,
|
|
"num_tokens": 30652660.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.124470853805542,
|
|
"epoch": 1.3067301965455629,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048414884485259235,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.21648158878087997,
|
|
"num_tokens": 30664181.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.063137722015381,
|
|
"epoch": 1.3073257891602144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004841331300366306,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.2147515371441841,
|
|
"num_tokens": 30676795.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.043116521835327,
|
|
"epoch": 1.307921381774866,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004841174077194033,
|
|
"loss": 4.7916,
|
|
"mean_token_accuracy": 0.21586713045835496,
|
|
"num_tokens": 30690173.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.092206382751465,
|
|
"epoch": 1.3085169743895175,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004841016779014747,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.21878390312194823,
|
|
"num_tokens": 30704490.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.083189630508423,
|
|
"epoch": 1.3091125670041692,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048408594058340894,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.21717534065246583,
|
|
"num_tokens": 30720148.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.103127431869507,
|
|
"epoch": 1.3097081596188207,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048407019576577037,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.21465280503034592,
|
|
"num_tokens": 30733307.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.050525140762329,
|
|
"epoch": 1.3103037522334722,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004840544434491238,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.21830625981092452,
|
|
"num_tokens": 30747455.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.185862922668457,
|
|
"epoch": 1.3108993448481239,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048403868363403437,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.2056407630443573,
|
|
"num_tokens": 30763173.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.115529870986938,
|
|
"epoch": 1.3114949374627756,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004840229163210671,
|
|
"loss": 4.7588,
|
|
"mean_token_accuracy": 0.21843291670084,
|
|
"num_tokens": 30777676.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.1092359066009525,
|
|
"epoch": 1.312090530077427,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048400714151078774,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.21684316992759706,
|
|
"num_tokens": 30792155.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.125505542755127,
|
|
"epoch": 1.3126861226920785,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048399135920376197,
|
|
"loss": 4.7674,
|
|
"mean_token_accuracy": 0.21879560947418214,
|
|
"num_tokens": 30805042.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.079707336425781,
|
|
"epoch": 1.3132817153067302,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000483975569400556,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.2141605868935585,
|
|
"num_tokens": 30821069.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.112805271148682,
|
|
"epoch": 1.313877307921382,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048395977210173607,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.21762364208698273,
|
|
"num_tokens": 30835442.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.009592056274414,
|
|
"epoch": 1.3144729005360334,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004839439673078689,
|
|
"loss": 4.6682,
|
|
"mean_token_accuracy": 0.22842734754085542,
|
|
"num_tokens": 30848691.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.094810581207275,
|
|
"epoch": 1.3150684931506849,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004839281550195214,
|
|
"loss": 4.7493,
|
|
"mean_token_accuracy": 0.21579935997724534,
|
|
"num_tokens": 30863023.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.113491106033325,
|
|
"epoch": 1.3156640857653366,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004839123352372606,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.21953235268592836,
|
|
"num_tokens": 30877280.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.069425010681153,
|
|
"epoch": 1.316259678379988,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048389650796165407,
|
|
"loss": 4.7825,
|
|
"mean_token_accuracy": 0.21173809468746185,
|
|
"num_tokens": 30891460.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.028025388717651,
|
|
"epoch": 1.3168552709946397,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048388067319326937,
|
|
"loss": 4.685,
|
|
"mean_token_accuracy": 0.2223370313644409,
|
|
"num_tokens": 30906012.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.117925453186035,
|
|
"epoch": 1.3174508636092912,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048386483093267464,
|
|
"loss": 4.8307,
|
|
"mean_token_accuracy": 0.20716989785432816,
|
|
"num_tokens": 30921866.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.1385962009429935,
|
|
"epoch": 1.318046456223943,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004838489811804379,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.20440768003463744,
|
|
"num_tokens": 30936526.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.069941139221191,
|
|
"epoch": 1.3186420488385944,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048383312393712784,
|
|
"loss": 4.6739,
|
|
"mean_token_accuracy": 0.22229950577020646,
|
|
"num_tokens": 30951960.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.044635152816772,
|
|
"epoch": 1.3192376414532458,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004838172592033132,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.21995973736047744,
|
|
"num_tokens": 30966927.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.086978530883789,
|
|
"epoch": 1.3198332340678975,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048380138697956294,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.21935055851936341,
|
|
"num_tokens": 30980808.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.053182935714721,
|
|
"epoch": 1.3204288266825492,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048378550726644644,
|
|
"loss": 4.6748,
|
|
"mean_token_accuracy": 0.2181550681591034,
|
|
"num_tokens": 30995105.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.029636096954346,
|
|
"epoch": 1.3210244192972007,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048376962006453324,
|
|
"loss": 4.6565,
|
|
"mean_token_accuracy": 0.22636539489030838,
|
|
"num_tokens": 31009647.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.107667636871338,
|
|
"epoch": 1.3216200119118522,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004837537253743932,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.21792885512113572,
|
|
"num_tokens": 31023861.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.071812343597412,
|
|
"epoch": 1.3222156045265039,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004837378231965965,
|
|
"loss": 4.7657,
|
|
"mean_token_accuracy": 0.2187174901366234,
|
|
"num_tokens": 31037075.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.05775465965271,
|
|
"epoch": 1.3228111971411556,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048372191353171333,
|
|
"loss": 4.6552,
|
|
"mean_token_accuracy": 0.22527401447296141,
|
|
"num_tokens": 31049198.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.083940124511718,
|
|
"epoch": 1.323406789755807,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048370599638031464,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.22032149285078048,
|
|
"num_tokens": 31063980.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.125510597229004,
|
|
"epoch": 1.3240023823704585,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048369007174297115,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.21408936381340027,
|
|
"num_tokens": 31078561.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.0599119663238525,
|
|
"epoch": 1.3245979749851102,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.000483674139620254,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.222470985352993,
|
|
"num_tokens": 31094704.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.106230926513672,
|
|
"epoch": 1.3251935675997617,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004836582000127349,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.20755754858255387,
|
|
"num_tokens": 31109003.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.027010583877564,
|
|
"epoch": 1.3257891602144134,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004836422529209853,
|
|
"loss": 4.7017,
|
|
"mean_token_accuracy": 0.22349957525730133,
|
|
"num_tokens": 31123287.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.0658941745758055,
|
|
"epoch": 1.3263847528290649,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048362629834557743,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.22378737479448318,
|
|
"num_tokens": 31138199.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.099581575393676,
|
|
"epoch": 1.3269803454437166,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048361033628708334,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.21592345982789993,
|
|
"num_tokens": 31150897.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.027634572982788,
|
|
"epoch": 1.327575938058368,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048359436674607573,
|
|
"loss": 4.6574,
|
|
"mean_token_accuracy": 0.22047366499900817,
|
|
"num_tokens": 31164075.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.07787389755249,
|
|
"epoch": 1.3281715306730195,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004835783897231273,
|
|
"loss": 4.7357,
|
|
"mean_token_accuracy": 0.21575111746788025,
|
|
"num_tokens": 31176274.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.085603427886963,
|
|
"epoch": 1.3287671232876712,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048356240521881113,
|
|
"loss": 4.7465,
|
|
"mean_token_accuracy": 0.2136189341545105,
|
|
"num_tokens": 31190227.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.091238498687744,
|
|
"epoch": 1.329362715902323,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004835464132337007,
|
|
"loss": 4.6986,
|
|
"mean_token_accuracy": 0.21687227338552476,
|
|
"num_tokens": 31201717.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.096542501449585,
|
|
"epoch": 1.3299583085169744,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048353041376836937,
|
|
"loss": 4.7764,
|
|
"mean_token_accuracy": 0.21503847986459732,
|
|
"num_tokens": 31216612.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.12487645149231,
|
|
"epoch": 1.3305539011316259,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048351440682339126,
|
|
"loss": 4.7526,
|
|
"mean_token_accuracy": 0.21536355465650558,
|
|
"num_tokens": 31230146.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.041668653488159,
|
|
"epoch": 1.3311494937462776,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048349839239934035,
|
|
"loss": 4.6734,
|
|
"mean_token_accuracy": 0.23132869303226472,
|
|
"num_tokens": 31245278.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.083516693115234,
|
|
"epoch": 1.3317450863609293,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048348237049679105,
|
|
"loss": 4.7213,
|
|
"mean_token_accuracy": 0.21318467408418657,
|
|
"num_tokens": 31260846.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.0636937618255615,
|
|
"epoch": 1.3323406789755807,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004834663411163182,
|
|
"loss": 4.7157,
|
|
"mean_token_accuracy": 0.21445562392473222,
|
|
"num_tokens": 31274007.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.051767587661743,
|
|
"epoch": 1.3329362715902322,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004834503042584966,
|
|
"loss": 4.7203,
|
|
"mean_token_accuracy": 0.21436796188354493,
|
|
"num_tokens": 31287739.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.02935299873352,
|
|
"epoch": 1.333531864204884,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004834342599239015,
|
|
"loss": 4.652,
|
|
"mean_token_accuracy": 0.2186615511775017,
|
|
"num_tokens": 31301601.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.059824228286743,
|
|
"epoch": 1.3341274568195354,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048341820811310834,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.21229389756917955,
|
|
"num_tokens": 31315297.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.020195865631104,
|
|
"epoch": 1.334723049434187,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048340214882669296,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.22330247908830642,
|
|
"num_tokens": 31330167.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.0268701076507565,
|
|
"epoch": 1.3353186420488385,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004833860820652314,
|
|
"loss": 4.5819,
|
|
"mean_token_accuracy": 0.230769282579422,
|
|
"num_tokens": 31343704.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.056244039535523,
|
|
"epoch": 1.3359142346634902,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004833700078292998,
|
|
"loss": 4.7248,
|
|
"mean_token_accuracy": 0.22303924709558487,
|
|
"num_tokens": 31355397.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.155304765701294,
|
|
"epoch": 1.3365098272781417,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004833539261194749,
|
|
"loss": 4.8521,
|
|
"mean_token_accuracy": 0.20785643458366393,
|
|
"num_tokens": 31369355.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.120462799072266,
|
|
"epoch": 1.3371054198927934,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004833378369363333,
|
|
"loss": 4.7657,
|
|
"mean_token_accuracy": 0.21140861213207246,
|
|
"num_tokens": 31383322.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.0482793807983395,
|
|
"epoch": 1.3377010125074449,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004833217402804523,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.21494070142507554,
|
|
"num_tokens": 31396900.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.049555015563965,
|
|
"epoch": 1.3382966051220966,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004833056361524092,
|
|
"loss": 4.7568,
|
|
"mean_token_accuracy": 0.21585899442434311,
|
|
"num_tokens": 31413277.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.043293046951294,
|
|
"epoch": 1.338892197736748,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004832895245527816,
|
|
"loss": 4.6819,
|
|
"mean_token_accuracy": 0.22120811492204667,
|
|
"num_tokens": 31428005.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.011766147613526,
|
|
"epoch": 1.3394877903513995,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004832734054821474,
|
|
"loss": 4.6419,
|
|
"mean_token_accuracy": 0.23069145828485488,
|
|
"num_tokens": 31440418.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.097989463806153,
|
|
"epoch": 1.3400833829660512,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048325727894108487,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.21191408187150956,
|
|
"num_tokens": 31453431.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.052160739898682,
|
|
"epoch": 1.340678975580703,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004832411449301723,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.21454216539859772,
|
|
"num_tokens": 31469490.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.0731171607971195,
|
|
"epoch": 1.3412745681953544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004832250034499884,
|
|
"loss": 4.692,
|
|
"mean_token_accuracy": 0.21886106580495834,
|
|
"num_tokens": 31482110.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.100617980957031,
|
|
"epoch": 1.3418701608100059,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004832088545011122,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.20782603621482848,
|
|
"num_tokens": 31494104.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.053195953369141,
|
|
"epoch": 1.3424657534246576,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004831926980841229,
|
|
"loss": 4.7293,
|
|
"mean_token_accuracy": 0.21932445615530013,
|
|
"num_tokens": 31507503.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.078162717819214,
|
|
"epoch": 1.343061346039309,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048317653419960007,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.2210163041949272,
|
|
"num_tokens": 31521213.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.111261892318725,
|
|
"epoch": 1.3436569386539607,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048316036284812335,
|
|
"loss": 4.7776,
|
|
"mean_token_accuracy": 0.21233008950948715,
|
|
"num_tokens": 31536552.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.109111738204956,
|
|
"epoch": 1.3442525312686122,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004831441840302729,
|
|
"loss": 4.7369,
|
|
"mean_token_accuracy": 0.21538686603307725,
|
|
"num_tokens": 31550663.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 4.989102363586426,
|
|
"epoch": 1.344848123883264,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048312799774662905,
|
|
"loss": 4.6711,
|
|
"mean_token_accuracy": 0.21785119622945787,
|
|
"num_tokens": 31565694.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.0630255222320555,
|
|
"epoch": 1.3454437164979154,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004831118039977722,
|
|
"loss": 4.693,
|
|
"mean_token_accuracy": 0.2210809111595154,
|
|
"num_tokens": 31581533.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.072645235061645,
|
|
"epoch": 1.346039309112567,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004830956027842834,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.21656236052513123,
|
|
"num_tokens": 31594439.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.053101634979248,
|
|
"epoch": 1.3466349017272186,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004830793941067437,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.22060758322477342,
|
|
"num_tokens": 31609080.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.07521276473999,
|
|
"epoch": 1.3472304943418703,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048306317796573426,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.22120178788900374,
|
|
"num_tokens": 31623017.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.171582412719727,
|
|
"epoch": 1.3478260869565217,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004830469543618371,
|
|
"loss": 4.8181,
|
|
"mean_token_accuracy": 0.20284496247768402,
|
|
"num_tokens": 31636845.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.0491523265838625,
|
|
"epoch": 1.3484216795711732,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004830307232956339,
|
|
"loss": 4.7562,
|
|
"mean_token_accuracy": 0.2192539632320404,
|
|
"num_tokens": 31649216.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.123000288009644,
|
|
"epoch": 1.349017272185825,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004830144847677069,
|
|
"loss": 4.8307,
|
|
"mean_token_accuracy": 0.2163475200533867,
|
|
"num_tokens": 31662392.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.053419351577759,
|
|
"epoch": 1.3496128648004766,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.00048299823877863857,
|
|
"loss": 4.6862,
|
|
"mean_token_accuracy": 0.22055768966674805,
|
|
"num_tokens": 31677801.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.174535512924194,
|
|
"epoch": 1.350208457415128,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004829819853290116,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.21495994180440903,
|
|
"num_tokens": 31692204.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.08797607421875,
|
|
"epoch": 1.3508040500297795,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004829657244194089,
|
|
"loss": 4.7217,
|
|
"mean_token_accuracy": 0.224532650411129,
|
|
"num_tokens": 31707277.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.086089611053467,
|
|
"epoch": 1.3513996426444312,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048294945605041384,
|
|
"loss": 4.7955,
|
|
"mean_token_accuracy": 0.21602621376514436,
|
|
"num_tokens": 31721725.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.103640365600586,
|
|
"epoch": 1.3519952352590827,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048293318022260995,
|
|
"loss": 4.6388,
|
|
"mean_token_accuracy": 0.22512976825237274,
|
|
"num_tokens": 31734945.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.124390554428101,
|
|
"epoch": 1.3525908278737344,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004829168969365809,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.21527827084064483,
|
|
"num_tokens": 31747336.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.029960441589355,
|
|
"epoch": 1.3531864204883859,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048290060619291084,
|
|
"loss": 4.6653,
|
|
"mean_token_accuracy": 0.21786846071481705,
|
|
"num_tokens": 31760405.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.105899047851563,
|
|
"epoch": 1.3537820131030376,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00048288430799218394,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.21240140348672867,
|
|
"num_tokens": 31775720.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.058178853988648,
|
|
"epoch": 1.354377605717689,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004828680023349851,
|
|
"loss": 4.6728,
|
|
"mean_token_accuracy": 0.21766302287578582,
|
|
"num_tokens": 31790211.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.1038031578063965,
|
|
"epoch": 1.3549731983323408,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048285168922189886,
|
|
"loss": 4.7934,
|
|
"mean_token_accuracy": 0.2048170194029808,
|
|
"num_tokens": 31804840.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.151084852218628,
|
|
"epoch": 1.3555687909469922,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048283536865351053,
|
|
"loss": 4.8662,
|
|
"mean_token_accuracy": 0.2092023268342018,
|
|
"num_tokens": 31818633.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.09196286201477,
|
|
"epoch": 1.356164383561644,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004828190406304054,
|
|
"loss": 4.6556,
|
|
"mean_token_accuracy": 0.22584821432828903,
|
|
"num_tokens": 31831804.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.071410226821899,
|
|
"epoch": 1.3567599761762954,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004828027051531692,
|
|
"loss": 4.7396,
|
|
"mean_token_accuracy": 0.21195027977228165,
|
|
"num_tokens": 31844419.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.122853374481201,
|
|
"epoch": 1.3573555687909469,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048278636222238785,
|
|
"loss": 4.7725,
|
|
"mean_token_accuracy": 0.21303293108940125,
|
|
"num_tokens": 31857222.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.096063470840454,
|
|
"epoch": 1.3579511614055986,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048277001183864756,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.21435879319906234,
|
|
"num_tokens": 31869377.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.05814528465271,
|
|
"epoch": 1.3585467540202503,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004827536540025347,
|
|
"loss": 4.7347,
|
|
"mean_token_accuracy": 0.22495677173137665,
|
|
"num_tokens": 31882934.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.068790864944458,
|
|
"epoch": 1.3591423466349017,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004827372887146361,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.2229880914092064,
|
|
"num_tokens": 31895649.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.066807746887207,
|
|
"epoch": 1.3597379392495532,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048272091597553865,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.2172992244362831,
|
|
"num_tokens": 31911061.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.126544666290283,
|
|
"epoch": 1.360333531864205,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048270453578582974,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.21736564487218857,
|
|
"num_tokens": 31923128.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.111534976959229,
|
|
"epoch": 1.3609291244788564,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004826881481460968,
|
|
"loss": 4.743,
|
|
"mean_token_accuracy": 0.2131933808326721,
|
|
"num_tokens": 31937947.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.081681156158448,
|
|
"epoch": 1.361524717093508,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048267175305692774,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.21296336203813554,
|
|
"num_tokens": 31952010.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.132434511184693,
|
|
"epoch": 1.3621203097081596,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004826553505189104,
|
|
"loss": 4.761,
|
|
"mean_token_accuracy": 0.21237456053495407,
|
|
"num_tokens": 31966068.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.0742034912109375,
|
|
"epoch": 1.3627159023228113,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004826389405326334,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.2138190448284149,
|
|
"num_tokens": 31979442.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.196679592132568,
|
|
"epoch": 1.3633114949374627,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004826225230986851,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.20936685055494308,
|
|
"num_tokens": 31993564.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.138419246673584,
|
|
"epoch": 1.3639070875521144,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048260609821765456,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.21679868996143342,
|
|
"num_tokens": 32008589.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.056251382827758,
|
|
"epoch": 1.364502680166766,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004825896658901308,
|
|
"loss": 4.6779,
|
|
"mean_token_accuracy": 0.21721394658088683,
|
|
"num_tokens": 32021975.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.080046463012695,
|
|
"epoch": 1.3650982727814176,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048257322611670324,
|
|
"loss": 4.7212,
|
|
"mean_token_accuracy": 0.21220317780971526,
|
|
"num_tokens": 32035438.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.146887540817261,
|
|
"epoch": 1.365693865396069,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048255677889796157,
|
|
"loss": 4.8907,
|
|
"mean_token_accuracy": 0.2065199837088585,
|
|
"num_tokens": 32051294.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.1270264148712155,
|
|
"epoch": 1.3662894580107205,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004825403242344957,
|
|
"loss": 4.7741,
|
|
"mean_token_accuracy": 0.2213093400001526,
|
|
"num_tokens": 32064424.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.073785924911499,
|
|
"epoch": 1.3668850506253722,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004825238621268958,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.2215292915701866,
|
|
"num_tokens": 32078402.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.08087649345398,
|
|
"epoch": 1.367480643240024,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004825073925757524,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.21561977565288543,
|
|
"num_tokens": 32091878.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.09191861152649,
|
|
"epoch": 1.3680762358546754,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004824909155816562,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.22252203673124313,
|
|
"num_tokens": 32104405.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.096531343460083,
|
|
"epoch": 1.368671828469327,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048247443114519825,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.22272804826498033,
|
|
"num_tokens": 32117927.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.117549085617066,
|
|
"epoch": 1.3692674210839786,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004824579392669698,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.21355071067810058,
|
|
"num_tokens": 32132314.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.13517689704895,
|
|
"epoch": 1.36986301369863,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048244143994756233,
|
|
"loss": 4.8336,
|
|
"mean_token_accuracy": 0.2193354770541191,
|
|
"num_tokens": 32145426.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.11249532699585,
|
|
"epoch": 1.3704586063132818,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004824249331875677,
|
|
"loss": 4.7291,
|
|
"mean_token_accuracy": 0.21607562899589539,
|
|
"num_tokens": 32160902.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.049780368804932,
|
|
"epoch": 1.3710541989279332,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048240841898757796,
|
|
"loss": 4.6729,
|
|
"mean_token_accuracy": 0.21548208445310593,
|
|
"num_tokens": 32173436.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.110393142700195,
|
|
"epoch": 1.371649791542585,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004823918973481855,
|
|
"loss": 4.7479,
|
|
"mean_token_accuracy": 0.21773308664560317,
|
|
"num_tokens": 32185822.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.138199377059936,
|
|
"epoch": 1.3722453841572364,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048237536826998287,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.21124062687158585,
|
|
"num_tokens": 32198995.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.0338531017303465,
|
|
"epoch": 1.372840976771888,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000482358831753563,
|
|
"loss": 4.5904,
|
|
"mean_token_accuracy": 0.22980234473943711,
|
|
"num_tokens": 32212090.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.093781137466431,
|
|
"epoch": 1.3734365693865396,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048234228779951883,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.21695090383291243,
|
|
"num_tokens": 32225838.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.135765552520752,
|
|
"epoch": 1.3740321620011913,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048232573640844407,
|
|
"loss": 4.7771,
|
|
"mean_token_accuracy": 0.21497935354709624,
|
|
"num_tokens": 32239603.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.144944715499878,
|
|
"epoch": 1.3746277546158427,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004823091775809321,
|
|
"loss": 4.8134,
|
|
"mean_token_accuracy": 0.21108753681182862,
|
|
"num_tokens": 32252808.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.136462450027466,
|
|
"epoch": 1.3752233472304942,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048229261131757707,
|
|
"loss": 4.7954,
|
|
"mean_token_accuracy": 0.21439777463674545,
|
|
"num_tokens": 32265893.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.103172492980957,
|
|
"epoch": 1.375818939845146,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048227603761897316,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.21324513703584672,
|
|
"num_tokens": 32280529.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.0669866561889645,
|
|
"epoch": 1.3764145324597976,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048225945648571475,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.21818965673446655,
|
|
"num_tokens": 32294222.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.150603818893432,
|
|
"epoch": 1.377010125074449,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048224286791839657,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.21451343446969987,
|
|
"num_tokens": 32308289.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.085991144180298,
|
|
"epoch": 1.3776057176891006,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004822262719176137,
|
|
"loss": 4.6639,
|
|
"mean_token_accuracy": 0.22564944475889206,
|
|
"num_tokens": 32321401.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.040739059448242,
|
|
"epoch": 1.3782013103037523,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048220966848396137,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.22066935002803803,
|
|
"num_tokens": 32335373.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.188859701156616,
|
|
"epoch": 1.3787969029184037,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004821930576180352,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.21137017607688904,
|
|
"num_tokens": 32349685.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.090391683578491,
|
|
"epoch": 1.3793924955330554,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004821764393204308,
|
|
"loss": 4.7534,
|
|
"mean_token_accuracy": 0.21021801978349686,
|
|
"num_tokens": 32363768.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.118274736404419,
|
|
"epoch": 1.379988088147707,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004821598135917445,
|
|
"loss": 4.7582,
|
|
"mean_token_accuracy": 0.22304786145687103,
|
|
"num_tokens": 32377483.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.125663948059082,
|
|
"epoch": 1.3805836807623586,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048214318043257246,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.2119297578930855,
|
|
"num_tokens": 32389693.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.0802699565887455,
|
|
"epoch": 1.38117927337701,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004821265398435113,
|
|
"loss": 4.6925,
|
|
"mean_token_accuracy": 0.22169038653373718,
|
|
"num_tokens": 32403479.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.14784951210022,
|
|
"epoch": 1.3817748659916618,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000482109891825158,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.21453174948692322,
|
|
"num_tokens": 32417152.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.110607385635376,
|
|
"epoch": 1.3823704586063132,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004820932363781096,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.21604276895523072,
|
|
"num_tokens": 32430653.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.045700120925903,
|
|
"epoch": 1.382966051220965,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048207657350296345,
|
|
"loss": 4.7352,
|
|
"mean_token_accuracy": 0.21448965668678283,
|
|
"num_tokens": 32446058.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.097786712646484,
|
|
"epoch": 1.3835616438356164,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048205990320031734,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.21884440630674362,
|
|
"num_tokens": 32460061.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.0792543411254885,
|
|
"epoch": 1.384157236450268,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048204322547076915,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.21284745186567305,
|
|
"num_tokens": 32472554.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.030055141448974,
|
|
"epoch": 1.3847528290649196,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048202654031491714,
|
|
"loss": 4.7094,
|
|
"mean_token_accuracy": 0.22799161523580552,
|
|
"num_tokens": 32485436.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.119005012512207,
|
|
"epoch": 1.3853484216795713,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048200984773335973,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.21512728035449982,
|
|
"num_tokens": 32498618.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.107369995117187,
|
|
"epoch": 1.3859440142942228,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004819931477266956,
|
|
"loss": 4.6468,
|
|
"mean_token_accuracy": 0.2259766787290573,
|
|
"num_tokens": 32510924.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.1346728801727295,
|
|
"epoch": 1.3865396069088742,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004819764402955239,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.20829180777072906,
|
|
"num_tokens": 32524347.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.188225412368775,
|
|
"epoch": 1.387135199523526,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048195972544044373,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.21418158262968062,
|
|
"num_tokens": 32537497.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.127142286300659,
|
|
"epoch": 1.3877307921381774,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048194300316205474,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.21455590873956681,
|
|
"num_tokens": 32552684.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.085914945602417,
|
|
"epoch": 1.388326384752829,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004819262734609567,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.21239417940378189,
|
|
"num_tokens": 32567202.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.087527418136597,
|
|
"epoch": 1.3889219773674806,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004819095363377496,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.21042081266641616,
|
|
"num_tokens": 32583085.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.0299680709838865,
|
|
"epoch": 1.3895175699821323,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004818927917930339,
|
|
"loss": 4.6814,
|
|
"mean_token_accuracy": 0.22487987577915192,
|
|
"num_tokens": 32598610.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.101728868484497,
|
|
"epoch": 1.3901131625967837,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048187603982741015,
|
|
"loss": 4.7095,
|
|
"mean_token_accuracy": 0.21598898470401764,
|
|
"num_tokens": 32611591.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.109165287017822,
|
|
"epoch": 1.3907087552114354,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004818592804414792,
|
|
"loss": 4.6844,
|
|
"mean_token_accuracy": 0.22103455662727356,
|
|
"num_tokens": 32625002.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.066283369064331,
|
|
"epoch": 1.391304347826087,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004818425136358422,
|
|
"loss": 4.7258,
|
|
"mean_token_accuracy": 0.22354370057582856,
|
|
"num_tokens": 32639812.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.0771934509277346,
|
|
"epoch": 1.3918999404407386,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048182573941110056,
|
|
"loss": 4.722,
|
|
"mean_token_accuracy": 0.21468741744756697,
|
|
"num_tokens": 32652045.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.133814525604248,
|
|
"epoch": 1.39249553305539,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004818089577678559,
|
|
"loss": 4.7825,
|
|
"mean_token_accuracy": 0.21323711574077606,
|
|
"num_tokens": 32666098.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.103631258010864,
|
|
"epoch": 1.3930911256700416,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004817921687067102,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.21528788059949874,
|
|
"num_tokens": 32681044.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.053554725646973,
|
|
"epoch": 1.3936867182846933,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004817753722282656,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.22340047657489776,
|
|
"num_tokens": 32696855.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.013873672485351,
|
|
"epoch": 1.394282310899345,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048175856833312464,
|
|
"loss": 4.6952,
|
|
"mean_token_accuracy": 0.21915522068738938,
|
|
"num_tokens": 32712248.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.07797327041626,
|
|
"epoch": 1.3948779035139964,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048174175702189,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.21353253722190857,
|
|
"num_tokens": 32727498.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.105211639404297,
|
|
"epoch": 1.395473496128648,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048172493829516465,
|
|
"loss": 4.6658,
|
|
"mean_token_accuracy": 0.22709927558898926,
|
|
"num_tokens": 32741450.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.0598231792449955,
|
|
"epoch": 1.3960690887432996,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004817081121535518,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.2224673718214035,
|
|
"num_tokens": 32756340.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 4.957618665695191,
|
|
"epoch": 1.3966646813579513,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004816912785976552,
|
|
"loss": 4.6222,
|
|
"mean_token_accuracy": 0.22481772154569626,
|
|
"num_tokens": 32770906.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.075853967666626,
|
|
"epoch": 1.3972602739726028,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048167443762807844,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.21853634268045424,
|
|
"num_tokens": 32785477.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.100567102432251,
|
|
"epoch": 1.3978558665872542,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004816575892454256,
|
|
"loss": 4.7381,
|
|
"mean_token_accuracy": 0.21716435253620148,
|
|
"num_tokens": 32798766.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.104428339004516,
|
|
"epoch": 1.398451459201906,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000481640733450301,
|
|
"loss": 4.7899,
|
|
"mean_token_accuracy": 0.22060540020465852,
|
|
"num_tokens": 32813918.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.078911018371582,
|
|
"epoch": 1.3990470518165574,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004816238702433094,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.2177945628762245,
|
|
"num_tokens": 32828701.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.180146551132202,
|
|
"epoch": 1.3996426444312091,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048160699962505546,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.21082785129547119,
|
|
"num_tokens": 32841517.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.080108976364135,
|
|
"epoch": 1.4002382370458606,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.00048159012159614434,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.2140612557530403,
|
|
"num_tokens": 32857108.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.151411676406861,
|
|
"epoch": 1.4008338296605123,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004815732361571815,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.21002797335386275,
|
|
"num_tokens": 32872384.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.104244899749756,
|
|
"epoch": 1.4014294222751638,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048155634330877253,
|
|
"loss": 4.6782,
|
|
"mean_token_accuracy": 0.22287166565656663,
|
|
"num_tokens": 32885890.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.0987437725067135,
|
|
"epoch": 1.4020250148898152,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004815394430515234,
|
|
"loss": 4.7072,
|
|
"mean_token_accuracy": 0.21496354341506957,
|
|
"num_tokens": 32899789.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.0860837459564205,
|
|
"epoch": 1.402620607504467,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004815225353860402,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.21504543721675873,
|
|
"num_tokens": 32914523.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.059079694747925,
|
|
"epoch": 1.4032162001191186,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004815056203129294,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.22184719741344452,
|
|
"num_tokens": 32929007.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.092992687225342,
|
|
"epoch": 1.40381179273377,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004814886978327978,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.2198839843273163,
|
|
"num_tokens": 32943884.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.125900745391846,
|
|
"epoch": 1.4044073853484216,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048147176794625235,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.22279750555753708,
|
|
"num_tokens": 32958828.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.084102439880371,
|
|
"epoch": 1.4050029779630733,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004814548306539003,
|
|
"loss": 4.7055,
|
|
"mean_token_accuracy": 0.221030293405056,
|
|
"num_tokens": 32971960.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.109138679504395,
|
|
"epoch": 1.405598570577725,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048143788595634917,
|
|
"loss": 4.8097,
|
|
"mean_token_accuracy": 0.2088762491941452,
|
|
"num_tokens": 32986571.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.140612173080444,
|
|
"epoch": 1.4061941631923764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004814209338542067,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.20962011814117432,
|
|
"num_tokens": 33000931.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.018594980239868,
|
|
"epoch": 1.406789755807028,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048140397434808094,
|
|
"loss": 4.6211,
|
|
"mean_token_accuracy": 0.22787486463785173,
|
|
"num_tokens": 33016451.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.0300798416137695,
|
|
"epoch": 1.4073853484216796,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048138700743858014,
|
|
"loss": 4.6655,
|
|
"mean_token_accuracy": 0.2260480895638466,
|
|
"num_tokens": 33030901.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.098274183273316,
|
|
"epoch": 1.407980941036331,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048137003312631306,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.22088535130023956,
|
|
"num_tokens": 33045328.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.099662637710571,
|
|
"epoch": 1.4085765336509828,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004813530514118884,
|
|
"loss": 4.6595,
|
|
"mean_token_accuracy": 0.22325084656476973,
|
|
"num_tokens": 33060897.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.091792583465576,
|
|
"epoch": 1.4091721262656343,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048133606229591524,
|
|
"loss": 4.6882,
|
|
"mean_token_accuracy": 0.22603083103895188,
|
|
"num_tokens": 33074440.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.184837770462036,
|
|
"epoch": 1.409767718880286,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004813190657790031,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.2036858931183815,
|
|
"num_tokens": 33091184.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.088597917556763,
|
|
"epoch": 1.4103633114949374,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048130206186176145,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.22136043906211852,
|
|
"num_tokens": 33107047.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.08053035736084,
|
|
"epoch": 1.410958904109589,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048128505054480036,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.22004683464765548,
|
|
"num_tokens": 33121814.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.068668556213379,
|
|
"epoch": 1.4115544967242406,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004812680318287298,
|
|
"loss": 4.7064,
|
|
"mean_token_accuracy": 0.2181071013212204,
|
|
"num_tokens": 33135665.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.094389343261719,
|
|
"epoch": 1.4121500893388923,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004812510057141603,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.2139117658138275,
|
|
"num_tokens": 33148995.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.069671726226806,
|
|
"epoch": 1.4127456819535438,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004812339722017027,
|
|
"loss": 4.6596,
|
|
"mean_token_accuracy": 0.21733720004558563,
|
|
"num_tokens": 33163055.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.030528926849366,
|
|
"epoch": 1.4133412745681952,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004812169312919677,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.2270377665758133,
|
|
"num_tokens": 33176203.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.074796342849732,
|
|
"epoch": 1.413936867182847,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048119988298556674,
|
|
"loss": 4.7538,
|
|
"mean_token_accuracy": 0.2151499569416046,
|
|
"num_tokens": 33191357.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.1557831287384035,
|
|
"epoch": 1.4145324597974986,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004811828272831112,
|
|
"loss": 4.827,
|
|
"mean_token_accuracy": 0.20882693231105803,
|
|
"num_tokens": 33207534.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.1206825256347654,
|
|
"epoch": 1.4151280524121501,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004811657641852129,
|
|
"loss": 4.7191,
|
|
"mean_token_accuracy": 0.22508948743343354,
|
|
"num_tokens": 33221186.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.063359642028809,
|
|
"epoch": 1.4157236450268016,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048114869369248386,
|
|
"loss": 4.684,
|
|
"mean_token_accuracy": 0.2149783119559288,
|
|
"num_tokens": 33235279.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.072126197814941,
|
|
"epoch": 1.4163192376414533,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004811316158055363,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.21475366204977037,
|
|
"num_tokens": 33250457.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.16411247253418,
|
|
"epoch": 1.4169148302561048,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004811145305249828,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.2173861250281334,
|
|
"num_tokens": 33263599.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.076122045516968,
|
|
"epoch": 1.4175104228707565,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048109743785143636,
|
|
"loss": 4.7583,
|
|
"mean_token_accuracy": 0.21475905179977417,
|
|
"num_tokens": 33277508.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.084055089950562,
|
|
"epoch": 1.418106015485408,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004810803377855098,
|
|
"loss": 4.786,
|
|
"mean_token_accuracy": 0.21670176684856415,
|
|
"num_tokens": 33290161.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.140715217590332,
|
|
"epoch": 1.4187016081000596,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004810632303278166,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.2125703439116478,
|
|
"num_tokens": 33303174.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.086669445037842,
|
|
"epoch": 1.419297200714711,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004810461154789704,
|
|
"loss": 4.7054,
|
|
"mean_token_accuracy": 0.22007043063640594,
|
|
"num_tokens": 33318070.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.069097948074341,
|
|
"epoch": 1.4198927933293626,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000481028993239585,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.2212446838617325,
|
|
"num_tokens": 33332135.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.081434106826782,
|
|
"epoch": 1.4204883859440143,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004810118636102747,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.21850218027830123,
|
|
"num_tokens": 33345414.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.108359432220459,
|
|
"epoch": 1.421083978558666,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004809947265916537,
|
|
"loss": 4.7683,
|
|
"mean_token_accuracy": 0.22150297611951827,
|
|
"num_tokens": 33359173.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.072337818145752,
|
|
"epoch": 1.4216795711733174,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048097758218433687,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.22237127274274826,
|
|
"num_tokens": 33371025.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.005428409576416,
|
|
"epoch": 1.422275163787969,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048096043038893895,
|
|
"loss": 4.6384,
|
|
"mean_token_accuracy": 0.22615883946418763,
|
|
"num_tokens": 33384482.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.185081100463867,
|
|
"epoch": 1.4228707564026206,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048094327120607534,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.21844191402196883,
|
|
"num_tokens": 33398250.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.048999309539795,
|
|
"epoch": 1.4234663490172723,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048092610463636143,
|
|
"loss": 4.6684,
|
|
"mean_token_accuracy": 0.22091204226016997,
|
|
"num_tokens": 33412845.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.139373826980591,
|
|
"epoch": 1.4240619416319238,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000480908930680413,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.21261388212442398,
|
|
"num_tokens": 33425418.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.118959188461304,
|
|
"epoch": 1.4246575342465753,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048089174933884597,
|
|
"loss": 4.7346,
|
|
"mean_token_accuracy": 0.21264842450618743,
|
|
"num_tokens": 33439431.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.0588479995727536,
|
|
"epoch": 1.425253126861227,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.00048087456061227666,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.22245626896619797,
|
|
"num_tokens": 33454504.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.024194955825806,
|
|
"epoch": 1.4258487194758784,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00048085736450132155,
|
|
"loss": 4.6684,
|
|
"mean_token_accuracy": 0.21799841672182083,
|
|
"num_tokens": 33469243.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.074317741394043,
|
|
"epoch": 1.4264443120905301,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048084016100659755,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.21717219203710555,
|
|
"num_tokens": 33484068.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.11810188293457,
|
|
"epoch": 1.4270399047051816,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004808229501287216,
|
|
"loss": 4.7562,
|
|
"mean_token_accuracy": 0.21002217680215834,
|
|
"num_tokens": 33497841.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.020758962631225,
|
|
"epoch": 1.4276354973198333,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048080573186831113,
|
|
"loss": 4.5966,
|
|
"mean_token_accuracy": 0.23146547824144365,
|
|
"num_tokens": 33512011.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.060372018814087,
|
|
"epoch": 1.4282310899344848,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048078850622598355,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.21537951827049256,
|
|
"num_tokens": 33525475.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.073163461685181,
|
|
"epoch": 1.4288266825491365,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00048077127320235696,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.21893789023160934,
|
|
"num_tokens": 33540069.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.089403533935547,
|
|
"epoch": 1.429422275163788,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048075403279804934,
|
|
"loss": 4.7018,
|
|
"mean_token_accuracy": 0.22038259208202363,
|
|
"num_tokens": 33554060.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.429422275163788,
|
|
"eval_entropy": 4.835260084953427,
|
|
"eval_loss": 4.731464862823486,
|
|
"eval_mean_token_accuracy": 0.22866669203560555,
|
|
"eval_num_tokens": 33554060.0,
|
|
"eval_runtime": 18.4615,
|
|
"eval_samples_per_second": 1381.956,
|
|
"eval_steps_per_second": 172.792,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.074542379379272,
|
|
"epoch": 1.4300178677784396,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004807367850136791,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.2217721536755562,
|
|
"num_tokens": 33566502.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.107910299301148,
|
|
"epoch": 1.4306134603930911,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004807195298498649,
|
|
"loss": 4.7146,
|
|
"mean_token_accuracy": 0.21426905691623688,
|
|
"num_tokens": 33581192.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.1359110355377195,
|
|
"epoch": 1.4312090530077426,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004807022673072257,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.210236032307148,
|
|
"num_tokens": 33595298.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.070293188095093,
|
|
"epoch": 1.4318046456223943,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048068499738638046,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.21172283589839935,
|
|
"num_tokens": 33607349.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.099677467346192,
|
|
"epoch": 1.432400238237046,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004806677200879489,
|
|
"loss": 4.7072,
|
|
"mean_token_accuracy": 0.22436511367559434,
|
|
"num_tokens": 33621443.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.081073904037476,
|
|
"epoch": 1.4329958308516975,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004806504354125505,
|
|
"loss": 4.6726,
|
|
"mean_token_accuracy": 0.22844330370426177,
|
|
"num_tokens": 33634430.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.1012434482574465,
|
|
"epoch": 1.433591423466349,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048063314336080554,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.21302445679903032,
|
|
"num_tokens": 33649192.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.0779914379119875,
|
|
"epoch": 1.4341870160810006,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004806158439333339,
|
|
"loss": 4.7068,
|
|
"mean_token_accuracy": 0.22087550014257432,
|
|
"num_tokens": 33662715.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.089471292495728,
|
|
"epoch": 1.434782608695652,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048059853713075637,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.2184678852558136,
|
|
"num_tokens": 33676363.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.153532886505127,
|
|
"epoch": 1.4353782013103038,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048058122295369354,
|
|
"loss": 4.8307,
|
|
"mean_token_accuracy": 0.21237795054912567,
|
|
"num_tokens": 33693285.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.076329898834229,
|
|
"epoch": 1.4359737939249553,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004805639014027665,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.22396495789289475,
|
|
"num_tokens": 33707291.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.02184910774231,
|
|
"epoch": 1.436569386539607,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004805465724785966,
|
|
"loss": 4.6415,
|
|
"mean_token_accuracy": 0.22152564525604249,
|
|
"num_tokens": 33721629.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.04160795211792,
|
|
"epoch": 1.4371649791542584,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004805292361818053,
|
|
"loss": 4.687,
|
|
"mean_token_accuracy": 0.2259563386440277,
|
|
"num_tokens": 33737427.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.059143114089966,
|
|
"epoch": 1.4377605717689101,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048051189251301443,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.22015606015920638,
|
|
"num_tokens": 33750851.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.092542266845703,
|
|
"epoch": 1.4383561643835616,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004804945414728461,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.2168523594737053,
|
|
"num_tokens": 33764663.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.051627922058105,
|
|
"epoch": 1.4389517569982133,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004804771830619227,
|
|
"loss": 4.6714,
|
|
"mean_token_accuracy": 0.2221412718296051,
|
|
"num_tokens": 33779875.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 4.994313669204712,
|
|
"epoch": 1.4395473496128648,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048045981728086687,
|
|
"loss": 4.6507,
|
|
"mean_token_accuracy": 0.2211131900548935,
|
|
"num_tokens": 33791867.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.042295360565186,
|
|
"epoch": 1.4401429422275163,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004804424441303015,
|
|
"loss": 4.6975,
|
|
"mean_token_accuracy": 0.23056577146053314,
|
|
"num_tokens": 33804957.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.110949468612671,
|
|
"epoch": 1.440738534842168,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004804250636108496,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.22180121541023254,
|
|
"num_tokens": 33816409.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.174254274368286,
|
|
"epoch": 1.4413341274568197,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004804076757231347,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.21320169866085054,
|
|
"num_tokens": 33830946.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.1009664058685305,
|
|
"epoch": 1.4419297200714711,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048039028046778043,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.21518755555152894,
|
|
"num_tokens": 33846133.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.026577615737915,
|
|
"epoch": 1.4425253126861226,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004803728778454108,
|
|
"loss": 4.6476,
|
|
"mean_token_accuracy": 0.2203105390071869,
|
|
"num_tokens": 33860168.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.113314151763916,
|
|
"epoch": 1.4431209053007743,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048035546785664987,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.21160838901996612,
|
|
"num_tokens": 33873260.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.101555919647216,
|
|
"epoch": 1.4437164979154258,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004803380505021222,
|
|
"loss": 4.7453,
|
|
"mean_token_accuracy": 0.21580857187509536,
|
|
"num_tokens": 33887568.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.136142349243164,
|
|
"epoch": 1.4443120905300775,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048032062578245256,
|
|
"loss": 4.7293,
|
|
"mean_token_accuracy": 0.21585696786642075,
|
|
"num_tokens": 33900464.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.003832530975342,
|
|
"epoch": 1.444907683144729,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048030319369826594,
|
|
"loss": 4.6606,
|
|
"mean_token_accuracy": 0.22294127345085143,
|
|
"num_tokens": 33913155.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.133718681335449,
|
|
"epoch": 1.4455032757593806,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004802857542501875,
|
|
"loss": 4.7712,
|
|
"mean_token_accuracy": 0.2153587445616722,
|
|
"num_tokens": 33928168.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.044047784805298,
|
|
"epoch": 1.4460988683740321,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00048026830743884283,
|
|
"loss": 4.6254,
|
|
"mean_token_accuracy": 0.22514089196920395,
|
|
"num_tokens": 33941525.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.001362228393555,
|
|
"epoch": 1.4466944609886838,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004802508532648578,
|
|
"loss": 4.5693,
|
|
"mean_token_accuracy": 0.22804440259933473,
|
|
"num_tokens": 33955300.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.0649150848388675,
|
|
"epoch": 1.4472900536033353,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004802333917288583,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.22177043110132216,
|
|
"num_tokens": 33968924.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.0884020805358885,
|
|
"epoch": 1.447885646217987,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048021592283147073,
|
|
"loss": 4.7128,
|
|
"mean_token_accuracy": 0.22048852890729903,
|
|
"num_tokens": 33982725.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.049281024932862,
|
|
"epoch": 1.4484812388326385,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048019844657332166,
|
|
"loss": 4.6561,
|
|
"mean_token_accuracy": 0.22465027570724488,
|
|
"num_tokens": 33997263.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.127010154724121,
|
|
"epoch": 1.44907683144729,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.000480180962955038,
|
|
"loss": 4.8291,
|
|
"mean_token_accuracy": 0.21365189403295518,
|
|
"num_tokens": 34013748.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.124413967132568,
|
|
"epoch": 1.4496724240619416,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048016347197724676,
|
|
"loss": 4.738,
|
|
"mean_token_accuracy": 0.21275374293327332,
|
|
"num_tokens": 34028086.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.020755243301392,
|
|
"epoch": 1.4502680166765933,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004801459736405754,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.221540205180645,
|
|
"num_tokens": 34042539.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.093195915222168,
|
|
"epoch": 1.4508636092912448,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048012846794565143,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.22123921811580657,
|
|
"num_tokens": 34055051.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.067578983306885,
|
|
"epoch": 1.4514592019058963,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004801109548931029,
|
|
"loss": 4.6437,
|
|
"mean_token_accuracy": 0.23477402031421662,
|
|
"num_tokens": 34068861.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.045392274856567,
|
|
"epoch": 1.452054794520548,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004800934344835579,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.22253888696432114,
|
|
"num_tokens": 34082353.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.053408527374268,
|
|
"epoch": 1.4526503871351995,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004800759067176448,
|
|
"loss": 4.7203,
|
|
"mean_token_accuracy": 0.21866591572761535,
|
|
"num_tokens": 34096993.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.058754253387451,
|
|
"epoch": 1.4532459797498511,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004800583715959924,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.21746120005846023,
|
|
"num_tokens": 34110648.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.079717397689819,
|
|
"epoch": 1.4538415723645026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004800408291192297,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.22401354014873504,
|
|
"num_tokens": 34123645.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.070383882522583,
|
|
"epoch": 1.4544371649791543,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004800232792879858,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.21605150699615477,
|
|
"num_tokens": 34139671.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.1655762672424315,
|
|
"epoch": 1.4550327575938058,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048000572210289016,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.2136520504951477,
|
|
"num_tokens": 34154451.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.16344199180603,
|
|
"epoch": 1.4556283502084575,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047998815756457265,
|
|
"loss": 4.7549,
|
|
"mean_token_accuracy": 0.2229592815041542,
|
|
"num_tokens": 34166974.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.136546611785889,
|
|
"epoch": 1.456223942823109,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047997058567366313,
|
|
"loss": 4.7589,
|
|
"mean_token_accuracy": 0.2228967934846878,
|
|
"num_tokens": 34180197.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.011868476867676,
|
|
"epoch": 1.4568195354377607,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004799530064307921,
|
|
"loss": 4.6074,
|
|
"mean_token_accuracy": 0.2248021438717842,
|
|
"num_tokens": 34193560.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.073341035842896,
|
|
"epoch": 1.4574151280524121,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047993541983658983,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.22154215574264527,
|
|
"num_tokens": 34206420.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.147740983963013,
|
|
"epoch": 1.4580107206670636,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047991782589168724,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.21231717616319656,
|
|
"num_tokens": 34220557.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.160543155670166,
|
|
"epoch": 1.4586063132817153,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004799002245967156,
|
|
"loss": 4.7668,
|
|
"mean_token_accuracy": 0.20968785285949706,
|
|
"num_tokens": 34232852.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.074496841430664,
|
|
"epoch": 1.459201905896367,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047988261595230587,
|
|
"loss": 4.6605,
|
|
"mean_token_accuracy": 0.22160521447658538,
|
|
"num_tokens": 34248410.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.044563484191895,
|
|
"epoch": 1.4597974985110185,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047986499995908996,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.21847046166658401,
|
|
"num_tokens": 34263600.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.1893689155578615,
|
|
"epoch": 1.46039309112567,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004798473766176994,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.20725114196538924,
|
|
"num_tokens": 34277031.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.106909942626953,
|
|
"epoch": 1.4609886837403216,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047982974592876665,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.2167613238096237,
|
|
"num_tokens": 34291646.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.034643173217773,
|
|
"epoch": 1.4615842763549731,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047981210789292396,
|
|
"loss": 4.6815,
|
|
"mean_token_accuracy": 0.22626426666975022,
|
|
"num_tokens": 34304769.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.027083063125611,
|
|
"epoch": 1.4621798689696248,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004797944625108039,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.22519779205322266,
|
|
"num_tokens": 34318186.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 4.98975830078125,
|
|
"epoch": 1.4627754615842763,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047977680978303946,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.22156846672296523,
|
|
"num_tokens": 34333305.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.036941623687744,
|
|
"epoch": 1.463371054198928,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004797591497102638,
|
|
"loss": 4.6197,
|
|
"mean_token_accuracy": 0.2279473677277565,
|
|
"num_tokens": 34345999.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.0702393531799315,
|
|
"epoch": 1.4639666468135795,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047974148229311034,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.21283964812755585,
|
|
"num_tokens": 34361462.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.057059717178345,
|
|
"epoch": 1.4645622394282312,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004797238075322128,
|
|
"loss": 4.6945,
|
|
"mean_token_accuracy": 0.22077235877513884,
|
|
"num_tokens": 34376638.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.13365364074707,
|
|
"epoch": 1.4651578320428826,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004797061254282052,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.21609392166137695,
|
|
"num_tokens": 34391091.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.09120774269104,
|
|
"epoch": 1.4657534246575343,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004796884359817217,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.2217974841594696,
|
|
"num_tokens": 34404976.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 4.946613502502442,
|
|
"epoch": 1.4663490172721858,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004796707391933967,
|
|
"loss": 4.6153,
|
|
"mean_token_accuracy": 0.23376434445381164,
|
|
"num_tokens": 34416781.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 4.980282115936279,
|
|
"epoch": 1.4669446098868373,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004796530350638652,
|
|
"loss": 4.582,
|
|
"mean_token_accuracy": 0.2318578526377678,
|
|
"num_tokens": 34431445.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.044071197509766,
|
|
"epoch": 1.467540202501489,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000479635323593762,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.23390360027551652,
|
|
"num_tokens": 34443515.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.053245735168457,
|
|
"epoch": 1.4681357951161407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047961760478372245,
|
|
"loss": 4.6238,
|
|
"mean_token_accuracy": 0.2309027761220932,
|
|
"num_tokens": 34456511.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.029330682754517,
|
|
"epoch": 1.4687313877307921,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047959987863438214,
|
|
"loss": 4.7467,
|
|
"mean_token_accuracy": 0.216081802546978,
|
|
"num_tokens": 34469156.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.054995203018189,
|
|
"epoch": 1.4693269803454436,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004795821451463769,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.2159108281135559,
|
|
"num_tokens": 34483735.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.177652597427368,
|
|
"epoch": 1.4699225729600953,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047956440432034265,
|
|
"loss": 4.7686,
|
|
"mean_token_accuracy": 0.2130955144762993,
|
|
"num_tokens": 34496731.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.101555299758911,
|
|
"epoch": 1.4705181655747468,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047954665615691577,
|
|
"loss": 4.738,
|
|
"mean_token_accuracy": 0.22086364924907684,
|
|
"num_tokens": 34509373.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.109379386901855,
|
|
"epoch": 1.4711137581893985,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004795289006567331,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.21904899030923844,
|
|
"num_tokens": 34525550.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.115800046920777,
|
|
"epoch": 1.47170935080405,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047951113782043113,
|
|
"loss": 4.7641,
|
|
"mean_token_accuracy": 0.21198250651359557,
|
|
"num_tokens": 34540555.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.0513543605804445,
|
|
"epoch": 1.4723049434187017,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004794933676486472,
|
|
"loss": 4.7073,
|
|
"mean_token_accuracy": 0.22692135274410247,
|
|
"num_tokens": 34554314.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.019661617279053,
|
|
"epoch": 1.4729005360333531,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004794755901420187,
|
|
"loss": 4.6528,
|
|
"mean_token_accuracy": 0.2290641948580742,
|
|
"num_tokens": 34567932.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.0638401985168455,
|
|
"epoch": 1.4734961286480048,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004794578053011833,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.2196633353829384,
|
|
"num_tokens": 34581556.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.00056300163269,
|
|
"epoch": 1.4740917212626563,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047944001312677867,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.22594978362321855,
|
|
"num_tokens": 34595765.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.022950315475464,
|
|
"epoch": 1.474687313877308,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047942221361944333,
|
|
"loss": 4.5835,
|
|
"mean_token_accuracy": 0.2349913850426674,
|
|
"num_tokens": 34608625.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 4.970704793930054,
|
|
"epoch": 1.4752829064919595,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047940440677981546,
|
|
"loss": 4.547,
|
|
"mean_token_accuracy": 0.23194261342287065,
|
|
"num_tokens": 34622699.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.050950574874878,
|
|
"epoch": 1.475878499106611,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004793865926085339,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.2161833792924881,
|
|
"num_tokens": 34635374.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.042737245559692,
|
|
"epoch": 1.4764740917212626,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004793687711062376,
|
|
"loss": 4.6697,
|
|
"mean_token_accuracy": 0.22963576316833495,
|
|
"num_tokens": 34648517.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.042704391479492,
|
|
"epoch": 1.4770696843359143,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004793509422735657,
|
|
"loss": 4.6807,
|
|
"mean_token_accuracy": 0.2214036077260971,
|
|
"num_tokens": 34662883.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.044325685501098,
|
|
"epoch": 1.4776652769505658,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047933310611115776,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.2200893521308899,
|
|
"num_tokens": 34677490.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.094255065917968,
|
|
"epoch": 1.4782608695652173,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047931526261965363,
|
|
"loss": 4.7261,
|
|
"mean_token_accuracy": 0.2191617116332054,
|
|
"num_tokens": 34690900.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.131014966964722,
|
|
"epoch": 1.478856462179869,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004792974117996931,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.21155956536531448,
|
|
"num_tokens": 34704916.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.092672824859619,
|
|
"epoch": 1.4794520547945205,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004792795536519167,
|
|
"loss": 4.7738,
|
|
"mean_token_accuracy": 0.213652141392231,
|
|
"num_tokens": 34719912.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.058773374557495,
|
|
"epoch": 1.4800476474091722,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047926168817696477,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.2228643536567688,
|
|
"num_tokens": 34735585.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.108404636383057,
|
|
"epoch": 1.4806432400238236,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004792438153754782,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.21836193650960922,
|
|
"num_tokens": 34750321.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.05635404586792,
|
|
"epoch": 1.4812388326384753,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047922593524809805,
|
|
"loss": 4.613,
|
|
"mean_token_accuracy": 0.22681078761816026,
|
|
"num_tokens": 34763555.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.1029280662536625,
|
|
"epoch": 1.4818344252531268,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004792080477954657,
|
|
"loss": 4.8221,
|
|
"mean_token_accuracy": 0.20995631366968154,
|
|
"num_tokens": 34777395.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.110771369934082,
|
|
"epoch": 1.4824300178677785,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047919015301822255,
|
|
"loss": 4.6446,
|
|
"mean_token_accuracy": 0.22108041793107985,
|
|
"num_tokens": 34791598.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.057524108886719,
|
|
"epoch": 1.48302561048243,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004791722509170108,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.2154722660779953,
|
|
"num_tokens": 34805647.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.051491212844849,
|
|
"epoch": 1.4836212030970817,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00047915434149247224,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.22646380960941315,
|
|
"num_tokens": 34820167.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.066374349594116,
|
|
"epoch": 1.4842167957117332,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047913642474524946,
|
|
"loss": 4.6887,
|
|
"mean_token_accuracy": 0.22070292830467225,
|
|
"num_tokens": 34834458.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.111847639083862,
|
|
"epoch": 1.4848123883263846,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047911850067598494,
|
|
"loss": 4.7439,
|
|
"mean_token_accuracy": 0.21483342051506044,
|
|
"num_tokens": 34849058.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.136333751678467,
|
|
"epoch": 1.4854079809410363,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047910056928532173,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.21830665320158005,
|
|
"num_tokens": 34863215.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.017152309417725,
|
|
"epoch": 1.486003573555688,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000479082630573903,
|
|
"loss": 4.6432,
|
|
"mean_token_accuracy": 0.22833801358938216,
|
|
"num_tokens": 34877198.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.052235460281372,
|
|
"epoch": 1.4865991661703395,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004790646845423721,
|
|
"loss": 4.7254,
|
|
"mean_token_accuracy": 0.22040158957242967,
|
|
"num_tokens": 34892150.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.115643692016602,
|
|
"epoch": 1.487194758784991,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004790467311913727,
|
|
"loss": 4.7427,
|
|
"mean_token_accuracy": 0.22335606664419175,
|
|
"num_tokens": 34904775.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.092574501037598,
|
|
"epoch": 1.4877903513996427,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047902877052154885,
|
|
"loss": 4.6892,
|
|
"mean_token_accuracy": 0.2163775682449341,
|
|
"num_tokens": 34919306.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.071080160140991,
|
|
"epoch": 1.4883859440142944,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047901080253354476,
|
|
"loss": 4.7371,
|
|
"mean_token_accuracy": 0.21591631025075914,
|
|
"num_tokens": 34932524.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.076800155639648,
|
|
"epoch": 1.4889815366289458,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047899282722800487,
|
|
"loss": 4.6995,
|
|
"mean_token_accuracy": 0.22397396862506866,
|
|
"num_tokens": 34945665.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.04377498626709,
|
|
"epoch": 1.4895771292435973,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047897484460557397,
|
|
"loss": 4.6502,
|
|
"mean_token_accuracy": 0.22886738628149034,
|
|
"num_tokens": 34958260.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.0596091747283936,
|
|
"epoch": 1.490172721858249,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000478956854666897,
|
|
"loss": 4.721,
|
|
"mean_token_accuracy": 0.21228838860988616,
|
|
"num_tokens": 34972047.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.052674436569214,
|
|
"epoch": 1.4907683144729005,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047893885741261924,
|
|
"loss": 4.6571,
|
|
"mean_token_accuracy": 0.22779595255851745,
|
|
"num_tokens": 34983672.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.05961012840271,
|
|
"epoch": 1.4913639070875522,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004789208528433862,
|
|
"loss": 4.6984,
|
|
"mean_token_accuracy": 0.22185770571231841,
|
|
"num_tokens": 34996639.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.067325830459595,
|
|
"epoch": 1.4919594997022037,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004789028409598438,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.217784321308136,
|
|
"num_tokens": 35010742.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.053822422027588,
|
|
"epoch": 1.4925550923168553,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047888482176263803,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.21699571907520293,
|
|
"num_tokens": 35024345.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.021348333358764,
|
|
"epoch": 1.4931506849315068,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047886679525241524,
|
|
"loss": 4.6331,
|
|
"mean_token_accuracy": 0.22724406123161317,
|
|
"num_tokens": 35036729.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 4.954583930969238,
|
|
"epoch": 1.4937462775461583,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004788487614298219,
|
|
"loss": 4.6026,
|
|
"mean_token_accuracy": 0.2324803277850151,
|
|
"num_tokens": 35050787.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.037403297424317,
|
|
"epoch": 1.49434187016081,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047883072029550496,
|
|
"loss": 4.6565,
|
|
"mean_token_accuracy": 0.2264443725347519,
|
|
"num_tokens": 35062639.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.045908975601196,
|
|
"epoch": 1.4949374627754617,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047881267185011147,
|
|
"loss": 4.6971,
|
|
"mean_token_accuracy": 0.2131554439663887,
|
|
"num_tokens": 35075059.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.048370313644409,
|
|
"epoch": 1.4955330553901132,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047879461609428876,
|
|
"loss": 4.662,
|
|
"mean_token_accuracy": 0.22042252123355865,
|
|
"num_tokens": 35088518.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.104294681549073,
|
|
"epoch": 1.4961286480047646,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004787765530286846,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.21412735134363176,
|
|
"num_tokens": 35102097.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.04328989982605,
|
|
"epoch": 1.4967242406194163,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004787584826539468,
|
|
"loss": 4.6749,
|
|
"mean_token_accuracy": 0.216722771525383,
|
|
"num_tokens": 35114925.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.110938978195191,
|
|
"epoch": 1.497319833234068,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004787404049707235,
|
|
"loss": 4.6634,
|
|
"mean_token_accuracy": 0.22800421118736267,
|
|
"num_tokens": 35127718.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.089277553558349,
|
|
"epoch": 1.4979154258487195,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047872231997966316,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.221102674305439,
|
|
"num_tokens": 35140687.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.151646137237549,
|
|
"epoch": 1.498511018463371,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004787042276814144,
|
|
"loss": 4.6875,
|
|
"mean_token_accuracy": 0.22062532007694244,
|
|
"num_tokens": 35153347.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.074645853042602,
|
|
"epoch": 1.4991066110780227,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047868612807662616,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.2191597506403923,
|
|
"num_tokens": 35165503.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.105155515670776,
|
|
"epoch": 1.4997022036926742,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047866802116594776,
|
|
"loss": 4.7672,
|
|
"mean_token_accuracy": 0.2192861407995224,
|
|
"num_tokens": 35180396.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.118942546844482,
|
|
"epoch": 1.5002977963073256,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004786499069500286,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.2170213907957077,
|
|
"num_tokens": 35194678.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.153042507171631,
|
|
"epoch": 1.5008933889219773,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047863178542951833,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.21405800729990004,
|
|
"num_tokens": 35208394.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.040212678909302,
|
|
"epoch": 1.501488981536629,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000478613656605067,
|
|
"loss": 4.7272,
|
|
"mean_token_accuracy": 0.22398677468299866,
|
|
"num_tokens": 35222645.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.032999086380005,
|
|
"epoch": 1.5020845741512805,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047859552047732493,
|
|
"loss": 4.6295,
|
|
"mean_token_accuracy": 0.22862437814474107,
|
|
"num_tokens": 35237791.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.055375623703003,
|
|
"epoch": 1.502680166765932,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047857737704694255,
|
|
"loss": 4.6255,
|
|
"mean_token_accuracy": 0.22491673231124878,
|
|
"num_tokens": 35250036.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.021020698547363,
|
|
"epoch": 1.5032757593805837,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004785592263145705,
|
|
"loss": 4.6273,
|
|
"mean_token_accuracy": 0.22408059537410735,
|
|
"num_tokens": 35264653.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.081314182281494,
|
|
"epoch": 1.5038713519952354,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047854106828086016,
|
|
"loss": 4.7594,
|
|
"mean_token_accuracy": 0.2203597381711006,
|
|
"num_tokens": 35278479.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.100339889526367,
|
|
"epoch": 1.5044669446098868,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047852290294646255,
|
|
"loss": 4.7282,
|
|
"mean_token_accuracy": 0.22447387427091597,
|
|
"num_tokens": 35291532.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.123757362365723,
|
|
"epoch": 1.5050625372245383,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047850473031202937,
|
|
"loss": 4.6971,
|
|
"mean_token_accuracy": 0.21873784065246582,
|
|
"num_tokens": 35305212.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.074941778182984,
|
|
"epoch": 1.50565812983919,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004784865503782124,
|
|
"loss": 4.7681,
|
|
"mean_token_accuracy": 0.22117607593536376,
|
|
"num_tokens": 35318317.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.078860569000244,
|
|
"epoch": 1.5062537224538417,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047846836314566356,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.22048415690660478,
|
|
"num_tokens": 35333081.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.188883590698242,
|
|
"epoch": 1.5068493150684932,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047845016861503556,
|
|
"loss": 4.7525,
|
|
"mean_token_accuracy": 0.20832157880067825,
|
|
"num_tokens": 35346417.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.059765720367432,
|
|
"epoch": 1.5074449076831447,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047843196678698063,
|
|
"loss": 4.6775,
|
|
"mean_token_accuracy": 0.227616149187088,
|
|
"num_tokens": 35359939.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.023557710647583,
|
|
"epoch": 1.5080405002977963,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004784137576621519,
|
|
"loss": 4.6965,
|
|
"mean_token_accuracy": 0.22913715988397598,
|
|
"num_tokens": 35373105.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.105262041091919,
|
|
"epoch": 1.508636092912448,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004783955412412024,
|
|
"loss": 4.7016,
|
|
"mean_token_accuracy": 0.2199159473180771,
|
|
"num_tokens": 35388576.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.159907245635987,
|
|
"epoch": 1.5092316855270993,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004783773175247856,
|
|
"loss": 4.7938,
|
|
"mean_token_accuracy": 0.2145047128200531,
|
|
"num_tokens": 35402023.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.152121543884277,
|
|
"epoch": 1.509827278141751,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047835908651355503,
|
|
"loss": 4.7786,
|
|
"mean_token_accuracy": 0.22037537395954132,
|
|
"num_tokens": 35415870.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.041024398803711,
|
|
"epoch": 1.5104228707564027,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004783408482081646,
|
|
"loss": 4.7201,
|
|
"mean_token_accuracy": 0.2164259970188141,
|
|
"num_tokens": 35430027.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.163581228256225,
|
|
"epoch": 1.5110184633710542,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004783226026092687,
|
|
"loss": 4.8372,
|
|
"mean_token_accuracy": 0.20483325868844987,
|
|
"num_tokens": 35445210.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.108348560333252,
|
|
"epoch": 1.5116140559857056,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004783043497175215,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.2215101182460785,
|
|
"num_tokens": 35461138.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.036071062088013,
|
|
"epoch": 1.5122096486003573,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004782860895335779,
|
|
"loss": 4.7352,
|
|
"mean_token_accuracy": 0.2202337473630905,
|
|
"num_tokens": 35474923.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.039771318435669,
|
|
"epoch": 1.512805241215009,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004782678220580928,
|
|
"loss": 4.5997,
|
|
"mean_token_accuracy": 0.23196091651916503,
|
|
"num_tokens": 35489379.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.044519329071045,
|
|
"epoch": 1.5134008338296605,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047824954729172136,
|
|
"loss": 4.6326,
|
|
"mean_token_accuracy": 0.23301972001791,
|
|
"num_tokens": 35502261.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.049761343002319,
|
|
"epoch": 1.513996426444312,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047823126523511916,
|
|
"loss": 4.6186,
|
|
"mean_token_accuracy": 0.2339571163058281,
|
|
"num_tokens": 35515958.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.069379138946533,
|
|
"epoch": 1.5145920190589637,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004782129758889419,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.22222964763641356,
|
|
"num_tokens": 35531559.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.084957456588745,
|
|
"epoch": 1.5151876116736154,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047819467925384564,
|
|
"loss": 4.7349,
|
|
"mean_token_accuracy": 0.22111294269561768,
|
|
"num_tokens": 35546995.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.1518110752105715,
|
|
"epoch": 1.5157832042882668,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004781763753304866,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.2165910318493843,
|
|
"num_tokens": 35560327.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.045904493331909,
|
|
"epoch": 1.5163787969029183,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004781580641195213,
|
|
"loss": 4.7015,
|
|
"mean_token_accuracy": 0.21398550719022752,
|
|
"num_tokens": 35574862.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.023190116882324,
|
|
"epoch": 1.51697438951757,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047813974562160654,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.22808683216571807,
|
|
"num_tokens": 35589429.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.103570175170899,
|
|
"epoch": 1.5175699821322217,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004781214198373994,
|
|
"loss": 4.7201,
|
|
"mean_token_accuracy": 0.22138672471046447,
|
|
"num_tokens": 35602846.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.137869453430175,
|
|
"epoch": 1.5181655747468732,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004781030867675572,
|
|
"loss": 4.7503,
|
|
"mean_token_accuracy": 0.22214630246162415,
|
|
"num_tokens": 35615724.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.082975101470947,
|
|
"epoch": 1.5187611673615247,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047808474641273743,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.2146101862192154,
|
|
"num_tokens": 35629602.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.116541814804077,
|
|
"epoch": 1.5193567599761764,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047806639877359805,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.22294490337371825,
|
|
"num_tokens": 35643736.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.137428426742554,
|
|
"epoch": 1.5199523525908278,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004780480438507972,
|
|
"loss": 4.7324,
|
|
"mean_token_accuracy": 0.22377744317054749,
|
|
"num_tokens": 35658483.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.0653266429901125,
|
|
"epoch": 1.5205479452054793,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000478029681644993,
|
|
"loss": 4.6461,
|
|
"mean_token_accuracy": 0.22544953227043152,
|
|
"num_tokens": 35672671.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.135803985595703,
|
|
"epoch": 1.521143537820131,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004780113121568443,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.21406811624765396,
|
|
"num_tokens": 35686326.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.031058835983276,
|
|
"epoch": 1.5217391304347827,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047799293538700993,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.22526145875453948,
|
|
"num_tokens": 35698855.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.124206638336181,
|
|
"epoch": 1.5223347230494342,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047797455133614903,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.2101440966129303,
|
|
"num_tokens": 35714118.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.081034898757935,
|
|
"epoch": 1.5229303156640857,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00047795616000492086,
|
|
"loss": 4.6859,
|
|
"mean_token_accuracy": 0.21761665791273116,
|
|
"num_tokens": 35729467.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.112248659133911,
|
|
"epoch": 1.5235259082787374,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047793776139398535,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.22209193259477616,
|
|
"num_tokens": 35744566.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.0084919929504395,
|
|
"epoch": 1.524121500893389,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004779193555040023,
|
|
"loss": 4.6102,
|
|
"mean_token_accuracy": 0.2351776987314224,
|
|
"num_tokens": 35756843.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.1047741889953615,
|
|
"epoch": 1.5247170935080405,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047790094233563185,
|
|
"loss": 4.8093,
|
|
"mean_token_accuracy": 0.2082599937915802,
|
|
"num_tokens": 35770131.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.040320777893067,
|
|
"epoch": 1.525312686122692,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047788252188953447,
|
|
"loss": 4.6406,
|
|
"mean_token_accuracy": 0.2250714957714081,
|
|
"num_tokens": 35784294.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.058502054214477,
|
|
"epoch": 1.5259082787373437,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004778640941663709,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.2136522114276886,
|
|
"num_tokens": 35797947.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.071959781646728,
|
|
"epoch": 1.5265038713519954,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047784565916680216,
|
|
"loss": 4.6795,
|
|
"mean_token_accuracy": 0.22153379619121552,
|
|
"num_tokens": 35812978.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.057756328582764,
|
|
"epoch": 1.5270994639666469,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047782721689148936,
|
|
"loss": 4.678,
|
|
"mean_token_accuracy": 0.21764727979898452,
|
|
"num_tokens": 35826094.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.08285927772522,
|
|
"epoch": 1.5276950565812983,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004778087673410942,
|
|
"loss": 4.7538,
|
|
"mean_token_accuracy": 0.21706288307905197,
|
|
"num_tokens": 35841192.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.052150583267212,
|
|
"epoch": 1.52829064919595,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004777903105162782,
|
|
"loss": 4.6997,
|
|
"mean_token_accuracy": 0.22202544361352922,
|
|
"num_tokens": 35854519.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.035966300964356,
|
|
"epoch": 1.5288862418106015,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004777718464177035,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.2195112884044647,
|
|
"num_tokens": 35870196.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.05916018486023,
|
|
"epoch": 1.529481834425253,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004777533750460323,
|
|
"loss": 4.6072,
|
|
"mean_token_accuracy": 0.22719061225652695,
|
|
"num_tokens": 35882815.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.099365949630737,
|
|
"epoch": 1.5300774270399047,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047773489640192724,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.21646713316440583,
|
|
"num_tokens": 35894770.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.008804512023926,
|
|
"epoch": 1.5306730196545564,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047771641048605107,
|
|
"loss": 4.615,
|
|
"mean_token_accuracy": 0.2324028119444847,
|
|
"num_tokens": 35909183.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.069613122940064,
|
|
"epoch": 1.5312686122692079,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047769791729906685,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.22745154798030853,
|
|
"num_tokens": 35922625.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.073608875274658,
|
|
"epoch": 1.5318642048838593,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000477679416841638,
|
|
"loss": 4.6872,
|
|
"mean_token_accuracy": 0.22120971530675887,
|
|
"num_tokens": 35934805.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.0906572341918945,
|
|
"epoch": 1.532459797498511,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047766090911442787,
|
|
"loss": 4.7941,
|
|
"mean_token_accuracy": 0.21763137429952623,
|
|
"num_tokens": 35949178.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.125094747543335,
|
|
"epoch": 1.5330553901131627,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004776423941181005,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.21627340614795684,
|
|
"num_tokens": 35963812.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.121819543838501,
|
|
"epoch": 1.5336509827278142,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004776238718533199,
|
|
"loss": 4.7225,
|
|
"mean_token_accuracy": 0.21725161522626876,
|
|
"num_tokens": 35977633.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.048765993118286,
|
|
"epoch": 1.5342465753424657,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047760534232075045,
|
|
"loss": 4.6858,
|
|
"mean_token_accuracy": 0.21780141294002534,
|
|
"num_tokens": 35990779.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.132305240631103,
|
|
"epoch": 1.5348421679571174,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004775868055210568,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.21777909398078918,
|
|
"num_tokens": 36004482.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.1247838020324705,
|
|
"epoch": 1.535437760571769,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047756826145490383,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.2201211705803871,
|
|
"num_tokens": 36017430.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.0832945823669435,
|
|
"epoch": 1.5360333531864205,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047754971012295666,
|
|
"loss": 4.7287,
|
|
"mean_token_accuracy": 0.21865113377571105,
|
|
"num_tokens": 36031141.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.095955514907837,
|
|
"epoch": 1.536628945801072,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004775311515258807,
|
|
"loss": 4.7046,
|
|
"mean_token_accuracy": 0.22133170664310456,
|
|
"num_tokens": 36046318.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.133487129211426,
|
|
"epoch": 1.5372245384157237,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047751258566434176,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.21505051255226135,
|
|
"num_tokens": 36060911.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.045647716522216,
|
|
"epoch": 1.5378201310303752,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004774940125390055,
|
|
"loss": 4.7298,
|
|
"mean_token_accuracy": 0.21477012187242508,
|
|
"num_tokens": 36074760.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.115228319168091,
|
|
"epoch": 1.5384157236450267,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004774754321505383,
|
|
"loss": 4.7248,
|
|
"mean_token_accuracy": 0.21422351002693177,
|
|
"num_tokens": 36089281.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.116209411621094,
|
|
"epoch": 1.5390113162596784,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047745684449960655,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.21399058997631074,
|
|
"num_tokens": 36105313.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.0305798053741455,
|
|
"epoch": 1.53960690887433,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00047743824958687694,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.22154761999845504,
|
|
"num_tokens": 36121212.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.1590413570404055,
|
|
"epoch": 1.5402025014889815,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004774196474130165,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.22019188702106476,
|
|
"num_tokens": 36135904.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.037002754211426,
|
|
"epoch": 1.540798094103633,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047740103797869237,
|
|
"loss": 4.7007,
|
|
"mean_token_accuracy": 0.21685263216495515,
|
|
"num_tokens": 36149455.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.037549448013306,
|
|
"epoch": 1.5413936867182847,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047738242128457216,
|
|
"loss": 4.6614,
|
|
"mean_token_accuracy": 0.2198242038488388,
|
|
"num_tokens": 36163843.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.1523863792419435,
|
|
"epoch": 1.5419892793329364,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047736379733132343,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.21794231086969376,
|
|
"num_tokens": 36180268.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.157000207901001,
|
|
"epoch": 1.5425848719475879,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047734516611961443,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.21542332470417022,
|
|
"num_tokens": 36193116.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.025064849853516,
|
|
"epoch": 1.5431804645622393,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004773265276501133,
|
|
"loss": 4.698,
|
|
"mean_token_accuracy": 0.22673477083444596,
|
|
"num_tokens": 36205383.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.031267309188843,
|
|
"epoch": 1.543776057176891,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047730788192348856,
|
|
"loss": 4.6963,
|
|
"mean_token_accuracy": 0.22908132821321486,
|
|
"num_tokens": 36219028.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.111426305770874,
|
|
"epoch": 1.5443716497915427,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047728922894040905,
|
|
"loss": 4.7454,
|
|
"mean_token_accuracy": 0.21575708836317062,
|
|
"num_tokens": 36233804.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.055451726913452,
|
|
"epoch": 1.5449672424061942,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004772705687015437,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.218123759329319,
|
|
"num_tokens": 36246900.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.087399435043335,
|
|
"epoch": 1.5455628350208457,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047725190120756207,
|
|
"loss": 4.7249,
|
|
"mean_token_accuracy": 0.2179608926177025,
|
|
"num_tokens": 36260060.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.113989591598511,
|
|
"epoch": 1.5461584276354974,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047723322645913354,
|
|
"loss": 4.7314,
|
|
"mean_token_accuracy": 0.22251368910074235,
|
|
"num_tokens": 36274529.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.10456109046936,
|
|
"epoch": 1.5467540202501489,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047721454445692795,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.2147260993719101,
|
|
"num_tokens": 36288089.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.109133625030518,
|
|
"epoch": 1.5473496128648003,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047719585520161544,
|
|
"loss": 4.748,
|
|
"mean_token_accuracy": 0.21567821502685547,
|
|
"num_tokens": 36301498.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.021605539321899,
|
|
"epoch": 1.547945205479452,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004771771586938664,
|
|
"loss": 4.6272,
|
|
"mean_token_accuracy": 0.22901255488395691,
|
|
"num_tokens": 36314087.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.078443241119385,
|
|
"epoch": 1.5485407980941037,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047715845493435135,
|
|
"loss": 4.7557,
|
|
"mean_token_accuracy": 0.21128955483436584,
|
|
"num_tokens": 36328573.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.052424573898316,
|
|
"epoch": 1.5491363907087552,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004771397439237412,
|
|
"loss": 4.6646,
|
|
"mean_token_accuracy": 0.22884632498025895,
|
|
"num_tokens": 36341536.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.080207395553589,
|
|
"epoch": 1.5497319833234067,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047712102566270715,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.21684449911117554,
|
|
"num_tokens": 36357125.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.104403972625732,
|
|
"epoch": 1.5503275759380584,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00047710230015192054,
|
|
"loss": 4.7055,
|
|
"mean_token_accuracy": 0.2145639941096306,
|
|
"num_tokens": 36372466.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.05295763015747,
|
|
"epoch": 1.55092316855271,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047708356739205294,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.22756929248571395,
|
|
"num_tokens": 36386207.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.142563676834106,
|
|
"epoch": 1.5515187611673615,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004770648273837764,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.21257668137550353,
|
|
"num_tokens": 36403862.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.043832015991211,
|
|
"epoch": 1.552114353782013,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000477046080127763,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.22251486778259277,
|
|
"num_tokens": 36417813.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.073468255996704,
|
|
"epoch": 1.5527099463966647,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004770273256246853,
|
|
"loss": 4.6511,
|
|
"mean_token_accuracy": 0.22026983499526978,
|
|
"num_tokens": 36431346.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.000574159622192,
|
|
"epoch": 1.5533055390113164,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047700856387521585,
|
|
"loss": 4.5741,
|
|
"mean_token_accuracy": 0.23405462950468064,
|
|
"num_tokens": 36445027.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.145325136184693,
|
|
"epoch": 1.5539011316259679,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004769897948800276,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.21104658246040345,
|
|
"num_tokens": 36461727.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.115487289428711,
|
|
"epoch": 1.5544967242406194,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.00047697101863979394,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.21374740749597548,
|
|
"num_tokens": 36477715.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.0588050365448,
|
|
"epoch": 1.555092316855271,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004769522351551882,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.22700694501399993,
|
|
"num_tokens": 36490478.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.081364870071411,
|
|
"epoch": 1.5556879094699225,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004769334444268841,
|
|
"loss": 4.6776,
|
|
"mean_token_accuracy": 0.22384128868579864,
|
|
"num_tokens": 36505876.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.052907705307007,
|
|
"epoch": 1.556283502084574,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047691464645555564,
|
|
"loss": 4.6203,
|
|
"mean_token_accuracy": 0.2224231481552124,
|
|
"num_tokens": 36519773.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.112029218673706,
|
|
"epoch": 1.5568790946992257,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004768958412418772,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.21277913600206375,
|
|
"num_tokens": 36534828.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.05659670829773,
|
|
"epoch": 1.5574746873138774,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047687702878652303,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.2136513650417328,
|
|
"num_tokens": 36550067.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.013444709777832,
|
|
"epoch": 1.5580702799285289,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047685820909016823,
|
|
"loss": 4.5731,
|
|
"mean_token_accuracy": 0.22445879578590394,
|
|
"num_tokens": 36564051.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 4.9752795696258545,
|
|
"epoch": 1.5586658725431803,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004768393821534877,
|
|
"loss": 4.5843,
|
|
"mean_token_accuracy": 0.22912081480026245,
|
|
"num_tokens": 36578606.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.001463985443115,
|
|
"epoch": 1.559261465157832,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004768205479771566,
|
|
"loss": 4.5466,
|
|
"mean_token_accuracy": 0.2351718932390213,
|
|
"num_tokens": 36592192.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.0723464012146,
|
|
"epoch": 1.5598570577724837,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004768017065618506,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.2175020009279251,
|
|
"num_tokens": 36606896.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.085331201553345,
|
|
"epoch": 1.5604526503871352,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047678285790824556,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.21602609604597092,
|
|
"num_tokens": 36621133.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.094567537307739,
|
|
"epoch": 1.5610482430017867,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004767640020170174,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.21758985072374343,
|
|
"num_tokens": 36636738.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.053544998168945,
|
|
"epoch": 1.5616438356164384,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004767451388888426,
|
|
"loss": 4.6362,
|
|
"mean_token_accuracy": 0.22222991287708282,
|
|
"num_tokens": 36649544.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.0441914081573485,
|
|
"epoch": 1.56223942823109,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004767262685243976,
|
|
"loss": 4.6275,
|
|
"mean_token_accuracy": 0.2289229080080986,
|
|
"num_tokens": 36663821.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.048936986923218,
|
|
"epoch": 1.5628350208457416,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004767073909243594,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.22516467720270156,
|
|
"num_tokens": 36677707.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.108595991134644,
|
|
"epoch": 1.563430613460393,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047668850608940504,
|
|
"loss": 4.7348,
|
|
"mean_token_accuracy": 0.21239226907491685,
|
|
"num_tokens": 36691704.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.096688318252563,
|
|
"epoch": 1.5640262060750447,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004766696140202119,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.21605604737997056,
|
|
"num_tokens": 36706636.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.1052069664001465,
|
|
"epoch": 1.5646217986896962,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047665071471745754,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.22182251662015914,
|
|
"num_tokens": 36720035.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.04338116645813,
|
|
"epoch": 1.5652173913043477,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047663180818181995,
|
|
"loss": 4.59,
|
|
"mean_token_accuracy": 0.22607166618108748,
|
|
"num_tokens": 36735102.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.043479108810425,
|
|
"epoch": 1.5658129839189994,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047661289441397724,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.21203693747520447,
|
|
"num_tokens": 36751666.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.123244333267212,
|
|
"epoch": 1.566408576533651,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004765939734146078,
|
|
"loss": 4.7282,
|
|
"mean_token_accuracy": 0.21779274493455886,
|
|
"num_tokens": 36767217.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.08219895362854,
|
|
"epoch": 1.5670041691483025,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004765750451843904,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.22065631598234176,
|
|
"num_tokens": 36784961.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.090515279769898,
|
|
"epoch": 1.567599761762954,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004765561097240037,
|
|
"loss": 4.7295,
|
|
"mean_token_accuracy": 0.22654860019683837,
|
|
"num_tokens": 36798166.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.001590394973755,
|
|
"epoch": 1.5681953543776057,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047653716703412717,
|
|
"loss": 4.6855,
|
|
"mean_token_accuracy": 0.22618380039930344,
|
|
"num_tokens": 36813356.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.133729028701782,
|
|
"epoch": 1.5687909469922574,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004765182171154401,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.21785947680473328,
|
|
"num_tokens": 36826502.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.0322023868560795,
|
|
"epoch": 1.5693865396069089,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004764992599686222,
|
|
"loss": 4.6495,
|
|
"mean_token_accuracy": 0.2204647406935692,
|
|
"num_tokens": 36841359.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.046367025375366,
|
|
"epoch": 1.5699821322215604,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004764802955943535,
|
|
"loss": 4.6427,
|
|
"mean_token_accuracy": 0.22503810077905656,
|
|
"num_tokens": 36853908.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.075233316421508,
|
|
"epoch": 1.570577724836212,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047646132399331413,
|
|
"loss": 4.6539,
|
|
"mean_token_accuracy": 0.22597759068012238,
|
|
"num_tokens": 36866429.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.088863039016724,
|
|
"epoch": 1.5711733174508637,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047644234516618474,
|
|
"loss": 4.6803,
|
|
"mean_token_accuracy": 0.21896335631608962,
|
|
"num_tokens": 36879744.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.06858081817627,
|
|
"epoch": 1.5717689100655152,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047642335911364585,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.21680521965026855,
|
|
"num_tokens": 36894123.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.1565821170806885,
|
|
"epoch": 1.5723645026801667,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047640436583637865,
|
|
"loss": 4.7297,
|
|
"mean_token_accuracy": 0.2180768832564354,
|
|
"num_tokens": 36908090.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.07566385269165,
|
|
"epoch": 1.5729600952948184,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047638536533506424,
|
|
"loss": 4.713,
|
|
"mean_token_accuracy": 0.22046612948179245,
|
|
"num_tokens": 36925074.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.091121816635132,
|
|
"epoch": 1.5735556879094699,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00047636635761038427,
|
|
"loss": 4.7322,
|
|
"mean_token_accuracy": 0.21794330775737764,
|
|
"num_tokens": 36940133.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 4.999896240234375,
|
|
"epoch": 1.5741512805241213,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047634734266302037,
|
|
"loss": 4.6351,
|
|
"mean_token_accuracy": 0.226416976749897,
|
|
"num_tokens": 36954035.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.071046257019043,
|
|
"epoch": 1.574746873138773,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004763283204936547,
|
|
"loss": 4.7319,
|
|
"mean_token_accuracy": 0.22463206946849823,
|
|
"num_tokens": 36967072.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.094922637939453,
|
|
"epoch": 1.5753424657534247,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004763092911029695,
|
|
"loss": 4.7001,
|
|
"mean_token_accuracy": 0.22368937134742736,
|
|
"num_tokens": 36980774.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.080136060714722,
|
|
"epoch": 1.5759380583680762,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004762902544916474,
|
|
"loss": 4.6609,
|
|
"mean_token_accuracy": 0.22398502826690675,
|
|
"num_tokens": 36993388.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.068062829971313,
|
|
"epoch": 1.5765336509827277,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004762712106603711,
|
|
"loss": 4.6935,
|
|
"mean_token_accuracy": 0.22213831543922424,
|
|
"num_tokens": 37007074.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.1337803363800045,
|
|
"epoch": 1.5771292435973794,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047625215960982376,
|
|
"loss": 4.8344,
|
|
"mean_token_accuracy": 0.21278729140758515,
|
|
"num_tokens": 37021133.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.0119400978088375,
|
|
"epoch": 1.577724836212031,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047623310134068867,
|
|
"loss": 4.6329,
|
|
"mean_token_accuracy": 0.2203529506921768,
|
|
"num_tokens": 37035584.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.077388715744019,
|
|
"epoch": 1.5783204288266826,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004762140358536493,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.2166518896818161,
|
|
"num_tokens": 37048374.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.063349199295044,
|
|
"epoch": 1.578916021441334,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047619496314938977,
|
|
"loss": 4.6887,
|
|
"mean_token_accuracy": 0.22038875222206117,
|
|
"num_tokens": 37062340.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.085461759567261,
|
|
"epoch": 1.5795116140559857,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047617588322859395,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.22326409369707106,
|
|
"num_tokens": 37077469.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.115679931640625,
|
|
"epoch": 1.5801072066706374,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004761567960919463,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.21184205263853073,
|
|
"num_tokens": 37092941.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.066108655929566,
|
|
"epoch": 1.580702799285289,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047613770174013146,
|
|
"loss": 4.6032,
|
|
"mean_token_accuracy": 0.23402422666549683,
|
|
"num_tokens": 37105033.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.125306558609009,
|
|
"epoch": 1.5812983918999404,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004761186001738342,
|
|
"loss": 4.6918,
|
|
"mean_token_accuracy": 0.21557155698537828,
|
|
"num_tokens": 37119182.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.089870929718018,
|
|
"epoch": 1.581893984514592,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047609949139373994,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.2174947142601013,
|
|
"num_tokens": 37135354.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 4.994643974304199,
|
|
"epoch": 1.5824895771292438,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004760803754005337,
|
|
"loss": 4.5363,
|
|
"mean_token_accuracy": 0.2314160019159317,
|
|
"num_tokens": 37150453.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.172658252716064,
|
|
"epoch": 1.583085169743895,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004760612521949014,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.21182213723659515,
|
|
"num_tokens": 37164714.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.127355289459229,
|
|
"epoch": 1.5836807623585467,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047604212177752885,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.21392386704683303,
|
|
"num_tokens": 37178904.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.147969961166382,
|
|
"epoch": 1.5842763549731984,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047602298414910237,
|
|
"loss": 4.7776,
|
|
"mean_token_accuracy": 0.2188148394227028,
|
|
"num_tokens": 37194158.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.153967046737671,
|
|
"epoch": 1.5848719475878499,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047600383931030823,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.22124862521886826,
|
|
"num_tokens": 37206906.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.036443614959717,
|
|
"epoch": 1.5854675402025014,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004759846872618332,
|
|
"loss": 4.6806,
|
|
"mean_token_accuracy": 0.2247695505619049,
|
|
"num_tokens": 37220512.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.038170957565308,
|
|
"epoch": 1.586063132817153,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047596552800436426,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.2307659924030304,
|
|
"num_tokens": 37233481.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.085260391235352,
|
|
"epoch": 1.5866587254318048,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047594636153858844,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.21653993874788285,
|
|
"num_tokens": 37247421.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.096694421768189,
|
|
"epoch": 1.5872543180464562,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047592718786519347,
|
|
"loss": 4.7112,
|
|
"mean_token_accuracy": 0.22105657011270524,
|
|
"num_tokens": 37261126.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.116060590744018,
|
|
"epoch": 1.5878499106611077,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047590800698486693,
|
|
"loss": 4.7548,
|
|
"mean_token_accuracy": 0.21559767574071884,
|
|
"num_tokens": 37273951.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.063026237487793,
|
|
"epoch": 1.5884455032757594,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004758888188982969,
|
|
"loss": 4.6677,
|
|
"mean_token_accuracy": 0.2222508519887924,
|
|
"num_tokens": 37286937.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.030515241622925,
|
|
"epoch": 1.589041095890411,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004758696236061715,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.2278137296438217,
|
|
"num_tokens": 37300030.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.101555347442627,
|
|
"epoch": 1.5896366885050626,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004758504211091793,
|
|
"loss": 4.7548,
|
|
"mean_token_accuracy": 0.21420149356126786,
|
|
"num_tokens": 37316025.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.084883117675782,
|
|
"epoch": 1.590232281119714,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047583121140800906,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.21739934384822845,
|
|
"num_tokens": 37328414.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.113908100128174,
|
|
"epoch": 1.5908278737343657,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004758119945033497,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.22107914239168167,
|
|
"num_tokens": 37342865.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.1185637474060055,
|
|
"epoch": 1.5914234663490174,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004757927703958907,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.223610121011734,
|
|
"num_tokens": 37356340.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.042609834671021,
|
|
"epoch": 1.5920190589636687,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047577353908632156,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.22472876608371734,
|
|
"num_tokens": 37371047.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.151598501205444,
|
|
"epoch": 1.5926146515783204,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004757543005753319,
|
|
"loss": 4.7292,
|
|
"mean_token_accuracy": 0.2187427431344986,
|
|
"num_tokens": 37383245.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.132323551177978,
|
|
"epoch": 1.593210244192972,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047573505486361183,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.21485312283039093,
|
|
"num_tokens": 37397346.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.018090677261353,
|
|
"epoch": 1.5938058368076236,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004757158019518519,
|
|
"loss": 4.5914,
|
|
"mean_token_accuracy": 0.23643356412649155,
|
|
"num_tokens": 37409223.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.066848993301392,
|
|
"epoch": 1.594401429422275,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004756965418407424,
|
|
"loss": 4.7749,
|
|
"mean_token_accuracy": 0.21775502413511277,
|
|
"num_tokens": 37424127.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.126536417007446,
|
|
"epoch": 1.5949970220369267,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047567727453097427,
|
|
"loss": 4.6836,
|
|
"mean_token_accuracy": 0.222588449716568,
|
|
"num_tokens": 37437618.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.115372180938721,
|
|
"epoch": 1.5955926146515784,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004756580000232385,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.21899885982275008,
|
|
"num_tokens": 37452703.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.0867242336273195,
|
|
"epoch": 1.59618820726623,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047563871831822664,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.21878315806388854,
|
|
"num_tokens": 37465895.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.13597412109375,
|
|
"epoch": 1.5967837998808814,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004756194294166301,
|
|
"loss": 4.7322,
|
|
"mean_token_accuracy": 0.21915700137615204,
|
|
"num_tokens": 37480468.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.167027235031128,
|
|
"epoch": 1.597379392495533,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004756001333191409,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.2104160115122795,
|
|
"num_tokens": 37494742.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.022080945968628,
|
|
"epoch": 1.5979749851101848,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00047558083002645097,
|
|
"loss": 4.6099,
|
|
"mean_token_accuracy": 0.22611017972230912,
|
|
"num_tokens": 37511150.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.0697681427001955,
|
|
"epoch": 1.5985705777248362,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047556151953925287,
|
|
"loss": 4.679,
|
|
"mean_token_accuracy": 0.22090090364217757,
|
|
"num_tokens": 37525752.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.123274040222168,
|
|
"epoch": 1.5991661703394877,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004755422018582391,
|
|
"loss": 4.6445,
|
|
"mean_token_accuracy": 0.23469638973474502,
|
|
"num_tokens": 37537982.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.110441827774048,
|
|
"epoch": 1.5997617629541394,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047552287698410267,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.21058059483766556,
|
|
"num_tokens": 37552220.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.067387104034424,
|
|
"epoch": 1.600357355568791,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004755035449175366,
|
|
"loss": 4.6689,
|
|
"mean_token_accuracy": 0.22265934497117995,
|
|
"num_tokens": 37565306.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.078441190719604,
|
|
"epoch": 1.6009529481834424,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004754842056592344,
|
|
"loss": 4.597,
|
|
"mean_token_accuracy": 0.23050579726696013,
|
|
"num_tokens": 37579417.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.001167249679566,
|
|
"epoch": 1.601548540798094,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047546485920988975,
|
|
"loss": 4.5776,
|
|
"mean_token_accuracy": 0.22608577013015746,
|
|
"num_tokens": 37593506.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.063577604293823,
|
|
"epoch": 1.6021441334127458,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004754455055701965,
|
|
"loss": 4.6126,
|
|
"mean_token_accuracy": 0.21909884512424468,
|
|
"num_tokens": 37607441.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.158424615859985,
|
|
"epoch": 1.6027397260273972,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004754261447408489,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.21549448519945144,
|
|
"num_tokens": 37622723.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.0689623832702635,
|
|
"epoch": 1.6033353186420487,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004754067767225413,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.2243838131427765,
|
|
"num_tokens": 37637426.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 4.976523542404175,
|
|
"epoch": 1.6039309112567004,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004753874015159685,
|
|
"loss": 4.5904,
|
|
"mean_token_accuracy": 0.23458503186702728,
|
|
"num_tokens": 37649996.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.129864120483399,
|
|
"epoch": 1.604526503871352,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004753680191218254,
|
|
"loss": 4.6891,
|
|
"mean_token_accuracy": 0.2267841652035713,
|
|
"num_tokens": 37664188.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.036105394363403,
|
|
"epoch": 1.6051220964860036,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004753486295408073,
|
|
"loss": 4.6289,
|
|
"mean_token_accuracy": 0.22502228617668152,
|
|
"num_tokens": 37678058.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.029757356643676,
|
|
"epoch": 1.605717689100655,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004753292327736095,
|
|
"loss": 4.6142,
|
|
"mean_token_accuracy": 0.2333371490240097,
|
|
"num_tokens": 37692830.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.082929515838623,
|
|
"epoch": 1.6063132817153067,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047530982882092794,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.21980771720409392,
|
|
"num_tokens": 37706587.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.041657638549805,
|
|
"epoch": 1.6069088743299584,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004752904176834584,
|
|
"loss": 4.7008,
|
|
"mean_token_accuracy": 0.22407088428735733,
|
|
"num_tokens": 37720625.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.209434938430786,
|
|
"epoch": 1.60750446694461,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047527099936189735,
|
|
"loss": 4.8286,
|
|
"mean_token_accuracy": 0.2189367026090622,
|
|
"num_tokens": 37734826.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.207345104217529,
|
|
"epoch": 1.6081000595592614,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000475251573856941,
|
|
"loss": 4.7576,
|
|
"mean_token_accuracy": 0.2172040805220604,
|
|
"num_tokens": 37747856.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.072801351547241,
|
|
"epoch": 1.608695652173913,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004752321411692864,
|
|
"loss": 4.764,
|
|
"mean_token_accuracy": 0.21881682872772218,
|
|
"num_tokens": 37760291.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 4.9818305492401125,
|
|
"epoch": 1.6092912447885648,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047521270129963043,
|
|
"loss": 4.5796,
|
|
"mean_token_accuracy": 0.22867767810821532,
|
|
"num_tokens": 37773704.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.0996010303497314,
|
|
"epoch": 1.6098868374032163,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004751932542486705,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.22004323899745942,
|
|
"num_tokens": 37787461.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.149409627914428,
|
|
"epoch": 1.6104824300178677,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004751738000171039,
|
|
"loss": 4.7993,
|
|
"mean_token_accuracy": 0.21336464136838912,
|
|
"num_tokens": 37802484.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.091543817520142,
|
|
"epoch": 1.6110780226325194,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047515433860562855,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.22006210386753083,
|
|
"num_tokens": 37816741.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.172426652908325,
|
|
"epoch": 1.611673615247171,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047513487001494257,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.21360513120889663,
|
|
"num_tokens": 37834424.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.094771146774292,
|
|
"epoch": 1.6122692078618224,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004751153942457442,
|
|
"loss": 4.7024,
|
|
"mean_token_accuracy": 0.2158638894557953,
|
|
"num_tokens": 37848392.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.06676926612854,
|
|
"epoch": 1.612864800476474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000475095911298732,
|
|
"loss": 4.689,
|
|
"mean_token_accuracy": 0.22437868565320968,
|
|
"num_tokens": 37862014.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.049844121932983,
|
|
"epoch": 1.6134603930911258,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004750764211746048,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.22598198801279068,
|
|
"num_tokens": 37876378.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.089218425750732,
|
|
"epoch": 1.6140559857057772,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047505692387406163,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.22029389142990113,
|
|
"num_tokens": 37888854.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.019489431381226,
|
|
"epoch": 1.6146515783204287,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047503741939780195,
|
|
"loss": 4.637,
|
|
"mean_token_accuracy": 0.2272485002875328,
|
|
"num_tokens": 37902659.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.085574960708618,
|
|
"epoch": 1.6152471709350804,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004750179077465252,
|
|
"loss": 4.7526,
|
|
"mean_token_accuracy": 0.2167251452803612,
|
|
"num_tokens": 37917218.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.135437631607056,
|
|
"epoch": 1.615842763549732,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047499838892093134,
|
|
"loss": 4.6572,
|
|
"mean_token_accuracy": 0.22260661125183107,
|
|
"num_tokens": 37932141.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.043860578536988,
|
|
"epoch": 1.6164383561643836,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047497886292172044,
|
|
"loss": 4.654,
|
|
"mean_token_accuracy": 0.22557231038808823,
|
|
"num_tokens": 37945817.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 4.952942562103272,
|
|
"epoch": 1.617033948779035,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047495932974959287,
|
|
"loss": 4.6454,
|
|
"mean_token_accuracy": 0.22887247800827026,
|
|
"num_tokens": 37960475.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.076902198791504,
|
|
"epoch": 1.6176295413936868,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004749397894052493,
|
|
"loss": 4.6567,
|
|
"mean_token_accuracy": 0.21902382224798203,
|
|
"num_tokens": 37973211.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.057897329330444,
|
|
"epoch": 1.6182251340083385,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047492024188939056,
|
|
"loss": 4.5996,
|
|
"mean_token_accuracy": 0.22854783087968827,
|
|
"num_tokens": 37986760.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.08065094947815,
|
|
"epoch": 1.61882072662299,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004749006872027178,
|
|
"loss": 4.7759,
|
|
"mean_token_accuracy": 0.21988181173801422,
|
|
"num_tokens": 38002755.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.199906635284424,
|
|
"epoch": 1.6194163192376414,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004748811253459324,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.21270019561052322,
|
|
"num_tokens": 38017735.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.155392789840699,
|
|
"epoch": 1.620011911852293,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004748615563197359,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.22507564574480057,
|
|
"num_tokens": 38033537.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.055964994430542,
|
|
"epoch": 1.6206075044669446,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004748419801248304,
|
|
"loss": 4.6706,
|
|
"mean_token_accuracy": 0.2211317837238312,
|
|
"num_tokens": 38049311.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.063900279998779,
|
|
"epoch": 1.621203097081596,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004748223967619181,
|
|
"loss": 4.6694,
|
|
"mean_token_accuracy": 0.2254470944404602,
|
|
"num_tokens": 38063269.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.148845100402832,
|
|
"epoch": 1.6217986896962477,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047480280623170116,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.2063573941588402,
|
|
"num_tokens": 38077642.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.156454133987427,
|
|
"epoch": 1.6223942823108994,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047478320853488256,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.21453038454055787,
|
|
"num_tokens": 38091910.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.123357439041138,
|
|
"epoch": 1.622989874925551,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047476360367216505,
|
|
"loss": 4.8247,
|
|
"mean_token_accuracy": 0.21149093955755233,
|
|
"num_tokens": 38105105.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.106569814682007,
|
|
"epoch": 1.6235854675402024,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004747439916442518,
|
|
"loss": 4.6849,
|
|
"mean_token_accuracy": 0.21649195551872252,
|
|
"num_tokens": 38118841.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.060335779190064,
|
|
"epoch": 1.624181060154854,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004747243724518465,
|
|
"loss": 4.6595,
|
|
"mean_token_accuracy": 0.22956012487411498,
|
|
"num_tokens": 38132116.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.039406394958496,
|
|
"epoch": 1.6247766527695058,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004747047460956525,
|
|
"loss": 4.6193,
|
|
"mean_token_accuracy": 0.23192200809717178,
|
|
"num_tokens": 38144944.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.002575206756592,
|
|
"epoch": 1.6253722453841573,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004746851125763741,
|
|
"loss": 4.6065,
|
|
"mean_token_accuracy": 0.23431940078735353,
|
|
"num_tokens": 38158464.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.081974935531616,
|
|
"epoch": 1.6259678379988087,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047466547189471534,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.21680967956781388,
|
|
"num_tokens": 38173807.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.103551149368286,
|
|
"epoch": 1.6265634306134604,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004746458240513807,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.21469406932592391,
|
|
"num_tokens": 38189478.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.093722295761109,
|
|
"epoch": 1.6271590232281121,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000474626169047075,
|
|
"loss": 4.6531,
|
|
"mean_token_accuracy": 0.2200460508465767,
|
|
"num_tokens": 38203478.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.046313619613647,
|
|
"epoch": 1.6277546158427636,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004746065068825032,
|
|
"loss": 4.6063,
|
|
"mean_token_accuracy": 0.22644207030534744,
|
|
"num_tokens": 38216273.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.091544246673584,
|
|
"epoch": 1.628350208457415,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047458683755837046,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.2263450264930725,
|
|
"num_tokens": 38228554.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 4.98862361907959,
|
|
"epoch": 1.6289458010720668,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004745671610753824,
|
|
"loss": 4.6668,
|
|
"mean_token_accuracy": 0.21610803306102752,
|
|
"num_tokens": 38242984.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.049959182739258,
|
|
"epoch": 1.6295413936867182,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004745474774342448,
|
|
"loss": 4.7291,
|
|
"mean_token_accuracy": 0.22741764187812805,
|
|
"num_tokens": 38256224.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.139156246185303,
|
|
"epoch": 1.6301369863013697,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004745277866356636,
|
|
"loss": 4.775,
|
|
"mean_token_accuracy": 0.21642098277807237,
|
|
"num_tokens": 38269919.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.055359172821045,
|
|
"epoch": 1.6307325789160214,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004745080886803451,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.23186200261116027,
|
|
"num_tokens": 38284363.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.105393791198731,
|
|
"epoch": 1.631328171530673,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004744883835689958,
|
|
"loss": 4.7235,
|
|
"mean_token_accuracy": 0.2216292530298233,
|
|
"num_tokens": 38299650.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.079978990554809,
|
|
"epoch": 1.6319237641453246,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047446867130232257,
|
|
"loss": 4.6728,
|
|
"mean_token_accuracy": 0.22596388906240464,
|
|
"num_tokens": 38313632.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.06387767791748,
|
|
"epoch": 1.632519356759976,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004744489518810324,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.22191354632377625,
|
|
"num_tokens": 38327037.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.109878301620483,
|
|
"epoch": 1.6331149493746278,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047442922530583265,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.22164003401994706,
|
|
"num_tokens": 38341833.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.140852642059326,
|
|
"epoch": 1.6337105419892795,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004744094915774308,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.21278569251298904,
|
|
"num_tokens": 38357261.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.120931911468506,
|
|
"epoch": 1.634306134603931,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047438975069653475,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.21828466057777404,
|
|
"num_tokens": 38371448.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 4.958218193054199,
|
|
"epoch": 1.6349017272185824,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004743700026638525,
|
|
"loss": 4.5857,
|
|
"mean_token_accuracy": 0.23538173884153366,
|
|
"num_tokens": 38385385.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.057118082046509,
|
|
"epoch": 1.635497319833234,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004743502474800924,
|
|
"loss": 4.6712,
|
|
"mean_token_accuracy": 0.22495939582586288,
|
|
"num_tokens": 38398506.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.116157579421997,
|
|
"epoch": 1.6360929124478858,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047433048514596303,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.2171803116798401,
|
|
"num_tokens": 38414283.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.090861225128174,
|
|
"epoch": 1.6366885050625373,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004743107156621733,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.22109084576368332,
|
|
"num_tokens": 38427436.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.1174397468566895,
|
|
"epoch": 1.6372840976771887,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00047429093902943227,
|
|
"loss": 4.7761,
|
|
"mean_token_accuracy": 0.21055519282817842,
|
|
"num_tokens": 38442414.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.105772352218628,
|
|
"epoch": 1.6378796902918404,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004742711552484492,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.22054517567157744,
|
|
"num_tokens": 38457196.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.048486375808716,
|
|
"epoch": 1.638475282906492,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004742513643199339,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.23074866980314254,
|
|
"num_tokens": 38470425.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.083620405197143,
|
|
"epoch": 1.6390708755211434,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000474231566244596,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.21750281304121016,
|
|
"num_tokens": 38484731.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.101421260833741,
|
|
"epoch": 1.639666468135795,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047421176102314586,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.21966370195150375,
|
|
"num_tokens": 38499291.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.078377389907837,
|
|
"epoch": 1.6402620607504468,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047419194865629366,
|
|
"loss": 4.6304,
|
|
"mean_token_accuracy": 0.22314734756946564,
|
|
"num_tokens": 38513082.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.0266101360321045,
|
|
"epoch": 1.6408576533650983,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047417212914475015,
|
|
"loss": 4.6737,
|
|
"mean_token_accuracy": 0.2223345845937729,
|
|
"num_tokens": 38526438.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.052158546447754,
|
|
"epoch": 1.6414532459797497,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047415230248922625,
|
|
"loss": 4.6445,
|
|
"mean_token_accuracy": 0.22833386957645416,
|
|
"num_tokens": 38541749.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.064024591445923,
|
|
"epoch": 1.6420488385944014,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004741324686904331,
|
|
"loss": 4.6706,
|
|
"mean_token_accuracy": 0.218344846367836,
|
|
"num_tokens": 38555406.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.029510354995727,
|
|
"epoch": 1.6426444312090531,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047411262774908194,
|
|
"loss": 4.6106,
|
|
"mean_token_accuracy": 0.2298828363418579,
|
|
"num_tokens": 38567959.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.096603775024414,
|
|
"epoch": 1.6432400238237046,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004740927796658846,
|
|
"loss": 4.7443,
|
|
"mean_token_accuracy": 0.2224123001098633,
|
|
"num_tokens": 38581199.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.069440841674805,
|
|
"epoch": 1.643835616438356,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000474072924441553,
|
|
"loss": 4.6622,
|
|
"mean_token_accuracy": 0.22065708935260772,
|
|
"num_tokens": 38594050.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.028115129470825,
|
|
"epoch": 1.6444312090530078,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00047405306207679926,
|
|
"loss": 4.731,
|
|
"mean_token_accuracy": 0.22332251965999603,
|
|
"num_tokens": 38608649.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.142982721328735,
|
|
"epoch": 1.6450268016676595,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047403319257233585,
|
|
"loss": 4.7027,
|
|
"mean_token_accuracy": 0.21898289322853087,
|
|
"num_tokens": 38623023.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.039276552200318,
|
|
"epoch": 1.645622394282311,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004740133159288753,
|
|
"loss": 4.5896,
|
|
"mean_token_accuracy": 0.23389507383108138,
|
|
"num_tokens": 38637738.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.008128261566162,
|
|
"epoch": 1.6462179868969624,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004739934321471308,
|
|
"loss": 4.5922,
|
|
"mean_token_accuracy": 0.22939784526824952,
|
|
"num_tokens": 38651542.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.112092447280884,
|
|
"epoch": 1.6468135795116141,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004739735412278154,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.20874992161989211,
|
|
"num_tokens": 38667607.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.093762445449829,
|
|
"epoch": 1.6474091721262656,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004739536431716427,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.22603701800107956,
|
|
"num_tokens": 38681192.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.144165134429931,
|
|
"epoch": 1.648004764740917,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047393373797932614,
|
|
"loss": 4.7616,
|
|
"mean_token_accuracy": 0.22261289060115813,
|
|
"num_tokens": 38694124.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.049265718460083,
|
|
"epoch": 1.6486003573555688,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047391382565157994,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.2195110648870468,
|
|
"num_tokens": 38709225.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.033479785919189,
|
|
"epoch": 1.6491959499702205,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004738939061891182,
|
|
"loss": 4.5989,
|
|
"mean_token_accuracy": 0.23244225978851318,
|
|
"num_tokens": 38723662.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.078571796417236,
|
|
"epoch": 1.649791542584872,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004738739795926554,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.22083508223295212,
|
|
"num_tokens": 38738561.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.1108996868133545,
|
|
"epoch": 1.6503871351995234,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004738540458629063,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.2170058622956276,
|
|
"num_tokens": 38752795.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.065823984146118,
|
|
"epoch": 1.650982727814175,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004738341050005859,
|
|
"loss": 4.6278,
|
|
"mean_token_accuracy": 0.22659876048564911,
|
|
"num_tokens": 38764854.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 4.994152975082398,
|
|
"epoch": 1.6515783204288268,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047381415700640953,
|
|
"loss": 4.6169,
|
|
"mean_token_accuracy": 0.22988577634096147,
|
|
"num_tokens": 38778856.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.063711023330688,
|
|
"epoch": 1.6521739130434783,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047379420188109245,
|
|
"loss": 4.6772,
|
|
"mean_token_accuracy": 0.23235953450202942,
|
|
"num_tokens": 38790970.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.054870843887329,
|
|
"epoch": 1.6527695056581297,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004737742396253506,
|
|
"loss": 4.6453,
|
|
"mean_token_accuracy": 0.22580572068691254,
|
|
"num_tokens": 38805311.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.065508556365967,
|
|
"epoch": 1.6533650982727814,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004737542702399,
|
|
"loss": 4.6443,
|
|
"mean_token_accuracy": 0.23104502111673356,
|
|
"num_tokens": 38818690.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.062322473526001,
|
|
"epoch": 1.6539606908874331,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047373429372545695,
|
|
"loss": 4.7133,
|
|
"mean_token_accuracy": 0.2136026993393898,
|
|
"num_tokens": 38833166.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.015437316894531,
|
|
"epoch": 1.6545562835020846,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004737143100827378,
|
|
"loss": 4.6862,
|
|
"mean_token_accuracy": 0.22133721113204957,
|
|
"num_tokens": 38847630.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.04729380607605,
|
|
"epoch": 1.655151876116736,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004736943193124595,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.23132118582725525,
|
|
"num_tokens": 38862483.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.083838319778442,
|
|
"epoch": 1.6557474687313878,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000473674321415339,
|
|
"loss": 4.6464,
|
|
"mean_token_accuracy": 0.2245562419295311,
|
|
"num_tokens": 38876619.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.13241171836853,
|
|
"epoch": 1.6563430613460393,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004736543163920936,
|
|
"loss": 4.7786,
|
|
"mean_token_accuracy": 0.21710905581712722,
|
|
"num_tokens": 38889125.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.099493169784546,
|
|
"epoch": 1.6569386539606907,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004736343042434409,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.21544788777828217,
|
|
"num_tokens": 38903392.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.113522577285766,
|
|
"epoch": 1.6575342465753424,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004736142849700986,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.21486711651086807,
|
|
"num_tokens": 38917610.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.113808679580688,
|
|
"epoch": 1.6581298391899941,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047359425857278485,
|
|
"loss": 4.766,
|
|
"mean_token_accuracy": 0.22108643800020217,
|
|
"num_tokens": 38930659.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.008272266387939,
|
|
"epoch": 1.6587254318046456,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000473574225052218,
|
|
"loss": 4.561,
|
|
"mean_token_accuracy": 0.22702931463718415,
|
|
"num_tokens": 38945958.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.090182065963745,
|
|
"epoch": 1.659321024419297,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004735541844091165,
|
|
"loss": 4.714,
|
|
"mean_token_accuracy": 0.22584151178598405,
|
|
"num_tokens": 38960817.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.095216369628906,
|
|
"epoch": 1.6599166170339488,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004735341366441993,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.2195375457406044,
|
|
"num_tokens": 38976227.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.098378896713257,
|
|
"epoch": 1.6605122096486005,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047351408175818537,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.21613662391901017,
|
|
"num_tokens": 38991586.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.016927909851074,
|
|
"epoch": 1.661107802263252,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004734940197517941,
|
|
"loss": 4.6212,
|
|
"mean_token_accuracy": 0.22112464159727097,
|
|
"num_tokens": 39004693.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.108083200454712,
|
|
"epoch": 1.6617033948779034,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000473473950625745,
|
|
"loss": 4.8147,
|
|
"mean_token_accuracy": 0.21764764487743377,
|
|
"num_tokens": 39018546.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.044873380661011,
|
|
"epoch": 1.6622989874925551,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047345387438075805,
|
|
"loss": 4.6104,
|
|
"mean_token_accuracy": 0.22598164081573485,
|
|
"num_tokens": 39032219.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.0947346687316895,
|
|
"epoch": 1.6628945801072068,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004734337910175533,
|
|
"loss": 4.7733,
|
|
"mean_token_accuracy": 0.21427765786647796,
|
|
"num_tokens": 39047379.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.051333618164063,
|
|
"epoch": 1.6634901727218583,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047341370053685113,
|
|
"loss": 4.6438,
|
|
"mean_token_accuracy": 0.22907203882932664,
|
|
"num_tokens": 39060627.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.079277658462525,
|
|
"epoch": 1.6640857653365098,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004733936029393721,
|
|
"loss": 4.6951,
|
|
"mean_token_accuracy": 0.23163777440786362,
|
|
"num_tokens": 39073210.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.024454116821289,
|
|
"epoch": 1.6646813579511615,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004733734982258371,
|
|
"loss": 4.6694,
|
|
"mean_token_accuracy": 0.22225516140460969,
|
|
"num_tokens": 39087957.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.069714164733886,
|
|
"epoch": 1.665276950565813,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047335338639696724,
|
|
"loss": 4.6495,
|
|
"mean_token_accuracy": 0.22079077810049058,
|
|
"num_tokens": 39102744.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.1675718307495115,
|
|
"epoch": 1.6658725431804644,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004733332674534839,
|
|
"loss": 4.783,
|
|
"mean_token_accuracy": 0.2148351714015007,
|
|
"num_tokens": 39116771.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.114459609985351,
|
|
"epoch": 1.666468135795116,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004733131413961087,
|
|
"loss": 4.7227,
|
|
"mean_token_accuracy": 0.21948347091674805,
|
|
"num_tokens": 39132634.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.146283054351807,
|
|
"epoch": 1.6670637284097678,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047329300822556363,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.2199109449982643,
|
|
"num_tokens": 39146837.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.120169925689697,
|
|
"epoch": 1.6676593210244193,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004732728679425707,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.2189948081970215,
|
|
"num_tokens": 39162067.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.053553771972656,
|
|
"epoch": 1.6682549136390707,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004732527205478524,
|
|
"loss": 4.6611,
|
|
"mean_token_accuracy": 0.2252824440598488,
|
|
"num_tokens": 39175466.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.055205583572388,
|
|
"epoch": 1.6688505062537224,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004732325660421314,
|
|
"loss": 4.6759,
|
|
"mean_token_accuracy": 0.22024868577718734,
|
|
"num_tokens": 39188943.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.027273845672608,
|
|
"epoch": 1.6694460988683741,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004732124044261304,
|
|
"loss": 4.6069,
|
|
"mean_token_accuracy": 0.2280747577548027,
|
|
"num_tokens": 39202544.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.071313762664795,
|
|
"epoch": 1.6700416914830256,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047319223570057293,
|
|
"loss": 4.6821,
|
|
"mean_token_accuracy": 0.22507928907871247,
|
|
"num_tokens": 39217183.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.0294890880584715,
|
|
"epoch": 1.670637284097677,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004731720598661821,
|
|
"loss": 4.6441,
|
|
"mean_token_accuracy": 0.2285213828086853,
|
|
"num_tokens": 39232227.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.131817436218261,
|
|
"epoch": 1.6712328767123288,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047315187692368167,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.2230467215180397,
|
|
"num_tokens": 39245393.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.1640702247619625,
|
|
"epoch": 1.6718284693269805,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004731316868737957,
|
|
"loss": 4.7213,
|
|
"mean_token_accuracy": 0.2130257695913315,
|
|
"num_tokens": 39258325.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.098360872268676,
|
|
"epoch": 1.672424061941632,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047311148971724816,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.21475444734096527,
|
|
"num_tokens": 39271372.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.023782634735108,
|
|
"epoch": 1.6730196545562834,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004730912854547636,
|
|
"loss": 4.6327,
|
|
"mean_token_accuracy": 0.2258676290512085,
|
|
"num_tokens": 39286054.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.111256790161133,
|
|
"epoch": 1.6736152471709351,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004730710740870667,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.21803996413946153,
|
|
"num_tokens": 39301005.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.1273682594299315,
|
|
"epoch": 1.6742108397855868,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047305085561488247,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.22212927788496017,
|
|
"num_tokens": 39315931.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.057091760635376,
|
|
"epoch": 1.674806432400238,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047303063003893605,
|
|
"loss": 4.6643,
|
|
"mean_token_accuracy": 0.22106578797101975,
|
|
"num_tokens": 39330015.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 4.970300006866455,
|
|
"epoch": 1.6754020250148898,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004730103973599529,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.22982407361268997,
|
|
"num_tokens": 39346024.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.076504516601562,
|
|
"epoch": 1.6759976176295415,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004729901575786588,
|
|
"loss": 4.7421,
|
|
"mean_token_accuracy": 0.2227202445268631,
|
|
"num_tokens": 39359887.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.10155758857727,
|
|
"epoch": 1.676593210244193,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00047296991069577953,
|
|
"loss": 4.6529,
|
|
"mean_token_accuracy": 0.22511101365089417,
|
|
"num_tokens": 39374999.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.070360088348389,
|
|
"epoch": 1.6771888028588444,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004729496567120415,
|
|
"loss": 4.6329,
|
|
"mean_token_accuracy": 0.23134259283542633,
|
|
"num_tokens": 39389246.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 4.994902753829956,
|
|
"epoch": 1.6777843954734961,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047292939562817115,
|
|
"loss": 4.586,
|
|
"mean_token_accuracy": 0.22917629033327103,
|
|
"num_tokens": 39403026.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.03957347869873,
|
|
"epoch": 1.6783799880881478,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004729091274448952,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.22263724952936173,
|
|
"num_tokens": 39414933.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.1046887874603275,
|
|
"epoch": 1.6789755807027993,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004728888521629406,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.2222687616944313,
|
|
"num_tokens": 39428369.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.107641506195068,
|
|
"epoch": 1.6795711733174508,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047286856978303465,
|
|
"loss": 4.714,
|
|
"mean_token_accuracy": 0.21859684437513352,
|
|
"num_tokens": 39440892.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.102293872833252,
|
|
"epoch": 1.6801667659321025,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004728482803059048,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.22166793793439865,
|
|
"num_tokens": 39454607.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.041917848587036,
|
|
"epoch": 1.6807623585467542,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004728279837322788,
|
|
"loss": 4.6423,
|
|
"mean_token_accuracy": 0.226563261449337,
|
|
"num_tokens": 39470112.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.108580112457275,
|
|
"epoch": 1.6813579511614056,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004728076800628847,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.2284761145710945,
|
|
"num_tokens": 39484498.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.042306566238404,
|
|
"epoch": 1.681953543776057,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004727873692984507,
|
|
"loss": 4.6381,
|
|
"mean_token_accuracy": 0.22364378869533538,
|
|
"num_tokens": 39500571.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.016297483444214,
|
|
"epoch": 1.6825491363907088,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004727670514397054,
|
|
"loss": 4.6118,
|
|
"mean_token_accuracy": 0.2281648576259613,
|
|
"num_tokens": 39514804.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.020611953735352,
|
|
"epoch": 1.6831447290053605,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004727467264873775,
|
|
"loss": 4.6068,
|
|
"mean_token_accuracy": 0.228270323574543,
|
|
"num_tokens": 39527190.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.006283903121949,
|
|
"epoch": 1.6837403216200117,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000472726394442196,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.22205183804035186,
|
|
"num_tokens": 39540658.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.065392780303955,
|
|
"epoch": 1.6843359142346634,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047270605530489026,
|
|
"loss": 4.6671,
|
|
"mean_token_accuracy": 0.22577531039714813,
|
|
"num_tokens": 39553648.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.127428293228149,
|
|
"epoch": 1.6849315068493151,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047268570907618967,
|
|
"loss": 4.7395,
|
|
"mean_token_accuracy": 0.2172837421298027,
|
|
"num_tokens": 39569011.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.108516550064087,
|
|
"epoch": 1.6855270994639666,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004726653557568242,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.22012814730405808,
|
|
"num_tokens": 39582512.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.069438171386719,
|
|
"epoch": 1.686122692078618,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047264499534752384,
|
|
"loss": 4.6739,
|
|
"mean_token_accuracy": 0.22500666975975037,
|
|
"num_tokens": 39596806.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.096463394165039,
|
|
"epoch": 1.6867182846932698,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047262462784901875,
|
|
"loss": 4.5898,
|
|
"mean_token_accuracy": 0.2263421818614006,
|
|
"num_tokens": 39609905.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.054474401473999,
|
|
"epoch": 1.6873138773079215,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047260425326203965,
|
|
"loss": 4.6352,
|
|
"mean_token_accuracy": 0.22421417832374574,
|
|
"num_tokens": 39622152.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.00434103012085,
|
|
"epoch": 1.687909469922573,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004725838715873172,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.22494445294141768,
|
|
"num_tokens": 39634041.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.05883936882019,
|
|
"epoch": 1.6885050625372244,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047256348282558264,
|
|
"loss": 4.6438,
|
|
"mean_token_accuracy": 0.22707951962947845,
|
|
"num_tokens": 39647932.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.093907451629638,
|
|
"epoch": 1.6891006551518761,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047254308697756704,
|
|
"loss": 4.7018,
|
|
"mean_token_accuracy": 0.21968656480312349,
|
|
"num_tokens": 39662393.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.080121278762817,
|
|
"epoch": 1.6896962477665278,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004725226840440022,
|
|
"loss": 4.6011,
|
|
"mean_token_accuracy": 0.22869340181350709,
|
|
"num_tokens": 39676718.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.174259424209595,
|
|
"epoch": 1.6902918403811793,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047250227402561976,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.2198458194732666,
|
|
"num_tokens": 39692663.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.059604549407959,
|
|
"epoch": 1.6908874329958308,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004724818569231519,
|
|
"loss": 4.6068,
|
|
"mean_token_accuracy": 0.23537128120660783,
|
|
"num_tokens": 39706874.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.086166906356811,
|
|
"epoch": 1.6914830256104825,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00047246143273733097,
|
|
"loss": 4.645,
|
|
"mean_token_accuracy": 0.2278333768248558,
|
|
"num_tokens": 39722194.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.0984924793243405,
|
|
"epoch": 1.6920786182251342,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004724410014688894,
|
|
"loss": 4.6918,
|
|
"mean_token_accuracy": 0.22893082052469255,
|
|
"num_tokens": 39735041.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 4.945257186889648,
|
|
"epoch": 1.6926742108397854,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047242056311856017,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.23212341368198394,
|
|
"num_tokens": 39749582.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.13014588356018,
|
|
"epoch": 1.6932698034544371,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004724001176870764,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.2217718243598938,
|
|
"num_tokens": 39764423.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.157340383529663,
|
|
"epoch": 1.6938653960690888,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004723796651751713,
|
|
"loss": 4.7371,
|
|
"mean_token_accuracy": 0.22330183088779448,
|
|
"num_tokens": 39778072.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.066633987426758,
|
|
"epoch": 1.6944609886837403,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004723592055835784,
|
|
"loss": 4.6315,
|
|
"mean_token_accuracy": 0.22634869515895845,
|
|
"num_tokens": 39791472.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 4.969272708892822,
|
|
"epoch": 1.6950565812983918,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047233873891303193,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.23468981832265853,
|
|
"num_tokens": 39804264.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.0902495861053465,
|
|
"epoch": 1.6956521739130435,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047231826516426554,
|
|
"loss": 4.7555,
|
|
"mean_token_accuracy": 0.221016925573349,
|
|
"num_tokens": 39818275.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.051016187667846,
|
|
"epoch": 1.6962477665276952,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004722977843380139,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.21676493138074876,
|
|
"num_tokens": 39832765.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.087419033050537,
|
|
"epoch": 1.6968433591423466,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004722772964350115,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.22304622530937196,
|
|
"num_tokens": 39846113.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.1282055377960205,
|
|
"epoch": 1.697438951756998,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047225680145599326,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.22300835251808165,
|
|
"num_tokens": 39860076.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.055011177062989,
|
|
"epoch": 1.6980345443716498,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004722362994016942,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.22652070373296737,
|
|
"num_tokens": 39873098.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.121267700195313,
|
|
"epoch": 1.6986301369863015,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004722157902728498,
|
|
"loss": 4.7799,
|
|
"mean_token_accuracy": 0.21729885041713715,
|
|
"num_tokens": 39886921.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.130379390716553,
|
|
"epoch": 1.699225729600953,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047219527407019575,
|
|
"loss": 4.6999,
|
|
"mean_token_accuracy": 0.22003719210624695,
|
|
"num_tokens": 39900525.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.086550283432007,
|
|
"epoch": 1.6998213222156044,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047217475079446773,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.2302380695939064,
|
|
"num_tokens": 39912302.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.121575927734375,
|
|
"epoch": 1.7004169148302561,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000472154220446402,
|
|
"loss": 4.6531,
|
|
"mean_token_accuracy": 0.22367972284555435,
|
|
"num_tokens": 39924575.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.044223499298096,
|
|
"epoch": 1.7010125074449078,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047213368302673496,
|
|
"loss": 4.6482,
|
|
"mean_token_accuracy": 0.21884367018938064,
|
|
"num_tokens": 39941997.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.084317970275879,
|
|
"epoch": 1.7016081000595593,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004721131385362033,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.22702962905168533,
|
|
"num_tokens": 39955490.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.116968059539795,
|
|
"epoch": 1.7022036926742108,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004720925869755437,
|
|
"loss": 4.6927,
|
|
"mean_token_accuracy": 0.2217881366610527,
|
|
"num_tokens": 39968051.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.043744325637817,
|
|
"epoch": 1.7027992852888625,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047207202834549357,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.22221606075763703,
|
|
"num_tokens": 39980609.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.078524971008301,
|
|
"epoch": 1.703394877903514,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047205146264679015,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.21478544026613236,
|
|
"num_tokens": 39995065.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.037719964981079,
|
|
"epoch": 1.7039904705181654,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047203088988017114,
|
|
"loss": 4.6232,
|
|
"mean_token_accuracy": 0.22374828308820724,
|
|
"num_tokens": 40010122.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.161655235290527,
|
|
"epoch": 1.7045860631328171,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047201031004637445,
|
|
"loss": 4.7003,
|
|
"mean_token_accuracy": 0.21419977843761445,
|
|
"num_tokens": 40022467.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.087610673904419,
|
|
"epoch": 1.7051816557474688,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004719897231461383,
|
|
"loss": 4.6435,
|
|
"mean_token_accuracy": 0.22465473562479019,
|
|
"num_tokens": 40036128.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.107357311248779,
|
|
"epoch": 1.7057772483621203,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004719691291802011,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.21618943512439728,
|
|
"num_tokens": 40049594.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.07416353225708,
|
|
"epoch": 1.7063728409767718,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047194852814930145,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.2162050113081932,
|
|
"num_tokens": 40064189.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.148539781570435,
|
|
"epoch": 1.7069684335914235,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047192792005417827,
|
|
"loss": 4.7348,
|
|
"mean_token_accuracy": 0.2126148983836174,
|
|
"num_tokens": 40079758.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.051669692993164,
|
|
"epoch": 1.7075640262060752,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004719073048955709,
|
|
"loss": 4.6445,
|
|
"mean_token_accuracy": 0.22989265024662017,
|
|
"num_tokens": 40093341.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.06863579750061,
|
|
"epoch": 1.7081596188207266,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004718866826742185,
|
|
"loss": 4.7166,
|
|
"mean_token_accuracy": 0.2286927655339241,
|
|
"num_tokens": 40106867.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.0971231937408445,
|
|
"epoch": 1.7087552114353781,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000471866053390861,
|
|
"loss": 4.6997,
|
|
"mean_token_accuracy": 0.21920481324195862,
|
|
"num_tokens": 40121836.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.103053426742553,
|
|
"epoch": 1.7093508040500298,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047184541704623823,
|
|
"loss": 4.695,
|
|
"mean_token_accuracy": 0.21954238265752793,
|
|
"num_tokens": 40135562.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.100372934341431,
|
|
"epoch": 1.7099463966646815,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047182477364109045,
|
|
"loss": 4.6895,
|
|
"mean_token_accuracy": 0.22010889947414397,
|
|
"num_tokens": 40149360.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.100749969482422,
|
|
"epoch": 1.710541989279333,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000471804123176158,
|
|
"loss": 4.6836,
|
|
"mean_token_accuracy": 0.22376246750354767,
|
|
"num_tokens": 40164000.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.159665727615357,
|
|
"epoch": 1.7111375818939845,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004717834656521816,
|
|
"loss": 4.7586,
|
|
"mean_token_accuracy": 0.2187399685382843,
|
|
"num_tokens": 40179382.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.031206941604614,
|
|
"epoch": 1.7117331745086362,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047176280106990233,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.22537822723388673,
|
|
"num_tokens": 40193665.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.060428285598755,
|
|
"epoch": 1.7123287671232876,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004717421294300612,
|
|
"loss": 4.632,
|
|
"mean_token_accuracy": 0.2279609337449074,
|
|
"num_tokens": 40207139.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.102038764953614,
|
|
"epoch": 1.712924359737939,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004717214507333999,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.21854139119386673,
|
|
"num_tokens": 40220851.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.069931077957153,
|
|
"epoch": 1.7135199523525908,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047170076498066,
|
|
"loss": 4.6687,
|
|
"mean_token_accuracy": 0.21777246445417403,
|
|
"num_tokens": 40235069.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.020923519134522,
|
|
"epoch": 1.7141155449672425,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004716800721725834,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.23710816353559494,
|
|
"num_tokens": 40247066.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 4.985678243637085,
|
|
"epoch": 1.714711137581894,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004716593723099124,
|
|
"loss": 4.562,
|
|
"mean_token_accuracy": 0.23645201772451402,
|
|
"num_tokens": 40261083.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.021317386627198,
|
|
"epoch": 1.7153067301965454,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047163866539338945,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.2351250559091568,
|
|
"num_tokens": 40276961.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 4.961863708496094,
|
|
"epoch": 1.7159023228111971,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047161795142375735,
|
|
"loss": 4.5594,
|
|
"mean_token_accuracy": 0.24001653492450714,
|
|
"num_tokens": 40290024.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.025754499435425,
|
|
"epoch": 1.7164979154258488,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047159723040175896,
|
|
"loss": 4.5876,
|
|
"mean_token_accuracy": 0.23192637115716935,
|
|
"num_tokens": 40301780.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.002983093261719,
|
|
"epoch": 1.7170935080405003,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004715765023281376,
|
|
"loss": 4.5865,
|
|
"mean_token_accuracy": 0.23476606458425522,
|
|
"num_tokens": 40315956.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.081049203872681,
|
|
"epoch": 1.7176891006551518,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004715557672036367,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.21507710963487625,
|
|
"num_tokens": 40330592.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.079067325592041,
|
|
"epoch": 1.7182846932698035,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047153502502899995,
|
|
"loss": 4.6605,
|
|
"mean_token_accuracy": 0.23157989382743835,
|
|
"num_tokens": 40343142.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.096324300765991,
|
|
"epoch": 1.7188802858844552,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047151427580497155,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.21783794462680817,
|
|
"num_tokens": 40355964.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.060385847091675,
|
|
"epoch": 1.7194758784991067,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004714935195322954,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.22079361528158187,
|
|
"num_tokens": 40368981.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.0329423427581785,
|
|
"epoch": 1.7200714711137581,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004714727562117163,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.22183918952941895,
|
|
"num_tokens": 40384158.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.041756057739258,
|
|
"epoch": 1.7206670637284098,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047145198584397884,
|
|
"loss": 4.6138,
|
|
"mean_token_accuracy": 0.22888200879096984,
|
|
"num_tokens": 40398202.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.055925703048706,
|
|
"epoch": 1.7212626563430613,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004714312084298281,
|
|
"loss": 4.6508,
|
|
"mean_token_accuracy": 0.2286693975329399,
|
|
"num_tokens": 40412011.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.090322494506836,
|
|
"epoch": 1.7218582489577128,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004714104239700093,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.22548163086175918,
|
|
"num_tokens": 40424986.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.0282188892364506,
|
|
"epoch": 1.7224538415723645,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004713896324652679,
|
|
"loss": 4.6656,
|
|
"mean_token_accuracy": 0.22692769318819045,
|
|
"num_tokens": 40440862.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.063308906555176,
|
|
"epoch": 1.7230494341870162,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047136883391634966,
|
|
"loss": 4.7038,
|
|
"mean_token_accuracy": 0.22111391723155976,
|
|
"num_tokens": 40454234.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.047975397109985,
|
|
"epoch": 1.7236450268016676,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004713480283240007,
|
|
"loss": 4.6674,
|
|
"mean_token_accuracy": 0.22610756754875183,
|
|
"num_tokens": 40467996.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.1171258926391605,
|
|
"epoch": 1.7242406194163191,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004713272156889672,
|
|
"loss": 4.7194,
|
|
"mean_token_accuracy": 0.22151944637298585,
|
|
"num_tokens": 40481334.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.044357013702393,
|
|
"epoch": 1.7248362120309708,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004713063960119956,
|
|
"loss": 4.6878,
|
|
"mean_token_accuracy": 0.2312727838754654,
|
|
"num_tokens": 40493332.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.046484184265137,
|
|
"epoch": 1.7254318046456225,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047128556929383283,
|
|
"loss": 4.6257,
|
|
"mean_token_accuracy": 0.22575318217277526,
|
|
"num_tokens": 40507840.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.139941453933716,
|
|
"epoch": 1.726027397260274,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047126473553522576,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.22204423397779466,
|
|
"num_tokens": 40521061.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.15124192237854,
|
|
"epoch": 1.7266229898749255,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004712438947369218,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.20890237092971803,
|
|
"num_tokens": 40533844.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.142440414428711,
|
|
"epoch": 1.7272185824895772,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004712230468996684,
|
|
"loss": 4.7182,
|
|
"mean_token_accuracy": 0.21574075073003768,
|
|
"num_tokens": 40545889.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.003011417388916,
|
|
"epoch": 1.7278141751042289,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004712021920242133,
|
|
"loss": 4.6122,
|
|
"mean_token_accuracy": 0.23373268246650697,
|
|
"num_tokens": 40558904.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.044976043701172,
|
|
"epoch": 1.7284097677188803,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047118133011130465,
|
|
"loss": 4.6403,
|
|
"mean_token_accuracy": 0.22303735017776488,
|
|
"num_tokens": 40574045.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.073249006271363,
|
|
"epoch": 1.7290053603335318,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004711604611616905,
|
|
"loss": 4.6329,
|
|
"mean_token_accuracy": 0.22409168928861617,
|
|
"num_tokens": 40589619.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.051073837280273,
|
|
"epoch": 1.7296009529481835,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004711395851761198,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.22326647490262985,
|
|
"num_tokens": 40602954.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.092361354827881,
|
|
"epoch": 1.730196545562835,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004711187021553409,
|
|
"loss": 4.6314,
|
|
"mean_token_accuracy": 0.22492071390151977,
|
|
"num_tokens": 40617987.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.050528621673584,
|
|
"epoch": 1.7307921381774864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047109781210010306,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.22112277895212173,
|
|
"num_tokens": 40631355.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.02967472076416,
|
|
"epoch": 1.7313877307921381,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047107691501115556,
|
|
"loss": 4.6598,
|
|
"mean_token_accuracy": 0.22297672629356385,
|
|
"num_tokens": 40645196.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.013451099395752,
|
|
"epoch": 1.7319833234067898,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004710560108892479,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.23465147167444228,
|
|
"num_tokens": 40659114.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.153370094299317,
|
|
"epoch": 1.7325789160214413,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047103509973513,
|
|
"loss": 4.68,
|
|
"mean_token_accuracy": 0.22738420814275742,
|
|
"num_tokens": 40672898.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.100232553482056,
|
|
"epoch": 1.7331745086360928,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047101418154955166,
|
|
"loss": 4.6794,
|
|
"mean_token_accuracy": 0.22023957669734956,
|
|
"num_tokens": 40686582.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.004459810256958,
|
|
"epoch": 1.7337701012507445,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004709932563332633,
|
|
"loss": 4.5923,
|
|
"mean_token_accuracy": 0.22608397156000137,
|
|
"num_tokens": 40701568.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.105982255935669,
|
|
"epoch": 1.7343656938653962,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047097232408701564,
|
|
"loss": 4.7705,
|
|
"mean_token_accuracy": 0.2206727832555771,
|
|
"num_tokens": 40714642.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.182003211975098,
|
|
"epoch": 1.7349612864800477,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047095138481155924,
|
|
"loss": 4.8426,
|
|
"mean_token_accuracy": 0.20998006612062453,
|
|
"num_tokens": 40728972.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.163022089004516,
|
|
"epoch": 1.7355568790946991,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047093043850764533,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.22160883992910385,
|
|
"num_tokens": 40742332.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.103336429595947,
|
|
"epoch": 1.7361524717093508,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004709094851760251,
|
|
"loss": 4.6475,
|
|
"mean_token_accuracy": 0.22930730879306793,
|
|
"num_tokens": 40755012.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.0659952640533445,
|
|
"epoch": 1.7367480643240025,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004708885248174503,
|
|
"loss": 4.6383,
|
|
"mean_token_accuracy": 0.22568667978048323,
|
|
"num_tokens": 40768215.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.0586060047149655,
|
|
"epoch": 1.737343656938654,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004708675574326724,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.22582352608442308,
|
|
"num_tokens": 40782939.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.052806758880616,
|
|
"epoch": 1.7379392495533055,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004708465830224438,
|
|
"loss": 4.7034,
|
|
"mean_token_accuracy": 0.2305576831102371,
|
|
"num_tokens": 40797796.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.113028430938721,
|
|
"epoch": 1.7385348421679572,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047082560158751675,
|
|
"loss": 4.7334,
|
|
"mean_token_accuracy": 0.21888525187969207,
|
|
"num_tokens": 40814349.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.1238339900970455,
|
|
"epoch": 1.7391304347826086,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047080461312864363,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.22344682067632676,
|
|
"num_tokens": 40827820.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.08628659248352,
|
|
"epoch": 1.7397260273972601,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00047078361764657745,
|
|
"loss": 4.6851,
|
|
"mean_token_accuracy": 0.2205620974302292,
|
|
"num_tokens": 40841801.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.05450119972229,
|
|
"epoch": 1.7403216200119118,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004707626151420713,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.22456130385398865,
|
|
"num_tokens": 40854095.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.029754400253296,
|
|
"epoch": 1.7409172126265635,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047074160561587835,
|
|
"loss": 4.6719,
|
|
"mean_token_accuracy": 0.2245263248682022,
|
|
"num_tokens": 40868449.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.140045118331909,
|
|
"epoch": 1.741512805241215,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004707205890687523,
|
|
"loss": 4.6668,
|
|
"mean_token_accuracy": 0.22237961292266845,
|
|
"num_tokens": 40881408.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.146451234817505,
|
|
"epoch": 1.7421083978558665,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004706995655014469,
|
|
"loss": 4.8053,
|
|
"mean_token_accuracy": 0.20986029654741287,
|
|
"num_tokens": 40896474.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.0025571346282955,
|
|
"epoch": 1.7427039904705182,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004706785349147163,
|
|
"loss": 4.6174,
|
|
"mean_token_accuracy": 0.2318250685930252,
|
|
"num_tokens": 40909141.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.019595336914063,
|
|
"epoch": 1.7432995830851699,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047065749730931485,
|
|
"loss": 4.5868,
|
|
"mean_token_accuracy": 0.2319699630141258,
|
|
"num_tokens": 40921928.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.072559499740601,
|
|
"epoch": 1.7438951756998213,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004706364526859971,
|
|
"loss": 4.6905,
|
|
"mean_token_accuracy": 0.22182510644197465,
|
|
"num_tokens": 40937385.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.12588472366333,
|
|
"epoch": 1.7444907683144728,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004706154010455178,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.2243889257311821,
|
|
"num_tokens": 40948726.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.0639485836029055,
|
|
"epoch": 1.7450863609291245,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047059434238863206,
|
|
"loss": 4.6031,
|
|
"mean_token_accuracy": 0.23056722283363343,
|
|
"num_tokens": 40962200.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.083348894119263,
|
|
"epoch": 1.7456819535437762,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004705732767160954,
|
|
"loss": 4.6334,
|
|
"mean_token_accuracy": 0.23141068816184998,
|
|
"num_tokens": 40975176.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.044769716262818,
|
|
"epoch": 1.7462775461584277,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004705522040286632,
|
|
"loss": 4.6259,
|
|
"mean_token_accuracy": 0.2285451665520668,
|
|
"num_tokens": 40990193.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.136948680877685,
|
|
"epoch": 1.7468731387730791,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004705311243270915,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.21055663526058196,
|
|
"num_tokens": 41005433.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.159543228149414,
|
|
"epoch": 1.7474687313877308,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004705100376121362,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.2201264202594757,
|
|
"num_tokens": 41019122.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.09914116859436,
|
|
"epoch": 1.7480643240023823,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004704889438845537,
|
|
"loss": 4.6,
|
|
"mean_token_accuracy": 0.22748032957315445,
|
|
"num_tokens": 41032791.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.073337984085083,
|
|
"epoch": 1.7486599166170338,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047046784314510074,
|
|
"loss": 4.7135,
|
|
"mean_token_accuracy": 0.21405409127473832,
|
|
"num_tokens": 41046145.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.042388105392456,
|
|
"epoch": 1.7492555092316855,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000470446735394534,
|
|
"loss": 4.5907,
|
|
"mean_token_accuracy": 0.22661186754703522,
|
|
"num_tokens": 41059597.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.067737245559693,
|
|
"epoch": 1.7498511018463372,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004704256206336106,
|
|
"loss": 4.6468,
|
|
"mean_token_accuracy": 0.2300160348415375,
|
|
"num_tokens": 41073990.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.069447040557861,
|
|
"epoch": 1.7504466944609887,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000470404498863088,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.2175321727991104,
|
|
"num_tokens": 41088509.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 4.975930690765381,
|
|
"epoch": 1.7510422870756401,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047038337008372365,
|
|
"loss": 4.5371,
|
|
"mean_token_accuracy": 0.2289377972483635,
|
|
"num_tokens": 41102307.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.087040042877197,
|
|
"epoch": 1.7516378796902918,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047036223429627557,
|
|
"loss": 4.664,
|
|
"mean_token_accuracy": 0.2273676574230194,
|
|
"num_tokens": 41115540.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.037485885620117,
|
|
"epoch": 1.7522334723049435,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047034109150150184,
|
|
"loss": 4.6189,
|
|
"mean_token_accuracy": 0.2306220844388008,
|
|
"num_tokens": 41129271.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.015266227722168,
|
|
"epoch": 1.752829064919595,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004703199417001607,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.223115998506546,
|
|
"num_tokens": 41144671.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.07888708114624,
|
|
"epoch": 1.7534246575342465,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047029878489301074,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.21642810702323914,
|
|
"num_tokens": 41157825.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.096775674819947,
|
|
"epoch": 1.7540202501488982,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004702776210808109,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.22391218692064285,
|
|
"num_tokens": 41171645.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.134004783630371,
|
|
"epoch": 1.7546158427635499,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004702564502643204,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.22375900745391847,
|
|
"num_tokens": 41185996.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.094346570968628,
|
|
"epoch": 1.7552114353782013,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047023527244429846,
|
|
"loss": 4.6298,
|
|
"mean_token_accuracy": 0.2179126635193825,
|
|
"num_tokens": 41199044.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.084762287139893,
|
|
"epoch": 1.7558070279928528,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004702140876215047,
|
|
"loss": 4.6872,
|
|
"mean_token_accuracy": 0.22312499284744264,
|
|
"num_tokens": 41213215.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.03463454246521,
|
|
"epoch": 1.7564026206075045,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004701928957966991,
|
|
"loss": 4.6963,
|
|
"mean_token_accuracy": 0.21971324682235718,
|
|
"num_tokens": 41227067.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.05840573310852,
|
|
"epoch": 1.756998213222156,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004701716969706416,
|
|
"loss": 4.5965,
|
|
"mean_token_accuracy": 0.23525390774011612,
|
|
"num_tokens": 41239272.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.07150821685791,
|
|
"epoch": 1.7575938058368075,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004701504911440927,
|
|
"loss": 4.6241,
|
|
"mean_token_accuracy": 0.22639221847057342,
|
|
"num_tokens": 41253230.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.102907514572143,
|
|
"epoch": 1.7581893984514592,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004701292783178129,
|
|
"loss": 4.7628,
|
|
"mean_token_accuracy": 0.21247691959142684,
|
|
"num_tokens": 41266349.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.123917484283448,
|
|
"epoch": 1.7587849910661109,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004701080584925633,
|
|
"loss": 4.662,
|
|
"mean_token_accuracy": 0.23133161962032317,
|
|
"num_tokens": 41280301.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.0178450584411625,
|
|
"epoch": 1.7593805836807623,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047008683166910477,
|
|
"loss": 4.6165,
|
|
"mean_token_accuracy": 0.2249760627746582,
|
|
"num_tokens": 41294813.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 4.963408803939819,
|
|
"epoch": 1.7599761762954138,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004700655978481988,
|
|
"loss": 4.5834,
|
|
"mean_token_accuracy": 0.23148883134126663,
|
|
"num_tokens": 41310493.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.0186309814453125,
|
|
"epoch": 1.7605717689100655,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000470044357030607,
|
|
"loss": 4.5602,
|
|
"mean_token_accuracy": 0.2320232793688774,
|
|
"num_tokens": 41324597.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.022298002243042,
|
|
"epoch": 1.7611673615247172,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047002310921709123,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.22823326587677,
|
|
"num_tokens": 41338019.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.044653224945068,
|
|
"epoch": 1.7617629541393687,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004700018544084136,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.22322936803102494,
|
|
"num_tokens": 41353199.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.10491623878479,
|
|
"epoch": 1.7623585467540201,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004699805926053365,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.22429988980293275,
|
|
"num_tokens": 41367783.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.08117036819458,
|
|
"epoch": 1.7629541393686718,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046995932380862254,
|
|
"loss": 4.6348,
|
|
"mean_token_accuracy": 0.2254233568906784,
|
|
"num_tokens": 41382371.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.036650228500366,
|
|
"epoch": 1.7635497319833235,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046993804801903475,
|
|
"loss": 4.6738,
|
|
"mean_token_accuracy": 0.2241274505853653,
|
|
"num_tokens": 41394965.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.081048250198364,
|
|
"epoch": 1.764145324597975,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046991676523733603,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.22080113291740416,
|
|
"num_tokens": 41408158.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.108467769622803,
|
|
"epoch": 1.7647409172126265,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046989547546428986,
|
|
"loss": 4.6913,
|
|
"mean_token_accuracy": 0.22006307244300843,
|
|
"num_tokens": 41421672.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.01907868385315,
|
|
"epoch": 1.7653365098272782,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046987417870065985,
|
|
"loss": 4.6386,
|
|
"mean_token_accuracy": 0.22353367805480956,
|
|
"num_tokens": 41435225.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.089569091796875,
|
|
"epoch": 1.7659321024419299,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004698528749472099,
|
|
"loss": 4.7073,
|
|
"mean_token_accuracy": 0.21686276644468308,
|
|
"num_tokens": 41449360.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.16480450630188,
|
|
"epoch": 1.7665276950565811,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004698315642047042,
|
|
"loss": 4.7336,
|
|
"mean_token_accuracy": 0.22119349986314774,
|
|
"num_tokens": 41462895.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 4.980090808868408,
|
|
"epoch": 1.7671232876712328,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000469810246473907,
|
|
"loss": 4.5845,
|
|
"mean_token_accuracy": 0.22948672771453857,
|
|
"num_tokens": 41477069.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.037868547439575,
|
|
"epoch": 1.7677188802858845,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046978892175558295,
|
|
"loss": 4.674,
|
|
"mean_token_accuracy": 0.22675431221723558,
|
|
"num_tokens": 41491097.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.145569229125977,
|
|
"epoch": 1.768314472900536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004697675900504971,
|
|
"loss": 4.7446,
|
|
"mean_token_accuracy": 0.21723510026931764,
|
|
"num_tokens": 41504570.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.093897962570191,
|
|
"epoch": 1.7689100655151875,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046974625135941445,
|
|
"loss": 4.7391,
|
|
"mean_token_accuracy": 0.22085356563329697,
|
|
"num_tokens": 41518618.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.087789392471313,
|
|
"epoch": 1.7695056581298392,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046972490568310043,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.22349512130022048,
|
|
"num_tokens": 41535802.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.095858764648438,
|
|
"epoch": 1.7701012507444909,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046970355302232056,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.2260465368628502,
|
|
"num_tokens": 41548588.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.0588274002075195,
|
|
"epoch": 1.7706968433591423,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00046968219337784083,
|
|
"loss": 4.6566,
|
|
"mean_token_accuracy": 0.2279609650373459,
|
|
"num_tokens": 41560934.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.004275894165039,
|
|
"epoch": 1.7712924359737938,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046966082675042745,
|
|
"loss": 4.5713,
|
|
"mean_token_accuracy": 0.23342489451169968,
|
|
"num_tokens": 41574066.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.09547119140625,
|
|
"epoch": 1.7718880285884455,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004696394531408466,
|
|
"loss": 4.6245,
|
|
"mean_token_accuracy": 0.2278762936592102,
|
|
"num_tokens": 41586586.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.049331712722778,
|
|
"epoch": 1.7724836212030972,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046961807254986503,
|
|
"loss": 4.597,
|
|
"mean_token_accuracy": 0.2272797167301178,
|
|
"num_tokens": 41598945.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.079680109024048,
|
|
"epoch": 1.7730792138177487,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004695966849782497,
|
|
"loss": 4.7064,
|
|
"mean_token_accuracy": 0.22284616976976396,
|
|
"num_tokens": 41614034.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.004239892959594,
|
|
"epoch": 1.7736748064324002,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004695752904267676,
|
|
"loss": 4.582,
|
|
"mean_token_accuracy": 0.22997456938028335,
|
|
"num_tokens": 41627626.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.064130449295044,
|
|
"epoch": 1.7742703990470519,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004695538888961862,
|
|
"loss": 4.6876,
|
|
"mean_token_accuracy": 0.21884192228317262,
|
|
"num_tokens": 41640060.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.055075311660767,
|
|
"epoch": 1.7748659916617036,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004695324803872732,
|
|
"loss": 4.662,
|
|
"mean_token_accuracy": 0.22727597802877425,
|
|
"num_tokens": 41653689.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.128499269485474,
|
|
"epoch": 1.7754615842763548,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046951106490079636,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.2124644085764885,
|
|
"num_tokens": 41666873.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 4.990399980545044,
|
|
"epoch": 1.7760571768910065,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00046948964243752393,
|
|
"loss": 4.5349,
|
|
"mean_token_accuracy": 0.23677636682987213,
|
|
"num_tokens": 41681418.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.017885732650757,
|
|
"epoch": 1.7766527695056582,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046946821299822416,
|
|
"loss": 4.6983,
|
|
"mean_token_accuracy": 0.2236136391758919,
|
|
"num_tokens": 41694728.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.1165846824646,
|
|
"epoch": 1.7772483621203097,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004694467765836659,
|
|
"loss": 4.65,
|
|
"mean_token_accuracy": 0.22238975018262863,
|
|
"num_tokens": 41707361.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.1015886783599855,
|
|
"epoch": 1.7778439547349612,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004694253331946178,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.22380791753530502,
|
|
"num_tokens": 41721746.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.108745288848877,
|
|
"epoch": 1.7784395473496128,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004694038828318492,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.21503503173589705,
|
|
"num_tokens": 41739296.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.117613029479981,
|
|
"epoch": 1.7790351399642645,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004693824254961294,
|
|
"loss": 4.7051,
|
|
"mean_token_accuracy": 0.21574125587940216,
|
|
"num_tokens": 41753416.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 4.994804382324219,
|
|
"epoch": 1.779630732578916,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046936096118822796,
|
|
"loss": 4.6022,
|
|
"mean_token_accuracy": 0.2347736954689026,
|
|
"num_tokens": 41764978.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 4.9685468673706055,
|
|
"epoch": 1.7802263251935675,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004693394899089149,
|
|
"loss": 4.6198,
|
|
"mean_token_accuracy": 0.22739493995904922,
|
|
"num_tokens": 41779467.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.1022899627685545,
|
|
"epoch": 1.7808219178082192,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046931801165896035,
|
|
"loss": 4.653,
|
|
"mean_token_accuracy": 0.22841126769781112,
|
|
"num_tokens": 41792541.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.132740449905396,
|
|
"epoch": 1.7814175104228709,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004692965264391346,
|
|
"loss": 4.7917,
|
|
"mean_token_accuracy": 0.2134143367409706,
|
|
"num_tokens": 41806127.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.036231613159179,
|
|
"epoch": 1.7820131030375224,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046927503425020847,
|
|
"loss": 4.6388,
|
|
"mean_token_accuracy": 0.23389394581317902,
|
|
"num_tokens": 41819632.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.056224536895752,
|
|
"epoch": 1.7826086956521738,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004692535350929525,
|
|
"loss": 4.6244,
|
|
"mean_token_accuracy": 0.23177485913038254,
|
|
"num_tokens": 41833144.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.126913213729859,
|
|
"epoch": 1.7832042882668255,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046923202896813825,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.22235630452632904,
|
|
"num_tokens": 41847994.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.156729745864868,
|
|
"epoch": 1.7837998808814772,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004692105158765369,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.21762816607952118,
|
|
"num_tokens": 41861708.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.003464031219482,
|
|
"epoch": 1.7843954734961287,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004691889958189201,
|
|
"loss": 4.5686,
|
|
"mean_token_accuracy": 0.23343702852725984,
|
|
"num_tokens": 41874609.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.065898132324219,
|
|
"epoch": 1.7849910661107802,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046916746879605974,
|
|
"loss": 4.7044,
|
|
"mean_token_accuracy": 0.22036000937223435,
|
|
"num_tokens": 41887105.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.053389072418213,
|
|
"epoch": 1.7855866587254319,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000469145934808728,
|
|
"loss": 4.6688,
|
|
"mean_token_accuracy": 0.22471954375505448,
|
|
"num_tokens": 41903298.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.098879957199097,
|
|
"epoch": 1.7861822513400833,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046912439385769723,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.22098224461078644,
|
|
"num_tokens": 41918173.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.050883102416992,
|
|
"epoch": 1.7867778439547348,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004691028459437401,
|
|
"loss": 4.6281,
|
|
"mean_token_accuracy": 0.228020578622818,
|
|
"num_tokens": 41932050.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.7867778439547348,
|
|
"eval_entropy": 4.824815840407225,
|
|
"eval_loss": 4.663299083709717,
|
|
"eval_mean_token_accuracy": 0.23540676822272774,
|
|
"eval_num_tokens": 41932050.0,
|
|
"eval_runtime": 18.6989,
|
|
"eval_samples_per_second": 1364.415,
|
|
"eval_steps_per_second": 170.599,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.059493112564087,
|
|
"epoch": 1.7873734365693865,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004690812910676294,
|
|
"loss": 4.6436,
|
|
"mean_token_accuracy": 0.23262622207403183,
|
|
"num_tokens": 41945874.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.062381172180176,
|
|
"epoch": 1.7879690291840382,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004690597292301384,
|
|
"loss": 4.6256,
|
|
"mean_token_accuracy": 0.2357962980866432,
|
|
"num_tokens": 41959084.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.039206171035767,
|
|
"epoch": 1.7885646217986897,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046903816043204045,
|
|
"loss": 4.6517,
|
|
"mean_token_accuracy": 0.2239149585366249,
|
|
"num_tokens": 41972872.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.008111906051636,
|
|
"epoch": 1.7891602144133412,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004690165846741092,
|
|
"loss": 4.6198,
|
|
"mean_token_accuracy": 0.23352219611406327,
|
|
"num_tokens": 41985045.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.112036657333374,
|
|
"epoch": 1.7897558070279929,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046899500195711843,
|
|
"loss": 4.6704,
|
|
"mean_token_accuracy": 0.2242175057530403,
|
|
"num_tokens": 41999760.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.036551570892334,
|
|
"epoch": 1.7903513996426446,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046897341228184237,
|
|
"loss": 4.5945,
|
|
"mean_token_accuracy": 0.22358949482440948,
|
|
"num_tokens": 42013871.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.046212434768677,
|
|
"epoch": 1.790946992257296,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004689518156490554,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.22377060502767562,
|
|
"num_tokens": 42028701.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.112361478805542,
|
|
"epoch": 1.7915425848719475,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004689302120595322,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.22205906510353088,
|
|
"num_tokens": 42042455.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.044269561767578,
|
|
"epoch": 1.7921381774865992,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046890860151404753,
|
|
"loss": 4.7086,
|
|
"mean_token_accuracy": 0.21942974925041198,
|
|
"num_tokens": 42055813.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.064653158187866,
|
|
"epoch": 1.792733770101251,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046888698401337665,
|
|
"loss": 4.6682,
|
|
"mean_token_accuracy": 0.21927086710929872,
|
|
"num_tokens": 42070545.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.100590181350708,
|
|
"epoch": 1.7933293627159024,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046886535955829487,
|
|
"loss": 4.6471,
|
|
"mean_token_accuracy": 0.2290172293782234,
|
|
"num_tokens": 42086021.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.097288942337036,
|
|
"epoch": 1.7939249553305538,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004688437281495779,
|
|
"loss": 4.6386,
|
|
"mean_token_accuracy": 0.2261241376399994,
|
|
"num_tokens": 42097775.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.005266904830933,
|
|
"epoch": 1.7945205479452055,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004688220897880015,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.22189023047685624,
|
|
"num_tokens": 42112126.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.117222499847412,
|
|
"epoch": 1.795116140559857,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004688004444743419,
|
|
"loss": 4.7009,
|
|
"mean_token_accuracy": 0.22469664365053177,
|
|
"num_tokens": 42125694.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.081678676605224,
|
|
"epoch": 1.7957117331745085,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00046877879220937546,
|
|
"loss": 4.6223,
|
|
"mean_token_accuracy": 0.2297704428434372,
|
|
"num_tokens": 42138996.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.002079868316651,
|
|
"epoch": 1.7963073257891602,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004687571329938788,
|
|
"loss": 4.579,
|
|
"mean_token_accuracy": 0.23116938918828964,
|
|
"num_tokens": 42150896.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.054537725448609,
|
|
"epoch": 1.7969029184038119,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046873546682862883,
|
|
"loss": 4.6286,
|
|
"mean_token_accuracy": 0.22843344360589982,
|
|
"num_tokens": 42163529.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.08344259262085,
|
|
"epoch": 1.7974985110184634,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046871379371440263,
|
|
"loss": 4.6139,
|
|
"mean_token_accuracy": 0.22835867404937743,
|
|
"num_tokens": 42177221.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.043451547622681,
|
|
"epoch": 1.7980941036331148,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004686921136519777,
|
|
"loss": 4.6043,
|
|
"mean_token_accuracy": 0.23156589716672898,
|
|
"num_tokens": 42190632.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.084614944458008,
|
|
"epoch": 1.7986896962477665,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004686704266421314,
|
|
"loss": 4.6623,
|
|
"mean_token_accuracy": 0.22352458238601686,
|
|
"num_tokens": 42204466.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.089415788650513,
|
|
"epoch": 1.7992852888624182,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004686487326856419,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.21262939274311066,
|
|
"num_tokens": 42219992.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.046115446090698,
|
|
"epoch": 1.7998808814770697,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004686270317832872,
|
|
"loss": 4.6194,
|
|
"mean_token_accuracy": 0.22587827742099761,
|
|
"num_tokens": 42233966.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.075564575195313,
|
|
"epoch": 1.8004764740917212,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004686053239358457,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.2213689863681793,
|
|
"num_tokens": 42246689.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.097459316253662,
|
|
"epoch": 1.8010720667063729,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00046858360914409596,
|
|
"loss": 4.7082,
|
|
"mean_token_accuracy": 0.21637485921382904,
|
|
"num_tokens": 42260145.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.140963459014893,
|
|
"epoch": 1.8016676593210246,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000468561887408817,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.2157963201403618,
|
|
"num_tokens": 42272851.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.081530380249023,
|
|
"epoch": 1.802263251935676,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004685401587307879,
|
|
"loss": 4.6372,
|
|
"mean_token_accuracy": 0.22513542026281358,
|
|
"num_tokens": 42286233.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.081133317947388,
|
|
"epoch": 1.8028588445503275,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004685184231107878,
|
|
"loss": 4.6211,
|
|
"mean_token_accuracy": 0.22891304194927214,
|
|
"num_tokens": 42301649.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.070801687240601,
|
|
"epoch": 1.8034544371649792,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004684966805495966,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.23003974109888076,
|
|
"num_tokens": 42315115.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 4.992529678344726,
|
|
"epoch": 1.8040500297796307,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000468474931047994,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.22978030145168304,
|
|
"num_tokens": 42328838.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.120778512954712,
|
|
"epoch": 1.8046456223942822,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046845317460676033,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.2236897438764572,
|
|
"num_tokens": 42343918.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 4.994722175598144,
|
|
"epoch": 1.8052412150089339,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046843141122667576,
|
|
"loss": 4.569,
|
|
"mean_token_accuracy": 0.238190458714962,
|
|
"num_tokens": 42356979.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 4.983795976638794,
|
|
"epoch": 1.8058368076235856,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046840964090852095,
|
|
"loss": 4.5777,
|
|
"mean_token_accuracy": 0.2257021814584732,
|
|
"num_tokens": 42370740.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.034759998321533,
|
|
"epoch": 1.806432400238237,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004683878636530768,
|
|
"loss": 4.6258,
|
|
"mean_token_accuracy": 0.22911524921655654,
|
|
"num_tokens": 42386232.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.093884992599487,
|
|
"epoch": 1.8070279928528885,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004683660794611244,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.22926073372364045,
|
|
"num_tokens": 42399234.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.033417510986328,
|
|
"epoch": 1.8076235854675402,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004683442883334451,
|
|
"loss": 4.6693,
|
|
"mean_token_accuracy": 0.223210933804512,
|
|
"num_tokens": 42412753.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.108496522903442,
|
|
"epoch": 1.808219178082192,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004683224902708206,
|
|
"loss": 4.6706,
|
|
"mean_token_accuracy": 0.2209859609603882,
|
|
"num_tokens": 42427150.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.111315727233887,
|
|
"epoch": 1.8088147706968434,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004683006852740326,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.2264738842844963,
|
|
"num_tokens": 42442245.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.1163383483886715,
|
|
"epoch": 1.8094103633114949,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004682788733438634,
|
|
"loss": 4.6916,
|
|
"mean_token_accuracy": 0.2278812512755394,
|
|
"num_tokens": 42456031.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.128440284729004,
|
|
"epoch": 1.8100059559261465,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004682570544810952,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.22435101568698884,
|
|
"num_tokens": 42470015.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.081506443023682,
|
|
"epoch": 1.8106015485407982,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046823522868651076,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.22120157778263091,
|
|
"num_tokens": 42482956.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.053608846664429,
|
|
"epoch": 1.8111971411554497,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004682133959608928,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.22115203589200974,
|
|
"num_tokens": 42495226.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.096707344055176,
|
|
"epoch": 1.8117927337701012,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004681915563050245,
|
|
"loss": 4.7479,
|
|
"mean_token_accuracy": 0.22086199820041658,
|
|
"num_tokens": 42509371.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.113627147674561,
|
|
"epoch": 1.812388326384753,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046816970971968916,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.2256641760468483,
|
|
"num_tokens": 42523360.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.185276794433594,
|
|
"epoch": 1.8129839189994044,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046814785620567036,
|
|
"loss": 4.7341,
|
|
"mean_token_accuracy": 0.2150643140077591,
|
|
"num_tokens": 42535661.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.087684392929077,
|
|
"epoch": 1.8135795116140558,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046812599576375206,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.21906427592039107,
|
|
"num_tokens": 42549342.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.083594465255738,
|
|
"epoch": 1.8141751042287075,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004681041283947182,
|
|
"loss": 4.6393,
|
|
"mean_token_accuracy": 0.2306084543466568,
|
|
"num_tokens": 42564904.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.068659162521362,
|
|
"epoch": 1.8147706968433592,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004680822540993534,
|
|
"loss": 4.6182,
|
|
"mean_token_accuracy": 0.2299012005329132,
|
|
"num_tokens": 42578877.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.045758247375488,
|
|
"epoch": 1.8153662894580107,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046806037287844195,
|
|
"loss": 4.6134,
|
|
"mean_token_accuracy": 0.23020339012145996,
|
|
"num_tokens": 42592704.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.115412616729737,
|
|
"epoch": 1.8159618820726622,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004680384847327689,
|
|
"loss": 4.7228,
|
|
"mean_token_accuracy": 0.22059611231088638,
|
|
"num_tokens": 42606414.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.106284046173096,
|
|
"epoch": 1.8165574746873139,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046801658966311914,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.22544486373662947,
|
|
"num_tokens": 42620047.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.143362617492675,
|
|
"epoch": 1.8171530673019656,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046799468767027826,
|
|
"loss": 4.728,
|
|
"mean_token_accuracy": 0.2241227939724922,
|
|
"num_tokens": 42634701.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.07300181388855,
|
|
"epoch": 1.817748659916617,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046797277875503164,
|
|
"loss": 4.6722,
|
|
"mean_token_accuracy": 0.2247755840420723,
|
|
"num_tokens": 42649619.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.0526731491088865,
|
|
"epoch": 1.8183442525312685,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046795086291816516,
|
|
"loss": 4.6145,
|
|
"mean_token_accuracy": 0.22372393012046815,
|
|
"num_tokens": 42663753.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.081807279586792,
|
|
"epoch": 1.8189398451459202,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004679289401604651,
|
|
"loss": 4.6482,
|
|
"mean_token_accuracy": 0.23128108382225038,
|
|
"num_tokens": 42678584.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.092727613449097,
|
|
"epoch": 1.819535437760572,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004679070104827176,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.22645066380500795,
|
|
"num_tokens": 42693125.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.03042950630188,
|
|
"epoch": 1.8201310303752234,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004678850738857092,
|
|
"loss": 4.6072,
|
|
"mean_token_accuracy": 0.23207499086856842,
|
|
"num_tokens": 42708218.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.064350748062134,
|
|
"epoch": 1.8207266229898749,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004678631303702268,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.21997583359479905,
|
|
"num_tokens": 42722137.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.19666428565979,
|
|
"epoch": 1.8213222156045266,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046784117993705753,
|
|
"loss": 4.75,
|
|
"mean_token_accuracy": 0.2182463601231575,
|
|
"num_tokens": 42737105.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.070397996902466,
|
|
"epoch": 1.821917808219178,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004678192225869888,
|
|
"loss": 4.566,
|
|
"mean_token_accuracy": 0.2347560003399849,
|
|
"num_tokens": 42750912.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.067264747619629,
|
|
"epoch": 1.8225134008338295,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046779725832080793,
|
|
"loss": 4.6857,
|
|
"mean_token_accuracy": 0.22735829651355743,
|
|
"num_tokens": 42762022.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.0448445796966555,
|
|
"epoch": 1.8231089934484812,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046777528713930287,
|
|
"loss": 4.6584,
|
|
"mean_token_accuracy": 0.2277050420641899,
|
|
"num_tokens": 42776195.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.101309156417846,
|
|
"epoch": 1.823704586063133,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004677533090432617,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.219817116856575,
|
|
"num_tokens": 42792938.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.106666183471679,
|
|
"epoch": 1.8243001786777844,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004677313240334727,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.2233342319726944,
|
|
"num_tokens": 42806088.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.122456121444702,
|
|
"epoch": 1.8248957712924359,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004677093321107245,
|
|
"loss": 4.6696,
|
|
"mean_token_accuracy": 0.2272876098752022,
|
|
"num_tokens": 42818870.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.185211277008056,
|
|
"epoch": 1.8254913639070875,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046768733327580593,
|
|
"loss": 4.7263,
|
|
"mean_token_accuracy": 0.21961636543273927,
|
|
"num_tokens": 42833144.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.043750762939453,
|
|
"epoch": 1.8260869565217392,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00046766532752950604,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.2317678898572922,
|
|
"num_tokens": 42847318.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 4.999736356735229,
|
|
"epoch": 1.8266825491363907,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000467643314872614,
|
|
"loss": 4.6273,
|
|
"mean_token_accuracy": 0.2252369523048401,
|
|
"num_tokens": 42862312.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.112482738494873,
|
|
"epoch": 1.8272781417510422,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004676212953059195,
|
|
"loss": 4.6324,
|
|
"mean_token_accuracy": 0.22747949957847596,
|
|
"num_tokens": 42876775.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.0445739269256595,
|
|
"epoch": 1.827873734365694,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046759926883021234,
|
|
"loss": 4.6233,
|
|
"mean_token_accuracy": 0.22872160822153093,
|
|
"num_tokens": 42889864.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.04236421585083,
|
|
"epoch": 1.8284693269803456,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046757723544628253,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.2321950152516365,
|
|
"num_tokens": 42902319.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.0443212509155275,
|
|
"epoch": 1.829064919594997,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004675551951549204,
|
|
"loss": 4.6476,
|
|
"mean_token_accuracy": 0.22674542665481567,
|
|
"num_tokens": 42915864.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.104865694046021,
|
|
"epoch": 1.8296605122096485,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046753314795691653,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.22374362498521805,
|
|
"num_tokens": 42931724.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.075432920455933,
|
|
"epoch": 1.8302561048243002,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004675110938530617,
|
|
"loss": 4.6735,
|
|
"mean_token_accuracy": 0.225162473320961,
|
|
"num_tokens": 42945848.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.110323810577393,
|
|
"epoch": 1.8308516974389517,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004674890328441469,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.2204821676015854,
|
|
"num_tokens": 42958443.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.061307096481324,
|
|
"epoch": 1.8314472900536032,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004674669649309634,
|
|
"loss": 4.638,
|
|
"mean_token_accuracy": 0.2261663094162941,
|
|
"num_tokens": 42972286.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.152126598358154,
|
|
"epoch": 1.8320428826682549,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004674448901143029,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.2126663252711296,
|
|
"num_tokens": 42987029.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.086118412017822,
|
|
"epoch": 1.8326384752829066,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004674228083949571,
|
|
"loss": 4.6377,
|
|
"mean_token_accuracy": 0.22773009091615676,
|
|
"num_tokens": 43000039.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.107501220703125,
|
|
"epoch": 1.833234067897558,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004674007197737179,
|
|
"loss": 4.6827,
|
|
"mean_token_accuracy": 0.21849780827760695,
|
|
"num_tokens": 43012942.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.030782079696655,
|
|
"epoch": 1.8338296605122095,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004673786242513778,
|
|
"loss": 4.6315,
|
|
"mean_token_accuracy": 0.2303841531276703,
|
|
"num_tokens": 43027523.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.093341827392578,
|
|
"epoch": 1.8344252531268612,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046735652182872925,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.21985693871974946,
|
|
"num_tokens": 43044438.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.088851833343506,
|
|
"epoch": 1.835020845741513,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046733441250656495,
|
|
"loss": 4.6579,
|
|
"mean_token_accuracy": 0.22261038571596145,
|
|
"num_tokens": 43058458.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.095347499847412,
|
|
"epoch": 1.8356164383561644,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000467312296285678,
|
|
"loss": 4.6841,
|
|
"mean_token_accuracy": 0.22321973443031312,
|
|
"num_tokens": 43071269.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.088699674606323,
|
|
"epoch": 1.8362120309708159,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004672901731668617,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.22641900032758713,
|
|
"num_tokens": 43084024.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.150217151641845,
|
|
"epoch": 1.8368076235854676,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046726804315090956,
|
|
"loss": 4.7169,
|
|
"mean_token_accuracy": 0.21641722619533538,
|
|
"num_tokens": 43097857.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.088169288635254,
|
|
"epoch": 1.8374032162001193,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004672459062386152,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.22775492668151856,
|
|
"num_tokens": 43111481.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.028949928283692,
|
|
"epoch": 1.8379988088147707,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004672237624307729,
|
|
"loss": 4.6137,
|
|
"mean_token_accuracy": 0.22984064370393753,
|
|
"num_tokens": 43123926.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.163101863861084,
|
|
"epoch": 1.8385944014294222,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004672016117281767,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.20984682589769363,
|
|
"num_tokens": 43136005.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.01514458656311,
|
|
"epoch": 1.839189994044074,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004671794541316212,
|
|
"loss": 4.5519,
|
|
"mean_token_accuracy": 0.23895952552556993,
|
|
"num_tokens": 43150641.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.029019689559936,
|
|
"epoch": 1.8397855866587254,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004671572896419011,
|
|
"loss": 4.63,
|
|
"mean_token_accuracy": 0.22712946236133574,
|
|
"num_tokens": 43164077.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.052417516708374,
|
|
"epoch": 1.8403811792733769,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004671351182598116,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.22637985944747924,
|
|
"num_tokens": 43176694.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.100107336044312,
|
|
"epoch": 1.8409767718880286,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004671129399861476,
|
|
"loss": 4.6304,
|
|
"mean_token_accuracy": 0.22312818169593812,
|
|
"num_tokens": 43190310.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.097910451889038,
|
|
"epoch": 1.8415723645026802,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046709075482170495,
|
|
"loss": 4.681,
|
|
"mean_token_accuracy": 0.22954761385917663,
|
|
"num_tokens": 43203642.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.150657892227173,
|
|
"epoch": 1.8421679571173317,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004670685627672792,
|
|
"loss": 4.755,
|
|
"mean_token_accuracy": 0.2209087774157524,
|
|
"num_tokens": 43216512.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.0255636215209964,
|
|
"epoch": 1.8427635497319832,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046704636382366633,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.22499692142009736,
|
|
"num_tokens": 43229713.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.050614356994629,
|
|
"epoch": 1.843359142346635,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004670241579916627,
|
|
"loss": 4.6216,
|
|
"mean_token_accuracy": 0.2285577356815338,
|
|
"num_tokens": 43242968.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.063863754272461,
|
|
"epoch": 1.8439547349612866,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00046700194527206476,
|
|
"loss": 4.669,
|
|
"mean_token_accuracy": 0.2278424471616745,
|
|
"num_tokens": 43256403.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.09156813621521,
|
|
"epoch": 1.844550327575938,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046697972566566917,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.22393908649682998,
|
|
"num_tokens": 43270004.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.187011957168579,
|
|
"epoch": 1.8451459201905895,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046695749917327297,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.21159969568252562,
|
|
"num_tokens": 43282934.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.080046844482422,
|
|
"epoch": 1.8457415128052412,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046693526579567337,
|
|
"loss": 4.7105,
|
|
"mean_token_accuracy": 0.22005880028009414,
|
|
"num_tokens": 43296378.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.080129623413086,
|
|
"epoch": 1.846337105419893,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046691302553366785,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.22748095393180848,
|
|
"num_tokens": 43309832.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.099719762802124,
|
|
"epoch": 1.8469326980345444,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004668907783880542,
|
|
"loss": 4.6669,
|
|
"mean_token_accuracy": 0.22759686410427094,
|
|
"num_tokens": 43324222.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.084100341796875,
|
|
"epoch": 1.8475282906491959,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046686852435963016,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.22191411703824998,
|
|
"num_tokens": 43339674.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.0663810729980465,
|
|
"epoch": 1.8481238832638476,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004668462634491943,
|
|
"loss": 4.6495,
|
|
"mean_token_accuracy": 0.22713978141546248,
|
|
"num_tokens": 43352265.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.1164881706237795,
|
|
"epoch": 1.848719475878499,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004668239956575448,
|
|
"loss": 4.6336,
|
|
"mean_token_accuracy": 0.23216167688369752,
|
|
"num_tokens": 43365428.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.017405271530151,
|
|
"epoch": 1.8493150684931505,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046680172098548044,
|
|
"loss": 4.6431,
|
|
"mean_token_accuracy": 0.2194194182753563,
|
|
"num_tokens": 43379099.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 4.996832227706909,
|
|
"epoch": 1.8499106611078022,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00046677943943380023,
|
|
"loss": 4.577,
|
|
"mean_token_accuracy": 0.22724697440862657,
|
|
"num_tokens": 43393127.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.070531034469605,
|
|
"epoch": 1.850506253722454,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004667571510033034,
|
|
"loss": 4.7184,
|
|
"mean_token_accuracy": 0.22568294852972032,
|
|
"num_tokens": 43409560.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.129261827468872,
|
|
"epoch": 1.8511018463371054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004667348556947893,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.22441977113485337,
|
|
"num_tokens": 43422986.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.107598924636841,
|
|
"epoch": 1.8516974389517569,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004667125535090577,
|
|
"loss": 4.6983,
|
|
"mean_token_accuracy": 0.2299719050526619,
|
|
"num_tokens": 43437176.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.175100183486938,
|
|
"epoch": 1.8522930315664086,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004666902444469084,
|
|
"loss": 4.7414,
|
|
"mean_token_accuracy": 0.21930938065052033,
|
|
"num_tokens": 43449917.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.0452367782592775,
|
|
"epoch": 1.8528886241810603,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004666679285091418,
|
|
"loss": 4.5992,
|
|
"mean_token_accuracy": 0.2289091095328331,
|
|
"num_tokens": 43462940.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.119784545898438,
|
|
"epoch": 1.8534842167957117,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046664560569655825,
|
|
"loss": 4.7581,
|
|
"mean_token_accuracy": 0.21792194247245789,
|
|
"num_tokens": 43477008.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.051094579696655,
|
|
"epoch": 1.8540798094103632,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004666232760099583,
|
|
"loss": 4.6729,
|
|
"mean_token_accuracy": 0.22912799268960954,
|
|
"num_tokens": 43492094.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.053370952606201,
|
|
"epoch": 1.854675402025015,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046660093945014307,
|
|
"loss": 4.6541,
|
|
"mean_token_accuracy": 0.23106335401535033,
|
|
"num_tokens": 43505256.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.003002548217774,
|
|
"epoch": 1.8552709946396666,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046657859601791367,
|
|
"loss": 4.6232,
|
|
"mean_token_accuracy": 0.22767620235681535,
|
|
"num_tokens": 43518056.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.075421619415283,
|
|
"epoch": 1.855866587254318,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004665562457140715,
|
|
"loss": 4.6173,
|
|
"mean_token_accuracy": 0.2247354969382286,
|
|
"num_tokens": 43531809.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.0378562927246096,
|
|
"epoch": 1.8564621798689696,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004665338885394183,
|
|
"loss": 4.6158,
|
|
"mean_token_accuracy": 0.22485689222812652,
|
|
"num_tokens": 43545272.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.044142150878907,
|
|
"epoch": 1.8570577724836212,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004665115244947559,
|
|
"loss": 4.6274,
|
|
"mean_token_accuracy": 0.2233537420630455,
|
|
"num_tokens": 43559981.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.089047813415528,
|
|
"epoch": 1.857653365098273,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004664891535808865,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.2259731709957123,
|
|
"num_tokens": 43574025.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.021483659744263,
|
|
"epoch": 1.8582489577129242,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046646677579861254,
|
|
"loss": 4.6204,
|
|
"mean_token_accuracy": 0.2221604511141777,
|
|
"num_tokens": 43586896.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.046879148483276,
|
|
"epoch": 1.858844550327576,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004664443911487366,
|
|
"loss": 4.6023,
|
|
"mean_token_accuracy": 0.22673239856958388,
|
|
"num_tokens": 43599289.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.067368602752685,
|
|
"epoch": 1.8594401429422276,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046642199963206155,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.22170559465885162,
|
|
"num_tokens": 43614172.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.0603835105896,
|
|
"epoch": 1.860035735556879,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046639960124939076,
|
|
"loss": 4.6147,
|
|
"mean_token_accuracy": 0.22424013912677765,
|
|
"num_tokens": 43626653.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.047134590148926,
|
|
"epoch": 1.8606313281715305,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00046637719600152737,
|
|
"loss": 4.6285,
|
|
"mean_token_accuracy": 0.23543135821819305,
|
|
"num_tokens": 43641128.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.127269172668457,
|
|
"epoch": 1.8612269207861822,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004663547838892751,
|
|
"loss": 4.7449,
|
|
"mean_token_accuracy": 0.2147100791335106,
|
|
"num_tokens": 43656315.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.067308855056763,
|
|
"epoch": 1.861822513400834,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004663323649134379,
|
|
"loss": 4.6368,
|
|
"mean_token_accuracy": 0.2277666747570038,
|
|
"num_tokens": 43669451.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.044738864898681,
|
|
"epoch": 1.8624181060154854,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004663099390748199,
|
|
"loss": 4.7066,
|
|
"mean_token_accuracy": 0.2235270157456398,
|
|
"num_tokens": 43683282.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.066547870635986,
|
|
"epoch": 1.8630136986301369,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046628750637422534,
|
|
"loss": 4.6632,
|
|
"mean_token_accuracy": 0.22527382671833038,
|
|
"num_tokens": 43697369.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.055381202697754,
|
|
"epoch": 1.8636092912447886,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000466265066812459,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.22838487327098847,
|
|
"num_tokens": 43711270.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.177098512649536,
|
|
"epoch": 1.8642048838594403,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046624262039032566,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.22115651220083238,
|
|
"num_tokens": 43725029.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.143962955474853,
|
|
"epoch": 1.8648004764740918,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00046622016710863053,
|
|
"loss": 4.6634,
|
|
"mean_token_accuracy": 0.2290288969874382,
|
|
"num_tokens": 43737953.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.041391801834107,
|
|
"epoch": 1.8653960690887432,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004661977069681789,
|
|
"loss": 4.6405,
|
|
"mean_token_accuracy": 0.22839270532131195,
|
|
"num_tokens": 43754006.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.085211992263794,
|
|
"epoch": 1.865991661703395,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004661752399697763,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.22289566099643707,
|
|
"num_tokens": 43767655.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.118039560317993,
|
|
"epoch": 1.8665872543180466,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046615276611422876,
|
|
"loss": 4.6294,
|
|
"mean_token_accuracy": 0.22489808350801468,
|
|
"num_tokens": 43780974.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.033271932601929,
|
|
"epoch": 1.8671828469326979,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046613028540234226,
|
|
"loss": 4.6335,
|
|
"mean_token_accuracy": 0.2221527397632599,
|
|
"num_tokens": 43794479.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.084943151473999,
|
|
"epoch": 1.8677784395473496,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004661077978349232,
|
|
"loss": 4.6231,
|
|
"mean_token_accuracy": 0.22684889137744904,
|
|
"num_tokens": 43810184.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.148999500274658,
|
|
"epoch": 1.8683740321620013,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004660853034127781,
|
|
"loss": 4.711,
|
|
"mean_token_accuracy": 0.21890387088060378,
|
|
"num_tokens": 43824436.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 4.967531061172485,
|
|
"epoch": 1.8689696247766527,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004660628021367139,
|
|
"loss": 4.5445,
|
|
"mean_token_accuracy": 0.23087466806173323,
|
|
"num_tokens": 43839095.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.080769491195679,
|
|
"epoch": 1.8695652173913042,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004660402940075377,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.22891414165496826,
|
|
"num_tokens": 43851850.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.171530771255493,
|
|
"epoch": 1.870160810005956,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004660177790260567,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.21223883479833602,
|
|
"num_tokens": 43866391.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.105115509033203,
|
|
"epoch": 1.8707564026206076,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004659952571930785,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.22480004280805588,
|
|
"num_tokens": 43881188.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.064380931854248,
|
|
"epoch": 1.871351995235259,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046597272850941104,
|
|
"loss": 4.6582,
|
|
"mean_token_accuracy": 0.23432717174291612,
|
|
"num_tokens": 43893189.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.057003164291382,
|
|
"epoch": 1.8719475878499106,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046595019297586226,
|
|
"loss": 4.6149,
|
|
"mean_token_accuracy": 0.23633186519145966,
|
|
"num_tokens": 43905327.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.1088340282440186,
|
|
"epoch": 1.8725431804645623,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004659276505932405,
|
|
"loss": 4.6179,
|
|
"mean_token_accuracy": 0.22882697135210037,
|
|
"num_tokens": 43921406.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.118775129318237,
|
|
"epoch": 1.873138773079214,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00046590510136235435,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.22071444541215895,
|
|
"num_tokens": 43937218.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.036332893371582,
|
|
"epoch": 1.8737343656938654,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046588254528401264,
|
|
"loss": 4.6355,
|
|
"mean_token_accuracy": 0.23282166868448256,
|
|
"num_tokens": 43952259.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.055658006668091,
|
|
"epoch": 1.874329958308517,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.00046585998235902437,
|
|
"loss": 4.6586,
|
|
"mean_token_accuracy": 0.23078413009643556,
|
|
"num_tokens": 43968016.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.029782438278199,
|
|
"epoch": 1.8749255509231686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046583741258819894,
|
|
"loss": 4.6035,
|
|
"mean_token_accuracy": 0.2332345649600029,
|
|
"num_tokens": 43980834.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.042930459976196,
|
|
"epoch": 1.8755211435378203,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004658148359723457,
|
|
"loss": 4.6534,
|
|
"mean_token_accuracy": 0.22457975149154663,
|
|
"num_tokens": 43994100.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.047662544250488,
|
|
"epoch": 1.8761167361524718,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004657922525122746,
|
|
"loss": 4.6331,
|
|
"mean_token_accuracy": 0.22793964445590972,
|
|
"num_tokens": 44007767.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.205951690673828,
|
|
"epoch": 1.8767123287671232,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004657696622087955,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.20381509512662888,
|
|
"num_tokens": 44022268.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.000747203826904,
|
|
"epoch": 1.877307921381775,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004657470650627189,
|
|
"loss": 4.5923,
|
|
"mean_token_accuracy": 0.22584989964962005,
|
|
"num_tokens": 44038254.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.094308376312256,
|
|
"epoch": 1.8779035139964264,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046572446107485515,
|
|
"loss": 4.6465,
|
|
"mean_token_accuracy": 0.22683871686458587,
|
|
"num_tokens": 44052595.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.06587929725647,
|
|
"epoch": 1.8784991066110779,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004657018502460152,
|
|
"loss": 4.6184,
|
|
"mean_token_accuracy": 0.23376501500606536,
|
|
"num_tokens": 44066036.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.099765729904175,
|
|
"epoch": 1.8790946992257296,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046567923257700983,
|
|
"loss": 4.7388,
|
|
"mean_token_accuracy": 0.22092245519161224,
|
|
"num_tokens": 44081931.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.096937942504883,
|
|
"epoch": 1.8796902918403813,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004656566080686504,
|
|
"loss": 4.7393,
|
|
"mean_token_accuracy": 0.21435273289680482,
|
|
"num_tokens": 44096461.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.1398149013519285,
|
|
"epoch": 1.8802858844550328,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004656339767217485,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.21338505744934083,
|
|
"num_tokens": 44110475.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.090802145004273,
|
|
"epoch": 1.8808814770696842,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046561133853711576,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.2267783761024475,
|
|
"num_tokens": 44125408.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.056651592254639,
|
|
"epoch": 1.881477069684336,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004655886935155643,
|
|
"loss": 4.6785,
|
|
"mean_token_accuracy": 0.21489898413419722,
|
|
"num_tokens": 44140678.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.093260860443115,
|
|
"epoch": 1.8820726622989876,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004655660416579062,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.22287690192461013,
|
|
"num_tokens": 44153828.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.131270265579223,
|
|
"epoch": 1.882668254913639,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000465543382964954,
|
|
"loss": 4.737,
|
|
"mean_token_accuracy": 0.21275418996810913,
|
|
"num_tokens": 44168063.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.060162830352783,
|
|
"epoch": 1.8832638475282906,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046552071743752055,
|
|
"loss": 4.6015,
|
|
"mean_token_accuracy": 0.22833111733198166,
|
|
"num_tokens": 44182797.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.058616828918457,
|
|
"epoch": 1.8838594401429423,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004654980450764186,
|
|
"loss": 4.6684,
|
|
"mean_token_accuracy": 0.22805323153734208,
|
|
"num_tokens": 44197191.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.079782009124756,
|
|
"epoch": 1.884455032757594,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046547536588246167,
|
|
"loss": 4.6923,
|
|
"mean_token_accuracy": 0.21967782378196715,
|
|
"num_tokens": 44209903.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.042008018493652,
|
|
"epoch": 1.8850506253722454,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046545267985646294,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.23241792768239974,
|
|
"num_tokens": 44223252.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.066993284225464,
|
|
"epoch": 1.885646217986897,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046542998699923625,
|
|
"loss": 4.6034,
|
|
"mean_token_accuracy": 0.23169383257627488,
|
|
"num_tokens": 44236839.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.072663307189941,
|
|
"epoch": 1.8862418106015486,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004654072873115956,
|
|
"loss": 4.6477,
|
|
"mean_token_accuracy": 0.22720049768686296,
|
|
"num_tokens": 44250125.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.109976291656494,
|
|
"epoch": 1.8868374032162,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00046538458079435516,
|
|
"loss": 4.6817,
|
|
"mean_token_accuracy": 0.21960776001214982,
|
|
"num_tokens": 44265543.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.105079793930054,
|
|
"epoch": 1.8874329958308516,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004653618674483293,
|
|
"loss": 4.7082,
|
|
"mean_token_accuracy": 0.22667431384325026,
|
|
"num_tokens": 44278914.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.152655792236328,
|
|
"epoch": 1.8880285884455033,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046533914727433276,
|
|
"loss": 4.7391,
|
|
"mean_token_accuracy": 0.21731774210929872,
|
|
"num_tokens": 44292393.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.0933106422424315,
|
|
"epoch": 1.888624181060155,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004653164202731804,
|
|
"loss": 4.6459,
|
|
"mean_token_accuracy": 0.2260459318757057,
|
|
"num_tokens": 44305835.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 4.982144832611084,
|
|
"epoch": 1.8892197736748064,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00046529368644568765,
|
|
"loss": 4.5979,
|
|
"mean_token_accuracy": 0.23437036275863649,
|
|
"num_tokens": 44320332.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.062830686569214,
|
|
"epoch": 1.889815366289458,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004652709457926697,
|
|
"loss": 4.6551,
|
|
"mean_token_accuracy": 0.22433653771877288,
|
|
"num_tokens": 44333440.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.069372510910034,
|
|
"epoch": 1.8904109589041096,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046524819831494224,
|
|
"loss": 4.636,
|
|
"mean_token_accuracy": 0.22423200607299804,
|
|
"num_tokens": 44347351.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.123613071441651,
|
|
"epoch": 1.8910065515187613,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004652254440133213,
|
|
"loss": 4.7622,
|
|
"mean_token_accuracy": 0.21812192499637603,
|
|
"num_tokens": 44362394.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.024874830245972,
|
|
"epoch": 1.8916021441334128,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004652026828886229,
|
|
"loss": 4.5056,
|
|
"mean_token_accuracy": 0.23885201066732406,
|
|
"num_tokens": 44375971.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.003815793991089,
|
|
"epoch": 1.8921977367480642,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004651799149416636,
|
|
"loss": 4.5469,
|
|
"mean_token_accuracy": 0.23492986261844634,
|
|
"num_tokens": 44389991.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.036855459213257,
|
|
"epoch": 1.892793329362716,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004651571401732599,
|
|
"loss": 4.6106,
|
|
"mean_token_accuracy": 0.2248600974678993,
|
|
"num_tokens": 44405737.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.063575792312622,
|
|
"epoch": 1.8933889219773676,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004651343585842287,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.23033171594142915,
|
|
"num_tokens": 44418641.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.091067171096801,
|
|
"epoch": 1.893984514592019,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004651115701753873,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.22399829477071762,
|
|
"num_tokens": 44433841.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 4.9932841777801515,
|
|
"epoch": 1.8945801072066706,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046508877494755296,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.23207173943519593,
|
|
"num_tokens": 44448715.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.0962224960327145,
|
|
"epoch": 1.8951756998213223,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00046506597290154337,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.2251291334629059,
|
|
"num_tokens": 44462757.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.0722850322723385,
|
|
"epoch": 1.8957712924359738,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046504316403817627,
|
|
"loss": 4.6146,
|
|
"mean_token_accuracy": 0.2272301122546196,
|
|
"num_tokens": 44477558.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.046186065673828,
|
|
"epoch": 1.8963668850506252,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004650203483582699,
|
|
"loss": 4.638,
|
|
"mean_token_accuracy": 0.22484681755304337,
|
|
"num_tokens": 44491520.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.099422836303711,
|
|
"epoch": 1.896962477665277,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00046499752586264264,
|
|
"loss": 4.722,
|
|
"mean_token_accuracy": 0.21550866961479187,
|
|
"num_tokens": 44505306.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.048105144500733,
|
|
"epoch": 1.8975580702799286,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004649746965521129,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.23281940221786498,
|
|
"num_tokens": 44518969.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.002604007720947,
|
|
"epoch": 1.89815366289458,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004649518604274999,
|
|
"loss": 4.5694,
|
|
"mean_token_accuracy": 0.23773820400238038,
|
|
"num_tokens": 44532260.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.033749961853028,
|
|
"epoch": 1.8987492555092316,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004649290174896223,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.2220497965812683,
|
|
"num_tokens": 44545172.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 4.991947031021118,
|
|
"epoch": 1.8993448481238833,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004649061677392998,
|
|
"loss": 4.5715,
|
|
"mean_token_accuracy": 0.23340903371572494,
|
|
"num_tokens": 44558326.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.098961019515992,
|
|
"epoch": 1.899940440738535,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046488331117735176,
|
|
"loss": 4.6659,
|
|
"mean_token_accuracy": 0.2200282946228981,
|
|
"num_tokens": 44572517.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.17340612411499,
|
|
"epoch": 1.9005360333531864,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004648604478045981,
|
|
"loss": 4.7374,
|
|
"mean_token_accuracy": 0.2227286219596863,
|
|
"num_tokens": 44585148.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.033579874038696,
|
|
"epoch": 1.901131625967838,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046483757762185877,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.23083145320415496,
|
|
"num_tokens": 44600103.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.069201278686523,
|
|
"epoch": 1.9017272185824896,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004648147006299543,
|
|
"loss": 4.7357,
|
|
"mean_token_accuracy": 0.2210848495364189,
|
|
"num_tokens": 44614653.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.114768028259277,
|
|
"epoch": 1.9023228111971413,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004647918168297051,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.22656756937503814,
|
|
"num_tokens": 44629320.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.071056842803955,
|
|
"epoch": 1.9029184038117928,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00046476892622193206,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.22898004204034805,
|
|
"num_tokens": 44645062.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.032510709762573,
|
|
"epoch": 1.9035139964264443,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004647460288074562,
|
|
"loss": 4.577,
|
|
"mean_token_accuracy": 0.2352146878838539,
|
|
"num_tokens": 44659563.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.144183874130249,
|
|
"epoch": 1.904109589041096,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004647231245870987,
|
|
"loss": 4.776,
|
|
"mean_token_accuracy": 0.21405414193868638,
|
|
"num_tokens": 44674259.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.087454605102539,
|
|
"epoch": 1.9047051816557474,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046470021356168116,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.22814490050077438,
|
|
"num_tokens": 44688057.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.059843826293945,
|
|
"epoch": 1.905300774270399,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046467729573202555,
|
|
"loss": 4.7008,
|
|
"mean_token_accuracy": 0.22013965547084807,
|
|
"num_tokens": 44705123.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.124520254135132,
|
|
"epoch": 1.9058963668850506,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046465437109895365,
|
|
"loss": 4.6761,
|
|
"mean_token_accuracy": 0.22419525384902955,
|
|
"num_tokens": 44719702.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.0372899055480955,
|
|
"epoch": 1.9064919594997023,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004646314396632878,
|
|
"loss": 4.592,
|
|
"mean_token_accuracy": 0.23451068252325058,
|
|
"num_tokens": 44733331.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.000662326812744,
|
|
"epoch": 1.9070875521143538,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004646085014258506,
|
|
"loss": 4.644,
|
|
"mean_token_accuracy": 0.22780255675315858,
|
|
"num_tokens": 44746095.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.1415030002594,
|
|
"epoch": 1.9076831447290052,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046458555638746464,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.2140692114830017,
|
|
"num_tokens": 44761314.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.130169630050659,
|
|
"epoch": 1.908278737343657,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046456260454895307,
|
|
"loss": 4.6372,
|
|
"mean_token_accuracy": 0.22884633988142014,
|
|
"num_tokens": 44776186.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 4.997229290008545,
|
|
"epoch": 1.9088743299583086,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046453964591113906,
|
|
"loss": 4.6374,
|
|
"mean_token_accuracy": 0.2256387621164322,
|
|
"num_tokens": 44791203.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.147152662277222,
|
|
"epoch": 1.90946992257296,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004645166804748462,
|
|
"loss": 4.6915,
|
|
"mean_token_accuracy": 0.23227602988481522,
|
|
"num_tokens": 44805114.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.0127513885498045,
|
|
"epoch": 1.9100655151876116,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046449370824089807,
|
|
"loss": 4.5679,
|
|
"mean_token_accuracy": 0.23495652973651887,
|
|
"num_tokens": 44818873.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.016363334655762,
|
|
"epoch": 1.9106611078022633,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046447072921011875,
|
|
"loss": 4.6954,
|
|
"mean_token_accuracy": 0.2263590171933174,
|
|
"num_tokens": 44832438.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.073802804946899,
|
|
"epoch": 1.911256700416915,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046444774338333253,
|
|
"loss": 4.6601,
|
|
"mean_token_accuracy": 0.22636915296316146,
|
|
"num_tokens": 44848304.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.1553511142730715,
|
|
"epoch": 1.9118522930315665,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004644247507613636,
|
|
"loss": 4.7006,
|
|
"mean_token_accuracy": 0.22080987244844436,
|
|
"num_tokens": 44862991.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.0811262130737305,
|
|
"epoch": 1.912447885646218,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000464401751345037,
|
|
"loss": 4.6332,
|
|
"mean_token_accuracy": 0.2222544714808464,
|
|
"num_tokens": 44876815.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.099851322174072,
|
|
"epoch": 1.9130434782608696,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004643787451351774,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.22159218043088913,
|
|
"num_tokens": 44890574.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.130878591537476,
|
|
"epoch": 1.913639070875521,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004643557321326102,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.22415203750133514,
|
|
"num_tokens": 44904447.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.037417078018189,
|
|
"epoch": 1.9142346634901726,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004643327123381607,
|
|
"loss": 4.5764,
|
|
"mean_token_accuracy": 0.2297166332602501,
|
|
"num_tokens": 44916500.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 4.996744823455811,
|
|
"epoch": 1.9148302561048243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004643096857526547,
|
|
"loss": 4.555,
|
|
"mean_token_accuracy": 0.23667467683553695,
|
|
"num_tokens": 44929738.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.061641263961792,
|
|
"epoch": 1.915425848719476,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046428665237691806,
|
|
"loss": 4.636,
|
|
"mean_token_accuracy": 0.22791038751602172,
|
|
"num_tokens": 44942528.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.077974605560303,
|
|
"epoch": 1.9160214413341274,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000464263612211777,
|
|
"loss": 4.6688,
|
|
"mean_token_accuracy": 0.2278636261820793,
|
|
"num_tokens": 44956126.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.0810754776000975,
|
|
"epoch": 1.916617033948779,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004642405652580578,
|
|
"loss": 4.6813,
|
|
"mean_token_accuracy": 0.2237590178847313,
|
|
"num_tokens": 44969733.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.024357652664184,
|
|
"epoch": 1.9172126265634306,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004642175115165873,
|
|
"loss": 4.5138,
|
|
"mean_token_accuracy": 0.2445756360888481,
|
|
"num_tokens": 44982751.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.075412225723267,
|
|
"epoch": 1.9178082191780823,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046419445098819223,
|
|
"loss": 4.6243,
|
|
"mean_token_accuracy": 0.22633190006017684,
|
|
"num_tokens": 44997898.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.07706127166748,
|
|
"epoch": 1.9184038117927338,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046417138367369995,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.22344694435596466,
|
|
"num_tokens": 45012617.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.04393253326416,
|
|
"epoch": 1.9189994044073853,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046414830957393756,
|
|
"loss": 4.6239,
|
|
"mean_token_accuracy": 0.23071643710136414,
|
|
"num_tokens": 45025847.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.08597412109375,
|
|
"epoch": 1.919594997022037,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00046412522868973297,
|
|
"loss": 4.6542,
|
|
"mean_token_accuracy": 0.22688702046871184,
|
|
"num_tokens": 45040674.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.11620602607727,
|
|
"epoch": 1.9201905896366886,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004641021410219138,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.22266179472208023,
|
|
"num_tokens": 45053585.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.036256551742554,
|
|
"epoch": 1.9207861822513401,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00046407904657130833,
|
|
"loss": 4.5754,
|
|
"mean_token_accuracy": 0.23593470603227615,
|
|
"num_tokens": 45069825.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.109752941131592,
|
|
"epoch": 1.9213817748659916,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004640559453387449,
|
|
"loss": 4.6628,
|
|
"mean_token_accuracy": 0.2197912022471428,
|
|
"num_tokens": 45085235.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.044204568862915,
|
|
"epoch": 1.9219773674806433,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004640328373250521,
|
|
"loss": 4.6131,
|
|
"mean_token_accuracy": 0.2335391089320183,
|
|
"num_tokens": 45099209.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.061818695068359,
|
|
"epoch": 1.9225729600952948,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046400972253105884,
|
|
"loss": 4.6548,
|
|
"mean_token_accuracy": 0.22524140328168868,
|
|
"num_tokens": 45114132.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 4.97294979095459,
|
|
"epoch": 1.9231685527099462,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000463986600957594,
|
|
"loss": 4.6016,
|
|
"mean_token_accuracy": 0.23288449943065642,
|
|
"num_tokens": 45126637.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.09079270362854,
|
|
"epoch": 1.923764145324598,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046396347260548715,
|
|
"loss": 4.7245,
|
|
"mean_token_accuracy": 0.21913429945707322,
|
|
"num_tokens": 45140950.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 4.995693206787109,
|
|
"epoch": 1.9243597379392496,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004639403374755678,
|
|
"loss": 4.5345,
|
|
"mean_token_accuracy": 0.23577630817890166,
|
|
"num_tokens": 45155050.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.073487997055054,
|
|
"epoch": 1.9249553305539011,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004639171955686657,
|
|
"loss": 4.6693,
|
|
"mean_token_accuracy": 0.2266031712293625,
|
|
"num_tokens": 45169864.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.1015379428863525,
|
|
"epoch": 1.9255509231685526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004638940468856109,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.23606465607881547,
|
|
"num_tokens": 45183148.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.027472257614136,
|
|
"epoch": 1.9261465157832043,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046387089142723386,
|
|
"loss": 4.5861,
|
|
"mean_token_accuracy": 0.23514939546585084,
|
|
"num_tokens": 45196652.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.043152809143066,
|
|
"epoch": 1.926742108397856,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046384772919436497,
|
|
"loss": 4.6344,
|
|
"mean_token_accuracy": 0.23025518506765366,
|
|
"num_tokens": 45210628.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.142118692398071,
|
|
"epoch": 1.9273377010125075,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00046382456018783513,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.21841877549886704,
|
|
"num_tokens": 45226276.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.085934162139893,
|
|
"epoch": 1.927933293627159,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004638013844084753,
|
|
"loss": 4.6561,
|
|
"mean_token_accuracy": 0.235136416554451,
|
|
"num_tokens": 45242214.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.1821516990661625,
|
|
"epoch": 1.9285288862418106,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004637782018571167,
|
|
"loss": 4.7467,
|
|
"mean_token_accuracy": 0.2218014732003212,
|
|
"num_tokens": 45256536.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.055187702178955,
|
|
"epoch": 1.9291244788564623,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004637550125345911,
|
|
"loss": 4.6279,
|
|
"mean_token_accuracy": 0.22590127289295198,
|
|
"num_tokens": 45269383.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.091261291503907,
|
|
"epoch": 1.9297200714711138,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046373181644173,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.2262285679578781,
|
|
"num_tokens": 45282265.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.131673049926758,
|
|
"epoch": 1.9303156640857653,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004637086135793655,
|
|
"loss": 4.6313,
|
|
"mean_token_accuracy": 0.22717079073190688,
|
|
"num_tokens": 45294379.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.030973863601685,
|
|
"epoch": 1.930911256700417,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004636854039483299,
|
|
"loss": 4.6189,
|
|
"mean_token_accuracy": 0.22796117067337035,
|
|
"num_tokens": 45307608.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.095137405395508,
|
|
"epoch": 1.9315068493150684,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046366218754945556,
|
|
"loss": 4.7545,
|
|
"mean_token_accuracy": 0.221234929561615,
|
|
"num_tokens": 45320382.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.083855867385864,
|
|
"epoch": 1.93210244192972,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004636389643835754,
|
|
"loss": 4.5865,
|
|
"mean_token_accuracy": 0.23067581355571748,
|
|
"num_tokens": 45334590.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.025308513641358,
|
|
"epoch": 1.9326980345443716,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046361573445152224,
|
|
"loss": 4.5761,
|
|
"mean_token_accuracy": 0.23200616389513015,
|
|
"num_tokens": 45348701.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.016618633270264,
|
|
"epoch": 1.9332936271590233,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046359249775412934,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.22766103744506835,
|
|
"num_tokens": 45362896.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.064988899230957,
|
|
"epoch": 1.9338892197736748,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004635692542922302,
|
|
"loss": 4.6311,
|
|
"mean_token_accuracy": 0.23303309381008147,
|
|
"num_tokens": 45378208.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.052515888214112,
|
|
"epoch": 1.9344848123883263,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00046354600406665853,
|
|
"loss": 4.6288,
|
|
"mean_token_accuracy": 0.22364211082458496,
|
|
"num_tokens": 45392101.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.041861057281494,
|
|
"epoch": 1.935080405002978,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046352274707824823,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.22710286527872087,
|
|
"num_tokens": 45405829.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.04812388420105,
|
|
"epoch": 1.9356759976176297,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004634994833278334,
|
|
"loss": 4.6313,
|
|
"mean_token_accuracy": 0.22397089004516602,
|
|
"num_tokens": 45419772.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.022906351089477,
|
|
"epoch": 1.9362715902322811,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004634762128162487,
|
|
"loss": 4.63,
|
|
"mean_token_accuracy": 0.22622617036104203,
|
|
"num_tokens": 45433192.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.061715364456177,
|
|
"epoch": 1.9368671828469326,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004634529355443287,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.2253592997789383,
|
|
"num_tokens": 45447409.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.0608021259307865,
|
|
"epoch": 1.9374627754615843,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046342965151290836,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.21826561093330382,
|
|
"num_tokens": 45460768.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.151774930953979,
|
|
"epoch": 1.938058368076236,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046340636072282273,
|
|
"loss": 4.7299,
|
|
"mean_token_accuracy": 0.21823116391897202,
|
|
"num_tokens": 45474500.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.1570969581604,
|
|
"epoch": 1.9386539606908875,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004633830631749072,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.21538199633359909,
|
|
"num_tokens": 45486699.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.011828947067261,
|
|
"epoch": 1.939249553305539,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046335975886999754,
|
|
"loss": 4.5993,
|
|
"mean_token_accuracy": 0.226052226126194,
|
|
"num_tokens": 45500431.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.108974885940552,
|
|
"epoch": 1.9398451459201906,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004633364478089296,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.22073269486427308,
|
|
"num_tokens": 45515813.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.104164934158325,
|
|
"epoch": 1.9404407385348421,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004633131299925395,
|
|
"loss": 4.6085,
|
|
"mean_token_accuracy": 0.23217309713363649,
|
|
"num_tokens": 45530454.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.122702312469483,
|
|
"epoch": 1.9410363311494936,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004632898054216636,
|
|
"loss": 4.7194,
|
|
"mean_token_accuracy": 0.21708723455667495,
|
|
"num_tokens": 45544526.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.053711366653443,
|
|
"epoch": 1.9416319237641453,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046326647409713844,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.22865440845489501,
|
|
"num_tokens": 45557992.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.058432149887085,
|
|
"epoch": 1.942227516378797,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046324313601980106,
|
|
"loss": 4.7207,
|
|
"mean_token_accuracy": 0.22472936958074569,
|
|
"num_tokens": 45572650.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.097335243225098,
|
|
"epoch": 1.9428231089934485,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004632197911904884,
|
|
"loss": 4.6224,
|
|
"mean_token_accuracy": 0.22501352578401565,
|
|
"num_tokens": 45586151.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.012929677963257,
|
|
"epoch": 1.9434187016081,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046319643961003785,
|
|
"loss": 4.5969,
|
|
"mean_token_accuracy": 0.22804910093545913,
|
|
"num_tokens": 45599862.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.088888549804688,
|
|
"epoch": 1.9440142942227516,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046317308127928706,
|
|
"loss": 4.6176,
|
|
"mean_token_accuracy": 0.2266446530818939,
|
|
"num_tokens": 45616075.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.022815895080567,
|
|
"epoch": 1.9446098868374033,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004631497161990738,
|
|
"loss": 4.5345,
|
|
"mean_token_accuracy": 0.2379020407795906,
|
|
"num_tokens": 45629006.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.062212896347046,
|
|
"epoch": 1.9452054794520548,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004631263443702361,
|
|
"loss": 4.696,
|
|
"mean_token_accuracy": 0.21705363988876342,
|
|
"num_tokens": 45641802.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.0614838123321535,
|
|
"epoch": 1.9458010720667063,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046310296579361225,
|
|
"loss": 4.6709,
|
|
"mean_token_accuracy": 0.22424391210079192,
|
|
"num_tokens": 45654982.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.0824745178222654,
|
|
"epoch": 1.946396664681358,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004630795804700409,
|
|
"loss": 4.6062,
|
|
"mean_token_accuracy": 0.2311028003692627,
|
|
"num_tokens": 45669547.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.011080026626587,
|
|
"epoch": 1.9469922572960097,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004630561884003608,
|
|
"loss": 4.6295,
|
|
"mean_token_accuracy": 0.22966065108776093,
|
|
"num_tokens": 45682026.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.031890773773194,
|
|
"epoch": 1.9475878499106611,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000463032789585411,
|
|
"loss": 4.6323,
|
|
"mean_token_accuracy": 0.2318716064095497,
|
|
"num_tokens": 45696637.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.1854815006256105,
|
|
"epoch": 1.9481834425253126,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004630093840260307,
|
|
"loss": 4.6767,
|
|
"mean_token_accuracy": 0.22021752148866652,
|
|
"num_tokens": 45710846.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.089163780212402,
|
|
"epoch": 1.9487790351399643,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046298597172305956,
|
|
"loss": 4.6939,
|
|
"mean_token_accuracy": 0.22707599103450776,
|
|
"num_tokens": 45724479.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.052905750274658,
|
|
"epoch": 1.949374627754616,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004629625526773372,
|
|
"loss": 4.6077,
|
|
"mean_token_accuracy": 0.225146646797657,
|
|
"num_tokens": 45738347.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.010669231414795,
|
|
"epoch": 1.9499702203692673,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004629391268897037,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.22811659127473832,
|
|
"num_tokens": 45751316.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.119338798522949,
|
|
"epoch": 1.950565812983919,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004629156943609993,
|
|
"loss": 4.7082,
|
|
"mean_token_accuracy": 0.21417022943496705,
|
|
"num_tokens": 45765479.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.139959001541138,
|
|
"epoch": 1.9511614055985707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046289225509206445,
|
|
"loss": 4.7099,
|
|
"mean_token_accuracy": 0.21995163559913636,
|
|
"num_tokens": 45779645.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.087260961532593,
|
|
"epoch": 1.9517569982132221,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004628688090837399,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.227116222679615,
|
|
"num_tokens": 45795057.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.119286108016968,
|
|
"epoch": 1.9523525908278736,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004628453563368666,
|
|
"loss": 4.7537,
|
|
"mean_token_accuracy": 0.21555387526750563,
|
|
"num_tokens": 45809055.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.1065761089324955,
|
|
"epoch": 1.9529481834425253,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004628218968522859,
|
|
"loss": 4.6374,
|
|
"mean_token_accuracy": 0.22720241248607637,
|
|
"num_tokens": 45822882.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.1031355381011965,
|
|
"epoch": 1.953543776057177,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004627984306308391,
|
|
"loss": 4.6532,
|
|
"mean_token_accuracy": 0.22527983784675598,
|
|
"num_tokens": 45839325.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.137907028198242,
|
|
"epoch": 1.9541393686718285,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046277495767336785,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.21331242471933365,
|
|
"num_tokens": 45853143.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.099273681640625,
|
|
"epoch": 1.95473496128648,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004627514779807142,
|
|
"loss": 4.6299,
|
|
"mean_token_accuracy": 0.2346652179956436,
|
|
"num_tokens": 45866775.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.017638349533081,
|
|
"epoch": 1.9553305539011316,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004627279915537204,
|
|
"loss": 4.5987,
|
|
"mean_token_accuracy": 0.22933042645454407,
|
|
"num_tokens": 45881164.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.1187561511993405,
|
|
"epoch": 1.9559261465157833,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046270449839322863,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.21920512467622758,
|
|
"num_tokens": 45894854.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.099669742584228,
|
|
"epoch": 1.9565217391304348,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046268099850008175,
|
|
"loss": 4.7033,
|
|
"mean_token_accuracy": 0.22049084901809693,
|
|
"num_tokens": 45909825.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.062675809860229,
|
|
"epoch": 1.9571173317450863,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004626574918751226,
|
|
"loss": 4.6497,
|
|
"mean_token_accuracy": 0.22484747022390367,
|
|
"num_tokens": 45924397.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.048088645935058,
|
|
"epoch": 1.957712924359738,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004626339785191944,
|
|
"loss": 4.5208,
|
|
"mean_token_accuracy": 0.2314680427312851,
|
|
"num_tokens": 45938178.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.063851451873779,
|
|
"epoch": 1.9583085169743897,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004626104584331404,
|
|
"loss": 4.6667,
|
|
"mean_token_accuracy": 0.23261450827121735,
|
|
"num_tokens": 45951632.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.130846261978149,
|
|
"epoch": 1.958904109589041,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004625869316178043,
|
|
"loss": 4.6631,
|
|
"mean_token_accuracy": 0.22924794703722,
|
|
"num_tokens": 45965524.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.006914234161377,
|
|
"epoch": 1.9594997022036926,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046256339807403,
|
|
"loss": 4.5762,
|
|
"mean_token_accuracy": 0.22970579862594603,
|
|
"num_tokens": 45978750.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 4.9830320358276365,
|
|
"epoch": 1.9600952948183443,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004625398578026615,
|
|
"loss": 4.5815,
|
|
"mean_token_accuracy": 0.23444883525371552,
|
|
"num_tokens": 45992587.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.050702428817749,
|
|
"epoch": 1.9606908874329958,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00046251631080454324,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.22527540922164918,
|
|
"num_tokens": 46008468.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.091706037521362,
|
|
"epoch": 1.9612864800476473,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004624927570805198,
|
|
"loss": 4.6414,
|
|
"mean_token_accuracy": 0.22449593096971512,
|
|
"num_tokens": 46022616.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.104506015777588,
|
|
"epoch": 1.961882072662299,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046246919663143603,
|
|
"loss": 4.6673,
|
|
"mean_token_accuracy": 0.23140378296375275,
|
|
"num_tokens": 46035890.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.069689083099365,
|
|
"epoch": 1.9624776652769507,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000462445629458137,
|
|
"loss": 4.6035,
|
|
"mean_token_accuracy": 0.23369396328926087,
|
|
"num_tokens": 46049881.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.0731470584869385,
|
|
"epoch": 1.9630732578916021,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046242205556146795,
|
|
"loss": 4.7069,
|
|
"mean_token_accuracy": 0.21902605295181274,
|
|
"num_tokens": 46063672.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.046088695526123,
|
|
"epoch": 1.9636688505062536,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004623984749422745,
|
|
"loss": 4.6346,
|
|
"mean_token_accuracy": 0.22907141596078873,
|
|
"num_tokens": 46076500.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.07530517578125,
|
|
"epoch": 1.9642644431209053,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004623748876014025,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.22996371537446975,
|
|
"num_tokens": 46089469.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.039407682418823,
|
|
"epoch": 1.964860035735557,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004623512935396979,
|
|
"loss": 4.5577,
|
|
"mean_token_accuracy": 0.23142593502998351,
|
|
"num_tokens": 46103334.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.049474716186523,
|
|
"epoch": 1.9654556283502085,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000462327692758007,
|
|
"loss": 4.6215,
|
|
"mean_token_accuracy": 0.23294229805469513,
|
|
"num_tokens": 46116107.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.007707691192627,
|
|
"epoch": 1.96605122096486,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004623040852571764,
|
|
"loss": 4.6113,
|
|
"mean_token_accuracy": 0.22949634492397308,
|
|
"num_tokens": 46130416.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.132959222793579,
|
|
"epoch": 1.9666468135795117,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046228047103805277,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.21379811614751815,
|
|
"num_tokens": 46144020.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.03669695854187,
|
|
"epoch": 1.9672424061941634,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004622568501014831,
|
|
"loss": 4.6407,
|
|
"mean_token_accuracy": 0.2286202311515808,
|
|
"num_tokens": 46157395.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.103311824798584,
|
|
"epoch": 1.9678379988088148,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046223322244831475,
|
|
"loss": 4.7125,
|
|
"mean_token_accuracy": 0.2257695272564888,
|
|
"num_tokens": 46171861.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.125542545318604,
|
|
"epoch": 1.9684335914234663,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000462209588079395,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.2205040618777275,
|
|
"num_tokens": 46187486.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.125516319274903,
|
|
"epoch": 1.969029184038118,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004621859469955718,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.22301127314567565,
|
|
"num_tokens": 46199699.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.112687778472901,
|
|
"epoch": 1.9696247766527695,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046216229919769305,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.22126420736312866,
|
|
"num_tokens": 46214209.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.065785932540893,
|
|
"epoch": 1.970220369267421,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000462138644686607,
|
|
"loss": 4.6708,
|
|
"mean_token_accuracy": 0.232820500433445,
|
|
"num_tokens": 46227475.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.090441560745239,
|
|
"epoch": 1.9708159618820726,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046211498346316194,
|
|
"loss": 4.7032,
|
|
"mean_token_accuracy": 0.224431549012661,
|
|
"num_tokens": 46240131.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.040850687026977,
|
|
"epoch": 1.9714115544967243,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004620913155282066,
|
|
"loss": 4.5966,
|
|
"mean_token_accuracy": 0.2361827477812767,
|
|
"num_tokens": 46253039.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.1450433254241945,
|
|
"epoch": 1.9720071471113758,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046206764088259003,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.2222209870815277,
|
|
"num_tokens": 46268618.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.075893115997315,
|
|
"epoch": 1.9726027397260273,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004620439595271613,
|
|
"loss": 4.6188,
|
|
"mean_token_accuracy": 0.23395799696445466,
|
|
"num_tokens": 46282447.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.147321367263794,
|
|
"epoch": 1.973198332340679,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004620202714627699,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.21594240367412568,
|
|
"num_tokens": 46295929.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 4.976794338226318,
|
|
"epoch": 1.9737939249553307,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004619965766902654,
|
|
"loss": 4.553,
|
|
"mean_token_accuracy": 0.2364545524120331,
|
|
"num_tokens": 46310876.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.086483907699585,
|
|
"epoch": 1.9743895175699822,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046197287521049777,
|
|
"loss": 4.6782,
|
|
"mean_token_accuracy": 0.22400160878896713,
|
|
"num_tokens": 46325555.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.069320249557495,
|
|
"epoch": 1.9749851101846336,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004619491670243171,
|
|
"loss": 4.6206,
|
|
"mean_token_accuracy": 0.2285171315073967,
|
|
"num_tokens": 46340226.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.100216102600098,
|
|
"epoch": 1.9755807027992853,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046192545213257375,
|
|
"loss": 4.6174,
|
|
"mean_token_accuracy": 0.22848768085241317,
|
|
"num_tokens": 46353268.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.123812055587768,
|
|
"epoch": 1.976176295413937,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004619017305361184,
|
|
"loss": 4.7068,
|
|
"mean_token_accuracy": 0.22429523319005967,
|
|
"num_tokens": 46367547.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.102049350738525,
|
|
"epoch": 1.9767718880285885,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004618780022358018,
|
|
"loss": 4.697,
|
|
"mean_token_accuracy": 0.21845548152923583,
|
|
"num_tokens": 46382980.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.122727727890014,
|
|
"epoch": 1.97736748064324,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004618542672324751,
|
|
"loss": 4.6524,
|
|
"mean_token_accuracy": 0.22821135371923446,
|
|
"num_tokens": 46396449.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.068984746932983,
|
|
"epoch": 1.9779630732578917,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046183052552698975,
|
|
"loss": 4.6506,
|
|
"mean_token_accuracy": 0.21893508732318878,
|
|
"num_tokens": 46410569.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.1228550434112545,
|
|
"epoch": 1.9785586658725431,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046180677712019707,
|
|
"loss": 4.7637,
|
|
"mean_token_accuracy": 0.21904849857091904,
|
|
"num_tokens": 46424391.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.195784235000611,
|
|
"epoch": 1.9791542584871946,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004617830220129491,
|
|
"loss": 4.8016,
|
|
"mean_token_accuracy": 0.2172147274017334,
|
|
"num_tokens": 46439778.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.0947919368743895,
|
|
"epoch": 1.9797498511018463,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004617592602060979,
|
|
"loss": 4.6601,
|
|
"mean_token_accuracy": 0.2322096809744835,
|
|
"num_tokens": 46454334.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.0831903457641605,
|
|
"epoch": 1.980345443716498,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046173549170049554,
|
|
"loss": 4.5938,
|
|
"mean_token_accuracy": 0.23416347950696945,
|
|
"num_tokens": 46465954.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.0485827922821045,
|
|
"epoch": 1.9809410363311495,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004617117164969948,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.2289298117160797,
|
|
"num_tokens": 46480947.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.071087646484375,
|
|
"epoch": 1.981536628945801,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046168793459644837,
|
|
"loss": 4.6403,
|
|
"mean_token_accuracy": 0.23055672347545625,
|
|
"num_tokens": 46494547.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.033303833007812,
|
|
"epoch": 1.9821322215604527,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004616641459997092,
|
|
"loss": 4.5817,
|
|
"mean_token_accuracy": 0.234116792678833,
|
|
"num_tokens": 46507759.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.063513994216919,
|
|
"epoch": 1.9827278141751044,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004616403507076306,
|
|
"loss": 4.6299,
|
|
"mean_token_accuracy": 0.22783446311950684,
|
|
"num_tokens": 46522942.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.093987083435058,
|
|
"epoch": 1.9833234067897558,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004616165487210661,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.23251935094594955,
|
|
"num_tokens": 46537071.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.131822919845581,
|
|
"epoch": 1.9839189994044073,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004615927400408695,
|
|
"loss": 4.7554,
|
|
"mean_token_accuracy": 0.21489864587783813,
|
|
"num_tokens": 46550430.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.071402883529663,
|
|
"epoch": 1.984514592019059,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004615689246678946,
|
|
"loss": 4.6007,
|
|
"mean_token_accuracy": 0.2366696387529373,
|
|
"num_tokens": 46563206.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.026041507720947,
|
|
"epoch": 1.9851101846337107,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004615451026029957,
|
|
"loss": 4.5528,
|
|
"mean_token_accuracy": 0.23351412117481232,
|
|
"num_tokens": 46576841.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.117838668823242,
|
|
"epoch": 1.9857057772483622,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004615212738470273,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.21909448653459548,
|
|
"num_tokens": 46591217.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.07193284034729,
|
|
"epoch": 1.9863013698630136,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046149743840084406,
|
|
"loss": 4.6362,
|
|
"mean_token_accuracy": 0.22940537482500076,
|
|
"num_tokens": 46605393.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.057305574417114,
|
|
"epoch": 1.9868969624776653,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046147359626530103,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.22315169423818587,
|
|
"num_tokens": 46622283.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.044653987884521,
|
|
"epoch": 1.9874925550923168,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004614497474412532,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.22517292499542235,
|
|
"num_tokens": 46637274.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.0085193634033205,
|
|
"epoch": 1.9880881477069683,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004614258919295561,
|
|
"loss": 4.5853,
|
|
"mean_token_accuracy": 0.23455539345741272,
|
|
"num_tokens": 46650722.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.098665428161621,
|
|
"epoch": 1.98868374032162,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004614020297310654,
|
|
"loss": 4.6207,
|
|
"mean_token_accuracy": 0.22878218144178392,
|
|
"num_tokens": 46665254.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.104337120056153,
|
|
"epoch": 1.9892793329362717,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004613781608466369,
|
|
"loss": 4.6519,
|
|
"mean_token_accuracy": 0.224040749669075,
|
|
"num_tokens": 46678696.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.174171686172485,
|
|
"epoch": 1.9898749255509232,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004613542852771269,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.2194940999150276,
|
|
"num_tokens": 46692188.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.153349447250366,
|
|
"epoch": 1.9904705181655746,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046133040302339155,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.21705158054828644,
|
|
"num_tokens": 46707452.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.125695037841797,
|
|
"epoch": 1.9910661107802263,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004613065140862877,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.22880093902349471,
|
|
"num_tokens": 46721612.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.075027418136597,
|
|
"epoch": 1.991661703394878,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000461282618466672,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.22476962953805923,
|
|
"num_tokens": 46734760.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.0629853248596195,
|
|
"epoch": 1.9922572960095295,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046125871616540165,
|
|
"loss": 4.6844,
|
|
"mean_token_accuracy": 0.2257062166929245,
|
|
"num_tokens": 46747202.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.078641319274903,
|
|
"epoch": 1.992852888624181,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004612348071833341,
|
|
"loss": 4.6925,
|
|
"mean_token_accuracy": 0.22412382960319518,
|
|
"num_tokens": 46759652.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.060224390029907,
|
|
"epoch": 1.9934484812388327,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004612108915213268,
|
|
"loss": 4.5987,
|
|
"mean_token_accuracy": 0.23672000467777252,
|
|
"num_tokens": 46774424.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.137433052062988,
|
|
"epoch": 1.9940440738534844,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046118696918023757,
|
|
"loss": 4.723,
|
|
"mean_token_accuracy": 0.22393242716789247,
|
|
"num_tokens": 46786916.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.044887542724609,
|
|
"epoch": 1.9946396664681358,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046116304016092445,
|
|
"loss": 4.5784,
|
|
"mean_token_accuracy": 0.23635538071393966,
|
|
"num_tokens": 46798453.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.0255005836486815,
|
|
"epoch": 1.9952352590827873,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004611391044642458,
|
|
"loss": 4.6235,
|
|
"mean_token_accuracy": 0.23341882824897767,
|
|
"num_tokens": 46811619.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 4.983158969879151,
|
|
"epoch": 1.995830851697439,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046111516209106004,
|
|
"loss": 4.5848,
|
|
"mean_token_accuracy": 0.23267709463834763,
|
|
"num_tokens": 46824956.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.083484172821045,
|
|
"epoch": 1.9964264443120905,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046109121304222607,
|
|
"loss": 4.6523,
|
|
"mean_token_accuracy": 0.2278706982731819,
|
|
"num_tokens": 46837898.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.069533491134644,
|
|
"epoch": 1.997022036926742,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004610672573186029,
|
|
"loss": 4.6078,
|
|
"mean_token_accuracy": 0.23407213240861893,
|
|
"num_tokens": 46853574.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.055312395095825,
|
|
"epoch": 1.9976176295413937,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046104329492104967,
|
|
"loss": 4.6254,
|
|
"mean_token_accuracy": 0.2318499431014061,
|
|
"num_tokens": 46869010.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.1276720523834225,
|
|
"epoch": 1.9982132221560454,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046101932585042597,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.2232221394777298,
|
|
"num_tokens": 46882326.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.092624521255493,
|
|
"epoch": 1.9988088147706968,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004609953501075915,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.22137695997953416,
|
|
"num_tokens": 46897216.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.079944229125976,
|
|
"epoch": 1.9994044073853483,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004609713676934062,
|
|
"loss": 4.6088,
|
|
"mean_token_accuracy": 0.22534349858760833,
|
|
"num_tokens": 46908774.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.14406795501709,
|
|
"epoch": 2.0,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004609473786087303,
|
|
"loss": 4.7272,
|
|
"mean_token_accuracy": 0.22310903817415237,
|
|
"num_tokens": 46922024.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.057645797729492,
|
|
"epoch": 2.0005955926146517,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004609233828544243,
|
|
"loss": 4.5419,
|
|
"mean_token_accuracy": 0.23367615789175034,
|
|
"num_tokens": 46934779.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.008983087539673,
|
|
"epoch": 2.001191185229303,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004608993804313489,
|
|
"loss": 4.531,
|
|
"mean_token_accuracy": 0.2303295001387596,
|
|
"num_tokens": 46950779.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.0656736373901365,
|
|
"epoch": 2.0017867778439546,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046087537134036484,
|
|
"loss": 4.5668,
|
|
"mean_token_accuracy": 0.23550090044736863,
|
|
"num_tokens": 46964897.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.120574855804444,
|
|
"epoch": 2.0023823704586063,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046085135558233357,
|
|
"loss": 4.5745,
|
|
"mean_token_accuracy": 0.23043115437030792,
|
|
"num_tokens": 46978201.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.048690748214722,
|
|
"epoch": 2.002977963073258,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046082733315811625,
|
|
"loss": 4.5673,
|
|
"mean_token_accuracy": 0.23312937319278718,
|
|
"num_tokens": 46992259.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 4.95126895904541,
|
|
"epoch": 2.0035735556879093,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046080330406857465,
|
|
"loss": 4.4546,
|
|
"mean_token_accuracy": 0.2421011969447136,
|
|
"num_tokens": 47005229.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.028235149383545,
|
|
"epoch": 2.004169148302561,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046077926831457073,
|
|
"loss": 4.5813,
|
|
"mean_token_accuracy": 0.23342529237270354,
|
|
"num_tokens": 47016671.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.052181911468506,
|
|
"epoch": 2.0047647409172127,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046075522589696636,
|
|
"loss": 4.48,
|
|
"mean_token_accuracy": 0.2391958490014076,
|
|
"num_tokens": 47031350.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.054667043685913,
|
|
"epoch": 2.0053603335318644,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046073117681662414,
|
|
"loss": 4.5895,
|
|
"mean_token_accuracy": 0.22979890257120134,
|
|
"num_tokens": 47043965.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.068663501739502,
|
|
"epoch": 2.0059559261465156,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004607071210744066,
|
|
"loss": 4.508,
|
|
"mean_token_accuracy": 0.23833304047584533,
|
|
"num_tokens": 47058140.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 4.9904200553894045,
|
|
"epoch": 2.0065515187611673,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046068305867117657,
|
|
"loss": 4.3876,
|
|
"mean_token_accuracy": 0.2573079526424408,
|
|
"num_tokens": 47072144.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.030803966522217,
|
|
"epoch": 2.007147111375819,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046065898960779704,
|
|
"loss": 4.5567,
|
|
"mean_token_accuracy": 0.22944639176130294,
|
|
"num_tokens": 47087917.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.014895820617676,
|
|
"epoch": 2.0077427039904707,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046063491388513144,
|
|
"loss": 4.4932,
|
|
"mean_token_accuracy": 0.23702369630336761,
|
|
"num_tokens": 47102494.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.019677686691284,
|
|
"epoch": 2.008338296605122,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004606108315040434,
|
|
"loss": 4.566,
|
|
"mean_token_accuracy": 0.23130310475826263,
|
|
"num_tokens": 47115749.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 4.998718404769898,
|
|
"epoch": 2.0089338892197737,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046058674246539653,
|
|
"loss": 4.547,
|
|
"mean_token_accuracy": 0.23552756756544113,
|
|
"num_tokens": 47130350.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.161088657379151,
|
|
"epoch": 2.0095294818344254,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004605626467700551,
|
|
"loss": 4.6068,
|
|
"mean_token_accuracy": 0.2299022912979126,
|
|
"num_tokens": 47144075.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.065914154052734,
|
|
"epoch": 2.0101250744490766,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046053854441888305,
|
|
"loss": 4.5817,
|
|
"mean_token_accuracy": 0.23250654190778733,
|
|
"num_tokens": 47156434.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 4.959687614440918,
|
|
"epoch": 2.0107206670637283,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004605144354127451,
|
|
"loss": 4.446,
|
|
"mean_token_accuracy": 0.237794491648674,
|
|
"num_tokens": 47169218.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.019824361801147,
|
|
"epoch": 2.01131625967838,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000460490319752506,
|
|
"loss": 4.5212,
|
|
"mean_token_accuracy": 0.23605496436357498,
|
|
"num_tokens": 47181517.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.087242317199707,
|
|
"epoch": 2.0119118522930317,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00046046619743903087,
|
|
"loss": 4.5868,
|
|
"mean_token_accuracy": 0.2249603673815727,
|
|
"num_tokens": 47195837.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.0313498973846436,
|
|
"epoch": 2.012507444907683,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046044206847318457,
|
|
"loss": 4.5689,
|
|
"mean_token_accuracy": 0.23527771085500718,
|
|
"num_tokens": 47211186.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.069920349121094,
|
|
"epoch": 2.0131030375223347,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004604179328558329,
|
|
"loss": 4.5435,
|
|
"mean_token_accuracy": 0.2404427096247673,
|
|
"num_tokens": 47225737.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.220113372802734,
|
|
"epoch": 2.0136986301369864,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004603937905878414,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.2219761684536934,
|
|
"num_tokens": 47238202.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.023685646057129,
|
|
"epoch": 2.014294222751638,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046036964167007615,
|
|
"loss": 4.5202,
|
|
"mean_token_accuracy": 0.23996281176805495,
|
|
"num_tokens": 47251757.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.045433521270752,
|
|
"epoch": 2.0148898153662893,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00046034548610340316,
|
|
"loss": 4.6024,
|
|
"mean_token_accuracy": 0.23324510008096694,
|
|
"num_tokens": 47268089.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.103947448730469,
|
|
"epoch": 2.015485407980941,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046032132388868895,
|
|
"loss": 4.6117,
|
|
"mean_token_accuracy": 0.23109029680490495,
|
|
"num_tokens": 47282542.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.085128355026245,
|
|
"epoch": 2.0160810005955927,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004602971550268002,
|
|
"loss": 4.6027,
|
|
"mean_token_accuracy": 0.23370055109262466,
|
|
"num_tokens": 47295592.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.041429281234741,
|
|
"epoch": 2.0166765932102444,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004602729795186038,
|
|
"loss": 4.5812,
|
|
"mean_token_accuracy": 0.23514838963747026,
|
|
"num_tokens": 47310737.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.05506706237793,
|
|
"epoch": 2.0172721858248956,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046024879736496677,
|
|
"loss": 4.5584,
|
|
"mean_token_accuracy": 0.2356592446565628,
|
|
"num_tokens": 47323904.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.011358737945557,
|
|
"epoch": 2.0178677784395473,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046022460856675663,
|
|
"loss": 4.4336,
|
|
"mean_token_accuracy": 0.24735228568315507,
|
|
"num_tokens": 47337253.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.0084997653961185,
|
|
"epoch": 2.018463371054199,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004602004131248409,
|
|
"loss": 4.4635,
|
|
"mean_token_accuracy": 0.24327898174524307,
|
|
"num_tokens": 47351634.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.070017290115357,
|
|
"epoch": 2.0190589636688503,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004601762110400875,
|
|
"loss": 4.5614,
|
|
"mean_token_accuracy": 0.23420994281768798,
|
|
"num_tokens": 47364984.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.073600578308105,
|
|
"epoch": 2.019654556283502,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046015200231336453,
|
|
"loss": 4.5797,
|
|
"mean_token_accuracy": 0.22897316068410872,
|
|
"num_tokens": 47379357.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.079392147064209,
|
|
"epoch": 2.0202501488981537,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004601277869455402,
|
|
"loss": 4.6394,
|
|
"mean_token_accuracy": 0.22717951536178588,
|
|
"num_tokens": 47394088.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.007873916625977,
|
|
"epoch": 2.0208457415128054,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046010356493748325,
|
|
"loss": 4.4782,
|
|
"mean_token_accuracy": 0.24869678169488907,
|
|
"num_tokens": 47406896.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.1033735275268555,
|
|
"epoch": 2.0214413341274566,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00046007933629006227,
|
|
"loss": 4.6279,
|
|
"mean_token_accuracy": 0.2263318732380867,
|
|
"num_tokens": 47422990.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.052951765060425,
|
|
"epoch": 2.0220369267421083,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004600551010041464,
|
|
"loss": 4.5581,
|
|
"mean_token_accuracy": 0.23400393277406692,
|
|
"num_tokens": 47437239.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.11246919631958,
|
|
"epoch": 2.02263251935676,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046003085908060505,
|
|
"loss": 4.5871,
|
|
"mean_token_accuracy": 0.22851316928863524,
|
|
"num_tokens": 47452930.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 4.965039348602295,
|
|
"epoch": 2.0232281119714117,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046000661052030765,
|
|
"loss": 4.4794,
|
|
"mean_token_accuracy": 0.24365232437849044,
|
|
"num_tokens": 47464453.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.00722827911377,
|
|
"epoch": 2.023823704586063,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004599823553241238,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.23969842344522477,
|
|
"num_tokens": 47478856.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.06428165435791,
|
|
"epoch": 2.0244192972007147,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004599580934929237,
|
|
"loss": 4.5341,
|
|
"mean_token_accuracy": 0.2352534905076027,
|
|
"num_tokens": 47493910.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.0621583461761475,
|
|
"epoch": 2.0250148898153664,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004599338250275775,
|
|
"loss": 4.547,
|
|
"mean_token_accuracy": 0.23384436815977097,
|
|
"num_tokens": 47506169.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.014513158798218,
|
|
"epoch": 2.025610482430018,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045990954992895566,
|
|
"loss": 4.495,
|
|
"mean_token_accuracy": 0.2375449299812317,
|
|
"num_tokens": 47519379.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.060106468200684,
|
|
"epoch": 2.0262060750446693,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00045988526819792897,
|
|
"loss": 4.5057,
|
|
"mean_token_accuracy": 0.2343178927898407,
|
|
"num_tokens": 47533054.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.031157064437866,
|
|
"epoch": 2.026801667659321,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004598609798353683,
|
|
"loss": 4.5539,
|
|
"mean_token_accuracy": 0.23219063878059387,
|
|
"num_tokens": 47546377.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 4.98444185256958,
|
|
"epoch": 2.0273972602739727,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004598366848421447,
|
|
"loss": 4.506,
|
|
"mean_token_accuracy": 0.23457171618938447,
|
|
"num_tokens": 47559232.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.027819061279297,
|
|
"epoch": 2.027992852888624,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004598123832191299,
|
|
"loss": 4.5572,
|
|
"mean_token_accuracy": 0.2386604905128479,
|
|
"num_tokens": 47573415.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.0699859142303465,
|
|
"epoch": 2.0285884455032757,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004597880749671954,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.22797466367483138,
|
|
"num_tokens": 47588199.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.060103702545166,
|
|
"epoch": 2.0291840381179274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045976376008721303,
|
|
"loss": 4.5095,
|
|
"mean_token_accuracy": 0.23336162865161897,
|
|
"num_tokens": 47602595.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.136521053314209,
|
|
"epoch": 2.029779630732579,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000459739438580055,
|
|
"loss": 4.6638,
|
|
"mean_token_accuracy": 0.22343652397394181,
|
|
"num_tokens": 47616162.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.087084531784058,
|
|
"epoch": 2.0303752233472303,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00045971511044659374,
|
|
"loss": 4.5733,
|
|
"mean_token_accuracy": 0.2278608947992325,
|
|
"num_tokens": 47631199.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.0193901538848875,
|
|
"epoch": 2.030970815961882,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004596907756877018,
|
|
"loss": 4.508,
|
|
"mean_token_accuracy": 0.23978840410709382,
|
|
"num_tokens": 47645256.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.03636417388916,
|
|
"epoch": 2.0315664085765337,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045966643430425197,
|
|
"loss": 4.5594,
|
|
"mean_token_accuracy": 0.2381669968366623,
|
|
"num_tokens": 47657938.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 4.980867910385132,
|
|
"epoch": 2.0321620011911854,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004596420862971174,
|
|
"loss": 4.5505,
|
|
"mean_token_accuracy": 0.23148486465215684,
|
|
"num_tokens": 47672823.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.020447444915772,
|
|
"epoch": 2.0327575938058366,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004596177316671714,
|
|
"loss": 4.5575,
|
|
"mean_token_accuracy": 0.2314867004752159,
|
|
"num_tokens": 47685348.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.029134511947632,
|
|
"epoch": 2.0333531864204883,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045959337041528753,
|
|
"loss": 4.5682,
|
|
"mean_token_accuracy": 0.2365615725517273,
|
|
"num_tokens": 47698488.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.055670928955078,
|
|
"epoch": 2.03394877903514,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004595690025423396,
|
|
"loss": 4.5467,
|
|
"mean_token_accuracy": 0.23940564692020416,
|
|
"num_tokens": 47713158.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.048037481307984,
|
|
"epoch": 2.0345443716497917,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004595446280492017,
|
|
"loss": 4.5696,
|
|
"mean_token_accuracy": 0.23393245935440063,
|
|
"num_tokens": 47727882.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.098673629760742,
|
|
"epoch": 2.035139964264443,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045952024693674795,
|
|
"loss": 4.6423,
|
|
"mean_token_accuracy": 0.22981843054294587,
|
|
"num_tokens": 47742890.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 4.991290283203125,
|
|
"epoch": 2.0357355568790947,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045949585920585304,
|
|
"loss": 4.5278,
|
|
"mean_token_accuracy": 0.23272222727537156,
|
|
"num_tokens": 47757327.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.083459949493408,
|
|
"epoch": 2.0363311494937464,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00045947146485739155,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.2308793142437935,
|
|
"num_tokens": 47772947.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.020419502258301,
|
|
"epoch": 2.036926742108398,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045944706389223854,
|
|
"loss": 4.5189,
|
|
"mean_token_accuracy": 0.23598092496395112,
|
|
"num_tokens": 47785859.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.037325525283814,
|
|
"epoch": 2.0375223347230493,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045942265631126935,
|
|
"loss": 4.5769,
|
|
"mean_token_accuracy": 0.232615926861763,
|
|
"num_tokens": 47799842.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.017747020721435,
|
|
"epoch": 2.038117927337701,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045939824211535925,
|
|
"loss": 4.5518,
|
|
"mean_token_accuracy": 0.2286510705947876,
|
|
"num_tokens": 47812886.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 4.991328287124634,
|
|
"epoch": 2.0387135199523527,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000459373821305384,
|
|
"loss": 4.555,
|
|
"mean_token_accuracy": 0.2357075110077858,
|
|
"num_tokens": 47827684.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 4.981380844116211,
|
|
"epoch": 2.039309112567004,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045934939388221966,
|
|
"loss": 4.5466,
|
|
"mean_token_accuracy": 0.2374630093574524,
|
|
"num_tokens": 47840907.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.1141101837158205,
|
|
"epoch": 2.0399047051816557,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045932495984674223,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.2316589966416359,
|
|
"num_tokens": 47854891.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.094178199768066,
|
|
"epoch": 2.0405002977963074,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045930051919982815,
|
|
"loss": 4.5375,
|
|
"mean_token_accuracy": 0.2378108024597168,
|
|
"num_tokens": 47867084.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.086365795135498,
|
|
"epoch": 2.041095890410959,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004592760719423541,
|
|
"loss": 4.6015,
|
|
"mean_token_accuracy": 0.23523307144641875,
|
|
"num_tokens": 47880892.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.080245590209961,
|
|
"epoch": 2.0416914830256103,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000459251618075197,
|
|
"loss": 4.5923,
|
|
"mean_token_accuracy": 0.23435407876968384,
|
|
"num_tokens": 47893688.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.0482447147369385,
|
|
"epoch": 2.042287075640262,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045922715759923394,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.23009706288576126,
|
|
"num_tokens": 47908415.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.069554948806763,
|
|
"epoch": 2.0428826682549137,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045920269051534225,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.22722838670015336,
|
|
"num_tokens": 47922224.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.08069429397583,
|
|
"epoch": 2.0434782608695654,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00045917821682439955,
|
|
"loss": 4.6161,
|
|
"mean_token_accuracy": 0.2297189012169838,
|
|
"num_tokens": 47935645.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.010673666000367,
|
|
"epoch": 2.0440738534842167,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004591537365272837,
|
|
"loss": 4.5319,
|
|
"mean_token_accuracy": 0.23589843958616258,
|
|
"num_tokens": 47950357.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.032699871063232,
|
|
"epoch": 2.0446694460988684,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045912924962487276,
|
|
"loss": 4.5208,
|
|
"mean_token_accuracy": 0.2343393534421921,
|
|
"num_tokens": 47965930.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.0835357189178465,
|
|
"epoch": 2.04526503871352,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045910475611804486,
|
|
"loss": 4.6635,
|
|
"mean_token_accuracy": 0.22829798907041549,
|
|
"num_tokens": 47979935.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.083349275588989,
|
|
"epoch": 2.0458606313281713,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045908025600767887,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.2299830734729767,
|
|
"num_tokens": 47995648.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.021368741989136,
|
|
"epoch": 2.046456223942823,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004590557492946533,
|
|
"loss": 4.5571,
|
|
"mean_token_accuracy": 0.23541914373636247,
|
|
"num_tokens": 48009613.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.1592369556427,
|
|
"epoch": 2.0470518165574747,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045903123597984725,
|
|
"loss": 4.662,
|
|
"mean_token_accuracy": 0.22605426162481307,
|
|
"num_tokens": 48023032.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.068078660964966,
|
|
"epoch": 2.0476474091721264,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045900671606414003,
|
|
"loss": 4.5497,
|
|
"mean_token_accuracy": 0.242087459564209,
|
|
"num_tokens": 48037202.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 4.99084701538086,
|
|
"epoch": 2.0482430017867777,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000458982189548411,
|
|
"loss": 4.5095,
|
|
"mean_token_accuracy": 0.24101127088069915,
|
|
"num_tokens": 48050373.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.080052280426026,
|
|
"epoch": 2.0488385944014293,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004589576564335401,
|
|
"loss": 4.6536,
|
|
"mean_token_accuracy": 0.22541272789239883,
|
|
"num_tokens": 48064029.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.005568170547486,
|
|
"epoch": 2.049434187016081,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004589331167204071,
|
|
"loss": 4.4722,
|
|
"mean_token_accuracy": 0.24087995588779448,
|
|
"num_tokens": 48077176.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.059876585006714,
|
|
"epoch": 2.0500297796307327,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004589085704098922,
|
|
"loss": 4.5231,
|
|
"mean_token_accuracy": 0.23440787345170974,
|
|
"num_tokens": 48090279.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.065604734420776,
|
|
"epoch": 2.050625372245384,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000458884017502876,
|
|
"loss": 4.5547,
|
|
"mean_token_accuracy": 0.23468409180641175,
|
|
"num_tokens": 48103650.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.074661684036255,
|
|
"epoch": 2.0512209648600357,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00045885945800023896,
|
|
"loss": 4.5748,
|
|
"mean_token_accuracy": 0.22964215278625488,
|
|
"num_tokens": 48119197.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.034805345535278,
|
|
"epoch": 2.0518165574746874,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045883489190286214,
|
|
"loss": 4.6022,
|
|
"mean_token_accuracy": 0.2273664027452469,
|
|
"num_tokens": 48134326.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.1038566589355465,
|
|
"epoch": 2.052412150089339,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004588103192116267,
|
|
"loss": 4.6152,
|
|
"mean_token_accuracy": 0.23392213582992555,
|
|
"num_tokens": 48149277.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.071701097488403,
|
|
"epoch": 2.0530077427039903,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004587857399274139,
|
|
"loss": 4.6064,
|
|
"mean_token_accuracy": 0.22914573699235916,
|
|
"num_tokens": 48162443.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 4.991318655014038,
|
|
"epoch": 2.053603335318642,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004587611540511055,
|
|
"loss": 4.4249,
|
|
"mean_token_accuracy": 0.24859565049409865,
|
|
"num_tokens": 48175537.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.02416672706604,
|
|
"epoch": 2.0541989279332937,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004587365615835832,
|
|
"loss": 4.5815,
|
|
"mean_token_accuracy": 0.23042218536138534,
|
|
"num_tokens": 48191976.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.052055788040161,
|
|
"epoch": 2.0547945205479454,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004587119625257292,
|
|
"loss": 4.6062,
|
|
"mean_token_accuracy": 0.23405972719192505,
|
|
"num_tokens": 48204891.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.022945690155029,
|
|
"epoch": 2.0553901131625967,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045868735687842584,
|
|
"loss": 4.5219,
|
|
"mean_token_accuracy": 0.23259375393390655,
|
|
"num_tokens": 48217957.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 4.983803462982178,
|
|
"epoch": 2.0559857057772484,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004586627446425556,
|
|
"loss": 4.5258,
|
|
"mean_token_accuracy": 0.25417167842388155,
|
|
"num_tokens": 48231605.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.026793622970581,
|
|
"epoch": 2.0565812983919,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004586381258190013,
|
|
"loss": 4.5213,
|
|
"mean_token_accuracy": 0.2347990795969963,
|
|
"num_tokens": 48245887.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.0565589427947994,
|
|
"epoch": 2.0571768910065513,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004586135004086461,
|
|
"loss": 4.5955,
|
|
"mean_token_accuracy": 0.22935987561941146,
|
|
"num_tokens": 48259913.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.164794492721557,
|
|
"epoch": 2.057772483621203,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004585888684123731,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.22176842093467714,
|
|
"num_tokens": 48273044.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.069805335998535,
|
|
"epoch": 2.0583680762358547,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004585642298310659,
|
|
"loss": 4.583,
|
|
"mean_token_accuracy": 0.23142746835947037,
|
|
"num_tokens": 48286835.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.0406989574432375,
|
|
"epoch": 2.0589636688505064,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004585395846656083,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.22134874016046524,
|
|
"num_tokens": 48301986.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.08070740699768,
|
|
"epoch": 2.0595592614651577,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004585149329168842,
|
|
"loss": 4.5266,
|
|
"mean_token_accuracy": 0.23880029767751693,
|
|
"num_tokens": 48314994.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.05347695350647,
|
|
"epoch": 2.0601548540798094,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045849027458577776,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.22460439503192903,
|
|
"num_tokens": 48329905.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.0250328540802,
|
|
"epoch": 2.060750446694461,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004584656096731735,
|
|
"loss": 4.5293,
|
|
"mean_token_accuracy": 0.23137685507535935,
|
|
"num_tokens": 48344582.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.147363138198853,
|
|
"epoch": 2.0613460393091128,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045844093817995615,
|
|
"loss": 4.6528,
|
|
"mean_token_accuracy": 0.21721698343753815,
|
|
"num_tokens": 48358373.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.032124710083008,
|
|
"epoch": 2.061941631923764,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045841626010701065,
|
|
"loss": 4.5212,
|
|
"mean_token_accuracy": 0.24188830852508544,
|
|
"num_tokens": 48371911.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.103136730194092,
|
|
"epoch": 2.0625372245384157,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004583915754552221,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.2335794001817703,
|
|
"num_tokens": 48384367.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.157677173614502,
|
|
"epoch": 2.0631328171530674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004583668842254759,
|
|
"loss": 4.6066,
|
|
"mean_token_accuracy": 0.2387697383761406,
|
|
"num_tokens": 48397034.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.048141288757324,
|
|
"epoch": 2.0637284097677187,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004583421864186577,
|
|
"loss": 4.5179,
|
|
"mean_token_accuracy": 0.23990840464830399,
|
|
"num_tokens": 48410451.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 4.9684099674224855,
|
|
"epoch": 2.0643240023823703,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045831748203565333,
|
|
"loss": 4.5725,
|
|
"mean_token_accuracy": 0.23789997398853302,
|
|
"num_tokens": 48424437.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.062968587875366,
|
|
"epoch": 2.064919594997022,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045829277107734895,
|
|
"loss": 4.61,
|
|
"mean_token_accuracy": 0.23247554749250413,
|
|
"num_tokens": 48438979.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.026688957214356,
|
|
"epoch": 2.0655151876116737,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004582680535446309,
|
|
"loss": 4.5601,
|
|
"mean_token_accuracy": 0.23831270039081573,
|
|
"num_tokens": 48450907.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.044146203994751,
|
|
"epoch": 2.066110780226325,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004582433294383858,
|
|
"loss": 4.5331,
|
|
"mean_token_accuracy": 0.23831800520420074,
|
|
"num_tokens": 48466231.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.016358470916748,
|
|
"epoch": 2.0667063728409767,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045821859875950035,
|
|
"loss": 4.5287,
|
|
"mean_token_accuracy": 0.2376201331615448,
|
|
"num_tokens": 48480472.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 4.980524921417237,
|
|
"epoch": 2.0673019654556284,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045819386150886167,
|
|
"loss": 4.4522,
|
|
"mean_token_accuracy": 0.24232326149940492,
|
|
"num_tokens": 48494535.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.071668434143066,
|
|
"epoch": 2.06789755807028,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000458169117687357,
|
|
"loss": 4.6457,
|
|
"mean_token_accuracy": 0.22207711040973663,
|
|
"num_tokens": 48508696.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.149874830245972,
|
|
"epoch": 2.0684931506849313,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004581443672958739,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.22692600935697554,
|
|
"num_tokens": 48521868.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.013295269012451,
|
|
"epoch": 2.069088743299583,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045811961033530014,
|
|
"loss": 4.5144,
|
|
"mean_token_accuracy": 0.23632737398147582,
|
|
"num_tokens": 48535710.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.026894617080688,
|
|
"epoch": 2.0696843359142347,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00045809484680652376,
|
|
"loss": 4.5846,
|
|
"mean_token_accuracy": 0.23552584499120713,
|
|
"num_tokens": 48550868.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.0455903053283695,
|
|
"epoch": 2.0702799285288864,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004580700767104328,
|
|
"loss": 4.5528,
|
|
"mean_token_accuracy": 0.23570671379566194,
|
|
"num_tokens": 48564827.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.0581409454345705,
|
|
"epoch": 2.0708755211435377,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045804530004791595,
|
|
"loss": 4.5501,
|
|
"mean_token_accuracy": 0.23649201393127442,
|
|
"num_tokens": 48578790.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.013926315307617,
|
|
"epoch": 2.0714711137581894,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004580205168198617,
|
|
"loss": 4.5299,
|
|
"mean_token_accuracy": 0.24725954383611679,
|
|
"num_tokens": 48592327.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.035023593902588,
|
|
"epoch": 2.072066706372841,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004579957270271592,
|
|
"loss": 4.5058,
|
|
"mean_token_accuracy": 0.23424022197723388,
|
|
"num_tokens": 48606830.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.073780632019043,
|
|
"epoch": 2.0726622989874928,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045797093067069734,
|
|
"loss": 4.5287,
|
|
"mean_token_accuracy": 0.24079985171556473,
|
|
"num_tokens": 48621790.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.0218493938446045,
|
|
"epoch": 2.073257891602144,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045794612775136584,
|
|
"loss": 4.548,
|
|
"mean_token_accuracy": 0.23799565732479094,
|
|
"num_tokens": 48636738.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.053096199035645,
|
|
"epoch": 2.0738534842167957,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004579213182700541,
|
|
"loss": 4.5433,
|
|
"mean_token_accuracy": 0.23865682184696196,
|
|
"num_tokens": 48651254.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.132093811035157,
|
|
"epoch": 2.0744490768314474,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004578965022276521,
|
|
"loss": 4.6694,
|
|
"mean_token_accuracy": 0.21636623591184617,
|
|
"num_tokens": 48666527.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.0832030296325685,
|
|
"epoch": 2.0750446694460987,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004578716796250501,
|
|
"loss": 4.6179,
|
|
"mean_token_accuracy": 0.22743384838104247,
|
|
"num_tokens": 48680005.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.110458087921143,
|
|
"epoch": 2.0756402620607504,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045784685046313804,
|
|
"loss": 4.6398,
|
|
"mean_token_accuracy": 0.22779723703861238,
|
|
"num_tokens": 48692819.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.179143953323364,
|
|
"epoch": 2.076235854675402,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045782201474280684,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.22386670410633086,
|
|
"num_tokens": 48706480.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.078287124633789,
|
|
"epoch": 2.0768314472900538,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045779717246494724,
|
|
"loss": 4.6959,
|
|
"mean_token_accuracy": 0.22110174149274825,
|
|
"num_tokens": 48719720.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.011696767807007,
|
|
"epoch": 2.077427039904705,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004577723236304503,
|
|
"loss": 4.5146,
|
|
"mean_token_accuracy": 0.24303217977285385,
|
|
"num_tokens": 48731388.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.084980201721192,
|
|
"epoch": 2.0780226325193567,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004577474682402072,
|
|
"loss": 4.5723,
|
|
"mean_token_accuracy": 0.23822213262319564,
|
|
"num_tokens": 48746595.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.153842782974243,
|
|
"epoch": 2.0786182251340084,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004577226062951096,
|
|
"loss": 4.6222,
|
|
"mean_token_accuracy": 0.2266036957502365,
|
|
"num_tokens": 48762067.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.090154933929443,
|
|
"epoch": 2.07921381774866,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004576977377960492,
|
|
"loss": 4.6719,
|
|
"mean_token_accuracy": 0.2237592965364456,
|
|
"num_tokens": 48775913.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 4.998254060745239,
|
|
"epoch": 2.0798094103633114,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004576728627439179,
|
|
"loss": 4.5049,
|
|
"mean_token_accuracy": 0.23999334871768951,
|
|
"num_tokens": 48790291.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.052488374710083,
|
|
"epoch": 2.080405002977963,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004576479811396082,
|
|
"loss": 4.5465,
|
|
"mean_token_accuracy": 0.2334999918937683,
|
|
"num_tokens": 48804235.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.117841291427612,
|
|
"epoch": 2.0810005955926147,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004576230929840123,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.2278003215789795,
|
|
"num_tokens": 48819634.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.089445018768311,
|
|
"epoch": 2.0815961882072664,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004575981982780229,
|
|
"loss": 4.5654,
|
|
"mean_token_accuracy": 0.23474422693252564,
|
|
"num_tokens": 48835654.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.108015298843384,
|
|
"epoch": 2.0821917808219177,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004575732970225331,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.2268066242337227,
|
|
"num_tokens": 48851374.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.039049100875855,
|
|
"epoch": 2.0827873734365694,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045754838921843597,
|
|
"loss": 4.4992,
|
|
"mean_token_accuracy": 0.24061862081289292,
|
|
"num_tokens": 48865024.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.096379709243775,
|
|
"epoch": 2.083382966051221,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004575234748666249,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.22643850445747377,
|
|
"num_tokens": 48878552.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.139949035644531,
|
|
"epoch": 2.0839785586658723,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004574985539679936,
|
|
"loss": 4.5837,
|
|
"mean_token_accuracy": 0.23100059926509858,
|
|
"num_tokens": 48891701.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 4.966013622283936,
|
|
"epoch": 2.084574151280524,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045747362652343585,
|
|
"loss": 4.4422,
|
|
"mean_token_accuracy": 0.24675652831792833,
|
|
"num_tokens": 48903961.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.062184858322143,
|
|
"epoch": 2.0851697438951757,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004574486925338458,
|
|
"loss": 4.599,
|
|
"mean_token_accuracy": 0.2309477373957634,
|
|
"num_tokens": 48918240.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.117518424987793,
|
|
"epoch": 2.0857653365098274,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004574237520001178,
|
|
"loss": 4.6038,
|
|
"mean_token_accuracy": 0.22770583033561706,
|
|
"num_tokens": 48932558.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.032974481582642,
|
|
"epoch": 2.0863609291244787,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045739880492314645,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.24104645997285842,
|
|
"num_tokens": 48947267.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.14728627204895,
|
|
"epoch": 2.0869565217391304,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004573738513038265,
|
|
"loss": 4.652,
|
|
"mean_token_accuracy": 0.22392976731061937,
|
|
"num_tokens": 48962811.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.095992374420166,
|
|
"epoch": 2.087552114353782,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000457348891143053,
|
|
"loss": 4.6286,
|
|
"mean_token_accuracy": 0.2229553446173668,
|
|
"num_tokens": 48975589.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.09865984916687,
|
|
"epoch": 2.0881477069684338,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004573239244417213,
|
|
"loss": 4.6007,
|
|
"mean_token_accuracy": 0.23470126390457152,
|
|
"num_tokens": 48987634.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.050380897521973,
|
|
"epoch": 2.088743299583085,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004572989512007268,
|
|
"loss": 4.5444,
|
|
"mean_token_accuracy": 0.2393022283911705,
|
|
"num_tokens": 49001023.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.055418395996094,
|
|
"epoch": 2.0893388921977367,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045727397142096543,
|
|
"loss": 4.5178,
|
|
"mean_token_accuracy": 0.234603251516819,
|
|
"num_tokens": 49015326.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.0431811809539795,
|
|
"epoch": 2.0899344848123884,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000457248985103333,
|
|
"loss": 4.5814,
|
|
"mean_token_accuracy": 0.22916839569807052,
|
|
"num_tokens": 49029798.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.15162239074707,
|
|
"epoch": 2.09053007742704,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004572239922487259,
|
|
"loss": 4.6459,
|
|
"mean_token_accuracy": 0.22854827493429183,
|
|
"num_tokens": 49043600.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.095768451690674,
|
|
"epoch": 2.0911256700416914,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045719899285804027,
|
|
"loss": 4.627,
|
|
"mean_token_accuracy": 0.23597129732370375,
|
|
"num_tokens": 49057213.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.06793098449707,
|
|
"epoch": 2.091721262656343,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045717398693217315,
|
|
"loss": 4.5916,
|
|
"mean_token_accuracy": 0.22470258325338363,
|
|
"num_tokens": 49071835.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.104105234146118,
|
|
"epoch": 2.0923168552709948,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045714897447202125,
|
|
"loss": 4.5699,
|
|
"mean_token_accuracy": 0.2370709165930748,
|
|
"num_tokens": 49083944.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.060418176651001,
|
|
"epoch": 2.092912447885646,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045712395547848185,
|
|
"loss": 4.5982,
|
|
"mean_token_accuracy": 0.23609945476055144,
|
|
"num_tokens": 49097576.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.112945890426635,
|
|
"epoch": 2.0935080405002977,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004570989299524523,
|
|
"loss": 4.6407,
|
|
"mean_token_accuracy": 0.23601873070001603,
|
|
"num_tokens": 49109580.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.104486751556396,
|
|
"epoch": 2.0941036331149494,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045707389789483016,
|
|
"loss": 4.5884,
|
|
"mean_token_accuracy": 0.23334723562002183,
|
|
"num_tokens": 49123646.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.034723472595215,
|
|
"epoch": 2.094699225729601,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004570488593065133,
|
|
"loss": 4.5463,
|
|
"mean_token_accuracy": 0.2356327846646309,
|
|
"num_tokens": 49137764.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.062044763565064,
|
|
"epoch": 2.0952948183442524,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004570238141883999,
|
|
"loss": 4.6036,
|
|
"mean_token_accuracy": 0.22722508311271666,
|
|
"num_tokens": 49151024.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.127727413177491,
|
|
"epoch": 2.095890410958904,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045699876254138823,
|
|
"loss": 4.6365,
|
|
"mean_token_accuracy": 0.22133959233760833,
|
|
"num_tokens": 49167439.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.025001144409179,
|
|
"epoch": 2.0964860035735557,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004569737043663768,
|
|
"loss": 4.5305,
|
|
"mean_token_accuracy": 0.2361663833260536,
|
|
"num_tokens": 49180856.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.056779432296753,
|
|
"epoch": 2.0970815961882074,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004569486396642645,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.2286345198750496,
|
|
"num_tokens": 49192577.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 4.986841773986816,
|
|
"epoch": 2.0976771888028587,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004569235684359504,
|
|
"loss": 4.489,
|
|
"mean_token_accuracy": 0.24036170393228531,
|
|
"num_tokens": 49208026.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.071071624755859,
|
|
"epoch": 2.0982727814175104,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004568984906823337,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.23572920858860016,
|
|
"num_tokens": 49221688.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.0969799041748045,
|
|
"epoch": 2.098868374032162,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00045687340640431374,
|
|
"loss": 4.5834,
|
|
"mean_token_accuracy": 0.22931289225816726,
|
|
"num_tokens": 49237537.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.080524158477783,
|
|
"epoch": 2.099463966646814,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004568483156027905,
|
|
"loss": 4.5528,
|
|
"mean_token_accuracy": 0.24047911912202835,
|
|
"num_tokens": 49250586.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.021454238891602,
|
|
"epoch": 2.100059559261465,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045682321827866383,
|
|
"loss": 4.5504,
|
|
"mean_token_accuracy": 0.23472087681293488,
|
|
"num_tokens": 49263579.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.037905597686768,
|
|
"epoch": 2.1006551518761167,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000456798114432834,
|
|
"loss": 4.5129,
|
|
"mean_token_accuracy": 0.2408007875084877,
|
|
"num_tokens": 49275967.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.08129768371582,
|
|
"epoch": 2.1012507444907684,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004567730040662013,
|
|
"loss": 4.5713,
|
|
"mean_token_accuracy": 0.23113982528448104,
|
|
"num_tokens": 49290178.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.083538293838501,
|
|
"epoch": 2.1018463371054197,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004567478871796665,
|
|
"loss": 4.619,
|
|
"mean_token_accuracy": 0.22840074747800826,
|
|
"num_tokens": 49302167.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.088832092285156,
|
|
"epoch": 2.1024419297200714,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045672276377413054,
|
|
"loss": 4.5642,
|
|
"mean_token_accuracy": 0.23438835740089417,
|
|
"num_tokens": 49316965.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.103084754943848,
|
|
"epoch": 2.103037522334723,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004566976338504945,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.22764303386211396,
|
|
"num_tokens": 49330670.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.073578929901123,
|
|
"epoch": 2.1036331149493748,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004566724974096597,
|
|
"loss": 4.5677,
|
|
"mean_token_accuracy": 0.23484709858894348,
|
|
"num_tokens": 49343786.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.0272575378417965,
|
|
"epoch": 2.104228707564026,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004566473544525279,
|
|
"loss": 4.5477,
|
|
"mean_token_accuracy": 0.22945298701524736,
|
|
"num_tokens": 49358668.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.033445882797241,
|
|
"epoch": 2.1048243001786777,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004566222049800008,
|
|
"loss": 4.5741,
|
|
"mean_token_accuracy": 0.23150084614753724,
|
|
"num_tokens": 49372127.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 4.997094297409058,
|
|
"epoch": 2.1054198927933294,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00045659704899298045,
|
|
"loss": 4.556,
|
|
"mean_token_accuracy": 0.23529333919286727,
|
|
"num_tokens": 49387579.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.0900074481964115,
|
|
"epoch": 2.106015485407981,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004565718864923693,
|
|
"loss": 4.6399,
|
|
"mean_token_accuracy": 0.23222732096910476,
|
|
"num_tokens": 49400306.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.0812249183654785,
|
|
"epoch": 2.1066110780226324,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004565467174790697,
|
|
"loss": 4.5668,
|
|
"mean_token_accuracy": 0.2335207000374794,
|
|
"num_tokens": 49413735.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.099720859527588,
|
|
"epoch": 2.107206670637284,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004565215419539846,
|
|
"loss": 4.6409,
|
|
"mean_token_accuracy": 0.23019631952047348,
|
|
"num_tokens": 49428554.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.0524779796600345,
|
|
"epoch": 2.1078022632519358,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045649635991801686,
|
|
"loss": 4.5008,
|
|
"mean_token_accuracy": 0.2397008165717125,
|
|
"num_tokens": 49441694.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.084787750244141,
|
|
"epoch": 2.1083978558665875,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004564711713720698,
|
|
"loss": 4.6272,
|
|
"mean_token_accuracy": 0.223720920085907,
|
|
"num_tokens": 49455222.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.196303272247315,
|
|
"epoch": 2.1089934484812387,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004564459763170469,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.22008481174707412,
|
|
"num_tokens": 49468768.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.073131418228149,
|
|
"epoch": 2.1095890410958904,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045642077475385186,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.23152164965867997,
|
|
"num_tokens": 49481399.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.06300983428955,
|
|
"epoch": 2.110184633710542,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045639556668338854,
|
|
"loss": 4.5492,
|
|
"mean_token_accuracy": 0.23341643661260605,
|
|
"num_tokens": 49496392.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 4.99938325881958,
|
|
"epoch": 2.1107802263251934,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045637035210656124,
|
|
"loss": 4.5094,
|
|
"mean_token_accuracy": 0.2430122286081314,
|
|
"num_tokens": 49509126.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.075080108642578,
|
|
"epoch": 2.111375818939845,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045634513102427426,
|
|
"loss": 4.6423,
|
|
"mean_token_accuracy": 0.22525354772806166,
|
|
"num_tokens": 49522913.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.071659851074219,
|
|
"epoch": 2.1119714115544967,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004563199034374323,
|
|
"loss": 4.5633,
|
|
"mean_token_accuracy": 0.23299697190523147,
|
|
"num_tokens": 49536593.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.070428514480591,
|
|
"epoch": 2.1125670041691484,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004562946693469402,
|
|
"loss": 4.5541,
|
|
"mean_token_accuracy": 0.22611355483531953,
|
|
"num_tokens": 49551032.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.086341476440429,
|
|
"epoch": 2.1131625967837997,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004562694287537031,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.2326162964105606,
|
|
"num_tokens": 49564159.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.1049662113189695,
|
|
"epoch": 2.1137581893984514,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045624418165862626,
|
|
"loss": 4.654,
|
|
"mean_token_accuracy": 0.22560494691133498,
|
|
"num_tokens": 49577426.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.078585147857666,
|
|
"epoch": 2.114353782013103,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004562189280626154,
|
|
"loss": 4.5788,
|
|
"mean_token_accuracy": 0.23211335837841035,
|
|
"num_tokens": 49592020.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.002594709396362,
|
|
"epoch": 2.114949374627755,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004561936679665761,
|
|
"loss": 4.4955,
|
|
"mean_token_accuracy": 0.2405523344874382,
|
|
"num_tokens": 49606203.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.01050295829773,
|
|
"epoch": 2.115544967242406,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004561684013714147,
|
|
"loss": 4.5453,
|
|
"mean_token_accuracy": 0.23398784399032593,
|
|
"num_tokens": 49620951.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.083518171310425,
|
|
"epoch": 2.1161405598570577,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004561431282780372,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.2312988206744194,
|
|
"num_tokens": 49636864.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.080377626419067,
|
|
"epoch": 2.1167361524717094,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045611784868735024,
|
|
"loss": 4.5924,
|
|
"mean_token_accuracy": 0.22632975727319718,
|
|
"num_tokens": 49650839.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.142970895767212,
|
|
"epoch": 2.117331745086361,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004560925626002605,
|
|
"loss": 4.6137,
|
|
"mean_token_accuracy": 0.22540777325630187,
|
|
"num_tokens": 49665920.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.044984436035156,
|
|
"epoch": 2.1179273377010124,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000456067270017675,
|
|
"loss": 4.6056,
|
|
"mean_token_accuracy": 0.2353798344731331,
|
|
"num_tokens": 49680789.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.052900886535644,
|
|
"epoch": 2.118522930315664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045604197094050087,
|
|
"loss": 4.5506,
|
|
"mean_token_accuracy": 0.2289200559258461,
|
|
"num_tokens": 49693069.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.073904085159302,
|
|
"epoch": 2.1191185229303158,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004560166653696457,
|
|
"loss": 4.648,
|
|
"mean_token_accuracy": 0.22913205474615098,
|
|
"num_tokens": 49709958.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.134455156326294,
|
|
"epoch": 2.1197141155449675,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000455991353306017,
|
|
"loss": 4.6678,
|
|
"mean_token_accuracy": 0.2277326315641403,
|
|
"num_tokens": 49723107.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.08301157951355,
|
|
"epoch": 2.1203097081596187,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004559660347505228,
|
|
"loss": 4.5583,
|
|
"mean_token_accuracy": 0.23249375373125075,
|
|
"num_tokens": 49738715.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.07455415725708,
|
|
"epoch": 2.1209053007742704,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000455940709704071,
|
|
"loss": 4.5971,
|
|
"mean_token_accuracy": 0.2218799725174904,
|
|
"num_tokens": 49752244.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 4.964584541320801,
|
|
"epoch": 2.121500893388922,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045591537816757027,
|
|
"loss": 4.4645,
|
|
"mean_token_accuracy": 0.2396186724305153,
|
|
"num_tokens": 49766303.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.041434955596924,
|
|
"epoch": 2.1220964860035734,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045589004014192903,
|
|
"loss": 4.4577,
|
|
"mean_token_accuracy": 0.24134083837270737,
|
|
"num_tokens": 49782254.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.034451198577881,
|
|
"epoch": 2.122692078618225,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045586469562805624,
|
|
"loss": 4.5584,
|
|
"mean_token_accuracy": 0.23398327976465225,
|
|
"num_tokens": 49797329.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.029845380783081,
|
|
"epoch": 2.1232876712328768,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004558393446268608,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.23140426129102706,
|
|
"num_tokens": 49810732.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.064167070388794,
|
|
"epoch": 2.1238832638475285,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004558139871392521,
|
|
"loss": 4.5827,
|
|
"mean_token_accuracy": 0.2295352727174759,
|
|
"num_tokens": 49827098.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 4.999539756774903,
|
|
"epoch": 2.1244788564621797,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004557886231661396,
|
|
"loss": 4.5399,
|
|
"mean_token_accuracy": 0.23892841935157777,
|
|
"num_tokens": 49841563.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.053615665435791,
|
|
"epoch": 2.1250744490768314,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045576325270843326,
|
|
"loss": 4.5814,
|
|
"mean_token_accuracy": 0.22965654283761977,
|
|
"num_tokens": 49855890.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.031672477722168,
|
|
"epoch": 2.125670041691483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004557378757670429,
|
|
"loss": 4.4736,
|
|
"mean_token_accuracy": 0.24788672626018524,
|
|
"num_tokens": 49869146.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.076297855377197,
|
|
"epoch": 2.126265634306135,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004557124923428788,
|
|
"loss": 4.5755,
|
|
"mean_token_accuracy": 0.2320940986275673,
|
|
"num_tokens": 49882940.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.123354959487915,
|
|
"epoch": 2.126861226920786,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004556871024368514,
|
|
"loss": 4.6233,
|
|
"mean_token_accuracy": 0.22325791865587236,
|
|
"num_tokens": 49897588.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.025477123260498,
|
|
"epoch": 2.1274568195354377,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045566170604987145,
|
|
"loss": 4.4951,
|
|
"mean_token_accuracy": 0.23638061285018921,
|
|
"num_tokens": 49910848.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.027909660339356,
|
|
"epoch": 2.1280524121500894,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004556363031828498,
|
|
"loss": 4.5847,
|
|
"mean_token_accuracy": 0.22652654945850373,
|
|
"num_tokens": 49926178.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.082362508773803,
|
|
"epoch": 2.1286480047647407,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045561089383669776,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.23856547027826308,
|
|
"num_tokens": 49940774.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.0295452117919925,
|
|
"epoch": 2.1292435973793924,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004555854780123265,
|
|
"loss": 4.5037,
|
|
"mean_token_accuracy": 0.23689173012971879,
|
|
"num_tokens": 49954573.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.075212621688843,
|
|
"epoch": 2.129839189994044,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004555600557106477,
|
|
"loss": 4.6266,
|
|
"mean_token_accuracy": 0.22851035445928575,
|
|
"num_tokens": 49967087.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.081135988235474,
|
|
"epoch": 2.130434782608696,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004555346269325734,
|
|
"loss": 4.5605,
|
|
"mean_token_accuracy": 0.23639562726020813,
|
|
"num_tokens": 49979147.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.075621318817139,
|
|
"epoch": 2.131030375223347,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045550919167901553,
|
|
"loss": 4.6283,
|
|
"mean_token_accuracy": 0.23497457951307296,
|
|
"num_tokens": 49991389.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.0272376537323,
|
|
"epoch": 2.1316259678379987,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004554837499508864,
|
|
"loss": 4.5054,
|
|
"mean_token_accuracy": 0.23860665857791902,
|
|
"num_tokens": 50004803.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.07566876411438,
|
|
"epoch": 2.1322215604526504,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004554583017490987,
|
|
"loss": 4.6532,
|
|
"mean_token_accuracy": 0.22996504753828048,
|
|
"num_tokens": 50018012.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.2261841773986815,
|
|
"epoch": 2.132817153067302,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045543284707456514,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.22456900924444198,
|
|
"num_tokens": 50033246.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.0336707592010494,
|
|
"epoch": 2.1334127456819534,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004554073859281986,
|
|
"loss": 4.5424,
|
|
"mean_token_accuracy": 0.2289934366941452,
|
|
"num_tokens": 50046392.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.064195966720581,
|
|
"epoch": 2.134008338296605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004553819183109125,
|
|
"loss": 4.6485,
|
|
"mean_token_accuracy": 0.22089705467224122,
|
|
"num_tokens": 50059342.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.049706029891968,
|
|
"epoch": 2.1346039309112568,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045535644422362026,
|
|
"loss": 4.5747,
|
|
"mean_token_accuracy": 0.23001881390810014,
|
|
"num_tokens": 50072787.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.002912425994873,
|
|
"epoch": 2.1351995235259085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045533096366723563,
|
|
"loss": 4.5421,
|
|
"mean_token_accuracy": 0.2378961905837059,
|
|
"num_tokens": 50085305.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.089179563522339,
|
|
"epoch": 2.1357951161405597,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004553054766426725,
|
|
"loss": 4.662,
|
|
"mean_token_accuracy": 0.2262948840856552,
|
|
"num_tokens": 50100974.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.047670364379883,
|
|
"epoch": 2.1363907087552114,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045527998315084513,
|
|
"loss": 4.6003,
|
|
"mean_token_accuracy": 0.2362498715519905,
|
|
"num_tokens": 50113752.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.04225378036499,
|
|
"epoch": 2.136986301369863,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004552544831926679,
|
|
"loss": 4.5497,
|
|
"mean_token_accuracy": 0.233021841943264,
|
|
"num_tokens": 50129337.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.049247360229492,
|
|
"epoch": 2.137581893984515,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045522897676905535,
|
|
"loss": 4.5589,
|
|
"mean_token_accuracy": 0.22988195568323136,
|
|
"num_tokens": 50143268.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.069071531295776,
|
|
"epoch": 2.138177486599166,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004552034638809225,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.22771678119897842,
|
|
"num_tokens": 50158669.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.058134365081787,
|
|
"epoch": 2.1387730792138178,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004551779445291843,
|
|
"loss": 4.5922,
|
|
"mean_token_accuracy": 0.22944982945919037,
|
|
"num_tokens": 50173191.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.0243682861328125,
|
|
"epoch": 2.1393686718284695,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045515241871475634,
|
|
"loss": 4.4854,
|
|
"mean_token_accuracy": 0.23426883518695832,
|
|
"num_tokens": 50188527.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.080678081512451,
|
|
"epoch": 2.1399642644431207,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004551268864385539,
|
|
"loss": 4.6385,
|
|
"mean_token_accuracy": 0.22223408669233322,
|
|
"num_tokens": 50202311.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.139279985427857,
|
|
"epoch": 2.1405598570577724,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000455101347701493,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.23111959546804428,
|
|
"num_tokens": 50217830.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.107001447677613,
|
|
"epoch": 2.141155449672424,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045507580250448955,
|
|
"loss": 4.5475,
|
|
"mean_token_accuracy": 0.2327786222100258,
|
|
"num_tokens": 50230464.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 4.982420921325684,
|
|
"epoch": 2.141751042287076,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004550502508484598,
|
|
"loss": 4.5345,
|
|
"mean_token_accuracy": 0.23705335110425949,
|
|
"num_tokens": 50247201.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.01177282333374,
|
|
"epoch": 2.142346634901727,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004550246927343203,
|
|
"loss": 4.5408,
|
|
"mean_token_accuracy": 0.22863005250692367,
|
|
"num_tokens": 50260618.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.108577632904053,
|
|
"epoch": 2.1429422275163788,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004549991281629879,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.2237588346004486,
|
|
"num_tokens": 50273529.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.1097705364227295,
|
|
"epoch": 2.1435378201310304,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004549735571353793,
|
|
"loss": 4.6965,
|
|
"mean_token_accuracy": 0.22619127184152604,
|
|
"num_tokens": 50287927.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.052711248397827,
|
|
"epoch": 2.144133412745682,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004549479796524119,
|
|
"loss": 4.5687,
|
|
"mean_token_accuracy": 0.23454484045505525,
|
|
"num_tokens": 50301318.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 2.144133412745682,
|
|
"eval_entropy": 4.809880950084675,
|
|
"eval_loss": 4.62203311920166,
|
|
"eval_mean_token_accuracy": 0.24020333918144338,
|
|
"eval_num_tokens": 50301318.0,
|
|
"eval_runtime": 18.6467,
|
|
"eval_samples_per_second": 1368.234,
|
|
"eval_steps_per_second": 171.076,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.085876369476319,
|
|
"epoch": 2.1447290053603334,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045492239571500305,
|
|
"loss": 4.5934,
|
|
"mean_token_accuracy": 0.23278273046016693,
|
|
"num_tokens": 50315160.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.080373334884643,
|
|
"epoch": 2.145324597974985,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004548968053240703,
|
|
"loss": 4.628,
|
|
"mean_token_accuracy": 0.22498273402452468,
|
|
"num_tokens": 50330335.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.0209287166595455,
|
|
"epoch": 2.145920190589637,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045487120848053175,
|
|
"loss": 4.5495,
|
|
"mean_token_accuracy": 0.23654035478830338,
|
|
"num_tokens": 50345693.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.069230270385742,
|
|
"epoch": 2.146515783204288,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004548456051853053,
|
|
"loss": 4.5613,
|
|
"mean_token_accuracy": 0.23501119017601013,
|
|
"num_tokens": 50359261.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.085465574264527,
|
|
"epoch": 2.1471113758189397,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004548199954393095,
|
|
"loss": 4.6521,
|
|
"mean_token_accuracy": 0.23223828822374343,
|
|
"num_tokens": 50373729.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.106818008422851,
|
|
"epoch": 2.1477069684335914,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045479437924346276,
|
|
"loss": 4.5941,
|
|
"mean_token_accuracy": 0.22853723764419556,
|
|
"num_tokens": 50387316.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.087789630889892,
|
|
"epoch": 2.148302561048243,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004547687565986841,
|
|
"loss": 4.6326,
|
|
"mean_token_accuracy": 0.229754339158535,
|
|
"num_tokens": 50401148.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.039290904998779,
|
|
"epoch": 2.1488981536628944,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045474312750589226,
|
|
"loss": 4.5868,
|
|
"mean_token_accuracy": 0.2335609868168831,
|
|
"num_tokens": 50415852.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.0662994384765625,
|
|
"epoch": 2.149493746277546,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045471749196600677,
|
|
"loss": 4.5556,
|
|
"mean_token_accuracy": 0.23162346780300141,
|
|
"num_tokens": 50429634.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.007318496704102,
|
|
"epoch": 2.1500893388921978,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00045469184997994706,
|
|
"loss": 4.5114,
|
|
"mean_token_accuracy": 0.23798431903123857,
|
|
"num_tokens": 50445885.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.063266754150391,
|
|
"epoch": 2.1506849315068495,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045466620154863276,
|
|
"loss": 4.5847,
|
|
"mean_token_accuracy": 0.23405971080064775,
|
|
"num_tokens": 50459914.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.029549980163575,
|
|
"epoch": 2.1512805241215007,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000454640546672984,
|
|
"loss": 4.5472,
|
|
"mean_token_accuracy": 0.23842614144086838,
|
|
"num_tokens": 50473023.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.100028467178345,
|
|
"epoch": 2.1518761167361524,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004546148853539209,
|
|
"loss": 4.6049,
|
|
"mean_token_accuracy": 0.23219924420118332,
|
|
"num_tokens": 50487900.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.02925066947937,
|
|
"epoch": 2.152471709350804,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00045458921759236387,
|
|
"loss": 4.5731,
|
|
"mean_token_accuracy": 0.23205233365297318,
|
|
"num_tokens": 50502757.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.134096240997314,
|
|
"epoch": 2.153067301965456,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004545635433892337,
|
|
"loss": 4.6236,
|
|
"mean_token_accuracy": 0.2290758118033409,
|
|
"num_tokens": 50518636.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.160458564758301,
|
|
"epoch": 2.153662894580107,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045453786274545106,
|
|
"loss": 4.6883,
|
|
"mean_token_accuracy": 0.22507789880037307,
|
|
"num_tokens": 50532210.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.0152613639831545,
|
|
"epoch": 2.1542584871947588,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045451217566193727,
|
|
"loss": 4.5356,
|
|
"mean_token_accuracy": 0.23843728005886078,
|
|
"num_tokens": 50545366.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.156438207626342,
|
|
"epoch": 2.1548540798094105,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004544864821396136,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.22517853677272798,
|
|
"num_tokens": 50560750.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.079514455795288,
|
|
"epoch": 2.155449672424062,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045446078217940155,
|
|
"loss": 4.5889,
|
|
"mean_token_accuracy": 0.23711322844028473,
|
|
"num_tokens": 50575529.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.0531291484832765,
|
|
"epoch": 2.1560452650387134,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045443507578222316,
|
|
"loss": 4.5485,
|
|
"mean_token_accuracy": 0.23688946217298507,
|
|
"num_tokens": 50587989.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.008891296386719,
|
|
"epoch": 2.156640857653365,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045440936294900025,
|
|
"loss": 4.4976,
|
|
"mean_token_accuracy": 0.24256012737751007,
|
|
"num_tokens": 50600656.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 4.905792665481568,
|
|
"epoch": 2.157236450268017,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045438364368065526,
|
|
"loss": 4.4538,
|
|
"mean_token_accuracy": 0.24934490621089936,
|
|
"num_tokens": 50613939.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.066275310516358,
|
|
"epoch": 2.157832042882668,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004543579179781106,
|
|
"loss": 4.5665,
|
|
"mean_token_accuracy": 0.233358296751976,
|
|
"num_tokens": 50627458.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.055052042007446,
|
|
"epoch": 2.1584276354973198,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045433218584228904,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.23850877434015275,
|
|
"num_tokens": 50642433.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 4.992457532882691,
|
|
"epoch": 2.1590232281119714,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004543064472741136,
|
|
"loss": 4.4793,
|
|
"mean_token_accuracy": 0.23703268319368362,
|
|
"num_tokens": 50656708.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.020438480377197,
|
|
"epoch": 2.159618820726623,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004542807022745073,
|
|
"loss": 4.5974,
|
|
"mean_token_accuracy": 0.2308060869574547,
|
|
"num_tokens": 50670404.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.044161605834961,
|
|
"epoch": 2.1602144133412744,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004542549508443938,
|
|
"loss": 4.5543,
|
|
"mean_token_accuracy": 0.23679755479097367,
|
|
"num_tokens": 50684479.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.036929368972778,
|
|
"epoch": 2.160810005955926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045422919298469664,
|
|
"loss": 4.524,
|
|
"mean_token_accuracy": 0.23592234402894974,
|
|
"num_tokens": 50698958.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.064022827148437,
|
|
"epoch": 2.161405598570578,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004542034286963398,
|
|
"loss": 4.598,
|
|
"mean_token_accuracy": 0.23089101016521454,
|
|
"num_tokens": 50711468.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.117631959915161,
|
|
"epoch": 2.1620011911852295,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045417765798024716,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.2294727861881256,
|
|
"num_tokens": 50725864.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.111256790161133,
|
|
"epoch": 2.1625967837998807,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045415188083734346,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.2231511116027832,
|
|
"num_tokens": 50740504.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 4.945083522796631,
|
|
"epoch": 2.1631923764145324,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000454126097268553,
|
|
"loss": 4.4981,
|
|
"mean_token_accuracy": 0.23716579526662826,
|
|
"num_tokens": 50752846.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.07813286781311,
|
|
"epoch": 2.163787969029184,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045410030727480063,
|
|
"loss": 4.6078,
|
|
"mean_token_accuracy": 0.23239888846874238,
|
|
"num_tokens": 50767643.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.070277118682862,
|
|
"epoch": 2.1643835616438354,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045407451085701154,
|
|
"loss": 4.602,
|
|
"mean_token_accuracy": 0.23688225150108339,
|
|
"num_tokens": 50780639.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.015784883499146,
|
|
"epoch": 2.164979154258487,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004540487080161108,
|
|
"loss": 4.6168,
|
|
"mean_token_accuracy": 0.2310093194246292,
|
|
"num_tokens": 50795597.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.09905424118042,
|
|
"epoch": 2.165574746873139,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045402289875302404,
|
|
"loss": 4.6087,
|
|
"mean_token_accuracy": 0.22747467011213302,
|
|
"num_tokens": 50810709.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.134043264389038,
|
|
"epoch": 2.1661703394877905,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000453997083068677,
|
|
"loss": 4.5891,
|
|
"mean_token_accuracy": 0.22608062624931335,
|
|
"num_tokens": 50824952.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.037500286102295,
|
|
"epoch": 2.1667659321024417,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004539712609639956,
|
|
"loss": 4.5743,
|
|
"mean_token_accuracy": 0.24287676811218262,
|
|
"num_tokens": 50838133.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.051697015762329,
|
|
"epoch": 2.1673615247170934,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004539454324399061,
|
|
"loss": 4.5541,
|
|
"mean_token_accuracy": 0.23157846927642822,
|
|
"num_tokens": 50853006.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.121454048156738,
|
|
"epoch": 2.167957117331745,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004539195974973348,
|
|
"loss": 4.645,
|
|
"mean_token_accuracy": 0.2239707201719284,
|
|
"num_tokens": 50867484.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.063731575012207,
|
|
"epoch": 2.168552709946397,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004538937561372086,
|
|
"loss": 4.5563,
|
|
"mean_token_accuracy": 0.23384938687086104,
|
|
"num_tokens": 50881323.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.058006238937378,
|
|
"epoch": 2.169148302561048,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045386790836045407,
|
|
"loss": 4.5633,
|
|
"mean_token_accuracy": 0.2325719937682152,
|
|
"num_tokens": 50894411.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.046675348281861,
|
|
"epoch": 2.1697438951756998,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004538420541679986,
|
|
"loss": 4.5943,
|
|
"mean_token_accuracy": 0.23297786116600036,
|
|
"num_tokens": 50909344.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.029067516326904,
|
|
"epoch": 2.1703394877903515,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004538161935607693,
|
|
"loss": 4.5581,
|
|
"mean_token_accuracy": 0.23312807232141494,
|
|
"num_tokens": 50923610.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.1141876697540285,
|
|
"epoch": 2.170935080405003,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004537903265396939,
|
|
"loss": 4.6332,
|
|
"mean_token_accuracy": 0.2309410825371742,
|
|
"num_tokens": 50938157.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.154739427566528,
|
|
"epoch": 2.1715306730196544,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004537644531057003,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.2227975383400917,
|
|
"num_tokens": 50953983.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.082137680053711,
|
|
"epoch": 2.172126265634306,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045373857325971636,
|
|
"loss": 4.5306,
|
|
"mean_token_accuracy": 0.23428149968385698,
|
|
"num_tokens": 50967630.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.077449655532837,
|
|
"epoch": 2.172721858248958,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045371268700267035,
|
|
"loss": 4.6171,
|
|
"mean_token_accuracy": 0.23098869770765304,
|
|
"num_tokens": 50982437.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.017802000045776,
|
|
"epoch": 2.1733174508636095,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004536867943354909,
|
|
"loss": 4.5096,
|
|
"mean_token_accuracy": 0.23856113404035567,
|
|
"num_tokens": 50996549.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.003601837158203,
|
|
"epoch": 2.1739130434782608,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045366089525910664,
|
|
"loss": 4.538,
|
|
"mean_token_accuracy": 0.23501924127340318,
|
|
"num_tokens": 51012182.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.13463249206543,
|
|
"epoch": 2.1745086360929125,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045363498977444655,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.22343092858791352,
|
|
"num_tokens": 51026115.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.10126314163208,
|
|
"epoch": 2.175104228707564,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004536090778824398,
|
|
"loss": 4.6353,
|
|
"mean_token_accuracy": 0.2267118811607361,
|
|
"num_tokens": 51039685.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.045271158218384,
|
|
"epoch": 2.1756998213222154,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045358315958401584,
|
|
"loss": 4.5531,
|
|
"mean_token_accuracy": 0.23306339234113693,
|
|
"num_tokens": 51052613.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.108397769927978,
|
|
"epoch": 2.176295413936867,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045355723488010435,
|
|
"loss": 4.5954,
|
|
"mean_token_accuracy": 0.23533149808645248,
|
|
"num_tokens": 51066941.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.145059728622437,
|
|
"epoch": 2.176891006551519,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045353130377163514,
|
|
"loss": 4.6243,
|
|
"mean_token_accuracy": 0.22601768374443054,
|
|
"num_tokens": 51081495.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.091873073577881,
|
|
"epoch": 2.1774865991661705,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004535053662595383,
|
|
"loss": 4.6514,
|
|
"mean_token_accuracy": 0.2253038167953491,
|
|
"num_tokens": 51096030.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.017023277282715,
|
|
"epoch": 2.1780821917808217,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045347942234474426,
|
|
"loss": 4.5499,
|
|
"mean_token_accuracy": 0.23833788931369781,
|
|
"num_tokens": 51109183.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.014598321914673,
|
|
"epoch": 2.1786777843954734,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004534534720281835,
|
|
"loss": 4.5371,
|
|
"mean_token_accuracy": 0.23020009696483612,
|
|
"num_tokens": 51122882.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.099009990692139,
|
|
"epoch": 2.179273377010125,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004534275153107868,
|
|
"loss": 4.6242,
|
|
"mean_token_accuracy": 0.23245882987976074,
|
|
"num_tokens": 51136593.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.103371715545654,
|
|
"epoch": 2.179868969624777,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045340155219348536,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.2298986703157425,
|
|
"num_tokens": 51153092.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.023465967178344,
|
|
"epoch": 2.180464562239428,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004533755826772102,
|
|
"loss": 4.5299,
|
|
"mean_token_accuracy": 0.23785023689270018,
|
|
"num_tokens": 51167191.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.0319243431091305,
|
|
"epoch": 2.18106015485408,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004533496067628929,
|
|
"loss": 4.5904,
|
|
"mean_token_accuracy": 0.23343528360128402,
|
|
"num_tokens": 51180310.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.063798236846924,
|
|
"epoch": 2.1816557474687315,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004533236244514652,
|
|
"loss": 4.5892,
|
|
"mean_token_accuracy": 0.23079952150583266,
|
|
"num_tokens": 51195249.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.03086576461792,
|
|
"epoch": 2.182251340083383,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045329763574385905,
|
|
"loss": 4.4856,
|
|
"mean_token_accuracy": 0.2374698653817177,
|
|
"num_tokens": 51207651.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.070770502090454,
|
|
"epoch": 2.1828469326980344,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045327164064100654,
|
|
"loss": 4.5607,
|
|
"mean_token_accuracy": 0.23138114362955092,
|
|
"num_tokens": 51219106.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.0740907192230225,
|
|
"epoch": 2.183442525312686,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00045324563914384024,
|
|
"loss": 4.5822,
|
|
"mean_token_accuracy": 0.2314831018447876,
|
|
"num_tokens": 51234509.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.078743839263916,
|
|
"epoch": 2.184038117927338,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004532196312532926,
|
|
"loss": 4.524,
|
|
"mean_token_accuracy": 0.23115333616733552,
|
|
"num_tokens": 51248284.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.050457096099853,
|
|
"epoch": 2.184633710541989,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004531936169702966,
|
|
"loss": 4.6045,
|
|
"mean_token_accuracy": 0.23079912960529328,
|
|
"num_tokens": 51260433.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.029037714004517,
|
|
"epoch": 2.1852293031566408,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004531675962957853,
|
|
"loss": 4.5813,
|
|
"mean_token_accuracy": 0.2290792480111122,
|
|
"num_tokens": 51272196.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.117112684249878,
|
|
"epoch": 2.1858248957712925,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004531415692306919,
|
|
"loss": 4.6648,
|
|
"mean_token_accuracy": 0.22803814560174943,
|
|
"num_tokens": 51284883.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.018735074996949,
|
|
"epoch": 2.186420488385944,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004531155357759501,
|
|
"loss": 4.5022,
|
|
"mean_token_accuracy": 0.23586077392101287,
|
|
"num_tokens": 51299547.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 4.942069864273071,
|
|
"epoch": 2.1870160810005954,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004530894959324937,
|
|
"loss": 4.4708,
|
|
"mean_token_accuracy": 0.24465154707431794,
|
|
"num_tokens": 51313385.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.113283014297485,
|
|
"epoch": 2.187611673615247,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045306344970125656,
|
|
"loss": 4.5971,
|
|
"mean_token_accuracy": 0.23375592976808549,
|
|
"num_tokens": 51325605.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.013584470748901,
|
|
"epoch": 2.188207266229899,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045303739708317303,
|
|
"loss": 4.5093,
|
|
"mean_token_accuracy": 0.23892022669315338,
|
|
"num_tokens": 51338977.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.129869031906128,
|
|
"epoch": 2.1888028588445505,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004530113380791775,
|
|
"loss": 4.6423,
|
|
"mean_token_accuracy": 0.22019275277853012,
|
|
"num_tokens": 51352536.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.037070226669312,
|
|
"epoch": 2.1893984514592018,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004529852726902047,
|
|
"loss": 4.5427,
|
|
"mean_token_accuracy": 0.23433966487646102,
|
|
"num_tokens": 51366536.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.011381006240844,
|
|
"epoch": 2.1899940440738535,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004529592009171896,
|
|
"loss": 4.4974,
|
|
"mean_token_accuracy": 0.24340590387582778,
|
|
"num_tokens": 51380219.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.030501031875611,
|
|
"epoch": 2.190589636688505,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045293312276106735,
|
|
"loss": 4.5968,
|
|
"mean_token_accuracy": 0.23467277735471725,
|
|
"num_tokens": 51394644.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.020058917999267,
|
|
"epoch": 2.191185229303157,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004529070382227732,
|
|
"loss": 4.4846,
|
|
"mean_token_accuracy": 0.24202847778797149,
|
|
"num_tokens": 51408850.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.047543096542358,
|
|
"epoch": 2.191780821917808,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004528809473032428,
|
|
"loss": 4.5996,
|
|
"mean_token_accuracy": 0.2323126882314682,
|
|
"num_tokens": 51423771.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 4.9458660125732425,
|
|
"epoch": 2.19237641453246,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045285485000341215,
|
|
"loss": 4.4616,
|
|
"mean_token_accuracy": 0.24133758395910263,
|
|
"num_tokens": 51439288.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.0423565864562985,
|
|
"epoch": 2.1929720071471115,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045282874632421717,
|
|
"loss": 4.5921,
|
|
"mean_token_accuracy": 0.23226254433393478,
|
|
"num_tokens": 51454394.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.0787676811218265,
|
|
"epoch": 2.1935675997617627,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004528026362665942,
|
|
"loss": 4.6101,
|
|
"mean_token_accuracy": 0.22355287224054338,
|
|
"num_tokens": 51468604.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.050064182281494,
|
|
"epoch": 2.1941631923764144,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004527765198314798,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.2331220656633377,
|
|
"num_tokens": 51482788.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.033520364761353,
|
|
"epoch": 2.194758784991066,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004527503970198105,
|
|
"loss": 4.5253,
|
|
"mean_token_accuracy": 0.23684919029474258,
|
|
"num_tokens": 51499024.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.027841997146607,
|
|
"epoch": 2.195354377605718,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004527242678325236,
|
|
"loss": 4.5332,
|
|
"mean_token_accuracy": 0.22901611477136613,
|
|
"num_tokens": 51512951.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 4.973797845840454,
|
|
"epoch": 2.195949970220369,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004526981322705562,
|
|
"loss": 4.4649,
|
|
"mean_token_accuracy": 0.2448524460196495,
|
|
"num_tokens": 51526530.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.153202486038208,
|
|
"epoch": 2.196545562835021,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004526719903348457,
|
|
"loss": 4.6535,
|
|
"mean_token_accuracy": 0.22803257703781127,
|
|
"num_tokens": 51540663.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.05274133682251,
|
|
"epoch": 2.1971411554496725,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004526458420263297,
|
|
"loss": 4.5285,
|
|
"mean_token_accuracy": 0.2374642863869667,
|
|
"num_tokens": 51554275.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.05585823059082,
|
|
"epoch": 2.197736748064324,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045261968734594624,
|
|
"loss": 4.6344,
|
|
"mean_token_accuracy": 0.22668208926916122,
|
|
"num_tokens": 51569148.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.091770029067993,
|
|
"epoch": 2.1983323406789754,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045259352629463336,
|
|
"loss": 4.5224,
|
|
"mean_token_accuracy": 0.2368082210421562,
|
|
"num_tokens": 51582391.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.011927080154419,
|
|
"epoch": 2.198927933293627,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004525673588733295,
|
|
"loss": 4.5423,
|
|
"mean_token_accuracy": 0.24222806990146636,
|
|
"num_tokens": 51598635.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.059064292907715,
|
|
"epoch": 2.199523525908279,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004525411850829732,
|
|
"loss": 4.6304,
|
|
"mean_token_accuracy": 0.2281517580151558,
|
|
"num_tokens": 51613169.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.12246150970459,
|
|
"epoch": 2.2001191185229305,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004525150049245032,
|
|
"loss": 4.5765,
|
|
"mean_token_accuracy": 0.229179310798645,
|
|
"num_tokens": 51626675.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.084690904617309,
|
|
"epoch": 2.2007147111375818,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004524888183988586,
|
|
"loss": 4.5556,
|
|
"mean_token_accuracy": 0.23380517363548278,
|
|
"num_tokens": 51640022.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.075265550613404,
|
|
"epoch": 2.2013103037522335,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004524626255069786,
|
|
"loss": 4.6582,
|
|
"mean_token_accuracy": 0.23165358752012252,
|
|
"num_tokens": 51655243.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.097029209136963,
|
|
"epoch": 2.201905896366885,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045243642624980283,
|
|
"loss": 4.6074,
|
|
"mean_token_accuracy": 0.2279600590467453,
|
|
"num_tokens": 51668978.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.072092962265015,
|
|
"epoch": 2.202501488981537,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004524102206282709,
|
|
"loss": 4.5386,
|
|
"mean_token_accuracy": 0.2354093611240387,
|
|
"num_tokens": 51683468.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.060188627243042,
|
|
"epoch": 2.203097081596188,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004523840086433229,
|
|
"loss": 4.5796,
|
|
"mean_token_accuracy": 0.23931190073490144,
|
|
"num_tokens": 51699123.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.06659951210022,
|
|
"epoch": 2.20369267421084,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045235779029589884,
|
|
"loss": 4.588,
|
|
"mean_token_accuracy": 0.23365225940942763,
|
|
"num_tokens": 51712152.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.0868151664733885,
|
|
"epoch": 2.2042882668254915,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045233156558693925,
|
|
"loss": 4.5696,
|
|
"mean_token_accuracy": 0.233111409842968,
|
|
"num_tokens": 51726345.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.007480239868164,
|
|
"epoch": 2.2048838594401428,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004523053345173848,
|
|
"loss": 4.4734,
|
|
"mean_token_accuracy": 0.24109937250614166,
|
|
"num_tokens": 51740155.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.033324384689331,
|
|
"epoch": 2.2054794520547945,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045227909708817613,
|
|
"loss": 4.5685,
|
|
"mean_token_accuracy": 0.22973202019929886,
|
|
"num_tokens": 51753260.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 4.974555778503418,
|
|
"epoch": 2.206075044669446,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004522528533002545,
|
|
"loss": 4.4921,
|
|
"mean_token_accuracy": 0.24118376672267913,
|
|
"num_tokens": 51767367.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.073940229415894,
|
|
"epoch": 2.206670637284098,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045222660315456125,
|
|
"loss": 4.6079,
|
|
"mean_token_accuracy": 0.2356255292892456,
|
|
"num_tokens": 51780350.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.060937833786011,
|
|
"epoch": 2.207266229898749,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045220034665203795,
|
|
"loss": 4.558,
|
|
"mean_token_accuracy": 0.23634615987539292,
|
|
"num_tokens": 51794395.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.020597267150879,
|
|
"epoch": 2.207861822513401,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045217408379362635,
|
|
"loss": 4.5506,
|
|
"mean_token_accuracy": 0.23609842509031295,
|
|
"num_tokens": 51808472.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.021250820159912,
|
|
"epoch": 2.2084574151280525,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045214781458026833,
|
|
"loss": 4.4855,
|
|
"mean_token_accuracy": 0.2423960030078888,
|
|
"num_tokens": 51821744.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.008804178237915,
|
|
"epoch": 2.209053007742704,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004521215390129063,
|
|
"loss": 4.4452,
|
|
"mean_token_accuracy": 0.24769534021615983,
|
|
"num_tokens": 51834695.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.041912364959717,
|
|
"epoch": 2.2096486003573554,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045209525709248257,
|
|
"loss": 4.522,
|
|
"mean_token_accuracy": 0.23778236657381058,
|
|
"num_tokens": 51847676.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.095893383026123,
|
|
"epoch": 2.210244192972007,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045206896881994,
|
|
"loss": 4.6475,
|
|
"mean_token_accuracy": 0.22712986618280412,
|
|
"num_tokens": 51861982.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.060191345214844,
|
|
"epoch": 2.210839785586659,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004520426741962213,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.23766329437494277,
|
|
"num_tokens": 51875671.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.052753162384033,
|
|
"epoch": 2.21143537820131,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045201637322226984,
|
|
"loss": 4.5679,
|
|
"mean_token_accuracy": 0.23025179356336595,
|
|
"num_tokens": 51889695.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.073564195632935,
|
|
"epoch": 2.212030970815962,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045199006589902884,
|
|
"loss": 4.6067,
|
|
"mean_token_accuracy": 0.2329387843608856,
|
|
"num_tokens": 51903390.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.042591857910156,
|
|
"epoch": 2.2126265634306135,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045196375222744195,
|
|
"loss": 4.5858,
|
|
"mean_token_accuracy": 0.23580174893140793,
|
|
"num_tokens": 51917010.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.1470983028411865,
|
|
"epoch": 2.213222156045265,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000451937432208453,
|
|
"loss": 4.6741,
|
|
"mean_token_accuracy": 0.22687569707632066,
|
|
"num_tokens": 51931025.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.080372142791748,
|
|
"epoch": 2.2138177486599164,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000451911105843006,
|
|
"loss": 4.6102,
|
|
"mean_token_accuracy": 0.230636265873909,
|
|
"num_tokens": 51945135.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.050354290008545,
|
|
"epoch": 2.214413341274568,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045188477313204536,
|
|
"loss": 4.5472,
|
|
"mean_token_accuracy": 0.2338612914085388,
|
|
"num_tokens": 51959301.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.049716186523438,
|
|
"epoch": 2.21500893388922,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045185843407651537,
|
|
"loss": 4.5578,
|
|
"mean_token_accuracy": 0.23953416645526887,
|
|
"num_tokens": 51973213.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.073163414001465,
|
|
"epoch": 2.2156045265038715,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045183208867736097,
|
|
"loss": 4.5128,
|
|
"mean_token_accuracy": 0.23709729313850403,
|
|
"num_tokens": 51988208.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 4.990968799591064,
|
|
"epoch": 2.2162001191185228,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045180573693552714,
|
|
"loss": 4.5074,
|
|
"mean_token_accuracy": 0.23541441559791565,
|
|
"num_tokens": 52002708.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.089429521560669,
|
|
"epoch": 2.2167957117331745,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045177937885195884,
|
|
"loss": 4.6194,
|
|
"mean_token_accuracy": 0.23267559558153153,
|
|
"num_tokens": 52017418.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.066135263442993,
|
|
"epoch": 2.217391304347826,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004517530144276018,
|
|
"loss": 4.6125,
|
|
"mean_token_accuracy": 0.23063611537218093,
|
|
"num_tokens": 52033228.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.12373948097229,
|
|
"epoch": 2.217986896962478,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004517266436634014,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.22446052730083466,
|
|
"num_tokens": 52046658.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.020249605178833,
|
|
"epoch": 2.218582489577129,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004517002665603037,
|
|
"loss": 4.4944,
|
|
"mean_token_accuracy": 0.2453988179564476,
|
|
"num_tokens": 52059844.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.046169090270996,
|
|
"epoch": 2.219178082191781,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004516738831192547,
|
|
"loss": 4.5658,
|
|
"mean_token_accuracy": 0.2306638777256012,
|
|
"num_tokens": 52073462.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.098554277420044,
|
|
"epoch": 2.2197736748064325,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00045164749334120074,
|
|
"loss": 4.6096,
|
|
"mean_token_accuracy": 0.2269144132733345,
|
|
"num_tokens": 52089109.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.023102569580078,
|
|
"epoch": 2.220369267421084,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004516210972270885,
|
|
"loss": 4.5863,
|
|
"mean_token_accuracy": 0.22813407629728316,
|
|
"num_tokens": 52101390.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.114339399337768,
|
|
"epoch": 2.2209648600357355,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045159469477786457,
|
|
"loss": 4.6387,
|
|
"mean_token_accuracy": 0.2278708964586258,
|
|
"num_tokens": 52115489.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.143280267715454,
|
|
"epoch": 2.221560452650387,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004515682859944762,
|
|
"loss": 4.6574,
|
|
"mean_token_accuracy": 0.22926288843154907,
|
|
"num_tokens": 52129425.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.137295913696289,
|
|
"epoch": 2.222156045265039,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004515418708778704,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.2245428517460823,
|
|
"num_tokens": 52143119.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.031148910522461,
|
|
"epoch": 2.22275163787969,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004515154494289947,
|
|
"loss": 4.5429,
|
|
"mean_token_accuracy": 0.23599670231342315,
|
|
"num_tokens": 52158569.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.080695486068725,
|
|
"epoch": 2.223347230494342,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045148902164879686,
|
|
"loss": 4.6405,
|
|
"mean_token_accuracy": 0.22856514751911164,
|
|
"num_tokens": 52172141.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.093775081634521,
|
|
"epoch": 2.2239428231089935,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045146258753822475,
|
|
"loss": 4.6282,
|
|
"mean_token_accuracy": 0.22213870733976365,
|
|
"num_tokens": 52185562.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.008696460723877,
|
|
"epoch": 2.224538415723645,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004514361470982266,
|
|
"loss": 4.4809,
|
|
"mean_token_accuracy": 0.24274175763130187,
|
|
"num_tokens": 52199817.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.184663867950439,
|
|
"epoch": 2.2251340083382964,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045140970032975057,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.224713696539402,
|
|
"num_tokens": 52214409.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.125465536117554,
|
|
"epoch": 2.225729600952948,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045138324723374565,
|
|
"loss": 4.6583,
|
|
"mean_token_accuracy": 0.23102642595767975,
|
|
"num_tokens": 52228365.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.027422618865967,
|
|
"epoch": 2.2263251935676,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045135678781116025,
|
|
"loss": 4.5626,
|
|
"mean_token_accuracy": 0.23572589904069902,
|
|
"num_tokens": 52240863.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.010335874557495,
|
|
"epoch": 2.2269207861822515,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045133032206294365,
|
|
"loss": 4.5074,
|
|
"mean_token_accuracy": 0.23823390603065492,
|
|
"num_tokens": 52255664.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.047237348556519,
|
|
"epoch": 2.227516378796903,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004513038499900451,
|
|
"loss": 4.4773,
|
|
"mean_token_accuracy": 0.23878661245107652,
|
|
"num_tokens": 52269246.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.028172349929809,
|
|
"epoch": 2.2281119714115545,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045127737159341406,
|
|
"loss": 4.5806,
|
|
"mean_token_accuracy": 0.23969354331493378,
|
|
"num_tokens": 52281797.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.056362009048462,
|
|
"epoch": 2.228707564026206,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004512508868740004,
|
|
"loss": 4.5713,
|
|
"mean_token_accuracy": 0.2323831558227539,
|
|
"num_tokens": 52297420.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.064774084091186,
|
|
"epoch": 2.2293031566408574,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000451224395832754,
|
|
"loss": 4.5515,
|
|
"mean_token_accuracy": 0.23452610820531844,
|
|
"num_tokens": 52311340.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.014689350128174,
|
|
"epoch": 2.229898749255509,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045119789847062496,
|
|
"loss": 4.5333,
|
|
"mean_token_accuracy": 0.23623991906642913,
|
|
"num_tokens": 52323476.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.05415096282959,
|
|
"epoch": 2.230494341870161,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045117139478856376,
|
|
"loss": 4.5522,
|
|
"mean_token_accuracy": 0.23448999375104904,
|
|
"num_tokens": 52336615.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.028048324584961,
|
|
"epoch": 2.2310899344848125,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004511448847875212,
|
|
"loss": 4.4845,
|
|
"mean_token_accuracy": 0.2408580869436264,
|
|
"num_tokens": 52349864.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.093850231170654,
|
|
"epoch": 2.2316855270994638,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045111836846844795,
|
|
"loss": 4.6656,
|
|
"mean_token_accuracy": 0.22796656042337418,
|
|
"num_tokens": 52363966.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.058377504348755,
|
|
"epoch": 2.2322811197141155,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00045109184583229514,
|
|
"loss": 4.5591,
|
|
"mean_token_accuracy": 0.22826747596263885,
|
|
"num_tokens": 52380348.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.112122392654419,
|
|
"epoch": 2.232876712328767,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045106531688001415,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.22659453004598618,
|
|
"num_tokens": 52394647.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.078737401962281,
|
|
"epoch": 2.233472304943419,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004510387816125566,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.23300707787275315,
|
|
"num_tokens": 52407940.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.083156299591065,
|
|
"epoch": 2.23406789755807,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000451012240030874,
|
|
"loss": 4.6396,
|
|
"mean_token_accuracy": 0.23339663445949554,
|
|
"num_tokens": 52421515.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.085856342315674,
|
|
"epoch": 2.234663490172722,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004509856921359186,
|
|
"loss": 4.6391,
|
|
"mean_token_accuracy": 0.2304915815591812,
|
|
"num_tokens": 52436709.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.081530380249023,
|
|
"epoch": 2.2352590827873735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045095913792864265,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.23262323588132858,
|
|
"num_tokens": 52450225.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 4.997070360183716,
|
|
"epoch": 2.235854675402025,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004509325774099984,
|
|
"loss": 4.5471,
|
|
"mean_token_accuracy": 0.23216598480939865,
|
|
"num_tokens": 52464915.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.037318897247315,
|
|
"epoch": 2.2364502680166765,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045090601058093874,
|
|
"loss": 4.5514,
|
|
"mean_token_accuracy": 0.23153069466352463,
|
|
"num_tokens": 52479246.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.117910242080688,
|
|
"epoch": 2.237045860631328,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004508794374424164,
|
|
"loss": 4.6238,
|
|
"mean_token_accuracy": 0.23028627187013626,
|
|
"num_tokens": 52492359.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.109125185012817,
|
|
"epoch": 2.23764145324598,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004508528579953846,
|
|
"loss": 4.6162,
|
|
"mean_token_accuracy": 0.23263876885175705,
|
|
"num_tokens": 52506075.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.046987915039063,
|
|
"epoch": 2.2382370458606315,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004508262722407968,
|
|
"loss": 4.5732,
|
|
"mean_token_accuracy": 0.23872588574886322,
|
|
"num_tokens": 52521294.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.070922374725342,
|
|
"epoch": 2.238832638475283,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045079968017960637,
|
|
"loss": 4.5507,
|
|
"mean_token_accuracy": 0.23167267441749573,
|
|
"num_tokens": 52534680.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.096469688415527,
|
|
"epoch": 2.2394282310899345,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045077308181276735,
|
|
"loss": 4.5984,
|
|
"mean_token_accuracy": 0.2337322488427162,
|
|
"num_tokens": 52548420.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.024083614349365,
|
|
"epoch": 2.240023823704586,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004507464771412336,
|
|
"loss": 4.4961,
|
|
"mean_token_accuracy": 0.24930352866649627,
|
|
"num_tokens": 52561882.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.009205913543701,
|
|
"epoch": 2.2406194163192374,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045071986616595946,
|
|
"loss": 4.506,
|
|
"mean_token_accuracy": 0.24129388779401778,
|
|
"num_tokens": 52575355.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.016815423965454,
|
|
"epoch": 2.241215008933889,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045069324888789955,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.22479650974273682,
|
|
"num_tokens": 52591125.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.12139253616333,
|
|
"epoch": 2.241810601548541,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045066662530800835,
|
|
"loss": 4.7225,
|
|
"mean_token_accuracy": 0.2207689791917801,
|
|
"num_tokens": 52604160.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.0609382629394535,
|
|
"epoch": 2.2424061941631925,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004506399954272409,
|
|
"loss": 4.5289,
|
|
"mean_token_accuracy": 0.2420847937464714,
|
|
"num_tokens": 52617697.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.009951543807984,
|
|
"epoch": 2.243001786777844,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045061335924655236,
|
|
"loss": 4.5247,
|
|
"mean_token_accuracy": 0.2314124345779419,
|
|
"num_tokens": 52630941.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.214996194839477,
|
|
"epoch": 2.2435973793924955,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004505867167668983,
|
|
"loss": 4.7594,
|
|
"mean_token_accuracy": 0.22477120161056519,
|
|
"num_tokens": 52644699.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.039949226379394,
|
|
"epoch": 2.244192972007147,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004505600679892341,
|
|
"loss": 4.5224,
|
|
"mean_token_accuracy": 0.23710764944553375,
|
|
"num_tokens": 52658617.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.058756160736084,
|
|
"epoch": 2.244788564621799,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045053341291451565,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.22408386021852494,
|
|
"num_tokens": 52672978.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.081331253051758,
|
|
"epoch": 2.24538415723645,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045050675154369917,
|
|
"loss": 4.5842,
|
|
"mean_token_accuracy": 0.2248382717370987,
|
|
"num_tokens": 52685806.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.091321706771851,
|
|
"epoch": 2.245979749851102,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004504800838777408,
|
|
"loss": 4.6214,
|
|
"mean_token_accuracy": 0.2375181332230568,
|
|
"num_tokens": 52699947.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 4.9636119365692135,
|
|
"epoch": 2.2465753424657535,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004504534099175972,
|
|
"loss": 4.4546,
|
|
"mean_token_accuracy": 0.24029117822647095,
|
|
"num_tokens": 52712273.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.054293966293335,
|
|
"epoch": 2.2471709350804048,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045042672966422506,
|
|
"loss": 4.5693,
|
|
"mean_token_accuracy": 0.2375127300620079,
|
|
"num_tokens": 52725579.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.1086265563964846,
|
|
"epoch": 2.2477665276950565,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004504000431185813,
|
|
"loss": 4.5715,
|
|
"mean_token_accuracy": 0.23750897049903869,
|
|
"num_tokens": 52741598.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.129747629165649,
|
|
"epoch": 2.248362120309708,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045037335028162327,
|
|
"loss": 4.585,
|
|
"mean_token_accuracy": 0.2305824339389801,
|
|
"num_tokens": 52755787.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.06435260772705,
|
|
"epoch": 2.24895771292436,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045034665115430817,
|
|
"loss": 4.6264,
|
|
"mean_token_accuracy": 0.22761640697717667,
|
|
"num_tokens": 52767594.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.118099117279053,
|
|
"epoch": 2.249553305539011,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004503199457375939,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.22925592362880706,
|
|
"num_tokens": 52783069.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.025798034667969,
|
|
"epoch": 2.250148898153663,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045029323403243817,
|
|
"loss": 4.5035,
|
|
"mean_token_accuracy": 0.2412623643875122,
|
|
"num_tokens": 52796456.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.0733389377594,
|
|
"epoch": 2.2507444907683145,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004502665160397991,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.23650464713573455,
|
|
"num_tokens": 52809224.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.096809148788452,
|
|
"epoch": 2.251340083382966,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004502397917606352,
|
|
"loss": 4.629,
|
|
"mean_token_accuracy": 0.2307504341006279,
|
|
"num_tokens": 52821943.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.184180688858032,
|
|
"epoch": 2.2519356759976175,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004502130611959048,
|
|
"loss": 4.6719,
|
|
"mean_token_accuracy": 0.22377922087907792,
|
|
"num_tokens": 52835662.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.110401058197022,
|
|
"epoch": 2.252531268612269,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004501863243465668,
|
|
"loss": 4.6523,
|
|
"mean_token_accuracy": 0.22389252483844757,
|
|
"num_tokens": 52849087.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.050496006011963,
|
|
"epoch": 2.253126861226921,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00045015958121358014,
|
|
"loss": 4.5659,
|
|
"mean_token_accuracy": 0.22868042588233947,
|
|
"num_tokens": 52863714.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.111572170257569,
|
|
"epoch": 2.2537224538415725,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004501328317979041,
|
|
"loss": 4.4967,
|
|
"mean_token_accuracy": 0.23890719562768936,
|
|
"num_tokens": 52876319.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.123208332061767,
|
|
"epoch": 2.254318046456224,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004501060761004982,
|
|
"loss": 4.7036,
|
|
"mean_token_accuracy": 0.22213598638772963,
|
|
"num_tokens": 52891005.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.103355026245117,
|
|
"epoch": 2.2549136390708755,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000450079314122322,
|
|
"loss": 4.5601,
|
|
"mean_token_accuracy": 0.23448464423418044,
|
|
"num_tokens": 52904780.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.029092025756836,
|
|
"epoch": 2.255509231685527,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004500525458643355,
|
|
"loss": 4.5149,
|
|
"mean_token_accuracy": 0.23917538672685623,
|
|
"num_tokens": 52917886.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.027967166900635,
|
|
"epoch": 2.256104824300179,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004500257713274988,
|
|
"loss": 4.5909,
|
|
"mean_token_accuracy": 0.23491695821285247,
|
|
"num_tokens": 52931450.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.186659717559815,
|
|
"epoch": 2.25670041691483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044999899051277213,
|
|
"loss": 4.6383,
|
|
"mean_token_accuracy": 0.2326135367155075,
|
|
"num_tokens": 52945434.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.118885612487793,
|
|
"epoch": 2.257296009529482,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044997220342111636,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.22782517373561859,
|
|
"num_tokens": 52959409.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.098511791229248,
|
|
"epoch": 2.2578916021441335,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044994541005349207,
|
|
"loss": 4.6071,
|
|
"mean_token_accuracy": 0.23118131160736083,
|
|
"num_tokens": 52972249.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.138086938858033,
|
|
"epoch": 2.258487194758785,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004499186104108604,
|
|
"loss": 4.6952,
|
|
"mean_token_accuracy": 0.22236647754907607,
|
|
"num_tokens": 52986865.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.024637222290039,
|
|
"epoch": 2.2590827873734365,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044989180449418254,
|
|
"loss": 4.5407,
|
|
"mean_token_accuracy": 0.23086747527122498,
|
|
"num_tokens": 53000096.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.097218418121338,
|
|
"epoch": 2.259678379988088,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044986499230442,
|
|
"loss": 4.6211,
|
|
"mean_token_accuracy": 0.2261293962597847,
|
|
"num_tokens": 53014136.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.020831775665283,
|
|
"epoch": 2.26027397260274,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004498381738425346,
|
|
"loss": 4.4926,
|
|
"mean_token_accuracy": 0.23829548209905624,
|
|
"num_tokens": 53028801.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.102446174621582,
|
|
"epoch": 2.260869565217391,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044981134910948806,
|
|
"loss": 4.6482,
|
|
"mean_token_accuracy": 0.22930533438920975,
|
|
"num_tokens": 53042087.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.084886074066162,
|
|
"epoch": 2.261465157832043,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044978451810624264,
|
|
"loss": 4.5939,
|
|
"mean_token_accuracy": 0.22878779619932174,
|
|
"num_tokens": 53058372.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.064225673675537,
|
|
"epoch": 2.2620607504466945,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044975768083376085,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.22973479479551315,
|
|
"num_tokens": 53075299.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.1142360210418705,
|
|
"epoch": 2.262656343061346,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044973083729300513,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.2255236878991127,
|
|
"num_tokens": 53090702.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.158019971847534,
|
|
"epoch": 2.2632519356759975,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044970398748493836,
|
|
"loss": 4.6158,
|
|
"mean_token_accuracy": 0.23262593746185303,
|
|
"num_tokens": 53104709.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.021278762817383,
|
|
"epoch": 2.263847528290649,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00044967713141052363,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.23224551677703859,
|
|
"num_tokens": 53119191.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.002847146987915,
|
|
"epoch": 2.264443120905301,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004496502690707242,
|
|
"loss": 4.5354,
|
|
"mean_token_accuracy": 0.2386656641960144,
|
|
"num_tokens": 53134424.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.053081703186035,
|
|
"epoch": 2.265038713519952,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044962340046650356,
|
|
"loss": 4.5373,
|
|
"mean_token_accuracy": 0.23453049957752228,
|
|
"num_tokens": 53148233.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.034140348434448,
|
|
"epoch": 2.265634306134604,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004495965255988255,
|
|
"loss": 4.443,
|
|
"mean_token_accuracy": 0.24353149086236953,
|
|
"num_tokens": 53162068.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.120568799972534,
|
|
"epoch": 2.2662298987492555,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004495696444686539,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.22825478315353392,
|
|
"num_tokens": 53177448.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.084431934356689,
|
|
"epoch": 2.266825491363907,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044954275707695304,
|
|
"loss": 4.643,
|
|
"mean_token_accuracy": 0.22853377759456633,
|
|
"num_tokens": 53193368.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.05605525970459,
|
|
"epoch": 2.267421083978559,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00044951586342468727,
|
|
"loss": 4.5094,
|
|
"mean_token_accuracy": 0.241086246073246,
|
|
"num_tokens": 53207924.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.103581190109253,
|
|
"epoch": 2.26801667659321,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004494889635128211,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.22932116091251373,
|
|
"num_tokens": 53220620.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.099059200286865,
|
|
"epoch": 2.268612269207862,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044946205734231967,
|
|
"loss": 4.5994,
|
|
"mean_token_accuracy": 0.2337297409772873,
|
|
"num_tokens": 53232130.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.0531164646148685,
|
|
"epoch": 2.2692078618225136,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00044943514491414783,
|
|
"loss": 4.5357,
|
|
"mean_token_accuracy": 0.23181337863206863,
|
|
"num_tokens": 53246882.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.0461992740631105,
|
|
"epoch": 2.269803454437165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044940822622927093,
|
|
"loss": 4.5784,
|
|
"mean_token_accuracy": 0.23717400580644607,
|
|
"num_tokens": 53259377.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.1043846130371096,
|
|
"epoch": 2.2703990470518165,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044938130128865456,
|
|
"loss": 4.6393,
|
|
"mean_token_accuracy": 0.22671162337064743,
|
|
"num_tokens": 53272249.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.027943325042725,
|
|
"epoch": 2.270994639666468,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004493543700932645,
|
|
"loss": 4.5363,
|
|
"mean_token_accuracy": 0.2371068760752678,
|
|
"num_tokens": 53286131.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.07381534576416,
|
|
"epoch": 2.27159023228112,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004493274326440666,
|
|
"loss": 4.6139,
|
|
"mean_token_accuracy": 0.23474131673574447,
|
|
"num_tokens": 53299097.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.145741701126099,
|
|
"epoch": 2.272185824895771,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004493004889420271,
|
|
"loss": 4.6084,
|
|
"mean_token_accuracy": 0.22935930341482164,
|
|
"num_tokens": 53312345.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.070896577835083,
|
|
"epoch": 2.272781417510423,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004492735389881125,
|
|
"loss": 4.5794,
|
|
"mean_token_accuracy": 0.23162765353918074,
|
|
"num_tokens": 53325661.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.044671821594238,
|
|
"epoch": 2.2733770101250745,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004492465827832894,
|
|
"loss": 4.5379,
|
|
"mean_token_accuracy": 0.23875971138477325,
|
|
"num_tokens": 53337650.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.078966903686523,
|
|
"epoch": 2.2739726027397262,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044921962032852466,
|
|
"loss": 4.6544,
|
|
"mean_token_accuracy": 0.23418206721544266,
|
|
"num_tokens": 53352270.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.029924011230468,
|
|
"epoch": 2.2745681953543775,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004491926516247854,
|
|
"loss": 4.5137,
|
|
"mean_token_accuracy": 0.2378143161535263,
|
|
"num_tokens": 53367077.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.011723756790161,
|
|
"epoch": 2.275163787969029,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000449165676673039,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.23440599590539932,
|
|
"num_tokens": 53380217.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.100679874420166,
|
|
"epoch": 2.275759380583681,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004491386954742529,
|
|
"loss": 4.6198,
|
|
"mean_token_accuracy": 0.22690772265195847,
|
|
"num_tokens": 53393819.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.086169767379761,
|
|
"epoch": 2.276354973198332,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000449111708029395,
|
|
"loss": 4.5671,
|
|
"mean_token_accuracy": 0.23227698653936385,
|
|
"num_tokens": 53407617.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.049292659759521,
|
|
"epoch": 2.276950565812984,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004490847143394332,
|
|
"loss": 4.6064,
|
|
"mean_token_accuracy": 0.23235871344804765,
|
|
"num_tokens": 53420362.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.0413861751556395,
|
|
"epoch": 2.2775461584276355,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004490577144053357,
|
|
"loss": 4.5477,
|
|
"mean_token_accuracy": 0.23546094745397567,
|
|
"num_tokens": 53435285.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.052705383300781,
|
|
"epoch": 2.278141751042287,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000449030708228071,
|
|
"loss": 4.5504,
|
|
"mean_token_accuracy": 0.2338324785232544,
|
|
"num_tokens": 53449274.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.138265705108642,
|
|
"epoch": 2.2787373436569385,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004490036958086078,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.22772389203310012,
|
|
"num_tokens": 53462932.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.038028335571289,
|
|
"epoch": 2.27933293627159,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004489766771479148,
|
|
"loss": 4.5701,
|
|
"mean_token_accuracy": 0.2342698961496353,
|
|
"num_tokens": 53477414.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.039794111251831,
|
|
"epoch": 2.279928528886242,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044894965224696144,
|
|
"loss": 4.625,
|
|
"mean_token_accuracy": 0.22314150482416154,
|
|
"num_tokens": 53490975.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.118505430221558,
|
|
"epoch": 2.2805241215008936,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00044892262110671677,
|
|
"loss": 4.5886,
|
|
"mean_token_accuracy": 0.23714262545108794,
|
|
"num_tokens": 53506982.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.200693225860595,
|
|
"epoch": 2.281119714115545,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004488955837281505,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.2206493839621544,
|
|
"num_tokens": 53521253.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.0698878288269045,
|
|
"epoch": 2.2817153067301965,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044886854011223234,
|
|
"loss": 4.5343,
|
|
"mean_token_accuracy": 0.2361481800675392,
|
|
"num_tokens": 53533893.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.148651647567749,
|
|
"epoch": 2.282310899344848,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004488414902599323,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.22581860423088074,
|
|
"num_tokens": 53548289.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.0233556747436525,
|
|
"epoch": 2.2829064919594995,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044881443417222076,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.22984002232551576,
|
|
"num_tokens": 53561856.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 4.967637300491333,
|
|
"epoch": 2.283502084574151,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044878737185006807,
|
|
"loss": 4.3873,
|
|
"mean_token_accuracy": 0.24241387099027634,
|
|
"num_tokens": 53575091.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.138021850585938,
|
|
"epoch": 2.284097677188803,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004487603032944448,
|
|
"loss": 4.7094,
|
|
"mean_token_accuracy": 0.22777484506368637,
|
|
"num_tokens": 53590138.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.068674373626709,
|
|
"epoch": 2.2846932698034546,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004487332285063221,
|
|
"loss": 4.549,
|
|
"mean_token_accuracy": 0.24176719039678574,
|
|
"num_tokens": 53606784.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.1100564956665036,
|
|
"epoch": 2.2852888624181062,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004487061474866709,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.23196177631616594,
|
|
"num_tokens": 53619111.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.070742416381836,
|
|
"epoch": 2.2858844550327575,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00044867906023646263,
|
|
"loss": 4.6532,
|
|
"mean_token_accuracy": 0.22563338428735732,
|
|
"num_tokens": 53632010.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.118616390228271,
|
|
"epoch": 2.286480047647409,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044865196675666886,
|
|
"loss": 4.6488,
|
|
"mean_token_accuracy": 0.22949382960796355,
|
|
"num_tokens": 53646913.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.12515811920166,
|
|
"epoch": 2.287075640262061,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004486248670482613,
|
|
"loss": 4.6203,
|
|
"mean_token_accuracy": 0.22872216403484344,
|
|
"num_tokens": 53660165.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.041327476501465,
|
|
"epoch": 2.287671232876712,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044859776111221217,
|
|
"loss": 4.6014,
|
|
"mean_token_accuracy": 0.22909582406282425,
|
|
"num_tokens": 53674459.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.10631160736084,
|
|
"epoch": 2.288266825491364,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044857064894949356,
|
|
"loss": 4.6278,
|
|
"mean_token_accuracy": 0.23006758689880372,
|
|
"num_tokens": 53687663.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.095389699935913,
|
|
"epoch": 2.2888624181060155,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000448543530561078,
|
|
"loss": 4.5095,
|
|
"mean_token_accuracy": 0.2389064371585846,
|
|
"num_tokens": 53701101.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 4.98786506652832,
|
|
"epoch": 2.2894580107206672,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004485164059479381,
|
|
"loss": 4.4754,
|
|
"mean_token_accuracy": 0.2449307307600975,
|
|
"num_tokens": 53715631.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.03356900215149,
|
|
"epoch": 2.2900536033353185,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044848927511104695,
|
|
"loss": 4.5652,
|
|
"mean_token_accuracy": 0.24158861935138704,
|
|
"num_tokens": 53729167.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.034671688079834,
|
|
"epoch": 2.29064919594997,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00044846213805137746,
|
|
"loss": 4.4961,
|
|
"mean_token_accuracy": 0.23905833214521408,
|
|
"num_tokens": 53742906.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.053197860717773,
|
|
"epoch": 2.291244788564622,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044843499476990317,
|
|
"loss": 4.6057,
|
|
"mean_token_accuracy": 0.22910828292369842,
|
|
"num_tokens": 53756145.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.043237257003784,
|
|
"epoch": 2.2918403811792736,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004484078452675977,
|
|
"loss": 4.5338,
|
|
"mean_token_accuracy": 0.23227475285530091,
|
|
"num_tokens": 53769980.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.097051286697388,
|
|
"epoch": 2.292435973793925,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004483806895454346,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.22048499435186386,
|
|
"num_tokens": 53783542.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.011335611343384,
|
|
"epoch": 2.2930315664085765,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004483535276043881,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.23619408011436463,
|
|
"num_tokens": 53797849.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.049181795120239,
|
|
"epoch": 2.2936271590232282,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044832635944543243,
|
|
"loss": 4.5507,
|
|
"mean_token_accuracy": 0.24011112600564957,
|
|
"num_tokens": 53811709.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.049682760238648,
|
|
"epoch": 2.2942227516378795,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044829918506954214,
|
|
"loss": 4.5514,
|
|
"mean_token_accuracy": 0.2326733484864235,
|
|
"num_tokens": 53827446.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.077026224136352,
|
|
"epoch": 2.294818344252531,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004482720044776918,
|
|
"loss": 4.6193,
|
|
"mean_token_accuracy": 0.22656889110803605,
|
|
"num_tokens": 53840468.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.006473445892334,
|
|
"epoch": 2.295413936867183,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004482448176708563,
|
|
"loss": 4.4885,
|
|
"mean_token_accuracy": 0.23929773569107055,
|
|
"num_tokens": 53852937.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.0322412014007565,
|
|
"epoch": 2.2960095294818346,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044821762465001096,
|
|
"loss": 4.5814,
|
|
"mean_token_accuracy": 0.23133858144283295,
|
|
"num_tokens": 53865986.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.0562046527862545,
|
|
"epoch": 2.296605122096486,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044819042541613104,
|
|
"loss": 4.6346,
|
|
"mean_token_accuracy": 0.23027096688747406,
|
|
"num_tokens": 53879307.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.0479264736175535,
|
|
"epoch": 2.2972007147111375,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004481632199701921,
|
|
"loss": 4.5156,
|
|
"mean_token_accuracy": 0.2337033897638321,
|
|
"num_tokens": 53894247.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.066580867767334,
|
|
"epoch": 2.297796307325789,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044813600831317016,
|
|
"loss": 4.499,
|
|
"mean_token_accuracy": 0.24139199852943422,
|
|
"num_tokens": 53907467.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.073994207382202,
|
|
"epoch": 2.298391899940441,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00044810879044604094,
|
|
"loss": 4.5634,
|
|
"mean_token_accuracy": 0.23204455226659776,
|
|
"num_tokens": 53922453.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.1002603530883786,
|
|
"epoch": 2.298987492555092,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044808156636978085,
|
|
"loss": 4.6332,
|
|
"mean_token_accuracy": 0.22491869926452637,
|
|
"num_tokens": 53937530.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.041741514205933,
|
|
"epoch": 2.299583085169744,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004480543360853665,
|
|
"loss": 4.5092,
|
|
"mean_token_accuracy": 0.23872604072093964,
|
|
"num_tokens": 53951014.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.02669129371643,
|
|
"epoch": 2.3001786777843956,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044802709959377446,
|
|
"loss": 4.568,
|
|
"mean_token_accuracy": 0.23332428485155104,
|
|
"num_tokens": 53963739.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.07692699432373,
|
|
"epoch": 2.300774270399047,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044799985689598167,
|
|
"loss": 4.6079,
|
|
"mean_token_accuracy": 0.23326285183429718,
|
|
"num_tokens": 53976681.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.125101375579834,
|
|
"epoch": 2.3013698630136985,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044797260799296526,
|
|
"loss": 4.6309,
|
|
"mean_token_accuracy": 0.22984302639961243,
|
|
"num_tokens": 53990910.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.112378787994385,
|
|
"epoch": 2.30196545562835,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044794535288570264,
|
|
"loss": 4.5974,
|
|
"mean_token_accuracy": 0.2295221209526062,
|
|
"num_tokens": 54005311.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.134903526306152,
|
|
"epoch": 2.302561048243002,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004479180915751715,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.22338318228721618,
|
|
"num_tokens": 54017458.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.0738057613372805,
|
|
"epoch": 2.3031566408576536,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044789082406234944,
|
|
"loss": 4.5795,
|
|
"mean_token_accuracy": 0.2331423968076706,
|
|
"num_tokens": 54031072.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.085110330581665,
|
|
"epoch": 2.303752233472305,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004478635503482147,
|
|
"loss": 4.4983,
|
|
"mean_token_accuracy": 0.24204071015119552,
|
|
"num_tokens": 54044742.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.061901712417603,
|
|
"epoch": 2.3043478260869565,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004478362704337454,
|
|
"loss": 4.6179,
|
|
"mean_token_accuracy": 0.22898914366960527,
|
|
"num_tokens": 54058993.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.060177040100098,
|
|
"epoch": 2.3049434187016082,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004478089843199202,
|
|
"loss": 4.6088,
|
|
"mean_token_accuracy": 0.2287194937467575,
|
|
"num_tokens": 54073291.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.107369089126587,
|
|
"epoch": 2.3055390113162595,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044778169200771764,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.23161497563123704,
|
|
"num_tokens": 54087839.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.158960628509521,
|
|
"epoch": 2.306134603930911,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004477543934981167,
|
|
"loss": 4.6696,
|
|
"mean_token_accuracy": 0.22346524894237518,
|
|
"num_tokens": 54103886.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.121478509902954,
|
|
"epoch": 2.306730196545563,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044772708879209654,
|
|
"loss": 4.6385,
|
|
"mean_token_accuracy": 0.22929819524288178,
|
|
"num_tokens": 54118387.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.034396648406982,
|
|
"epoch": 2.3073257891602146,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004476997778906366,
|
|
"loss": 4.5352,
|
|
"mean_token_accuracy": 0.2345580905675888,
|
|
"num_tokens": 54131500.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.061524248123169,
|
|
"epoch": 2.307921381774866,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004476724607947164,
|
|
"loss": 4.6407,
|
|
"mean_token_accuracy": 0.22826731353998184,
|
|
"num_tokens": 54144575.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.107310819625854,
|
|
"epoch": 2.3085169743895175,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004476451375053157,
|
|
"loss": 4.5905,
|
|
"mean_token_accuracy": 0.2287679672241211,
|
|
"num_tokens": 54158883.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.055636835098267,
|
|
"epoch": 2.3091125670041692,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004476178080234147,
|
|
"loss": 4.5478,
|
|
"mean_token_accuracy": 0.2360640972852707,
|
|
"num_tokens": 54171955.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.073064374923706,
|
|
"epoch": 2.309708159618821,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044759047234999363,
|
|
"loss": 4.6052,
|
|
"mean_token_accuracy": 0.2286201000213623,
|
|
"num_tokens": 54190286.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.068883991241455,
|
|
"epoch": 2.310303752233472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004475631304860328,
|
|
"loss": 4.5615,
|
|
"mean_token_accuracy": 0.23355667144060135,
|
|
"num_tokens": 54205577.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.082349157333374,
|
|
"epoch": 2.310899344848124,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044753578243251314,
|
|
"loss": 4.5907,
|
|
"mean_token_accuracy": 0.23214597702026368,
|
|
"num_tokens": 54219385.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.024262857437134,
|
|
"epoch": 2.3114949374627756,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044750842819041547,
|
|
"loss": 4.4824,
|
|
"mean_token_accuracy": 0.24977637976408004,
|
|
"num_tokens": 54231401.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.073494482040405,
|
|
"epoch": 2.312090530077427,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044748106776072103,
|
|
"loss": 4.688,
|
|
"mean_token_accuracy": 0.2196677416563034,
|
|
"num_tokens": 54244852.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.091749668121338,
|
|
"epoch": 2.3126861226920785,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00044745370114441103,
|
|
"loss": 4.5763,
|
|
"mean_token_accuracy": 0.23021861761808396,
|
|
"num_tokens": 54259295.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.1881242275238035,
|
|
"epoch": 2.31328171530673,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044742632834246716,
|
|
"loss": 4.685,
|
|
"mean_token_accuracy": 0.2190784439444542,
|
|
"num_tokens": 54273595.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.135920095443725,
|
|
"epoch": 2.313877307921382,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00044739894935587126,
|
|
"loss": 4.6202,
|
|
"mean_token_accuracy": 0.23420561850070953,
|
|
"num_tokens": 54288122.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.155249547958374,
|
|
"epoch": 2.314472900536033,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044737156418560536,
|
|
"loss": 4.6656,
|
|
"mean_token_accuracy": 0.22998458445072173,
|
|
"num_tokens": 54299901.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.109646797180176,
|
|
"epoch": 2.315068493150685,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004473441728326518,
|
|
"loss": 4.603,
|
|
"mean_token_accuracy": 0.22534194439649582,
|
|
"num_tokens": 54314022.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.0800557136535645,
|
|
"epoch": 2.3156640857653366,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044731677529799286,
|
|
"loss": 4.5852,
|
|
"mean_token_accuracy": 0.23881981670856475,
|
|
"num_tokens": 54328110.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.127986812591553,
|
|
"epoch": 2.3162596783799883,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004472893715826114,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.2224826842546463,
|
|
"num_tokens": 54341087.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.120282316207886,
|
|
"epoch": 2.3168552709946395,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004472619616874903,
|
|
"loss": 4.629,
|
|
"mean_token_accuracy": 0.2361947327852249,
|
|
"num_tokens": 54355922.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.091643667221069,
|
|
"epoch": 2.317450863609291,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004472345456136127,
|
|
"loss": 4.6057,
|
|
"mean_token_accuracy": 0.23320924192667009,
|
|
"num_tokens": 54371577.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.040700531005859,
|
|
"epoch": 2.318046456223943,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044720712336196195,
|
|
"loss": 4.5621,
|
|
"mean_token_accuracy": 0.23407698571681976,
|
|
"num_tokens": 54384586.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.030226182937622,
|
|
"epoch": 2.3186420488385946,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004471796949335217,
|
|
"loss": 4.5725,
|
|
"mean_token_accuracy": 0.22768062502145767,
|
|
"num_tokens": 54398548.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.048391580581665,
|
|
"epoch": 2.319237641453246,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044715226032927585,
|
|
"loss": 4.5638,
|
|
"mean_token_accuracy": 0.2343517556786537,
|
|
"num_tokens": 54413237.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.042281866073608,
|
|
"epoch": 2.3198332340678975,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004471248195502082,
|
|
"loss": 4.4986,
|
|
"mean_token_accuracy": 0.23828287720680236,
|
|
"num_tokens": 54427537.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.029124212265015,
|
|
"epoch": 2.3204288266825492,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044709737259730314,
|
|
"loss": 4.5678,
|
|
"mean_token_accuracy": 0.23415071666240692,
|
|
"num_tokens": 54441120.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.038785791397094,
|
|
"epoch": 2.321024419297201,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004470699194715452,
|
|
"loss": 4.5557,
|
|
"mean_token_accuracy": 0.2330973133444786,
|
|
"num_tokens": 54456303.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.0567436695098875,
|
|
"epoch": 2.321620011911852,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044704246017391897,
|
|
"loss": 4.5,
|
|
"mean_token_accuracy": 0.24026369154453278,
|
|
"num_tokens": 54469854.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.028910875320435,
|
|
"epoch": 2.322215604526504,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004470149947054095,
|
|
"loss": 4.5099,
|
|
"mean_token_accuracy": 0.2400701552629471,
|
|
"num_tokens": 54485080.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.042369365692139,
|
|
"epoch": 2.3228111971411556,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044698752306700175,
|
|
"loss": 4.5096,
|
|
"mean_token_accuracy": 0.23139642626047136,
|
|
"num_tokens": 54497451.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.0771484375,
|
|
"epoch": 2.323406789755807,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004469600452596812,
|
|
"loss": 4.5472,
|
|
"mean_token_accuracy": 0.24101130962371825,
|
|
"num_tokens": 54510681.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.092778015136719,
|
|
"epoch": 2.3240023823704585,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044693256128443336,
|
|
"loss": 4.6152,
|
|
"mean_token_accuracy": 0.230009064078331,
|
|
"num_tokens": 54524231.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.027684211730957,
|
|
"epoch": 2.3245979749851102,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004469050711422442,
|
|
"loss": 4.5253,
|
|
"mean_token_accuracy": 0.23667671233415605,
|
|
"num_tokens": 54538687.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 4.96023588180542,
|
|
"epoch": 2.325193567599762,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044687757483409963,
|
|
"loss": 4.5166,
|
|
"mean_token_accuracy": 0.2460944265127182,
|
|
"num_tokens": 54552917.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.1501987934112545,
|
|
"epoch": 2.325789160214413,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004468500723609859,
|
|
"loss": 4.6855,
|
|
"mean_token_accuracy": 0.22528135627508164,
|
|
"num_tokens": 54566528.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.102973175048828,
|
|
"epoch": 2.326384752829065,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004468225637238894,
|
|
"loss": 4.6163,
|
|
"mean_token_accuracy": 0.229486183822155,
|
|
"num_tokens": 54581812.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 4.985968494415284,
|
|
"epoch": 2.3269803454437166,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000446795048923797,
|
|
"loss": 4.4584,
|
|
"mean_token_accuracy": 0.24031545370817184,
|
|
"num_tokens": 54596118.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.073562669754028,
|
|
"epoch": 2.3275759380583683,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004467675279616955,
|
|
"loss": 4.5368,
|
|
"mean_token_accuracy": 0.22890665978193284,
|
|
"num_tokens": 54610197.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.051004362106323,
|
|
"epoch": 2.3281715306730195,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044674000083857205,
|
|
"loss": 4.4879,
|
|
"mean_token_accuracy": 0.2407570645213127,
|
|
"num_tokens": 54623037.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.01142578125,
|
|
"epoch": 2.328767123287671,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044671246755541397,
|
|
"loss": 4.5062,
|
|
"mean_token_accuracy": 0.2325227826833725,
|
|
"num_tokens": 54636914.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.053097867965699,
|
|
"epoch": 2.329362715902323,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004466849281132089,
|
|
"loss": 4.6052,
|
|
"mean_token_accuracy": 0.22582946866750717,
|
|
"num_tokens": 54652047.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.0405858039855955,
|
|
"epoch": 2.329958308516974,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004466573825129446,
|
|
"loss": 4.5419,
|
|
"mean_token_accuracy": 0.23286224007606507,
|
|
"num_tokens": 54665475.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.011683416366577,
|
|
"epoch": 2.330553901131626,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044662983075560904,
|
|
"loss": 4.5266,
|
|
"mean_token_accuracy": 0.23908064067363738,
|
|
"num_tokens": 54679239.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.088250970840454,
|
|
"epoch": 2.3311494937462776,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044660227284219056,
|
|
"loss": 4.5635,
|
|
"mean_token_accuracy": 0.22949269860982896,
|
|
"num_tokens": 54693327.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.058748340606689,
|
|
"epoch": 2.3317450863609293,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004465747087736775,
|
|
"loss": 4.5994,
|
|
"mean_token_accuracy": 0.22847549021244049,
|
|
"num_tokens": 54707293.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.064195871353149,
|
|
"epoch": 2.332340678975581,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044654713855105864,
|
|
"loss": 4.543,
|
|
"mean_token_accuracy": 0.23326314836740494,
|
|
"num_tokens": 54719706.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.142984676361084,
|
|
"epoch": 2.332936271590232,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004465195621753229,
|
|
"loss": 4.6576,
|
|
"mean_token_accuracy": 0.23199851661920548,
|
|
"num_tokens": 54734802.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.066614818572998,
|
|
"epoch": 2.333531864204884,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044649197964745927,
|
|
"loss": 4.6141,
|
|
"mean_token_accuracy": 0.22903420478105546,
|
|
"num_tokens": 54748048.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.107349491119384,
|
|
"epoch": 2.3341274568195356,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004464643909684571,
|
|
"loss": 4.5807,
|
|
"mean_token_accuracy": 0.2299181878566742,
|
|
"num_tokens": 54763052.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.089812755584717,
|
|
"epoch": 2.334723049434187,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004464367961393061,
|
|
"loss": 4.5904,
|
|
"mean_token_accuracy": 0.22784509807825087,
|
|
"num_tokens": 54776403.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.069285535812378,
|
|
"epoch": 2.3353186420488385,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004464091951609959,
|
|
"loss": 4.6375,
|
|
"mean_token_accuracy": 0.2271212726831436,
|
|
"num_tokens": 54790736.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.125627851486206,
|
|
"epoch": 2.3359142346634902,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004463815880345166,
|
|
"loss": 4.6488,
|
|
"mean_token_accuracy": 0.22574892193078994,
|
|
"num_tokens": 54804756.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.149472761154175,
|
|
"epoch": 2.336509827278142,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044635397476085843,
|
|
"loss": 4.6392,
|
|
"mean_token_accuracy": 0.22748199254274368,
|
|
"num_tokens": 54821156.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.061890411376953,
|
|
"epoch": 2.337105419892793,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044632635534101175,
|
|
"loss": 4.5463,
|
|
"mean_token_accuracy": 0.2348863199353218,
|
|
"num_tokens": 54836658.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.078394031524658,
|
|
"epoch": 2.337701012507445,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044629872977596717,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.2278698593378067,
|
|
"num_tokens": 54849848.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.126906776428223,
|
|
"epoch": 2.3382966051220966,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004462710980667158,
|
|
"loss": 4.6204,
|
|
"mean_token_accuracy": 0.22855122834444047,
|
|
"num_tokens": 54862964.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.162305021286011,
|
|
"epoch": 2.3388921977367483,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004462434602142486,
|
|
"loss": 4.6759,
|
|
"mean_token_accuracy": 0.2279726728796959,
|
|
"num_tokens": 54876893.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.0875297546386715,
|
|
"epoch": 2.3394877903513995,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044621581621955686,
|
|
"loss": 4.6134,
|
|
"mean_token_accuracy": 0.2301342085003853,
|
|
"num_tokens": 54889109.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.145110416412353,
|
|
"epoch": 2.3400833829660512,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004461881660836322,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.23040554523468018,
|
|
"num_tokens": 54904280.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.029517889022827,
|
|
"epoch": 2.340678975580703,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044616050980746634,
|
|
"loss": 4.4639,
|
|
"mean_token_accuracy": 0.24894301891326903,
|
|
"num_tokens": 54917489.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.109511089324951,
|
|
"epoch": 2.341274568195354,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044613284739205124,
|
|
"loss": 4.6188,
|
|
"mean_token_accuracy": 0.2256331741809845,
|
|
"num_tokens": 54930122.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.0347517967224125,
|
|
"epoch": 2.341870160810006,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044610517883837924,
|
|
"loss": 4.5335,
|
|
"mean_token_accuracy": 0.23867109715938567,
|
|
"num_tokens": 54943812.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.094723510742187,
|
|
"epoch": 2.3424657534246576,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004460775041474426,
|
|
"loss": 4.5517,
|
|
"mean_token_accuracy": 0.2385518044233322,
|
|
"num_tokens": 54957617.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.090878629684449,
|
|
"epoch": 2.3430613460393093,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004460498233202341,
|
|
"loss": 4.5493,
|
|
"mean_token_accuracy": 0.2370254248380661,
|
|
"num_tokens": 54970663.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.00463376045227,
|
|
"epoch": 2.3436569386539605,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004460221363577465,
|
|
"loss": 4.4819,
|
|
"mean_token_accuracy": 0.23817128986120223,
|
|
"num_tokens": 54984322.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.004859161376953,
|
|
"epoch": 2.344252531268612,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044599444326097297,
|
|
"loss": 4.4705,
|
|
"mean_token_accuracy": 0.24804508984088897,
|
|
"num_tokens": 54997173.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.080795049667358,
|
|
"epoch": 2.344848123883264,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044596674403090677,
|
|
"loss": 4.5469,
|
|
"mean_token_accuracy": 0.23749467879533767,
|
|
"num_tokens": 55012818.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.080647706985474,
|
|
"epoch": 2.3454437164979156,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004459390386685414,
|
|
"loss": 4.6009,
|
|
"mean_token_accuracy": 0.2358061134815216,
|
|
"num_tokens": 55029483.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.110161209106446,
|
|
"epoch": 2.346039309112567,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004459113271748707,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.22034087628126145,
|
|
"num_tokens": 55043474.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.144142007827758,
|
|
"epoch": 2.3466349017272186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004458836095508886,
|
|
"loss": 4.6479,
|
|
"mean_token_accuracy": 0.23153600543737413,
|
|
"num_tokens": 55058685.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.063829612731934,
|
|
"epoch": 2.3472304943418703,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004458558857975892,
|
|
"loss": 4.5436,
|
|
"mean_token_accuracy": 0.23970397412776948,
|
|
"num_tokens": 55072025.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 4.990268516540527,
|
|
"epoch": 2.3478260869565215,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000445828155915967,
|
|
"loss": 4.4719,
|
|
"mean_token_accuracy": 0.23547677844762802,
|
|
"num_tokens": 55084752.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.024780511856079,
|
|
"epoch": 2.348421679571173,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044580041990701654,
|
|
"loss": 4.5162,
|
|
"mean_token_accuracy": 0.23885871917009355,
|
|
"num_tokens": 55100499.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.0706493854522705,
|
|
"epoch": 2.349017272185825,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004457726777717328,
|
|
"loss": 4.5452,
|
|
"mean_token_accuracy": 0.23087761402130128,
|
|
"num_tokens": 55116702.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.038762044906616,
|
|
"epoch": 2.3496128648004766,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004457449295111108,
|
|
"loss": 4.4952,
|
|
"mean_token_accuracy": 0.2404787853360176,
|
|
"num_tokens": 55129205.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.029953575134277,
|
|
"epoch": 2.3502084574151283,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044571717512614567,
|
|
"loss": 4.5464,
|
|
"mean_token_accuracy": 0.23731295615434647,
|
|
"num_tokens": 55142591.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.0473042011260985,
|
|
"epoch": 2.3508040500297795,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004456894146178331,
|
|
"loss": 4.6034,
|
|
"mean_token_accuracy": 0.23403285592794418,
|
|
"num_tokens": 55155876.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.0682155132293705,
|
|
"epoch": 2.3513996426444312,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004456616479871687,
|
|
"loss": 4.5731,
|
|
"mean_token_accuracy": 0.2331791490316391,
|
|
"num_tokens": 55169829.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.078815364837647,
|
|
"epoch": 2.351995235259083,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044563387523514854,
|
|
"loss": 4.5723,
|
|
"mean_token_accuracy": 0.23714835792779923,
|
|
"num_tokens": 55182983.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.064499378204346,
|
|
"epoch": 2.352590827873734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004456060963627687,
|
|
"loss": 4.5693,
|
|
"mean_token_accuracy": 0.23450487703084946,
|
|
"num_tokens": 55196568.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.046344995498657,
|
|
"epoch": 2.353186420488386,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044557831137102556,
|
|
"loss": 4.5832,
|
|
"mean_token_accuracy": 0.2309361681342125,
|
|
"num_tokens": 55210245.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.039496421813965,
|
|
"epoch": 2.3537820131030376,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044555052026091574,
|
|
"loss": 4.5432,
|
|
"mean_token_accuracy": 0.23654859215021135,
|
|
"num_tokens": 55224158.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.057737922668457,
|
|
"epoch": 2.3543776057176893,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044552272303343603,
|
|
"loss": 4.6054,
|
|
"mean_token_accuracy": 0.23153489977121353,
|
|
"num_tokens": 55237936.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.09548716545105,
|
|
"epoch": 2.3549731983323405,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044549491968958355,
|
|
"loss": 4.5864,
|
|
"mean_token_accuracy": 0.23550266474485398,
|
|
"num_tokens": 55252358.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.029927110671997,
|
|
"epoch": 2.3555687909469922,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044546711023035545,
|
|
"loss": 4.486,
|
|
"mean_token_accuracy": 0.24372150599956513,
|
|
"num_tokens": 55267057.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.018410682678223,
|
|
"epoch": 2.356164383561644,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044543929465674925,
|
|
"loss": 4.5698,
|
|
"mean_token_accuracy": 0.23534005284309387,
|
|
"num_tokens": 55279271.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.160203981399536,
|
|
"epoch": 2.3567599761762956,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044541147296976274,
|
|
"loss": 4.642,
|
|
"mean_token_accuracy": 0.23115628510713576,
|
|
"num_tokens": 55291067.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.063254547119141,
|
|
"epoch": 2.357355568790947,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004453836451703937,
|
|
"loss": 4.5774,
|
|
"mean_token_accuracy": 0.22872448712587357,
|
|
"num_tokens": 55306398.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 4.999613523483276,
|
|
"epoch": 2.3579511614055986,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044535581125964045,
|
|
"loss": 4.519,
|
|
"mean_token_accuracy": 0.23274175375699996,
|
|
"num_tokens": 55319511.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.032390975952149,
|
|
"epoch": 2.3585467540202503,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004453279712385011,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.23928651958703995,
|
|
"num_tokens": 55333033.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.036785125732422,
|
|
"epoch": 2.3591423466349015,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044530012510797447,
|
|
"loss": 4.5276,
|
|
"mean_token_accuracy": 0.23970262408256532,
|
|
"num_tokens": 55345913.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.1246936321258545,
|
|
"epoch": 2.359737939249553,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044527227286905914,
|
|
"loss": 4.5503,
|
|
"mean_token_accuracy": 0.23526620417833327,
|
|
"num_tokens": 55361220.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 4.9926482200622555,
|
|
"epoch": 2.360333531864205,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044524441452275425,
|
|
"loss": 4.5087,
|
|
"mean_token_accuracy": 0.24107636213302613,
|
|
"num_tokens": 55375480.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.0512879371643065,
|
|
"epoch": 2.3609291244788566,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044521655007005907,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.23974285274744034,
|
|
"num_tokens": 55389793.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.076925945281983,
|
|
"epoch": 2.361524717093508,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044518867951197296,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.23844847977161407,
|
|
"num_tokens": 55403206.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.134078550338745,
|
|
"epoch": 2.3621203097081596,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004451608028494956,
|
|
"loss": 4.6077,
|
|
"mean_token_accuracy": 0.23555146008729935,
|
|
"num_tokens": 55417474.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.082880353927612,
|
|
"epoch": 2.3627159023228113,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044513292008362696,
|
|
"loss": 4.5158,
|
|
"mean_token_accuracy": 0.24673154652118684,
|
|
"num_tokens": 55430334.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.081581401824951,
|
|
"epoch": 2.363311494937463,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004451050312153671,
|
|
"loss": 4.6059,
|
|
"mean_token_accuracy": 0.2291390910744667,
|
|
"num_tokens": 55444910.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.097399568557739,
|
|
"epoch": 2.363907087552114,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044507713624571626,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.225383023917675,
|
|
"num_tokens": 55459762.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.0289853572845455,
|
|
"epoch": 2.364502680166766,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044504923517567515,
|
|
"loss": 4.5054,
|
|
"mean_token_accuracy": 0.24067555665969848,
|
|
"num_tokens": 55474865.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.073425245285034,
|
|
"epoch": 2.3650982727814176,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004450213280062444,
|
|
"loss": 4.4845,
|
|
"mean_token_accuracy": 0.2421156644821167,
|
|
"num_tokens": 55488854.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.048632287979126,
|
|
"epoch": 2.365693865396069,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004449934147384251,
|
|
"loss": 4.6171,
|
|
"mean_token_accuracy": 0.23827245086431503,
|
|
"num_tokens": 55501467.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.157009077072144,
|
|
"epoch": 2.3662894580107205,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004449654953732183,
|
|
"loss": 4.6721,
|
|
"mean_token_accuracy": 0.22498213052749633,
|
|
"num_tokens": 55515293.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.039984130859375,
|
|
"epoch": 2.3668850506253722,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004449375699116257,
|
|
"loss": 4.4966,
|
|
"mean_token_accuracy": 0.2398304358124733,
|
|
"num_tokens": 55529103.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.035486030578613,
|
|
"epoch": 2.367480643240024,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004449096383546487,
|
|
"loss": 4.5374,
|
|
"mean_token_accuracy": 0.24302442222833634,
|
|
"num_tokens": 55544299.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.037176656723022,
|
|
"epoch": 2.3680762358546756,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004448817007032892,
|
|
"loss": 4.6121,
|
|
"mean_token_accuracy": 0.22505197674036026,
|
|
"num_tokens": 55560222.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.051385593414307,
|
|
"epoch": 2.368671828469327,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044485375695854927,
|
|
"loss": 4.5188,
|
|
"mean_token_accuracy": 0.23179800659418107,
|
|
"num_tokens": 55573910.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.071458387374878,
|
|
"epoch": 2.3692674210839786,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044482580712143136,
|
|
"loss": 4.5351,
|
|
"mean_token_accuracy": 0.23479315638542175,
|
|
"num_tokens": 55587832.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.08374137878418,
|
|
"epoch": 2.3698630136986303,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044479785119293783,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.23167701065540314,
|
|
"num_tokens": 55601688.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.163956356048584,
|
|
"epoch": 2.3704586063132815,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044476988917407136,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.23376867175102234,
|
|
"num_tokens": 55617693.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.085490608215332,
|
|
"epoch": 2.3710541989279332,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004447419210658351,
|
|
"loss": 4.5146,
|
|
"mean_token_accuracy": 0.23567213267087936,
|
|
"num_tokens": 55633485.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.04327507019043,
|
|
"epoch": 2.371649791542585,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044471394686923206,
|
|
"loss": 4.6006,
|
|
"mean_token_accuracy": 0.2243342101573944,
|
|
"num_tokens": 55648086.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 4.979903936386108,
|
|
"epoch": 2.3722453841572366,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00044468596658526566,
|
|
"loss": 4.5401,
|
|
"mean_token_accuracy": 0.23517804443836213,
|
|
"num_tokens": 55661614.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.120869112014771,
|
|
"epoch": 2.372840976771888,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004446579802149396,
|
|
"loss": 4.6552,
|
|
"mean_token_accuracy": 0.22975039333105088,
|
|
"num_tokens": 55675404.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.137306833267212,
|
|
"epoch": 2.3734365693865396,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00044462998775925757,
|
|
"loss": 4.5869,
|
|
"mean_token_accuracy": 0.226426200568676,
|
|
"num_tokens": 55689872.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.101782608032226,
|
|
"epoch": 2.3740321620011913,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004446019892192237,
|
|
"loss": 4.6214,
|
|
"mean_token_accuracy": 0.2322747990489006,
|
|
"num_tokens": 55706292.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.048449516296387,
|
|
"epoch": 2.374627754615843,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004445739845958423,
|
|
"loss": 4.5004,
|
|
"mean_token_accuracy": 0.24772045910358428,
|
|
"num_tokens": 55719716.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.070455312728882,
|
|
"epoch": 2.375223347230494,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004445459738901177,
|
|
"loss": 4.5992,
|
|
"mean_token_accuracy": 0.23146930038928987,
|
|
"num_tokens": 55734565.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.0959326267242435,
|
|
"epoch": 2.375818939845146,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044451795710305476,
|
|
"loss": 4.6482,
|
|
"mean_token_accuracy": 0.22336234003305436,
|
|
"num_tokens": 55748392.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.1217310428619385,
|
|
"epoch": 2.3764145324597976,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044448993423565824,
|
|
"loss": 4.5619,
|
|
"mean_token_accuracy": 0.2324232503771782,
|
|
"num_tokens": 55762489.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.04377932548523,
|
|
"epoch": 2.377010125074449,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004444619052889334,
|
|
"loss": 4.5518,
|
|
"mean_token_accuracy": 0.2275247409939766,
|
|
"num_tokens": 55777293.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.051957750320435,
|
|
"epoch": 2.3776057176891006,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004444338702638855,
|
|
"loss": 4.5631,
|
|
"mean_token_accuracy": 0.23783262372016906,
|
|
"num_tokens": 55789996.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.097733449935913,
|
|
"epoch": 2.3782013103037523,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004444058291615202,
|
|
"loss": 4.5647,
|
|
"mean_token_accuracy": 0.22830247581005098,
|
|
"num_tokens": 55803205.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.082065725326538,
|
|
"epoch": 2.378796902918404,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004443777819828432,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.23336538672447205,
|
|
"num_tokens": 55816476.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.1674097061157225,
|
|
"epoch": 2.379392495533055,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004443497287288606,
|
|
"loss": 4.6431,
|
|
"mean_token_accuracy": 0.22629370540380478,
|
|
"num_tokens": 55829987.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.024713563919067,
|
|
"epoch": 2.379988088147707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044432166940057855,
|
|
"loss": 4.5175,
|
|
"mean_token_accuracy": 0.23311819285154342,
|
|
"num_tokens": 55842903.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.0647132396698,
|
|
"epoch": 2.3805836807623586,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044429360399900355,
|
|
"loss": 4.5536,
|
|
"mean_token_accuracy": 0.23587832003831863,
|
|
"num_tokens": 55856253.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.050709629058838,
|
|
"epoch": 2.3811792733770103,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004442655325251422,
|
|
"loss": 4.5271,
|
|
"mean_token_accuracy": 0.2373644858598709,
|
|
"num_tokens": 55869848.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.084028339385986,
|
|
"epoch": 2.3817748659916615,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004442374549800014,
|
|
"loss": 4.5625,
|
|
"mean_token_accuracy": 0.23107422292232513,
|
|
"num_tokens": 55883794.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.09784197807312,
|
|
"epoch": 2.3823704586063132,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044420937136458827,
|
|
"loss": 4.6008,
|
|
"mean_token_accuracy": 0.2328011304140091,
|
|
"num_tokens": 55897626.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.0800577163696286,
|
|
"epoch": 2.382966051220965,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004441812816799101,
|
|
"loss": 4.6387,
|
|
"mean_token_accuracy": 0.22930970788002014,
|
|
"num_tokens": 55912519.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.093694877624512,
|
|
"epoch": 2.383561643835616,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004441531859269745,
|
|
"loss": 4.5139,
|
|
"mean_token_accuracy": 0.23944141268730162,
|
|
"num_tokens": 55927135.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.033066987991333,
|
|
"epoch": 2.384157236450268,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000444125084106789,
|
|
"loss": 4.4808,
|
|
"mean_token_accuracy": 0.24217627197504044,
|
|
"num_tokens": 55939741.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.107706785202026,
|
|
"epoch": 2.3847528290649196,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004440969762203618,
|
|
"loss": 4.6162,
|
|
"mean_token_accuracy": 0.22739683240652084,
|
|
"num_tokens": 55952408.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.1566400051116945,
|
|
"epoch": 2.3853484216795713,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000444068862268701,
|
|
"loss": 4.6479,
|
|
"mean_token_accuracy": 0.230485001206398,
|
|
"num_tokens": 55965536.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.102747774124145,
|
|
"epoch": 2.385944014294223,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000444040742252815,
|
|
"loss": 4.5534,
|
|
"mean_token_accuracy": 0.24045329093933104,
|
|
"num_tokens": 55979038.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.016748523712158,
|
|
"epoch": 2.3865396069088742,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00044401261617371234,
|
|
"loss": 4.5481,
|
|
"mean_token_accuracy": 0.23727451711893083,
|
|
"num_tokens": 55995249.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.091477632522583,
|
|
"epoch": 2.387135199523526,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044398448403240213,
|
|
"loss": 4.6514,
|
|
"mean_token_accuracy": 0.22560420930385588,
|
|
"num_tokens": 56011626.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.228400850296021,
|
|
"epoch": 2.3877307921381776,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044395634582989306,
|
|
"loss": 4.7259,
|
|
"mean_token_accuracy": 0.2222339078783989,
|
|
"num_tokens": 56024889.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.006273317337036,
|
|
"epoch": 2.388326384752829,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004439282015671946,
|
|
"loss": 4.5124,
|
|
"mean_token_accuracy": 0.2391775593161583,
|
|
"num_tokens": 56041599.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.070698642730713,
|
|
"epoch": 2.3889219773674806,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044390005124531626,
|
|
"loss": 4.5611,
|
|
"mean_token_accuracy": 0.23169635832309723,
|
|
"num_tokens": 56054523.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.078446578979492,
|
|
"epoch": 2.3895175699821323,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004438718948652676,
|
|
"loss": 4.5625,
|
|
"mean_token_accuracy": 0.22815042734146118,
|
|
"num_tokens": 56067542.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.0291660785675045,
|
|
"epoch": 2.390113162596784,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004438437324280587,
|
|
"loss": 4.4298,
|
|
"mean_token_accuracy": 0.23762813359498977,
|
|
"num_tokens": 56083391.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.079647397994995,
|
|
"epoch": 2.390708755211435,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004438155639346997,
|
|
"loss": 4.6039,
|
|
"mean_token_accuracy": 0.23518768399953843,
|
|
"num_tokens": 56096987.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.023134708404541,
|
|
"epoch": 2.391304347826087,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004437873893862008,
|
|
"loss": 4.4594,
|
|
"mean_token_accuracy": 0.2445029377937317,
|
|
"num_tokens": 56111102.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.020350122451783,
|
|
"epoch": 2.3918999404407386,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044375920878357274,
|
|
"loss": 4.4554,
|
|
"mean_token_accuracy": 0.243310084939003,
|
|
"num_tokens": 56123688.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.059719467163086,
|
|
"epoch": 2.3924955330553903,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004437310221278262,
|
|
"loss": 4.6155,
|
|
"mean_token_accuracy": 0.23023184090852739,
|
|
"num_tokens": 56137977.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.002892589569091,
|
|
"epoch": 2.3930911256700416,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004437028294199723,
|
|
"loss": 4.4729,
|
|
"mean_token_accuracy": 0.24641238898038864,
|
|
"num_tokens": 56153090.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.023816871643066,
|
|
"epoch": 2.3936867182846933,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044367463066102207,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.23940173536539078,
|
|
"num_tokens": 56165991.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.013829231262207,
|
|
"epoch": 2.394282310899345,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004436464258519872,
|
|
"loss": 4.5143,
|
|
"mean_token_accuracy": 0.23467710465192795,
|
|
"num_tokens": 56180063.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.12381501197815,
|
|
"epoch": 2.394877903513996,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004436182149938792,
|
|
"loss": 4.7003,
|
|
"mean_token_accuracy": 0.23055266439914704,
|
|
"num_tokens": 56194462.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.039074945449829,
|
|
"epoch": 2.395473496128648,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00044358999808771007,
|
|
"loss": 4.5177,
|
|
"mean_token_accuracy": 0.23213681429624558,
|
|
"num_tokens": 56209278.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.049777269363403,
|
|
"epoch": 2.3960690887432996,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004435617751344917,
|
|
"loss": 4.5101,
|
|
"mean_token_accuracy": 0.24073849022388458,
|
|
"num_tokens": 56223145.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.083037042617798,
|
|
"epoch": 2.3966646813579513,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004435335461352366,
|
|
"loss": 4.6048,
|
|
"mean_token_accuracy": 0.240766179561615,
|
|
"num_tokens": 56237289.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.088617849349975,
|
|
"epoch": 2.3972602739726026,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004435053110909572,
|
|
"loss": 4.6381,
|
|
"mean_token_accuracy": 0.22796376347541808,
|
|
"num_tokens": 56252731.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.069956970214844,
|
|
"epoch": 2.3978558665872542,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00044347707000266627,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.23269533216953278,
|
|
"num_tokens": 56265743.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.057643175125122,
|
|
"epoch": 2.398451459201906,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044344882287137676,
|
|
"loss": 4.5118,
|
|
"mean_token_accuracy": 0.2347644090652466,
|
|
"num_tokens": 56280308.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.058631706237793,
|
|
"epoch": 2.3990470518165576,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004434205696981018,
|
|
"loss": 4.5706,
|
|
"mean_token_accuracy": 0.23553066700696945,
|
|
"num_tokens": 56295181.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.154003238677978,
|
|
"epoch": 2.399642644431209,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044339231048385485,
|
|
"loss": 4.5637,
|
|
"mean_token_accuracy": 0.23680200725793837,
|
|
"num_tokens": 56307241.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.081638288497925,
|
|
"epoch": 2.4002382370458606,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044336404522964963,
|
|
"loss": 4.6069,
|
|
"mean_token_accuracy": 0.22745763510465622,
|
|
"num_tokens": 56320712.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.075459957122803,
|
|
"epoch": 2.4008338296605123,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004433357739364998,
|
|
"loss": 4.5502,
|
|
"mean_token_accuracy": 0.23847085535526275,
|
|
"num_tokens": 56333226.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.103112459182739,
|
|
"epoch": 2.4014294222751635,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00044330749660541943,
|
|
"loss": 4.6455,
|
|
"mean_token_accuracy": 0.21857509464025499,
|
|
"num_tokens": 56347246.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.062003755569458,
|
|
"epoch": 2.4020250148898152,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044327921323742276,
|
|
"loss": 4.5541,
|
|
"mean_token_accuracy": 0.239035265147686,
|
|
"num_tokens": 56361730.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.04808874130249,
|
|
"epoch": 2.402620607504467,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00044325092383352434,
|
|
"loss": 4.5494,
|
|
"mean_token_accuracy": 0.23454678058624268,
|
|
"num_tokens": 56378197.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.101956844329834,
|
|
"epoch": 2.4032162001191186,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004432226283947388,
|
|
"loss": 4.594,
|
|
"mean_token_accuracy": 0.22989865839481355,
|
|
"num_tokens": 56391495.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.018935680389404,
|
|
"epoch": 2.4038117927337703,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044319432692208115,
|
|
"loss": 4.522,
|
|
"mean_token_accuracy": 0.24088395088911058,
|
|
"num_tokens": 56405503.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.113521337509155,
|
|
"epoch": 2.4044073853484216,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044316601941656655,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.21871016025543213,
|
|
"num_tokens": 56420526.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.0312721729278564,
|
|
"epoch": 2.4050029779630733,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004431377058792101,
|
|
"loss": 4.4492,
|
|
"mean_token_accuracy": 0.2517487645149231,
|
|
"num_tokens": 56433437.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.1055535793304445,
|
|
"epoch": 2.405598570577725,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004431093863110276,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.2289966881275177,
|
|
"num_tokens": 56447074.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.024591255187988,
|
|
"epoch": 2.4061941631923762,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004430810607130347,
|
|
"loss": 4.5197,
|
|
"mean_token_accuracy": 0.23662737756967545,
|
|
"num_tokens": 56462533.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.136719226837158,
|
|
"epoch": 2.406789755807028,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044305272908624747,
|
|
"loss": 4.6552,
|
|
"mean_token_accuracy": 0.22709753215312958,
|
|
"num_tokens": 56476914.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.112655735015869,
|
|
"epoch": 2.4073853484216796,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00044302439143168213,
|
|
"loss": 4.5963,
|
|
"mean_token_accuracy": 0.23391076773405076,
|
|
"num_tokens": 56492962.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.038599872589112,
|
|
"epoch": 2.4079809410363313,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044299604775035497,
|
|
"loss": 4.599,
|
|
"mean_token_accuracy": 0.23181732445955278,
|
|
"num_tokens": 56506629.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.11487774848938,
|
|
"epoch": 2.4085765336509826,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044296769804328274,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.23060139268636703,
|
|
"num_tokens": 56520287.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.009727811813354,
|
|
"epoch": 2.4091721262656343,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004429393423114824,
|
|
"loss": 4.5343,
|
|
"mean_token_accuracy": 0.236195807158947,
|
|
"num_tokens": 56534481.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.103219652175904,
|
|
"epoch": 2.409767718880286,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00044291098055597076,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.22487780302762986,
|
|
"num_tokens": 56549133.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.081121492385864,
|
|
"epoch": 2.4103633114949377,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044288261277776524,
|
|
"loss": 4.5116,
|
|
"mean_token_accuracy": 0.2356012284755707,
|
|
"num_tokens": 56563433.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 4.978317070007324,
|
|
"epoch": 2.410958904109589,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004428542389778834,
|
|
"loss": 4.4812,
|
|
"mean_token_accuracy": 0.23631357103586198,
|
|
"num_tokens": 56577368.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.085072660446167,
|
|
"epoch": 2.4115544967242406,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044282585915734297,
|
|
"loss": 4.5847,
|
|
"mean_token_accuracy": 0.22707610130310057,
|
|
"num_tokens": 56594500.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.092737770080566,
|
|
"epoch": 2.4121500893388923,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004427974733171618,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.23652010411024094,
|
|
"num_tokens": 56607951.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.040308427810669,
|
|
"epoch": 2.4127456819535436,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004427690814583581,
|
|
"loss": 4.5124,
|
|
"mean_token_accuracy": 0.24010181277990342,
|
|
"num_tokens": 56623195.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.085533857345581,
|
|
"epoch": 2.4133412745681952,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004427406835819502,
|
|
"loss": 4.5995,
|
|
"mean_token_accuracy": 0.22828981429338455,
|
|
"num_tokens": 56637731.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.09259786605835,
|
|
"epoch": 2.413936867182847,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004427122796889567,
|
|
"loss": 4.573,
|
|
"mean_token_accuracy": 0.234257273375988,
|
|
"num_tokens": 56651221.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.105594968795776,
|
|
"epoch": 2.4145324597974986,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004426838697803965,
|
|
"loss": 4.5937,
|
|
"mean_token_accuracy": 0.23062963038682938,
|
|
"num_tokens": 56665210.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.123667764663696,
|
|
"epoch": 2.4151280524121503,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044265545385728847,
|
|
"loss": 4.5567,
|
|
"mean_token_accuracy": 0.23726998567581176,
|
|
"num_tokens": 56677856.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.163232851028442,
|
|
"epoch": 2.4157236450268016,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044262703192065185,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.22424813657999038,
|
|
"num_tokens": 56691431.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.122965717315674,
|
|
"epoch": 2.4163192376414533,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044259860397150616,
|
|
"loss": 4.6144,
|
|
"mean_token_accuracy": 0.2298188641667366,
|
|
"num_tokens": 56706939.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.071986961364746,
|
|
"epoch": 2.416914830256105,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044257017001087114,
|
|
"loss": 4.5001,
|
|
"mean_token_accuracy": 0.23913474529981613,
|
|
"num_tokens": 56720996.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.067772245407104,
|
|
"epoch": 2.4175104228707562,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004425417300397665,
|
|
"loss": 4.6086,
|
|
"mean_token_accuracy": 0.23089305460453033,
|
|
"num_tokens": 56734890.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.102693510055542,
|
|
"epoch": 2.418106015485408,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044251328405921236,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.23848191052675247,
|
|
"num_tokens": 56747591.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.0604719638824465,
|
|
"epoch": 2.4187016081000596,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004424848320702291,
|
|
"loss": 4.5997,
|
|
"mean_token_accuracy": 0.23011535853147508,
|
|
"num_tokens": 56759250.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.100051546096802,
|
|
"epoch": 2.4192972007147113,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004424563740738373,
|
|
"loss": 4.6018,
|
|
"mean_token_accuracy": 0.22417562007904052,
|
|
"num_tokens": 56775003.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.085923910140991,
|
|
"epoch": 2.4198927933293626,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044242791007105764,
|
|
"loss": 4.5146,
|
|
"mean_token_accuracy": 0.24190982133150102,
|
|
"num_tokens": 56788221.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.117676448822022,
|
|
"epoch": 2.4204883859440143,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000442399440062911,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.22996582835912704,
|
|
"num_tokens": 56803291.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.056469917297363,
|
|
"epoch": 2.421083978558666,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044237096405041863,
|
|
"loss": 4.5794,
|
|
"mean_token_accuracy": 0.23108630925416945,
|
|
"num_tokens": 56817550.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.1691957950592045,
|
|
"epoch": 2.4216795711733177,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044234248203460193,
|
|
"loss": 4.6246,
|
|
"mean_token_accuracy": 0.22846759557724,
|
|
"num_tokens": 56831573.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.112192535400391,
|
|
"epoch": 2.422275163787969,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044231399401648247,
|
|
"loss": 4.5506,
|
|
"mean_token_accuracy": 0.2284644991159439,
|
|
"num_tokens": 56847286.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.06643590927124,
|
|
"epoch": 2.4228707564026206,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044228549999708204,
|
|
"loss": 4.5767,
|
|
"mean_token_accuracy": 0.22780856043100356,
|
|
"num_tokens": 56862680.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.090669250488281,
|
|
"epoch": 2.4234663490172723,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004422569999774228,
|
|
"loss": 4.5224,
|
|
"mean_token_accuracy": 0.24008914232254028,
|
|
"num_tokens": 56876813.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.166809940338135,
|
|
"epoch": 2.4240619416319236,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044222849395852683,
|
|
"loss": 4.6808,
|
|
"mean_token_accuracy": 0.22744908481836318,
|
|
"num_tokens": 56892525.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.103673219680786,
|
|
"epoch": 2.4246575342465753,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004421999819414167,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.23920125216245652,
|
|
"num_tokens": 56906668.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.026108741760254,
|
|
"epoch": 2.425253126861227,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004421714639271151,
|
|
"loss": 4.5386,
|
|
"mean_token_accuracy": 0.2364346817135811,
|
|
"num_tokens": 56919365.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.061708211898804,
|
|
"epoch": 2.4258487194758787,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004421429399166449,
|
|
"loss": 4.5404,
|
|
"mean_token_accuracy": 0.23455384522676467,
|
|
"num_tokens": 56933790.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.065751314163208,
|
|
"epoch": 2.42644431209053,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004421144099110292,
|
|
"loss": 4.5257,
|
|
"mean_token_accuracy": 0.2402285948395729,
|
|
"num_tokens": 56947556.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.0237328052520756,
|
|
"epoch": 2.4270399047051816,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004420858739112913,
|
|
"loss": 4.5168,
|
|
"mean_token_accuracy": 0.23150845617055893,
|
|
"num_tokens": 56960477.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.1047605037689205,
|
|
"epoch": 2.4276354973198333,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044205733191845473,
|
|
"loss": 4.6383,
|
|
"mean_token_accuracy": 0.2302380084991455,
|
|
"num_tokens": 56974539.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.05125846862793,
|
|
"epoch": 2.428231089934485,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004420287839335434,
|
|
"loss": 4.4927,
|
|
"mean_token_accuracy": 0.23069287240505218,
|
|
"num_tokens": 56988838.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.07018461227417,
|
|
"epoch": 2.4288266825491363,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00044200022995758104,
|
|
"loss": 4.6111,
|
|
"mean_token_accuracy": 0.22997058779001237,
|
|
"num_tokens": 57004440.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.062420797348023,
|
|
"epoch": 2.429422275163788,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044197166999159203,
|
|
"loss": 4.5411,
|
|
"mean_token_accuracy": 0.23224121183156968,
|
|
"num_tokens": 57017936.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.140793657302856,
|
|
"epoch": 2.4300178677784396,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004419431040366007,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.22730056345462799,
|
|
"num_tokens": 57032984.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.110620594024658,
|
|
"epoch": 2.430613460393091,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00044191453209363165,
|
|
"loss": 4.6179,
|
|
"mean_token_accuracy": 0.2347440466284752,
|
|
"num_tokens": 57046608.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.138640880584717,
|
|
"epoch": 2.4312090530077426,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004418859541637097,
|
|
"loss": 4.6129,
|
|
"mean_token_accuracy": 0.23378441780805587,
|
|
"num_tokens": 57059200.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.111855411529541,
|
|
"epoch": 2.4318046456223943,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044185737024785986,
|
|
"loss": 4.5937,
|
|
"mean_token_accuracy": 0.23148195892572404,
|
|
"num_tokens": 57073316.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.074338579177857,
|
|
"epoch": 2.432400238237046,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00044182878034710753,
|
|
"loss": 4.5865,
|
|
"mean_token_accuracy": 0.2314729332923889,
|
|
"num_tokens": 57089710.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.080836343765259,
|
|
"epoch": 2.4329958308516977,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044180018446247807,
|
|
"loss": 4.5592,
|
|
"mean_token_accuracy": 0.23408009260892867,
|
|
"num_tokens": 57102770.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.074964237213135,
|
|
"epoch": 2.433591423466349,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004417715825949972,
|
|
"loss": 4.5649,
|
|
"mean_token_accuracy": 0.23376997262239457,
|
|
"num_tokens": 57117055.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.087630367279052,
|
|
"epoch": 2.4341870160810006,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004417429747456908,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.23853053152561188,
|
|
"num_tokens": 57130344.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.070722150802612,
|
|
"epoch": 2.4347826086956523,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000441714360915585,
|
|
"loss": 4.58,
|
|
"mean_token_accuracy": 0.23338377177715303,
|
|
"num_tokens": 57143639.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.176698875427246,
|
|
"epoch": 2.4353782013103036,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004416857411057062,
|
|
"loss": 4.6987,
|
|
"mean_token_accuracy": 0.21308176666498185,
|
|
"num_tokens": 57157903.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.052857160568237,
|
|
"epoch": 2.4359737939249553,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044165711531708073,
|
|
"loss": 4.5251,
|
|
"mean_token_accuracy": 0.23773594200611115,
|
|
"num_tokens": 57171224.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.076496696472168,
|
|
"epoch": 2.436569386539607,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044162848355073565,
|
|
"loss": 4.5624,
|
|
"mean_token_accuracy": 0.22820667028427125,
|
|
"num_tokens": 57184624.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.074141168594361,
|
|
"epoch": 2.4371649791542587,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004415998458076978,
|
|
"loss": 4.5905,
|
|
"mean_token_accuracy": 0.2319393962621689,
|
|
"num_tokens": 57199603.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.0853376388549805,
|
|
"epoch": 2.43776057176891,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004415712020889943,
|
|
"loss": 4.5643,
|
|
"mean_token_accuracy": 0.22962258458137513,
|
|
"num_tokens": 57214448.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.148058557510376,
|
|
"epoch": 2.4383561643835616,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044154255239565256,
|
|
"loss": 4.6363,
|
|
"mean_token_accuracy": 0.2287995308637619,
|
|
"num_tokens": 57229162.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.052226591110229,
|
|
"epoch": 2.4389517569982133,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004415138967287003,
|
|
"loss": 4.5032,
|
|
"mean_token_accuracy": 0.24301315546035768,
|
|
"num_tokens": 57242208.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.076539802551269,
|
|
"epoch": 2.439547349612865,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004414852350891653,
|
|
"loss": 4.5141,
|
|
"mean_token_accuracy": 0.2335806220769882,
|
|
"num_tokens": 57254206.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.095198249816894,
|
|
"epoch": 2.4401429422275163,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004414565674780756,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.23029936105012894,
|
|
"num_tokens": 57268163.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.057505989074707,
|
|
"epoch": 2.440738534842168,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044142789389645944,
|
|
"loss": 4.5552,
|
|
"mean_token_accuracy": 0.23541587442159653,
|
|
"num_tokens": 57282758.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.076127910614014,
|
|
"epoch": 2.4413341274568197,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004413992143453453,
|
|
"loss": 4.5801,
|
|
"mean_token_accuracy": 0.23554858714342117,
|
|
"num_tokens": 57295079.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.012902116775512,
|
|
"epoch": 2.441929720071471,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000441370528825762,
|
|
"loss": 4.5188,
|
|
"mean_token_accuracy": 0.23855238109827043,
|
|
"num_tokens": 57308664.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.008280944824219,
|
|
"epoch": 2.4425253126861226,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044134183733873827,
|
|
"loss": 4.5069,
|
|
"mean_token_accuracy": 0.23926257640123366,
|
|
"num_tokens": 57321932.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 4.9959770202636715,
|
|
"epoch": 2.4431209053007743,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044131313988530325,
|
|
"loss": 4.5046,
|
|
"mean_token_accuracy": 0.24363980889320375,
|
|
"num_tokens": 57336395.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.160128211975097,
|
|
"epoch": 2.443716497915426,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044128443646648634,
|
|
"loss": 4.6626,
|
|
"mean_token_accuracy": 0.22565396130084991,
|
|
"num_tokens": 57350259.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.105645418167114,
|
|
"epoch": 2.4443120905300773,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044125572708331705,
|
|
"loss": 4.5766,
|
|
"mean_token_accuracy": 0.22697211503982545,
|
|
"num_tokens": 57364305.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.107352876663208,
|
|
"epoch": 2.444907683144729,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044122701173682514,
|
|
"loss": 4.5891,
|
|
"mean_token_accuracy": 0.23293305337429046,
|
|
"num_tokens": 57378843.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.022368001937866,
|
|
"epoch": 2.4455032757593806,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004411982904280407,
|
|
"loss": 4.4658,
|
|
"mean_token_accuracy": 0.2420320600271225,
|
|
"num_tokens": 57392190.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.053235006332398,
|
|
"epoch": 2.4460988683740323,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004411695631579936,
|
|
"loss": 4.4892,
|
|
"mean_token_accuracy": 0.2471463441848755,
|
|
"num_tokens": 57405952.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.0854755401611325,
|
|
"epoch": 2.4466944609886836,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044114082992771457,
|
|
"loss": 4.5737,
|
|
"mean_token_accuracy": 0.22898843735456467,
|
|
"num_tokens": 57419678.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.123478698730469,
|
|
"epoch": 2.4472900536033353,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00044111209073823416,
|
|
"loss": 4.593,
|
|
"mean_token_accuracy": 0.23366887122392654,
|
|
"num_tokens": 57434262.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.102289915084839,
|
|
"epoch": 2.447885646217987,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000441083345590583,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.24022153913974761,
|
|
"num_tokens": 57447039.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.111950635910034,
|
|
"epoch": 2.4484812388326382,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004410545944857923,
|
|
"loss": 4.6047,
|
|
"mean_token_accuracy": 0.23491517454385757,
|
|
"num_tokens": 57461368.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.070684623718262,
|
|
"epoch": 2.44907683144729,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044102583742489337,
|
|
"loss": 4.5279,
|
|
"mean_token_accuracy": 0.2391681358218193,
|
|
"num_tokens": 57475466.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.097577619552612,
|
|
"epoch": 2.4496724240619416,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004409970744089175,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.2346647173166275,
|
|
"num_tokens": 57488743.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.0854404926300045,
|
|
"epoch": 2.4502680166765933,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044096830543889653,
|
|
"loss": 4.5972,
|
|
"mean_token_accuracy": 0.2305808261036873,
|
|
"num_tokens": 57502747.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 4.980028104782105,
|
|
"epoch": 2.450863609291245,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044093953051586225,
|
|
"loss": 4.4893,
|
|
"mean_token_accuracy": 0.24456288069486617,
|
|
"num_tokens": 57516994.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.096589183807373,
|
|
"epoch": 2.4514592019058963,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004409107496408468,
|
|
"loss": 4.4861,
|
|
"mean_token_accuracy": 0.2418987438082695,
|
|
"num_tokens": 57529995.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.031802940368652,
|
|
"epoch": 2.452054794520548,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044088196281488257,
|
|
"loss": 4.4911,
|
|
"mean_token_accuracy": 0.23341825604438782,
|
|
"num_tokens": 57543554.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.0478003978729244,
|
|
"epoch": 2.4526503871351997,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000440853170039002,
|
|
"loss": 4.5461,
|
|
"mean_token_accuracy": 0.24303203970193862,
|
|
"num_tokens": 57558055.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.074827671051025,
|
|
"epoch": 2.453245979749851,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044082437131423785,
|
|
"loss": 4.5415,
|
|
"mean_token_accuracy": 0.23053931891918183,
|
|
"num_tokens": 57572981.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.149468851089478,
|
|
"epoch": 2.4538415723645026,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044079556664162323,
|
|
"loss": 4.5562,
|
|
"mean_token_accuracy": 0.23145655691623687,
|
|
"num_tokens": 57585955.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.09798641204834,
|
|
"epoch": 2.4544371649791543,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004407667560221911,
|
|
"loss": 4.5923,
|
|
"mean_token_accuracy": 0.23912218064069748,
|
|
"num_tokens": 57600879.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.08589358329773,
|
|
"epoch": 2.455032757593806,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000440737939456975,
|
|
"loss": 4.5711,
|
|
"mean_token_accuracy": 0.2323153629899025,
|
|
"num_tokens": 57613956.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.121565294265747,
|
|
"epoch": 2.4556283502084573,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044070911694700846,
|
|
"loss": 4.6431,
|
|
"mean_token_accuracy": 0.2391891896724701,
|
|
"num_tokens": 57626321.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.071623468399048,
|
|
"epoch": 2.456223942823109,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004406802884933253,
|
|
"loss": 4.5064,
|
|
"mean_token_accuracy": 0.23413577824831008,
|
|
"num_tokens": 57640669.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.051331806182861,
|
|
"epoch": 2.4568195354377607,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004406514540969596,
|
|
"loss": 4.5637,
|
|
"mean_token_accuracy": 0.2375494956970215,
|
|
"num_tokens": 57654917.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.136236715316772,
|
|
"epoch": 2.4574151280524124,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044062261375894563,
|
|
"loss": 4.643,
|
|
"mean_token_accuracy": 0.23372738510370256,
|
|
"num_tokens": 57668355.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.089270830154419,
|
|
"epoch": 2.4580107206670636,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004405937674803177,
|
|
"loss": 4.5535,
|
|
"mean_token_accuracy": 0.23076958805322648,
|
|
"num_tokens": 57683128.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.061903476715088,
|
|
"epoch": 2.4586063132817153,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044056491526211063,
|
|
"loss": 4.5233,
|
|
"mean_token_accuracy": 0.23687639832496643,
|
|
"num_tokens": 57696034.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.072178936004638,
|
|
"epoch": 2.459201905896367,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004405360571053592,
|
|
"loss": 4.5769,
|
|
"mean_token_accuracy": 0.23134000301361085,
|
|
"num_tokens": 57711496.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.052002716064453,
|
|
"epoch": 2.4597974985110183,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044050719301109856,
|
|
"loss": 4.5419,
|
|
"mean_token_accuracy": 0.23978788107633592,
|
|
"num_tokens": 57724250.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.069577836990357,
|
|
"epoch": 2.46039309112567,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000440478322980364,
|
|
"loss": 4.521,
|
|
"mean_token_accuracy": 0.2433473914861679,
|
|
"num_tokens": 57736979.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.112225294113159,
|
|
"epoch": 2.4609886837403216,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044044944701419105,
|
|
"loss": 4.6267,
|
|
"mean_token_accuracy": 0.22317378968000412,
|
|
"num_tokens": 57750745.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.087930583953858,
|
|
"epoch": 2.4615842763549733,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004404205651136155,
|
|
"loss": 4.5857,
|
|
"mean_token_accuracy": 0.23376805186271668,
|
|
"num_tokens": 57766414.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.1589618682861325,
|
|
"epoch": 2.4621798689696246,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004403916772796731,
|
|
"loss": 4.6405,
|
|
"mean_token_accuracy": 0.22472499459981918,
|
|
"num_tokens": 57781696.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.154582595825195,
|
|
"epoch": 2.4627754615842763,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044036278351340023,
|
|
"loss": 4.6071,
|
|
"mean_token_accuracy": 0.23283606320619582,
|
|
"num_tokens": 57795437.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.098466920852661,
|
|
"epoch": 2.463371054198928,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044033388381583324,
|
|
"loss": 4.6031,
|
|
"mean_token_accuracy": 0.23222249299287795,
|
|
"num_tokens": 57808366.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.076330471038818,
|
|
"epoch": 2.4639666468135797,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004403049781880086,
|
|
"loss": 4.5956,
|
|
"mean_token_accuracy": 0.2317999079823494,
|
|
"num_tokens": 57821654.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.111643218994141,
|
|
"epoch": 2.464562239428231,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004402760666309631,
|
|
"loss": 4.6379,
|
|
"mean_token_accuracy": 0.230289588868618,
|
|
"num_tokens": 57834897.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 4.986612033843994,
|
|
"epoch": 2.4651578320428826,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004402471491457339,
|
|
"loss": 4.4435,
|
|
"mean_token_accuracy": 0.2449421301484108,
|
|
"num_tokens": 57851005.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.046429967880249,
|
|
"epoch": 2.4657534246575343,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004402182257333581,
|
|
"loss": 4.5177,
|
|
"mean_token_accuracy": 0.23846951276063919,
|
|
"num_tokens": 57863101.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.12035903930664,
|
|
"epoch": 2.4663490172721856,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004401892963948732,
|
|
"loss": 4.632,
|
|
"mean_token_accuracy": 0.22742458879947663,
|
|
"num_tokens": 57879507.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.023994016647339,
|
|
"epoch": 2.4669446098868373,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044016036113131673,
|
|
"loss": 4.4863,
|
|
"mean_token_accuracy": 0.2397181436419487,
|
|
"num_tokens": 57893065.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.06818528175354,
|
|
"epoch": 2.467540202501489,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044013141994372673,
|
|
"loss": 4.6033,
|
|
"mean_token_accuracy": 0.22927697598934174,
|
|
"num_tokens": 57906005.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.063212776184082,
|
|
"epoch": 2.4681357951161407,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004401024728331411,
|
|
"loss": 4.583,
|
|
"mean_token_accuracy": 0.22728059887886048,
|
|
"num_tokens": 57920411.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.07806077003479,
|
|
"epoch": 2.4687313877307924,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044007351980059826,
|
|
"loss": 4.5355,
|
|
"mean_token_accuracy": 0.23654174357652663,
|
|
"num_tokens": 57933230.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 4.992774915695191,
|
|
"epoch": 2.4693269803454436,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004400445608471367,
|
|
"loss": 4.4533,
|
|
"mean_token_accuracy": 0.24666715562343597,
|
|
"num_tokens": 57946923.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.036278629302979,
|
|
"epoch": 2.4699225729600953,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044001559597379503,
|
|
"loss": 4.5078,
|
|
"mean_token_accuracy": 0.23886729031801224,
|
|
"num_tokens": 57960545.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.1037952423095705,
|
|
"epoch": 2.470518165574747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043998662518161233,
|
|
"loss": 4.5966,
|
|
"mean_token_accuracy": 0.23093903809785843,
|
|
"num_tokens": 57975564.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.044365644454956,
|
|
"epoch": 2.4711137581893983,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043995764847162757,
|
|
"loss": 4.5134,
|
|
"mean_token_accuracy": 0.2372580274939537,
|
|
"num_tokens": 57990047.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.134750890731811,
|
|
"epoch": 2.47170935080405,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043992866584488007,
|
|
"loss": 4.6796,
|
|
"mean_token_accuracy": 0.22443362921476365,
|
|
"num_tokens": 58005850.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.062934541702271,
|
|
"epoch": 2.4723049434187017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004398996773024096,
|
|
"loss": 4.5287,
|
|
"mean_token_accuracy": 0.23738970309495927,
|
|
"num_tokens": 58018473.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.100398159027099,
|
|
"epoch": 2.4729005360333534,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004398706828452558,
|
|
"loss": 4.5771,
|
|
"mean_token_accuracy": 0.2346976488828659,
|
|
"num_tokens": 58032893.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.006748867034912,
|
|
"epoch": 2.4734961286480046,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004398416824744586,
|
|
"loss": 4.4202,
|
|
"mean_token_accuracy": 0.24770939350128174,
|
|
"num_tokens": 58046031.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.0340046882629395,
|
|
"epoch": 2.4740917212626563,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043981267619105837,
|
|
"loss": 4.5713,
|
|
"mean_token_accuracy": 0.2376718506217003,
|
|
"num_tokens": 58059589.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.181832647323608,
|
|
"epoch": 2.474687313877308,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004397836639960953,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.23056762516498566,
|
|
"num_tokens": 58073042.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.092503690719605,
|
|
"epoch": 2.4752829064919597,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004397546458906102,
|
|
"loss": 4.599,
|
|
"mean_token_accuracy": 0.23353813588619232,
|
|
"num_tokens": 58087450.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.014113187789917,
|
|
"epoch": 2.475878499106611,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043972562187564383,
|
|
"loss": 4.5576,
|
|
"mean_token_accuracy": 0.2329071879386902,
|
|
"num_tokens": 58101167.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.067032146453857,
|
|
"epoch": 2.4764740917212626,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004396965919522373,
|
|
"loss": 4.5603,
|
|
"mean_token_accuracy": 0.2369812995195389,
|
|
"num_tokens": 58116010.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.091748285293579,
|
|
"epoch": 2.4770696843359143,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043966755612143165,
|
|
"loss": 4.5703,
|
|
"mean_token_accuracy": 0.23393478393554687,
|
|
"num_tokens": 58132318.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.142641830444336,
|
|
"epoch": 2.4776652769505656,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043963851438426853,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.22743646800518036,
|
|
"num_tokens": 58145953.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.112294006347656,
|
|
"epoch": 2.4782608695652173,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004396094667417896,
|
|
"loss": 4.5968,
|
|
"mean_token_accuracy": 0.2305901125073433,
|
|
"num_tokens": 58160544.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.061129808425903,
|
|
"epoch": 2.478856462179869,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004395804131950368,
|
|
"loss": 4.5554,
|
|
"mean_token_accuracy": 0.23733810633420943,
|
|
"num_tokens": 58174894.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.1233912944793705,
|
|
"epoch": 2.4794520547945207,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043955135374505207,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.2297413319349289,
|
|
"num_tokens": 58187061.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.054000329971314,
|
|
"epoch": 2.480047647409172,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004395222883928779,
|
|
"loss": 4.5873,
|
|
"mean_token_accuracy": 0.22661390155553818,
|
|
"num_tokens": 58201815.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.0475616455078125,
|
|
"epoch": 2.4806432400238236,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00043949321713955677,
|
|
"loss": 4.5093,
|
|
"mean_token_accuracy": 0.2404245913028717,
|
|
"num_tokens": 58216781.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.036484146118164,
|
|
"epoch": 2.4812388326384753,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004394641399861313,
|
|
"loss": 4.4681,
|
|
"mean_token_accuracy": 0.24406418353319168,
|
|
"num_tokens": 58229594.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.022649765014648,
|
|
"epoch": 2.481834425253127,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004394350569336445,
|
|
"loss": 4.5221,
|
|
"mean_token_accuracy": 0.24496053159236908,
|
|
"num_tokens": 58243140.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.09974479675293,
|
|
"epoch": 2.4824300178677783,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043940596798313963,
|
|
"loss": 4.5735,
|
|
"mean_token_accuracy": 0.23704340159893036,
|
|
"num_tokens": 58256927.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.062928295135498,
|
|
"epoch": 2.48302561048243,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043937687313565997,
|
|
"loss": 4.5366,
|
|
"mean_token_accuracy": 0.2392688512802124,
|
|
"num_tokens": 58271768.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.056711912155151,
|
|
"epoch": 2.4836212030970817,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004393477723922492,
|
|
"loss": 4.5588,
|
|
"mean_token_accuracy": 0.23310785740613937,
|
|
"num_tokens": 58286263.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.113080596923828,
|
|
"epoch": 2.484216795711733,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000439318665753951,
|
|
"loss": 4.6136,
|
|
"mean_token_accuracy": 0.22508435994386672,
|
|
"num_tokens": 58299287.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.057101774215698,
|
|
"epoch": 2.4848123883263846,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043928955322180944,
|
|
"loss": 4.5155,
|
|
"mean_token_accuracy": 0.24552031457424164,
|
|
"num_tokens": 58312482.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.102430248260498,
|
|
"epoch": 2.4854079809410363,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004392604347968687,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.22890023291110992,
|
|
"num_tokens": 58324684.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.176059055328369,
|
|
"epoch": 2.486003573555688,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00043923131048017325,
|
|
"loss": 4.6652,
|
|
"mean_token_accuracy": 0.22946431785821914,
|
|
"num_tokens": 58338342.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.149746608734131,
|
|
"epoch": 2.4865991661703397,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043920218027276777,
|
|
"loss": 4.6058,
|
|
"mean_token_accuracy": 0.2315344363451004,
|
|
"num_tokens": 58352819.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.100259923934937,
|
|
"epoch": 2.487194758784991,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043917304417569696,
|
|
"loss": 4.5762,
|
|
"mean_token_accuracy": 0.23501268029212952,
|
|
"num_tokens": 58365952.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.0731912612915036,
|
|
"epoch": 2.4877903513996427,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043914390219000605,
|
|
"loss": 4.5682,
|
|
"mean_token_accuracy": 0.23871516585350036,
|
|
"num_tokens": 58378631.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.099018669128418,
|
|
"epoch": 2.4883859440142944,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043911475431674025,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.2297488570213318,
|
|
"num_tokens": 58390534.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.115691518783569,
|
|
"epoch": 2.4889815366289456,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000439085600556945,
|
|
"loss": 4.5497,
|
|
"mean_token_accuracy": 0.2261161834001541,
|
|
"num_tokens": 58404248.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.054912424087524,
|
|
"epoch": 2.4895771292435973,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004390564409116661,
|
|
"loss": 4.5844,
|
|
"mean_token_accuracy": 0.23377244621515275,
|
|
"num_tokens": 58417139.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 4.938780832290649,
|
|
"epoch": 2.490172721858249,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004390272753819494,
|
|
"loss": 4.3518,
|
|
"mean_token_accuracy": 0.24876561313867568,
|
|
"num_tokens": 58431131.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.084322500228882,
|
|
"epoch": 2.4907683144729007,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000438998103968841,
|
|
"loss": 4.5939,
|
|
"mean_token_accuracy": 0.2309810474514961,
|
|
"num_tokens": 58446378.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.092353248596192,
|
|
"epoch": 2.491363907087552,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043896892667338725,
|
|
"loss": 4.5351,
|
|
"mean_token_accuracy": 0.23541754335165024,
|
|
"num_tokens": 58460441.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.048524618148804,
|
|
"epoch": 2.4919594997022037,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043893974349663465,
|
|
"loss": 4.5594,
|
|
"mean_token_accuracy": 0.23520146012306214,
|
|
"num_tokens": 58474080.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.122053909301758,
|
|
"epoch": 2.4925550923168553,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004389105544396301,
|
|
"loss": 4.5787,
|
|
"mean_token_accuracy": 0.2309805691242218,
|
|
"num_tokens": 58488376.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.032143545150757,
|
|
"epoch": 2.493150684931507,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004388813595034204,
|
|
"loss": 4.4734,
|
|
"mean_token_accuracy": 0.24166369587182998,
|
|
"num_tokens": 58501413.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.046249008178711,
|
|
"epoch": 2.4937462775461583,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00043885215868905283,
|
|
"loss": 4.5956,
|
|
"mean_token_accuracy": 0.2308048874139786,
|
|
"num_tokens": 58517520.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.15789647102356,
|
|
"epoch": 2.49434187016081,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043882295199757464,
|
|
"loss": 4.5915,
|
|
"mean_token_accuracy": 0.2395290270447731,
|
|
"num_tokens": 58533394.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.035839796066284,
|
|
"epoch": 2.4949374627754617,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004387937394300336,
|
|
"loss": 4.507,
|
|
"mean_token_accuracy": 0.23881060183048247,
|
|
"num_tokens": 58547108.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.077879238128662,
|
|
"epoch": 2.495533055390113,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004387645209874775,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.22838880270719528,
|
|
"num_tokens": 58559612.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.123593091964722,
|
|
"epoch": 2.4961286480047646,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043873529667095423,
|
|
"loss": 4.6236,
|
|
"mean_token_accuracy": 0.22692562341690065,
|
|
"num_tokens": 58573357.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.075484943389893,
|
|
"epoch": 2.4967242406194163,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043870606648151205,
|
|
"loss": 4.5335,
|
|
"mean_token_accuracy": 0.23947317004203797,
|
|
"num_tokens": 58588694.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.102662372589111,
|
|
"epoch": 2.497319833234068,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004386768304201995,
|
|
"loss": 4.5684,
|
|
"mean_token_accuracy": 0.23450845181941987,
|
|
"num_tokens": 58600706.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.013095235824585,
|
|
"epoch": 2.4979154258487193,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043864758848806515,
|
|
"loss": 4.4933,
|
|
"mean_token_accuracy": 0.23660112619400026,
|
|
"num_tokens": 58616314.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.064970827102661,
|
|
"epoch": 2.498511018463371,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004386183406861579,
|
|
"loss": 4.5658,
|
|
"mean_token_accuracy": 0.2349696636199951,
|
|
"num_tokens": 58630551.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.039459609985352,
|
|
"epoch": 2.4991066110780227,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004385890870155267,
|
|
"loss": 4.4851,
|
|
"mean_token_accuracy": 0.23863089829683304,
|
|
"num_tokens": 58645375.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.069157457351684,
|
|
"epoch": 2.4997022036926744,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000438559827477221,
|
|
"loss": 4.6002,
|
|
"mean_token_accuracy": 0.22968757897615433,
|
|
"num_tokens": 58659869.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.148730516433716,
|
|
"epoch": 2.5002977963073256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004385305620722902,
|
|
"loss": 4.6535,
|
|
"mean_token_accuracy": 0.23187745362520218,
|
|
"num_tokens": 58672387.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.082141971588134,
|
|
"epoch": 2.5008933889219773,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000438501290801784,
|
|
"loss": 4.5165,
|
|
"mean_token_accuracy": 0.23963285237550735,
|
|
"num_tokens": 58684579.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.110419702529907,
|
|
"epoch": 2.501488981536629,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00043847201366675243,
|
|
"loss": 4.6137,
|
|
"mean_token_accuracy": 0.23240216821432114,
|
|
"num_tokens": 58700602.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.501488981536629,
|
|
"eval_entropy": 4.841399176217919,
|
|
"eval_loss": 4.5945210456848145,
|
|
"eval_mean_token_accuracy": 0.2435683936371138,
|
|
"eval_num_tokens": 58700602.0,
|
|
"eval_runtime": 18.5032,
|
|
"eval_samples_per_second": 1378.844,
|
|
"eval_steps_per_second": 172.403,
|
|
"step": 21000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 83940,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.54778285758464e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|