2c7a0efbfc
Model: fpadovani/urd-arab-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
60145 lines
1.6 MiB
60145 lines
1.6 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.5735556879094696,
|
|
"eval_steps": 3000,
|
|
"global_step": 30000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.926274108886719,
|
|
"epoch": 0.0005955926146515784,
|
|
"grad_norm": 15.8125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.4668,
|
|
"mean_token_accuracy": 0.00011862700339406728,
|
|
"num_tokens": 13933.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.932535886764526,
|
|
"epoch": 0.0011911852293031567,
|
|
"grad_norm": 16.0,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.4393,
|
|
"mean_token_accuracy": 0.00014443041873164476,
|
|
"num_tokens": 28184.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.941028690338134,
|
|
"epoch": 0.001786777843954735,
|
|
"grad_norm": 16.375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.366,
|
|
"mean_token_accuracy": 5.685048527084291e-05,
|
|
"num_tokens": 42481.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.974720859527588,
|
|
"epoch": 0.0023823704586063135,
|
|
"grad_norm": 18.25,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.2566,
|
|
"mean_token_accuracy": 9.621907083783299e-05,
|
|
"num_tokens": 58257.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.058082151412964,
|
|
"epoch": 0.0029779630732578916,
|
|
"grad_norm": 21.625,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.8803,
|
|
"mean_token_accuracy": 0.00022898090537637472,
|
|
"num_tokens": 73037.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.31669545173645,
|
|
"epoch": 0.00357355568790947,
|
|
"grad_norm": 24.875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.2981,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 87144.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.431478261947632,
|
|
"epoch": 0.004169148302561048,
|
|
"grad_norm": 26.125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 12.2997,
|
|
"mean_token_accuracy": 0.00021689585410058498,
|
|
"num_tokens": 100908.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 9.774415397644043,
|
|
"epoch": 0.004764740917212627,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 11.0372,
|
|
"mean_token_accuracy": 0.00017865551344584674,
|
|
"num_tokens": 116164.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.664159393310547,
|
|
"epoch": 0.005360333531864205,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.734,
|
|
"mean_token_accuracy": 0.008229692280292512,
|
|
"num_tokens": 129754.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.731787872314452,
|
|
"epoch": 0.005955926146515783,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.595,
|
|
"mean_token_accuracy": 0.012316014664247633,
|
|
"num_tokens": 143356.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.736772346496583,
|
|
"epoch": 0.006551518761167362,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.4613,
|
|
"mean_token_accuracy": 0.010549227753654123,
|
|
"num_tokens": 159656.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.722232151031495,
|
|
"epoch": 0.00714711137581894,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.2733,
|
|
"mean_token_accuracy": 0.010485857352614402,
|
|
"num_tokens": 176053.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.731705951690675,
|
|
"epoch": 0.007742703990470518,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.1271,
|
|
"mean_token_accuracy": 0.011739565338939429,
|
|
"num_tokens": 191011.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.737554550170898,
|
|
"epoch": 0.008338296605122097,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.9987,
|
|
"mean_token_accuracy": 0.020756381284445524,
|
|
"num_tokens": 203975.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.73554105758667,
|
|
"epoch": 0.008933889219773675,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.9208,
|
|
"mean_token_accuracy": 0.02677243258804083,
|
|
"num_tokens": 216231.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.731139755249023,
|
|
"epoch": 0.009529481834425254,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.8468,
|
|
"mean_token_accuracy": 0.019028229545801877,
|
|
"num_tokens": 230525.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.729487705230714,
|
|
"epoch": 0.01012507444907683,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.7316,
|
|
"mean_token_accuracy": 0.01892870357260108,
|
|
"num_tokens": 243197.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.723625087738037,
|
|
"epoch": 0.01072066706372841,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5835,
|
|
"mean_token_accuracy": 0.024439648631960152,
|
|
"num_tokens": 257358.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.716553783416748,
|
|
"epoch": 0.011316259678379988,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.5493,
|
|
"mean_token_accuracy": 0.030682512372732163,
|
|
"num_tokens": 271978.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.702925300598144,
|
|
"epoch": 0.011911852293031567,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.4086,
|
|
"mean_token_accuracy": 0.03231615498661995,
|
|
"num_tokens": 286644.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.68063383102417,
|
|
"epoch": 0.012507444907683145,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2776,
|
|
"mean_token_accuracy": 0.03108740095049143,
|
|
"num_tokens": 299888.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.65084342956543,
|
|
"epoch": 0.013103037522334724,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1219,
|
|
"mean_token_accuracy": 0.03252283651381731,
|
|
"num_tokens": 314062.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.616011810302734,
|
|
"epoch": 0.0136986301369863,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9673,
|
|
"mean_token_accuracy": 0.0338243318721652,
|
|
"num_tokens": 326877.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.572829627990723,
|
|
"epoch": 0.01429422275163788,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8608,
|
|
"mean_token_accuracy": 0.037117029167711736,
|
|
"num_tokens": 339831.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.519098854064941,
|
|
"epoch": 0.014889815366289458,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7606,
|
|
"mean_token_accuracy": 0.034193937107920645,
|
|
"num_tokens": 353316.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.45387372970581,
|
|
"epoch": 0.015485407980941036,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6455,
|
|
"mean_token_accuracy": 0.034920128993690014,
|
|
"num_tokens": 368263.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.377443218231202,
|
|
"epoch": 0.016081000595592615,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5523,
|
|
"mean_token_accuracy": 0.03318903725594282,
|
|
"num_tokens": 381899.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.28380470275879,
|
|
"epoch": 0.016676593210244194,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3856,
|
|
"mean_token_accuracy": 0.03339306432753801,
|
|
"num_tokens": 393924.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.16828088760376,
|
|
"epoch": 0.017272185824895772,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2307,
|
|
"mean_token_accuracy": 0.03646030705422163,
|
|
"num_tokens": 404670.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.028338718414307,
|
|
"epoch": 0.01786777843954735,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1711,
|
|
"mean_token_accuracy": 0.032446819357573986,
|
|
"num_tokens": 418805.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.875869274139404,
|
|
"epoch": 0.01846337105419893,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1096,
|
|
"mean_token_accuracy": 0.0350328603759408,
|
|
"num_tokens": 434053.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.687991714477539,
|
|
"epoch": 0.019058963668850508,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9651,
|
|
"mean_token_accuracy": 0.03275042381137609,
|
|
"num_tokens": 447771.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.478072261810302,
|
|
"epoch": 0.019654556283502083,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8309,
|
|
"mean_token_accuracy": 0.035520490072667596,
|
|
"num_tokens": 462055.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.239253616333007,
|
|
"epoch": 0.02025014889815366,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7862,
|
|
"mean_token_accuracy": 0.034369570948183534,
|
|
"num_tokens": 475573.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.978817081451416,
|
|
"epoch": 0.02084574151280524,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.716,
|
|
"mean_token_accuracy": 0.030998582765460015,
|
|
"num_tokens": 490172.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.754789733886719,
|
|
"epoch": 0.02144133412745682,
|
|
"grad_norm": 0.6640625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.6854,
|
|
"mean_token_accuracy": 0.03425474334508181,
|
|
"num_tokens": 503073.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.57414264678955,
|
|
"epoch": 0.022036926742108397,
|
|
"grad_norm": 0.66015625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5492,
|
|
"mean_token_accuracy": 0.03272276725620031,
|
|
"num_tokens": 518422.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.40087013244629,
|
|
"epoch": 0.022632519356759976,
|
|
"grad_norm": 0.63671875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.6062,
|
|
"mean_token_accuracy": 0.03543335385620594,
|
|
"num_tokens": 531422.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.252633190155029,
|
|
"epoch": 0.023228111971411555,
|
|
"grad_norm": 0.6171875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.6646,
|
|
"mean_token_accuracy": 0.03285746406763792,
|
|
"num_tokens": 547556.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.170538139343261,
|
|
"epoch": 0.023823704586063133,
|
|
"grad_norm": 0.6796875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.5794,
|
|
"mean_token_accuracy": 0.033370182104408744,
|
|
"num_tokens": 559950.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.103077602386474,
|
|
"epoch": 0.024419297200714712,
|
|
"grad_norm": 0.51171875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.5337,
|
|
"mean_token_accuracy": 0.031332789547741415,
|
|
"num_tokens": 573158.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.034292221069336,
|
|
"epoch": 0.02501488981536629,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.5766,
|
|
"mean_token_accuracy": 0.031351211667060855,
|
|
"num_tokens": 587653.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.992253684997559,
|
|
"epoch": 0.02561048243001787,
|
|
"grad_norm": 0.5625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.5704,
|
|
"mean_token_accuracy": 0.03251508735120297,
|
|
"num_tokens": 599566.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.959266328811646,
|
|
"epoch": 0.026206075044669448,
|
|
"grad_norm": 0.578125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.4667,
|
|
"mean_token_accuracy": 0.03331163264811039,
|
|
"num_tokens": 613870.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.948250102996826,
|
|
"epoch": 0.026801667659321026,
|
|
"grad_norm": 0.57421875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.4818,
|
|
"mean_token_accuracy": 0.0346223758533597,
|
|
"num_tokens": 625417.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.9228109359741214,
|
|
"epoch": 0.0273972602739726,
|
|
"grad_norm": 0.58203125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.5592,
|
|
"mean_token_accuracy": 0.031082126125693322,
|
|
"num_tokens": 638091.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.910252237319947,
|
|
"epoch": 0.02799285288862418,
|
|
"grad_norm": 0.6328125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.4702,
|
|
"mean_token_accuracy": 0.03281628340482712,
|
|
"num_tokens": 653733.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.909072208404541,
|
|
"epoch": 0.02858844550327576,
|
|
"grad_norm": 0.59375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.5194,
|
|
"mean_token_accuracy": 0.03327430803328753,
|
|
"num_tokens": 667197.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.887023973464966,
|
|
"epoch": 0.029184038117927337,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.5134,
|
|
"mean_token_accuracy": 0.037746869027614594,
|
|
"num_tokens": 682333.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.89075927734375,
|
|
"epoch": 0.029779630732578916,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.5539,
|
|
"mean_token_accuracy": 0.032532981038093566,
|
|
"num_tokens": 698745.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.955071830749512,
|
|
"epoch": 0.030375223347230494,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4173,
|
|
"mean_token_accuracy": 0.043024342879652976,
|
|
"num_tokens": 713585.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.944690847396851,
|
|
"epoch": 0.030970815961882073,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.4623,
|
|
"mean_token_accuracy": 0.042671557515859604,
|
|
"num_tokens": 728735.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.956158876419067,
|
|
"epoch": 0.03156640857653365,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.4475,
|
|
"mean_token_accuracy": 0.04548847936093807,
|
|
"num_tokens": 742292.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.925923490524292,
|
|
"epoch": 0.03216200119118523,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.3578,
|
|
"mean_token_accuracy": 0.047962702065706256,
|
|
"num_tokens": 755915.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.94246187210083,
|
|
"epoch": 0.03275759380583681,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.4207,
|
|
"mean_token_accuracy": 0.04774568788707256,
|
|
"num_tokens": 769669.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.911481952667236,
|
|
"epoch": 0.03335318642048839,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.4256,
|
|
"mean_token_accuracy": 0.04661661200225353,
|
|
"num_tokens": 782871.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.880767726898194,
|
|
"epoch": 0.033948779035139966,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.2966,
|
|
"mean_token_accuracy": 0.0506436686962843,
|
|
"num_tokens": 796354.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.867405939102173,
|
|
"epoch": 0.034544371649791544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.4574,
|
|
"mean_token_accuracy": 0.05282125771045685,
|
|
"num_tokens": 810833.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.86374797821045,
|
|
"epoch": 0.03513996426444312,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.3082,
|
|
"mean_token_accuracy": 0.05726734437048435,
|
|
"num_tokens": 824970.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.800059223175049,
|
|
"epoch": 0.0357355568790947,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.2385,
|
|
"mean_token_accuracy": 0.05636283792555332,
|
|
"num_tokens": 838403.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.823443984985351,
|
|
"epoch": 0.03633114949374628,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.3552,
|
|
"mean_token_accuracy": 0.05279202722012997,
|
|
"num_tokens": 850970.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.811036491394043,
|
|
"epoch": 0.03692674210839786,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.3013,
|
|
"mean_token_accuracy": 0.05962081924080849,
|
|
"num_tokens": 864950.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.821821880340576,
|
|
"epoch": 0.03752233472304944,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.358,
|
|
"mean_token_accuracy": 0.06332920268177986,
|
|
"num_tokens": 876860.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.865830898284912,
|
|
"epoch": 0.038117927337701016,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.2622,
|
|
"mean_token_accuracy": 0.05612402558326721,
|
|
"num_tokens": 890278.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.752763891220093,
|
|
"epoch": 0.03871351995235259,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.267,
|
|
"mean_token_accuracy": 0.06026482917368412,
|
|
"num_tokens": 903716.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.753884935379029,
|
|
"epoch": 0.039309112567004166,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.2011,
|
|
"mean_token_accuracy": 0.06185343787074089,
|
|
"num_tokens": 919346.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.750566244125366,
|
|
"epoch": 0.039904705181655745,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.2541,
|
|
"mean_token_accuracy": 0.06152658350765705,
|
|
"num_tokens": 931959.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.695417499542236,
|
|
"epoch": 0.04050029779630732,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.16,
|
|
"mean_token_accuracy": 0.062984299659729,
|
|
"num_tokens": 947237.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.685136985778809,
|
|
"epoch": 0.0410958904109589,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.1835,
|
|
"mean_token_accuracy": 0.06309934109449386,
|
|
"num_tokens": 961650.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.685891962051391,
|
|
"epoch": 0.04169148302561048,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.1755,
|
|
"mean_token_accuracy": 0.06446794606745243,
|
|
"num_tokens": 976138.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.718321514129639,
|
|
"epoch": 0.04228707564026206,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.1981,
|
|
"mean_token_accuracy": 0.06850187592208386,
|
|
"num_tokens": 991306.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.708969354629517,
|
|
"epoch": 0.04288266825491364,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.1376,
|
|
"mean_token_accuracy": 0.06881025917828083,
|
|
"num_tokens": 1006494.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.608221101760864,
|
|
"epoch": 0.043478260869565216,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.0733,
|
|
"mean_token_accuracy": 0.07095063887536526,
|
|
"num_tokens": 1020458.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.748707485198975,
|
|
"epoch": 0.044073853484216795,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.2174,
|
|
"mean_token_accuracy": 0.06676653660833835,
|
|
"num_tokens": 1035801.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.570728588104248,
|
|
"epoch": 0.04466944609886837,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.0279,
|
|
"mean_token_accuracy": 0.07174774669110776,
|
|
"num_tokens": 1051671.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.636310958862305,
|
|
"epoch": 0.04526503871351995,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.0157,
|
|
"mean_token_accuracy": 0.07355342879891395,
|
|
"num_tokens": 1065580.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.610966634750366,
|
|
"epoch": 0.04586063132817153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.0201,
|
|
"mean_token_accuracy": 0.07639546617865563,
|
|
"num_tokens": 1078646.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.600120115280151,
|
|
"epoch": 0.04645622394282311,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.0033,
|
|
"mean_token_accuracy": 0.07510423436760902,
|
|
"num_tokens": 1090921.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.629261922836304,
|
|
"epoch": 0.04705181655747469,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.0276,
|
|
"mean_token_accuracy": 0.07344624996185303,
|
|
"num_tokens": 1103223.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.4967241287231445,
|
|
"epoch": 0.047647409172126266,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.938,
|
|
"mean_token_accuracy": 0.08089623451232911,
|
|
"num_tokens": 1117103.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.512509059906006,
|
|
"epoch": 0.048243001786777845,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.0582,
|
|
"mean_token_accuracy": 0.07738725878298283,
|
|
"num_tokens": 1131452.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.531740188598633,
|
|
"epoch": 0.048838594401429423,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9661,
|
|
"mean_token_accuracy": 0.08345204256474972,
|
|
"num_tokens": 1144755.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.527704954147339,
|
|
"epoch": 0.049434187016081,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.9606,
|
|
"mean_token_accuracy": 0.07925527319312095,
|
|
"num_tokens": 1157544.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.476634216308594,
|
|
"epoch": 0.05002977963073258,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.929,
|
|
"mean_token_accuracy": 0.08062414154410362,
|
|
"num_tokens": 1171753.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.422762823104859,
|
|
"epoch": 0.05062537224538416,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8737,
|
|
"mean_token_accuracy": 0.07864995375275612,
|
|
"num_tokens": 1186570.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.452899742126465,
|
|
"epoch": 0.05122096486003574,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.9745,
|
|
"mean_token_accuracy": 0.08109329342842102,
|
|
"num_tokens": 1201674.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.437095403671265,
|
|
"epoch": 0.051816557474687316,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8102,
|
|
"mean_token_accuracy": 0.08515282273292542,
|
|
"num_tokens": 1216060.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.481182050704956,
|
|
"epoch": 0.052412150089338895,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.8696,
|
|
"mean_token_accuracy": 0.08633813112974167,
|
|
"num_tokens": 1229736.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.398722457885742,
|
|
"epoch": 0.053007742703990474,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.8579,
|
|
"mean_token_accuracy": 0.08321957737207412,
|
|
"num_tokens": 1243253.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.358558320999146,
|
|
"epoch": 0.05360333531864205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8454,
|
|
"mean_token_accuracy": 0.08370575830340385,
|
|
"num_tokens": 1256399.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.358534049987793,
|
|
"epoch": 0.054198927933293624,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8999,
|
|
"mean_token_accuracy": 0.08046779558062553,
|
|
"num_tokens": 1270676.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.415665769577027,
|
|
"epoch": 0.0547945205479452,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8241,
|
|
"mean_token_accuracy": 0.09082722887396813,
|
|
"num_tokens": 1283059.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.483054494857788,
|
|
"epoch": 0.05539011316259678,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8842,
|
|
"mean_token_accuracy": 0.0829451285302639,
|
|
"num_tokens": 1297312.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.381071615219116,
|
|
"epoch": 0.05598570577724836,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8459,
|
|
"mean_token_accuracy": 0.08478990085422992,
|
|
"num_tokens": 1309608.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.31707239151001,
|
|
"epoch": 0.05658129839189994,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.829,
|
|
"mean_token_accuracy": 0.08446860313415527,
|
|
"num_tokens": 1323605.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.327056503295898,
|
|
"epoch": 0.05717689100655152,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.8202,
|
|
"mean_token_accuracy": 0.0890904888510704,
|
|
"num_tokens": 1335742.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.3317619323730465,
|
|
"epoch": 0.057772483621203095,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.8002,
|
|
"mean_token_accuracy": 0.08907385244965553,
|
|
"num_tokens": 1349190.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.346725845336914,
|
|
"epoch": 0.058368076235854674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.881,
|
|
"mean_token_accuracy": 0.0836374070495367,
|
|
"num_tokens": 1365737.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.2879852771759035,
|
|
"epoch": 0.05896366885050625,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.8055,
|
|
"mean_token_accuracy": 0.0872837707400322,
|
|
"num_tokens": 1380591.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.267280864715576,
|
|
"epoch": 0.05955926146515783,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7571,
|
|
"mean_token_accuracy": 0.09086202606558799,
|
|
"num_tokens": 1394303.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.285760402679443,
|
|
"epoch": 0.06015485407980941,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7195,
|
|
"mean_token_accuracy": 0.09099448174238205,
|
|
"num_tokens": 1407232.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.2401186466217045,
|
|
"epoch": 0.06075044669446099,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.7664,
|
|
"mean_token_accuracy": 0.08979170322418213,
|
|
"num_tokens": 1421822.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.341850996017456,
|
|
"epoch": 0.06134603930911257,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7861,
|
|
"mean_token_accuracy": 0.09510571733117104,
|
|
"num_tokens": 1434555.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.195777559280396,
|
|
"epoch": 0.061941631923764146,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.7399,
|
|
"mean_token_accuracy": 0.09447200521826744,
|
|
"num_tokens": 1446221.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.192428064346314,
|
|
"epoch": 0.06253722453841572,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6389,
|
|
"mean_token_accuracy": 0.09402211159467697,
|
|
"num_tokens": 1459623.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.193966436386108,
|
|
"epoch": 0.0631328171530673,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6863,
|
|
"mean_token_accuracy": 0.09898325428366661,
|
|
"num_tokens": 1474618.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.175309848785401,
|
|
"epoch": 0.06372840976771887,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.5813,
|
|
"mean_token_accuracy": 0.10318320542573929,
|
|
"num_tokens": 1486820.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.207240247726441,
|
|
"epoch": 0.06432400238237046,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7186,
|
|
"mean_token_accuracy": 0.091385018825531,
|
|
"num_tokens": 1500696.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.12197847366333,
|
|
"epoch": 0.06491959499702203,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.09674113467335702,
|
|
"num_tokens": 1513926.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.137995910644531,
|
|
"epoch": 0.06551518761167362,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7211,
|
|
"mean_token_accuracy": 0.09307532459497452,
|
|
"num_tokens": 1527390.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.130176258087158,
|
|
"epoch": 0.06611078022632519,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5932,
|
|
"mean_token_accuracy": 0.09782459288835525,
|
|
"num_tokens": 1540631.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.2148011207580565,
|
|
"epoch": 0.06670637284097677,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6975,
|
|
"mean_token_accuracy": 0.09347774386405945,
|
|
"num_tokens": 1554822.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.03975887298584,
|
|
"epoch": 0.06730196545562835,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5584,
|
|
"mean_token_accuracy": 0.09844642356038094,
|
|
"num_tokens": 1569702.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.067330551147461,
|
|
"epoch": 0.06789755807027993,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.6223,
|
|
"mean_token_accuracy": 0.09400645792484283,
|
|
"num_tokens": 1583023.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.115908527374268,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6192,
|
|
"mean_token_accuracy": 0.09033841267228127,
|
|
"num_tokens": 1597012.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.209295701980591,
|
|
"epoch": 0.06908874329958309,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.7117,
|
|
"mean_token_accuracy": 0.09010799154639244,
|
|
"num_tokens": 1610668.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.150216722488404,
|
|
"epoch": 0.06968433591423466,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7749,
|
|
"mean_token_accuracy": 0.08841467723250389,
|
|
"num_tokens": 1628312.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.064253616333008,
|
|
"epoch": 0.07027992852888625,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.561,
|
|
"mean_token_accuracy": 0.09543564394116402,
|
|
"num_tokens": 1642933.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.070201730728149,
|
|
"epoch": 0.07087552114353782,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6413,
|
|
"mean_token_accuracy": 0.09548119828104973,
|
|
"num_tokens": 1659141.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.122019195556641,
|
|
"epoch": 0.0714711137581894,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.6093,
|
|
"mean_token_accuracy": 0.09905487075448036,
|
|
"num_tokens": 1673555.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.053143501281738,
|
|
"epoch": 0.07206670637284097,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6697,
|
|
"mean_token_accuracy": 0.10019941478967667,
|
|
"num_tokens": 1688619.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.0462723731994625,
|
|
"epoch": 0.07266229898749256,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5425,
|
|
"mean_token_accuracy": 0.10600225329399109,
|
|
"num_tokens": 1702096.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.132640171051025,
|
|
"epoch": 0.07325789160214413,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6215,
|
|
"mean_token_accuracy": 0.10150862634181976,
|
|
"num_tokens": 1716915.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.936264419555664,
|
|
"epoch": 0.07385348421679572,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4838,
|
|
"mean_token_accuracy": 0.10570442453026771,
|
|
"num_tokens": 1730743.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.994334936141968,
|
|
"epoch": 0.07444907683144729,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5033,
|
|
"mean_token_accuracy": 0.10180857703089714,
|
|
"num_tokens": 1744537.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.99732551574707,
|
|
"epoch": 0.07504466944609887,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5182,
|
|
"mean_token_accuracy": 0.10188300311565399,
|
|
"num_tokens": 1757394.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.927392387390137,
|
|
"epoch": 0.07564026206075045,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.4358,
|
|
"mean_token_accuracy": 0.10770431458950043,
|
|
"num_tokens": 1772966.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.026741075515747,
|
|
"epoch": 0.07623585467540203,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5425,
|
|
"mean_token_accuracy": 0.10556690841913223,
|
|
"num_tokens": 1786753.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.861152505874633,
|
|
"epoch": 0.0768314472900536,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.3763,
|
|
"mean_token_accuracy": 0.11122649013996125,
|
|
"num_tokens": 1799665.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.868685913085938,
|
|
"epoch": 0.07742703990470517,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4846,
|
|
"mean_token_accuracy": 0.10084349736571312,
|
|
"num_tokens": 1813363.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.994466543197632,
|
|
"epoch": 0.07802263251935676,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5685,
|
|
"mean_token_accuracy": 0.10275080278515816,
|
|
"num_tokens": 1827715.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.026219892501831,
|
|
"epoch": 0.07861822513400833,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.6268,
|
|
"mean_token_accuracy": 0.10650768801569939,
|
|
"num_tokens": 1842248.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.900357961654663,
|
|
"epoch": 0.07921381774865992,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5266,
|
|
"mean_token_accuracy": 0.10092263966798783,
|
|
"num_tokens": 1855993.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.938298559188842,
|
|
"epoch": 0.07980941036331149,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4194,
|
|
"mean_token_accuracy": 0.10466923043131829,
|
|
"num_tokens": 1869053.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.966603469848633,
|
|
"epoch": 0.08040500297796307,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5734,
|
|
"mean_token_accuracy": 0.09326259717345238,
|
|
"num_tokens": 1883371.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.978801679611206,
|
|
"epoch": 0.08100059559261465,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.09706588312983513,
|
|
"num_tokens": 1899299.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.844657135009766,
|
|
"epoch": 0.08159618820726623,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.11091078594326972,
|
|
"num_tokens": 1913908.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.786835432052612,
|
|
"epoch": 0.0821917808219178,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4239,
|
|
"mean_token_accuracy": 0.10840331017971039,
|
|
"num_tokens": 1928379.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.835281419754028,
|
|
"epoch": 0.08278737343656939,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4283,
|
|
"mean_token_accuracy": 0.10425578132271766,
|
|
"num_tokens": 1942308.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.762073135375976,
|
|
"epoch": 0.08338296605122096,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.2387,
|
|
"mean_token_accuracy": 0.1136186271905899,
|
|
"num_tokens": 1954659.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.8574135303497314,
|
|
"epoch": 0.08397855866587255,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4196,
|
|
"mean_token_accuracy": 0.10803430527448654,
|
|
"num_tokens": 1969847.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.853384637832642,
|
|
"epoch": 0.08457415128052412,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.429,
|
|
"mean_token_accuracy": 0.105791487544775,
|
|
"num_tokens": 1983973.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.732511758804321,
|
|
"epoch": 0.0851697438951757,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.3518,
|
|
"mean_token_accuracy": 0.11114974096417427,
|
|
"num_tokens": 1997786.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.8639874935150145,
|
|
"epoch": 0.08576533650982728,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5061,
|
|
"mean_token_accuracy": 0.10455258190631866,
|
|
"num_tokens": 2012849.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.807453870773315,
|
|
"epoch": 0.08636092912447886,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4032,
|
|
"mean_token_accuracy": 0.10928454548120499,
|
|
"num_tokens": 2026935.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.772582387924194,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3773,
|
|
"mean_token_accuracy": 0.1119888186454773,
|
|
"num_tokens": 2039722.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.834014654159546,
|
|
"epoch": 0.08755211435378202,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.11609113588929176,
|
|
"num_tokens": 2053064.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.904176330566406,
|
|
"epoch": 0.08814770696843359,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5257,
|
|
"mean_token_accuracy": 0.10476789623498917,
|
|
"num_tokens": 2065401.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.737480878829956,
|
|
"epoch": 0.08874329958308518,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3052,
|
|
"mean_token_accuracy": 0.11336522176861763,
|
|
"num_tokens": 2078975.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.735174989700317,
|
|
"epoch": 0.08933889219773675,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3974,
|
|
"mean_token_accuracy": 0.10913275107741356,
|
|
"num_tokens": 2094427.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.722973251342774,
|
|
"epoch": 0.08993448481238833,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3871,
|
|
"mean_token_accuracy": 0.11023307666182518,
|
|
"num_tokens": 2108993.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.706762838363647,
|
|
"epoch": 0.0905300774270399,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.11945048868656158,
|
|
"num_tokens": 2121913.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.8349220752716064,
|
|
"epoch": 0.09112567004169149,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3578,
|
|
"mean_token_accuracy": 0.11043609380722046,
|
|
"num_tokens": 2135224.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.7104603290557865,
|
|
"epoch": 0.09172126265634306,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3964,
|
|
"mean_token_accuracy": 0.10966008827090264,
|
|
"num_tokens": 2150603.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.725274705886841,
|
|
"epoch": 0.09231685527099463,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3326,
|
|
"mean_token_accuracy": 0.11593154519796371,
|
|
"num_tokens": 2165710.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.652264928817749,
|
|
"epoch": 0.09291244788564622,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.11332699209451676,
|
|
"num_tokens": 2180477.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.686633014678955,
|
|
"epoch": 0.09350804050029779,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2586,
|
|
"mean_token_accuracy": 0.11259361952543259,
|
|
"num_tokens": 2193654.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.678912401199341,
|
|
"epoch": 0.09410363311494938,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.12137154266238212,
|
|
"num_tokens": 2208161.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.70740065574646,
|
|
"epoch": 0.09469922572960095,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3116,
|
|
"mean_token_accuracy": 0.11378278210759163,
|
|
"num_tokens": 2222306.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.733925533294678,
|
|
"epoch": 0.09529481834425253,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4299,
|
|
"mean_token_accuracy": 0.11220810115337372,
|
|
"num_tokens": 2237919.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.621367502212524,
|
|
"epoch": 0.0958904109589041,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.2794,
|
|
"mean_token_accuracy": 0.11783934608101845,
|
|
"num_tokens": 2253244.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.794623804092407,
|
|
"epoch": 0.09648600357355569,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.10893271565437317,
|
|
"num_tokens": 2267429.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.614417934417725,
|
|
"epoch": 0.09708159618820726,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.11502965763211251,
|
|
"num_tokens": 2281830.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.656324005126953,
|
|
"epoch": 0.09767718880285885,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.11383071094751358,
|
|
"num_tokens": 2297243.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.720933055877685,
|
|
"epoch": 0.09827278141751042,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.11662096157670021,
|
|
"num_tokens": 2308952.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.655382871627808,
|
|
"epoch": 0.098868374032162,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2587,
|
|
"mean_token_accuracy": 0.11734143644571304,
|
|
"num_tokens": 2321645.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.577720689773559,
|
|
"epoch": 0.09946396664681358,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.2649,
|
|
"mean_token_accuracy": 0.11464339271187782,
|
|
"num_tokens": 2333309.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.664750051498413,
|
|
"epoch": 0.10005955926146516,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.2765,
|
|
"mean_token_accuracy": 0.1120231382548809,
|
|
"num_tokens": 2347843.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.639902114868164,
|
|
"epoch": 0.10065515187611673,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.11536335200071335,
|
|
"num_tokens": 2361024.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.580413913726806,
|
|
"epoch": 0.10125074449076832,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2427,
|
|
"mean_token_accuracy": 0.11439065337181091,
|
|
"num_tokens": 2375498.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.6116190433502195,
|
|
"epoch": 0.10184633710541989,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.1921,
|
|
"mean_token_accuracy": 0.11994925290346145,
|
|
"num_tokens": 2392063.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.6043500900268555,
|
|
"epoch": 0.10244192972007148,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.1885,
|
|
"mean_token_accuracy": 0.12353525608778,
|
|
"num_tokens": 2407267.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.604389762878418,
|
|
"epoch": 0.10303752233472305,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.1569,
|
|
"mean_token_accuracy": 0.11905085891485215,
|
|
"num_tokens": 2421814.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.589984607696533,
|
|
"epoch": 0.10363311494937463,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2479,
|
|
"mean_token_accuracy": 0.11835012435913086,
|
|
"num_tokens": 2438931.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.581540298461914,
|
|
"epoch": 0.1042287075640262,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.12253711521625518,
|
|
"num_tokens": 2451210.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.536899662017822,
|
|
"epoch": 0.10482430017867779,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2706,
|
|
"mean_token_accuracy": 0.1189447209239006,
|
|
"num_tokens": 2465343.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.474660968780517,
|
|
"epoch": 0.10541989279332936,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.11866791471838951,
|
|
"num_tokens": 2478732.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.55727915763855,
|
|
"epoch": 0.10601548540798095,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.1909,
|
|
"mean_token_accuracy": 0.1250196047127247,
|
|
"num_tokens": 2493362.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.629166555404663,
|
|
"epoch": 0.10661107802263252,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.12227484285831451,
|
|
"num_tokens": 2506154.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.558849668502807,
|
|
"epoch": 0.1072066706372841,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.1186575561761856,
|
|
"num_tokens": 2519189.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.536633110046386,
|
|
"epoch": 0.10780226325193568,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.11862791329622269,
|
|
"num_tokens": 2532486.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.55183367729187,
|
|
"epoch": 0.10839785586658725,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.1728,
|
|
"mean_token_accuracy": 0.12181233391165733,
|
|
"num_tokens": 2546239.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.576446437835694,
|
|
"epoch": 0.10899344848123883,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.11069378778338432,
|
|
"num_tokens": 2563054.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.497651290893555,
|
|
"epoch": 0.1095890410958904,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.11671268492937088,
|
|
"num_tokens": 2577503.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.728296566009521,
|
|
"epoch": 0.11018463371054199,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.11801609098911285,
|
|
"num_tokens": 2591506.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.558925008773803,
|
|
"epoch": 0.11078022632519356,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2352,
|
|
"mean_token_accuracy": 0.11240646243095398,
|
|
"num_tokens": 2607777.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.600870990753174,
|
|
"epoch": 0.11137581893984515,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2738,
|
|
"mean_token_accuracy": 0.11794044449925423,
|
|
"num_tokens": 2619506.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.54284782409668,
|
|
"epoch": 0.11197141155449672,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.11557438299059868,
|
|
"num_tokens": 2634182.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.573303747177124,
|
|
"epoch": 0.1125670041691483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1622,
|
|
"mean_token_accuracy": 0.12252075374126434,
|
|
"num_tokens": 2649266.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.426169967651367,
|
|
"epoch": 0.11316259678379988,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.12529388517141343,
|
|
"num_tokens": 2662745.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.451272201538086,
|
|
"epoch": 0.11375818939845146,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.12483394667506217,
|
|
"num_tokens": 2676071.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.480741739273071,
|
|
"epoch": 0.11435378201310303,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.1708,
|
|
"mean_token_accuracy": 0.11926832273602486,
|
|
"num_tokens": 2690511.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.507002210617065,
|
|
"epoch": 0.11494937462775462,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.1042,
|
|
"mean_token_accuracy": 0.1290435165166855,
|
|
"num_tokens": 2704891.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.419072484970092,
|
|
"epoch": 0.11554496724240619,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.1196157082915306,
|
|
"num_tokens": 2718288.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.415342903137207,
|
|
"epoch": 0.11614055985705778,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.12383151575922965,
|
|
"num_tokens": 2732853.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.471505546569825,
|
|
"epoch": 0.11673615247170935,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2046,
|
|
"mean_token_accuracy": 0.11899536103010178,
|
|
"num_tokens": 2746801.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.459245824813843,
|
|
"epoch": 0.11733174508636093,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.112,
|
|
"mean_token_accuracy": 0.11679932549595833,
|
|
"num_tokens": 2760896.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.412615394592285,
|
|
"epoch": 0.1179273377010125,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.0678,
|
|
"mean_token_accuracy": 0.12289713546633721,
|
|
"num_tokens": 2774464.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.399781894683838,
|
|
"epoch": 0.11852293031566409,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.11976283565163612,
|
|
"num_tokens": 2789696.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.381843900680542,
|
|
"epoch": 0.11911852293031566,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.0924,
|
|
"mean_token_accuracy": 0.12352070063352585,
|
|
"num_tokens": 2802830.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.375089693069458,
|
|
"epoch": 0.11971411554496725,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999999974174771,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.1244612418115139,
|
|
"num_tokens": 2816983.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.407578754425049,
|
|
"epoch": 0.12030970815961882,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999869259778,
|
|
"loss": 6.1444,
|
|
"mean_token_accuracy": 0.12450993210077285,
|
|
"num_tokens": 2831192.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.504035902023316,
|
|
"epoch": 0.1209053007742704,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999999683640947,
|
|
"loss": 6.1288,
|
|
"mean_token_accuracy": 0.12754198983311654,
|
|
"num_tokens": 2844621.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.333795022964478,
|
|
"epoch": 0.12150089338892198,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999999417318286,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.12644676640629768,
|
|
"num_tokens": 2857056.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.424797821044922,
|
|
"epoch": 0.12209648600357356,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999999070291805,
|
|
"loss": 6.2119,
|
|
"mean_token_accuracy": 0.1165068842470646,
|
|
"num_tokens": 2870129.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.512726831436157,
|
|
"epoch": 0.12269207861822513,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004999998642561514,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.11828980967402458,
|
|
"num_tokens": 2883395.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.3232306957244875,
|
|
"epoch": 0.1232876712328767,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999998134127432,
|
|
"loss": 5.9703,
|
|
"mean_token_accuracy": 0.1303369678556919,
|
|
"num_tokens": 2897295.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.368861484527588,
|
|
"epoch": 0.12388326384752829,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999997544989574,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.12177211344242096,
|
|
"num_tokens": 2910532.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.435405492782593,
|
|
"epoch": 0.12447885646217986,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999996875147963,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.12170586735010147,
|
|
"num_tokens": 2924713.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.515688467025757,
|
|
"epoch": 0.12507444907683143,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999996124602621,
|
|
"loss": 6.2032,
|
|
"mean_token_accuracy": 0.11491205915808678,
|
|
"num_tokens": 2941652.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.393681001663208,
|
|
"epoch": 0.12567004169148302,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999995293353578,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.12318666279315948,
|
|
"num_tokens": 2953863.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.332122325897217,
|
|
"epoch": 0.1262656343061346,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999994381400862,
|
|
"loss": 6.0083,
|
|
"mean_token_accuracy": 0.1310349240899086,
|
|
"num_tokens": 2965301.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.278225326538086,
|
|
"epoch": 0.1268612269207862,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999993388744504,
|
|
"loss": 6.0302,
|
|
"mean_token_accuracy": 0.12268994748592377,
|
|
"num_tokens": 2979693.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.272536945343018,
|
|
"epoch": 0.12745681953543775,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999992315384543,
|
|
"loss": 5.9527,
|
|
"mean_token_accuracy": 0.13503969833254814,
|
|
"num_tokens": 2993089.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.530353593826294,
|
|
"epoch": 0.12805241215008933,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999991161321014,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.12093808650970458,
|
|
"num_tokens": 3006201.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.327599763870239,
|
|
"epoch": 0.12864800476474092,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999989926553962,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.12528552636504173,
|
|
"num_tokens": 3021067.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.2632410526275635,
|
|
"epoch": 0.1292435973793925,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000499998861108343,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.12118237018585205,
|
|
"num_tokens": 3035126.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.388171243667602,
|
|
"epoch": 0.12983918999404406,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999987214909464,
|
|
"loss": 6.0118,
|
|
"mean_token_accuracy": 0.12827680110931397,
|
|
"num_tokens": 3048811.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.295111227035522,
|
|
"epoch": 0.13043478260869565,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999985738032115,
|
|
"loss": 6.0147,
|
|
"mean_token_accuracy": 0.12736694738268853,
|
|
"num_tokens": 3061651.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.3264165878295895,
|
|
"epoch": 0.13103037522334723,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999984180451436,
|
|
"loss": 6.0131,
|
|
"mean_token_accuracy": 0.12697443291544913,
|
|
"num_tokens": 3074075.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.3050531387329105,
|
|
"epoch": 0.13162596783799882,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999982542167483,
|
|
"loss": 5.9899,
|
|
"mean_token_accuracy": 0.1274932511150837,
|
|
"num_tokens": 3086217.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.262260293960571,
|
|
"epoch": 0.13222156045265038,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999980823180314,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.12617919519543647,
|
|
"num_tokens": 3101375.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.304317045211792,
|
|
"epoch": 0.13281715306730196,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499997902348999,
|
|
"loss": 6.02,
|
|
"mean_token_accuracy": 0.12563774064183236,
|
|
"num_tokens": 3116799.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.35048394203186,
|
|
"epoch": 0.13341274568195355,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999977143096578,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.1243694968521595,
|
|
"num_tokens": 3130224.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.344778823852539,
|
|
"epoch": 0.13400833829660513,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999975182000143,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.12919701635837555,
|
|
"num_tokens": 3145627.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.211950254440308,
|
|
"epoch": 0.1346039309112567,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999973140200759,
|
|
"loss": 5.8887,
|
|
"mean_token_accuracy": 0.1368369199335575,
|
|
"num_tokens": 3159927.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.157776784896851,
|
|
"epoch": 0.13519952352590828,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999971017698495,
|
|
"loss": 5.8927,
|
|
"mean_token_accuracy": 0.13457455784082412,
|
|
"num_tokens": 3174135.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.223761987686157,
|
|
"epoch": 0.13579511614055986,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999968814493428,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.1311629109084606,
|
|
"num_tokens": 3186673.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.327444362640381,
|
|
"epoch": 0.13639070875521145,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999966530585639,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.11745902895927429,
|
|
"num_tokens": 3201645.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.238715696334839,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999964165975209,
|
|
"loss": 5.9617,
|
|
"mean_token_accuracy": 0.13160938993096352,
|
|
"num_tokens": 3215255.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.319231986999512,
|
|
"epoch": 0.1375818939845146,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999961720662221,
|
|
"loss": 5.9325,
|
|
"mean_token_accuracy": 0.13657833486795426,
|
|
"num_tokens": 3228207.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.222438335418701,
|
|
"epoch": 0.13817748659916618,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999959194646766,
|
|
"loss": 6.0412,
|
|
"mean_token_accuracy": 0.13396313041448593,
|
|
"num_tokens": 3242242.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.300257539749145,
|
|
"epoch": 0.13877307921381773,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999956587928932,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.13306989818811416,
|
|
"num_tokens": 3257408.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.260866117477417,
|
|
"epoch": 0.13936867182846932,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999953900508814,
|
|
"loss": 5.9639,
|
|
"mean_token_accuracy": 0.129524414986372,
|
|
"num_tokens": 3269991.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.170885848999023,
|
|
"epoch": 0.1399642644431209,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999951132386507,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.1295623980462551,
|
|
"num_tokens": 3285119.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.208763122558594,
|
|
"epoch": 0.1405598570577725,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999948283562111,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.12472678646445275,
|
|
"num_tokens": 3299102.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.304540395736694,
|
|
"epoch": 0.14115544967242405,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499994535403573,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.13086569234728812,
|
|
"num_tokens": 3313907.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.254537677764892,
|
|
"epoch": 0.14175104228707563,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999942343807465,
|
|
"loss": 5.9941,
|
|
"mean_token_accuracy": 0.12761559188365937,
|
|
"num_tokens": 3326128.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.257322597503662,
|
|
"epoch": 0.14234663490172722,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999939252877428,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.12958202362060547,
|
|
"num_tokens": 3339257.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.337223196029663,
|
|
"epoch": 0.1429422275163788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999936081245727,
|
|
"loss": 6.0419,
|
|
"mean_token_accuracy": 0.12149293422698974,
|
|
"num_tokens": 3353893.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.252517747879028,
|
|
"epoch": 0.14353782013103036,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999932828912478,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.13144316002726555,
|
|
"num_tokens": 3370872.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.252450323104858,
|
|
"epoch": 0.14413341274568195,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999929495877796,
|
|
"loss": 6.0004,
|
|
"mean_token_accuracy": 0.13029421120882034,
|
|
"num_tokens": 3384741.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.208795642852783,
|
|
"epoch": 0.14472900536033353,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999926082141801,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.13095673248171807,
|
|
"num_tokens": 3399813.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.242795705795288,
|
|
"epoch": 0.14532459797498512,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999922587704616,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.13632318675518035,
|
|
"num_tokens": 3413314.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.179244565963745,
|
|
"epoch": 0.14592019058963668,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999919012566366,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.13855719268321992,
|
|
"num_tokens": 3427973.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.1802732944488525,
|
|
"epoch": 0.14651578320428826,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999915356727179,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.13377300053834915,
|
|
"num_tokens": 3443097.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.246569728851318,
|
|
"epoch": 0.14711137581893985,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999911620187186,
|
|
"loss": 6.021,
|
|
"mean_token_accuracy": 0.12546632513403894,
|
|
"num_tokens": 3456922.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.243866634368897,
|
|
"epoch": 0.14770696843359143,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999907802946521,
|
|
"loss": 5.9183,
|
|
"mean_token_accuracy": 0.1375621698796749,
|
|
"num_tokens": 3471247.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.177654361724853,
|
|
"epoch": 0.148302561048243,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999903905005323,
|
|
"loss": 5.8653,
|
|
"mean_token_accuracy": 0.13714087158441543,
|
|
"num_tokens": 3485026.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.271946573257447,
|
|
"epoch": 0.14889815366289458,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999899926363729,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.13483964279294014,
|
|
"num_tokens": 3498012.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.2273016452789305,
|
|
"epoch": 0.14949374627754616,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999895867021882,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.1265692263841629,
|
|
"num_tokens": 3511732.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.1190019130706785,
|
|
"epoch": 0.15008933889219775,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999891726979928,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.1352582648396492,
|
|
"num_tokens": 3527204.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.21186671257019,
|
|
"epoch": 0.1506849315068493,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999887506238018,
|
|
"loss": 5.9262,
|
|
"mean_token_accuracy": 0.12997026965022088,
|
|
"num_tokens": 3540571.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.112713384628296,
|
|
"epoch": 0.1512805241215009,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049998832047963,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.13946565240621567,
|
|
"num_tokens": 3553888.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.157454872131348,
|
|
"epoch": 0.15187611673615248,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999878822654929,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.13053104430437087,
|
|
"num_tokens": 3565304.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.218049049377441,
|
|
"epoch": 0.15247170935080406,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999874359814064,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.13851200342178344,
|
|
"num_tokens": 3580109.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.0666327476501465,
|
|
"epoch": 0.15306730196545562,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999869816273863,
|
|
"loss": 5.8879,
|
|
"mean_token_accuracy": 0.13641879782080651,
|
|
"num_tokens": 3594204.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.171440553665161,
|
|
"epoch": 0.1536628945801072,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999865192034489,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.1309145838022232,
|
|
"num_tokens": 3608722.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.045901823043823,
|
|
"epoch": 0.1542584871947588,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499986048709611,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.13367475122213363,
|
|
"num_tokens": 3624597.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.179301786422729,
|
|
"epoch": 0.15485407980941035,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999855701458893,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.1315551571547985,
|
|
"num_tokens": 3641733.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.143159103393555,
|
|
"epoch": 0.15544967242406194,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999850835123009,
|
|
"loss": 5.8434,
|
|
"mean_token_accuracy": 0.1379377357661724,
|
|
"num_tokens": 3654188.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.202222394943237,
|
|
"epoch": 0.15604526503871352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999845888088635,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.1310037076473236,
|
|
"num_tokens": 3667738.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.162489032745361,
|
|
"epoch": 0.1566408576533651,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999840860355946,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.13672316521406175,
|
|
"num_tokens": 3682616.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.092942190170288,
|
|
"epoch": 0.15723645026801666,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999835751925124,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.13373669609427452,
|
|
"num_tokens": 3695873.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.259343481063842,
|
|
"epoch": 0.15783204288266825,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999830562796351,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.1330730862915516,
|
|
"num_tokens": 3710117.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.187768888473511,
|
|
"epoch": 0.15842763549731984,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999825292969814,
|
|
"loss": 5.9429,
|
|
"mean_token_accuracy": 0.13421416878700257,
|
|
"num_tokens": 3723153.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.122033786773682,
|
|
"epoch": 0.15902322811197142,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999819942445703,
|
|
"loss": 5.9251,
|
|
"mean_token_accuracy": 0.12868732511997222,
|
|
"num_tokens": 3736970.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.176203823089599,
|
|
"epoch": 0.15961882072662298,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999814511224207,
|
|
"loss": 5.9061,
|
|
"mean_token_accuracy": 0.13429975584149362,
|
|
"num_tokens": 3750737.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.204562568664551,
|
|
"epoch": 0.16021441334127456,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999808999305523,
|
|
"loss": 5.9856,
|
|
"mean_token_accuracy": 0.13239325806498528,
|
|
"num_tokens": 3764955.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.120605897903443,
|
|
"epoch": 0.16081000595592615,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999803406689848,
|
|
"loss": 5.7805,
|
|
"mean_token_accuracy": 0.13752676397562028,
|
|
"num_tokens": 3780107.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.095135593414307,
|
|
"epoch": 0.16140559857057774,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999797733377384,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.13585890531539918,
|
|
"num_tokens": 3794609.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.1934168338775635,
|
|
"epoch": 0.1620011911852293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999791979368332,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.13824013844132424,
|
|
"num_tokens": 3808870.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.155633926391602,
|
|
"epoch": 0.16259678379988088,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999786144662899,
|
|
"loss": 5.9078,
|
|
"mean_token_accuracy": 0.13579775020480156,
|
|
"num_tokens": 3822608.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.087682104110717,
|
|
"epoch": 0.16319237641453246,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999780229261295,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.1425986669957638,
|
|
"num_tokens": 3837175.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.055517578125,
|
|
"epoch": 0.16378796902918405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999774233163734,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.14461472779512405,
|
|
"num_tokens": 3851298.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 5.9919859886169435,
|
|
"epoch": 0.1643835616438356,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999768156370428,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.13986781537532805,
|
|
"num_tokens": 3865396.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.064241790771485,
|
|
"epoch": 0.1649791542584872,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999761998881596,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.14307337179780005,
|
|
"num_tokens": 3876827.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.164361906051636,
|
|
"epoch": 0.16557474687313878,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999755760697459,
|
|
"loss": 5.9011,
|
|
"mean_token_accuracy": 0.1336224891245365,
|
|
"num_tokens": 3892707.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.203294897079468,
|
|
"epoch": 0.16617033948779036,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499974944181824,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.1365553431212902,
|
|
"num_tokens": 3906193.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.9282581329345705,
|
|
"epoch": 0.16676593210244192,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999743042244167,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.14891034066677095,
|
|
"num_tokens": 3919175.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.144384336471558,
|
|
"epoch": 0.1673615247170935,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499973656197547,
|
|
"loss": 5.9674,
|
|
"mean_token_accuracy": 0.1305065281689167,
|
|
"num_tokens": 3933207.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.057987260818481,
|
|
"epoch": 0.1679571173317451,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999730001012379,
|
|
"loss": 5.7858,
|
|
"mean_token_accuracy": 0.14294685795903206,
|
|
"num_tokens": 3945962.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.053352546691895,
|
|
"epoch": 0.16855270994639668,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999723359355131,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.1461661621928215,
|
|
"num_tokens": 3959645.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.040371036529541,
|
|
"epoch": 0.16914830256104824,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999716637003965,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.13801866844296456,
|
|
"num_tokens": 3975142.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.112378263473511,
|
|
"epoch": 0.16974389517569982,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499970983395912,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.13851202577352523,
|
|
"num_tokens": 3989214.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.057251453399658,
|
|
"epoch": 0.1703394877903514,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999702950220841,
|
|
"loss": 5.8493,
|
|
"mean_token_accuracy": 0.1395124040544033,
|
|
"num_tokens": 4003753.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.071414852142334,
|
|
"epoch": 0.17093508040500296,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999695985789376,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.1433809742331505,
|
|
"num_tokens": 4018739.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.13561372756958,
|
|
"epoch": 0.17153067301965455,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999688940664972,
|
|
"loss": 5.882,
|
|
"mean_token_accuracy": 0.13892385587096215,
|
|
"num_tokens": 4031822.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.02050461769104,
|
|
"epoch": 0.17212626563430614,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999681814847884,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.137375108897686,
|
|
"num_tokens": 4044757.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.991058826446533,
|
|
"epoch": 0.17272185824895772,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999674608338367,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.14199545755982398,
|
|
"num_tokens": 4059795.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.073600339889526,
|
|
"epoch": 0.17331745086360928,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999667321136681,
|
|
"loss": 5.8503,
|
|
"mean_token_accuracy": 0.13699849992990493,
|
|
"num_tokens": 4074772.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.116254615783691,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999659953243085,
|
|
"loss": 5.8433,
|
|
"mean_token_accuracy": 0.13740890696644784,
|
|
"num_tokens": 4088534.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.042709302902222,
|
|
"epoch": 0.17450863609291245,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999652504657844,
|
|
"loss": 5.7693,
|
|
"mean_token_accuracy": 0.1436406798660755,
|
|
"num_tokens": 4101729.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.04177188873291,
|
|
"epoch": 0.17510422870756404,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999644975381226,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.14489644914865493,
|
|
"num_tokens": 4114463.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.989459562301636,
|
|
"epoch": 0.1756998213222156,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049996373654135,
|
|
"loss": 5.7785,
|
|
"mean_token_accuracy": 0.146892012655735,
|
|
"num_tokens": 4125822.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.07545657157898,
|
|
"epoch": 0.17629541393686718,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999629674754939,
|
|
"loss": 5.7073,
|
|
"mean_token_accuracy": 0.14525049775838852,
|
|
"num_tokens": 4139385.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.043941879272461,
|
|
"epoch": 0.17689100655151876,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999621903405819,
|
|
"loss": 5.8951,
|
|
"mean_token_accuracy": 0.1356865182518959,
|
|
"num_tokens": 4153713.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.044046068191529,
|
|
"epoch": 0.17748659916617035,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999614051366421,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.14461283832788469,
|
|
"num_tokens": 4167030.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.990119695663452,
|
|
"epoch": 0.1780821917808219,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999606118637022,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.14729824513196946,
|
|
"num_tokens": 4179525.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.981477880477906,
|
|
"epoch": 0.1786777843954735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999598105217911,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.14276750460267068,
|
|
"num_tokens": 4193234.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.173784637451172,
|
|
"epoch": 0.17927337701012508,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999590011109373,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.128591887652874,
|
|
"num_tokens": 4207822.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.923196935653687,
|
|
"epoch": 0.17986896962477666,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049995818363117,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.14714332669973373,
|
|
"num_tokens": 4219990.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.953115797042846,
|
|
"epoch": 0.18046456223942822,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999573580825182,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.15343131870031357,
|
|
"num_tokens": 4232842.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.9914970874786375,
|
|
"epoch": 0.1810601548540798,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999565244650119,
|
|
"loss": 5.7544,
|
|
"mean_token_accuracy": 0.13864349573850632,
|
|
"num_tokens": 4247750.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.050769424438476,
|
|
"epoch": 0.1816557474687314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999556827786807,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.1400708667933941,
|
|
"num_tokens": 4260757.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.06231541633606,
|
|
"epoch": 0.18225134008338298,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999548330235549,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.14363204836845397,
|
|
"num_tokens": 4274430.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.96493010520935,
|
|
"epoch": 0.18284693269803454,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999539751996651,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.14499881193041803,
|
|
"num_tokens": 4288289.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.992290449142456,
|
|
"epoch": 0.18344252531268612,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499953109307042,
|
|
"loss": 5.8219,
|
|
"mean_token_accuracy": 0.1416143000125885,
|
|
"num_tokens": 4303460.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.035411548614502,
|
|
"epoch": 0.1840381179273377,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999522353457165,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.13796049132943153,
|
|
"num_tokens": 4317812.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.015031242370606,
|
|
"epoch": 0.18463371054198927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999513533157201,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.14893085807561873,
|
|
"num_tokens": 4331298.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.161585998535156,
|
|
"epoch": 0.18522930315664085,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999504632170844,
|
|
"loss": 5.8794,
|
|
"mean_token_accuracy": 0.1360538810491562,
|
|
"num_tokens": 4347241.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.964785718917847,
|
|
"epoch": 0.18582489577129244,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999495650498413,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.14079782590270043,
|
|
"num_tokens": 4363523.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.911650562286377,
|
|
"epoch": 0.18642048838594402,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999486588140231,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.15331710651516914,
|
|
"num_tokens": 4375701.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.014779376983642,
|
|
"epoch": 0.18701608100059558,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999477445096623,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.14194864854216577,
|
|
"num_tokens": 4388482.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.080461072921753,
|
|
"epoch": 0.18761167361524717,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999468221367916,
|
|
"loss": 5.8348,
|
|
"mean_token_accuracy": 0.13843949511647224,
|
|
"num_tokens": 4404275.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.975428628921509,
|
|
"epoch": 0.18820726622989875,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999458916954442,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.14692061692476271,
|
|
"num_tokens": 4418076.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.872400999069214,
|
|
"epoch": 0.18880285884455034,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999449531856532,
|
|
"loss": 5.6354,
|
|
"mean_token_accuracy": 0.15272490680217743,
|
|
"num_tokens": 4431241.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.013757419586182,
|
|
"epoch": 0.1893984514592019,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999440066074526,
|
|
"loss": 5.7146,
|
|
"mean_token_accuracy": 0.14599696099758147,
|
|
"num_tokens": 4443915.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.0449987888336185,
|
|
"epoch": 0.18999404407385348,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999430519608762,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.13701653406023978,
|
|
"num_tokens": 4459976.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.991712522506714,
|
|
"epoch": 0.19058963668850507,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999420892459584,
|
|
"loss": 5.8444,
|
|
"mean_token_accuracy": 0.13542850986123084,
|
|
"num_tokens": 4473955.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.052430200576782,
|
|
"epoch": 0.19118522930315665,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999411184627334,
|
|
"loss": 5.7773,
|
|
"mean_token_accuracy": 0.13845517933368684,
|
|
"num_tokens": 4489008.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.891053676605225,
|
|
"epoch": 0.1917808219178082,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999401396112364,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.155222550034523,
|
|
"num_tokens": 4502755.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.040102434158325,
|
|
"epoch": 0.1923764145324598,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499939152691502,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.1377498872578144,
|
|
"num_tokens": 4518225.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.924446630477905,
|
|
"epoch": 0.19297200714711138,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999381577035663,
|
|
"loss": 5.6818,
|
|
"mean_token_accuracy": 0.14550431594252586,
|
|
"num_tokens": 4533246.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.977464389801026,
|
|
"epoch": 0.19356759976176297,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999371546474643,
|
|
"loss": 5.8221,
|
|
"mean_token_accuracy": 0.1356734313070774,
|
|
"num_tokens": 4547726.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.014477348327636,
|
|
"epoch": 0.19416319237641452,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999361435232324,
|
|
"loss": 5.8476,
|
|
"mean_token_accuracy": 0.13353351354599,
|
|
"num_tokens": 4564462.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.023280191421509,
|
|
"epoch": 0.1947587849910661,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999351243309069,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.13879656195640563,
|
|
"num_tokens": 4578846.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.872073411941528,
|
|
"epoch": 0.1953543776057177,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999340970705241,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.1500879056751728,
|
|
"num_tokens": 4593547.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.015725040435791,
|
|
"epoch": 0.19594997022036928,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999330617421209,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.14505322128534318,
|
|
"num_tokens": 4607466.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.9246180057525635,
|
|
"epoch": 0.19654556283502084,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999320183457346,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.148372121155262,
|
|
"num_tokens": 4621624.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.9067527770996096,
|
|
"epoch": 0.19714115544967242,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999309668814024,
|
|
"loss": 5.617,
|
|
"mean_token_accuracy": 0.14399564936757087,
|
|
"num_tokens": 4635720.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.892867851257324,
|
|
"epoch": 0.197736748064324,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999299073491623,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.1508186750113964,
|
|
"num_tokens": 4649614.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.997893524169922,
|
|
"epoch": 0.1983323406789756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999288397490519,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.1456414595246315,
|
|
"num_tokens": 4661930.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.971903896331787,
|
|
"epoch": 0.19892793329362715,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999277640811099,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.14272156581282616,
|
|
"num_tokens": 4677016.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.008993244171142,
|
|
"epoch": 0.19952352590827874,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999266803453747,
|
|
"loss": 5.7464,
|
|
"mean_token_accuracy": 0.1429272286593914,
|
|
"num_tokens": 4692780.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.033808994293213,
|
|
"epoch": 0.20011911852293032,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999255885418852,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.1426839977502823,
|
|
"num_tokens": 4707069.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.893804407119751,
|
|
"epoch": 0.20071471113758188,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999244886706804,
|
|
"loss": 5.7063,
|
|
"mean_token_accuracy": 0.1458833895623684,
|
|
"num_tokens": 4720658.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.945674657821655,
|
|
"epoch": 0.20131030375223347,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999233807318001,
|
|
"loss": 5.682,
|
|
"mean_token_accuracy": 0.13697761818766593,
|
|
"num_tokens": 4735901.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.00821590423584,
|
|
"epoch": 0.20190589636688505,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999222647252837,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.13373836725950242,
|
|
"num_tokens": 4748725.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.044517755508423,
|
|
"epoch": 0.20250148898153664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999211406511714,
|
|
"loss": 5.767,
|
|
"mean_token_accuracy": 0.14149385541677476,
|
|
"num_tokens": 4761593.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.001615190505982,
|
|
"epoch": 0.2030970815961882,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999200085095035,
|
|
"loss": 5.7362,
|
|
"mean_token_accuracy": 0.14610189199447632,
|
|
"num_tokens": 4774304.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.923042249679566,
|
|
"epoch": 0.20369267421083978,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999188683003207,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.14059431999921798,
|
|
"num_tokens": 4787350.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.941183710098267,
|
|
"epoch": 0.20428826682549137,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999177200236635,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.1450108490884304,
|
|
"num_tokens": 4801465.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.852363920211792,
|
|
"epoch": 0.20488385944014295,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999165636795736,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.1463468052446842,
|
|
"num_tokens": 4815757.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.936472415924072,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999153992680923,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.14150822386145592,
|
|
"num_tokens": 4830164.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.937071943283081,
|
|
"epoch": 0.2060750446694461,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999142267892612,
|
|
"loss": 5.6803,
|
|
"mean_token_accuracy": 0.14392196759581566,
|
|
"num_tokens": 4844459.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.925596857070923,
|
|
"epoch": 0.20667063728409768,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999130462431224,
|
|
"loss": 5.752,
|
|
"mean_token_accuracy": 0.14532395526766778,
|
|
"num_tokens": 4859189.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.925850582122803,
|
|
"epoch": 0.20726622989874927,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999118576297185,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.14198393672704696,
|
|
"num_tokens": 4872911.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.92238974571228,
|
|
"epoch": 0.20786182251340082,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999106609490918,
|
|
"loss": 5.6761,
|
|
"mean_token_accuracy": 0.14941318109631538,
|
|
"num_tokens": 4886260.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.746127891540527,
|
|
"epoch": 0.2084574151280524,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999094562012855,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.15673593282699586,
|
|
"num_tokens": 4899177.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.8976975440979,
|
|
"epoch": 0.209053007742704,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999082433863426,
|
|
"loss": 5.7069,
|
|
"mean_token_accuracy": 0.1483059123158455,
|
|
"num_tokens": 4912071.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.992261219024658,
|
|
"epoch": 0.20964860035735558,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999070225043068,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.15259260535240174,
|
|
"num_tokens": 4925247.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.855973911285401,
|
|
"epoch": 0.21024419297200714,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999057935552217,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.1384056493639946,
|
|
"num_tokens": 4940380.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.892102193832398,
|
|
"epoch": 0.21083978558665872,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999045565391313,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.14626146107912064,
|
|
"num_tokens": 4955868.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.883128595352173,
|
|
"epoch": 0.2114353782013103,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999033114560803,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.1434931829571724,
|
|
"num_tokens": 4969986.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.85156774520874,
|
|
"epoch": 0.2120309708159619,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999020583061132,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.14893678277730943,
|
|
"num_tokens": 4985980.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.833650159835815,
|
|
"epoch": 0.21262656343061345,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999007970892749,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.14920421838760375,
|
|
"num_tokens": 5001932.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.931062793731689,
|
|
"epoch": 0.21322215604526504,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998995278056107,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.15090135633945465,
|
|
"num_tokens": 5015375.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.942039728164673,
|
|
"epoch": 0.21381774865991662,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998982504551661,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.14353301078081132,
|
|
"num_tokens": 5030520.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.952792167663574,
|
|
"epoch": 0.2144133412745682,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998969650379869,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.14696830362081528,
|
|
"num_tokens": 5045020.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.917175245285034,
|
|
"epoch": 0.21500893388921977,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998956715541192,
|
|
"loss": 5.6059,
|
|
"mean_token_accuracy": 0.15293274223804473,
|
|
"num_tokens": 5058195.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.824610185623169,
|
|
"epoch": 0.21560452650387135,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998943700036095,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.15144876390695572,
|
|
"num_tokens": 5071687.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.900070285797119,
|
|
"epoch": 0.21620011911852294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998930603865042,
|
|
"loss": 5.6928,
|
|
"mean_token_accuracy": 0.14285470619797708,
|
|
"num_tokens": 5083817.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.899575519561767,
|
|
"epoch": 0.2167957117331745,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998917427028507,
|
|
"loss": 5.666,
|
|
"mean_token_accuracy": 0.14626671373844147,
|
|
"num_tokens": 5097957.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.856019687652588,
|
|
"epoch": 0.21739130434782608,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998904169526959,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.1456719234585762,
|
|
"num_tokens": 5112681.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.894531869888306,
|
|
"epoch": 0.21798689696247767,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998890831360876,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.1507721021771431,
|
|
"num_tokens": 5126152.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.829772663116455,
|
|
"epoch": 0.21858248957712925,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998877412530735,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.15387759804725648,
|
|
"num_tokens": 5140452.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.849728775024414,
|
|
"epoch": 0.2191780821917808,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998863913037017,
|
|
"loss": 5.7084,
|
|
"mean_token_accuracy": 0.142798063904047,
|
|
"num_tokens": 5155020.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.9373781204223635,
|
|
"epoch": 0.2197736748064324,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998850332880208,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.1517767332494259,
|
|
"num_tokens": 5169321.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.874116325378418,
|
|
"epoch": 0.22036926742108398,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998836672060795,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.15280101597309112,
|
|
"num_tokens": 5182156.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.7975139141082765,
|
|
"epoch": 0.22096486003573557,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998822930579264,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.1467317521572113,
|
|
"num_tokens": 5196543.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.843800210952759,
|
|
"epoch": 0.22156045265038712,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998809108436112,
|
|
"loss": 5.6274,
|
|
"mean_token_accuracy": 0.15367698073387145,
|
|
"num_tokens": 5210454.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.956942701339722,
|
|
"epoch": 0.2221560452650387,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998795205631834,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.14255602583289145,
|
|
"num_tokens": 5226371.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.8665846824646,
|
|
"epoch": 0.2227516378796903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998781222166929,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.15659446865320206,
|
|
"num_tokens": 5239182.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.79332127571106,
|
|
"epoch": 0.22334723049434188,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998767158041897,
|
|
"loss": 5.5635,
|
|
"mean_token_accuracy": 0.15482927113771439,
|
|
"num_tokens": 5254704.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.805406188964843,
|
|
"epoch": 0.22394282310899344,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998753013257242,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.15331717804074288,
|
|
"num_tokens": 5267218.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.863832473754883,
|
|
"epoch": 0.22453841572364502,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998738787813475,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.147457355260849,
|
|
"num_tokens": 5282376.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.861818122863769,
|
|
"epoch": 0.2251340083382966,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998724481711103,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.14824887365102768,
|
|
"num_tokens": 5296135.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.85996036529541,
|
|
"epoch": 0.2257296009529482,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499871009495064,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.15290106683969498,
|
|
"num_tokens": 5310347.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.905732774734497,
|
|
"epoch": 0.22632519356759975,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998695627532601,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.1427819922566414,
|
|
"num_tokens": 5324958.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.7436851978302,
|
|
"epoch": 0.22692078618225134,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998681079457507,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.15394582152366637,
|
|
"num_tokens": 5338913.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.749853086471558,
|
|
"epoch": 0.22751637879690292,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499866645072588,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.15937881916761398,
|
|
"num_tokens": 5351151.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.723223495483398,
|
|
"epoch": 0.2281119714115545,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998651741338242,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.1528441146016121,
|
|
"num_tokens": 5365139.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.908973503112793,
|
|
"epoch": 0.22870756402620607,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998636951295122,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.1462341070175171,
|
|
"num_tokens": 5378821.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.833300638198852,
|
|
"epoch": 0.22930315664085765,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998622080597052,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.14569789469242095,
|
|
"num_tokens": 5393912.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.967876863479614,
|
|
"epoch": 0.22989874925550924,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998607129244563,
|
|
"loss": 5.6855,
|
|
"mean_token_accuracy": 0.15573813542723655,
|
|
"num_tokens": 5406373.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.776638650894165,
|
|
"epoch": 0.23049434187016082,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998592097238192,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.15726928114891053,
|
|
"num_tokens": 5421701.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.802846050262451,
|
|
"epoch": 0.23108993448481238,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998576984578479,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.15237817242741586,
|
|
"num_tokens": 5435584.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.832087850570678,
|
|
"epoch": 0.23168552709946397,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998561791265966,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.1429808333516121,
|
|
"num_tokens": 5451241.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.9865015029907225,
|
|
"epoch": 0.23228111971411555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998546517301196,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.14687193483114241,
|
|
"num_tokens": 5465740.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.813498163223267,
|
|
"epoch": 0.2328767123287671,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499853116268472,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.16084107905626296,
|
|
"num_tokens": 5479142.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.917529582977295,
|
|
"epoch": 0.2334723049434187,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998515727417086,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.15238895416259765,
|
|
"num_tokens": 5491503.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.757050943374634,
|
|
"epoch": 0.23406789755807028,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998500211498848,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.1481686107814312,
|
|
"num_tokens": 5506817.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.877749013900757,
|
|
"epoch": 0.23466349017272187,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998484614930566,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.15181323289871215,
|
|
"num_tokens": 5519223.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.817584753036499,
|
|
"epoch": 0.23525908278737342,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998468937712794,
|
|
"loss": 5.6774,
|
|
"mean_token_accuracy": 0.1495397612452507,
|
|
"num_tokens": 5534904.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.852335691452026,
|
|
"epoch": 0.235854675402025,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998453179846098,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.15499591827392578,
|
|
"num_tokens": 5548815.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.812982559204102,
|
|
"epoch": 0.2364502680166766,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998437341331043,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.1524474650621414,
|
|
"num_tokens": 5563277.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.866748237609864,
|
|
"epoch": 0.23704586063132818,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998421422168195,
|
|
"loss": 5.6701,
|
|
"mean_token_accuracy": 0.15211372300982476,
|
|
"num_tokens": 5576083.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.858061838150024,
|
|
"epoch": 0.23764145324597974,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998405422358126,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.1504637897014618,
|
|
"num_tokens": 5592293.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.70010781288147,
|
|
"epoch": 0.23823704586063132,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998389341901411,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.16007496565580367,
|
|
"num_tokens": 5606088.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.788255786895752,
|
|
"epoch": 0.2388326384752829,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998373180798626,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.15649832785129547,
|
|
"num_tokens": 5620039.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.769215250015259,
|
|
"epoch": 0.2394282310899345,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998356939050351,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.15451158285140992,
|
|
"num_tokens": 5634738.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.819713115692139,
|
|
"epoch": 0.24002382370458605,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998340616657168,
|
|
"loss": 5.4799,
|
|
"mean_token_accuracy": 0.15834107398986816,
|
|
"num_tokens": 5649410.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.685422706604004,
|
|
"epoch": 0.24061941631923764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998324213619661,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.15346736013889312,
|
|
"num_tokens": 5662641.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.892227458953857,
|
|
"epoch": 0.24121500893388922,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998307729938423,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.15353201925754548,
|
|
"num_tokens": 5675558.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.6808325290679935,
|
|
"epoch": 0.2418106015485408,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499829116561404,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.1574713483452797,
|
|
"num_tokens": 5690152.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.824256658554077,
|
|
"epoch": 0.24240619416319237,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998274520647109,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.15091209411621093,
|
|
"num_tokens": 5705378.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.792923498153686,
|
|
"epoch": 0.24300178677784395,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998257795038227,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.1475793808698654,
|
|
"num_tokens": 5718470.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.796890020370483,
|
|
"epoch": 0.24359737939249554,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998240988787992,
|
|
"loss": 5.5579,
|
|
"mean_token_accuracy": 0.1571284055709839,
|
|
"num_tokens": 5731073.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.7663506984710695,
|
|
"epoch": 0.24419297200714712,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998224101897009,
|
|
"loss": 5.5347,
|
|
"mean_token_accuracy": 0.15575063228607178,
|
|
"num_tokens": 5744978.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.83977370262146,
|
|
"epoch": 0.24478856462179868,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998207134365883,
|
|
"loss": 5.6617,
|
|
"mean_token_accuracy": 0.1565300188958645,
|
|
"num_tokens": 5758723.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.721971750259399,
|
|
"epoch": 0.24538415723645027,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998190086195223,
|
|
"loss": 5.508,
|
|
"mean_token_accuracy": 0.15415533781051635,
|
|
"num_tokens": 5773646.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.807780694961548,
|
|
"epoch": 0.24597974985110185,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998172957385638,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.1513384312391281,
|
|
"num_tokens": 5787226.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.807900142669678,
|
|
"epoch": 0.2465753424657534,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998155747937746,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.15615093782544137,
|
|
"num_tokens": 5801378.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.811914014816284,
|
|
"epoch": 0.247170935080405,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998138457852162,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.15894006341695785,
|
|
"num_tokens": 5815136.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.7826625347137455,
|
|
"epoch": 0.24776652769505658,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998121087129507,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.1564724251627922,
|
|
"num_tokens": 5830222.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.774316072463989,
|
|
"epoch": 0.24836212030970817,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998103635770404,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.14870412200689315,
|
|
"num_tokens": 5844289.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.8135326385498045,
|
|
"epoch": 0.24895771292435973,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998086103775478,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.1576744720339775,
|
|
"num_tokens": 5857876.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.755991125106812,
|
|
"epoch": 0.2495533055390113,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998068491145359,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.14946600943803787,
|
|
"num_tokens": 5872032.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.7675745487213135,
|
|
"epoch": 0.25014889815366287,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998050797880678,
|
|
"loss": 5.5291,
|
|
"mean_token_accuracy": 0.15345812737941741,
|
|
"num_tokens": 5885478.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.835575771331787,
|
|
"epoch": 0.25074449076831445,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998033023982071,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.14204476475715638,
|
|
"num_tokens": 5900888.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.732381963729859,
|
|
"epoch": 0.25134008338296604,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998015169450174,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.15993799418210983,
|
|
"num_tokens": 5917158.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.7967307567596436,
|
|
"epoch": 0.2519356759976176,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997997234285627,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.1500745326280594,
|
|
"num_tokens": 5931879.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.675069808959961,
|
|
"epoch": 0.2525312686122692,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997979218489076,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.15455867499113082,
|
|
"num_tokens": 5947015.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.684785461425781,
|
|
"epoch": 0.2531268612269208,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997961122061164,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.15598441213369368,
|
|
"num_tokens": 5962063.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.699853420257568,
|
|
"epoch": 0.2537224538415724,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997942945002543,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.16179423332214354,
|
|
"num_tokens": 5977697.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.768417644500732,
|
|
"epoch": 0.25431804645622397,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997924687313862,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.1563252717256546,
|
|
"num_tokens": 5994117.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.733187580108643,
|
|
"epoch": 0.2549136390708755,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997906348995777,
|
|
"loss": 5.525,
|
|
"mean_token_accuracy": 0.15403501689434052,
|
|
"num_tokens": 6009878.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.760872936248779,
|
|
"epoch": 0.2555092316855271,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997887930048947,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.15625921934843062,
|
|
"num_tokens": 6021152.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.78124737739563,
|
|
"epoch": 0.25610482430017867,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997869430474033,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.15420911312103272,
|
|
"num_tokens": 6035975.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.628174638748169,
|
|
"epoch": 0.25670041691483025,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997850850271696,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.15644560009241104,
|
|
"num_tokens": 6048326.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.875419235229492,
|
|
"epoch": 0.25729600952948184,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997832189442604,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.15095992684364318,
|
|
"num_tokens": 6063327.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.737497997283936,
|
|
"epoch": 0.2578916021441334,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997813447987426,
|
|
"loss": 5.5316,
|
|
"mean_token_accuracy": 0.15511489361524583,
|
|
"num_tokens": 6077207.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.731353807449341,
|
|
"epoch": 0.258487194758785,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997794625906834,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.15723375827074051,
|
|
"num_tokens": 6094691.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.758441305160522,
|
|
"epoch": 0.2590827873734366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997775723201504,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.15815255790948868,
|
|
"num_tokens": 6108539.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.736060714721679,
|
|
"epoch": 0.2596783799880881,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997756739872112,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.1544911876320839,
|
|
"num_tokens": 6122799.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.797795200347901,
|
|
"epoch": 0.2602739726027397,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997737675919344,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.16468376070261,
|
|
"num_tokens": 6137525.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.8151754379272464,
|
|
"epoch": 0.2608695652173913,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997718531343877,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.15274518579244614,
|
|
"num_tokens": 6151418.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.805972099304199,
|
|
"epoch": 0.2614651578320429,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997699306146402,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.15299971848726274,
|
|
"num_tokens": 6164839.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.637115383148194,
|
|
"epoch": 0.26206075044669447,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997680000327607,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.16252323240041733,
|
|
"num_tokens": 6179641.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.771062994003296,
|
|
"epoch": 0.26265634306134605,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997660613888185,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.1493033602833748,
|
|
"num_tokens": 6196204.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.878154134750366,
|
|
"epoch": 0.26325193567599764,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997641146828831,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.1535416066646576,
|
|
"num_tokens": 6210704.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.677254629135132,
|
|
"epoch": 0.26384752829064917,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997621599150244,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.16301869750022888,
|
|
"num_tokens": 6226028.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.774082469940185,
|
|
"epoch": 0.26444312090530075,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997601970853124,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.15197534412145614,
|
|
"num_tokens": 6242376.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.740234518051148,
|
|
"epoch": 0.26503871351995234,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997582261938177,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.1531852275133133,
|
|
"num_tokens": 6255471.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.733001852035523,
|
|
"epoch": 0.2656343061346039,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997562472406107,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.16006610095500945,
|
|
"num_tokens": 6268081.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.684260606765747,
|
|
"epoch": 0.2662298987492555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997542602257626,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.1666449248790741,
|
|
"num_tokens": 6281765.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.790953207015991,
|
|
"epoch": 0.2668254913639071,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997522651493447,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.1565714307129383,
|
|
"num_tokens": 6297392.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.612934255599976,
|
|
"epoch": 0.2674210839785587,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997502620114284,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.1620727762579918,
|
|
"num_tokens": 6310726.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.775699138641357,
|
|
"epoch": 0.26801667659321027,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997482508120856,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.16205329895019532,
|
|
"num_tokens": 6325290.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.702234697341919,
|
|
"epoch": 0.2686122692078618,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997462315513884,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.15332119464874266,
|
|
"num_tokens": 6340056.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.680809068679809,
|
|
"epoch": 0.2692078618225134,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997442042294095,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.1613737717270851,
|
|
"num_tokens": 6353378.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.730574035644532,
|
|
"epoch": 0.26980345443716497,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997421688462213,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.15490979701280594,
|
|
"num_tokens": 6365916.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.720281267166138,
|
|
"epoch": 0.27039904705181655,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997401254018969,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.16011253744363785,
|
|
"num_tokens": 6380274.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.747355031967163,
|
|
"epoch": 0.27099463966646814,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997380738965096,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.15410203337669373,
|
|
"num_tokens": 6394769.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.685437393188477,
|
|
"epoch": 0.2715902322811197,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499736014330133,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.1563577249646187,
|
|
"num_tokens": 6408980.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.707857322692871,
|
|
"epoch": 0.2721858248957713,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997339467028409,
|
|
"loss": 5.4466,
|
|
"mean_token_accuracy": 0.1624538853764534,
|
|
"num_tokens": 6424267.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.687609052658081,
|
|
"epoch": 0.2727814175104229,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997318710147076,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.16648496836423873,
|
|
"num_tokens": 6438827.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.690534782409668,
|
|
"epoch": 0.2733770101250744,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997297872658075,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.15981334447860718,
|
|
"num_tokens": 6453040.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.738874864578247,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997276954562152,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.15814361572265626,
|
|
"num_tokens": 6469960.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.6687750816345215,
|
|
"epoch": 0.2745681953543776,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499725595586006,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.1565321996808052,
|
|
"num_tokens": 6483914.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.600572776794434,
|
|
"epoch": 0.2751637879690292,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499723487655255,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.165006785094738,
|
|
"num_tokens": 6497290.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.638116407394409,
|
|
"epoch": 0.27575938058368077,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997213716640378,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.1609934851527214,
|
|
"num_tokens": 6512558.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.681073951721191,
|
|
"epoch": 0.27635497319833235,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997192476124306,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.1543683797121048,
|
|
"num_tokens": 6527786.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.664290475845337,
|
|
"epoch": 0.27695056581298394,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997171155005091,
|
|
"loss": 5.4506,
|
|
"mean_token_accuracy": 0.1584233894944191,
|
|
"num_tokens": 6540925.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.691961193084717,
|
|
"epoch": 0.27754615842763547,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997149753283502,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.15958700627088546,
|
|
"num_tokens": 6553945.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.706377840042114,
|
|
"epoch": 0.27814175104228706,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997128270960304,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.16332324147224425,
|
|
"num_tokens": 6568986.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.6778669357299805,
|
|
"epoch": 0.27873734365693864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997106708036268,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.1605681896209717,
|
|
"num_tokens": 6582219.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.675868034362793,
|
|
"epoch": 0.2793329362715902,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499708506451217,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.15856398940086364,
|
|
"num_tokens": 6597670.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.651786422729492,
|
|
"epoch": 0.2799285288862418,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997063340388783,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.1593650110065937,
|
|
"num_tokens": 6612923.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.812162923812866,
|
|
"epoch": 0.2805241215008934,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997041535666888,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.16022965535521508,
|
|
"num_tokens": 6624762.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.630000257492066,
|
|
"epoch": 0.281119714115545,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997019650347266,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.1686081826686859,
|
|
"num_tokens": 6637910.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.7279884815216064,
|
|
"epoch": 0.28171530673019657,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996997684430703,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.158505779504776,
|
|
"num_tokens": 6652212.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.750305461883545,
|
|
"epoch": 0.2823108993448481,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996975637917986,
|
|
"loss": 5.5519,
|
|
"mean_token_accuracy": 0.15858569145202636,
|
|
"num_tokens": 6665535.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.708090734481812,
|
|
"epoch": 0.2829064919594997,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996953510809906,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.16342256516218184,
|
|
"num_tokens": 6680013.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.6703039646148685,
|
|
"epoch": 0.28350208457415127,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996931303107258,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.16596188247203827,
|
|
"num_tokens": 6692384.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.69407286643982,
|
|
"epoch": 0.28409767718880286,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996909014810837,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.1595408760011196,
|
|
"num_tokens": 6707127.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.690748167037964,
|
|
"epoch": 0.28469326980345444,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996886645921442,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.16248813569545745,
|
|
"num_tokens": 6720434.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.661434459686279,
|
|
"epoch": 0.285288862418106,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996864196439877,
|
|
"loss": 5.5837,
|
|
"mean_token_accuracy": 0.1565555177628994,
|
|
"num_tokens": 6734457.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.750744819641113,
|
|
"epoch": 0.2858844550327576,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996841666366947,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.15229643881320953,
|
|
"num_tokens": 6750351.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.658818674087525,
|
|
"epoch": 0.2864800476474092,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996819055703458,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.16347557157278061,
|
|
"num_tokens": 6765252.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.655593967437744,
|
|
"epoch": 0.2870756402620607,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996796364450224,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.1633814185857773,
|
|
"num_tokens": 6778020.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.649205923080444,
|
|
"epoch": 0.2876712328767123,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996773592608057,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.16340244710445403,
|
|
"num_tokens": 6792233.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.806488037109375,
|
|
"epoch": 0.2882668254913639,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996750740177775,
|
|
"loss": 5.593,
|
|
"mean_token_accuracy": 0.15179218500852584,
|
|
"num_tokens": 6807781.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.601470994949341,
|
|
"epoch": 0.2888624181060155,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996727807160196,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.1655975565314293,
|
|
"num_tokens": 6822406.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.62792272567749,
|
|
"epoch": 0.28945801072066707,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996704793556144,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.15741414576768875,
|
|
"num_tokens": 6835192.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.686983442306518,
|
|
"epoch": 0.29005360333531865,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996681699366443,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.1636321559548378,
|
|
"num_tokens": 6846921.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.634683132171631,
|
|
"epoch": 0.29064919594997024,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996658524591924,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.1642177626490593,
|
|
"num_tokens": 6864195.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.62883620262146,
|
|
"epoch": 0.2912447885646218,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996635269233415,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.15959485471248627,
|
|
"num_tokens": 6879095.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.645639038085937,
|
|
"epoch": 0.29184038117927336,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996611933291752,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.16254814714193344,
|
|
"num_tokens": 6891853.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.682731676101684,
|
|
"epoch": 0.29243597379392494,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996588516767772,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.15918793380260468,
|
|
"num_tokens": 6905235.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.622744417190551,
|
|
"epoch": 0.2930315664085765,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996565019662315,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.1667335644364357,
|
|
"num_tokens": 6918438.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.684930801391602,
|
|
"epoch": 0.2936271590232281,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996541441976223,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.16349320709705353,
|
|
"num_tokens": 6931749.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.6001488208770756,
|
|
"epoch": 0.2942227516378797,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996517783710342,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.17157334089279175,
|
|
"num_tokens": 6946114.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.642820072174072,
|
|
"epoch": 0.2948183442525313,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996494044865521,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.16377470642328262,
|
|
"num_tokens": 6959002.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.623351621627807,
|
|
"epoch": 0.29541393686718287,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996470225442611,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.16650692522525787,
|
|
"num_tokens": 6973248.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.604974031448364,
|
|
"epoch": 0.2960095294818344,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996446325442466,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.16485302448272704,
|
|
"num_tokens": 6985223.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.659956407546997,
|
|
"epoch": 0.296605122096486,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996422344865945,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.16301326006650924,
|
|
"num_tokens": 6998948.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.703521823883056,
|
|
"epoch": 0.29720071471113757,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996398283713907,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.16087786257266998,
|
|
"num_tokens": 7011594.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.517322826385498,
|
|
"epoch": 0.29779630732578916,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996374141987215,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.16284587234258652,
|
|
"num_tokens": 7025451.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.603648471832275,
|
|
"epoch": 0.29839189994044074,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996349919686733,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.16220980733633042,
|
|
"num_tokens": 7038301.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.7301164150238035,
|
|
"epoch": 0.2989874925550923,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996325616813334,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.1573624238371849,
|
|
"num_tokens": 7053777.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.654399871826172,
|
|
"epoch": 0.2995830851697439,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996301233367886,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.16134716123342513,
|
|
"num_tokens": 7069516.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.63122296333313,
|
|
"epoch": 0.3001786777843955,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996276769351265,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.15889426767826081,
|
|
"num_tokens": 7083514.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.625289440155029,
|
|
"epoch": 0.30077427039904703,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996252224764349,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.16070133969187736,
|
|
"num_tokens": 7096637.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.757515525817871,
|
|
"epoch": 0.3013698630136986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996227599608018,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.17124143242835999,
|
|
"num_tokens": 7111994.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.60223240852356,
|
|
"epoch": 0.3019654556283502,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996202893883156,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.16722567081451417,
|
|
"num_tokens": 7125148.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.6869062900543215,
|
|
"epoch": 0.3025610482430018,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996178107590648,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.1579883798956871,
|
|
"num_tokens": 7140015.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.694077968597412,
|
|
"epoch": 0.30315664085765337,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996153240731381,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.16261224448680878,
|
|
"num_tokens": 7152939.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.656959056854248,
|
|
"epoch": 0.30375223347230496,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996128293306251,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.15252157896757126,
|
|
"num_tokens": 7167115.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.650059747695923,
|
|
"epoch": 0.30434782608695654,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996103265316152,
|
|
"loss": 5.405,
|
|
"mean_token_accuracy": 0.1619548663496971,
|
|
"num_tokens": 7180455.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.621711111068725,
|
|
"epoch": 0.3049434187016081,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996078156761979,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.16667965352535247,
|
|
"num_tokens": 7193777.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.720235681533813,
|
|
"epoch": 0.30553901131625966,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996052967644636,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.16859492510557175,
|
|
"num_tokens": 7205851.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.658883047103882,
|
|
"epoch": 0.30613460393091124,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996027697965024,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.15974574387073517,
|
|
"num_tokens": 7221359.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.722562074661255,
|
|
"epoch": 0.3067301965455628,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499600234772405,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.15828749239444734,
|
|
"num_tokens": 7235583.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.659008884429932,
|
|
"epoch": 0.3073257891602144,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995976916922624,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.16872933506965637,
|
|
"num_tokens": 7250477.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.575438928604126,
|
|
"epoch": 0.307921381774866,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995951405561658,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.16320499032735825,
|
|
"num_tokens": 7264197.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.7057945728302,
|
|
"epoch": 0.3085169743895176,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995925813642068,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.1670471578836441,
|
|
"num_tokens": 7278989.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.596223020553589,
|
|
"epoch": 0.30911256700416917,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995900141164768,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.16520352214574813,
|
|
"num_tokens": 7293213.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.642040157318116,
|
|
"epoch": 0.3097081596188207,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995874388130683,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.1643291413784027,
|
|
"num_tokens": 7306774.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.541489362716675,
|
|
"epoch": 0.3103037522334723,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995848554540734,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.16852965205907822,
|
|
"num_tokens": 7321239.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.608112096786499,
|
|
"epoch": 0.31089934484812387,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499582264039585,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.16969144344329834,
|
|
"num_tokens": 7335872.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.587273740768433,
|
|
"epoch": 0.31149493746277546,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499579664569696,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.16438512206077577,
|
|
"num_tokens": 7350523.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.714767551422119,
|
|
"epoch": 0.31209053007742704,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995770570444996,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.16590621918439866,
|
|
"num_tokens": 7363201.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.672125720977784,
|
|
"epoch": 0.3126861226920786,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995744414640892,
|
|
"loss": 5.4776,
|
|
"mean_token_accuracy": 0.16536226719617844,
|
|
"num_tokens": 7375377.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.598500680923462,
|
|
"epoch": 0.3132817153067302,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995718178285587,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.1610244855284691,
|
|
"num_tokens": 7388871.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.603353834152221,
|
|
"epoch": 0.3138773079213818,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995691861380022,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.1694616049528122,
|
|
"num_tokens": 7402235.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.588888549804688,
|
|
"epoch": 0.31447290053603333,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995665463925142,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.1702384278178215,
|
|
"num_tokens": 7414673.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.603456687927246,
|
|
"epoch": 0.3150684931506849,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995638985921893,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.1671357810497284,
|
|
"num_tokens": 7429039.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.653233814239502,
|
|
"epoch": 0.3156640857653365,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995612427371224,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.1631896674633026,
|
|
"num_tokens": 7443060.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.561821508407593,
|
|
"epoch": 0.3162596783799881,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499558578827409,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.1673417568206787,
|
|
"num_tokens": 7456717.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.510098791122436,
|
|
"epoch": 0.31685527099463967,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995559068631444,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.16376861929893494,
|
|
"num_tokens": 7470878.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.585044717788696,
|
|
"epoch": 0.31745086360929126,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995532268444244,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.1690148487687111,
|
|
"num_tokens": 7486427.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.680125522613525,
|
|
"epoch": 0.31804645622394284,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995505387713453,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.15970658510923386,
|
|
"num_tokens": 7500759.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.595620584487915,
|
|
"epoch": 0.3186420488385944,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995478426440037,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.16363002210855485,
|
|
"num_tokens": 7513224.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.56921157836914,
|
|
"epoch": 0.31923764145324596,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995451384624959,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.16787581592798234,
|
|
"num_tokens": 7528128.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.619098758697509,
|
|
"epoch": 0.31983323406789754,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995424262269191,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.17019287794828414,
|
|
"num_tokens": 7541731.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.637658786773682,
|
|
"epoch": 0.32042882668254913,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995397059373704,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.16239553838968276,
|
|
"num_tokens": 7555938.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.5821184635162355,
|
|
"epoch": 0.3210244192972007,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995369775939478,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.16661161184310913,
|
|
"num_tokens": 7570033.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.588184785842896,
|
|
"epoch": 0.3216200119118523,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995342411967487,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.16195307672023773,
|
|
"num_tokens": 7585131.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.5823287010192875,
|
|
"epoch": 0.3222156045265039,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995314967458715,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.16910858303308487,
|
|
"num_tokens": 7600167.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.595126008987426,
|
|
"epoch": 0.32281119714115547,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995287442414145,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.16785854250192642,
|
|
"num_tokens": 7612301.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.670919895172119,
|
|
"epoch": 0.323406789755807,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995259836834767,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.16672904193401336,
|
|
"num_tokens": 7625837.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.593075847625732,
|
|
"epoch": 0.3240023823704586,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995232150721568,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.1659615993499756,
|
|
"num_tokens": 7640555.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.521756744384765,
|
|
"epoch": 0.32459797498511017,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995204384075542,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.16779649555683135,
|
|
"num_tokens": 7655395.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.592764663696289,
|
|
"epoch": 0.32519356759976176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995176536897685,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.15718302726745606,
|
|
"num_tokens": 7670429.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.564849042892456,
|
|
"epoch": 0.32578916021441334,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995148609188997,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.1616342008113861,
|
|
"num_tokens": 7684240.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.677158641815185,
|
|
"epoch": 0.32638475282906493,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995120600950479,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.16039044857025148,
|
|
"num_tokens": 7698412.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.597699451446533,
|
|
"epoch": 0.3269803454437165,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995092512183134,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.1639407083392143,
|
|
"num_tokens": 7712814.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.653441715240478,
|
|
"epoch": 0.3275759380583681,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995064342887972,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.1640625,
|
|
"num_tokens": 7726740.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.585921716690064,
|
|
"epoch": 0.32817153067301963,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995036093066001,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.1629028469324112,
|
|
"num_tokens": 7741411.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.535441064834595,
|
|
"epoch": 0.3287671232876712,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995007762718237,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.1750536099076271,
|
|
"num_tokens": 7753530.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.548461389541626,
|
|
"epoch": 0.3293627159023228,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994979351845693,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.1694473460316658,
|
|
"num_tokens": 7766924.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.568308877944946,
|
|
"epoch": 0.3299583085169744,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994950860449392,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.16138947308063506,
|
|
"num_tokens": 7781561.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.650861835479736,
|
|
"epoch": 0.33055390113162597,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994922288530353,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.1612231746315956,
|
|
"num_tokens": 7796254.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.5372191905975345,
|
|
"epoch": 0.33114949374627756,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994893636089601,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.1660068452358246,
|
|
"num_tokens": 7808683.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.674601745605469,
|
|
"epoch": 0.33174508636092914,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994864903128164,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.160142220556736,
|
|
"num_tokens": 7822688.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.652541589736939,
|
|
"epoch": 0.33234067897558073,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994836089647073,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.1659604012966156,
|
|
"num_tokens": 7838425.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.51391978263855,
|
|
"epoch": 0.33293627159023226,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994807195647362,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.17419065684080123,
|
|
"num_tokens": 7851685.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.596407079696656,
|
|
"epoch": 0.33353186420488384,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994778221130066,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.16951974332332612,
|
|
"num_tokens": 7864735.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.506788825988769,
|
|
"epoch": 0.33412745681953543,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004994749166096226,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.16573702692985534,
|
|
"num_tokens": 7880240.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.481150054931641,
|
|
"epoch": 0.334723049434187,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994720030546882,
|
|
"loss": 5.3548,
|
|
"mean_token_accuracy": 0.16667070090770722,
|
|
"num_tokens": 7893749.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.611258029937744,
|
|
"epoch": 0.3353186420488386,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994690814483081,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.17003161758184432,
|
|
"num_tokens": 7906132.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.484817552566528,
|
|
"epoch": 0.3359142346634902,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994661517905869,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.1729711577296257,
|
|
"num_tokens": 7919621.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.451206493377685,
|
|
"epoch": 0.33650982727814177,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994632140816299,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.17531078755855561,
|
|
"num_tokens": 7932882.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.579314470291138,
|
|
"epoch": 0.33710541989279336,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994602683215424,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.16776238679885863,
|
|
"num_tokens": 7946374.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.608100175857544,
|
|
"epoch": 0.3377010125074449,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049945731451043,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.16137655675411225,
|
|
"num_tokens": 7959766.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.522439289093017,
|
|
"epoch": 0.33829660512209647,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994543526483985,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.16792797297239304,
|
|
"num_tokens": 7974976.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.633068704605103,
|
|
"epoch": 0.33889219773674806,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994513827355546,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.15954930037260057,
|
|
"num_tokens": 7990605.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.561303997039795,
|
|
"epoch": 0.33948779035139964,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994484047720043,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.17052376717329026,
|
|
"num_tokens": 8004346.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.62995285987854,
|
|
"epoch": 0.34008338296605123,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994454187578547,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.1709371492266655,
|
|
"num_tokens": 8020219.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.68173189163208,
|
|
"epoch": 0.3406789755807028,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994424246932129,
|
|
"loss": 5.5041,
|
|
"mean_token_accuracy": 0.16103566735982894,
|
|
"num_tokens": 8034486.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.546448850631714,
|
|
"epoch": 0.3412745681953544,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994394225781863,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.16636965572834014,
|
|
"num_tokens": 8047661.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.5298261642456055,
|
|
"epoch": 0.34187016081000593,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994364124128825,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.1692613497376442,
|
|
"num_tokens": 8063638.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.557293844223023,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994333941974094,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.16984928846359254,
|
|
"num_tokens": 8075743.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.562584686279297,
|
|
"epoch": 0.3430613460393091,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994303679318754,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.17036716639995575,
|
|
"num_tokens": 8090169.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.520627689361572,
|
|
"epoch": 0.3436569386539607,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994273336163891,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.16793280690908433,
|
|
"num_tokens": 8104919.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.607230520248413,
|
|
"epoch": 0.34425253126861227,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994242912510591,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.17202310562133788,
|
|
"num_tokens": 8117893.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.5752369403839115,
|
|
"epoch": 0.34484812388326386,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994212408359948,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.15659124553203582,
|
|
"num_tokens": 8133325.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.555515193939209,
|
|
"epoch": 0.34544371649791544,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994181823713054,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.17399801909923554,
|
|
"num_tokens": 8147728.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.53694109916687,
|
|
"epoch": 0.34603930911256703,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994151158571006,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.1690783217549324,
|
|
"num_tokens": 8163045.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.579945468902588,
|
|
"epoch": 0.34663490172721856,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994120412934906,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.16330579668283463,
|
|
"num_tokens": 8176946.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.55695333480835,
|
|
"epoch": 0.34723049434187014,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.17500018179416657,
|
|
"num_tokens": 8189507.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.5458403587341305,
|
|
"epoch": 0.34782608695652173,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994058680184959,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.16473894268274308,
|
|
"num_tokens": 8203920.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.583098363876343,
|
|
"epoch": 0.3484216795711733,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994027693073327,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.16916266828775406,
|
|
"num_tokens": 8217719.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.498113679885864,
|
|
"epoch": 0.3490172721858249,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993996625472071,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.1656230941414833,
|
|
"num_tokens": 8232796.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.611781883239746,
|
|
"epoch": 0.3496128648004765,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993965477382304,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.16605483144521713,
|
|
"num_tokens": 8244150.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.51896595954895,
|
|
"epoch": 0.35020845741512807,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993934248805143,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.1716987296938896,
|
|
"num_tokens": 8259070.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.557607984542846,
|
|
"epoch": 0.35080405002977966,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993902939741709,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.17213038504123687,
|
|
"num_tokens": 8273558.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.558725500106812,
|
|
"epoch": 0.3513996426444312,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004993871550193126,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.16512211114168168,
|
|
"num_tokens": 8287816.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.551508140563965,
|
|
"epoch": 0.3519952352590828,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993840080160519,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.16179206371307372,
|
|
"num_tokens": 8303047.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.5350017070770265,
|
|
"epoch": 0.35259082787373436,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993808529645016,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.17535457462072374,
|
|
"num_tokens": 8315907.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.526376485824585,
|
|
"epoch": 0.35318642048838594,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993776898647749,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.18118688762187957,
|
|
"num_tokens": 8329343.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.607866668701172,
|
|
"epoch": 0.35378201310303753,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993745187169852,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.16549852937459947,
|
|
"num_tokens": 8343698.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.615293073654175,
|
|
"epoch": 0.3543776057176891,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993713395212464,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.1712152659893036,
|
|
"num_tokens": 8357697.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.4842555046081545,
|
|
"epoch": 0.3549731983323407,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993681522776725,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.16991902887821198,
|
|
"num_tokens": 8370743.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.450813293457031,
|
|
"epoch": 0.35556879094699223,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993649569863778,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.1822266697883606,
|
|
"num_tokens": 8383328.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.515005159378052,
|
|
"epoch": 0.3561643835616438,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993617536474768,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.17316077202558516,
|
|
"num_tokens": 8398539.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.561909484863281,
|
|
"epoch": 0.3567599761762954,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993585422610845,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.1747918203473091,
|
|
"num_tokens": 8411238.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.403289079666138,
|
|
"epoch": 0.357355568790947,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993553228273161,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.1780083805322647,
|
|
"num_tokens": 8424818.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.357355568790947,
|
|
"eval_entropy": 5.37680235925513,
|
|
"eval_loss": 5.318552017211914,
|
|
"eval_mean_token_accuracy": 0.17886876086923395,
|
|
"eval_num_tokens": 8424818.0,
|
|
"eval_runtime": 18.7597,
|
|
"eval_samples_per_second": 1359.988,
|
|
"eval_steps_per_second": 170.045,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.680321264266968,
|
|
"epoch": 0.3579511614055986,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499352095346287,
|
|
"loss": 5.399,
|
|
"mean_token_accuracy": 0.1633133828639984,
|
|
"num_tokens": 8438974.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.512087774276734,
|
|
"epoch": 0.35854675402025016,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993488598181131,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.17261969894170762,
|
|
"num_tokens": 8453583.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.586219453811646,
|
|
"epoch": 0.35914234663490174,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993456162429103,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.1768076851963997,
|
|
"num_tokens": 8467621.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.497888278961182,
|
|
"epoch": 0.35973793924955333,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993423646207951,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.16826776117086412,
|
|
"num_tokens": 8482697.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.587547063827515,
|
|
"epoch": 0.36033353186420486,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499339104951884,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.1691280946135521,
|
|
"num_tokens": 8495347.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.386959505081177,
|
|
"epoch": 0.36092912447885644,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993358372362939,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.17298889458179473,
|
|
"num_tokens": 8509132.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.58005108833313,
|
|
"epoch": 0.36152471709350803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993325614741421,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.1748684138059616,
|
|
"num_tokens": 8523563.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.462400150299072,
|
|
"epoch": 0.3621203097081596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993292776655461,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.17874590456485748,
|
|
"num_tokens": 8536399.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.38701868057251,
|
|
"epoch": 0.3627159023228112,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993259858106236,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.1766919583082199,
|
|
"num_tokens": 8550969.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.559665727615356,
|
|
"epoch": 0.3633114949374628,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993226859094927,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.16338545382022857,
|
|
"num_tokens": 8567051.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.580748558044434,
|
|
"epoch": 0.36390708755211437,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993193779622719,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.16738884449005126,
|
|
"num_tokens": 8581255.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.528922605514526,
|
|
"epoch": 0.36450268016676596,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993160619690796,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.16771526932716369,
|
|
"num_tokens": 8595640.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.544296360015869,
|
|
"epoch": 0.3650982727814175,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993127379300349,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.17728762030601503,
|
|
"num_tokens": 8609506.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.492613697052002,
|
|
"epoch": 0.3656938653960691,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499309405845257,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.1677103117108345,
|
|
"num_tokens": 8624691.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.452147674560547,
|
|
"epoch": 0.36628945801072066,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993060657148654,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.1761177286505699,
|
|
"num_tokens": 8637218.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.438749027252197,
|
|
"epoch": 0.36688505062537224,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00049930271753898,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.16596392095088958,
|
|
"num_tokens": 8650153.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.507561540603637,
|
|
"epoch": 0.36748064324002383,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004992993613177208,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.17530115246772765,
|
|
"num_tokens": 8663280.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.494558048248291,
|
|
"epoch": 0.3680762358546754,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992959970512082,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.17123837321996688,
|
|
"num_tokens": 8677266.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.454576587677002,
|
|
"epoch": 0.368671828469327,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992926247395627,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.16978070735931397,
|
|
"num_tokens": 8692660.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.541762828826904,
|
|
"epoch": 0.36926742108397853,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992892443829057,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.16679900139570236,
|
|
"num_tokens": 8706200.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.477366161346436,
|
|
"epoch": 0.3698630136986301,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499285855981358,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.18339828699827193,
|
|
"num_tokens": 8720421.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.4448723793029785,
|
|
"epoch": 0.3704586063132817,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992824595350414,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.17096095830202102,
|
|
"num_tokens": 8732343.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.54713077545166,
|
|
"epoch": 0.3710541989279333,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992790550440775,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.169817216694355,
|
|
"num_tokens": 8746247.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.476923227310181,
|
|
"epoch": 0.3716497915425849,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992756425085887,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.17333812415599822,
|
|
"num_tokens": 8760964.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.406105470657349,
|
|
"epoch": 0.37224538415723646,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992722219286972,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.17805521190166473,
|
|
"num_tokens": 8774889.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.49105749130249,
|
|
"epoch": 0.37284097677188804,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004992687933045258,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.17202328592538835,
|
|
"num_tokens": 8790479.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.518159627914429,
|
|
"epoch": 0.37343656938653963,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992653566361974,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.17018354088068008,
|
|
"num_tokens": 8805129.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.51479058265686,
|
|
"epoch": 0.37403216200119116,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992619119238351,
|
|
"loss": 5.2554,
|
|
"mean_token_accuracy": 0.17537494003772736,
|
|
"num_tokens": 8818046.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.474508285522461,
|
|
"epoch": 0.37462775461584275,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499258459167563,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.17804195433855058,
|
|
"num_tokens": 8830715.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.538359642028809,
|
|
"epoch": 0.37522334723049433,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992549983675043,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.1781470611691475,
|
|
"num_tokens": 8846349.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.456615257263183,
|
|
"epoch": 0.3758189398451459,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004992515295237835,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.17611448764801024,
|
|
"num_tokens": 8861316.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.466844654083252,
|
|
"epoch": 0.3764145324597975,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499248052636525,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.168072509765625,
|
|
"num_tokens": 8874349.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.5694833278656,
|
|
"epoch": 0.3770101250744491,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992445677058534,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.16894514560699464,
|
|
"num_tokens": 8887836.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.4926026344299315,
|
|
"epoch": 0.3776057176891007,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004992410747318938,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.17341060191392899,
|
|
"num_tokens": 8902009.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.46876220703125,
|
|
"epoch": 0.37820131030375226,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004992375737147715,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.1756640538573265,
|
|
"num_tokens": 8915960.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.444065523147583,
|
|
"epoch": 0.3787969029184038,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992340646546118,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.17703939378261566,
|
|
"num_tokens": 8930742.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.522914028167724,
|
|
"epoch": 0.3793924955330554,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499230547551541,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.16881698220968247,
|
|
"num_tokens": 8943535.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.406088829040527,
|
|
"epoch": 0.37998808814770696,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992270224056849,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.17789653837680816,
|
|
"num_tokens": 8958187.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.460651969909668,
|
|
"epoch": 0.38058368076235854,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992234892171702,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.17661686539649962,
|
|
"num_tokens": 8970409.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.5636115074157715,
|
|
"epoch": 0.38117927337701013,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992199479861235,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.1653168261051178,
|
|
"num_tokens": 8982302.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.482617282867432,
|
|
"epoch": 0.3817748659916617,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992163987126717,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.17122839987277985,
|
|
"num_tokens": 8996215.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.508302402496338,
|
|
"epoch": 0.3823704586063133,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004992128413969423,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.17007533311843873,
|
|
"num_tokens": 9011423.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.532516860961914,
|
|
"epoch": 0.3829660512209649,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992092760390628,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.1655038118362427,
|
|
"num_tokens": 9025322.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.524756622314453,
|
|
"epoch": 0.3835616438356164,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004992057026391612,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.17595667839050294,
|
|
"num_tokens": 9039199.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.467118883132935,
|
|
"epoch": 0.384157236450268,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992021211973655,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.18080250918865204,
|
|
"num_tokens": 9051808.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.549422788619995,
|
|
"epoch": 0.3847528290649196,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991985317138043,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.16935683488845826,
|
|
"num_tokens": 9066068.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.519559907913208,
|
|
"epoch": 0.3853484216795712,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991949341886063,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.17499166280031203,
|
|
"num_tokens": 9079209.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.506857776641846,
|
|
"epoch": 0.38594401429422276,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991913286219004,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.1776731863617897,
|
|
"num_tokens": 9092270.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.487370443344116,
|
|
"epoch": 0.38653960690887434,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991877150138162,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.1630220353603363,
|
|
"num_tokens": 9106231.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.474565696716309,
|
|
"epoch": 0.38713519952352593,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991840933644831,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.16995661556720734,
|
|
"num_tokens": 9119325.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.470413160324097,
|
|
"epoch": 0.38773079213817746,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499180463674031,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.16592499911785125,
|
|
"num_tokens": 9132792.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.473909616470337,
|
|
"epoch": 0.38832638475282905,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991768259425903,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.18330173641443254,
|
|
"num_tokens": 9146659.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.479486703872681,
|
|
"epoch": 0.38892197736748063,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991731801702914,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.17022957354784013,
|
|
"num_tokens": 9161035.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.531767892837524,
|
|
"epoch": 0.3895175699821322,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991695263572648,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.17080482095479965,
|
|
"num_tokens": 9176057.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.455781269073486,
|
|
"epoch": 0.3901131625967838,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991658645036419,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.1727764666080475,
|
|
"num_tokens": 9191021.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.406662321090698,
|
|
"epoch": 0.3907087552114354,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991621946095539,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.18158661425113679,
|
|
"num_tokens": 9204717.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.5115703582763675,
|
|
"epoch": 0.391304347826087,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991585166751325,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.17364758551120757,
|
|
"num_tokens": 9218395.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.437616539001465,
|
|
"epoch": 0.39189994044073856,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991548307005094,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.17418505400419235,
|
|
"num_tokens": 9231419.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.457427072525024,
|
|
"epoch": 0.3924955330553901,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991511366858172,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.17052946090698243,
|
|
"num_tokens": 9246557.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.466603088378906,
|
|
"epoch": 0.3930911256700417,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991474346311879,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.17370083630084993,
|
|
"num_tokens": 9261173.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.501963996887207,
|
|
"epoch": 0.39368671828469326,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991437245367547,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.17294615060091018,
|
|
"num_tokens": 9274819.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.363840007781983,
|
|
"epoch": 0.39428231089934485,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991400064026506,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.18551855087280272,
|
|
"num_tokens": 9287219.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.423783922195435,
|
|
"epoch": 0.39487790351399643,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991362802290089,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.16937638223171234,
|
|
"num_tokens": 9301069.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.46996488571167,
|
|
"epoch": 0.395473496128648,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991325460159631,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.16755855083465576,
|
|
"num_tokens": 9314807.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.426510858535766,
|
|
"epoch": 0.3960690887432996,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991288037636474,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.17628339678049088,
|
|
"num_tokens": 9328702.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.4537323951721195,
|
|
"epoch": 0.3966646813579512,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991250534721959,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.17392530888319016,
|
|
"num_tokens": 9342949.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.451861000061035,
|
|
"epoch": 0.3972602739726027,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991212951417431,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.1817117303609848,
|
|
"num_tokens": 9357382.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.535891103744507,
|
|
"epoch": 0.3978558665872543,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991175287724239,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.16250568628311157,
|
|
"num_tokens": 9371297.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.55002384185791,
|
|
"epoch": 0.3984514592019059,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991137543643733,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.16425398588180543,
|
|
"num_tokens": 9386213.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.467666053771973,
|
|
"epoch": 0.3990470518165575,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991099719177268,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.17735555768013,
|
|
"num_tokens": 9398166.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.394056797027588,
|
|
"epoch": 0.39964264443120906,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004991061814326198,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.17660689502954482,
|
|
"num_tokens": 9411611.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.422789573669434,
|
|
"epoch": 0.40023823704586065,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004991023829091887,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.1764301061630249,
|
|
"num_tokens": 9426461.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.447587490081787,
|
|
"epoch": 0.40083382966051223,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990985763475694,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.1825166314840317,
|
|
"num_tokens": 9437337.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.3998894691467285,
|
|
"epoch": 0.40142942227516376,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990947617478984,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.17848754674196243,
|
|
"num_tokens": 9450361.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.436241626739502,
|
|
"epoch": 0.40202501488981535,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004990909391103127,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.17749863415956496,
|
|
"num_tokens": 9463336.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.586833906173706,
|
|
"epoch": 0.40262060750446693,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990871084349494,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.17890213876962663,
|
|
"num_tokens": 9476602.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.424135065078735,
|
|
"epoch": 0.4032162001191185,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990832697219459,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.1717560201883316,
|
|
"num_tokens": 9490355.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.488651895523072,
|
|
"epoch": 0.4038117927337701,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990794229714398,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.17166533917188645,
|
|
"num_tokens": 9502191.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.564592266082764,
|
|
"epoch": 0.4044073853484217,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004990755681835693,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.1683407500386238,
|
|
"num_tokens": 9515694.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.45644359588623,
|
|
"epoch": 0.4050029779630733,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004990717053584723,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.1660124346613884,
|
|
"num_tokens": 9530146.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.529081010818482,
|
|
"epoch": 0.40559857057772486,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990678344962876,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.17050016224384307,
|
|
"num_tokens": 9541969.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.462375020980835,
|
|
"epoch": 0.4061941631923764,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990639555971539,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.16662318557500838,
|
|
"num_tokens": 9555837.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.532939672470093,
|
|
"epoch": 0.406789755807028,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990600686612106,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.1663308322429657,
|
|
"num_tokens": 9570841.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.449370431900024,
|
|
"epoch": 0.40738534842167956,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990561736885968,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.1833135575056076,
|
|
"num_tokens": 9583342.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.474269104003906,
|
|
"epoch": 0.40798094103633115,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004990522706794523,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.175234092772007,
|
|
"num_tokens": 9597217.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.464181041717529,
|
|
"epoch": 0.40857653365098273,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004990483596339174,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.17360809892416001,
|
|
"num_tokens": 9612251.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.450800228118896,
|
|
"epoch": 0.4091721262656343,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990444405521318,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.17209622710943223,
|
|
"num_tokens": 9625693.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.442666816711426,
|
|
"epoch": 0.4097677188802859,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004990405134342366,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.17929224520921708,
|
|
"num_tokens": 9639687.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.452113676071167,
|
|
"epoch": 0.4103633114949375,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990365782803724,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.17022576034069062,
|
|
"num_tokens": 9652258.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.467024660110473,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004990326350906803,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.18065717816352844,
|
|
"num_tokens": 9665946.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.425072288513183,
|
|
"epoch": 0.4115544967242406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990286838653019,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.17535804063081742,
|
|
"num_tokens": 9680474.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.42586760520935,
|
|
"epoch": 0.4121500893388922,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990247246043789,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.1768714651465416,
|
|
"num_tokens": 9693797.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.498319005966186,
|
|
"epoch": 0.4127456819535438,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990207573080533,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.17165374159812927,
|
|
"num_tokens": 9705875.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.544101190567017,
|
|
"epoch": 0.41334127456819536,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990167819764672,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.16366368532180786,
|
|
"num_tokens": 9720968.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.46802339553833,
|
|
"epoch": 0.41393686718284695,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990127986097636,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.17400429993867875,
|
|
"num_tokens": 9735586.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.406962060928345,
|
|
"epoch": 0.41453245979749853,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499008807208085,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.17054087668657303,
|
|
"num_tokens": 9750253.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.470438528060913,
|
|
"epoch": 0.4151280524121501,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990048077715746,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.17191239446401596,
|
|
"num_tokens": 9762814.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.51074800491333,
|
|
"epoch": 0.41572364502680165,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990008003003762,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.16247006505727768,
|
|
"num_tokens": 9777144.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.449260807037353,
|
|
"epoch": 0.41631923764145323,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989967847946331,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.17618376314640044,
|
|
"num_tokens": 9791746.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.452185726165771,
|
|
"epoch": 0.4169148302561048,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989927612544895,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.18122688978910445,
|
|
"num_tokens": 9804599.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.381531381607056,
|
|
"epoch": 0.4175104228707564,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989887296800899,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.1840138852596283,
|
|
"num_tokens": 9817030.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.5035069465637205,
|
|
"epoch": 0.418106015485408,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004989846900715786,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.16727980375289916,
|
|
"num_tokens": 9832478.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.484005308151245,
|
|
"epoch": 0.4187016081000596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989806424291008,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.17928555905818938,
|
|
"num_tokens": 9844534.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.313459587097168,
|
|
"epoch": 0.41929720071471116,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989765867528014,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.17965180724859237,
|
|
"num_tokens": 9856610.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.420787525177002,
|
|
"epoch": 0.4198927933293627,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989725230428262,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.17461090832948684,
|
|
"num_tokens": 9870527.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.393940591812134,
|
|
"epoch": 0.4204883859440143,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004989684512993205,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.1825983390212059,
|
|
"num_tokens": 9883616.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.339281606674194,
|
|
"epoch": 0.42108397855866586,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989643715224307,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.1792970046401024,
|
|
"num_tokens": 9896261.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.488557291030884,
|
|
"epoch": 0.42167957117331745,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989602837123031,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.17837779670953752,
|
|
"num_tokens": 9910405.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.512346267700195,
|
|
"epoch": 0.42227516378796903,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989561878690842,
|
|
"loss": 5.3244,
|
|
"mean_token_accuracy": 0.18207647353410722,
|
|
"num_tokens": 9923932.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.411928462982178,
|
|
"epoch": 0.4228707564026206,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000498952083992921,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.178289432823658,
|
|
"num_tokens": 9938132.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.391793441772461,
|
|
"epoch": 0.4234663490172722,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989479720839605,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.18577739149332045,
|
|
"num_tokens": 9952468.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.468659734725952,
|
|
"epoch": 0.4240619416319238,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989438521423506,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.1724991723895073,
|
|
"num_tokens": 9967269.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.389604949951172,
|
|
"epoch": 0.4246575342465753,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989397241682387,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.17644831985235215,
|
|
"num_tokens": 9979776.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.555214786529541,
|
|
"epoch": 0.4252531268612269,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000498935588161773,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.16603707075119017,
|
|
"num_tokens": 9993276.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.3539684295654295,
|
|
"epoch": 0.4258487194758785,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989314441231019,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.1891721025109291,
|
|
"num_tokens": 10005683.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.405005931854248,
|
|
"epoch": 0.4264443120905301,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004989272920523741,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.17995380461215973,
|
|
"num_tokens": 10018526.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.44573974609375,
|
|
"epoch": 0.42703990470518166,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004989231319497382,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.1663253426551819,
|
|
"num_tokens": 10034505.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.50796422958374,
|
|
"epoch": 0.42763549731983325,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989189638153437,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.17348333597183227,
|
|
"num_tokens": 10047465.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.407271909713745,
|
|
"epoch": 0.42823108993448483,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004989147876493401,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.17431857883930207,
|
|
"num_tokens": 10061644.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.4884562492370605,
|
|
"epoch": 0.4288266825491364,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989106034518771,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.16636295318603517,
|
|
"num_tokens": 10076672.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.47823576927185,
|
|
"epoch": 0.42942227516378795,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004989064112231049,
|
|
"loss": 5.3624,
|
|
"mean_token_accuracy": 0.16651387363672257,
|
|
"num_tokens": 10091784.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.440695524215698,
|
|
"epoch": 0.43001786777843953,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004989022109631736,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.17865151762962342,
|
|
"num_tokens": 10104848.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.313720750808716,
|
|
"epoch": 0.4306134603930911,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988980026722341,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.17476957142353058,
|
|
"num_tokens": 10120561.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.463210964202881,
|
|
"epoch": 0.4312090530077427,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004988937863504373,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.17324580252170563,
|
|
"num_tokens": 10135692.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.414644336700439,
|
|
"epoch": 0.4318046456223943,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004988895619979344,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.18038345873355865,
|
|
"num_tokens": 10148768.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.408927726745605,
|
|
"epoch": 0.4324002382370459,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498885329614877,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.17999188899993895,
|
|
"num_tokens": 10162234.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.443536901473999,
|
|
"epoch": 0.43299583085169746,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988810892014168,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.17555629163980485,
|
|
"num_tokens": 10177588.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.392063570022583,
|
|
"epoch": 0.433591423466349,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004988768407577058,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.18176117688417434,
|
|
"num_tokens": 10190324.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.280470323562622,
|
|
"epoch": 0.4341870160810006,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988725842838968,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.18004910945892333,
|
|
"num_tokens": 10204790.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.429841375350952,
|
|
"epoch": 0.43478260869565216,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000498868319780142,
|
|
"loss": 5.1764,
|
|
"mean_token_accuracy": 0.17985706627368928,
|
|
"num_tokens": 10219777.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.392672491073609,
|
|
"epoch": 0.43537820131030375,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988640472465947,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.174774831533432,
|
|
"num_tokens": 10234477.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.326955938339234,
|
|
"epoch": 0.43597379392495533,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004988597666834078,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.18471942394971846,
|
|
"num_tokens": 10247196.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.453542613983155,
|
|
"epoch": 0.4365693865396069,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988554780907353,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.1743731051683426,
|
|
"num_tokens": 10260752.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.379400730133057,
|
|
"epoch": 0.4371649791542585,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988511814687306,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.17780135124921798,
|
|
"num_tokens": 10274500.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.440290880203247,
|
|
"epoch": 0.4377605717689101,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004988468768175479,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.17906238734722138,
|
|
"num_tokens": 10290271.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.457077503204346,
|
|
"epoch": 0.4383561643835616,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988425641373418,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.1688911572098732,
|
|
"num_tokens": 10305645.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.367054414749146,
|
|
"epoch": 0.4389517569982132,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004988382434282668,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.18412871211767196,
|
|
"num_tokens": 10321267.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.478347396850586,
|
|
"epoch": 0.4395473496128648,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498833914690478,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.17777034193277358,
|
|
"num_tokens": 10336597.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.423448801040649,
|
|
"epoch": 0.4401429422275164,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988295779241306,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.17510208189487458,
|
|
"num_tokens": 10351887.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.320586347579956,
|
|
"epoch": 0.44073853484216796,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004988252331293802,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.17715793550014497,
|
|
"num_tokens": 10366078.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.372301197052002,
|
|
"epoch": 0.44133412745681955,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988208803063827,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.18149596601724624,
|
|
"num_tokens": 10380382.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.412890100479126,
|
|
"epoch": 0.44192972007147113,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004988165194552939,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.18643212467432022,
|
|
"num_tokens": 10394554.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.385644626617432,
|
|
"epoch": 0.4425253126861227,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988121505762706,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.1813192620873451,
|
|
"num_tokens": 10408803.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.433049821853638,
|
|
"epoch": 0.44312090530077425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988077736694693,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.17627055197954178,
|
|
"num_tokens": 10421577.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.406940555572509,
|
|
"epoch": 0.44371649791542583,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988033887350471,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.17448823451995848,
|
|
"num_tokens": 10435117.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.4828883647918705,
|
|
"epoch": 0.4443120905300774,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987989957731611,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.1733681872487068,
|
|
"num_tokens": 10448762.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.406545734405517,
|
|
"epoch": 0.444907683144729,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987945947839691,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.17133970111608504,
|
|
"num_tokens": 10462722.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.471333360671997,
|
|
"epoch": 0.4455032757593806,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498790185767629,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.1732810392975807,
|
|
"num_tokens": 10477834.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.389318656921387,
|
|
"epoch": 0.4460988683740322,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987857687242986,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.1818789780139923,
|
|
"num_tokens": 10490807.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.3262608528137205,
|
|
"epoch": 0.44669446098868376,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987813436541366,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.18469011336565017,
|
|
"num_tokens": 10505064.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.360294532775879,
|
|
"epoch": 0.4472900536033353,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987769105573016,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.183121694624424,
|
|
"num_tokens": 10517567.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.517618465423584,
|
|
"epoch": 0.4478856462179869,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004987724694339526,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.1762111082673073,
|
|
"num_tokens": 10533697.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.3861993789672855,
|
|
"epoch": 0.44848123883263846,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987680202842491,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.1786264106631279,
|
|
"num_tokens": 10547533.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.376552867889404,
|
|
"epoch": 0.44907683144729005,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987635631083505,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.1777271956205368,
|
|
"num_tokens": 10562193.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.372302389144897,
|
|
"epoch": 0.44967242406194163,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987590979064167,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.18318057358264922,
|
|
"num_tokens": 10575202.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.469649791717529,
|
|
"epoch": 0.4502680166765932,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987546246786078,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.17711444050073624,
|
|
"num_tokens": 10589064.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.476633310317993,
|
|
"epoch": 0.4508636092912448,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987501434250844,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.16773197799921036,
|
|
"num_tokens": 10602837.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.409980726242066,
|
|
"epoch": 0.4514592019058964,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498745654146007,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.17838809937238692,
|
|
"num_tokens": 10618200.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.402648162841797,
|
|
"epoch": 0.4520547945205479,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000498741156841537,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.1775661364197731,
|
|
"num_tokens": 10631804.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.450578212738037,
|
|
"epoch": 0.4526503871351995,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004987366515118353,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.1735926926136017,
|
|
"num_tokens": 10647066.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.3924126625061035,
|
|
"epoch": 0.4532459797498511,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004987321381570638,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.17805004715919495,
|
|
"num_tokens": 10661436.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.439834356307983,
|
|
"epoch": 0.4538415723645027,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987276167773842,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.17254049926996232,
|
|
"num_tokens": 10675299.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.331587505340576,
|
|
"epoch": 0.45443716497915426,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987230873729588,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.18543247133493423,
|
|
"num_tokens": 10689073.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.310808563232422,
|
|
"epoch": 0.45503275759380585,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049871854994395,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.18927500993013383,
|
|
"num_tokens": 10703017.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.510147285461426,
|
|
"epoch": 0.45562835020845743,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004987140044905205,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.17074571251869203,
|
|
"num_tokens": 10718151.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.4032470226287845,
|
|
"epoch": 0.456223942823109,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987094510128335,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.18504303991794585,
|
|
"num_tokens": 10731299.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.340116786956787,
|
|
"epoch": 0.45681953543776055,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987048895110522,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.17852347046136857,
|
|
"num_tokens": 10745152.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.321061706542968,
|
|
"epoch": 0.45741512805241213,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987003199853401,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.1791461393237114,
|
|
"num_tokens": 10758557.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.434852409362793,
|
|
"epoch": 0.4580107206670637,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986957424358613,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.17962770760059357,
|
|
"num_tokens": 10773647.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.408813190460205,
|
|
"epoch": 0.4586063132817153,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049869115686278,
|
|
"loss": 5.2314,
|
|
"mean_token_accuracy": 0.18089141547679902,
|
|
"num_tokens": 10786973.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.457066488265991,
|
|
"epoch": 0.4592019058963669,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004986865632662606,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.17332253456115723,
|
|
"num_tokens": 10800521.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.422528409957886,
|
|
"epoch": 0.4597974985110185,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986819616464678,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.181814606487751,
|
|
"num_tokens": 10814934.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.399583959579468,
|
|
"epoch": 0.46039309112567006,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986773520035667,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.18810149431228637,
|
|
"num_tokens": 10830156.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.361807823181152,
|
|
"epoch": 0.46098868374032165,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004986727343377227,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.18367910534143447,
|
|
"num_tokens": 10844354.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.3933305740356445,
|
|
"epoch": 0.4615842763549732,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986681086491014,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.18292448669672012,
|
|
"num_tokens": 10855978.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.37632040977478,
|
|
"epoch": 0.46217986896962476,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986634749378686,
|
|
"loss": 5.0983,
|
|
"mean_token_accuracy": 0.1917484551668167,
|
|
"num_tokens": 10869395.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.326293659210205,
|
|
"epoch": 0.46277546158427635,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004986588332041908,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.18216816186904908,
|
|
"num_tokens": 10884817.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.371928930282593,
|
|
"epoch": 0.46337105419892793,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986541834482342,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.18720285147428511,
|
|
"num_tokens": 10898435.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.342796754837036,
|
|
"epoch": 0.4639666468135795,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004986495256701657,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.17733437120914458,
|
|
"num_tokens": 10911777.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.416338014602661,
|
|
"epoch": 0.4645622394282311,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986448598701523,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.18013208210468293,
|
|
"num_tokens": 10925025.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.366250228881836,
|
|
"epoch": 0.4651578320428827,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004986401860483615,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.18250798135995866,
|
|
"num_tokens": 10940019.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.43860969543457,
|
|
"epoch": 0.4657534246575342,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004986355042049608,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.17277711629867554,
|
|
"num_tokens": 10954702.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.377546691894532,
|
|
"epoch": 0.4663490172721858,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004986308143401181,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.1878010779619217,
|
|
"num_tokens": 10970231.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.394086408615112,
|
|
"epoch": 0.4669446098868374,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004986261164540018,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.17613804936408997,
|
|
"num_tokens": 10986561.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.428871011734008,
|
|
"epoch": 0.467540202501489,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004986214105467801,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.18019791692495346,
|
|
"num_tokens": 11000246.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.331533193588257,
|
|
"epoch": 0.46813579511614056,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004986166966186223,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.1948564752936363,
|
|
"num_tokens": 11012590.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.266906261444092,
|
|
"epoch": 0.46873138773079215,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004986119746696969,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.18875349164009095,
|
|
"num_tokens": 11025620.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.310734844207763,
|
|
"epoch": 0.46932698034544373,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986072447001736,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.1885087177157402,
|
|
"num_tokens": 11038352.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.331786203384399,
|
|
"epoch": 0.4699225729600953,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986025067102221,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.19463525116443633,
|
|
"num_tokens": 11051226.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.4130147933959964,
|
|
"epoch": 0.47051816557474685,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985977607000121,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.18284327983856202,
|
|
"num_tokens": 11065910.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.420770120620728,
|
|
"epoch": 0.47111375818939843,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985930066697141,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.18784887790679933,
|
|
"num_tokens": 11078804.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.364886808395386,
|
|
"epoch": 0.47170935080405,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985882446194984,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.19021952003240586,
|
|
"num_tokens": 11090903.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.432231760025024,
|
|
"epoch": 0.4723049434187016,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498583474549536,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.17478130906820297,
|
|
"num_tokens": 11106914.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.420093584060669,
|
|
"epoch": 0.4729005360333532,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985786964599978,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.18365588784217834,
|
|
"num_tokens": 11121471.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.304426050186157,
|
|
"epoch": 0.4734961286480048,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985739103510553,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.18712460696697236,
|
|
"num_tokens": 11135553.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.394079256057739,
|
|
"epoch": 0.47409172126265636,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985691162228802,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.18243786990642546,
|
|
"num_tokens": 11149335.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.423213386535645,
|
|
"epoch": 0.47468731387730795,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985643140756442,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.17831269204616546,
|
|
"num_tokens": 11161589.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.368987321853638,
|
|
"epoch": 0.4752829064919595,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00049855950390952,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.1739825874567032,
|
|
"num_tokens": 11175094.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.3500786304473875,
|
|
"epoch": 0.47587849910661106,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004985546857246797,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.18300384730100633,
|
|
"num_tokens": 11191452.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.331335973739624,
|
|
"epoch": 0.47647409172126265,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985498595212964,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.18484076261520385,
|
|
"num_tokens": 11203831.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.402827215194702,
|
|
"epoch": 0.47706968433591423,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004985450252995431,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.17342661917209626,
|
|
"num_tokens": 11218022.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.377013206481934,
|
|
"epoch": 0.4776652769505658,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985401830595932,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.17944857925176622,
|
|
"num_tokens": 11229993.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.443713617324829,
|
|
"epoch": 0.4782608695652174,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985353328016204,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.1754394769668579,
|
|
"num_tokens": 11243089.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.444408416748047,
|
|
"epoch": 0.478856462179869,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004985304745257986,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.17147151678800582,
|
|
"num_tokens": 11260349.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.401764726638794,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985256082323022,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.18407257348299028,
|
|
"num_tokens": 11275875.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.424989700317383,
|
|
"epoch": 0.4800476474091721,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985207339213057,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.18253789991140365,
|
|
"num_tokens": 11289611.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.379727458953857,
|
|
"epoch": 0.4806432400238237,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985158515929837,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.177983558177948,
|
|
"num_tokens": 11303917.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.368940591812134,
|
|
"epoch": 0.4812388326384753,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004985109612475116,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.18253531455993652,
|
|
"num_tokens": 11317400.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.367254209518433,
|
|
"epoch": 0.48183442525312686,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985060628850648,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.1823686182498932,
|
|
"num_tokens": 11330771.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.408759593963623,
|
|
"epoch": 0.48243001786777845,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985011565058189,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.18497083336114883,
|
|
"num_tokens": 11344430.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.483620691299438,
|
|
"epoch": 0.48302561048243003,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004984962421099498,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.1729663148522377,
|
|
"num_tokens": 11358940.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.334818410873413,
|
|
"epoch": 0.4836212030970816,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498491319697634,
|
|
"loss": 5.1855,
|
|
"mean_token_accuracy": 0.18312254995107652,
|
|
"num_tokens": 11371772.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.387055587768555,
|
|
"epoch": 0.48421679571173315,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498486389269048,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.17532442808151244,
|
|
"num_tokens": 11383976.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.414940881729126,
|
|
"epoch": 0.48481238832638474,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984814508243685,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.17781192064285278,
|
|
"num_tokens": 11398659.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.515937662124633,
|
|
"epoch": 0.4854079809410363,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984765043637727,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.17402607202529907,
|
|
"num_tokens": 11413083.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.359595489501953,
|
|
"epoch": 0.4860035735556879,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000498471549887438,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.18464861810207367,
|
|
"num_tokens": 11426408.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.402296161651611,
|
|
"epoch": 0.4865991661703395,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004984665873955422,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.1712955966591835,
|
|
"num_tokens": 11440609.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.3476975440979,
|
|
"epoch": 0.4871947587849911,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004984616168882632,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.18086556494235992,
|
|
"num_tokens": 11454795.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.393082523345948,
|
|
"epoch": 0.48779035139964266,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984566383657794,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.1818688228726387,
|
|
"num_tokens": 11468695.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.334658479690551,
|
|
"epoch": 0.48838594401429425,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004984516518282692,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.18530638217926027,
|
|
"num_tokens": 11483601.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.491518497467041,
|
|
"epoch": 0.4889815366289458,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004984466572759117,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.17401891052722931,
|
|
"num_tokens": 11497860.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.3319940090179445,
|
|
"epoch": 0.48957712924359736,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984416547088858,
|
|
"loss": 5.0456,
|
|
"mean_token_accuracy": 0.18910971134901047,
|
|
"num_tokens": 11512582.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.273644924163818,
|
|
"epoch": 0.49017272185824895,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004984366441273711,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.1824891299009323,
|
|
"num_tokens": 11525480.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.331992197036743,
|
|
"epoch": 0.49076831447290054,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004984316255315472,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.1852354273200035,
|
|
"num_tokens": 11540465.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.343194818496704,
|
|
"epoch": 0.4913639070875521,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984265989215942,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.1740109443664551,
|
|
"num_tokens": 11555622.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.365783548355102,
|
|
"epoch": 0.4919594997022037,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984215642976923,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.18323372453451156,
|
|
"num_tokens": 11569547.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.354334735870362,
|
|
"epoch": 0.4925550923168553,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984165216600224,
|
|
"loss": 5.1192,
|
|
"mean_token_accuracy": 0.18380082100629808,
|
|
"num_tokens": 11583464.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.326048707962036,
|
|
"epoch": 0.4931506849315068,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004984114710087648,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.1819705381989479,
|
|
"num_tokens": 11597639.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.384754037857055,
|
|
"epoch": 0.4937462775461584,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984064123441011,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.17815957367420196,
|
|
"num_tokens": 11610645.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.401113748550415,
|
|
"epoch": 0.49434187016081,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984013456662127,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.17818289399147033,
|
|
"num_tokens": 11624802.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.427695322036743,
|
|
"epoch": 0.4949374627754616,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004983962709752812,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.18149085938930512,
|
|
"num_tokens": 11638538.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.411260271072388,
|
|
"epoch": 0.49553305539011316,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983911882714886,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.1772036150097847,
|
|
"num_tokens": 11651639.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.382980918884277,
|
|
"epoch": 0.49612864800476475,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983860975550174,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.17371416836977005,
|
|
"num_tokens": 11668784.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.41145601272583,
|
|
"epoch": 0.49672424061941634,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004983809988260501,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.18291076570749282,
|
|
"num_tokens": 11682737.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.279611301422119,
|
|
"epoch": 0.4973198332340679,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983758920847696,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.18731954097747802,
|
|
"num_tokens": 11697666.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.40027174949646,
|
|
"epoch": 0.49791542584871945,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004983707773313589,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.17676257342100143,
|
|
"num_tokens": 11712747.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.382396697998047,
|
|
"epoch": 0.49851101846337104,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004983656545660016,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.17878617644309996,
|
|
"num_tokens": 11727233.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.371932077407837,
|
|
"epoch": 0.4991066110780226,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983605237888815,
|
|
"loss": 5.265,
|
|
"mean_token_accuracy": 0.17287526577711104,
|
|
"num_tokens": 11743677.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.4083061695098875,
|
|
"epoch": 0.4997022036926742,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983553850001826,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.18976587653160096,
|
|
"num_tokens": 11756362.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.228198432922364,
|
|
"epoch": 0.5002977963073257,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983502382000892,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.18061042875051497,
|
|
"num_tokens": 11769955.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.255529689788818,
|
|
"epoch": 0.5008933889219773,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004983450833887859,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.19134392440319062,
|
|
"num_tokens": 11783617.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.417185735702515,
|
|
"epoch": 0.5014889815366289,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004983399205664575,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.17644449174404145,
|
|
"num_tokens": 11797408.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.450252199172974,
|
|
"epoch": 0.5020845741512805,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983347497332894,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.16968824416399003,
|
|
"num_tokens": 11810058.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.324225902557373,
|
|
"epoch": 0.5026801667659321,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983295708894668,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.1793075233697891,
|
|
"num_tokens": 11822921.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.356392240524292,
|
|
"epoch": 0.5032757593805837,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983243840351757,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.18140227496623992,
|
|
"num_tokens": 11837189.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.407381677627564,
|
|
"epoch": 0.5038713519952353,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983191891706021,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.18710006326436995,
|
|
"num_tokens": 11851579.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.273737382888794,
|
|
"epoch": 0.5044669446098868,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983139862959322,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.1863243132829666,
|
|
"num_tokens": 11867013.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.247968244552612,
|
|
"epoch": 0.5050625372245384,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983087754113527,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.19239823520183563,
|
|
"num_tokens": 11879566.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.36608738899231,
|
|
"epoch": 0.50565812983919,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004983035565170505,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.18535499274730682,
|
|
"num_tokens": 11893103.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.336899375915527,
|
|
"epoch": 0.5062537224538416,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982983296132128,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.1883890300989151,
|
|
"num_tokens": 11907396.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.317756032943725,
|
|
"epoch": 0.5068493150684932,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982930947000271,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.18940700888633727,
|
|
"num_tokens": 11921674.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.38133659362793,
|
|
"epoch": 0.5074449076831448,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982878517776812,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.18168587237596512,
|
|
"num_tokens": 11933739.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.218308448791504,
|
|
"epoch": 0.5080405002977963,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498282600846363,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.19236501008272172,
|
|
"num_tokens": 11946686.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.3818175315856935,
|
|
"epoch": 0.5086360929124479,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498277341906261,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.18358779102563857,
|
|
"num_tokens": 11962112.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.321989727020264,
|
|
"epoch": 0.5092316855270994,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004982720749575637,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.186101932823658,
|
|
"num_tokens": 11976094.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.334202766418457,
|
|
"epoch": 0.509827278141751,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982668000004602,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.17744266092777253,
|
|
"num_tokens": 11991969.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.421050214767456,
|
|
"epoch": 0.5104228707564026,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982615170351395,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.1779862806200981,
|
|
"num_tokens": 12007588.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.292688941955566,
|
|
"epoch": 0.5110184633710542,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982562260617912,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.18632632941007615,
|
|
"num_tokens": 12021658.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.3696043491363525,
|
|
"epoch": 0.5116140559857058,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982509270806052,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.17920160740613938,
|
|
"num_tokens": 12035216.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.366880273818969,
|
|
"epoch": 0.5122096486003573,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982456200917712,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.18781054466962815,
|
|
"num_tokens": 12047435.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.43516058921814,
|
|
"epoch": 0.5128052412150089,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049824030509548,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.17456135600805284,
|
|
"num_tokens": 12060314.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.4427807331085205,
|
|
"epoch": 0.5134008338296605,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498234982091922,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.17351605147123336,
|
|
"num_tokens": 12076829.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.342952823638916,
|
|
"epoch": 0.5139964264443121,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004982296510812879,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.18961286991834642,
|
|
"num_tokens": 12090008.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.334354257583618,
|
|
"epoch": 0.5145920190589637,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004982243120637694,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.1797313079237938,
|
|
"num_tokens": 12103163.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.441323900222779,
|
|
"epoch": 0.5151876116736153,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982189650395577,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.1782443955540657,
|
|
"num_tokens": 12117398.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.315100240707397,
|
|
"epoch": 0.5157832042882668,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004982136100088447,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.1855406641960144,
|
|
"num_tokens": 12132649.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.306979608535767,
|
|
"epoch": 0.5163787969029184,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982082469718224,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.1825730711221695,
|
|
"num_tokens": 12146385.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.274682950973511,
|
|
"epoch": 0.51697438951757,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982028759286831,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.19284637421369552,
|
|
"num_tokens": 12159928.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.261528635025025,
|
|
"epoch": 0.5175699821322216,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981974968796197,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.18565332591533662,
|
|
"num_tokens": 12174624.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.308650350570678,
|
|
"epoch": 0.5181655747468732,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004981921098248249,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.19029283076524733,
|
|
"num_tokens": 12187383.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.368241548538208,
|
|
"epoch": 0.5187611673615247,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498186714764492,
|
|
"loss": 5.1671,
|
|
"mean_token_accuracy": 0.17929755598306657,
|
|
"num_tokens": 12200381.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.406327629089356,
|
|
"epoch": 0.5193567599761763,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004981813116988145,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.1789672315120697,
|
|
"num_tokens": 12216497.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.309513139724731,
|
|
"epoch": 0.5199523525908278,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981759006279864,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.1865038126707077,
|
|
"num_tokens": 12230368.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.3643265724182125,
|
|
"epoch": 0.5205479452054794,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981704815522014,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.17929701060056685,
|
|
"num_tokens": 12246492.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.363251352310181,
|
|
"epoch": 0.521143537820131,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004981650544716542,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.18221537619829178,
|
|
"num_tokens": 12260486.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.290689611434937,
|
|
"epoch": 0.5217391304347826,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981596193865393,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.1854724481701851,
|
|
"num_tokens": 12275001.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.286444282531738,
|
|
"epoch": 0.5223347230494342,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004981541762970517,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.18841983526945114,
|
|
"num_tokens": 12289690.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.306200170516968,
|
|
"epoch": 0.5229303156640858,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981487252033866,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.18047735393047332,
|
|
"num_tokens": 12304098.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.335263347625732,
|
|
"epoch": 0.5235259082787374,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004981432661057396,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.18927100896835328,
|
|
"num_tokens": 12318583.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.377587938308716,
|
|
"epoch": 0.5241215008933889,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004981377990043064,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.1801874965429306,
|
|
"num_tokens": 12332239.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.279301881790161,
|
|
"epoch": 0.5247170935080405,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981323238992831,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.18113580644130706,
|
|
"num_tokens": 12344730.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.363180828094483,
|
|
"epoch": 0.5253126861226921,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004981268407908662,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.18083513528108597,
|
|
"num_tokens": 12358661.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.350935792922973,
|
|
"epoch": 0.5259082787373437,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981213496792523,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.18657889664173127,
|
|
"num_tokens": 12372876.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.409125471115113,
|
|
"epoch": 0.5265038713519953,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981158505646383,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.17748216688632965,
|
|
"num_tokens": 12386960.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.2739006042480465,
|
|
"epoch": 0.5270994639666469,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981103434472216,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.19526512920856476,
|
|
"num_tokens": 12400497.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.407064628601074,
|
|
"epoch": 0.5276950565812983,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981048283271997,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.1837845429778099,
|
|
"num_tokens": 12415013.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.376692056655884,
|
|
"epoch": 0.5282906491959499,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004980993052047701,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.1846063882112503,
|
|
"num_tokens": 12427915.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.3180173397064205,
|
|
"epoch": 0.5288862418106015,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980937740801313,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.183672171831131,
|
|
"num_tokens": 12440136.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.306796073913574,
|
|
"epoch": 0.5294818344252531,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004980882349534816,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.18244660794734954,
|
|
"num_tokens": 12454190.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.463627767562866,
|
|
"epoch": 0.5300774270399047,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004980826878250195,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.17683406919240952,
|
|
"num_tokens": 12470069.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.3316303253173825,
|
|
"epoch": 0.5306730196545563,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980771326949442,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.17865769416093827,
|
|
"num_tokens": 12485349.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.359301424026489,
|
|
"epoch": 0.5312686122692079,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004980715695634549,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.1834998235106468,
|
|
"num_tokens": 12500690.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.3912193775177,
|
|
"epoch": 0.5318642048838594,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004980659984307511,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.18115987703204156,
|
|
"num_tokens": 12512619.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.43045334815979,
|
|
"epoch": 0.532459797498511,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004980604192970325,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.17694442868232726,
|
|
"num_tokens": 12527193.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.325862789154053,
|
|
"epoch": 0.5330553901131626,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004980548321624993,
|
|
"loss": 5.1922,
|
|
"mean_token_accuracy": 0.1832765594124794,
|
|
"num_tokens": 12540127.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.325676584243775,
|
|
"epoch": 0.5336509827278142,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000498049237027352,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.18478801995515823,
|
|
"num_tokens": 12555818.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.341642713546753,
|
|
"epoch": 0.5342465753424658,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980436338917914,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.18077556937932968,
|
|
"num_tokens": 12568337.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.315216779708862,
|
|
"epoch": 0.5348421679571174,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498038022756018,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.18242402970790864,
|
|
"num_tokens": 12581368.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.3535552501678465,
|
|
"epoch": 0.535437760571769,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004980324036202335,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.18351043313741683,
|
|
"num_tokens": 12595738.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.283936214447022,
|
|
"epoch": 0.5360333531864205,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980267764846393,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.1905273526906967,
|
|
"num_tokens": 12609736.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.267637300491333,
|
|
"epoch": 0.5366289458010721,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004980211413494373,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.183333058655262,
|
|
"num_tokens": 12624101.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.236968851089477,
|
|
"epoch": 0.5372245384157236,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004980154982148296,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.19253573715686798,
|
|
"num_tokens": 12639126.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.323569059371948,
|
|
"epoch": 0.5378201310303752,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004980098470810185,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.18165246695280074,
|
|
"num_tokens": 12652532.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.349842882156372,
|
|
"epoch": 0.5384157236450268,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980041879482068,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.1902925729751587,
|
|
"num_tokens": 12666270.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.295321464538574,
|
|
"epoch": 0.5390113162596784,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004979985208165975,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.1878521516919136,
|
|
"num_tokens": 12682393.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.372230148315429,
|
|
"epoch": 0.5396069088743299,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979928456863937,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.18520011156797409,
|
|
"num_tokens": 12696685.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.217958593368531,
|
|
"epoch": 0.5402025014889815,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004979871625577991,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.19265486299991608,
|
|
"num_tokens": 12711091.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.317847633361817,
|
|
"epoch": 0.5407980941036331,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979814714310177,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.1897505909204483,
|
|
"num_tokens": 12725041.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.351825428009033,
|
|
"epoch": 0.5413936867182847,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979757723062533,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.18284923881292342,
|
|
"num_tokens": 12738318.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.288203430175781,
|
|
"epoch": 0.5419892793329363,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979700651837107,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.1857344388961792,
|
|
"num_tokens": 12750695.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.274901437759399,
|
|
"epoch": 0.5425848719475879,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004979643500635942,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.18815772086381913,
|
|
"num_tokens": 12764779.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.340201425552368,
|
|
"epoch": 0.5431804645622395,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979586269461089,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.17946089059114456,
|
|
"num_tokens": 12779197.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.322599029541015,
|
|
"epoch": 0.543776057176891,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979528958314604,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.18912597000598907,
|
|
"num_tokens": 12791140.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.254619216918945,
|
|
"epoch": 0.5443716497915426,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004979471567198539,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.19738948941230774,
|
|
"num_tokens": 12806382.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.309173154830932,
|
|
"epoch": 0.5449672424061942,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979414096114953,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.19092788249254228,
|
|
"num_tokens": 12819095.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.191449928283691,
|
|
"epoch": 0.5455628350208458,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497935654506591,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.1970282480120659,
|
|
"num_tokens": 12831562.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.396162366867065,
|
|
"epoch": 0.5461584276354973,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000497929891405347,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.17817889600992204,
|
|
"num_tokens": 12845535.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.240388965606689,
|
|
"epoch": 0.5467540202501489,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979241203079705,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.19041113704442977,
|
|
"num_tokens": 12859067.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.341919183731079,
|
|
"epoch": 0.5473496128648004,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979183412146681,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.19000178277492524,
|
|
"num_tokens": 12872712.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.3105340003967285,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004979125541256474,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.18238989412784576,
|
|
"num_tokens": 12886701.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.300245380401611,
|
|
"epoch": 0.5485407980941036,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979067590411157,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.1909145936369896,
|
|
"num_tokens": 12900041.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.292470169067383,
|
|
"epoch": 0.5491363907087552,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497900955961281,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.19345691055059433,
|
|
"num_tokens": 12912454.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.398757410049439,
|
|
"epoch": 0.5497319833234068,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978951448863514,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.18304414600133895,
|
|
"num_tokens": 12926373.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.363936805725098,
|
|
"epoch": 0.5503275759380584,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004978893258165354,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.1858728438615799,
|
|
"num_tokens": 12939837.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.343402624130249,
|
|
"epoch": 0.55092316855271,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004978834987520417,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.18721891194581985,
|
|
"num_tokens": 12952904.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.362418746948242,
|
|
"epoch": 0.5515187611673615,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004978776636930792,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.17951781302690506,
|
|
"num_tokens": 12966896.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.3260987281799315,
|
|
"epoch": 0.5521143537820131,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004978718206398574,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.18791312277317046,
|
|
"num_tokens": 12980841.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.257918167114258,
|
|
"epoch": 0.5527099463966647,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978659695925856,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.1898777574300766,
|
|
"num_tokens": 12994506.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.3139807224273685,
|
|
"epoch": 0.5533055390113163,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004978601105514739,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.18538330644369125,
|
|
"num_tokens": 13008817.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.323249340057373,
|
|
"epoch": 0.5539011316259679,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004978542435167324,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.18302487283945085,
|
|
"num_tokens": 13024227.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.274266052246094,
|
|
"epoch": 0.5544967242406195,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004978483684885716,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.19358408749103545,
|
|
"num_tokens": 13037448.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.213516473770142,
|
|
"epoch": 0.5550923168552709,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004978424854672021,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.19025247246026994,
|
|
"num_tokens": 13050582.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.352503919601441,
|
|
"epoch": 0.5556879094699225,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004978365944528349,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.18656214624643325,
|
|
"num_tokens": 13063059.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.40325140953064,
|
|
"epoch": 0.5562835020845741,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978306954456814,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.17506725639104842,
|
|
"num_tokens": 13077193.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.320083713531494,
|
|
"epoch": 0.5568790946992257,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004978247884459532,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.17727275043725968,
|
|
"num_tokens": 13091462.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.274306726455689,
|
|
"epoch": 0.5574746873138773,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004978188734538621,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.18309739977121353,
|
|
"num_tokens": 13107406.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.328941059112549,
|
|
"epoch": 0.5580702799285289,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004978129504696203,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.18748715072870253,
|
|
"num_tokens": 13123623.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.251247930526733,
|
|
"epoch": 0.5586658725431805,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978070194934402,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.18562707751989366,
|
|
"num_tokens": 13138644.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.318075704574585,
|
|
"epoch": 0.559261465157832,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004978010805255347,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.17561105340719224,
|
|
"num_tokens": 13152485.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.349049663543701,
|
|
"epoch": 0.5598570577724836,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004977951335661165,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.19345757663249968,
|
|
"num_tokens": 13165766.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.2103844165802,
|
|
"epoch": 0.5604526503871352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977891786153992,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.17944135665893554,
|
|
"num_tokens": 13180298.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.368817710876465,
|
|
"epoch": 0.5610482430017868,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004977832156735963,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.1776925280690193,
|
|
"num_tokens": 13194925.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.355443143844605,
|
|
"epoch": 0.5616438356164384,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977772447409217,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.18947134017944336,
|
|
"num_tokens": 13208486.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.282683181762695,
|
|
"epoch": 0.56223942823109,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004977712658175894,
|
|
"loss": 5.1205,
|
|
"mean_token_accuracy": 0.1868671163916588,
|
|
"num_tokens": 13222428.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.324584197998047,
|
|
"epoch": 0.5628350208457416,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004977652789038142,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.18026006817817689,
|
|
"num_tokens": 13237341.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.3339954853057865,
|
|
"epoch": 0.5634306134603931,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004977592839998105,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.18767637610435486,
|
|
"num_tokens": 13251085.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.354875707626343,
|
|
"epoch": 0.5640262060750447,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004977532811057936,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.18514059633016586,
|
|
"num_tokens": 13266660.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.2686361312866214,
|
|
"epoch": 0.5646217986896962,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977472702219786,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.18778657615184785,
|
|
"num_tokens": 13280550.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.300787258148193,
|
|
"epoch": 0.5652173913043478,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004977412513485812,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.18928858041763305,
|
|
"num_tokens": 13292905.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.266883802413941,
|
|
"epoch": 0.5658129839189994,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977352244858172,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.19949344992637635,
|
|
"num_tokens": 13305271.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.359965848922729,
|
|
"epoch": 0.566408576533651,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004977291896339029,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.18041886985301972,
|
|
"num_tokens": 13319904.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.309332466125488,
|
|
"epoch": 0.5670041691483025,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004977231467930546,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.19170868694782256,
|
|
"num_tokens": 13331799.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.349821329116821,
|
|
"epoch": 0.5675997617629541,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004977170959634893,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.19196423143148422,
|
|
"num_tokens": 13345269.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.247021245956421,
|
|
"epoch": 0.5681953543776057,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004977110371454239,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.18546835482120513,
|
|
"num_tokens": 13358555.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.3337883949279785,
|
|
"epoch": 0.5687909469922573,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977049703390755,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.18396190404891968,
|
|
"num_tokens": 13373444.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.358067464828491,
|
|
"epoch": 0.5693865396069089,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004976988955446622,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.18579309284687043,
|
|
"num_tokens": 13387530.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.301473951339721,
|
|
"epoch": 0.5699821322215605,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004976928127624013,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.1862201377749443,
|
|
"num_tokens": 13402718.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.3818285942077635,
|
|
"epoch": 0.570577724836212,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004976867219925116,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.18179702758789062,
|
|
"num_tokens": 13416076.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.250191974639892,
|
|
"epoch": 0.5711733174508636,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497680623235211,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.19693999290466307,
|
|
"num_tokens": 13428286.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.27693543434143,
|
|
"epoch": 0.5717689100655152,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004976745164907185,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.18380515724420549,
|
|
"num_tokens": 13442801.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.391993284225464,
|
|
"epoch": 0.5723645026801668,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976684017592533,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.18104581236839296,
|
|
"num_tokens": 13457796.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.323946619033814,
|
|
"epoch": 0.5729600952948184,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976622790410345,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.18597734570503235,
|
|
"num_tokens": 13473291.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.204704236984253,
|
|
"epoch": 0.5735556879094699,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004976561483362818,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.18793633133172988,
|
|
"num_tokens": 13487275.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.2825428485870365,
|
|
"epoch": 0.5741512805241215,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497650009645215,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.19531758427619933,
|
|
"num_tokens": 13500148.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.308289289474487,
|
|
"epoch": 0.574746873138773,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976438629680543,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.19100415259599685,
|
|
"num_tokens": 13514231.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.318165969848633,
|
|
"epoch": 0.5753424657534246,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004976377083050204,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.18271679878234864,
|
|
"num_tokens": 13528691.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.306242322921753,
|
|
"epoch": 0.5759380583680762,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004976315456563339,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.18551575839519502,
|
|
"num_tokens": 13542115.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.301770448684692,
|
|
"epoch": 0.5765336509827278,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976253750222157,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.1829224482178688,
|
|
"num_tokens": 13556269.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.343232870101929,
|
|
"epoch": 0.5771292435973794,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004976191964028874,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.1852123335003853,
|
|
"num_tokens": 13571853.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.3390281200408936,
|
|
"epoch": 0.577724836212031,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004976130097985703,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.18490727990865707,
|
|
"num_tokens": 13587631.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.318580245971679,
|
|
"epoch": 0.5783204288266826,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004976068152094867,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.19177399575710297,
|
|
"num_tokens": 13603140.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.204405355453491,
|
|
"epoch": 0.5789160214413341,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004976006126358584,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.19838816821575164,
|
|
"num_tokens": 13617606.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.357296276092529,
|
|
"epoch": 0.5795116140559857,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975944020779082,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.18520898520946502,
|
|
"num_tokens": 13632244.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.309529113769531,
|
|
"epoch": 0.5801072066706373,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975881835358586,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.18462262749671937,
|
|
"num_tokens": 13646166.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.294286060333252,
|
|
"epoch": 0.5807027992852889,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004975819570099328,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.18599398732185363,
|
|
"num_tokens": 13661141.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.3408928394317625,
|
|
"epoch": 0.5812983918999405,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497575722500354,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.18936541229486464,
|
|
"num_tokens": 13675007.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.3129129886627195,
|
|
"epoch": 0.5818939845145921,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000497569480007346,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.1885376289486885,
|
|
"num_tokens": 13690679.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.242873954772949,
|
|
"epoch": 0.5824895771292437,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975632295311327,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.1896588459610939,
|
|
"num_tokens": 13705068.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.269522476196289,
|
|
"epoch": 0.5830851697438951,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004975569710719382,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.19121027886867523,
|
|
"num_tokens": 13719550.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.333636665344239,
|
|
"epoch": 0.5836807623585467,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975507046299869,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.1869287446141243,
|
|
"num_tokens": 13733516.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.417228651046753,
|
|
"epoch": 0.5842763549731983,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975444302055038,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.18411969393491745,
|
|
"num_tokens": 13747242.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.219224071502685,
|
|
"epoch": 0.5848719475878499,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004975381477987136,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.18591572791337968,
|
|
"num_tokens": 13761434.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.3894013404846195,
|
|
"epoch": 0.5854675402025015,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004975318574098422,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.18624072819948195,
|
|
"num_tokens": 13773942.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.327998971939087,
|
|
"epoch": 0.586063132817153,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004975255590391147,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.19349586665630342,
|
|
"num_tokens": 13787217.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.302249526977539,
|
|
"epoch": 0.5866587254318046,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004975192526867572,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.19150582551956177,
|
|
"num_tokens": 13801444.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.344896459579468,
|
|
"epoch": 0.5872543180464562,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975129383529959,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.18853237181901933,
|
|
"num_tokens": 13814453.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.3083351135253904,
|
|
"epoch": 0.5878499106611078,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004975066160380573,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.18458928018808365,
|
|
"num_tokens": 13829620.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.220902061462402,
|
|
"epoch": 0.5884455032757594,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975002857421681,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.18334962278604508,
|
|
"num_tokens": 13842005.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.185434198379516,
|
|
"epoch": 0.589041095890411,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004974939474655554,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.19217298179864883,
|
|
"num_tokens": 13854299.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.237213563919068,
|
|
"epoch": 0.5896366885050626,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004974876012084468,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.19455666095018387,
|
|
"num_tokens": 13866294.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.286949968338012,
|
|
"epoch": 0.5902322811197142,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974812469710694,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.18583744168281555,
|
|
"num_tokens": 13879820.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.244901895523071,
|
|
"epoch": 0.5908278737343657,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004974748847536516,
|
|
"loss": 5.0855,
|
|
"mean_token_accuracy": 0.17792990505695344,
|
|
"num_tokens": 13894664.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.331088590621948,
|
|
"epoch": 0.5914234663490173,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974685145564213,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.18015981912612916,
|
|
"num_tokens": 13908706.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.280873966217041,
|
|
"epoch": 0.5920190589636688,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004974621363796071,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.19480266869068147,
|
|
"num_tokens": 13921402.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.244831800460815,
|
|
"epoch": 0.5926146515783204,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004974557502234378,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.1833819180727005,
|
|
"num_tokens": 13934731.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.280506706237793,
|
|
"epoch": 0.593210244192972,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974493560881423,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.18667688667774202,
|
|
"num_tokens": 13947990.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.322307014465332,
|
|
"epoch": 0.5938058368076236,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004974429539739502,
|
|
"loss": 4.9994,
|
|
"mean_token_accuracy": 0.19545883387327195,
|
|
"num_tokens": 13961167.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.248807811737061,
|
|
"epoch": 0.5944014294222751,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004974365438810911,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.195140278339386,
|
|
"num_tokens": 13974136.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.217555189132691,
|
|
"epoch": 0.5949970220369267,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004974301258097948,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.18835571855306626,
|
|
"num_tokens": 13989229.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.366804361343384,
|
|
"epoch": 0.5955926146515783,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004974236997602915,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.17720674574375153,
|
|
"num_tokens": 14003136.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.3019743919372555,
|
|
"epoch": 0.5961882072662299,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004974172657328116,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.18821991980075836,
|
|
"num_tokens": 14017712.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.364273643493652,
|
|
"epoch": 0.5967837998808815,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497410823727586,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.18556804805994034,
|
|
"num_tokens": 14032740.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.28114881515503,
|
|
"epoch": 0.5973793924955331,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497404373744846,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.18723592758178711,
|
|
"num_tokens": 14048059.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.284004831314087,
|
|
"epoch": 0.5979749851101847,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004973979157848227,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.1942220449447632,
|
|
"num_tokens": 14062318.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.325515365600586,
|
|
"epoch": 0.5985705777248362,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973914498477475,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.18517005294561387,
|
|
"num_tokens": 14076617.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.317840814590454,
|
|
"epoch": 0.5991661703394878,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004973849759338527,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.18557091653347016,
|
|
"num_tokens": 14092067.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.326718473434449,
|
|
"epoch": 0.5997617629541394,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004973784940433706,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.18405185490846634,
|
|
"num_tokens": 14106969.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.25502347946167,
|
|
"epoch": 0.600357355568791,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973720041765332,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.18913086056709288,
|
|
"num_tokens": 14119877.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.29155535697937,
|
|
"epoch": 0.6009529481834425,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004973655063335736,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.18656927794218064,
|
|
"num_tokens": 14133831.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.266172075271607,
|
|
"epoch": 0.6015485407980941,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000497359000514725,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.1908604919910431,
|
|
"num_tokens": 14147482.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.202458667755127,
|
|
"epoch": 0.6021441334127456,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004973524867202205,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.18654340356588364,
|
|
"num_tokens": 14162276.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.254043626785278,
|
|
"epoch": 0.6027397260273972,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004973459649502939,
|
|
"loss": 5.0707,
|
|
"mean_token_accuracy": 0.18662265837192535,
|
|
"num_tokens": 14177129.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.302168226242065,
|
|
"epoch": 0.6033353186420488,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004973394352051789,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.1908659130334854,
|
|
"num_tokens": 14191104.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.2784045219421385,
|
|
"epoch": 0.6039309112567004,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049733289748511,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.18507454544305801,
|
|
"num_tokens": 14205703.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.178795957565308,
|
|
"epoch": 0.604526503871352,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004973263517903213,
|
|
"loss": 4.9013,
|
|
"mean_token_accuracy": 0.20626239776611327,
|
|
"num_tokens": 14219108.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.303779602050781,
|
|
"epoch": 0.6051220964860036,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973197981210481,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.1848259225487709,
|
|
"num_tokens": 14231677.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.20259838104248,
|
|
"epoch": 0.6057176891006552,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004973132364775252,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.1981998175382614,
|
|
"num_tokens": 14246844.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.3327240467071535,
|
|
"epoch": 0.6063132817153067,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973066668599879,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.18779212683439256,
|
|
"num_tokens": 14261879.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.359662628173828,
|
|
"epoch": 0.6069088743299583,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004973000892686719,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.18234526216983796,
|
|
"num_tokens": 14276884.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.198430299758911,
|
|
"epoch": 0.6075044669446099,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004972935037038131,
|
|
"loss": 5.0431,
|
|
"mean_token_accuracy": 0.19098564088344575,
|
|
"num_tokens": 14291997.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.271669673919678,
|
|
"epoch": 0.6081000595592615,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972869101656478,
|
|
"loss": 4.9896,
|
|
"mean_token_accuracy": 0.196336230635643,
|
|
"num_tokens": 14304407.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.282280206680298,
|
|
"epoch": 0.6086956521739131,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004972803086544125,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.18773432523012162,
|
|
"num_tokens": 14317948.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.276966619491577,
|
|
"epoch": 0.6092912447885647,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004972736991703439,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.19231303483247758,
|
|
"num_tokens": 14330100.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.209065723419189,
|
|
"epoch": 0.6098868374032163,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004972670817136791,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.18684857785701753,
|
|
"num_tokens": 14343655.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.263560581207275,
|
|
"epoch": 0.6104824300178677,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004972604562846554,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.19189692735671998,
|
|
"num_tokens": 14357049.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.28076548576355,
|
|
"epoch": 0.6110780226325193,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972538228835106,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.18721731901168823,
|
|
"num_tokens": 14371184.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.362889242172241,
|
|
"epoch": 0.6116736152471709,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004972471815104825,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.18689340800046922,
|
|
"num_tokens": 14385076.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.282217979431152,
|
|
"epoch": 0.6122692078618225,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004972405321658094,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.18430265486240388,
|
|
"num_tokens": 14400071.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.31106653213501,
|
|
"epoch": 0.6128648004764741,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004972338748497297,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.18941776901483537,
|
|
"num_tokens": 14414203.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.3473796367645265,
|
|
"epoch": 0.6134603930911257,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004972272095624822,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.1794777810573578,
|
|
"num_tokens": 14429325.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.255878448486328,
|
|
"epoch": 0.6140559857057772,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000497220536304306,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.1894165277481079,
|
|
"num_tokens": 14443432.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.315220737457276,
|
|
"epoch": 0.6146515783204288,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004972138550754405,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.1881655976176262,
|
|
"num_tokens": 14457251.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.270356750488281,
|
|
"epoch": 0.6152471709350804,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972071658761254,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.19277913123369217,
|
|
"num_tokens": 14472931.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.328121185302734,
|
|
"epoch": 0.615842763549732,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972004687066005,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.19259994029998778,
|
|
"num_tokens": 14484689.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.2825531482696535,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004971937635671061,
|
|
"loss": 5.0429,
|
|
"mean_token_accuracy": 0.18971439301967621,
|
|
"num_tokens": 14499522.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.271452188491821,
|
|
"epoch": 0.6170339487790352,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971870504578825,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.1883655458688736,
|
|
"num_tokens": 14513347.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.217121171951294,
|
|
"epoch": 0.6176295413936868,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004971803293791708,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.18621584326028823,
|
|
"num_tokens": 14526741.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.162420463562012,
|
|
"epoch": 0.6182251340083383,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971736003312119,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.19757253378629686,
|
|
"num_tokens": 14540317.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.235009241104126,
|
|
"epoch": 0.6188207266229899,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004971668633142472,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.19080387204885482,
|
|
"num_tokens": 14553468.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.304305648803711,
|
|
"epoch": 0.6194163192376414,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004971601183285183,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.18930230438709258,
|
|
"num_tokens": 14566294.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.268048572540283,
|
|
"epoch": 0.620011911852293,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004971533653742672,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.19278932809829713,
|
|
"num_tokens": 14581603.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.226327657699585,
|
|
"epoch": 0.6206075044669446,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000497146604451736,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.19570356160402297,
|
|
"num_tokens": 14596957.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.209311532974243,
|
|
"epoch": 0.6212030970815962,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004971398355611674,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.19735753238201142,
|
|
"num_tokens": 14609228.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.258736610412598,
|
|
"epoch": 0.6217986896962477,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497133058702804,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.18860846906900405,
|
|
"num_tokens": 14621928.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.260164213180542,
|
|
"epoch": 0.6223942823108993,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497126273876889,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.19348251074552536,
|
|
"num_tokens": 14634896.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.267403078079224,
|
|
"epoch": 0.6229898749255509,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004971194810836657,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.18580241054296492,
|
|
"num_tokens": 14648867.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.320101690292359,
|
|
"epoch": 0.6235854675402025,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004971126803233778,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.17945374846458434,
|
|
"num_tokens": 14664360.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.247040796279907,
|
|
"epoch": 0.6241810601548541,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004971058715962691,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.18712168633937837,
|
|
"num_tokens": 14678173.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.295566701889038,
|
|
"epoch": 0.6247766527695057,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000497099054902584,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.1858678475022316,
|
|
"num_tokens": 14690710.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.242764663696289,
|
|
"epoch": 0.6253722453841573,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004970922302425669,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.1859528675675392,
|
|
"num_tokens": 14705678.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.2264985084533695,
|
|
"epoch": 0.6259678379988088,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004970853976164624,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.19399054795503617,
|
|
"num_tokens": 14719357.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.255155181884765,
|
|
"epoch": 0.6265634306134604,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000497078557024516,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.1903844103217125,
|
|
"num_tokens": 14732176.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.264030456542969,
|
|
"epoch": 0.627159023228112,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970717084669728,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.19436786621809005,
|
|
"num_tokens": 14746789.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.230049324035645,
|
|
"epoch": 0.6277546158427636,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970648519440785,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.18883288502693177,
|
|
"num_tokens": 14759233.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.287742280960083,
|
|
"epoch": 0.6283502084574152,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004970579874560789,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.18382622599601744,
|
|
"num_tokens": 14773187.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.381859397888183,
|
|
"epoch": 0.6289458010720667,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004970511150032205,
|
|
"loss": 5.1357,
|
|
"mean_token_accuracy": 0.1838845729827881,
|
|
"num_tokens": 14788501.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.209787178039551,
|
|
"epoch": 0.6295413936867182,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004970442345857495,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.18424489200115204,
|
|
"num_tokens": 14802945.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.359104967117309,
|
|
"epoch": 0.6301369863013698,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004970373462039128,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.1816278278827667,
|
|
"num_tokens": 14818572.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.356029891967774,
|
|
"epoch": 0.6307325789160214,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004970304498579576,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.1861602783203125,
|
|
"num_tokens": 14832962.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.2350891590118405,
|
|
"epoch": 0.631328171530673,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004970235455481312,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.19681889265775682,
|
|
"num_tokens": 14846181.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.208218765258789,
|
|
"epoch": 0.6319237641453246,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004970166332746811,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.19732060432434081,
|
|
"num_tokens": 14858859.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.226653528213501,
|
|
"epoch": 0.6325193567599762,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004970097130378554,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.19484451711177825,
|
|
"num_tokens": 14873858.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.239650583267212,
|
|
"epoch": 0.6331149493746278,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004970027848379023,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.1990181490778923,
|
|
"num_tokens": 14888287.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.221383476257325,
|
|
"epoch": 0.6337105419892793,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004969958486750702,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.1946862056851387,
|
|
"num_tokens": 14903261.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.241174030303955,
|
|
"epoch": 0.6343061346039309,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000496988904549608,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.19759255945682525,
|
|
"num_tokens": 14917788.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.301777267456055,
|
|
"epoch": 0.6349017272185825,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969819524617647,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.18964486867189406,
|
|
"num_tokens": 14930975.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.319721746444702,
|
|
"epoch": 0.6354973198332341,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004969749924117896,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.187764573097229,
|
|
"num_tokens": 14945904.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.223715496063233,
|
|
"epoch": 0.6360929124478857,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004969680243999325,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.19319533705711364,
|
|
"num_tokens": 14960885.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.194136905670166,
|
|
"epoch": 0.6366885050625373,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969610484264433,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.19384798556566238,
|
|
"num_tokens": 14973061.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.282986307144165,
|
|
"epoch": 0.6372840976771889,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969540644915721,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.19514816850423813,
|
|
"num_tokens": 14985921.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.329117298126221,
|
|
"epoch": 0.6378796902918403,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969470725955695,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.1879531517624855,
|
|
"num_tokens": 15000008.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.255239820480346,
|
|
"epoch": 0.6384752829064919,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004969400727386864,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.18171454668045045,
|
|
"num_tokens": 15014175.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.254637622833252,
|
|
"epoch": 0.6390708755211435,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004969330649211737,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.18522126078605652,
|
|
"num_tokens": 15027872.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.387550020217896,
|
|
"epoch": 0.6396664681357951,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969260491432826,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.18494511097669603,
|
|
"num_tokens": 15041295.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.241433763504029,
|
|
"epoch": 0.6402620607504467,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004969190254052651,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.19218669533729554,
|
|
"num_tokens": 15055756.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.262500762939453,
|
|
"epoch": 0.6408576533650983,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004969119937073731,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.1927003115415573,
|
|
"num_tokens": 15070375.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.198754072189331,
|
|
"epoch": 0.6414532459797498,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004969049540498585,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.1988879844546318,
|
|
"num_tokens": 15084580.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.1839128017425535,
|
|
"epoch": 0.6420488385944014,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004968979064329741,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.18755934834480287,
|
|
"num_tokens": 15097137.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.241489410400391,
|
|
"epoch": 0.642644431209053,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004968908508569725,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.19350459575653076,
|
|
"num_tokens": 15112375.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.301629686355591,
|
|
"epoch": 0.6432400238237046,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968837873221069,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.1879799708724022,
|
|
"num_tokens": 15126356.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.301209449768066,
|
|
"epoch": 0.6438356164383562,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004968767158286306,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.18719206899404525,
|
|
"num_tokens": 15140626.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.290619802474976,
|
|
"epoch": 0.6444312090530078,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968696363767972,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.1827332302927971,
|
|
"num_tokens": 15155131.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.278539085388184,
|
|
"epoch": 0.6450268016676594,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004968625489668607,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.18880775570869446,
|
|
"num_tokens": 15170488.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.278753137588501,
|
|
"epoch": 0.6456223942823109,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004968554535990754,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.1999405801296234,
|
|
"num_tokens": 15182905.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.286464738845825,
|
|
"epoch": 0.6462179868969625,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004968483502736956,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.1871281534433365,
|
|
"num_tokens": 15196341.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.256410455703735,
|
|
"epoch": 0.646813579511614,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004968412389909762,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.1897108554840088,
|
|
"num_tokens": 15208973.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.273350620269776,
|
|
"epoch": 0.6474091721262656,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004968341197511722,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.18364183604717255,
|
|
"num_tokens": 15225122.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.305637407302856,
|
|
"epoch": 0.6480047647409172,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004968269925545391,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.18446778506040573,
|
|
"num_tokens": 15236932.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.243228816986084,
|
|
"epoch": 0.6486003573555688,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968198574013323,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.19088656306266785,
|
|
"num_tokens": 15249060.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.220152759552002,
|
|
"epoch": 0.6491959499702203,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004968127142918081,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.19013717621564866,
|
|
"num_tokens": 15263544.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.2159802436828615,
|
|
"epoch": 0.6497915425848719,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004968055632262223,
|
|
"loss": 4.9349,
|
|
"mean_token_accuracy": 0.1959513857960701,
|
|
"num_tokens": 15276294.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.268005228042602,
|
|
"epoch": 0.6503871351995235,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004967984042048317,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.19301596134901047,
|
|
"num_tokens": 15290352.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.272830152511597,
|
|
"epoch": 0.6509827278141751,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004967912372278928,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.18969148695468901,
|
|
"num_tokens": 15304607.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.282205295562744,
|
|
"epoch": 0.6515783204288267,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000496784062295663,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.18474604338407516,
|
|
"num_tokens": 15319846.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.286567640304566,
|
|
"epoch": 0.6521739130434783,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004967768794083994,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.1871288999915123,
|
|
"num_tokens": 15335668.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.233797836303711,
|
|
"epoch": 0.6527695056581299,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004967696885663597,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.18956888616085052,
|
|
"num_tokens": 15350839.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.212251806259156,
|
|
"epoch": 0.6533650982727814,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000496762489769802,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.19383188039064408,
|
|
"num_tokens": 15364289.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.188838911056519,
|
|
"epoch": 0.653960690887433,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967552830189842,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.19442096650600432,
|
|
"num_tokens": 15378042.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.3160505294799805,
|
|
"epoch": 0.6545562835020846,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967480683141651,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.18779717683792113,
|
|
"num_tokens": 15392128.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.297846412658691,
|
|
"epoch": 0.6551518761167362,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496740845655603,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.17973996996879577,
|
|
"num_tokens": 15406723.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.250408697128296,
|
|
"epoch": 0.6557474687313878,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004967336150435576,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.19129544496536255,
|
|
"num_tokens": 15421036.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.212464332580566,
|
|
"epoch": 0.6563430613460393,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967263764782878,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.18914392292499543,
|
|
"num_tokens": 15434486.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.3145856857299805,
|
|
"epoch": 0.6569386539606908,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967191299600535,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.18856205195188522,
|
|
"num_tokens": 15449378.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.328000545501709,
|
|
"epoch": 0.6575342465753424,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004967118754891144,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.19267208278179168,
|
|
"num_tokens": 15463983.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.267809057235718,
|
|
"epoch": 0.658129839189994,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004967046130657309,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.18885381668806075,
|
|
"num_tokens": 15478397.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.207084703445434,
|
|
"epoch": 0.6587254318046456,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004966973426901634,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.18576074242591858,
|
|
"num_tokens": 15491511.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.226274490356445,
|
|
"epoch": 0.6593210244192972,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966900643626726,
|
|
"loss": 4.944,
|
|
"mean_token_accuracy": 0.196894171833992,
|
|
"num_tokens": 15505103.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.279523324966431,
|
|
"epoch": 0.6599166170339488,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004966827780835197,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.18975903391838073,
|
|
"num_tokens": 15520216.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.181684255599976,
|
|
"epoch": 0.6605122096486004,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004966754838529659,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.19669175446033477,
|
|
"num_tokens": 15532879.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.256427955627442,
|
|
"epoch": 0.6611078022632519,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496668181671273,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.19731294959783555,
|
|
"num_tokens": 15545600.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.25473837852478,
|
|
"epoch": 0.6617033948779035,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004966608715387029,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.18452006131410598,
|
|
"num_tokens": 15560910.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.34370985031128,
|
|
"epoch": 0.6622989874925551,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966535534555175,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.18671540468931197,
|
|
"num_tokens": 15575041.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.218348121643066,
|
|
"epoch": 0.6628945801072067,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004966462274219797,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.19417762756347656,
|
|
"num_tokens": 15588399.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.179234790802002,
|
|
"epoch": 0.6634901727218583,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000496638893438352,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.20641662776470185,
|
|
"num_tokens": 15600010.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.294523906707764,
|
|
"epoch": 0.6640857653365099,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004966315515048977,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.19217442274093627,
|
|
"num_tokens": 15613703.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.306127309799194,
|
|
"epoch": 0.6646813579511615,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004966242016218799,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.18512095063924788,
|
|
"num_tokens": 15628198.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.272443056106567,
|
|
"epoch": 0.6652769505658129,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004966168437895624,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.1836185410618782,
|
|
"num_tokens": 15641410.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.172276830673217,
|
|
"epoch": 0.6658725431804645,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004966094780082089,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.19570461064577102,
|
|
"num_tokens": 15656052.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.242552042007446,
|
|
"epoch": 0.6664681357951161,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966021042780837,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.19634895771741867,
|
|
"num_tokens": 15669319.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.241170120239258,
|
|
"epoch": 0.6670637284097677,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004965947225994516,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.1931735619902611,
|
|
"num_tokens": 15684951.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.249751329421997,
|
|
"epoch": 0.6676593210244193,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004965873329725769,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.18289056718349456,
|
|
"num_tokens": 15699352.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.2152252197265625,
|
|
"epoch": 0.6682549136390709,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004965799353977248,
|
|
"loss": 4.926,
|
|
"mean_token_accuracy": 0.19909475594758988,
|
|
"num_tokens": 15713183.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.280290269851685,
|
|
"epoch": 0.6688505062537224,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965725298751608,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.1881798177957535,
|
|
"num_tokens": 15725985.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.2790521621704105,
|
|
"epoch": 0.669446098868374,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004965651164051504,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.1837506487965584,
|
|
"num_tokens": 15740146.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.226727676391602,
|
|
"epoch": 0.6700416914830256,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004965576949879594,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.19253317266702652,
|
|
"num_tokens": 15753590.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.23234748840332,
|
|
"epoch": 0.6706372840976772,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965502656238543,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.19132742285728455,
|
|
"num_tokens": 15768018.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.226779365539551,
|
|
"epoch": 0.6712328767123288,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004965428283131013,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.1980260655283928,
|
|
"num_tokens": 15783112.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.276091146469116,
|
|
"epoch": 0.6718284693269804,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004965353830559671,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.19180409759283065,
|
|
"num_tokens": 15798730.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.215128469467163,
|
|
"epoch": 0.672424061941632,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004965279298527192,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.1981203407049179,
|
|
"num_tokens": 15812555.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.279513549804688,
|
|
"epoch": 0.6730196545562835,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004965204687036244,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.1966586321592331,
|
|
"num_tokens": 15824512.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.291729688644409,
|
|
"epoch": 0.6736152471709351,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004965129996089507,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.1806118220090866,
|
|
"num_tokens": 15839960.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.303473091125488,
|
|
"epoch": 0.6742108397855867,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004965055225689658,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.18702482879161836,
|
|
"num_tokens": 15854841.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.233872175216675,
|
|
"epoch": 0.6748064324002382,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004964980375839379,
|
|
"loss": 4.9845,
|
|
"mean_token_accuracy": 0.19708098471164703,
|
|
"num_tokens": 15866701.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.184519577026367,
|
|
"epoch": 0.6754020250148898,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004964905446541355,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.19654641300439835,
|
|
"num_tokens": 15880227.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.2238609313964846,
|
|
"epoch": 0.6759976176295414,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004964830437798276,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.18559536933898926,
|
|
"num_tokens": 15894748.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.235979509353638,
|
|
"epoch": 0.6765932102441929,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004964755349612829,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.19552299678325652,
|
|
"num_tokens": 15908103.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.2999091148376465,
|
|
"epoch": 0.6771888028588445,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004964680181987709,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.184394970536232,
|
|
"num_tokens": 15920996.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.267886734008789,
|
|
"epoch": 0.6777843954734961,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000496460493492561,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.18569493293762207,
|
|
"num_tokens": 15934922.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.258800411224366,
|
|
"epoch": 0.6783799880881477,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004964529608429234,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.18828275203704833,
|
|
"num_tokens": 15948903.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.3015834331512455,
|
|
"epoch": 0.6789755807027993,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004964454202501282,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.19011245667934418,
|
|
"num_tokens": 15963610.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.1792679786682125,
|
|
"epoch": 0.6795711733174509,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004964378717144458,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.19334629327058792,
|
|
"num_tokens": 15977247.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.161413908004761,
|
|
"epoch": 0.6801667659321025,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000496430315236147,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.19741306751966475,
|
|
"num_tokens": 15991856.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.220260715484619,
|
|
"epoch": 0.680762358546754,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964227508155027,
|
|
"loss": 5.0029,
|
|
"mean_token_accuracy": 0.19149223119020461,
|
|
"num_tokens": 16006071.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.226979446411133,
|
|
"epoch": 0.6813579511614056,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004964151784527844,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.19196676462888718,
|
|
"num_tokens": 16021164.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.247955989837647,
|
|
"epoch": 0.6819535437760572,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964075981482637,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.19261963814496993,
|
|
"num_tokens": 16035251.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.212866926193238,
|
|
"epoch": 0.6825491363907088,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964000099022124,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.19760527908802034,
|
|
"num_tokens": 16048628.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.167464971542358,
|
|
"epoch": 0.6831447290053604,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004963924137149027,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.20154782235622407,
|
|
"num_tokens": 16061612.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.183085489273071,
|
|
"epoch": 0.6837403216200119,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963848095866072,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.19481744468212128,
|
|
"num_tokens": 16075506.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.267515659332275,
|
|
"epoch": 0.6843359142346634,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004963771975175984,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.1793405681848526,
|
|
"num_tokens": 16090629.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.195936822891236,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004963695775081495,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.1995197892189026,
|
|
"num_tokens": 16105219.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.232565069198609,
|
|
"epoch": 0.6855270994639666,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004963619495585338,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.19518732875585557,
|
|
"num_tokens": 16118851.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.163709545135498,
|
|
"epoch": 0.6861226920786182,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004963543136690247,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.19295049756765364,
|
|
"num_tokens": 16132435.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.180385780334473,
|
|
"epoch": 0.6867182846932698,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004963466698398965,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.19070562422275544,
|
|
"num_tokens": 16145922.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.1947588443756105,
|
|
"epoch": 0.6873138773079214,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004963390180714231,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.19403730183839799,
|
|
"num_tokens": 16158056.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.266003608703613,
|
|
"epoch": 0.687909469922573,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000496331358363879,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.19434632509946823,
|
|
"num_tokens": 16172836.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.289444828033448,
|
|
"epoch": 0.6885050625372245,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004963236907175388,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.17846478372812272,
|
|
"num_tokens": 16187787.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.178939151763916,
|
|
"epoch": 0.6891006551518761,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004963160151326778,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.19745612442493438,
|
|
"num_tokens": 16201861.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.107771635055542,
|
|
"epoch": 0.6896962477665277,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004963083316095712,
|
|
"loss": 4.899,
|
|
"mean_token_accuracy": 0.19720693528652192,
|
|
"num_tokens": 16215447.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.200075244903564,
|
|
"epoch": 0.6902918403811793,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004963006401484945,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.19762418121099473,
|
|
"num_tokens": 16229127.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.27059497833252,
|
|
"epoch": 0.6908874329958309,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004962929407497236,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.19065853357315063,
|
|
"num_tokens": 16242911.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.268238258361817,
|
|
"epoch": 0.6914830256104825,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004962852334135348,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.18754418790340424,
|
|
"num_tokens": 16257430.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.152529907226563,
|
|
"epoch": 0.6920786182251341,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004962775181402044,
|
|
"loss": 4.8955,
|
|
"mean_token_accuracy": 0.20580868124961854,
|
|
"num_tokens": 16270187.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.264871120452881,
|
|
"epoch": 0.6926742108397855,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004962697949300093,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.1892458453774452,
|
|
"num_tokens": 16282750.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.23567419052124,
|
|
"epoch": 0.6932698034544371,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004962620637832263,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.1986319899559021,
|
|
"num_tokens": 16295985.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.2512218952178955,
|
|
"epoch": 0.6938653960690887,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004962543247001329,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.18572293519973754,
|
|
"num_tokens": 16308735.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.283103656768799,
|
|
"epoch": 0.6944609886837403,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004962465776810066,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.19015296548604965,
|
|
"num_tokens": 16322722.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.193598842620849,
|
|
"epoch": 0.6950565812983919,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004962388227261253,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.19867675602436066,
|
|
"num_tokens": 16336075.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.233902025222778,
|
|
"epoch": 0.6956521739130435,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004962310598357672,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.18685352206230163,
|
|
"num_tokens": 16351487.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.236039733886718,
|
|
"epoch": 0.696247766527695,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004962232890102106,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.19590164572000504,
|
|
"num_tokens": 16365518.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.179704761505127,
|
|
"epoch": 0.6968433591423466,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004962155102497342,
|
|
"loss": 5.0151,
|
|
"mean_token_accuracy": 0.19118821620941162,
|
|
"num_tokens": 16379665.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.320987176895142,
|
|
"epoch": 0.6974389517569982,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004962077235546173,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.19109077006578445,
|
|
"num_tokens": 16394540.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.212607383728027,
|
|
"epoch": 0.6980345443716498,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004961999289251389,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.19521069079637526,
|
|
"num_tokens": 16406628.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.176800537109375,
|
|
"epoch": 0.6986301369863014,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004961921263615788,
|
|
"loss": 4.9583,
|
|
"mean_token_accuracy": 0.20125830173492432,
|
|
"num_tokens": 16417516.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.163766956329345,
|
|
"epoch": 0.699225729600953,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004961843158642167,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.1979386940598488,
|
|
"num_tokens": 16431899.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.253143787384033,
|
|
"epoch": 0.6998213222156046,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004961764974333328,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.18762757033109664,
|
|
"num_tokens": 16444716.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.212019252777099,
|
|
"epoch": 0.7004169148302561,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004961686710692076,
|
|
"loss": 4.9366,
|
|
"mean_token_accuracy": 0.19871095716953277,
|
|
"num_tokens": 16459544.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.243808889389038,
|
|
"epoch": 0.7010125074449077,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004961608367721217,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.19384327679872512,
|
|
"num_tokens": 16472537.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.137933206558228,
|
|
"epoch": 0.7016081000595593,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004961529945423563,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.197707898914814,
|
|
"num_tokens": 16486184.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.1593376159667965,
|
|
"epoch": 0.7022036926742108,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004961451443801924,
|
|
"loss": 4.9758,
|
|
"mean_token_accuracy": 0.19458836913108826,
|
|
"num_tokens": 16499584.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.176172208786011,
|
|
"epoch": 0.7027992852888624,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004961372862859119,
|
|
"loss": 4.9443,
|
|
"mean_token_accuracy": 0.19392507076263427,
|
|
"num_tokens": 16512701.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.312985277175903,
|
|
"epoch": 0.703394877903514,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004961294202597962,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.1849490761756897,
|
|
"num_tokens": 16525019.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.249667024612426,
|
|
"epoch": 0.7039904705181655,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004961215463021281,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.19512701481580735,
|
|
"num_tokens": 16539335.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.178429412841797,
|
|
"epoch": 0.7045860631328171,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004961136644131894,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.19686115980148317,
|
|
"num_tokens": 16552680.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.136629962921143,
|
|
"epoch": 0.7051816557474687,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004961057745932633,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.20011175274848939,
|
|
"num_tokens": 16565819.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.221772193908691,
|
|
"epoch": 0.7057772483621203,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004960978768426323,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.1973884806036949,
|
|
"num_tokens": 16579280.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.210810708999634,
|
|
"epoch": 0.7063728409767719,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049608997116158,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.18434540331363677,
|
|
"num_tokens": 16594090.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.25242509841919,
|
|
"epoch": 0.7069684335914235,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00049608205755039,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.1942136138677597,
|
|
"num_tokens": 16609287.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.238081264495849,
|
|
"epoch": 0.7075640262060751,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004960741360093459,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.18787476569414138,
|
|
"num_tokens": 16624873.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.188109016418457,
|
|
"epoch": 0.7081596188207266,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004960662065387322,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.19419119507074356,
|
|
"num_tokens": 16637885.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.2546460151672365,
|
|
"epoch": 0.7087552114353782,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000496058269138833,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.1934243619441986,
|
|
"num_tokens": 16650961.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.224667358398437,
|
|
"epoch": 0.7093508040500298,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004960503238099331,
|
|
"loss": 5.0464,
|
|
"mean_token_accuracy": 0.19252557456493377,
|
|
"num_tokens": 16665740.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.275289678573609,
|
|
"epoch": 0.7099463966646814,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004960423705523175,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.18924264907836913,
|
|
"num_tokens": 16679143.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.236150217056275,
|
|
"epoch": 0.710541989279333,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004960344093662714,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.1954708531498909,
|
|
"num_tokens": 16692460.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.209852266311645,
|
|
"epoch": 0.7111375818939845,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004960264402520804,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.20065396577119826,
|
|
"num_tokens": 16707037.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.26790418624878,
|
|
"epoch": 0.711733174508636,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004960184632100304,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.19775129109621048,
|
|
"num_tokens": 16719857.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.2152056217193605,
|
|
"epoch": 0.7123287671232876,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004960104782404075,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.19611058980226517,
|
|
"num_tokens": 16732221.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.245729064941406,
|
|
"epoch": 0.7129243597379392,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960024853434982,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.1929053083062172,
|
|
"num_tokens": 16747384.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.2037725925445555,
|
|
"epoch": 0.7135199523525908,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000495994484519589,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.18775837868452072,
|
|
"num_tokens": 16761269.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.186244869232178,
|
|
"epoch": 0.7141155449672424,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004959864757689669,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.19541864544153215,
|
|
"num_tokens": 16775403.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.246415662765503,
|
|
"epoch": 0.714711137581894,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004959784590919192,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.19306568205356597,
|
|
"num_tokens": 16790740.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.714711137581894,
|
|
"eval_entropy": 4.940415644421472,
|
|
"eval_loss": 4.973916053771973,
|
|
"eval_mean_token_accuracy": 0.20525089036264577,
|
|
"eval_num_tokens": 16790740.0,
|
|
"eval_runtime": 18.485,
|
|
"eval_samples_per_second": 1380.201,
|
|
"eval_steps_per_second": 172.573,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.167508745193482,
|
|
"epoch": 0.7153067301965456,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004959704344887335,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.19130657762289047,
|
|
"num_tokens": 16805005.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.2230690002441404,
|
|
"epoch": 0.7159023228111971,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004959624019596976,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.19440141916275025,
|
|
"num_tokens": 16818227.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.2072625160217285,
|
|
"epoch": 0.7164979154258487,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004959543615050996,
|
|
"loss": 5.0052,
|
|
"mean_token_accuracy": 0.19660791456699372,
|
|
"num_tokens": 16831113.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.222737121582031,
|
|
"epoch": 0.7170935080405003,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004959463131252278,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.19122221916913987,
|
|
"num_tokens": 16844952.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.319234418869018,
|
|
"epoch": 0.7176891006551519,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004959382568203711,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.19028442800045015,
|
|
"num_tokens": 16858360.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.156467723846435,
|
|
"epoch": 0.7182846932698035,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004959301925908184,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.19866423755884172,
|
|
"num_tokens": 16869172.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.146221256256103,
|
|
"epoch": 0.7188802858844551,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004959221204368588,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.18832390159368514,
|
|
"num_tokens": 16884322.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.327645969390869,
|
|
"epoch": 0.7194758784991067,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004959140403587819,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.19371753484010695,
|
|
"num_tokens": 16896686.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.241466474533081,
|
|
"epoch": 0.7200714711137582,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004959059523568778,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.19565755724906922,
|
|
"num_tokens": 16912819.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.226687002182007,
|
|
"epoch": 0.7206670637284097,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004958978564314361,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.19182371646165847,
|
|
"num_tokens": 16926615.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.21510157585144,
|
|
"epoch": 0.7212626563430613,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004958897525827476,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.1957946538925171,
|
|
"num_tokens": 16940934.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.181780385971069,
|
|
"epoch": 0.7218582489577129,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004958816408111027,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.20601600557565689,
|
|
"num_tokens": 16953016.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.133279275894165,
|
|
"epoch": 0.7224538415723645,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004958735211167926,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.19957727789878846,
|
|
"num_tokens": 16964460.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.238236999511718,
|
|
"epoch": 0.7230494341870161,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004958653935001083,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.18826861530542374,
|
|
"num_tokens": 16978307.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.2710285663604735,
|
|
"epoch": 0.7236450268016676,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004958572579613415,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.19542692601680756,
|
|
"num_tokens": 16992240.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.119581508636474,
|
|
"epoch": 0.7242406194163192,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000495849114500784,
|
|
"loss": 4.876,
|
|
"mean_token_accuracy": 0.20546600967645645,
|
|
"num_tokens": 17004865.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.197304153442383,
|
|
"epoch": 0.7248362120309708,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004958409631187278,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.2029432773590088,
|
|
"num_tokens": 17018377.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.140698337554932,
|
|
"epoch": 0.7254318046456224,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004958328038154652,
|
|
"loss": 4.8872,
|
|
"mean_token_accuracy": 0.20156844854354858,
|
|
"num_tokens": 17032487.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.230426263809204,
|
|
"epoch": 0.726027397260274,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004958246365912891,
|
|
"loss": 5.0276,
|
|
"mean_token_accuracy": 0.1968516767024994,
|
|
"num_tokens": 17045783.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.319394302368164,
|
|
"epoch": 0.7266229898749256,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004958164614464923,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.18237221390008926,
|
|
"num_tokens": 17060359.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.249917078018188,
|
|
"epoch": 0.7272185824895772,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.19599988013505937,
|
|
"num_tokens": 17074510.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.194752550125122,
|
|
"epoch": 0.7278141751042287,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004958000873962099,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.19430559277534484,
|
|
"num_tokens": 17088551.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.273688650131225,
|
|
"epoch": 0.7284097677188803,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004957918884913115,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.18327474147081374,
|
|
"num_tokens": 17102674.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.269916009902954,
|
|
"epoch": 0.7290053603335319,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004957836816669672,
|
|
"loss": 5.028,
|
|
"mean_token_accuracy": 0.19103916585445405,
|
|
"num_tokens": 17116891.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.239763402938843,
|
|
"epoch": 0.7296009529481834,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957754669234711,
|
|
"loss": 4.9638,
|
|
"mean_token_accuracy": 0.1953309416770935,
|
|
"num_tokens": 17129003.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.147449970245361,
|
|
"epoch": 0.730196545562835,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000495767244261118,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.20167790800333024,
|
|
"num_tokens": 17142225.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.194434452056885,
|
|
"epoch": 0.7307921381774866,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004957590136802028,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.19738942682743071,
|
|
"num_tokens": 17154849.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.200641679763794,
|
|
"epoch": 0.7313877307921381,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004957507751810207,
|
|
"loss": 4.9321,
|
|
"mean_token_accuracy": 0.198508320748806,
|
|
"num_tokens": 17170335.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.207217502593994,
|
|
"epoch": 0.7319833234067897,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004957425287638673,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.18515270054340363,
|
|
"num_tokens": 17185181.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.3468546867370605,
|
|
"epoch": 0.7325789160214413,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957342744290381,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.19273507297039033,
|
|
"num_tokens": 17198960.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.281911706924438,
|
|
"epoch": 0.7331745086360929,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004957260121768296,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.19284442514181138,
|
|
"num_tokens": 17212233.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.224344778060913,
|
|
"epoch": 0.7337701012507445,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004957177420075377,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.1968523681163788,
|
|
"num_tokens": 17224012.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.156566476821899,
|
|
"epoch": 0.7343656938653961,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004957094639214594,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.18235350102186204,
|
|
"num_tokens": 17236943.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.294571208953857,
|
|
"epoch": 0.7349612864800477,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004957011779188915,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.1878274843096733,
|
|
"num_tokens": 17249835.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.307394123077392,
|
|
"epoch": 0.7355568790946992,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004956928840001312,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.1867114022374153,
|
|
"num_tokens": 17263260.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.286664295196533,
|
|
"epoch": 0.7361524717093508,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004956845821654758,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.191137632727623,
|
|
"num_tokens": 17277309.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.2535703659057615,
|
|
"epoch": 0.7367480643240024,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004956762724152234,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.19457209706306458,
|
|
"num_tokens": 17291354.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.196777582168579,
|
|
"epoch": 0.737343656938654,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004956679547496719,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.19505695700645448,
|
|
"num_tokens": 17305805.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.188502502441406,
|
|
"epoch": 0.7379392495533056,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004956596291691197,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.1996886521577835,
|
|
"num_tokens": 17319031.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.253202962875366,
|
|
"epoch": 0.7385348421679571,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004956512956738652,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.19299153238534927,
|
|
"num_tokens": 17332455.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.201680278778076,
|
|
"epoch": 0.7391304347826086,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004956429542642075,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.19257753044366838,
|
|
"num_tokens": 17346849.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.201982736587524,
|
|
"epoch": 0.7397260273972602,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004956346049404459,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.19815541952848434,
|
|
"num_tokens": 17360204.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.252338075637818,
|
|
"epoch": 0.7403216200119118,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004956262477028797,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.1929316520690918,
|
|
"num_tokens": 17373430.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.250050973892212,
|
|
"epoch": 0.7409172126265634,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956178825518087,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.20340880751609802,
|
|
"num_tokens": 17386856.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.134352445602417,
|
|
"epoch": 0.741512805241215,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956095094875329,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.19527941346168518,
|
|
"num_tokens": 17401657.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.200413608551026,
|
|
"epoch": 0.7421083978558666,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004956011285103528,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.1915552094578743,
|
|
"num_tokens": 17415688.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.262109613418579,
|
|
"epoch": 0.7427039904705182,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004955927396205689,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.19540394842624664,
|
|
"num_tokens": 17428272.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.196072340011597,
|
|
"epoch": 0.7432995830851697,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000495584342818482,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.20016586035490036,
|
|
"num_tokens": 17440858.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.303284072875977,
|
|
"epoch": 0.7438951756998213,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004955759381043934,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.19344063401222228,
|
|
"num_tokens": 17453946.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.239511585235595,
|
|
"epoch": 0.7444907683144729,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004955675254786045,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.19466943591833114,
|
|
"num_tokens": 17470565.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.216199779510498,
|
|
"epoch": 0.7450863609291245,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004955591049414171,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.19631701111793518,
|
|
"num_tokens": 17484604.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.253848361968994,
|
|
"epoch": 0.7456819535437761,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004955506764931332,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.18659911006689073,
|
|
"num_tokens": 17500578.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.213921022415161,
|
|
"epoch": 0.7462775461584277,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004955422401340553,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.18858876675367356,
|
|
"num_tokens": 17516999.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.213530778884888,
|
|
"epoch": 0.7468731387730793,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004955337958644857,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.197228866815567,
|
|
"num_tokens": 17530943.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.161210584640503,
|
|
"epoch": 0.7474687313877308,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004955253436847273,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.20546384155750275,
|
|
"num_tokens": 17543698.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.083687829971313,
|
|
"epoch": 0.7480643240023823,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004955168835950835,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.20950689911842346,
|
|
"num_tokens": 17556141.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.159177207946778,
|
|
"epoch": 0.7486599166170339,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004955084155958576,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.2055245339870453,
|
|
"num_tokens": 17569186.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.256765460968017,
|
|
"epoch": 0.7492555092316855,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004954999396873534,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.1869715377688408,
|
|
"num_tokens": 17583826.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.237720346450805,
|
|
"epoch": 0.7498511018463371,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004954914558698748,
|
|
"loss": 4.9657,
|
|
"mean_token_accuracy": 0.1989605247974396,
|
|
"num_tokens": 17597196.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.2814994812011715,
|
|
"epoch": 0.7504466944609887,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004954829641437261,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.18891747742891313,
|
|
"num_tokens": 17611283.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.233958625793457,
|
|
"epoch": 0.7510422870756402,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004954744645092121,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.2020708292722702,
|
|
"num_tokens": 17626089.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.246726369857788,
|
|
"epoch": 0.7516378796902918,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004954659569666375,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.19530968517065048,
|
|
"num_tokens": 17639915.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.290156126022339,
|
|
"epoch": 0.7522334723049434,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004954574415163075,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.19318126738071442,
|
|
"num_tokens": 17654563.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.20617184638977,
|
|
"epoch": 0.752829064919595,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004954489181585275,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.19626425206661224,
|
|
"num_tokens": 17669132.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.152454423904419,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004954403868936032,
|
|
"loss": 4.9239,
|
|
"mean_token_accuracy": 0.19740720838308334,
|
|
"num_tokens": 17682794.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.257226037979126,
|
|
"epoch": 0.7540202501488982,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004954318477218406,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.19156909883022308,
|
|
"num_tokens": 17697325.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.236366128921508,
|
|
"epoch": 0.7546158427635498,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000495423300643546,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.1868755355477333,
|
|
"num_tokens": 17710136.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.195476627349853,
|
|
"epoch": 0.7552114353782013,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004954147456590262,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.19309208840131759,
|
|
"num_tokens": 17723138.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.187572574615478,
|
|
"epoch": 0.7558070279928529,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004954061827685877,
|
|
"loss": 4.944,
|
|
"mean_token_accuracy": 0.20160356014966965,
|
|
"num_tokens": 17735059.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.170554351806641,
|
|
"epoch": 0.7564026206075045,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004953976119725378,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.1945444792509079,
|
|
"num_tokens": 17750361.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.207920932769776,
|
|
"epoch": 0.756998213222156,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004953890332711839,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.1910410165786743,
|
|
"num_tokens": 17766597.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.318069314956665,
|
|
"epoch": 0.7575938058368076,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004953804466648337,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.18902000337839125,
|
|
"num_tokens": 17780086.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.173790454864502,
|
|
"epoch": 0.7581893984514592,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953718521537952,
|
|
"loss": 4.9289,
|
|
"mean_token_accuracy": 0.20532690435647966,
|
|
"num_tokens": 17793316.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.229732656478882,
|
|
"epoch": 0.7587849910661107,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953632497383766,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.18840504437685013,
|
|
"num_tokens": 17807766.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.1557056427001955,
|
|
"epoch": 0.7593805836807623,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004953546394188867,
|
|
"loss": 4.9352,
|
|
"mean_token_accuracy": 0.2043674260377884,
|
|
"num_tokens": 17819778.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.247732162475586,
|
|
"epoch": 0.7599761762954139,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000495346021195634,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.19394806325435637,
|
|
"num_tokens": 17835432.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.2031028270721436,
|
|
"epoch": 0.7605717689100655,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004953373950689279,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.20307695865631104,
|
|
"num_tokens": 17848861.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.216523170471191,
|
|
"epoch": 0.7611673615247171,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004953287610390775,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.19733566790819168,
|
|
"num_tokens": 17863173.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.1563797950744625,
|
|
"epoch": 0.7617629541393687,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953201191063928,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.19484409391880037,
|
|
"num_tokens": 17876497.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.217193984985352,
|
|
"epoch": 0.7623585467540203,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004953114692711837,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.20320072323083876,
|
|
"num_tokens": 17890582.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.216400480270385,
|
|
"epoch": 0.7629541393686718,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004953028115337603,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.19127855598926544,
|
|
"num_tokens": 17905476.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.193920135498047,
|
|
"epoch": 0.7635497319833234,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952941458944333,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.19307632446289064,
|
|
"num_tokens": 17918571.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.193931722640992,
|
|
"epoch": 0.764145324597975,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004952854723535134,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.1926618680357933,
|
|
"num_tokens": 17932169.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.189862442016602,
|
|
"epoch": 0.7647409172126266,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004952767909113118,
|
|
"loss": 4.9169,
|
|
"mean_token_accuracy": 0.21033641397953035,
|
|
"num_tokens": 17944772.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.160337686538696,
|
|
"epoch": 0.7653365098272782,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004952681015681398,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.2048033967614174,
|
|
"num_tokens": 17957903.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.218353605270385,
|
|
"epoch": 0.7659321024419298,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952594043243092,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.19353794753551484,
|
|
"num_tokens": 17972214.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.1584851264953615,
|
|
"epoch": 0.7665276950565812,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952506991801319,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.20294411033391951,
|
|
"num_tokens": 17986722.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.217153263092041,
|
|
"epoch": 0.7671232876712328,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004952419861359201,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.2062564119696617,
|
|
"num_tokens": 17999392.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.216296863555908,
|
|
"epoch": 0.7677188802858844,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004952332651919864,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.19546557664871217,
|
|
"num_tokens": 18013560.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.3441825866699215,
|
|
"epoch": 0.768314472900536,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952245363486435,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.18818190693855286,
|
|
"num_tokens": 18027631.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.164026117324829,
|
|
"epoch": 0.7689100655151876,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004952157996062046,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.19969597905874253,
|
|
"num_tokens": 18041618.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.225600719451904,
|
|
"epoch": 0.7695056581298392,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000495207054964983,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.19665047377347947,
|
|
"num_tokens": 18053783.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.21432056427002,
|
|
"epoch": 0.7701012507444908,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004951983024252924,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.1900701865553856,
|
|
"num_tokens": 18067471.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.218812561035156,
|
|
"epoch": 0.7706968433591423,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004951895419874466,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.19593874216079712,
|
|
"num_tokens": 18081173.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.306157350540161,
|
|
"epoch": 0.7712924359737939,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00049518077365176,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.18314757496118544,
|
|
"num_tokens": 18094237.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.184618949890137,
|
|
"epoch": 0.7718880285884455,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000495171997418547,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.20103740841150283,
|
|
"num_tokens": 18109184.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.18105731010437,
|
|
"epoch": 0.7724836212030971,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004951632132881225,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.19993216097354888,
|
|
"num_tokens": 18122801.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.212755727767944,
|
|
"epoch": 0.7730792138177487,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004951544212608015,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.1965155303478241,
|
|
"num_tokens": 18135807.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.190378475189209,
|
|
"epoch": 0.7736748064324003,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004951456213368994,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.19493371546268462,
|
|
"num_tokens": 18149093.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.3449249267578125,
|
|
"epoch": 0.7742703990470519,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004951368135167316,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.18750405460596084,
|
|
"num_tokens": 18162878.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.207848739624024,
|
|
"epoch": 0.7748659916617034,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004951279978006143,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.19590355157852174,
|
|
"num_tokens": 18176443.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.141319322586059,
|
|
"epoch": 0.7754615842763549,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004951191741888638,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.19382061958312988,
|
|
"num_tokens": 18194684.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.157397365570068,
|
|
"epoch": 0.7760571768910065,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004951103426817961,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.20886114239692688,
|
|
"num_tokens": 18207667.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.189918851852417,
|
|
"epoch": 0.7766527695056581,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004951015032797286,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.19991605132818221,
|
|
"num_tokens": 18220594.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.157913017272949,
|
|
"epoch": 0.7772483621203097,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004950926559829778,
|
|
"loss": 4.9486,
|
|
"mean_token_accuracy": 0.19604713320732117,
|
|
"num_tokens": 18235193.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.218387031555176,
|
|
"epoch": 0.7778439547349613,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004950838007918615,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.20040399730205535,
|
|
"num_tokens": 18246647.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.170574522018432,
|
|
"epoch": 0.7784395473496128,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000495074937706697,
|
|
"loss": 4.9781,
|
|
"mean_token_accuracy": 0.1947624132037163,
|
|
"num_tokens": 18260255.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.189462900161743,
|
|
"epoch": 0.7790351399642644,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004950660667278023,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.20121008902788162,
|
|
"num_tokens": 18274505.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.19947304725647,
|
|
"epoch": 0.779630732578916,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004950571878554956,
|
|
"loss": 4.9635,
|
|
"mean_token_accuracy": 0.20336953103542327,
|
|
"num_tokens": 18288386.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.275217294692993,
|
|
"epoch": 0.7802263251935676,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004950483010900953,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.19346607029438018,
|
|
"num_tokens": 18303602.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.177950000762939,
|
|
"epoch": 0.7808219178082192,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004950394064319203,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.19990218579769134,
|
|
"num_tokens": 18318561.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.196379232406616,
|
|
"epoch": 0.7814175104228708,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004950305038812895,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.20022922158241271,
|
|
"num_tokens": 18331903.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.117612838745117,
|
|
"epoch": 0.7820131030375224,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004950215934385223,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.2092200994491577,
|
|
"num_tokens": 18344958.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.244729280471802,
|
|
"epoch": 0.782608695652174,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004950126751039382,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.1904166355729103,
|
|
"num_tokens": 18359343.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.185728216171265,
|
|
"epoch": 0.7832042882668255,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004950037488778572,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.19252391457557677,
|
|
"num_tokens": 18372672.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.2596580505371096,
|
|
"epoch": 0.7837998808814771,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004949948147605996,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.19485182911157609,
|
|
"num_tokens": 18385013.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.261306858062744,
|
|
"epoch": 0.7843954734961287,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004949858727524855,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.19415438175201416,
|
|
"num_tokens": 18398411.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.177626419067383,
|
|
"epoch": 0.7849910661107802,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004949769228538359,
|
|
"loss": 4.9506,
|
|
"mean_token_accuracy": 0.19288806468248368,
|
|
"num_tokens": 18411317.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.292327117919922,
|
|
"epoch": 0.7855866587254318,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004949679650649717,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.190231154859066,
|
|
"num_tokens": 18426503.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.174467611312866,
|
|
"epoch": 0.7861822513400833,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004949589993862143,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.20611148029565812,
|
|
"num_tokens": 18439465.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.102931261062622,
|
|
"epoch": 0.7867778439547349,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004949500258178851,
|
|
"loss": 4.9009,
|
|
"mean_token_accuracy": 0.19426576495170594,
|
|
"num_tokens": 18452539.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.219004201889038,
|
|
"epoch": 0.7873734365693865,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004949410443603062,
|
|
"loss": 4.946,
|
|
"mean_token_accuracy": 0.2001374989748001,
|
|
"num_tokens": 18466040.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.256741046905518,
|
|
"epoch": 0.7879690291840381,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004949320550137996,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.19557258784770964,
|
|
"num_tokens": 18478621.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.240972280502319,
|
|
"epoch": 0.7885646217986897,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004949230577786877,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.20098492056131362,
|
|
"num_tokens": 18492000.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.087990236282349,
|
|
"epoch": 0.7891602144133413,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004949140526552934,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.2073688954114914,
|
|
"num_tokens": 18506459.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.125224876403808,
|
|
"epoch": 0.7897558070279929,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004949050396439395,
|
|
"loss": 4.8581,
|
|
"mean_token_accuracy": 0.20849994271993638,
|
|
"num_tokens": 18518325.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.178883981704712,
|
|
"epoch": 0.7903513996426444,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948960187449495,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.20768900513648986,
|
|
"num_tokens": 18533329.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.216421604156494,
|
|
"epoch": 0.790946992257296,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004948869899586467,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.2045308381319046,
|
|
"num_tokens": 18544635.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.152740716934204,
|
|
"epoch": 0.7915425848719476,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004948779532853552,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.20945716351270677,
|
|
"num_tokens": 18558576.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.193213605880738,
|
|
"epoch": 0.7921381774865992,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004948689087253989,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.1911552891135216,
|
|
"num_tokens": 18573393.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.202578401565551,
|
|
"epoch": 0.7927337701012508,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004948598562791025,
|
|
"loss": 4.8841,
|
|
"mean_token_accuracy": 0.2067822188138962,
|
|
"num_tokens": 18586273.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.249826145172119,
|
|
"epoch": 0.7933293627159024,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004948507959467905,
|
|
"loss": 5.067,
|
|
"mean_token_accuracy": 0.19914352297782897,
|
|
"num_tokens": 18600040.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.14374737739563,
|
|
"epoch": 0.7939249553305538,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004948417277287877,
|
|
"loss": 4.8485,
|
|
"mean_token_accuracy": 0.20845488011837005,
|
|
"num_tokens": 18613723.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.205537271499634,
|
|
"epoch": 0.7945205479452054,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004948326516254197,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.1989010214805603,
|
|
"num_tokens": 18628575.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.240116882324219,
|
|
"epoch": 0.795116140559857,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494823567637012,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.19002011716365813,
|
|
"num_tokens": 18642179.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.189844846725464,
|
|
"epoch": 0.7957117331745086,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004948144757638902,
|
|
"loss": 4.9619,
|
|
"mean_token_accuracy": 0.19549095630645752,
|
|
"num_tokens": 18655450.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.192246055603027,
|
|
"epoch": 0.7963073257891602,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004948053760063806,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.20517516434192656,
|
|
"num_tokens": 18668434.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.184614801406861,
|
|
"epoch": 0.7969029184038118,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004947962683648095,
|
|
"loss": 4.9529,
|
|
"mean_token_accuracy": 0.19955021291971206,
|
|
"num_tokens": 18683674.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.164677572250366,
|
|
"epoch": 0.7974985110184634,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004947871528395038,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.19832128435373306,
|
|
"num_tokens": 18697323.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.212483501434326,
|
|
"epoch": 0.798094103633115,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00049477802943079,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.19775326550006866,
|
|
"num_tokens": 18711110.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.240968132019043,
|
|
"epoch": 0.7986896962477665,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004947688981389958,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.19157029688358307,
|
|
"num_tokens": 18725753.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.160842227935791,
|
|
"epoch": 0.7992852888624181,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004947597589644484,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.20104837864637376,
|
|
"num_tokens": 18740363.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.146410894393921,
|
|
"epoch": 0.7998808814770697,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004947506119074759,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.19810617417097093,
|
|
"num_tokens": 18755157.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.1218959331512455,
|
|
"epoch": 0.8004764740917213,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004947414569684062,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.20115058422088622,
|
|
"num_tokens": 18769828.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.197394704818725,
|
|
"epoch": 0.8010720667063729,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004947322941475677,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.19985956251621245,
|
|
"num_tokens": 18785810.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.260333585739136,
|
|
"epoch": 0.8016676593210245,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004947231234452891,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.18300077319145203,
|
|
"num_tokens": 18801730.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.188740062713623,
|
|
"epoch": 0.802263251935676,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004947139448618994,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.20209090262651444,
|
|
"num_tokens": 18816684.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.1887282371521,
|
|
"epoch": 0.8028588445503275,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004947047583977276,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.19222164899110794,
|
|
"num_tokens": 18832487.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.116547107696533,
|
|
"epoch": 0.8034544371649791,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004946955640531033,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.20503035932779312,
|
|
"num_tokens": 18845136.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.214083051681518,
|
|
"epoch": 0.8040500297796307,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004946863618283565,
|
|
"loss": 4.9297,
|
|
"mean_token_accuracy": 0.19984907507896424,
|
|
"num_tokens": 18859082.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.209629726409912,
|
|
"epoch": 0.8046456223942823,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004946771517238169,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.19937164038419725,
|
|
"num_tokens": 18872957.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.20362024307251,
|
|
"epoch": 0.8052412150089339,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004946679337398151,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.20129719823598863,
|
|
"num_tokens": 18887189.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.216832637786865,
|
|
"epoch": 0.8058368076235854,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004946587078766818,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.19818754643201827,
|
|
"num_tokens": 18900325.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.166711139678955,
|
|
"epoch": 0.806432400238237,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004946494741347476,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.19886155128479005,
|
|
"num_tokens": 18914583.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.208052349090576,
|
|
"epoch": 0.8070279928528886,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004946402325143439,
|
|
"loss": 5.0101,
|
|
"mean_token_accuracy": 0.19739667922258378,
|
|
"num_tokens": 18928796.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.185489368438721,
|
|
"epoch": 0.8076235854675402,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004946309830158024,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.193352310359478,
|
|
"num_tokens": 18942976.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.141387605667115,
|
|
"epoch": 0.8082191780821918,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946217256394544,
|
|
"loss": 4.9345,
|
|
"mean_token_accuracy": 0.20610932260751724,
|
|
"num_tokens": 18955384.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.231763887405395,
|
|
"epoch": 0.8088147706968434,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004946124603856322,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.19366343170404435,
|
|
"num_tokens": 18969149.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.158548307418823,
|
|
"epoch": 0.809410363311495,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004946031872546683,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.19997966140508652,
|
|
"num_tokens": 18982216.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.180615234375,
|
|
"epoch": 0.8100059559261465,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000494593906246895,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.19309812188148498,
|
|
"num_tokens": 18998075.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.112532138824463,
|
|
"epoch": 0.8106015485407981,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004945846173626453,
|
|
"loss": 4.8576,
|
|
"mean_token_accuracy": 0.20594166964292526,
|
|
"num_tokens": 19011088.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.1699967861175535,
|
|
"epoch": 0.8111971411554497,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004945753206022525,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.20013341754674913,
|
|
"num_tokens": 19025864.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.169614267349243,
|
|
"epoch": 0.8117927337701013,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004945660159660499,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.1953017607331276,
|
|
"num_tokens": 19039803.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.078014469146728,
|
|
"epoch": 0.8123883263847528,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945567034543712,
|
|
"loss": 4.9069,
|
|
"mean_token_accuracy": 0.20980737954378129,
|
|
"num_tokens": 19053784.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.161725854873657,
|
|
"epoch": 0.8129839189994044,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945473830675507,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.19564930647611617,
|
|
"num_tokens": 19068730.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.281051063537598,
|
|
"epoch": 0.813579511614056,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945380548059224,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.19808235466480256,
|
|
"num_tokens": 19082354.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.286688947677613,
|
|
"epoch": 0.8141751042287075,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945287186698211,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.1937915563583374,
|
|
"num_tokens": 19095051.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.185162830352783,
|
|
"epoch": 0.8147706968433591,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004945193746595815,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.20006429702043532,
|
|
"num_tokens": 19110653.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.1859112739562985,
|
|
"epoch": 0.8153662894580107,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004945100227755389,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.19498492777347565,
|
|
"num_tokens": 19125112.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.2671980381011965,
|
|
"epoch": 0.8159618820726623,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004945006630180288,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.18735138475894927,
|
|
"num_tokens": 19140153.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.2187727928161625,
|
|
"epoch": 0.8165574746873139,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004944912953873865,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.19942758232355118,
|
|
"num_tokens": 19154423.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.1965680599212645,
|
|
"epoch": 0.8171530673019655,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004944819198839486,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.19912686944007874,
|
|
"num_tokens": 19169909.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.165954303741455,
|
|
"epoch": 0.817748659916617,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000494472536508051,
|
|
"loss": 4.9519,
|
|
"mean_token_accuracy": 0.2020408555865288,
|
|
"num_tokens": 19184068.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.158046913146973,
|
|
"epoch": 0.8183442525312686,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004944631452600303,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.19725150465965272,
|
|
"num_tokens": 19199281.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.236583185195923,
|
|
"epoch": 0.8189398451459202,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004944537461402234,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.1877261593937874,
|
|
"num_tokens": 19213893.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.263673496246338,
|
|
"epoch": 0.8195354377605718,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004944443391489676,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.19104332476854324,
|
|
"num_tokens": 19227873.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.178918838500977,
|
|
"epoch": 0.8201310303752234,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004944349242865999,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.21028520911931992,
|
|
"num_tokens": 19241287.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.185282135009766,
|
|
"epoch": 0.820726622989875,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004944255015534585,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.20108973383903503,
|
|
"num_tokens": 19255428.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.150266981124878,
|
|
"epoch": 0.8213222156045265,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000494416070949881,
|
|
"loss": 4.9167,
|
|
"mean_token_accuracy": 0.2015451192855835,
|
|
"num_tokens": 19268234.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.187671804428101,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004944066324762058,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.19600512981414794,
|
|
"num_tokens": 19281443.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.202685546875,
|
|
"epoch": 0.8225134008338296,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004943971861327713,
|
|
"loss": 4.8924,
|
|
"mean_token_accuracy": 0.20731243193149568,
|
|
"num_tokens": 19293791.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.170107316970825,
|
|
"epoch": 0.8231089934484812,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004943877319199167,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.20116084963083267,
|
|
"num_tokens": 19305634.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.2271058559417725,
|
|
"epoch": 0.8237045860631328,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004943782698379807,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.189031483232975,
|
|
"num_tokens": 19319719.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.142617654800415,
|
|
"epoch": 0.8243001786777844,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004943687998873029,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.21468710154294968,
|
|
"num_tokens": 19333596.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.117456674575806,
|
|
"epoch": 0.824895771292436,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004943593220682229,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.19865041077136994,
|
|
"num_tokens": 19347750.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.147422742843628,
|
|
"epoch": 0.8254913639070875,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004943498363810807,
|
|
"loss": 4.904,
|
|
"mean_token_accuracy": 0.2047455295920372,
|
|
"num_tokens": 19360584.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.156736135482788,
|
|
"epoch": 0.8260869565217391,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004943403428262164,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.20417164266109467,
|
|
"num_tokens": 19375113.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.157262849807739,
|
|
"epoch": 0.8266825491363907,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004943308414039708,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.18991622924804688,
|
|
"num_tokens": 19387748.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.249469947814942,
|
|
"epoch": 0.8272781417510423,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004943213321146843,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.19418000131845475,
|
|
"num_tokens": 19404374.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.163524341583252,
|
|
"epoch": 0.8278737343656939,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004943118149586984,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.20486054122447966,
|
|
"num_tokens": 19419209.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.143970251083374,
|
|
"epoch": 0.8284693269803455,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004943022899363542,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.2001874938607216,
|
|
"num_tokens": 19433127.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.205447244644165,
|
|
"epoch": 0.8290649195949971,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004942927570479934,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.19444992691278457,
|
|
"num_tokens": 19447718.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.160541296005249,
|
|
"epoch": 0.8296605122096486,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004942832162939581,
|
|
"loss": 4.8948,
|
|
"mean_token_accuracy": 0.2041360393166542,
|
|
"num_tokens": 19459193.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.106111240386963,
|
|
"epoch": 0.8302561048243002,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004942736676745902,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.19808810949325562,
|
|
"num_tokens": 19472791.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.265562295913696,
|
|
"epoch": 0.8308516974389517,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004942641111902324,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.19660953283309937,
|
|
"num_tokens": 19484903.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.1872107028961185,
|
|
"epoch": 0.8314472900536033,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004942545468412275,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.19705149233341218,
|
|
"num_tokens": 19499833.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.127726268768311,
|
|
"epoch": 0.8320428826682549,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004942449746279184,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.20868579298257828,
|
|
"num_tokens": 19511744.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.159153270721435,
|
|
"epoch": 0.8326384752829065,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004942353945506485,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.2082059934735298,
|
|
"num_tokens": 19525192.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.098970031738281,
|
|
"epoch": 0.833234067897558,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004942258066097617,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.1946823239326477,
|
|
"num_tokens": 19539397.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.129020690917969,
|
|
"epoch": 0.8338296605122096,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004942162108056015,
|
|
"loss": 4.9084,
|
|
"mean_token_accuracy": 0.2096063643693924,
|
|
"num_tokens": 19554322.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.234167671203613,
|
|
"epoch": 0.8344252531268612,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942066071385122,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.1922169119119644,
|
|
"num_tokens": 19567652.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.204717206954956,
|
|
"epoch": 0.8350208457415128,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004941969956088383,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.19228022992610933,
|
|
"num_tokens": 19582921.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.181436681747437,
|
|
"epoch": 0.8356164383561644,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004941873762169246,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.19572365880012513,
|
|
"num_tokens": 19597298.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.2012396335601805,
|
|
"epoch": 0.836212030970816,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004941777489631161,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.19664670526981354,
|
|
"num_tokens": 19611200.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.181854581832885,
|
|
"epoch": 0.8368076235854676,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004941681138477582,
|
|
"loss": 4.8497,
|
|
"mean_token_accuracy": 0.20953864455223084,
|
|
"num_tokens": 19623910.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.102773571014405,
|
|
"epoch": 0.8374032162001191,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004941584708711962,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.2057928204536438,
|
|
"num_tokens": 19638308.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.123822975158691,
|
|
"epoch": 0.8379988088147707,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004941488200337763,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.19732289314270018,
|
|
"num_tokens": 19652987.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.199441432952881,
|
|
"epoch": 0.8385944014294223,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004941391613358444,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.1936160981655121,
|
|
"num_tokens": 19667789.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.234569692611695,
|
|
"epoch": 0.8391899940440739,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004941294947777473,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.19623250514268875,
|
|
"num_tokens": 19682775.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.211414480209351,
|
|
"epoch": 0.8397855866587254,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004941198203598314,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.20020330399274827,
|
|
"num_tokens": 19696714.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.130775690078735,
|
|
"epoch": 0.840381179273377,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004941101380824438,
|
|
"loss": 4.9167,
|
|
"mean_token_accuracy": 0.20109327435493468,
|
|
"num_tokens": 19711132.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.087300062179565,
|
|
"epoch": 0.8409767718880286,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004941004479459318,
|
|
"loss": 4.8234,
|
|
"mean_token_accuracy": 0.2063111647963524,
|
|
"num_tokens": 19726680.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.1805281162261965,
|
|
"epoch": 0.8415723645026801,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000494090749950643,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.1980413392186165,
|
|
"num_tokens": 19740152.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.214729833602905,
|
|
"epoch": 0.8421679571173317,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004940810440969253,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.19330805242061616,
|
|
"num_tokens": 19756233.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.128584480285644,
|
|
"epoch": 0.8427635497319833,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004940713303851265,
|
|
"loss": 4.862,
|
|
"mean_token_accuracy": 0.20172089338302612,
|
|
"num_tokens": 19771178.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.271034145355225,
|
|
"epoch": 0.8433591423466349,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004940616088155954,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.19161928147077562,
|
|
"num_tokens": 19786180.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.068975162506104,
|
|
"epoch": 0.8439547349612865,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004940518793886807,
|
|
"loss": 4.8505,
|
|
"mean_token_accuracy": 0.2094910353422165,
|
|
"num_tokens": 19800472.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.138592290878296,
|
|
"epoch": 0.8445503275759381,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004940421421047311,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.20622486025094985,
|
|
"num_tokens": 19816060.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.172881746292115,
|
|
"epoch": 0.8451459201905897,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000494032396964096,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.20144321769475937,
|
|
"num_tokens": 19832219.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.087926578521729,
|
|
"epoch": 0.8457415128052412,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000494022643967125,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.21398750841617584,
|
|
"num_tokens": 19844913.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.176878929138184,
|
|
"epoch": 0.8463371054198928,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004940128831141679,
|
|
"loss": 4.9235,
|
|
"mean_token_accuracy": 0.19802037328481675,
|
|
"num_tokens": 19858375.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.213673067092896,
|
|
"epoch": 0.8469326980345444,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004940031144055747,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.19598734229803086,
|
|
"num_tokens": 19872004.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.163327646255493,
|
|
"epoch": 0.847528290649196,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004939933378416959,
|
|
"loss": 4.8838,
|
|
"mean_token_accuracy": 0.19919876307249068,
|
|
"num_tokens": 19886340.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.198000764846801,
|
|
"epoch": 0.8481238832638476,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004939835534228821,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.2045590192079544,
|
|
"num_tokens": 19899185.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.199259424209595,
|
|
"epoch": 0.848719475878499,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004939737611494842,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.18782405257225038,
|
|
"num_tokens": 19912886.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.214553546905518,
|
|
"epoch": 0.8493150684931506,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004939639610218536,
|
|
"loss": 4.9773,
|
|
"mean_token_accuracy": 0.18926315903663635,
|
|
"num_tokens": 19927780.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.168109989166259,
|
|
"epoch": 0.8499106611078022,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004939541530403419,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.2045607641339302,
|
|
"num_tokens": 19940181.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.12690110206604,
|
|
"epoch": 0.8505062537224538,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004939443372053004,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.19709809273481368,
|
|
"num_tokens": 19952823.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.1767298698425295,
|
|
"epoch": 0.8511018463371054,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004939345135170818,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.1882709965109825,
|
|
"num_tokens": 19966528.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.248154973983764,
|
|
"epoch": 0.851697438951757,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000493924681976038,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.19386336505413054,
|
|
"num_tokens": 19981259.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.146277952194214,
|
|
"epoch": 0.8522930315664086,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004939148425825219,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.20037278681993484,
|
|
"num_tokens": 19995096.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.142520809173584,
|
|
"epoch": 0.8528886241810602,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004939049953368863,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.19382059276103974,
|
|
"num_tokens": 20008895.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.219720888137817,
|
|
"epoch": 0.8534842167957117,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004938951402394844,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.19996455311775208,
|
|
"num_tokens": 20023506.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.1646040916442875,
|
|
"epoch": 0.8540798094103633,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004938852772906697,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.19635888934135437,
|
|
"num_tokens": 20036810.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.16309552192688,
|
|
"epoch": 0.8546754020250149,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004938754064907961,
|
|
"loss": 4.8525,
|
|
"mean_token_accuracy": 0.20518708378076553,
|
|
"num_tokens": 20050653.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.149541807174683,
|
|
"epoch": 0.8552709946396665,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004938655278402175,
|
|
"loss": 4.9153,
|
|
"mean_token_accuracy": 0.20307961106300354,
|
|
"num_tokens": 20065361.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.082183408737182,
|
|
"epoch": 0.8558665872543181,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004938556413392882,
|
|
"loss": 4.8699,
|
|
"mean_token_accuracy": 0.21139221340417863,
|
|
"num_tokens": 20079160.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.169384002685547,
|
|
"epoch": 0.8564621798689697,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004938457469883629,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.20199144780635833,
|
|
"num_tokens": 20095036.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.114953184127808,
|
|
"epoch": 0.8570577724836212,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004938358447877966,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.2067757472395897,
|
|
"num_tokens": 20112319.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.164311027526855,
|
|
"epoch": 0.8576533650982728,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004938259347379442,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.19935424029827117,
|
|
"num_tokens": 20126683.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.1974780559539795,
|
|
"epoch": 0.8582489577129243,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004938160168391614,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.19651492834091186,
|
|
"num_tokens": 20142016.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.134807586669922,
|
|
"epoch": 0.8588445503275759,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004938060910918038,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.20476272106170654,
|
|
"num_tokens": 20156199.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.2619225025177006,
|
|
"epoch": 0.8594401429422275,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004937961574962274,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.1910216599702835,
|
|
"num_tokens": 20169443.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.129044389724731,
|
|
"epoch": 0.8600357355568791,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004937862160527887,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.20377827137708665,
|
|
"num_tokens": 20184187.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.1636748790740965,
|
|
"epoch": 0.8606313281715307,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004937762667618441,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.20472845137119294,
|
|
"num_tokens": 20198217.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.1480090618133545,
|
|
"epoch": 0.8612269207861822,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004937663096237505,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.20224204063415527,
|
|
"num_tokens": 20214253.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.123743629455566,
|
|
"epoch": 0.8618225134008338,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004937563446388652,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.20535139888525009,
|
|
"num_tokens": 20227880.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.055837774276734,
|
|
"epoch": 0.8624181060154854,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004937463718075453,
|
|
"loss": 4.8437,
|
|
"mean_token_accuracy": 0.21040962487459183,
|
|
"num_tokens": 20242642.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.088917875289917,
|
|
"epoch": 0.863013698630137,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004937363911301488,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.20503964573144912,
|
|
"num_tokens": 20255950.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.174100875854492,
|
|
"epoch": 0.8636092912447886,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004937264026070336,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.20366551131010055,
|
|
"num_tokens": 20270067.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.286001205444336,
|
|
"epoch": 0.8642048838594402,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000493716406238558,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.19882625937461854,
|
|
"num_tokens": 20283326.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.100559520721435,
|
|
"epoch": 0.8648004764740918,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004937064020250804,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.20179162919521332,
|
|
"num_tokens": 20296161.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.090710783004761,
|
|
"epoch": 0.8653960690887433,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004936963899669599,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.1996309846639633,
|
|
"num_tokens": 20310662.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.192110443115235,
|
|
"epoch": 0.8659916617033949,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004936863700645554,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.19874917715787888,
|
|
"num_tokens": 20324381.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.146421813964844,
|
|
"epoch": 0.8665872543180465,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004936763423182264,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.19659116715192795,
|
|
"num_tokens": 20338093.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.152958011627197,
|
|
"epoch": 0.867182846932698,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004936663067283325,
|
|
"loss": 4.8647,
|
|
"mean_token_accuracy": 0.20840763300657272,
|
|
"num_tokens": 20350534.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.094810867309571,
|
|
"epoch": 0.8677784395473496,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004936562632952337,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.20936393439769746,
|
|
"num_tokens": 20364230.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.2586547374725345,
|
|
"epoch": 0.8683740321620012,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004936462120192903,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.18948373794555665,
|
|
"num_tokens": 20380605.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.204036092758178,
|
|
"epoch": 0.8689696247766527,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004936361529008627,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.1979580357670784,
|
|
"num_tokens": 20392760.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.137707948684692,
|
|
"epoch": 0.8695652173913043,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004936260859403119,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.2031350091099739,
|
|
"num_tokens": 20408519.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.121989727020264,
|
|
"epoch": 0.8701608100059559,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004936160111379987,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.20652975291013717,
|
|
"num_tokens": 20421322.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.157418584823608,
|
|
"epoch": 0.8707564026206075,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004936059284942848,
|
|
"loss": 4.9231,
|
|
"mean_token_accuracy": 0.19750603586435317,
|
|
"num_tokens": 20436056.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.126880168914795,
|
|
"epoch": 0.8713519952352591,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004935958380095316,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.19979116916656495,
|
|
"num_tokens": 20449268.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.188067245483398,
|
|
"epoch": 0.8719475878499107,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000493585739684101,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.2011038437485695,
|
|
"num_tokens": 20462635.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.151953268051147,
|
|
"epoch": 0.8725431804645623,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004935756335183554,
|
|
"loss": 4.8944,
|
|
"mean_token_accuracy": 0.2064547762274742,
|
|
"num_tokens": 20476048.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.117564678192139,
|
|
"epoch": 0.8731387730792138,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004935655195126572,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.20720231682062148,
|
|
"num_tokens": 20488856.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.114104700088501,
|
|
"epoch": 0.8737343656938654,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004935553976673692,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.20091983824968337,
|
|
"num_tokens": 20503426.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.19834270477295,
|
|
"epoch": 0.874329958308517,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004935452679828545,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.1985922411084175,
|
|
"num_tokens": 20518305.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.104052448272705,
|
|
"epoch": 0.8749255509231686,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004935351304594763,
|
|
"loss": 4.8628,
|
|
"mean_token_accuracy": 0.20786418169736862,
|
|
"num_tokens": 20532310.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.160271310806275,
|
|
"epoch": 0.8755211435378202,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004935249850975983,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.19921597093343735,
|
|
"num_tokens": 20546149.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.17770619392395,
|
|
"epoch": 0.8761167361524718,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004935148318975843,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.20873825401067733,
|
|
"num_tokens": 20560077.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.260556268692016,
|
|
"epoch": 0.8767123287671232,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004935046708597986,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.19336255937814711,
|
|
"num_tokens": 20574657.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.100927400588989,
|
|
"epoch": 0.8773079213817748,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004934945019846057,
|
|
"loss": 4.8254,
|
|
"mean_token_accuracy": 0.20545119196176528,
|
|
"num_tokens": 20587091.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.137057495117188,
|
|
"epoch": 0.8779035139964264,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004934843252723702,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.2046142727136612,
|
|
"num_tokens": 20600537.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.229600524902343,
|
|
"epoch": 0.878499106611078,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004934741407234572,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.19335699826478958,
|
|
"num_tokens": 20614029.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.155656051635742,
|
|
"epoch": 0.8790946992257296,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000493463948338232,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.2026839792728424,
|
|
"num_tokens": 20627906.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.165369653701783,
|
|
"epoch": 0.8796902918403812,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004934537481170602,
|
|
"loss": 4.8923,
|
|
"mean_token_accuracy": 0.1987556606531143,
|
|
"num_tokens": 20642717.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.13789005279541,
|
|
"epoch": 0.8802858844550328,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004934435400603077,
|
|
"loss": 4.9127,
|
|
"mean_token_accuracy": 0.1991451248526573,
|
|
"num_tokens": 20657234.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.15365080833435,
|
|
"epoch": 0.8808814770696843,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004934333241683404,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.20178160518407823,
|
|
"num_tokens": 20672162.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.247027063369751,
|
|
"epoch": 0.8814770696843359,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004934231004415251,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.20047924369573594,
|
|
"num_tokens": 20684565.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.211897325515747,
|
|
"epoch": 0.8820726622989875,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004934128688802282,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.19821293652057648,
|
|
"num_tokens": 20699931.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.171431970596314,
|
|
"epoch": 0.8826682549136391,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004934026294848168,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.20023156255483626,
|
|
"num_tokens": 20715031.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.155258369445801,
|
|
"epoch": 0.8832638475282907,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004933923822556583,
|
|
"loss": 4.9342,
|
|
"mean_token_accuracy": 0.19958258420228958,
|
|
"num_tokens": 20730825.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.219849967956543,
|
|
"epoch": 0.8838594401429423,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049338212719312,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.2013201117515564,
|
|
"num_tokens": 20743287.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.18552598953247,
|
|
"epoch": 0.8844550327575939,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00049337186429757,
|
|
"loss": 4.9482,
|
|
"mean_token_accuracy": 0.19571833163499833,
|
|
"num_tokens": 20759911.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.114535856246948,
|
|
"epoch": 0.8850506253722454,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004933615935693762,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.20583552718162537,
|
|
"num_tokens": 20772842.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.214235925674439,
|
|
"epoch": 0.8856462179868969,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004933513150089069,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.193477301299572,
|
|
"num_tokens": 20787524.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.122951555252075,
|
|
"epoch": 0.8862418106015485,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004933410286165311,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.21194293051958085,
|
|
"num_tokens": 20800332.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.158557462692261,
|
|
"epoch": 0.8868374032162001,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004933307343926177,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.20811442285776138,
|
|
"num_tokens": 20813231.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.222035217285156,
|
|
"epoch": 0.8874329958308517,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004933204323375358,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.1982417270541191,
|
|
"num_tokens": 20827116.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.271926307678223,
|
|
"epoch": 0.8880285884455033,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000493310122451655,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.19548407196998596,
|
|
"num_tokens": 20838536.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.104053497314453,
|
|
"epoch": 0.8886241810601548,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004932998047353449,
|
|
"loss": 4.8425,
|
|
"mean_token_accuracy": 0.21043538749217988,
|
|
"num_tokens": 20850849.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.128205156326294,
|
|
"epoch": 0.8892197736748064,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004932894791889759,
|
|
"loss": 4.8982,
|
|
"mean_token_accuracy": 0.20407332479953766,
|
|
"num_tokens": 20866140.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.147731113433838,
|
|
"epoch": 0.889815366289458,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004932791458129181,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.20002410113811492,
|
|
"num_tokens": 20879458.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.124208593368531,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004932688046075422,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.20428954511880876,
|
|
"num_tokens": 20893516.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.2379045486450195,
|
|
"epoch": 0.8910065515187612,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004932584555732192,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.190228471159935,
|
|
"num_tokens": 20908713.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.192844724655151,
|
|
"epoch": 0.8916021441334128,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004932480987103204,
|
|
"loss": 4.9157,
|
|
"mean_token_accuracy": 0.20541791766881942,
|
|
"num_tokens": 20922080.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.1689728736877445,
|
|
"epoch": 0.8921977367480644,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004932377340192169,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.19958229064941407,
|
|
"num_tokens": 20935484.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.2711019039154055,
|
|
"epoch": 0.8927933293627159,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004932273615002809,
|
|
"loss": 4.9981,
|
|
"mean_token_accuracy": 0.19082930386066438,
|
|
"num_tokens": 20948851.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.131562232971191,
|
|
"epoch": 0.8933889219773675,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004932169811538843,
|
|
"loss": 4.9443,
|
|
"mean_token_accuracy": 0.2004090815782547,
|
|
"num_tokens": 20961637.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.240088176727295,
|
|
"epoch": 0.8939845145920191,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004932065929803993,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.1903009831905365,
|
|
"num_tokens": 20976236.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.160513067245484,
|
|
"epoch": 0.8945801072066706,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004931961969801985,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.20021743029356004,
|
|
"num_tokens": 20990439.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.187777423858643,
|
|
"epoch": 0.8951756998213222,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000493185793153655,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.20091027468442918,
|
|
"num_tokens": 21003632.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.135032033920288,
|
|
"epoch": 0.8957712924359738,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004931753815011419,
|
|
"loss": 4.8909,
|
|
"mean_token_accuracy": 0.2077113837003708,
|
|
"num_tokens": 21017685.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.116024160385132,
|
|
"epoch": 0.8963668850506253,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004931649620230325,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.2107477754354477,
|
|
"num_tokens": 21029720.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.122563362121582,
|
|
"epoch": 0.8969624776652769,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004931545347197006,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.20440852344036103,
|
|
"num_tokens": 21044148.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.216667938232422,
|
|
"epoch": 0.8975580702799285,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004931440995915203,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.20074666291475296,
|
|
"num_tokens": 21059278.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.103487396240235,
|
|
"epoch": 0.8981536628945801,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004931336566388658,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.20388510078191757,
|
|
"num_tokens": 21074258.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.192672777175903,
|
|
"epoch": 0.8987492555092317,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004931232058621117,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.19489986896514894,
|
|
"num_tokens": 21087283.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.220127010345459,
|
|
"epoch": 0.8993448481238833,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004931127472616328,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.20450807958841324,
|
|
"num_tokens": 21101461.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.177894258499146,
|
|
"epoch": 0.8999404407385349,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004931022808378044,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.2034042075276375,
|
|
"num_tokens": 21115067.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.151477956771851,
|
|
"epoch": 0.9005360333531864,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004930918065910018,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.20054860264062882,
|
|
"num_tokens": 21129029.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.201594495773316,
|
|
"epoch": 0.901131625967838,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004930813245216005,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.19962978810071946,
|
|
"num_tokens": 21142037.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.170756387710571,
|
|
"epoch": 0.9017272185824896,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004930708346299769,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.20054658651351928,
|
|
"num_tokens": 21157036.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.19022388458252,
|
|
"epoch": 0.9023228111971412,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004930603369165069,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.19947717785835267,
|
|
"num_tokens": 21170025.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.177037954330444,
|
|
"epoch": 0.9029184038117928,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004930498313815672,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.20403429865837097,
|
|
"num_tokens": 21183664.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.0528747081756595,
|
|
"epoch": 0.9035139964264444,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004930393180255345,
|
|
"loss": 4.8431,
|
|
"mean_token_accuracy": 0.2092731177806854,
|
|
"num_tokens": 21198299.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.103593111038208,
|
|
"epoch": 0.9041095890410958,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000493028796848786,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.21420642137527465,
|
|
"num_tokens": 21210133.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.174817132949829,
|
|
"epoch": 0.9047051816557474,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004930182678516992,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.20276188403367995,
|
|
"num_tokens": 21225813.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.274481582641601,
|
|
"epoch": 0.905300774270399,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004930077310346515,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.19923958033323289,
|
|
"num_tokens": 21238602.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.164350843429565,
|
|
"epoch": 0.9058963668850506,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004929971863980209,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.199314646422863,
|
|
"num_tokens": 21254367.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.241876888275146,
|
|
"epoch": 0.9064919594997022,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004929866339421857,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.19825731366872787,
|
|
"num_tokens": 21268285.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.101060009002685,
|
|
"epoch": 0.9070875521143538,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004929760736675243,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.1980912819504738,
|
|
"num_tokens": 21282398.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.208746290206909,
|
|
"epoch": 0.9076831447290054,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004929655055744157,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.19202795177698134,
|
|
"num_tokens": 21296991.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.198200225830078,
|
|
"epoch": 0.9082787373436569,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004929549296632387,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.19940607398748397,
|
|
"num_tokens": 21313677.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.151069641113281,
|
|
"epoch": 0.9088743299583085,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004929443459343728,
|
|
"loss": 4.8937,
|
|
"mean_token_accuracy": 0.20646460205316544,
|
|
"num_tokens": 21325252.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.1430309295654295,
|
|
"epoch": 0.9094699225729601,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004929337543881975,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.20131825357675553,
|
|
"num_tokens": 21341771.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.201722908020019,
|
|
"epoch": 0.9100655151876117,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004929231550250927,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.20166292786598206,
|
|
"num_tokens": 21356029.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.27152943611145,
|
|
"epoch": 0.9106611078022633,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004929125478454389,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.20222508907318115,
|
|
"num_tokens": 21369943.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.218910837173462,
|
|
"epoch": 0.9112567004169149,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004929019328496161,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.20571470260620117,
|
|
"num_tokens": 21385078.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.071431398391724,
|
|
"epoch": 0.9118522930315665,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004928913100380053,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.21606407612562178,
|
|
"num_tokens": 21398249.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.129451608657837,
|
|
"epoch": 0.912447885646218,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004928806794109875,
|
|
"loss": 4.9614,
|
|
"mean_token_accuracy": 0.20498874336481093,
|
|
"num_tokens": 21414773.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.247469472885132,
|
|
"epoch": 0.9130434782608695,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000492870040968944,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.19853055626153945,
|
|
"num_tokens": 21428551.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.154452705383301,
|
|
"epoch": 0.9136390708755211,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004928593947122564,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.19509592801332473,
|
|
"num_tokens": 21442916.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.194934225082397,
|
|
"epoch": 0.9142346634901727,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004928487406413065,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.2002209261059761,
|
|
"num_tokens": 21457686.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.195427083969117,
|
|
"epoch": 0.9148302561048243,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004928380787564764,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.20670426338911058,
|
|
"num_tokens": 21473503.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.1257812023162845,
|
|
"epoch": 0.9154258487194759,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004928274090581486,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.20538197010755538,
|
|
"num_tokens": 21486362.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.096245050430298,
|
|
"epoch": 0.9160214413341274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004928167315467059,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.20149521082639693,
|
|
"num_tokens": 21500445.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.18103985786438,
|
|
"epoch": 0.916617033948779,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004928060462225312,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.19944300055503844,
|
|
"num_tokens": 21513648.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.183280992507934,
|
|
"epoch": 0.9172126265634306,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004927953530860077,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.2016470417380333,
|
|
"num_tokens": 21528103.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.153290796279907,
|
|
"epoch": 0.9178082191780822,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004927846521375189,
|
|
"loss": 4.8477,
|
|
"mean_token_accuracy": 0.2130131796002388,
|
|
"num_tokens": 21542435.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.182994031906128,
|
|
"epoch": 0.9184038117927338,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004927739433774489,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.20480589866638182,
|
|
"num_tokens": 21557993.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.163361549377441,
|
|
"epoch": 0.9189994044073854,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004927632268061815,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.20079663693904876,
|
|
"num_tokens": 21573383.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.187111043930054,
|
|
"epoch": 0.919594997022037,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004927525024241013,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.2092558667063713,
|
|
"num_tokens": 21588179.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.133381319046021,
|
|
"epoch": 0.9201905896366885,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004927417702315928,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.2013625204563141,
|
|
"num_tokens": 21603595.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.184838962554932,
|
|
"epoch": 0.9207861822513401,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004927310302290411,
|
|
"loss": 4.934,
|
|
"mean_token_accuracy": 0.20356503278017044,
|
|
"num_tokens": 21618487.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.1615783214569095,
|
|
"epoch": 0.9213817748659917,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004927202824168313,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.2036508470773697,
|
|
"num_tokens": 21632970.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.184818267822266,
|
|
"epoch": 0.9219773674806433,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000492709526795349,
|
|
"loss": 4.9124,
|
|
"mean_token_accuracy": 0.2016807332634926,
|
|
"num_tokens": 21645943.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.139384031295776,
|
|
"epoch": 0.9225729600952948,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049269876336498,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.2088763028383255,
|
|
"num_tokens": 21658028.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.161565542221069,
|
|
"epoch": 0.9231685527099464,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004926879921261101,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.2042483150959015,
|
|
"num_tokens": 21672265.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.100625848770141,
|
|
"epoch": 0.9237641453245979,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004926772130791261,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.20385824888944626,
|
|
"num_tokens": 21685871.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.0828193664550785,
|
|
"epoch": 0.9243597379392495,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004926664262244143,
|
|
"loss": 4.7921,
|
|
"mean_token_accuracy": 0.21346231997013093,
|
|
"num_tokens": 21699783.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.171153736114502,
|
|
"epoch": 0.9249553305539011,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004926556315623617,
|
|
"loss": 4.9127,
|
|
"mean_token_accuracy": 0.2048138976097107,
|
|
"num_tokens": 21716144.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.198909902572632,
|
|
"epoch": 0.9255509231685527,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004926448290933555,
|
|
"loss": 4.9085,
|
|
"mean_token_accuracy": 0.20456106215715408,
|
|
"num_tokens": 21727334.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.187424278259277,
|
|
"epoch": 0.9261465157832043,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004926340188177831,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.1996648922562599,
|
|
"num_tokens": 21740989.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.183287763595581,
|
|
"epoch": 0.9267421083978559,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004926232007360324,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.19798339605331422,
|
|
"num_tokens": 21756776.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.2097574234008786,
|
|
"epoch": 0.9273377010125075,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004926123748484911,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.20227449536323547,
|
|
"num_tokens": 21771864.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.139037942886352,
|
|
"epoch": 0.927933293627159,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492601541155548,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.20507404953241348,
|
|
"num_tokens": 21785161.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.23163743019104,
|
|
"epoch": 0.9285288862418106,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004925906996575912,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.18925505131483078,
|
|
"num_tokens": 21799350.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.224358797073364,
|
|
"epoch": 0.9291244788564622,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004925798503550099,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.20562706142663956,
|
|
"num_tokens": 21813925.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.138200855255127,
|
|
"epoch": 0.9297200714711138,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004925689932481931,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.20111260414123536,
|
|
"num_tokens": 21828356.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.07058892250061,
|
|
"epoch": 0.9303156640857654,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004925581283375303,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.21321394592523574,
|
|
"num_tokens": 21842667.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.176006269454956,
|
|
"epoch": 0.930911256700417,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004925472556234111,
|
|
"loss": 4.9432,
|
|
"mean_token_accuracy": 0.201265449821949,
|
|
"num_tokens": 21856116.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.176999425888061,
|
|
"epoch": 0.9315068493150684,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004925363751062256,
|
|
"loss": 4.9123,
|
|
"mean_token_accuracy": 0.20339296013116837,
|
|
"num_tokens": 21870630.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.223974084854126,
|
|
"epoch": 0.93210244192972,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000492525486786364,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.20349437594413758,
|
|
"num_tokens": 21884982.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.122536039352417,
|
|
"epoch": 0.9326980345443716,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004925145906642169,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.2069467067718506,
|
|
"num_tokens": 21899301.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.1309592723846436,
|
|
"epoch": 0.9332936271590232,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004925036867401751,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.20727040022611617,
|
|
"num_tokens": 21913903.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.116994857788086,
|
|
"epoch": 0.9338892197736748,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004924927750146296,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.20629644095897676,
|
|
"num_tokens": 21930123.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.121788883209229,
|
|
"epoch": 0.9344848123883264,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004924818554879718,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.2012730970978737,
|
|
"num_tokens": 21945164.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.1744256019592285,
|
|
"epoch": 0.935080405002978,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004924709281605938,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.19980432689189911,
|
|
"num_tokens": 21959341.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.1632630825042725,
|
|
"epoch": 0.9356759976176295,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004924599930328869,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.2094835564494133,
|
|
"num_tokens": 21973049.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.084960794448852,
|
|
"epoch": 0.9362715902322811,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004924490501052437,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.21566962599754333,
|
|
"num_tokens": 21985604.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.212312459945679,
|
|
"epoch": 0.9368671828469327,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004924380993780566,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.1968146815896034,
|
|
"num_tokens": 22000472.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.18281512260437,
|
|
"epoch": 0.9374627754615843,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004924271408517185,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.20772419422864913,
|
|
"num_tokens": 22014162.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.190010690689087,
|
|
"epoch": 0.9380583680762359,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924161745266222,
|
|
"loss": 4.9071,
|
|
"mean_token_accuracy": 0.19506201446056365,
|
|
"num_tokens": 22026832.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.054138278961181,
|
|
"epoch": 0.9386539606908875,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004924052004031613,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.2083499699831009,
|
|
"num_tokens": 22038816.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.227738666534424,
|
|
"epoch": 0.939249553305539,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004923942184817293,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.19772869348526,
|
|
"num_tokens": 22053356.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.125162363052368,
|
|
"epoch": 0.9398451459201906,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004923832287627202,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.19789994657039642,
|
|
"num_tokens": 22066879.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.159626722335815,
|
|
"epoch": 0.9404407385348421,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004923722312465281,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.199508199095726,
|
|
"num_tokens": 22081036.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.206025695800781,
|
|
"epoch": 0.9410363311494937,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004923612259335476,
|
|
"loss": 4.969,
|
|
"mean_token_accuracy": 0.19389960616827012,
|
|
"num_tokens": 22095609.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.12523889541626,
|
|
"epoch": 0.9416319237641453,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923502128241732,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.20452393293380738,
|
|
"num_tokens": 22107539.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.124048519134521,
|
|
"epoch": 0.9422275163787969,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004923391919188001,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.210932220518589,
|
|
"num_tokens": 22120438.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.172843074798584,
|
|
"epoch": 0.9428231089934485,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004923281632178236,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.19242430180311204,
|
|
"num_tokens": 22134796.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.209022855758667,
|
|
"epoch": 0.9434187016081,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004923171267216392,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.19904885292053223,
|
|
"num_tokens": 22149178.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.138788652420044,
|
|
"epoch": 0.9440142942227516,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004923060824306428,
|
|
"loss": 4.9434,
|
|
"mean_token_accuracy": 0.20030947178602218,
|
|
"num_tokens": 22163652.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.236685705184937,
|
|
"epoch": 0.9446098868374032,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004922950303452306,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.19679114669561387,
|
|
"num_tokens": 22178116.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.126060247421265,
|
|
"epoch": 0.9452054794520548,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004922839704657988,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.21089723110198974,
|
|
"num_tokens": 22191750.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.199862337112426,
|
|
"epoch": 0.9458010720667064,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004922729027927444,
|
|
"loss": 4.9302,
|
|
"mean_token_accuracy": 0.20172469615936278,
|
|
"num_tokens": 22204889.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.143636226654053,
|
|
"epoch": 0.946396664681358,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004922618273264642,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.2046049192547798,
|
|
"num_tokens": 22218312.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.172827577590942,
|
|
"epoch": 0.9469922572960096,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004922507440673555,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.2017950162291527,
|
|
"num_tokens": 22232443.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.062731027603149,
|
|
"epoch": 0.9475878499106611,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004922396530158159,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.21881678104400634,
|
|
"num_tokens": 22245070.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.104772520065308,
|
|
"epoch": 0.9481834425253127,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004922285541722431,
|
|
"loss": 4.8364,
|
|
"mean_token_accuracy": 0.20839131325483323,
|
|
"num_tokens": 22257324.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.160326719284058,
|
|
"epoch": 0.9487790351399643,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004922174475370352,
|
|
"loss": 4.904,
|
|
"mean_token_accuracy": 0.2034693494439125,
|
|
"num_tokens": 22273438.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.172707223892212,
|
|
"epoch": 0.9493746277546159,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004922063331105907,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.20446984171867372,
|
|
"num_tokens": 22285824.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.055586528778076,
|
|
"epoch": 0.9499702203692674,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004921952108933083,
|
|
"loss": 4.842,
|
|
"mean_token_accuracy": 0.20966906398534774,
|
|
"num_tokens": 22299345.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.130138111114502,
|
|
"epoch": 0.950565812983919,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004921840808855865,
|
|
"loss": 4.8369,
|
|
"mean_token_accuracy": 0.2015565201640129,
|
|
"num_tokens": 22313684.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.178604507446289,
|
|
"epoch": 0.9511614055985705,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004921729430878252,
|
|
"loss": 4.9239,
|
|
"mean_token_accuracy": 0.20589034408330917,
|
|
"num_tokens": 22327474.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.164416885375976,
|
|
"epoch": 0.9517569982132221,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004921617975004233,
|
|
"loss": 4.9617,
|
|
"mean_token_accuracy": 0.19927801787853242,
|
|
"num_tokens": 22343026.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.142657518386841,
|
|
"epoch": 0.9523525908278737,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004921506441237809,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.2055016949772835,
|
|
"num_tokens": 22358734.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.155494213104248,
|
|
"epoch": 0.9529481834425253,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004921394829582979,
|
|
"loss": 4.8611,
|
|
"mean_token_accuracy": 0.20359614491462708,
|
|
"num_tokens": 22371840.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.081371641159057,
|
|
"epoch": 0.9535437760571769,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921283140043748,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.2150975614786148,
|
|
"num_tokens": 22384450.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.0925039768219,
|
|
"epoch": 0.9541393686718285,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004921171372624121,
|
|
"loss": 4.8687,
|
|
"mean_token_accuracy": 0.20968499034643173,
|
|
"num_tokens": 22398988.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.09598298072815,
|
|
"epoch": 0.95473496128648,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004921059527328106,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.21253437995910646,
|
|
"num_tokens": 22411703.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.245681476593018,
|
|
"epoch": 0.9553305539011316,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004920947604159716,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.19802498668432236,
|
|
"num_tokens": 22427229.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.117247438430786,
|
|
"epoch": 0.9559261465157832,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004920835603122965,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.20804524123668672,
|
|
"num_tokens": 22439357.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.117840576171875,
|
|
"epoch": 0.9565217391304348,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004920723524221871,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.19851011633872986,
|
|
"num_tokens": 22453214.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.1265171527862545,
|
|
"epoch": 0.9571173317450864,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004920611367460453,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.20378010272979735,
|
|
"num_tokens": 22468030.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.207348346710205,
|
|
"epoch": 0.957712924359738,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004920499132842734,
|
|
"loss": 4.8642,
|
|
"mean_token_accuracy": 0.20335048139095308,
|
|
"num_tokens": 22481975.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.176688098907471,
|
|
"epoch": 0.9583085169743896,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004920386820372741,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.20494133681058885,
|
|
"num_tokens": 22495047.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.18166151046753,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004920274430054502,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.20546743720769883,
|
|
"num_tokens": 22509310.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.157048559188842,
|
|
"epoch": 0.9594997022036926,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004920161961892047,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.20335931777954103,
|
|
"num_tokens": 22525220.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.07274899482727,
|
|
"epoch": 0.9600952948183442,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004920049415889411,
|
|
"loss": 4.8186,
|
|
"mean_token_accuracy": 0.2204504758119583,
|
|
"num_tokens": 22538123.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.133922576904297,
|
|
"epoch": 0.9606908874329958,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004919936792050631,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.2025282561779022,
|
|
"num_tokens": 22552229.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.155880308151245,
|
|
"epoch": 0.9612864800476474,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004919824090379747,
|
|
"loss": 4.8679,
|
|
"mean_token_accuracy": 0.20475835353136063,
|
|
"num_tokens": 22566398.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.129514503479004,
|
|
"epoch": 0.961882072662299,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049197113108808,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.20763185024261474,
|
|
"num_tokens": 22579736.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.047914457321167,
|
|
"epoch": 0.9624776652769506,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004919598453557836,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.2150944247841835,
|
|
"num_tokens": 22593325.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.1221473693847654,
|
|
"epoch": 0.9630732578916021,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004919485518414902,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.19957116693258287,
|
|
"num_tokens": 22607306.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.134184122085571,
|
|
"epoch": 0.9636688505062537,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004919372505456051,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.2082940384745598,
|
|
"num_tokens": 22620504.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.179799795150757,
|
|
"epoch": 0.9642644431209053,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004919259414685336,
|
|
"loss": 4.953,
|
|
"mean_token_accuracy": 0.1983841598033905,
|
|
"num_tokens": 22634097.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.225040245056152,
|
|
"epoch": 0.9648600357355569,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004919146246106812,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.1978405937552452,
|
|
"num_tokens": 22648457.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.166402196884155,
|
|
"epoch": 0.9654556283502085,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004919032999724539,
|
|
"loss": 4.8683,
|
|
"mean_token_accuracy": 0.20020982176065444,
|
|
"num_tokens": 22662128.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.058289861679077,
|
|
"epoch": 0.9660512209648601,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004918919675542579,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.2175946354866028,
|
|
"num_tokens": 22676085.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.160419607162476,
|
|
"epoch": 0.9666468135795117,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004918806273564996,
|
|
"loss": 4.8798,
|
|
"mean_token_accuracy": 0.20911625921726226,
|
|
"num_tokens": 22689672.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.180479860305786,
|
|
"epoch": 0.9672424061941632,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000491869279379586,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.2053300827741623,
|
|
"num_tokens": 22705240.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.123101758956909,
|
|
"epoch": 0.9678379988088148,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004918579236239238,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.20302197337150574,
|
|
"num_tokens": 22718532.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.135009717941284,
|
|
"epoch": 0.9684335914234663,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004918465600899205,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.19907732158899308,
|
|
"num_tokens": 22732146.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.144668054580689,
|
|
"epoch": 0.9690291840381179,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004918351887779837,
|
|
"loss": 4.8578,
|
|
"mean_token_accuracy": 0.20739332735538482,
|
|
"num_tokens": 22744590.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.146660947799683,
|
|
"epoch": 0.9696247766527695,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004918238096885213,
|
|
"loss": 4.8633,
|
|
"mean_token_accuracy": 0.202810201048851,
|
|
"num_tokens": 22758607.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.029603433609009,
|
|
"epoch": 0.9702203692674211,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004918124228219412,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.2115254133939743,
|
|
"num_tokens": 22771846.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.116102170944214,
|
|
"epoch": 0.9708159618820726,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004918010281786522,
|
|
"loss": 4.8221,
|
|
"mean_token_accuracy": 0.20801041275262833,
|
|
"num_tokens": 22784705.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.122978067398071,
|
|
"epoch": 0.9714115544967242,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004917896257590627,
|
|
"loss": 4.8673,
|
|
"mean_token_accuracy": 0.2069874107837677,
|
|
"num_tokens": 22799706.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.126592493057251,
|
|
"epoch": 0.9720071471113758,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004917782155635817,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.2016233429312706,
|
|
"num_tokens": 22813021.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.1057013988494875,
|
|
"epoch": 0.9726027397260274,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004917667975926187,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.20625873059034347,
|
|
"num_tokens": 22827936.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.189203834533691,
|
|
"epoch": 0.973198332340679,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004917553718465832,
|
|
"loss": 4.8969,
|
|
"mean_token_accuracy": 0.20302240252494813,
|
|
"num_tokens": 22842307.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.111174297332764,
|
|
"epoch": 0.9737939249553306,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004917439383258848,
|
|
"loss": 4.8336,
|
|
"mean_token_accuracy": 0.21007844060659409,
|
|
"num_tokens": 22856137.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.128695058822632,
|
|
"epoch": 0.9743895175699822,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004917324970309337,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.20106206834316254,
|
|
"num_tokens": 22870705.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.161596870422363,
|
|
"epoch": 0.9749851101846337,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004917210479621404,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.1973010390996933,
|
|
"num_tokens": 22883860.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.132380485534668,
|
|
"epoch": 0.9755807027992853,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004917095911199155,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.2078588053584099,
|
|
"num_tokens": 22897233.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.1388849258422855,
|
|
"epoch": 0.9761762954139369,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049169812650467,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.1961691215634346,
|
|
"num_tokens": 22911931.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.113099384307861,
|
|
"epoch": 0.9767718880285885,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004916866541168148,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.20882253646850585,
|
|
"num_tokens": 22925615.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.109107494354248,
|
|
"epoch": 0.97736748064324,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004916751739567617,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.20995472818613053,
|
|
"num_tokens": 22939178.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.167370891571045,
|
|
"epoch": 0.9779630732578916,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004916636860249225,
|
|
"loss": 4.9015,
|
|
"mean_token_accuracy": 0.20654659122228622,
|
|
"num_tokens": 22954681.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.1004133224487305,
|
|
"epoch": 0.9785586658725431,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000491652190321709,
|
|
"loss": 4.7839,
|
|
"mean_token_accuracy": 0.2092840313911438,
|
|
"num_tokens": 22965843.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.11631932258606,
|
|
"epoch": 0.9791542584871947,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004916406868475338,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.20195459425449372,
|
|
"num_tokens": 22980695.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.159639692306518,
|
|
"epoch": 0.9797498511018463,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004916291756028094,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.2037738159298897,
|
|
"num_tokens": 22994146.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.065694284439087,
|
|
"epoch": 0.9803454437164979,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004916176565879487,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.20535910427570342,
|
|
"num_tokens": 23008397.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.104378747940063,
|
|
"epoch": 0.9809410363311495,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004916061298033648,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.21251035779714583,
|
|
"num_tokens": 23020693.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.139512634277343,
|
|
"epoch": 0.9815366289458011,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004915945952494713,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.20690144449472428,
|
|
"num_tokens": 23035444.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.13489146232605,
|
|
"epoch": 0.9821322215604527,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004915830529266818,
|
|
"loss": 4.8788,
|
|
"mean_token_accuracy": 0.20919089913368225,
|
|
"num_tokens": 23050185.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.118703842163086,
|
|
"epoch": 0.9827278141751042,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004915715028354102,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.21309648752212523,
|
|
"num_tokens": 23063588.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.081256580352783,
|
|
"epoch": 0.9833234067897558,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004915599449760711,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.21496672183275223,
|
|
"num_tokens": 23076581.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.134102869033813,
|
|
"epoch": 0.9839189994044074,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004915483793490788,
|
|
"loss": 4.8978,
|
|
"mean_token_accuracy": 0.19896964132785797,
|
|
"num_tokens": 23089583.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.268817901611328,
|
|
"epoch": 0.984514592019059,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004915368059548482,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.18863581418991088,
|
|
"num_tokens": 23103029.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.165845680236816,
|
|
"epoch": 0.9851101846337106,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004915252247937944,
|
|
"loss": 4.9994,
|
|
"mean_token_accuracy": 0.19887207597494125,
|
|
"num_tokens": 23119056.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.160630369186402,
|
|
"epoch": 0.9857057772483622,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000491513635866333,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.20203275233507156,
|
|
"num_tokens": 23132774.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.123512697219849,
|
|
"epoch": 0.9863013698630136,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004915020391728792,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.20866781920194627,
|
|
"num_tokens": 23147666.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.130696058273315,
|
|
"epoch": 0.9868969624776652,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004914904347138495,
|
|
"loss": 4.8707,
|
|
"mean_token_accuracy": 0.2131431892514229,
|
|
"num_tokens": 23161868.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.119625759124756,
|
|
"epoch": 0.9874925550923168,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004914788224896599,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.20434631407260895,
|
|
"num_tokens": 23174938.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.086147308349609,
|
|
"epoch": 0.9880881477069684,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004914672025007269,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.1998431444168091,
|
|
"num_tokens": 23189294.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.2044493675231935,
|
|
"epoch": 0.98868374032162,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004914555747474673,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.20362543016672136,
|
|
"num_tokens": 23202715.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.083755111694336,
|
|
"epoch": 0.9892793329362716,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004914439392302981,
|
|
"loss": 4.8247,
|
|
"mean_token_accuracy": 0.2105051040649414,
|
|
"num_tokens": 23216216.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.126770877838135,
|
|
"epoch": 0.9898749255509232,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004914322959496367,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.2100026935338974,
|
|
"num_tokens": 23228795.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.1669329643249515,
|
|
"epoch": 0.9904705181655747,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004914206449059008,
|
|
"loss": 4.9147,
|
|
"mean_token_accuracy": 0.2001165747642517,
|
|
"num_tokens": 23244288.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.147449636459351,
|
|
"epoch": 0.9910661107802263,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004914089860995084,
|
|
"loss": 4.9221,
|
|
"mean_token_accuracy": 0.2072264313697815,
|
|
"num_tokens": 23259067.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.135837841033935,
|
|
"epoch": 0.9916617033948779,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004913973195308772,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.20832079648971558,
|
|
"num_tokens": 23270939.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.059817123413086,
|
|
"epoch": 0.9922572960095295,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004913856452004262,
|
|
"loss": 4.8096,
|
|
"mean_token_accuracy": 0.20970795303583145,
|
|
"num_tokens": 23285309.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.160462188720703,
|
|
"epoch": 0.9928528886241811,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004913739631085739,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.20631538480520248,
|
|
"num_tokens": 23299609.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.094571685791015,
|
|
"epoch": 0.9934484812388327,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004913622732557394,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.21267436891794206,
|
|
"num_tokens": 23312817.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.113551807403565,
|
|
"epoch": 0.9940440738534843,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004913505756423418,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.21212999969720842,
|
|
"num_tokens": 23324944.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.006036424636841,
|
|
"epoch": 0.9946396664681358,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004913388702688009,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.21768101006746293,
|
|
"num_tokens": 23338200.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.131504487991333,
|
|
"epoch": 0.9952352590827874,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004913271571355365,
|
|
"loss": 4.8458,
|
|
"mean_token_accuracy": 0.20577962845563888,
|
|
"num_tokens": 23352009.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.2044923305511475,
|
|
"epoch": 0.9958308516974389,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004913154362429686,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.19077352583408355,
|
|
"num_tokens": 23366680.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.092619800567627,
|
|
"epoch": 0.9964264443120905,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004913037075915178,
|
|
"loss": 4.881,
|
|
"mean_token_accuracy": 0.2102571740746498,
|
|
"num_tokens": 23379900.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.131239032745361,
|
|
"epoch": 0.9970220369267421,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004912919711816047,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.21425295025110244,
|
|
"num_tokens": 23393366.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.125626516342163,
|
|
"epoch": 0.9976176295413937,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004912802270136503,
|
|
"loss": 4.8694,
|
|
"mean_token_accuracy": 0.20147457867860794,
|
|
"num_tokens": 23407272.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.044153785705566,
|
|
"epoch": 0.9982132221560452,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004912684750880757,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.20625961869955062,
|
|
"num_tokens": 23421167.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.137872552871704,
|
|
"epoch": 0.9988088147706968,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004912567154053025,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.20144322514533997,
|
|
"num_tokens": 23434264.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.187752103805542,
|
|
"epoch": 0.9994044073853484,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004912449479657526,
|
|
"loss": 4.8808,
|
|
"mean_token_accuracy": 0.2050936073064804,
|
|
"num_tokens": 23448000.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.176060676574707,
|
|
"epoch": 1.0,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004912331727698481,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.20628693848848342,
|
|
"num_tokens": 23461012.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.136442565917969,
|
|
"epoch": 1.0005955926146515,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004912213898180111,
|
|
"loss": 4.8779,
|
|
"mean_token_accuracy": 0.19998240768909453,
|
|
"num_tokens": 23473230.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.196777248382569,
|
|
"epoch": 1.0011911852293032,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004912095991106644,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.19686558842658997,
|
|
"num_tokens": 23488201.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.2483603954315186,
|
|
"epoch": 1.0017867778439546,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004911978006482311,
|
|
"loss": 4.8322,
|
|
"mean_token_accuracy": 0.2002608746290207,
|
|
"num_tokens": 23505057.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.18873085975647,
|
|
"epoch": 1.0023823704586063,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004911859944311341,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.20979276448488235,
|
|
"num_tokens": 23518061.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.1693449974060055,
|
|
"epoch": 1.0029779630732578,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000491174180459797,
|
|
"loss": 4.9102,
|
|
"mean_token_accuracy": 0.20113812386989594,
|
|
"num_tokens": 23532902.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.0985006332397464,
|
|
"epoch": 1.0035735556879095,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004911623587346434,
|
|
"loss": 4.7026,
|
|
"mean_token_accuracy": 0.21948463171720506,
|
|
"num_tokens": 23546329.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.202975654602051,
|
|
"epoch": 1.004169148302561,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004911505292560977,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.2042056515812874,
|
|
"num_tokens": 23562153.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.127773714065552,
|
|
"epoch": 1.0047647409172127,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004911386920245837,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.21222690641880035,
|
|
"num_tokens": 23576582.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.145722198486328,
|
|
"epoch": 1.0053603335318642,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004911268470405263,
|
|
"loss": 4.8264,
|
|
"mean_token_accuracy": 0.2075497955083847,
|
|
"num_tokens": 23591007.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.112020635604859,
|
|
"epoch": 1.0059559261465159,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004911149943043504,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.21815158277750016,
|
|
"num_tokens": 23605269.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.169770574569702,
|
|
"epoch": 1.0065515187611673,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000491103133816481,
|
|
"loss": 4.8961,
|
|
"mean_token_accuracy": 0.20218004286289215,
|
|
"num_tokens": 23622448.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.049387502670288,
|
|
"epoch": 1.007147111375819,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004910912655773436,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.21600185036659242,
|
|
"num_tokens": 23636573.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.104780435562134,
|
|
"epoch": 1.0077427039904705,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004910793895873637,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.21923694014549255,
|
|
"num_tokens": 23649542.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.0665326595306395,
|
|
"epoch": 1.0083382966051222,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910675058469675,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.2127515360713005,
|
|
"num_tokens": 23662270.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.177072906494141,
|
|
"epoch": 1.0089338892197737,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910556143565812,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.20002064406871795,
|
|
"num_tokens": 23675998.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.239354801177979,
|
|
"epoch": 1.0095294818344251,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004910437151166312,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.20879549086093901,
|
|
"num_tokens": 23691511.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.056886911392212,
|
|
"epoch": 1.0101250744490768,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004910318081275445,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.2206580385565758,
|
|
"num_tokens": 23705412.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.0839372158050535,
|
|
"epoch": 1.0107206670637283,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000491019893389748,
|
|
"loss": 4.7691,
|
|
"mean_token_accuracy": 0.21029432117938995,
|
|
"num_tokens": 23721303.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.132709980010986,
|
|
"epoch": 1.01131625967838,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004910079709036692,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.21426697373390197,
|
|
"num_tokens": 23735018.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.1665081024169925,
|
|
"epoch": 1.0119118522930315,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004909960406697358,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.21062742322683334,
|
|
"num_tokens": 23747262.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.083658170700073,
|
|
"epoch": 1.0125074449076832,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004909841026883755,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.2109810918569565,
|
|
"num_tokens": 23761195.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.147108125686645,
|
|
"epoch": 1.0131030375223347,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004909721569600166,
|
|
"loss": 4.793,
|
|
"mean_token_accuracy": 0.20104781836271285,
|
|
"num_tokens": 23775789.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.071705007553101,
|
|
"epoch": 1.0136986301369864,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004909602034850875,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.22341578006744384,
|
|
"num_tokens": 23788554.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.045306825637818,
|
|
"epoch": 1.0142942227516378,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004909482422640172,
|
|
"loss": 4.793,
|
|
"mean_token_accuracy": 0.21022316962480544,
|
|
"num_tokens": 23802033.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.190822792053223,
|
|
"epoch": 1.0148898153662895,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004909362732972344,
|
|
"loss": 4.9159,
|
|
"mean_token_accuracy": 0.20383305996656417,
|
|
"num_tokens": 23819250.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.173139476776123,
|
|
"epoch": 1.015485407980941,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004909242965851688,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.20450522303581237,
|
|
"num_tokens": 23833917.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.130035924911499,
|
|
"epoch": 1.0160810005955927,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004909123121282495,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.21165162920951844,
|
|
"num_tokens": 23848177.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.075819587707519,
|
|
"epoch": 1.0166765932102442,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004909003199269068,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.206368350982666,
|
|
"num_tokens": 23861640.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.028302574157715,
|
|
"epoch": 1.0172721858248959,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004908883199815705,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.21404478549957276,
|
|
"num_tokens": 23875580.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.060949516296387,
|
|
"epoch": 1.0178677784395473,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004908763122926712,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.2120327189564705,
|
|
"num_tokens": 23887977.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.111125946044922,
|
|
"epoch": 1.018463371054199,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004908642968606396,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.2047650471329689,
|
|
"num_tokens": 23902079.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.148727893829346,
|
|
"epoch": 1.0190589636688505,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004908522736859068,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.20443788468837737,
|
|
"num_tokens": 23915468.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.084004306793213,
|
|
"epoch": 1.019654556283502,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004908402427689037,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.21450404077768326,
|
|
"num_tokens": 23932059.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.154594373703003,
|
|
"epoch": 1.0202501488981537,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004908282041100621,
|
|
"loss": 4.8339,
|
|
"mean_token_accuracy": 0.21192444413900374,
|
|
"num_tokens": 23946730.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.221394634246826,
|
|
"epoch": 1.0208457415128052,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004908161577098137,
|
|
"loss": 4.9405,
|
|
"mean_token_accuracy": 0.19017888009548187,
|
|
"num_tokens": 23961298.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.122244834899902,
|
|
"epoch": 1.0214413341274569,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004908041035685907,
|
|
"loss": 4.7668,
|
|
"mean_token_accuracy": 0.2048646926879883,
|
|
"num_tokens": 23975419.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.101758432388306,
|
|
"epoch": 1.0220369267421083,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004907920416868253,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.20534600764513017,
|
|
"num_tokens": 23989563.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.196707487106323,
|
|
"epoch": 1.02263251935676,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004907799720649502,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.20685559809207915,
|
|
"num_tokens": 24004961.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.099379158020019,
|
|
"epoch": 1.0232281119714115,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004907678947033984,
|
|
"loss": 4.777,
|
|
"mean_token_accuracy": 0.21603196412324904,
|
|
"num_tokens": 24019636.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.13806004524231,
|
|
"epoch": 1.0238237045860632,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004907558096026031,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.2161066710948944,
|
|
"num_tokens": 24031406.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.081039619445801,
|
|
"epoch": 1.0244192972007147,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004907437167629976,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.21254531145095826,
|
|
"num_tokens": 24045468.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.0566709518432615,
|
|
"epoch": 1.0250148898153664,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004907316161850158,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.2081230953335762,
|
|
"num_tokens": 24059712.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.160747051239014,
|
|
"epoch": 1.0256104824300178,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004907195078690916,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.20502697229385375,
|
|
"num_tokens": 24073549.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.107241868972778,
|
|
"epoch": 1.0262060750446695,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004907073918156595,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.21136015951633452,
|
|
"num_tokens": 24085770.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.1574255466461185,
|
|
"epoch": 1.026801667659321,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004906952680251539,
|
|
"loss": 4.8843,
|
|
"mean_token_accuracy": 0.20026927590370178,
|
|
"num_tokens": 24102289.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.068690490722656,
|
|
"epoch": 1.0273972602739727,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004906831364980098,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.21471716463565826,
|
|
"num_tokens": 24116075.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.176452159881592,
|
|
"epoch": 1.0279928528886242,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004906709972346623,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.20752755850553511,
|
|
"num_tokens": 24129599.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.0878197193145756,
|
|
"epoch": 1.0285884455032757,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004906588502355467,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.20653905868530273,
|
|
"num_tokens": 24143322.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.135210084915161,
|
|
"epoch": 1.0291840381179274,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004906466955010988,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.2158731311559677,
|
|
"num_tokens": 24157431.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.102326107025147,
|
|
"epoch": 1.0297796307325788,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004906345330317546,
|
|
"loss": 4.7528,
|
|
"mean_token_accuracy": 0.20844392478466034,
|
|
"num_tokens": 24172228.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.03387336730957,
|
|
"epoch": 1.0303752233472305,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004906223628279502,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.2141445979475975,
|
|
"num_tokens": 24184436.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.079369831085205,
|
|
"epoch": 1.030970815961882,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004906101848901224,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.215261110663414,
|
|
"num_tokens": 24197765.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.0715752124786375,
|
|
"epoch": 1.0315664085765337,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004905979992187076,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.21235434710979462,
|
|
"num_tokens": 24211336.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.1120506763458256,
|
|
"epoch": 1.0321620011911852,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004905858058141433,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.2026548907160759,
|
|
"num_tokens": 24226027.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.015224599838257,
|
|
"epoch": 1.0327575938058369,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004905736046768665,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.21744753867387773,
|
|
"num_tokens": 24240108.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.1732035160064695,
|
|
"epoch": 1.0333531864204883,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004905613958073151,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.20300986915826796,
|
|
"num_tokens": 24253664.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.136033725738526,
|
|
"epoch": 1.03394877903514,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000490549179205927,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.2148702085018158,
|
|
"num_tokens": 24268958.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.108251571655273,
|
|
"epoch": 1.0345443716497915,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004905369548731402,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.20090168714523315,
|
|
"num_tokens": 24283750.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.1481507301330565,
|
|
"epoch": 1.0351399642644432,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004905247228093933,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.2041677102446556,
|
|
"num_tokens": 24298316.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.061338472366333,
|
|
"epoch": 1.0357355568790947,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000490512483015125,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.21628960072994233,
|
|
"num_tokens": 24311113.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.122244119644165,
|
|
"epoch": 1.0363311494937464,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004905002354907743,
|
|
"loss": 4.7637,
|
|
"mean_token_accuracy": 0.21095712184906007,
|
|
"num_tokens": 24326579.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.1031396865844725,
|
|
"epoch": 1.0369267421083979,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004904879802367806,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.20412065386772155,
|
|
"num_tokens": 24339208.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.142496633529663,
|
|
"epoch": 1.0375223347230493,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004904757172535833,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.20668528825044633,
|
|
"num_tokens": 24351659.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.132928514480591,
|
|
"epoch": 1.038117927337701,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004904634465416226,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.20869979560375213,
|
|
"num_tokens": 24365646.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.136101913452149,
|
|
"epoch": 1.0387135199523525,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004904511681013382,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.20708570033311843,
|
|
"num_tokens": 24379577.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.10656247138977,
|
|
"epoch": 1.0393091125670042,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004904388819331707,
|
|
"loss": 4.8005,
|
|
"mean_token_accuracy": 0.20908545702695847,
|
|
"num_tokens": 24394441.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.127030324935913,
|
|
"epoch": 1.0399047051816557,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004904265880375609,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.2126027375459671,
|
|
"num_tokens": 24408443.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.16377272605896,
|
|
"epoch": 1.0405002977963074,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004904142864149496,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.20641391724348068,
|
|
"num_tokens": 24423416.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.150284957885742,
|
|
"epoch": 1.0410958904109588,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000490401977065778,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.20657679289579392,
|
|
"num_tokens": 24436205.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.117693090438843,
|
|
"epoch": 1.0416914830256105,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004903896599904878,
|
|
"loss": 4.8211,
|
|
"mean_token_accuracy": 0.20828820019960403,
|
|
"num_tokens": 24449472.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.11019115447998,
|
|
"epoch": 1.042287075640262,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004903773351895206,
|
|
"loss": 4.7158,
|
|
"mean_token_accuracy": 0.21656163781881332,
|
|
"num_tokens": 24462861.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.159122896194458,
|
|
"epoch": 1.0428826682549137,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004903650026633187,
|
|
"loss": 4.7406,
|
|
"mean_token_accuracy": 0.2265960916876793,
|
|
"num_tokens": 24474981.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.013250160217285,
|
|
"epoch": 1.0434782608695652,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004903526624123243,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.2172481581568718,
|
|
"num_tokens": 24489283.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 4.992848253250122,
|
|
"epoch": 1.0440738534842169,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049034031443698,
|
|
"loss": 4.6102,
|
|
"mean_token_accuracy": 0.21873778551816941,
|
|
"num_tokens": 24501859.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.111286783218384,
|
|
"epoch": 1.0446694460988684,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004903279587377287,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.21076543927192687,
|
|
"num_tokens": 24515586.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.184897136688233,
|
|
"epoch": 1.04526503871352,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004903155953150137,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.2028117746114731,
|
|
"num_tokens": 24531912.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.096513748168945,
|
|
"epoch": 1.0458606313281715,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004903032241692784,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.2122521474957466,
|
|
"num_tokens": 24544958.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.0598982810974125,
|
|
"epoch": 1.046456223942823,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004902908453009664,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.21561241894960403,
|
|
"num_tokens": 24556979.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.1843681812286375,
|
|
"epoch": 1.0470518165574747,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004902784587105218,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.19415746927261351,
|
|
"num_tokens": 24571299.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.15225658416748,
|
|
"epoch": 1.0476474091721262,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000490266064398389,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.21171940714120865,
|
|
"num_tokens": 24584292.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.116628789901734,
|
|
"epoch": 1.0482430017867779,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004902536623650125,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.2082578495144844,
|
|
"num_tokens": 24597245.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.028639030456543,
|
|
"epoch": 1.0488385944014293,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004902412526108371,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.2315194234251976,
|
|
"num_tokens": 24610388.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.1403624534606935,
|
|
"epoch": 1.049434187016081,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004902288351363079,
|
|
"loss": 4.8755,
|
|
"mean_token_accuracy": 0.20016805082559586,
|
|
"num_tokens": 24625939.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.107317781448364,
|
|
"epoch": 1.0500297796307325,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004902164099418703,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.21651236414909364,
|
|
"num_tokens": 24641133.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.06811752319336,
|
|
"epoch": 1.0506253722453842,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049020397702797,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.21243818253278732,
|
|
"num_tokens": 24654555.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.052727460861206,
|
|
"epoch": 1.0512209648600357,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000490191536395053,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.21332450658082963,
|
|
"num_tokens": 24669048.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.093867206573487,
|
|
"epoch": 1.0518165574746874,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004901790880435655,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.21727802306413652,
|
|
"num_tokens": 24683420.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.135576963424683,
|
|
"epoch": 1.0524121500893389,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004901666319739537,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.20144369453191757,
|
|
"num_tokens": 24696972.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.051600551605224,
|
|
"epoch": 1.0530077427039906,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004901541681866649,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.21089925169944762,
|
|
"num_tokens": 24710581.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.040735054016113,
|
|
"epoch": 1.053603335318642,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004901416966821459,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.21958364844322203,
|
|
"num_tokens": 24723055.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.122497463226319,
|
|
"epoch": 1.0541989279332937,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000490129217460844,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.20972866266965867,
|
|
"num_tokens": 24738073.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.167162179946899,
|
|
"epoch": 1.0547945205479452,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004901167305232068,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.20195484310388565,
|
|
"num_tokens": 24751566.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.096008682250977,
|
|
"epoch": 1.0553901131625967,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004901042358696823,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.21978194266557693,
|
|
"num_tokens": 24765401.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.0686338424682615,
|
|
"epoch": 1.0559857057772484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004900917335007186,
|
|
"loss": 4.7726,
|
|
"mean_token_accuracy": 0.21189576983451844,
|
|
"num_tokens": 24779180.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.101472282409668,
|
|
"epoch": 1.0565812983918998,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004900792234167642,
|
|
"loss": 4.8036,
|
|
"mean_token_accuracy": 0.209900926053524,
|
|
"num_tokens": 24794536.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.10550217628479,
|
|
"epoch": 1.0571768910065515,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004900667056182676,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.20769141167402266,
|
|
"num_tokens": 24809721.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.126291131973266,
|
|
"epoch": 1.057772483621203,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004900541801056781,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.2109765186905861,
|
|
"num_tokens": 24823818.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.074911451339721,
|
|
"epoch": 1.0583680762358547,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004900416468794446,
|
|
"loss": 4.7038,
|
|
"mean_token_accuracy": 0.2215084806084633,
|
|
"num_tokens": 24836028.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.013275241851806,
|
|
"epoch": 1.0589636688505062,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004900291059400171,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.21286247968673705,
|
|
"num_tokens": 24849957.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.105123472213745,
|
|
"epoch": 1.0595592614651579,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000490016557287845,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.20392756015062333,
|
|
"num_tokens": 24862123.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.106251287460327,
|
|
"epoch": 1.0601548540798094,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004900040009233787,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.2094264566898346,
|
|
"num_tokens": 24874584.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.149079942703247,
|
|
"epoch": 1.060750446694461,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004899914368470685,
|
|
"loss": 4.9068,
|
|
"mean_token_accuracy": 0.19997520595788956,
|
|
"num_tokens": 24890828.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.157776117324829,
|
|
"epoch": 1.0613460393091125,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004899788650593648,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.20981544405221939,
|
|
"num_tokens": 24905266.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.11357684135437,
|
|
"epoch": 1.0619416319237642,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004899662855607189,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.2110016778111458,
|
|
"num_tokens": 24918867.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.092357587814331,
|
|
"epoch": 1.0625372245384157,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004899536983515819,
|
|
"loss": 4.8159,
|
|
"mean_token_accuracy": 0.20619207620620728,
|
|
"num_tokens": 24934619.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.215360403060913,
|
|
"epoch": 1.0631328171530674,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004899411034324051,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.20198035538196563,
|
|
"num_tokens": 24950582.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.125244855880737,
|
|
"epoch": 1.0637284097677189,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004899285008036406,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.21074910312891007,
|
|
"num_tokens": 24964456.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.06676607131958,
|
|
"epoch": 1.0643240023823703,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048991589046574,
|
|
"loss": 4.7576,
|
|
"mean_token_accuracy": 0.2130242884159088,
|
|
"num_tokens": 24977443.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.02127513885498,
|
|
"epoch": 1.064919594997022,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004899032724191559,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.22398424446582793,
|
|
"num_tokens": 24989343.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.111344814300537,
|
|
"epoch": 1.0655151876116735,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004898906466643409,
|
|
"loss": 4.7735,
|
|
"mean_token_accuracy": 0.21355585008859634,
|
|
"num_tokens": 25004157.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.064301013946533,
|
|
"epoch": 1.0661107802263252,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004898780132017478,
|
|
"loss": 4.8192,
|
|
"mean_token_accuracy": 0.21036376804113388,
|
|
"num_tokens": 25016292.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.152235889434815,
|
|
"epoch": 1.0667063728409767,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004898653720318296,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.20676702558994292,
|
|
"num_tokens": 25032374.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.166051387786865,
|
|
"epoch": 1.0673019654556284,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048985272315504,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.2134851947426796,
|
|
"num_tokens": 25045290.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.051154327392578,
|
|
"epoch": 1.0678975580702799,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004898400665718325,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.2064426764845848,
|
|
"num_tokens": 25058733.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.032707357406617,
|
|
"epoch": 1.0684931506849316,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004898274022826611,
|
|
"loss": 4.7259,
|
|
"mean_token_accuracy": 0.21326858550310135,
|
|
"num_tokens": 25073274.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.131275701522827,
|
|
"epoch": 1.069088743299583,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004898147302879801,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.2084283709526062,
|
|
"num_tokens": 25088339.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.095667552947998,
|
|
"epoch": 1.0696843359142347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004898020505882441,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.22387228310108184,
|
|
"num_tokens": 25100031.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.162352228164673,
|
|
"epoch": 1.0702799285288862,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004897893631839076,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.19989098757505416,
|
|
"num_tokens": 25113070.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.144609689712524,
|
|
"epoch": 1.070875521143538,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000489776668075426,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.21411727517843246,
|
|
"num_tokens": 25126584.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.128993177413941,
|
|
"epoch": 1.0714711137581894,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004897639652632544,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.21786815971136092,
|
|
"num_tokens": 25139292.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.044837617874146,
|
|
"epoch": 1.072066706372841,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004897512547478487,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.20518420189619063,
|
|
"num_tokens": 25153590.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.072066706372841,
|
|
"eval_entropy": 4.851628258833691,
|
|
"eval_loss": 4.820348739624023,
|
|
"eval_mean_token_accuracy": 0.21951477543266962,
|
|
"eval_num_tokens": 25153590.0,
|
|
"eval_runtime": 18.511,
|
|
"eval_samples_per_second": 1378.263,
|
|
"eval_steps_per_second": 172.33,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.150787353515625,
|
|
"epoch": 1.0726622989874925,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004897385365296645,
|
|
"loss": 4.8445,
|
|
"mean_token_accuracy": 0.2019414037466049,
|
|
"num_tokens": 25168050.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.112744379043579,
|
|
"epoch": 1.073257891602144,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004897258106091582,
|
|
"loss": 4.7209,
|
|
"mean_token_accuracy": 0.21675765216350557,
|
|
"num_tokens": 25182650.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.072797441482544,
|
|
"epoch": 1.0738534842167957,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004897130769867862,
|
|
"loss": 4.7447,
|
|
"mean_token_accuracy": 0.2143941640853882,
|
|
"num_tokens": 25196264.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.033927631378174,
|
|
"epoch": 1.0744490768314472,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004897003356630052,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.20587211698293686,
|
|
"num_tokens": 25214240.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.183612966537476,
|
|
"epoch": 1.0750446694460989,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004896875866382723,
|
|
"loss": 4.8795,
|
|
"mean_token_accuracy": 0.20107775032520295,
|
|
"num_tokens": 25229866.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.097641801834106,
|
|
"epoch": 1.0756402620607504,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004896748299130447,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.21113065034151077,
|
|
"num_tokens": 25244046.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.129254531860352,
|
|
"epoch": 1.076235854675402,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048966206548778,
|
|
"loss": 4.8145,
|
|
"mean_token_accuracy": 0.2066723495721817,
|
|
"num_tokens": 25261180.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.088765335083008,
|
|
"epoch": 1.0768314472900535,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000489649293362936,
|
|
"loss": 4.7948,
|
|
"mean_token_accuracy": 0.20919542908668518,
|
|
"num_tokens": 25274905.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.054131603240966,
|
|
"epoch": 1.0774270399047052,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004896365135389709,
|
|
"loss": 4.6819,
|
|
"mean_token_accuracy": 0.21914481222629548,
|
|
"num_tokens": 25288236.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.13776273727417,
|
|
"epoch": 1.0780226325193567,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000489623726016343,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.2079479068517685,
|
|
"num_tokens": 25301362.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.213931751251221,
|
|
"epoch": 1.0786182251340084,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000489610930795511,
|
|
"loss": 4.9282,
|
|
"mean_token_accuracy": 0.19422980695962905,
|
|
"num_tokens": 25316951.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.117910242080688,
|
|
"epoch": 1.0792138177486599,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000489598127876934,
|
|
"loss": 4.811,
|
|
"mean_token_accuracy": 0.20939702838659285,
|
|
"num_tokens": 25330417.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.100612449645996,
|
|
"epoch": 1.0798094103633116,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004895853172610709,
|
|
"loss": 4.7636,
|
|
"mean_token_accuracy": 0.223005211353302,
|
|
"num_tokens": 25344857.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.1138448238372805,
|
|
"epoch": 1.080405002977963,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004895724989483814,
|
|
"loss": 4.8088,
|
|
"mean_token_accuracy": 0.2077636331319809,
|
|
"num_tokens": 25359353.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.088219690322876,
|
|
"epoch": 1.0810005955926147,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004895596729393252,
|
|
"loss": 4.7876,
|
|
"mean_token_accuracy": 0.2172169491648674,
|
|
"num_tokens": 25373661.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.052983045578003,
|
|
"epoch": 1.0815961882072662,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004895468392343623,
|
|
"loss": 4.6733,
|
|
"mean_token_accuracy": 0.22543083429336547,
|
|
"num_tokens": 25387384.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.0395337581634525,
|
|
"epoch": 1.0821917808219177,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004895339978339534,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.222732812166214,
|
|
"num_tokens": 25400677.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.097601795196534,
|
|
"epoch": 1.0827873734365694,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004895211487385586,
|
|
"loss": 4.8167,
|
|
"mean_token_accuracy": 0.20086563378572464,
|
|
"num_tokens": 25416345.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.125475835800171,
|
|
"epoch": 1.0833829660512209,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000489508291948639,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.2062401369214058,
|
|
"num_tokens": 25430685.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.138735914230347,
|
|
"epoch": 1.0839785586658726,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004894954274646557,
|
|
"loss": 4.816,
|
|
"mean_token_accuracy": 0.20629726946353913,
|
|
"num_tokens": 25444527.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.164917278289795,
|
|
"epoch": 1.084574151280524,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004894825552870703,
|
|
"loss": 4.8064,
|
|
"mean_token_accuracy": 0.21377422362565995,
|
|
"num_tokens": 25457556.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.086795425415039,
|
|
"epoch": 1.0851697438951757,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004894696754163442,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.20752629935741423,
|
|
"num_tokens": 25471357.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.142022275924683,
|
|
"epoch": 1.0857653365098272,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004894567878529397,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.2090730220079422,
|
|
"num_tokens": 25484443.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.204201698303223,
|
|
"epoch": 1.086360929124479,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004894438925973189,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.2083446517586708,
|
|
"num_tokens": 25497515.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.059213495254516,
|
|
"epoch": 1.0869565217391304,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004894309896499443,
|
|
"loss": 4.7225,
|
|
"mean_token_accuracy": 0.21601756811141967,
|
|
"num_tokens": 25512398.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 4.951541471481323,
|
|
"epoch": 1.087552114353782,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004894180790112787,
|
|
"loss": 4.611,
|
|
"mean_token_accuracy": 0.22743048369884492,
|
|
"num_tokens": 25525339.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.119224691390992,
|
|
"epoch": 1.0881477069684335,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004894051606817851,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.2079568848013878,
|
|
"num_tokens": 25539622.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.212293863296509,
|
|
"epoch": 1.0887432995830852,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004893922346619272,
|
|
"loss": 4.8927,
|
|
"mean_token_accuracy": 0.19685571342706681,
|
|
"num_tokens": 25555066.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.0554829120635985,
|
|
"epoch": 1.0893388921977367,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004893793009521684,
|
|
"loss": 4.7145,
|
|
"mean_token_accuracy": 0.21496761292219163,
|
|
"num_tokens": 25567324.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.043254375457764,
|
|
"epoch": 1.0899344848123884,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004893663595529725,
|
|
"loss": 4.691,
|
|
"mean_token_accuracy": 0.2142171025276184,
|
|
"num_tokens": 25581530.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.11319489479065,
|
|
"epoch": 1.09053007742704,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000489353410464804,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.20157086849212646,
|
|
"num_tokens": 25594769.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.024503326416015,
|
|
"epoch": 1.0911256700416916,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004893404536881271,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.2184139147400856,
|
|
"num_tokens": 25609212.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.122885465621948,
|
|
"epoch": 1.091721262656343,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004893274892234066,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.20177493542432784,
|
|
"num_tokens": 25624203.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.161136198043823,
|
|
"epoch": 1.0923168552709945,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004893145170711075,
|
|
"loss": 4.8546,
|
|
"mean_token_accuracy": 0.2040960118174553,
|
|
"num_tokens": 25639040.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.293997192382813,
|
|
"epoch": 1.0929124478856462,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004893015372316953,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.2030816689133644,
|
|
"num_tokens": 25653145.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.10302619934082,
|
|
"epoch": 1.0935080405002977,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004892885497056353,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.2096012994647026,
|
|
"num_tokens": 25666691.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.053180074691772,
|
|
"epoch": 1.0941036331149494,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004892755544933934,
|
|
"loss": 4.7178,
|
|
"mean_token_accuracy": 0.22108241766691208,
|
|
"num_tokens": 25681140.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.035969305038452,
|
|
"epoch": 1.0946992257296009,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004892625515954357,
|
|
"loss": 4.6706,
|
|
"mean_token_accuracy": 0.22152233123779297,
|
|
"num_tokens": 25695835.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 4.99121413230896,
|
|
"epoch": 1.0952948183442526,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004892495410122288,
|
|
"loss": 4.6428,
|
|
"mean_token_accuracy": 0.22280181795358658,
|
|
"num_tokens": 25710395.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.046789884567261,
|
|
"epoch": 1.095890410958904,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004892365227442392,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.20936286300420762,
|
|
"num_tokens": 25724804.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.139118814468384,
|
|
"epoch": 1.0964860035735557,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004892234967919337,
|
|
"loss": 4.8068,
|
|
"mean_token_accuracy": 0.21011084467172622,
|
|
"num_tokens": 25737025.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.031025648117065,
|
|
"epoch": 1.0970815961882072,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004892104631557797,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.21403830796480178,
|
|
"num_tokens": 25751737.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.078107261657715,
|
|
"epoch": 1.097677188802859,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004891974218362448,
|
|
"loss": 4.702,
|
|
"mean_token_accuracy": 0.21466573029756547,
|
|
"num_tokens": 25764187.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.144401931762696,
|
|
"epoch": 1.0982727814175104,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004891843728337965,
|
|
"loss": 4.8152,
|
|
"mean_token_accuracy": 0.20070611834526061,
|
|
"num_tokens": 25778500.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.1242753028869625,
|
|
"epoch": 1.098868374032162,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004891713161489031,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.2118389919400215,
|
|
"num_tokens": 25791964.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.09406590461731,
|
|
"epoch": 1.0994639666468136,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004891582517820328,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.20781631171703338,
|
|
"num_tokens": 25806730.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.1510004043579105,
|
|
"epoch": 1.1000595592614653,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004891451797336541,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.21274488270282746,
|
|
"num_tokens": 25821507.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.0478301525115965,
|
|
"epoch": 1.1006551518761167,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004891321000042361,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.2124520719051361,
|
|
"num_tokens": 25834710.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.079886960983276,
|
|
"epoch": 1.1012507444907684,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004891190125942478,
|
|
"loss": 4.7642,
|
|
"mean_token_accuracy": 0.20861360132694245,
|
|
"num_tokens": 25849138.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.1300990104675295,
|
|
"epoch": 1.10184633710542,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004891059175041586,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.20795159935951232,
|
|
"num_tokens": 25862026.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.100421905517578,
|
|
"epoch": 1.1024419297200714,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004890928147344383,
|
|
"loss": 4.8009,
|
|
"mean_token_accuracy": 0.20305687934160233,
|
|
"num_tokens": 25875791.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.048101377487183,
|
|
"epoch": 1.103037522334723,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004890797042855569,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.21282497197389602,
|
|
"num_tokens": 25888648.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.061988306045532,
|
|
"epoch": 1.1036331149493745,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004890665861579845,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.20815017372369765,
|
|
"num_tokens": 25902307.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.142223501205445,
|
|
"epoch": 1.1042287075640262,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004890534603521917,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.2077449306845665,
|
|
"num_tokens": 25915401.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.154867649078369,
|
|
"epoch": 1.1048243001786777,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004890403268686494,
|
|
"loss": 4.8344,
|
|
"mean_token_accuracy": 0.20872175693511963,
|
|
"num_tokens": 25929692.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.098754978179931,
|
|
"epoch": 1.1054198927933294,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004890271857078285,
|
|
"loss": 4.8003,
|
|
"mean_token_accuracy": 0.21674443632364274,
|
|
"num_tokens": 25943789.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.138971424102783,
|
|
"epoch": 1.106015485407981,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004890140368702003,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.2042955458164215,
|
|
"num_tokens": 25958662.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.0793139934539795,
|
|
"epoch": 1.1066110780226326,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004890008803562368,
|
|
"loss": 4.7747,
|
|
"mean_token_accuracy": 0.21002264469861984,
|
|
"num_tokens": 25974176.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.073871994018555,
|
|
"epoch": 1.107206670637284,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.21886782646179198,
|
|
"num_tokens": 25988513.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.116059017181397,
|
|
"epoch": 1.1078022632519358,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004889745443011909,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.21425316631793975,
|
|
"num_tokens": 26002117.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.101800870895386,
|
|
"epoch": 1.1083978558665872,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004889613647610532,
|
|
"loss": 4.7558,
|
|
"mean_token_accuracy": 0.21742239147424697,
|
|
"num_tokens": 26016092.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.077026224136352,
|
|
"epoch": 1.108993448481239,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004889481775464692,
|
|
"loss": 4.692,
|
|
"mean_token_accuracy": 0.21357480585575103,
|
|
"num_tokens": 26030237.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.047873210906983,
|
|
"epoch": 1.1095890410958904,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000488934982657912,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.21745862513780595,
|
|
"num_tokens": 26041848.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.044446229934692,
|
|
"epoch": 1.110184633710542,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004889217800958548,
|
|
"loss": 4.7614,
|
|
"mean_token_accuracy": 0.2175893023610115,
|
|
"num_tokens": 26056123.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.048743152618409,
|
|
"epoch": 1.1107802263251936,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004889085698607711,
|
|
"loss": 4.7381,
|
|
"mean_token_accuracy": 0.21928799748420716,
|
|
"num_tokens": 26071043.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.024953746795655,
|
|
"epoch": 1.111375818939845,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004888953519531349,
|
|
"loss": 4.6972,
|
|
"mean_token_accuracy": 0.22355735152959824,
|
|
"num_tokens": 26083946.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.03220911026001,
|
|
"epoch": 1.1119714115544967,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048888212637342,
|
|
"loss": 4.7077,
|
|
"mean_token_accuracy": 0.21735489517450332,
|
|
"num_tokens": 26099631.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.024740743637085,
|
|
"epoch": 1.1125670041691482,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004888688931221012,
|
|
"loss": 4.6952,
|
|
"mean_token_accuracy": 0.22479794621467591,
|
|
"num_tokens": 26113613.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.026474285125732,
|
|
"epoch": 1.1131625967838,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004888556521996529,
|
|
"loss": 4.6516,
|
|
"mean_token_accuracy": 0.21775984317064284,
|
|
"num_tokens": 26127357.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.1161237239837645,
|
|
"epoch": 1.1137581893984514,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048884240360655,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.21259021162986755,
|
|
"num_tokens": 26142087.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.065466737747192,
|
|
"epoch": 1.114353782013103,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004888291473432678,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.2144769623875618,
|
|
"num_tokens": 26157153.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.050486898422241,
|
|
"epoch": 1.1149493746277546,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004888158834102816,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.21753180921077728,
|
|
"num_tokens": 26170573.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.013914680480957,
|
|
"epoch": 1.1155449672424063,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004888026118080675,
|
|
"loss": 4.7383,
|
|
"mean_token_accuracy": 0.21992782950401307,
|
|
"num_tokens": 26185201.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.128102254867554,
|
|
"epoch": 1.1161405598570577,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004887893325371013,
|
|
"loss": 4.8038,
|
|
"mean_token_accuracy": 0.21767649799585342,
|
|
"num_tokens": 26199016.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.055191230773926,
|
|
"epoch": 1.1167361524717094,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004887760455978592,
|
|
"loss": 4.7492,
|
|
"mean_token_accuracy": 0.2146980047225952,
|
|
"num_tokens": 26213077.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.039746236801148,
|
|
"epoch": 1.117331745086361,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000488762750990818,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.2203819677233696,
|
|
"num_tokens": 26228281.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.174646520614624,
|
|
"epoch": 1.1179273377010126,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004887494487164546,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.20968627333641052,
|
|
"num_tokens": 26242258.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.116078186035156,
|
|
"epoch": 1.118522930315664,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004887361387752459,
|
|
"loss": 4.7651,
|
|
"mean_token_accuracy": 0.21373095810413362,
|
|
"num_tokens": 26257028.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.0369367599487305,
|
|
"epoch": 1.1191185229303158,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004887228211676694,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.21487769335508347,
|
|
"num_tokens": 26269965.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.085951662063598,
|
|
"epoch": 1.1197141155449672,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004887094958942029,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.21386145949363708,
|
|
"num_tokens": 26283833.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.071313381195068,
|
|
"epoch": 1.1203097081596187,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004886961629553242,
|
|
"loss": 4.7396,
|
|
"mean_token_accuracy": 0.21663007736206055,
|
|
"num_tokens": 26296526.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.1147161483764645,
|
|
"epoch": 1.1209053007742704,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004886828223515115,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.21003105938434602,
|
|
"num_tokens": 26311426.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.093265104293823,
|
|
"epoch": 1.121500893388922,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004886694740832434,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.21036736965179442,
|
|
"num_tokens": 26324260.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.064689111709595,
|
|
"epoch": 1.1220964860035736,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004886561181509988,
|
|
"loss": 4.7536,
|
|
"mean_token_accuracy": 0.21636945754289627,
|
|
"num_tokens": 26337964.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.073522472381592,
|
|
"epoch": 1.122692078618225,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004886427545552567,
|
|
"loss": 4.7753,
|
|
"mean_token_accuracy": 0.21053402423858641,
|
|
"num_tokens": 26352293.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.066984224319458,
|
|
"epoch": 1.1232876712328768,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004886293832964961,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.21006952822208405,
|
|
"num_tokens": 26368979.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.089788389205933,
|
|
"epoch": 1.1238832638475282,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000488616004375197,
|
|
"loss": 4.7586,
|
|
"mean_token_accuracy": 0.21920893341302872,
|
|
"num_tokens": 26382230.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.081624603271484,
|
|
"epoch": 1.12447885646218,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000488602617791839,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.2156142309308052,
|
|
"num_tokens": 26396046.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.07423734664917,
|
|
"epoch": 1.1250744490768314,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004885892235469026,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.20602148473262788,
|
|
"num_tokens": 26408774.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.0976697444915775,
|
|
"epoch": 1.125670041691483,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000488575821640868,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.21104227602481843,
|
|
"num_tokens": 26423261.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.038685321807861,
|
|
"epoch": 1.1262656343061346,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004885624120742158,
|
|
"loss": 4.759,
|
|
"mean_token_accuracy": 0.22043586075305938,
|
|
"num_tokens": 26435834.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.105526638031006,
|
|
"epoch": 1.1268612269207863,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004885489948474272,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.21039220243692397,
|
|
"num_tokens": 26450522.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.087070322036743,
|
|
"epoch": 1.1274568195354377,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004885355699609834,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.20461962521076202,
|
|
"num_tokens": 26465375.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.088864517211914,
|
|
"epoch": 1.1280524121500894,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004885221374153657,
|
|
"loss": 4.781,
|
|
"mean_token_accuracy": 0.20887732803821563,
|
|
"num_tokens": 26477408.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.052274703979492,
|
|
"epoch": 1.128648004764741,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004885086972110563,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.21496180295944214,
|
|
"num_tokens": 26490057.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.130745077133179,
|
|
"epoch": 1.1292435973793924,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000488495249348537,
|
|
"loss": 4.753,
|
|
"mean_token_accuracy": 0.21267545819282532,
|
|
"num_tokens": 26503020.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.074029207229614,
|
|
"epoch": 1.129839189994044,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004884817938282902,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.21343780010938646,
|
|
"num_tokens": 26517527.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.114904832839966,
|
|
"epoch": 1.1304347826086956,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004884683306507987,
|
|
"loss": 4.7885,
|
|
"mean_token_accuracy": 0.2154198855161667,
|
|
"num_tokens": 26532101.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.1132556915283205,
|
|
"epoch": 1.1310303752233473,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000488454859816545,
|
|
"loss": 4.857,
|
|
"mean_token_accuracy": 0.20031475871801377,
|
|
"num_tokens": 26544232.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.07278265953064,
|
|
"epoch": 1.1316259678379987,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004884413813260127,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.2119667187333107,
|
|
"num_tokens": 26558731.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.122006416320801,
|
|
"epoch": 1.1322215604526504,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004884278951796851,
|
|
"loss": 4.7892,
|
|
"mean_token_accuracy": 0.20673802345991135,
|
|
"num_tokens": 26572784.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.111510562896728,
|
|
"epoch": 1.132817153067302,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004884144013780459,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.21133843213319778,
|
|
"num_tokens": 26585847.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.136905288696289,
|
|
"epoch": 1.1334127456819536,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004884008999215792,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.20960143059492112,
|
|
"num_tokens": 26600996.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.171458292007446,
|
|
"epoch": 1.134008338296605,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000488387390810769,
|
|
"loss": 4.8739,
|
|
"mean_token_accuracy": 0.1965889886021614,
|
|
"num_tokens": 26613550.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.102839994430542,
|
|
"epoch": 1.1346039309112568,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004883738740461001,
|
|
"loss": 4.8068,
|
|
"mean_token_accuracy": 0.209405817091465,
|
|
"num_tokens": 26627453.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.108716440200806,
|
|
"epoch": 1.1351995235259082,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004883603496280573,
|
|
"loss": 4.822,
|
|
"mean_token_accuracy": 0.21098555326461793,
|
|
"num_tokens": 26642659.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.0979231834411625,
|
|
"epoch": 1.13579511614056,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004883468175571256,
|
|
"loss": 4.8405,
|
|
"mean_token_accuracy": 0.20386731773614883,
|
|
"num_tokens": 26655995.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.120604944229126,
|
|
"epoch": 1.1363907087552114,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004883332778337905,
|
|
"loss": 4.7116,
|
|
"mean_token_accuracy": 0.21493760198354722,
|
|
"num_tokens": 26669619.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.111782169342041,
|
|
"epoch": 1.1369863013698631,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004883197304585376,
|
|
"loss": 4.8288,
|
|
"mean_token_accuracy": 0.21109145730733872,
|
|
"num_tokens": 26684168.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.091547012329102,
|
|
"epoch": 1.1375818939845146,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004883061754318528,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.2165799006819725,
|
|
"num_tokens": 26696891.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.124940729141235,
|
|
"epoch": 1.138177486599166,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004882926127542222,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.20875079780817032,
|
|
"num_tokens": 26712523.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.074097728729248,
|
|
"epoch": 1.1387730792138178,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004882790424261325,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.21002187579870224,
|
|
"num_tokens": 26726393.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.117510986328125,
|
|
"epoch": 1.1393686718284692,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004882654644480702,
|
|
"loss": 4.7928,
|
|
"mean_token_accuracy": 0.20914884358644487,
|
|
"num_tokens": 26742567.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.120869445800781,
|
|
"epoch": 1.139964264443121,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004882518788205225,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.1983715057373047,
|
|
"num_tokens": 26755052.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 4.988274955749512,
|
|
"epoch": 1.1405598570577724,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048823828554397664,
|
|
"loss": 4.6528,
|
|
"mean_token_accuracy": 0.22422029674053193,
|
|
"num_tokens": 26767194.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.05300726890564,
|
|
"epoch": 1.141155449672424,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004882246846189202,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.20925441831350328,
|
|
"num_tokens": 26779744.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.123053693771363,
|
|
"epoch": 1.1417510422870756,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048821107604584096,
|
|
"loss": 4.8692,
|
|
"mean_token_accuracy": 0.20522311478853225,
|
|
"num_tokens": 26793413.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.136895799636841,
|
|
"epoch": 1.1423466349017273,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004881974598252271,
|
|
"loss": 4.8504,
|
|
"mean_token_accuracy": 0.20881866961717604,
|
|
"num_tokens": 26809168.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.141160106658935,
|
|
"epoch": 1.1429422275163788,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000488183835957567,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.2184304803609848,
|
|
"num_tokens": 26821597.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.092326068878174,
|
|
"epoch": 1.1435378201310304,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048817020444334936,
|
|
"loss": 4.7874,
|
|
"mean_token_accuracy": 0.2131797820329666,
|
|
"num_tokens": 26835971.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.049999523162842,
|
|
"epoch": 1.144133412745682,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048815656528306304,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.2131850004196167,
|
|
"num_tokens": 26849787.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.160692739486694,
|
|
"epoch": 1.1447290053603336,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004881429184771973,
|
|
"loss": 4.8419,
|
|
"mean_token_accuracy": 0.21014492064714432,
|
|
"num_tokens": 26863886.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.1769766330719,
|
|
"epoch": 1.145324597974985,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004881292640262416,
|
|
"loss": 4.7822,
|
|
"mean_token_accuracy": 0.21174596697092057,
|
|
"num_tokens": 26877249.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.171154403686524,
|
|
"epoch": 1.1459201905896368,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004881156019306857,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.20292078256607055,
|
|
"num_tokens": 26891882.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.213681936264038,
|
|
"epoch": 1.1465157832042883,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004881019321910198,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.21124029010534287,
|
|
"num_tokens": 26907990.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.013013505935669,
|
|
"epoch": 1.1471113758189397,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048808825480773396,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.21311194598674774,
|
|
"num_tokens": 26922302.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.1446836471557615,
|
|
"epoch": 1.1477069684335914,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004880745697813189,
|
|
"loss": 4.8197,
|
|
"mean_token_accuracy": 0.21470504254102707,
|
|
"num_tokens": 26935849.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.242047739028931,
|
|
"epoch": 1.148302561048243,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004880608771122654,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.19674744457006454,
|
|
"num_tokens": 26949413.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.20243091583252,
|
|
"epoch": 1.1488981536628946,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048804717680106475,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.20194920897483826,
|
|
"num_tokens": 26963901.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.0412229061126705,
|
|
"epoch": 1.149493746277546,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004880334688482082,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.22083678096532822,
|
|
"num_tokens": 26977963.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.199512338638305,
|
|
"epoch": 1.1500893388921978,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004880197532541875,
|
|
"loss": 4.9319,
|
|
"mean_token_accuracy": 0.20163936614990235,
|
|
"num_tokens": 26992282.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.083458662033081,
|
|
"epoch": 1.1506849315068493,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004880060300194947,
|
|
"loss": 4.7506,
|
|
"mean_token_accuracy": 0.2148539736866951,
|
|
"num_tokens": 27006397.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.0990105152130125,
|
|
"epoch": 1.151280524121501,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004879922991446218,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.2148880824446678,
|
|
"num_tokens": 27021030.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.053799247741699,
|
|
"epoch": 1.1518761167361524,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048797856063006144,
|
|
"loss": 4.6748,
|
|
"mean_token_accuracy": 0.21361653357744217,
|
|
"num_tokens": 27034446.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.089489221572876,
|
|
"epoch": 1.1524717093508041,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048796481447630646,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.20661308169364928,
|
|
"num_tokens": 27046748.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.087613534927368,
|
|
"epoch": 1.1530673019654556,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048795106068384985,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.21067581325769424,
|
|
"num_tokens": 27060253.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.099388694763183,
|
|
"epoch": 1.1536628945801073,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004879372992531849,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.22263210862874985,
|
|
"num_tokens": 27072877.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.11762261390686,
|
|
"epoch": 1.1542584871947588,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004879235301848052,
|
|
"loss": 4.8317,
|
|
"mean_token_accuracy": 0.20991775393486023,
|
|
"num_tokens": 27085396.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.021579170227051,
|
|
"epoch": 1.1548540798094105,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004879097534792047,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.21875714361667634,
|
|
"num_tokens": 27100810.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.102883386611938,
|
|
"epoch": 1.155449672424062,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004878959691368776,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.2102932170033455,
|
|
"num_tokens": 27115704.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.044609069824219,
|
|
"epoch": 1.1560452650387134,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004878821771583181,
|
|
"loss": 4.7059,
|
|
"mean_token_accuracy": 0.2195827454328537,
|
|
"num_tokens": 27128500.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.08982515335083,
|
|
"epoch": 1.156640857653365,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048786837754402114,
|
|
"loss": 4.7444,
|
|
"mean_token_accuracy": 0.21344458907842637,
|
|
"num_tokens": 27141259.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.1116047382354735,
|
|
"epoch": 1.1572364502680166,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004878545702944815,
|
|
"loss": 4.7404,
|
|
"mean_token_accuracy": 0.2163914203643799,
|
|
"num_tokens": 27155355.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.076908445358276,
|
|
"epoch": 1.1578320428826683,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048784075541019454,
|
|
"loss": 4.7205,
|
|
"mean_token_accuracy": 0.21941207349300385,
|
|
"num_tokens": 27170044.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.07362060546875,
|
|
"epoch": 1.1584276354973198,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004878269328916557,
|
|
"loss": 4.7467,
|
|
"mean_token_accuracy": 0.2100954011082649,
|
|
"num_tokens": 27186018.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.040517330169678,
|
|
"epoch": 1.1590232281119714,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004878131027393609,
|
|
"loss": 4.6866,
|
|
"mean_token_accuracy": 0.22033116817474366,
|
|
"num_tokens": 27200336.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.1144664764404295,
|
|
"epoch": 1.159618820726623,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000487799264953806,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.21070817857980728,
|
|
"num_tokens": 27214941.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 4.9996572971344,
|
|
"epoch": 1.1602144133412746,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048778541953548753,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.21742765307426454,
|
|
"num_tokens": 27228441.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 4.997694730758667,
|
|
"epoch": 1.160810005955926,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000487771566484902,
|
|
"loss": 4.6442,
|
|
"mean_token_accuracy": 0.22244423478841782,
|
|
"num_tokens": 27244524.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.15859055519104,
|
|
"epoch": 1.1614055985705778,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048775770580254636,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.21119443625211715,
|
|
"num_tokens": 27259109.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.079555082321167,
|
|
"epoch": 1.1620011911852293,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048774383748891774,
|
|
"loss": 4.7429,
|
|
"mean_token_accuracy": 0.21592990309000015,
|
|
"num_tokens": 27273746.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.15833158493042,
|
|
"epoch": 1.162596783799881,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048772996154451356,
|
|
"loss": 4.8165,
|
|
"mean_token_accuracy": 0.21203916668891906,
|
|
"num_tokens": 27288414.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.120090436935425,
|
|
"epoch": 1.1631923764145324,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004877160779698315,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.20684983283281327,
|
|
"num_tokens": 27302274.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.154197740554809,
|
|
"epoch": 1.1637879690291841,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048770218676536957,
|
|
"loss": 4.7453,
|
|
"mean_token_accuracy": 0.2034846678376198,
|
|
"num_tokens": 27316960.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.156201887130737,
|
|
"epoch": 1.1643835616438356,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048768828793162614,
|
|
"loss": 4.8501,
|
|
"mean_token_accuracy": 0.20996566563844682,
|
|
"num_tokens": 27331861.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.081696224212647,
|
|
"epoch": 1.164979154258487,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004876743814690995,
|
|
"loss": 4.809,
|
|
"mean_token_accuracy": 0.21635312139987944,
|
|
"num_tokens": 27345248.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.081339597702026,
|
|
"epoch": 1.1655747468731388,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004876604673782887,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.21438461691141128,
|
|
"num_tokens": 27359579.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.046064949035644,
|
|
"epoch": 1.1661703394877905,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004876465456596926,
|
|
"loss": 4.7353,
|
|
"mean_token_accuracy": 0.2165594682097435,
|
|
"num_tokens": 27374595.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.031744194030762,
|
|
"epoch": 1.166765932102442,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048763261631381075,
|
|
"loss": 4.6514,
|
|
"mean_token_accuracy": 0.23084752708673478,
|
|
"num_tokens": 27386446.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.10148434638977,
|
|
"epoch": 1.1673615247170934,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004876186793411426,
|
|
"loss": 4.816,
|
|
"mean_token_accuracy": 0.20738651752471923,
|
|
"num_tokens": 27400307.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.0579382419586185,
|
|
"epoch": 1.1679571173317451,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048760473474218814,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.21700129956007003,
|
|
"num_tokens": 27412495.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.123201560974121,
|
|
"epoch": 1.1685527099463966,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048759078251744747,
|
|
"loss": 4.8437,
|
|
"mean_token_accuracy": 0.20428713262081147,
|
|
"num_tokens": 27426201.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.173625421524048,
|
|
"epoch": 1.1691483025610483,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048757682266742115,
|
|
"loss": 4.8412,
|
|
"mean_token_accuracy": 0.2128562495112419,
|
|
"num_tokens": 27440418.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.018284940719605,
|
|
"epoch": 1.1697438951756998,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004875628551926098,
|
|
"loss": 4.606,
|
|
"mean_token_accuracy": 0.23567034006118776,
|
|
"num_tokens": 27452756.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 4.976924133300781,
|
|
"epoch": 1.1703394877903515,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004875488800935144,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.22324468791484833,
|
|
"num_tokens": 27465245.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.069247055053711,
|
|
"epoch": 1.170935080405003,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004875348973706363,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.21518896371126175,
|
|
"num_tokens": 27480054.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.236036062240601,
|
|
"epoch": 1.1715306730196546,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000487520907024477,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.1957458570599556,
|
|
"num_tokens": 27493963.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.165649890899658,
|
|
"epoch": 1.172126265634306,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048750690905553833,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.2131643772125244,
|
|
"num_tokens": 27508072.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.0727935314178465,
|
|
"epoch": 1.1727218582489578,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004874929034643223,
|
|
"loss": 4.7885,
|
|
"mean_token_accuracy": 0.22099121212959288,
|
|
"num_tokens": 27520354.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.058797550201416,
|
|
"epoch": 1.1733174508636093,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004874788902513314,
|
|
"loss": 4.7652,
|
|
"mean_token_accuracy": 0.21531681418418885,
|
|
"num_tokens": 27534486.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.128304862976075,
|
|
"epoch": 1.1739130434782608,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004874648694170681,
|
|
"loss": 4.7217,
|
|
"mean_token_accuracy": 0.21424034535884856,
|
|
"num_tokens": 27548821.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.130733633041382,
|
|
"epoch": 1.1745086360929125,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048745084096203536,
|
|
"loss": 4.7697,
|
|
"mean_token_accuracy": 0.218520949780941,
|
|
"num_tokens": 27561534.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.028663301467896,
|
|
"epoch": 1.1751042287075641,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004874368048867364,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.21892057061195375,
|
|
"num_tokens": 27573858.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.115526437759399,
|
|
"epoch": 1.1756998213222156,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048742276119167463,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.2081610694527626,
|
|
"num_tokens": 27588376.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.067438173294067,
|
|
"epoch": 1.176295413936867,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048740870987735383,
|
|
"loss": 4.6371,
|
|
"mean_token_accuracy": 0.2196599707007408,
|
|
"num_tokens": 27601233.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.036075735092163,
|
|
"epoch": 1.1768910065515188,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004873946509442779,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.2172190248966217,
|
|
"num_tokens": 27614878.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.084037733078003,
|
|
"epoch": 1.1774865991661703,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004873805843929512,
|
|
"loss": 4.7534,
|
|
"mean_token_accuracy": 0.2125864714384079,
|
|
"num_tokens": 27629588.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 4.999048709869385,
|
|
"epoch": 1.178082191780822,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004873665102238783,
|
|
"loss": 4.5978,
|
|
"mean_token_accuracy": 0.22757744342088698,
|
|
"num_tokens": 27643068.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 4.946952199935913,
|
|
"epoch": 1.1786777843954734,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048735242843756394,
|
|
"loss": 4.7796,
|
|
"mean_token_accuracy": 0.2081539288163185,
|
|
"num_tokens": 27657404.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.032840919494629,
|
|
"epoch": 1.1792733770101251,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004873383390345132,
|
|
"loss": 4.6807,
|
|
"mean_token_accuracy": 0.22351807355880737,
|
|
"num_tokens": 27672145.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.164626407623291,
|
|
"epoch": 1.1798689696247766,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048732424201523156,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.20938758105039595,
|
|
"num_tokens": 27686542.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.056358480453492,
|
|
"epoch": 1.1804645622394283,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004873101373802245,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.2253192439675331,
|
|
"num_tokens": 27700783.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.106373691558838,
|
|
"epoch": 1.1810601548540798,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004872960251299981,
|
|
"loss": 4.8169,
|
|
"mean_token_accuracy": 0.20563007146120071,
|
|
"num_tokens": 27714604.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.075225400924682,
|
|
"epoch": 1.1816557474687315,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048728190526505834,
|
|
"loss": 4.7757,
|
|
"mean_token_accuracy": 0.21591618955135344,
|
|
"num_tokens": 27728690.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.093154382705689,
|
|
"epoch": 1.182251340083383,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048726777778591184,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.2125860944390297,
|
|
"num_tokens": 27740603.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.06792197227478,
|
|
"epoch": 1.1828469326980344,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004872536426930653,
|
|
"loss": 4.7033,
|
|
"mean_token_accuracy": 0.22418288588523866,
|
|
"num_tokens": 27753541.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.041484355926514,
|
|
"epoch": 1.1834425253126861,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004872394999870256,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.21913310289382934,
|
|
"num_tokens": 27766459.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.1215863704681395,
|
|
"epoch": 1.1840381179273378,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048722534966830027,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.20498422384262086,
|
|
"num_tokens": 27779427.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.1801502227783205,
|
|
"epoch": 1.1846337105419893,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048721119173739667,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.20756400674581527,
|
|
"num_tokens": 27793075.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.109794664382934,
|
|
"epoch": 1.1852293031566408,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048719702619482255,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.2151437371969223,
|
|
"num_tokens": 27807738.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.125386333465576,
|
|
"epoch": 1.1858248957712925,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048718285304108613,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.20928864181041718,
|
|
"num_tokens": 27823047.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.006713056564331,
|
|
"epoch": 1.186420488385944,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004871686722766958,
|
|
"loss": 4.6393,
|
|
"mean_token_accuracy": 0.2192234292626381,
|
|
"num_tokens": 27837918.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.016340351104736,
|
|
"epoch": 1.1870160810005956,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048715448390216015,
|
|
"loss": 4.7482,
|
|
"mean_token_accuracy": 0.21234889179468155,
|
|
"num_tokens": 27851649.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.091741943359375,
|
|
"epoch": 1.187611673615247,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048714028791798817,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.21793779581785203,
|
|
"num_tokens": 27863579.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.114759635925293,
|
|
"epoch": 1.1882072662298988,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004871260843246889,
|
|
"loss": 4.7169,
|
|
"mean_token_accuracy": 0.21740537732839585,
|
|
"num_tokens": 27877526.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.068059015274048,
|
|
"epoch": 1.1888028588445503,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048711187312277187,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.21501984745264052,
|
|
"num_tokens": 27890425.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.092368316650391,
|
|
"epoch": 1.189398451459202,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048709765431274686,
|
|
"loss": 4.8113,
|
|
"mean_token_accuracy": 0.2171088919043541,
|
|
"num_tokens": 27903247.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.0987663745880125,
|
|
"epoch": 1.1899940440738535,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004870834278951238,
|
|
"loss": 4.7868,
|
|
"mean_token_accuracy": 0.2125082165002823,
|
|
"num_tokens": 27916387.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.113531112670898,
|
|
"epoch": 1.1905896366885051,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004870691938704131,
|
|
"loss": 4.6839,
|
|
"mean_token_accuracy": 0.21980431228876113,
|
|
"num_tokens": 27930647.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.0434284687042235,
|
|
"epoch": 1.1911852293031566,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004870549522391252,
|
|
"loss": 4.718,
|
|
"mean_token_accuracy": 0.219195955991745,
|
|
"num_tokens": 27943881.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.05001654624939,
|
|
"epoch": 1.191780821917808,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048704070300177094,
|
|
"loss": 4.714,
|
|
"mean_token_accuracy": 0.2226917564868927,
|
|
"num_tokens": 27958428.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.000334644317627,
|
|
"epoch": 1.1923764145324598,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048702644615886137,
|
|
"loss": 4.6926,
|
|
"mean_token_accuracy": 0.2181678146123886,
|
|
"num_tokens": 27972342.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.129312467575073,
|
|
"epoch": 1.1929720071471115,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004870121817109079,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.21204454749822615,
|
|
"num_tokens": 27986153.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.11451563835144,
|
|
"epoch": 1.193567599761763,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048699790965842224,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.2119580790400505,
|
|
"num_tokens": 27999375.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.111536359786987,
|
|
"epoch": 1.1941631923764144,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004869836300019162,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.20832929462194444,
|
|
"num_tokens": 28014309.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.05393009185791,
|
|
"epoch": 1.1947587849910661,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004869693427419021,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.21718734055757521,
|
|
"num_tokens": 28027779.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.037198495864868,
|
|
"epoch": 1.1953543776057176,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004869550478788922,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.21459229588508605,
|
|
"num_tokens": 28043500.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.136988973617553,
|
|
"epoch": 1.1959499702203693,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048694074541339946,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.2127627342939377,
|
|
"num_tokens": 28058561.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.055279064178467,
|
|
"epoch": 1.1965455628350208,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048692643534593665,
|
|
"loss": 4.6238,
|
|
"mean_token_accuracy": 0.22294659465551375,
|
|
"num_tokens": 28072409.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.065593004226685,
|
|
"epoch": 1.1971411554496725,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004869121176770173,
|
|
"loss": 4.8479,
|
|
"mean_token_accuracy": 0.21202408373355866,
|
|
"num_tokens": 28085164.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.044088506698609,
|
|
"epoch": 1.197736748064324,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048689779240715484,
|
|
"loss": 4.7435,
|
|
"mean_token_accuracy": 0.21551853865385057,
|
|
"num_tokens": 28099908.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.174683046340943,
|
|
"epoch": 1.1983323406789756,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048688345953686296,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.20941151678562164,
|
|
"num_tokens": 28114558.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.12911057472229,
|
|
"epoch": 1.1989279332936271,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048686911906665597,
|
|
"loss": 4.7816,
|
|
"mean_token_accuracy": 0.21389362663030625,
|
|
"num_tokens": 28129468.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.066749906539917,
|
|
"epoch": 1.1995235259082788,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048685477099704816,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.217695415019989,
|
|
"num_tokens": 28141810.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.090766191482544,
|
|
"epoch": 1.2001191185229303,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048684041532855415,
|
|
"loss": 4.7257,
|
|
"mean_token_accuracy": 0.21759364008903503,
|
|
"num_tokens": 28154848.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.0873514175415036,
|
|
"epoch": 1.2007147111375818,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004868260520616889,
|
|
"loss": 4.7586,
|
|
"mean_token_accuracy": 0.21705198884010315,
|
|
"num_tokens": 28168625.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.103702592849731,
|
|
"epoch": 1.2013103037522335,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048681168119696757,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.20251544415950776,
|
|
"num_tokens": 28183551.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.1684974193572994,
|
|
"epoch": 1.2019058963668852,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004867973027349056,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.20318487286567688,
|
|
"num_tokens": 28197839.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.084750366210938,
|
|
"epoch": 1.2025014889815366,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004867829166760188,
|
|
"loss": 4.6648,
|
|
"mean_token_accuracy": 0.22087876498699188,
|
|
"num_tokens": 28210662.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.0526762962341305,
|
|
"epoch": 1.2030970815961881,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048676852302082305,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.2126505419611931,
|
|
"num_tokens": 28225553.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.021056175231934,
|
|
"epoch": 1.2036926742108398,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004867541217698347,
|
|
"loss": 4.7234,
|
|
"mean_token_accuracy": 0.21744104772806166,
|
|
"num_tokens": 28239732.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 4.999292182922363,
|
|
"epoch": 1.2042882668254913,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048673971292357025,
|
|
"loss": 4.6719,
|
|
"mean_token_accuracy": 0.22500913143157958,
|
|
"num_tokens": 28254929.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.1198334217071535,
|
|
"epoch": 1.204883859440143,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004867252964825467,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.20652068704366683,
|
|
"num_tokens": 28272111.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.1679603099823,
|
|
"epoch": 1.2054794520547945,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048671087244728093,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.20692037045955658,
|
|
"num_tokens": 28286533.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.138511323928833,
|
|
"epoch": 1.2060750446694462,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048669644081829035,
|
|
"loss": 4.8336,
|
|
"mean_token_accuracy": 0.20558492988348007,
|
|
"num_tokens": 28299272.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.056736326217651,
|
|
"epoch": 1.2066706372840976,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.00048668200159609267,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.21599942892789842,
|
|
"num_tokens": 28316388.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.114729738235473,
|
|
"epoch": 1.2072662298987493,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048666755478120576,
|
|
"loss": 4.8307,
|
|
"mean_token_accuracy": 0.2134178340435028,
|
|
"num_tokens": 28330575.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.110183763504028,
|
|
"epoch": 1.2078618225134008,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048665310037414777,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.21584305465221404,
|
|
"num_tokens": 28343678.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.091619539260864,
|
|
"epoch": 1.2084574151280525,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004866386383754373,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.21399844586849212,
|
|
"num_tokens": 28357401.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.031204271316528,
|
|
"epoch": 1.209053007742704,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004866241687855929,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.21365389972925186,
|
|
"num_tokens": 28370676.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.14142804145813,
|
|
"epoch": 1.2096486003573557,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048660969160513367,
|
|
"loss": 4.8119,
|
|
"mean_token_accuracy": 0.20941576659679412,
|
|
"num_tokens": 28385167.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.08908634185791,
|
|
"epoch": 1.2102441929720071,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004865952068345788,
|
|
"loss": 4.6551,
|
|
"mean_token_accuracy": 0.21781337410211563,
|
|
"num_tokens": 28399940.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.098989200592041,
|
|
"epoch": 1.2108397855866588,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048658071447444794,
|
|
"loss": 4.8168,
|
|
"mean_token_accuracy": 0.20497384220361708,
|
|
"num_tokens": 28413525.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 4.9969895362854,
|
|
"epoch": 1.2114353782013103,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004865662145252609,
|
|
"loss": 4.6402,
|
|
"mean_token_accuracy": 0.22803255021572114,
|
|
"num_tokens": 28428273.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.113328075408935,
|
|
"epoch": 1.2120309708159618,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048655170698753774,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.21429696083068847,
|
|
"num_tokens": 28442030.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.084974718093872,
|
|
"epoch": 1.2126265634306135,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048653719186179874,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.20143139064311982,
|
|
"num_tokens": 28457514.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.084963417053222,
|
|
"epoch": 1.213222156045265,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004865226691485646,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.21830307096242904,
|
|
"num_tokens": 28471833.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.05917649269104,
|
|
"epoch": 1.2138177486599167,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.00048650813884835634,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.2123307079076767,
|
|
"num_tokens": 28486769.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.037999868392944,
|
|
"epoch": 1.2144133412745681,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004864936009616949,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.21382934898138045,
|
|
"num_tokens": 28501668.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.108226156234741,
|
|
"epoch": 1.2150089338892198,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000486479055489102,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.21357246041297911,
|
|
"num_tokens": 28515844.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.049693202972412,
|
|
"epoch": 1.2156045265038713,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004864645024310991,
|
|
"loss": 4.7097,
|
|
"mean_token_accuracy": 0.21619830280542374,
|
|
"num_tokens": 28531910.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.079723930358886,
|
|
"epoch": 1.216200119118523,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004864499417882084,
|
|
"loss": 4.7039,
|
|
"mean_token_accuracy": 0.22042734622955323,
|
|
"num_tokens": 28547044.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.128556776046753,
|
|
"epoch": 1.2167957117331745,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000486435373560952,
|
|
"loss": 4.7976,
|
|
"mean_token_accuracy": 0.21565648913383484,
|
|
"num_tokens": 28560684.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.118874645233154,
|
|
"epoch": 1.2173913043478262,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048642079774985255,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.21620320975780488,
|
|
"num_tokens": 28574889.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.060290956497193,
|
|
"epoch": 1.2179868969624776,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048640621435543286,
|
|
"loss": 4.7123,
|
|
"mean_token_accuracy": 0.21178014874458312,
|
|
"num_tokens": 28588740.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.134068632125855,
|
|
"epoch": 1.2185824895771293,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000486391623378216,
|
|
"loss": 4.8497,
|
|
"mean_token_accuracy": 0.2087557017803192,
|
|
"num_tokens": 28601908.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.1487054347991945,
|
|
"epoch": 1.2191780821917808,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004863770248187253,
|
|
"loss": 4.817,
|
|
"mean_token_accuracy": 0.2101613000035286,
|
|
"num_tokens": 28617025.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.145915508270264,
|
|
"epoch": 1.2197736748064325,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004863624186774844,
|
|
"loss": 4.8682,
|
|
"mean_token_accuracy": 0.20155038237571715,
|
|
"num_tokens": 28630432.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.1197545528411865,
|
|
"epoch": 1.220369267421084,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004863478049550171,
|
|
"loss": 4.8322,
|
|
"mean_token_accuracy": 0.2101418673992157,
|
|
"num_tokens": 28644815.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.11309814453125,
|
|
"epoch": 1.2209648600357355,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048633318365184783,
|
|
"loss": 4.7449,
|
|
"mean_token_accuracy": 0.20985113829374313,
|
|
"num_tokens": 28658368.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.0541785717010494,
|
|
"epoch": 1.2215604526503872,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048631855476850074,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.22474855482578276,
|
|
"num_tokens": 28672934.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.115467834472656,
|
|
"epoch": 1.2221560452650386,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048630391830550076,
|
|
"loss": 4.7896,
|
|
"mean_token_accuracy": 0.2127269372344017,
|
|
"num_tokens": 28688855.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.098454093933105,
|
|
"epoch": 1.2227516378796903,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004862892742633727,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.21176558136940002,
|
|
"num_tokens": 28703184.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.049653768539429,
|
|
"epoch": 1.2233472304943418,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000486274622642642,
|
|
"loss": 4.6685,
|
|
"mean_token_accuracy": 0.21787823140621185,
|
|
"num_tokens": 28718237.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.088371658325196,
|
|
"epoch": 1.2239428231089935,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048625996344383405,
|
|
"loss": 4.7278,
|
|
"mean_token_accuracy": 0.2189376324415207,
|
|
"num_tokens": 28731911.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.068746328353882,
|
|
"epoch": 1.224538415723645,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004862452966674747,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.2197734534740448,
|
|
"num_tokens": 28744844.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.166915416717529,
|
|
"epoch": 1.2251340083382967,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004862306223140901,
|
|
"loss": 4.8344,
|
|
"mean_token_accuracy": 0.21405510306358339,
|
|
"num_tokens": 28761011.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.1565831184387205,
|
|
"epoch": 1.2257296009529481,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004862159403842064,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.20771791487932206,
|
|
"num_tokens": 28775425.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.101288652420044,
|
|
"epoch": 1.2263251935675998,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048620125087835045,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.21447914093732834,
|
|
"num_tokens": 28790054.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.074117422103882,
|
|
"epoch": 1.2269207861822513,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004861865537970489,
|
|
"loss": 4.795,
|
|
"mean_token_accuracy": 0.20993747860193251,
|
|
"num_tokens": 28805604.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.023859024047852,
|
|
"epoch": 1.227516378796903,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004861718491408291,
|
|
"loss": 4.6621,
|
|
"mean_token_accuracy": 0.21995629072189332,
|
|
"num_tokens": 28820986.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.120316219329834,
|
|
"epoch": 1.2281119714115545,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004861571369102184,
|
|
"loss": 4.897,
|
|
"mean_token_accuracy": 0.20775902271270752,
|
|
"num_tokens": 28836305.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.0649659633636475,
|
|
"epoch": 1.2287075640262062,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004861424171057445,
|
|
"loss": 4.791,
|
|
"mean_token_accuracy": 0.21380301266908647,
|
|
"num_tokens": 28849303.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.171183681488037,
|
|
"epoch": 1.2293031566408577,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004861276897279354,
|
|
"loss": 4.712,
|
|
"mean_token_accuracy": 0.21385083496570587,
|
|
"num_tokens": 28863682.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.025707960128784,
|
|
"epoch": 1.2298987492555091,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004861129547773194,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.22021373957395554,
|
|
"num_tokens": 28878533.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 4.980743646621704,
|
|
"epoch": 1.2304943418701608,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048609821225442494,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.21954563707113267,
|
|
"num_tokens": 28893837.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.0738592624664305,
|
|
"epoch": 1.2310899344848123,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004860834621597808,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.21461417526006699,
|
|
"num_tokens": 28907754.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.149386596679688,
|
|
"epoch": 1.231685527099464,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048606870449391604,
|
|
"loss": 4.82,
|
|
"mean_token_accuracy": 0.21685511469841004,
|
|
"num_tokens": 28920994.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.0404950141906735,
|
|
"epoch": 1.2322811197141155,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004860539392573601,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.2113217145204544,
|
|
"num_tokens": 28937298.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.0779002666473385,
|
|
"epoch": 1.2328767123287672,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048603916645064256,
|
|
"loss": 4.7359,
|
|
"mean_token_accuracy": 0.21687496602535247,
|
|
"num_tokens": 28951050.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.209011030197144,
|
|
"epoch": 1.2334723049434186,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048602438607429313,
|
|
"loss": 4.8455,
|
|
"mean_token_accuracy": 0.20723322927951812,
|
|
"num_tokens": 28965054.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.064710569381714,
|
|
"epoch": 1.2340678975580703,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048600959812884217,
|
|
"loss": 4.6591,
|
|
"mean_token_accuracy": 0.22471597343683242,
|
|
"num_tokens": 28978162.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.1489098072052,
|
|
"epoch": 1.2346634901727218,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004859948026148199,
|
|
"loss": 4.8109,
|
|
"mean_token_accuracy": 0.20687151104211807,
|
|
"num_tokens": 28991426.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.109814643859863,
|
|
"epoch": 1.2352590827873735,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048597999953275717,
|
|
"loss": 4.7712,
|
|
"mean_token_accuracy": 0.2191115751862526,
|
|
"num_tokens": 29005159.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.063030052185058,
|
|
"epoch": 1.235854675402025,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00048596518888318485,
|
|
"loss": 4.6858,
|
|
"mean_token_accuracy": 0.22141996026039124,
|
|
"num_tokens": 29020957.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.115081262588501,
|
|
"epoch": 1.2364502680166767,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048595037066663434,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.20887145549058914,
|
|
"num_tokens": 29035133.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.092573928833008,
|
|
"epoch": 1.2370458606313282,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004859355448836369,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.21801059693098068,
|
|
"num_tokens": 29047351.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.051088953018189,
|
|
"epoch": 1.2376414532459799,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048592071153472446,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.22198666930198668,
|
|
"num_tokens": 29061395.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.13611912727356,
|
|
"epoch": 1.2382370458606313,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048590587062042907,
|
|
"loss": 4.8064,
|
|
"mean_token_accuracy": 0.2109228178858757,
|
|
"num_tokens": 29074952.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.098400068283081,
|
|
"epoch": 1.2388326384752828,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004858910221412829,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.21743632853031158,
|
|
"num_tokens": 29087954.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.1055655002594,
|
|
"epoch": 1.2394282310899345,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004858761660978188,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.21275280714035033,
|
|
"num_tokens": 29102437.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.053399562835693,
|
|
"epoch": 1.240023823704586,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004858613024905694,
|
|
"loss": 4.7079,
|
|
"mean_token_accuracy": 0.22084005028009415,
|
|
"num_tokens": 29116652.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.043447971343994,
|
|
"epoch": 1.2406194163192377,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004858464313200679,
|
|
"loss": 4.7784,
|
|
"mean_token_accuracy": 0.2125244453549385,
|
|
"num_tokens": 29131866.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.132731914520264,
|
|
"epoch": 1.2412150089338891,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004858315525868478,
|
|
"loss": 4.7831,
|
|
"mean_token_accuracy": 0.21703592389822007,
|
|
"num_tokens": 29145512.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.01729097366333,
|
|
"epoch": 1.2418106015485408,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004858166662914426,
|
|
"loss": 4.6861,
|
|
"mean_token_accuracy": 0.22129107713699342,
|
|
"num_tokens": 29158789.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.028016805648804,
|
|
"epoch": 1.2424061941631923,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004858017724343864,
|
|
"loss": 4.6762,
|
|
"mean_token_accuracy": 0.21296747922897338,
|
|
"num_tokens": 29172536.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.019027757644653,
|
|
"epoch": 1.243001786777844,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00048578687101621346,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.22053342908620835,
|
|
"num_tokens": 29185837.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.05751404762268,
|
|
"epoch": 1.2435973793924955,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000485771962037458,
|
|
"loss": 4.72,
|
|
"mean_token_accuracy": 0.21117210239171982,
|
|
"num_tokens": 29198821.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.088331937789917,
|
|
"epoch": 1.2441929720071472,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048575704549865505,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.2167715847492218,
|
|
"num_tokens": 29211240.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.044820117950439,
|
|
"epoch": 1.2447885646217987,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048574212140033965,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.21657606065273285,
|
|
"num_tokens": 29225413.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 4.9870336055755615,
|
|
"epoch": 1.2453841572364504,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048572718974304683,
|
|
"loss": 4.6658,
|
|
"mean_token_accuracy": 0.22002291530370713,
|
|
"num_tokens": 29236804.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.055012321472168,
|
|
"epoch": 1.2459797498511018,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048571225052731245,
|
|
"loss": 4.8056,
|
|
"mean_token_accuracy": 0.21614363491535188,
|
|
"num_tokens": 29249884.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.09596471786499,
|
|
"epoch": 1.2465753424657535,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048569730375367217,
|
|
"loss": 4.7691,
|
|
"mean_token_accuracy": 0.20969401448965072,
|
|
"num_tokens": 29266123.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.089838695526123,
|
|
"epoch": 1.247170935080405,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048568234942266217,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.21481408178806305,
|
|
"num_tokens": 29281222.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.0456154346466064,
|
|
"epoch": 1.2477665276950565,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048566738753481886,
|
|
"loss": 4.6933,
|
|
"mean_token_accuracy": 0.21995252668857573,
|
|
"num_tokens": 29293855.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.08104829788208,
|
|
"epoch": 1.2483621203097082,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004856524180906789,
|
|
"loss": 4.7697,
|
|
"mean_token_accuracy": 0.21296416968107224,
|
|
"num_tokens": 29305968.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.093236303329467,
|
|
"epoch": 1.2489577129243596,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048563744109077916,
|
|
"loss": 4.7839,
|
|
"mean_token_accuracy": 0.21073487251996995,
|
|
"num_tokens": 29320806.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.082816076278687,
|
|
"epoch": 1.2495533055390113,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004856224565356569,
|
|
"loss": 4.7407,
|
|
"mean_token_accuracy": 0.2183045268058777,
|
|
"num_tokens": 29334727.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.068000173568725,
|
|
"epoch": 1.2501488981536628,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048560746442584965,
|
|
"loss": 4.7013,
|
|
"mean_token_accuracy": 0.21934992223978042,
|
|
"num_tokens": 29348362.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.056110382080078,
|
|
"epoch": 1.2507444907683145,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000485592464761895,
|
|
"loss": 4.7147,
|
|
"mean_token_accuracy": 0.21944681257009507,
|
|
"num_tokens": 29360919.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.081822299957276,
|
|
"epoch": 1.251340083382966,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004855774575443311,
|
|
"loss": 4.7551,
|
|
"mean_token_accuracy": 0.21848029643297195,
|
|
"num_tokens": 29374627.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.081923341751098,
|
|
"epoch": 1.2519356759976177,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004855624427736961,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.20955681055784225,
|
|
"num_tokens": 29386660.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.03731517791748,
|
|
"epoch": 1.2525312686122692,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004855474204505287,
|
|
"loss": 4.7038,
|
|
"mean_token_accuracy": 0.21186403632164003,
|
|
"num_tokens": 29401521.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.075048303604126,
|
|
"epoch": 1.2531268612269209,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048553239057536757,
|
|
"loss": 4.6529,
|
|
"mean_token_accuracy": 0.22599828541278838,
|
|
"num_tokens": 29414629.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.108787631988525,
|
|
"epoch": 1.2537224538415723,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048551735314875203,
|
|
"loss": 4.7702,
|
|
"mean_token_accuracy": 0.20784667879343033,
|
|
"num_tokens": 29428049.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.092012786865235,
|
|
"epoch": 1.254318046456224,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004855023081712212,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.20585442781448365,
|
|
"num_tokens": 29441656.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.051765251159668,
|
|
"epoch": 1.2549136390708755,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004854872556433149,
|
|
"loss": 4.702,
|
|
"mean_token_accuracy": 0.20978105664253235,
|
|
"num_tokens": 29455613.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.192390775680542,
|
|
"epoch": 1.2555092316855272,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004854721955655729,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.2063297525048256,
|
|
"num_tokens": 29470322.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.137262535095215,
|
|
"epoch": 1.2561048243001787,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048545712793853554,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.21344178915023804,
|
|
"num_tokens": 29484288.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.122713613510132,
|
|
"epoch": 1.2567004169148301,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004854420527627431,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.22030557990074157,
|
|
"num_tokens": 29497311.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.1118920803070065,
|
|
"epoch": 1.2572960095294818,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048542697003873636,
|
|
"loss": 4.7676,
|
|
"mean_token_accuracy": 0.2223504215478897,
|
|
"num_tokens": 29510352.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.0918059825897215,
|
|
"epoch": 1.2578916021441335,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048541187976705645,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.21406323760747908,
|
|
"num_tokens": 29523888.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.083281230926514,
|
|
"epoch": 1.258487194758785,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004853967819482445,
|
|
"loss": 4.7072,
|
|
"mean_token_accuracy": 0.21921358853578568,
|
|
"num_tokens": 29536219.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.062257099151611,
|
|
"epoch": 1.2590827873734365,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000485381676582842,
|
|
"loss": 4.6984,
|
|
"mean_token_accuracy": 0.22097013592720033,
|
|
"num_tokens": 29549570.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.100824213027954,
|
|
"epoch": 1.2596783799880882,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048536656367139085,
|
|
"loss": 4.7103,
|
|
"mean_token_accuracy": 0.22157984524965285,
|
|
"num_tokens": 29563278.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.038971996307373,
|
|
"epoch": 1.2602739726027397,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048535144321443317,
|
|
"loss": 4.7211,
|
|
"mean_token_accuracy": 0.2153027206659317,
|
|
"num_tokens": 29580363.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.024352502822876,
|
|
"epoch": 1.2608695652173914,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048533631521251115,
|
|
"loss": 4.6145,
|
|
"mean_token_accuracy": 0.2218450888991356,
|
|
"num_tokens": 29594339.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.104221343994141,
|
|
"epoch": 1.2614651578320428,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004853211796661675,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.21142324656248093,
|
|
"num_tokens": 29606678.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.058618402481079,
|
|
"epoch": 1.2620607504466945,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004853060365759451,
|
|
"loss": 4.7798,
|
|
"mean_token_accuracy": 0.21702388375997544,
|
|
"num_tokens": 29621791.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.120791006088257,
|
|
"epoch": 1.262656343061346,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048529088594238714,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.22046814113855362,
|
|
"num_tokens": 29633679.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.081716632843017,
|
|
"epoch": 1.2632519356759977,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004852757277660369,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.21363850980997084,
|
|
"num_tokens": 29648218.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.0961400985717775,
|
|
"epoch": 1.2638475282906492,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048526056204743827,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.20914745926856995,
|
|
"num_tokens": 29662819.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.103581142425537,
|
|
"epoch": 1.2644431209053009,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048524538878713517,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.2154724821448326,
|
|
"num_tokens": 29678298.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.0178813457489015,
|
|
"epoch": 1.2650387135199523,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004852302079856718,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.22077107578516006,
|
|
"num_tokens": 29692001.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.056954431533813,
|
|
"epoch": 1.2656343061346038,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004852150196435927,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.20833270996809006,
|
|
"num_tokens": 29706641.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 4.998144483566284,
|
|
"epoch": 1.2662298987492555,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048519982376144254,
|
|
"loss": 4.6461,
|
|
"mean_token_accuracy": 0.22371459156274795,
|
|
"num_tokens": 29719694.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.019096374511719,
|
|
"epoch": 1.2668254913639072,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048518462033976653,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.2210816279053688,
|
|
"num_tokens": 29733769.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.087557649612426,
|
|
"epoch": 1.2674210839785587,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048516940937910996,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.20609893202781676,
|
|
"num_tokens": 29748419.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.0847508907318115,
|
|
"epoch": 1.2680166765932102,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004851541908800184,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.21022090911865235,
|
|
"num_tokens": 29761356.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.049299097061157,
|
|
"epoch": 1.2686122692078619,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048513896484303763,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.2202333152294159,
|
|
"num_tokens": 29774245.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.0042438983917235,
|
|
"epoch": 1.2692078618225133,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048512373126871383,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.210321544110775,
|
|
"num_tokens": 29788153.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.147933435440064,
|
|
"epoch": 1.269803454437165,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004851084901575935,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.21418434381484985,
|
|
"num_tokens": 29802299.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.062897443771362,
|
|
"epoch": 1.2703990470518165,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048509324151022325,
|
|
"loss": 4.6486,
|
|
"mean_token_accuracy": 0.22736422568559647,
|
|
"num_tokens": 29815461.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.061071920394897,
|
|
"epoch": 1.2709946396664682,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048507798532715005,
|
|
"loss": 4.7192,
|
|
"mean_token_accuracy": 0.2165900230407715,
|
|
"num_tokens": 29829341.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 4.985272645950317,
|
|
"epoch": 1.2715902322811197,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000485062721608921,
|
|
"loss": 4.6757,
|
|
"mean_token_accuracy": 0.22197916060686113,
|
|
"num_tokens": 29842520.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.100663042068481,
|
|
"epoch": 1.2721858248957714,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004850474503560837,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.21760646998882294,
|
|
"num_tokens": 29857950.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.081542444229126,
|
|
"epoch": 1.2727814175104228,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004850321715691858,
|
|
"loss": 4.7363,
|
|
"mean_token_accuracy": 0.21237954944372178,
|
|
"num_tokens": 29872558.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.123494863510132,
|
|
"epoch": 1.2733770101250745,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048501688524877555,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.22058525681495667,
|
|
"num_tokens": 29884083.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.101854944229126,
|
|
"epoch": 1.273972602739726,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000485001591395401,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.2186516508460045,
|
|
"num_tokens": 29898088.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.046045732498169,
|
|
"epoch": 1.2745681953543775,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004849862900096108,
|
|
"loss": 4.7121,
|
|
"mean_token_accuracy": 0.21862944215536118,
|
|
"num_tokens": 29911394.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.171640491485595,
|
|
"epoch": 1.2751637879690292,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048497098109195387,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.20511210709810257,
|
|
"num_tokens": 29925968.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.118676328659058,
|
|
"epoch": 1.2757593805836809,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048495566464297913,
|
|
"loss": 4.7384,
|
|
"mean_token_accuracy": 0.21794828921556472,
|
|
"num_tokens": 29939853.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.073410749435425,
|
|
"epoch": 1.2763549731983324,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004849403406632361,
|
|
"loss": 4.7071,
|
|
"mean_token_accuracy": 0.2197026416659355,
|
|
"num_tokens": 29953512.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.077576065063477,
|
|
"epoch": 1.2769505658129838,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004849250091532744,
|
|
"loss": 4.7742,
|
|
"mean_token_accuracy": 0.2153234750032425,
|
|
"num_tokens": 29967681.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.201327896118164,
|
|
"epoch": 1.2775461584276355,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048490967011364394,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.21120241582393645,
|
|
"num_tokens": 29982726.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.0559803485870365,
|
|
"epoch": 1.278141751042287,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048489432354489496,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.22025915384292602,
|
|
"num_tokens": 29997881.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.03769965171814,
|
|
"epoch": 1.2787373436569387,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048487896944757777,
|
|
"loss": 4.7475,
|
|
"mean_token_accuracy": 0.21409468501806259,
|
|
"num_tokens": 30012707.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.140826749801636,
|
|
"epoch": 1.2793329362715902,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004848636078222433,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.20735774487257003,
|
|
"num_tokens": 30027098.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.077753353118896,
|
|
"epoch": 1.2799285288862419,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004848482386694424,
|
|
"loss": 4.731,
|
|
"mean_token_accuracy": 0.21759721040725707,
|
|
"num_tokens": 30042228.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.079695796966552,
|
|
"epoch": 1.2805241215008933,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048483286198972627,
|
|
"loss": 4.6545,
|
|
"mean_token_accuracy": 0.2207878977060318,
|
|
"num_tokens": 30055789.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 4.964877462387085,
|
|
"epoch": 1.281119714115545,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004848174777836466,
|
|
"loss": 4.6415,
|
|
"mean_token_accuracy": 0.22214703261852264,
|
|
"num_tokens": 30068129.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.064983654022217,
|
|
"epoch": 1.2817153067301965,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004848020860517552,
|
|
"loss": 4.7706,
|
|
"mean_token_accuracy": 0.21213543564081191,
|
|
"num_tokens": 30081922.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.059475326538086,
|
|
"epoch": 1.2823108993448482,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000484786686794604,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.2238725319504738,
|
|
"num_tokens": 30095277.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.0869122505187985,
|
|
"epoch": 1.2829064919594997,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.00048477128001274557,
|
|
"loss": 4.7584,
|
|
"mean_token_accuracy": 0.20876907855272292,
|
|
"num_tokens": 30110490.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.097704648971558,
|
|
"epoch": 1.2835020845741512,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048475586570673223,
|
|
"loss": 4.7681,
|
|
"mean_token_accuracy": 0.21307615488767623,
|
|
"num_tokens": 30124082.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.098470783233642,
|
|
"epoch": 1.2840976771888029,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004847404438771172,
|
|
"loss": 4.7565,
|
|
"mean_token_accuracy": 0.20865121781826018,
|
|
"num_tokens": 30137617.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.041198301315307,
|
|
"epoch": 1.2846932698034546,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048472501452445334,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.21254301220178604,
|
|
"num_tokens": 30151354.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.058543157577515,
|
|
"epoch": 1.285288862418106,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004847095776492942,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.2161496326327324,
|
|
"num_tokens": 30165067.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.0409551620483395,
|
|
"epoch": 1.2858844550327575,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048469413325219355,
|
|
"loss": 4.6933,
|
|
"mean_token_accuracy": 0.21881163716316224,
|
|
"num_tokens": 30177484.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.0771173477172855,
|
|
"epoch": 1.2864800476474092,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048467868133370527,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.21093069911003112,
|
|
"num_tokens": 30192765.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.038828706741333,
|
|
"epoch": 1.2870756402620607,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048466322189438354,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.2132812350988388,
|
|
"num_tokens": 30207569.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.061366605758667,
|
|
"epoch": 1.2876712328767124,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048464775493478303,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.2128644958138466,
|
|
"num_tokens": 30221741.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 4.994628763198852,
|
|
"epoch": 1.2882668254913638,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048463228045545837,
|
|
"loss": 4.6469,
|
|
"mean_token_accuracy": 0.2233950138092041,
|
|
"num_tokens": 30237107.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.108135175704956,
|
|
"epoch": 1.2888624181060155,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.00048461679845696466,
|
|
"loss": 4.8116,
|
|
"mean_token_accuracy": 0.21412390023469924,
|
|
"num_tokens": 30251748.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.155687522888184,
|
|
"epoch": 1.289458010720667,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004846013089398572,
|
|
"loss": 4.7105,
|
|
"mean_token_accuracy": 0.2179737865924835,
|
|
"num_tokens": 30265333.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.065202808380127,
|
|
"epoch": 1.2900536033353187,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048458581190469153,
|
|
"loss": 4.7325,
|
|
"mean_token_accuracy": 0.22023010849952698,
|
|
"num_tokens": 30279320.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.0488416194915775,
|
|
"epoch": 1.2906491959499702,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004845703073520236,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.21758912950754167,
|
|
"num_tokens": 30292233.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 4.978660821914673,
|
|
"epoch": 1.2912447885646219,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004845547952824095,
|
|
"loss": 4.734,
|
|
"mean_token_accuracy": 0.21649222671985627,
|
|
"num_tokens": 30305729.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.05220627784729,
|
|
"epoch": 1.2918403811792734,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048453927569640557,
|
|
"loss": 4.7042,
|
|
"mean_token_accuracy": 0.21173890233039855,
|
|
"num_tokens": 30319856.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.077410316467285,
|
|
"epoch": 1.2924359737939248,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048452374859456855,
|
|
"loss": 4.7948,
|
|
"mean_token_accuracy": 0.21713354140520097,
|
|
"num_tokens": 30334774.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.1705962181091305,
|
|
"epoch": 1.2930315664085765,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004845082139774553,
|
|
"loss": 4.7978,
|
|
"mean_token_accuracy": 0.20741339772939682,
|
|
"num_tokens": 30349321.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.037952613830567,
|
|
"epoch": 1.2936271590232282,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004844926718456231,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.22345904856920243,
|
|
"num_tokens": 30362403.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.065132522583008,
|
|
"epoch": 1.2942227516378797,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004844771221996293,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.2146191567182541,
|
|
"num_tokens": 30375156.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.088714981079102,
|
|
"epoch": 1.2948183442525312,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004844615650400318,
|
|
"loss": 4.7305,
|
|
"mean_token_accuracy": 0.2196314662694931,
|
|
"num_tokens": 30390900.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.1661882400512695,
|
|
"epoch": 1.2954139368671829,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048444600036738844,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.2035394638776779,
|
|
"num_tokens": 30405578.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.039736747741699,
|
|
"epoch": 1.2960095294818343,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048443042818225766,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.21182907223701478,
|
|
"num_tokens": 30417539.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.032610988616943,
|
|
"epoch": 1.296605122096486,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048441484848519786,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.21832898557186126,
|
|
"num_tokens": 30429638.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.105026435852051,
|
|
"epoch": 1.2972007147111375,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048439926127676796,
|
|
"loss": 4.7624,
|
|
"mean_token_accuracy": 0.20833118557929992,
|
|
"num_tokens": 30444586.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.055223226547241,
|
|
"epoch": 1.2977963073257892,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00048438366655752707,
|
|
"loss": 4.6812,
|
|
"mean_token_accuracy": 0.2184169337153435,
|
|
"num_tokens": 30459758.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.025353670120239,
|
|
"epoch": 1.2983918999404407,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004843680643280345,
|
|
"loss": 4.7079,
|
|
"mean_token_accuracy": 0.21930186003446578,
|
|
"num_tokens": 30473022.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.074250411987305,
|
|
"epoch": 1.2989874925550924,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004843524545888498,
|
|
"loss": 4.7418,
|
|
"mean_token_accuracy": 0.21866490244865416,
|
|
"num_tokens": 30487008.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.100239324569702,
|
|
"epoch": 1.2995830851697439,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000484336837340533,
|
|
"loss": 4.7672,
|
|
"mean_token_accuracy": 0.21697113513946534,
|
|
"num_tokens": 30500512.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.054620170593262,
|
|
"epoch": 1.3001786777843956,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048432121258364417,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.21323101073503495,
|
|
"num_tokens": 30513754.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.0290450096130375,
|
|
"epoch": 1.300774270399047,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004843055803187438,
|
|
"loss": 4.7154,
|
|
"mean_token_accuracy": 0.21756694763898848,
|
|
"num_tokens": 30529102.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.083279609680176,
|
|
"epoch": 1.3013698630136985,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048428994054639256,
|
|
"loss": 4.659,
|
|
"mean_token_accuracy": 0.23070869743824005,
|
|
"num_tokens": 30541595.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.020699691772461,
|
|
"epoch": 1.3019654556283502,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004842742932671514,
|
|
"loss": 4.6116,
|
|
"mean_token_accuracy": 0.22969114929437637,
|
|
"num_tokens": 30554439.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 4.982890272140503,
|
|
"epoch": 1.302561048243002,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004842586384815817,
|
|
"loss": 4.6859,
|
|
"mean_token_accuracy": 0.22301334589719773,
|
|
"num_tokens": 30569662.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.057023382186889,
|
|
"epoch": 1.3031566408576534,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004842429761902448,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.21957022100687026,
|
|
"num_tokens": 30582815.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.107422971725464,
|
|
"epoch": 1.3037522334723048,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048422730639370256,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.2175888702273369,
|
|
"num_tokens": 30598455.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.08170166015625,
|
|
"epoch": 1.3043478260869565,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004842116290925171,
|
|
"loss": 4.7783,
|
|
"mean_token_accuracy": 0.21203359067440034,
|
|
"num_tokens": 30613063.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.040268325805664,
|
|
"epoch": 1.3049434187016082,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004841959442872505,
|
|
"loss": 4.7553,
|
|
"mean_token_accuracy": 0.2152252197265625,
|
|
"num_tokens": 30628330.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.092995738983154,
|
|
"epoch": 1.3055390113162597,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004841802519784656,
|
|
"loss": 4.7072,
|
|
"mean_token_accuracy": 0.2096129447221756,
|
|
"num_tokens": 30643329.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.0311541080474855,
|
|
"epoch": 1.3061346039309112,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048416455216672525,
|
|
"loss": 4.7193,
|
|
"mean_token_accuracy": 0.21373564451932908,
|
|
"num_tokens": 30658285.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 4.98501672744751,
|
|
"epoch": 1.3067301965455629,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048414884485259235,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.22561901062726974,
|
|
"num_tokens": 30673531.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.052079582214356,
|
|
"epoch": 1.3073257891602144,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004841331300366306,
|
|
"loss": 4.7046,
|
|
"mean_token_accuracy": 0.22079990655183793,
|
|
"num_tokens": 30686339.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.0183549404144285,
|
|
"epoch": 1.307921381774866,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004841174077194033,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.22297889590263367,
|
|
"num_tokens": 30699265.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.0292151927947994,
|
|
"epoch": 1.3085169743895175,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004841016779014747,
|
|
"loss": 4.6774,
|
|
"mean_token_accuracy": 0.22265759110450745,
|
|
"num_tokens": 30712796.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.08302059173584,
|
|
"epoch": 1.3091125670041692,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048408594058340894,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.21711514741182328,
|
|
"num_tokens": 30725986.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.13332462310791,
|
|
"epoch": 1.3097081596188207,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048407019576577037,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.20929431766271592,
|
|
"num_tokens": 30739015.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.0884117603302,
|
|
"epoch": 1.3103037522334722,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004840544434491238,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.2264530450105667,
|
|
"num_tokens": 30751762.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.089567852020264,
|
|
"epoch": 1.3108993448481239,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048403868363403437,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.22019364982843398,
|
|
"num_tokens": 30765015.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.035674142837524,
|
|
"epoch": 1.3114949374627756,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004840229163210671,
|
|
"loss": 4.7596,
|
|
"mean_token_accuracy": 0.21706255674362182,
|
|
"num_tokens": 30777662.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.053467702865601,
|
|
"epoch": 1.312090530077427,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048400714151078774,
|
|
"loss": 4.7383,
|
|
"mean_token_accuracy": 0.21531935185194015,
|
|
"num_tokens": 30790501.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.1365824222564695,
|
|
"epoch": 1.3126861226920785,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048399135920376197,
|
|
"loss": 4.8029,
|
|
"mean_token_accuracy": 0.21340820491313933,
|
|
"num_tokens": 30803410.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.133308219909668,
|
|
"epoch": 1.3132817153067302,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000483975569400556,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.21490296423435212,
|
|
"num_tokens": 30818312.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.066787195205689,
|
|
"epoch": 1.313877307921382,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048395977210173607,
|
|
"loss": 4.7614,
|
|
"mean_token_accuracy": 0.21695376485586165,
|
|
"num_tokens": 30832555.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.0531857967376705,
|
|
"epoch": 1.3144729005360334,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004839439673078689,
|
|
"loss": 4.7245,
|
|
"mean_token_accuracy": 0.2178058370947838,
|
|
"num_tokens": 30847786.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.127396297454834,
|
|
"epoch": 1.3150684931506849,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004839281550195214,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.22128154337406158,
|
|
"num_tokens": 30860512.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.074536752700806,
|
|
"epoch": 1.3156640857653366,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004839123352372606,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.22094912678003312,
|
|
"num_tokens": 30876290.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.069233179092407,
|
|
"epoch": 1.316259678379988,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048389650796165407,
|
|
"loss": 4.7427,
|
|
"mean_token_accuracy": 0.21434062719345093,
|
|
"num_tokens": 30890561.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.042046928405762,
|
|
"epoch": 1.3168552709946397,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048388067319326937,
|
|
"loss": 4.6762,
|
|
"mean_token_accuracy": 0.2258329540491104,
|
|
"num_tokens": 30905149.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.080725431442261,
|
|
"epoch": 1.3174508636092912,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048386483093267464,
|
|
"loss": 4.7244,
|
|
"mean_token_accuracy": 0.2216785028576851,
|
|
"num_tokens": 30918591.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.089390897750855,
|
|
"epoch": 1.318046456223943,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004838489811804379,
|
|
"loss": 4.8236,
|
|
"mean_token_accuracy": 0.20734969675540924,
|
|
"num_tokens": 30933452.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.072166204452515,
|
|
"epoch": 1.3186420488385944,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048383312393712784,
|
|
"loss": 4.7319,
|
|
"mean_token_accuracy": 0.21580897122621537,
|
|
"num_tokens": 30946904.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.052209711074829,
|
|
"epoch": 1.3192376414532458,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004838172592033132,
|
|
"loss": 4.6655,
|
|
"mean_token_accuracy": 0.22075366228818893,
|
|
"num_tokens": 30960598.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.012240076065064,
|
|
"epoch": 1.3198332340678975,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048380138697956294,
|
|
"loss": 4.7271,
|
|
"mean_token_accuracy": 0.21314852684736252,
|
|
"num_tokens": 30973978.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.11098084449768,
|
|
"epoch": 1.3204288266825492,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048378550726644644,
|
|
"loss": 4.7994,
|
|
"mean_token_accuracy": 0.20739504396915437,
|
|
"num_tokens": 30986543.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.135040044784546,
|
|
"epoch": 1.3210244192972007,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048376962006453324,
|
|
"loss": 4.811,
|
|
"mean_token_accuracy": 0.20877470076084137,
|
|
"num_tokens": 31000389.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.100145769119263,
|
|
"epoch": 1.3216200119118522,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004837537253743932,
|
|
"loss": 4.7708,
|
|
"mean_token_accuracy": 0.2178392753005028,
|
|
"num_tokens": 31014252.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.095039510726929,
|
|
"epoch": 1.3222156045265039,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004837378231965965,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.21694895923137664,
|
|
"num_tokens": 31027482.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.030222082138062,
|
|
"epoch": 1.3228111971411556,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048372191353171333,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.21234306544065476,
|
|
"num_tokens": 31041804.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.02154860496521,
|
|
"epoch": 1.323406789755807,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048370599638031464,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.21611257791519164,
|
|
"num_tokens": 31054558.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.193205213546753,
|
|
"epoch": 1.3240023823704585,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048369007174297115,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.21181834042072295,
|
|
"num_tokens": 31069922.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.119004726409912,
|
|
"epoch": 1.3245979749851102,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000483674139620254,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.2162121757864952,
|
|
"num_tokens": 31082170.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.0882080554962155,
|
|
"epoch": 1.3251935675997617,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004836582000127349,
|
|
"loss": 4.7721,
|
|
"mean_token_accuracy": 0.221160626411438,
|
|
"num_tokens": 31095269.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.10098934173584,
|
|
"epoch": 1.3257891602144134,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004836422529209853,
|
|
"loss": 4.7119,
|
|
"mean_token_accuracy": 0.22506955713033677,
|
|
"num_tokens": 31107682.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.090397644042969,
|
|
"epoch": 1.3263847528290649,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00048362629834557743,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.2149156704545021,
|
|
"num_tokens": 31123619.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.160652351379395,
|
|
"epoch": 1.3269803454437166,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048361033628708334,
|
|
"loss": 4.7772,
|
|
"mean_token_accuracy": 0.2140670746564865,
|
|
"num_tokens": 31138806.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.1218674659729,
|
|
"epoch": 1.327575938058368,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048359436674607573,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.21078120768070222,
|
|
"num_tokens": 31153488.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.127497148513794,
|
|
"epoch": 1.3281715306730195,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004835783897231273,
|
|
"loss": 4.7845,
|
|
"mean_token_accuracy": 0.21609201282262802,
|
|
"num_tokens": 31168073.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.013316011428833,
|
|
"epoch": 1.3287671232876712,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00048356240521881113,
|
|
"loss": 4.6972,
|
|
"mean_token_accuracy": 0.22376392483711244,
|
|
"num_tokens": 31181269.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 4.983470392227173,
|
|
"epoch": 1.329362715902323,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004835464132337007,
|
|
"loss": 4.6273,
|
|
"mean_token_accuracy": 0.22186522483825682,
|
|
"num_tokens": 31196690.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.100880289077759,
|
|
"epoch": 1.3299583085169744,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048353041376836937,
|
|
"loss": 4.854,
|
|
"mean_token_accuracy": 0.20929199010133742,
|
|
"num_tokens": 31212832.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.104710912704467,
|
|
"epoch": 1.3305539011316259,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048351440682339126,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.2173945814371109,
|
|
"num_tokens": 31225538.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.0498888969421385,
|
|
"epoch": 1.3311494937462776,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048349839239934035,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.2177090123295784,
|
|
"num_tokens": 31238911.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.052954483032226,
|
|
"epoch": 1.3317450863609293,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048348237049679105,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.21033775806427002,
|
|
"num_tokens": 31253284.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.063226509094238,
|
|
"epoch": 1.3323406789755807,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004834663411163182,
|
|
"loss": 4.6793,
|
|
"mean_token_accuracy": 0.21635152846574784,
|
|
"num_tokens": 31267925.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.097304487228394,
|
|
"epoch": 1.3329362715902322,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004834503042584966,
|
|
"loss": 4.7973,
|
|
"mean_token_accuracy": 0.21067506670951844,
|
|
"num_tokens": 31281957.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.097035217285156,
|
|
"epoch": 1.333531864204884,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004834342599239015,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.21270082145929337,
|
|
"num_tokens": 31297411.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.079129695892334,
|
|
"epoch": 1.3341274568195354,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048341820811310834,
|
|
"loss": 4.7552,
|
|
"mean_token_accuracy": 0.21461350917816163,
|
|
"num_tokens": 31311695.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.102942705154419,
|
|
"epoch": 1.334723049434187,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048340214882669296,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.21714113354682923,
|
|
"num_tokens": 31325149.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.088803768157959,
|
|
"epoch": 1.3353186420488385,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004833860820652314,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.20762055069208146,
|
|
"num_tokens": 31339653.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.133391189575195,
|
|
"epoch": 1.3359142346634902,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004833700078292998,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.21850966215133666,
|
|
"num_tokens": 31352592.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.046467113494873,
|
|
"epoch": 1.3365098272781417,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004833539261194749,
|
|
"loss": 4.7256,
|
|
"mean_token_accuracy": 0.21730366796255113,
|
|
"num_tokens": 31366276.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 4.988755750656128,
|
|
"epoch": 1.3371054198927934,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004833378369363333,
|
|
"loss": 4.6201,
|
|
"mean_token_accuracy": 0.22270160019397736,
|
|
"num_tokens": 31380152.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.068698596954346,
|
|
"epoch": 1.3377010125074449,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004833217402804523,
|
|
"loss": 4.7908,
|
|
"mean_token_accuracy": 0.21652640402317047,
|
|
"num_tokens": 31395388.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.13175778388977,
|
|
"epoch": 1.3382966051220966,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004833056361524092,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.22335366755723954,
|
|
"num_tokens": 31409327.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.011513900756836,
|
|
"epoch": 1.338892197736748,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004832895245527816,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.21787315160036086,
|
|
"num_tokens": 31423069.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 4.99115571975708,
|
|
"epoch": 1.3394877903513995,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004832734054821474,
|
|
"loss": 4.6284,
|
|
"mean_token_accuracy": 0.22509334683418275,
|
|
"num_tokens": 31436494.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.1351806640625,
|
|
"epoch": 1.3400833829660512,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048325727894108487,
|
|
"loss": 4.7807,
|
|
"mean_token_accuracy": 0.22007686346769334,
|
|
"num_tokens": 31450520.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.09600133895874,
|
|
"epoch": 1.340678975580703,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004832411449301723,
|
|
"loss": 4.6648,
|
|
"mean_token_accuracy": 0.22285298258066177,
|
|
"num_tokens": 31463681.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.044473171234131,
|
|
"epoch": 1.3412745681953544,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004832250034499884,
|
|
"loss": 4.7717,
|
|
"mean_token_accuracy": 0.20997408628463746,
|
|
"num_tokens": 31479677.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.057120084762573,
|
|
"epoch": 1.3418701608100059,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004832088545011122,
|
|
"loss": 4.7437,
|
|
"mean_token_accuracy": 0.21488965451717376,
|
|
"num_tokens": 31493880.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.010081338882446,
|
|
"epoch": 1.3424657534246576,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004831926980841229,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.21551918983459473,
|
|
"num_tokens": 31507044.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 4.993059968948364,
|
|
"epoch": 1.343061346039309,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048317653419960007,
|
|
"loss": 4.6458,
|
|
"mean_token_accuracy": 0.2227797031402588,
|
|
"num_tokens": 31519903.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.023637533187866,
|
|
"epoch": 1.3436569386539607,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048316036284812335,
|
|
"loss": 4.6721,
|
|
"mean_token_accuracy": 0.2220311090350151,
|
|
"num_tokens": 31534015.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 4.963773155212403,
|
|
"epoch": 1.3442525312686122,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004831441840302729,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.2296604484319687,
|
|
"num_tokens": 31549980.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.096844244003296,
|
|
"epoch": 1.344848123883264,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00048312799774662905,
|
|
"loss": 4.7453,
|
|
"mean_token_accuracy": 0.2170630946755409,
|
|
"num_tokens": 31563550.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.016311550140381,
|
|
"epoch": 1.3454437164979154,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004831118039977722,
|
|
"loss": 4.6189,
|
|
"mean_token_accuracy": 0.22846042662858962,
|
|
"num_tokens": 31576552.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.030277299880981,
|
|
"epoch": 1.346039309112567,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004830956027842834,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.21431634277105333,
|
|
"num_tokens": 31592423.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.098979139328003,
|
|
"epoch": 1.3466349017272186,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004830793941067437,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.2173745721578598,
|
|
"num_tokens": 31606166.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.055399942398071,
|
|
"epoch": 1.3472304943418703,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048306317796573426,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.21300651431083678,
|
|
"num_tokens": 31622342.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.024492025375366,
|
|
"epoch": 1.3478260869565217,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004830469543618371,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.21758272051811217,
|
|
"num_tokens": 31634784.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.1000336647033695,
|
|
"epoch": 1.3484216795711732,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004830307232956339,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.21391461044549942,
|
|
"num_tokens": 31648871.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.124278354644775,
|
|
"epoch": 1.349017272185825,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004830144847677069,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.21866867393255235,
|
|
"num_tokens": 31662066.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.020068073272705,
|
|
"epoch": 1.3496128648004766,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048299823877863857,
|
|
"loss": 4.6583,
|
|
"mean_token_accuracy": 0.22264743000268936,
|
|
"num_tokens": 31675439.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.0761942863464355,
|
|
"epoch": 1.350208457415128,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004829819853290116,
|
|
"loss": 4.6847,
|
|
"mean_token_accuracy": 0.22342778891324996,
|
|
"num_tokens": 31688670.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.043859195709229,
|
|
"epoch": 1.3508040500297795,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004829657244194089,
|
|
"loss": 4.7515,
|
|
"mean_token_accuracy": 0.21722293198108672,
|
|
"num_tokens": 31704749.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.042710685729981,
|
|
"epoch": 1.3513996426444312,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048294945605041384,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.2157512426376343,
|
|
"num_tokens": 31717530.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.078386402130127,
|
|
"epoch": 1.3519952352590827,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048293318022260995,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.2108689159154892,
|
|
"num_tokens": 31731683.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.027771997451782,
|
|
"epoch": 1.3525908278737344,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004829168969365809,
|
|
"loss": 4.6856,
|
|
"mean_token_accuracy": 0.21816764771938324,
|
|
"num_tokens": 31745841.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.0766880989074705,
|
|
"epoch": 1.3531864204883859,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048290060619291084,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.21258434057235717,
|
|
"num_tokens": 31760634.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.0325658321380615,
|
|
"epoch": 1.3537820131030376,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048288430799218394,
|
|
"loss": 4.6194,
|
|
"mean_token_accuracy": 0.23003166615962983,
|
|
"num_tokens": 31774759.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.118846988677978,
|
|
"epoch": 1.354377605717689,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004828680023349851,
|
|
"loss": 4.8718,
|
|
"mean_token_accuracy": 0.1992761269211769,
|
|
"num_tokens": 31789531.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.011839532852173,
|
|
"epoch": 1.3549731983323408,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048285168922189886,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.21828421652317048,
|
|
"num_tokens": 31802896.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.1339499950408936,
|
|
"epoch": 1.3555687909469922,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048283536865351053,
|
|
"loss": 4.7889,
|
|
"mean_token_accuracy": 0.21092680841684341,
|
|
"num_tokens": 31816205.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.066387176513672,
|
|
"epoch": 1.356164383561644,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004828190406304054,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.21870915591716766,
|
|
"num_tokens": 31831590.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.097203302383423,
|
|
"epoch": 1.3567599761762954,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004828027051531692,
|
|
"loss": 4.7696,
|
|
"mean_token_accuracy": 0.21502708941698073,
|
|
"num_tokens": 31845063.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.072376251220703,
|
|
"epoch": 1.3573555687909469,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048278636222238785,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.21753996908664702,
|
|
"num_tokens": 31858417.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.041041040420533,
|
|
"epoch": 1.3579511614055986,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00048277001183864756,
|
|
"loss": 4.639,
|
|
"mean_token_accuracy": 0.22286647707223892,
|
|
"num_tokens": 31874634.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.0900774002075195,
|
|
"epoch": 1.3585467540202503,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004827536540025347,
|
|
"loss": 4.7742,
|
|
"mean_token_accuracy": 0.2156004250049591,
|
|
"num_tokens": 31888020.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.123513412475586,
|
|
"epoch": 1.3591423466349017,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004827372887146361,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.2069798842072487,
|
|
"num_tokens": 31903634.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.155634355545044,
|
|
"epoch": 1.3597379392495532,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00048272091597553865,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.20767731815576554,
|
|
"num_tokens": 31918844.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.120942878723144,
|
|
"epoch": 1.360333531864205,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048270453578582974,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.21227542012929917,
|
|
"num_tokens": 31932752.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.089857912063598,
|
|
"epoch": 1.3609291244788564,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004826881481460968,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.22560051828622818,
|
|
"num_tokens": 31945630.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.097190999984742,
|
|
"epoch": 1.361524717093508,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048267175305692774,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.22187815457582474,
|
|
"num_tokens": 31958640.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.158788824081421,
|
|
"epoch": 1.3621203097081596,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004826553505189104,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.20436090528964995,
|
|
"num_tokens": 31975502.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.046694374084472,
|
|
"epoch": 1.3627159023228113,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004826389405326334,
|
|
"loss": 4.7082,
|
|
"mean_token_accuracy": 0.21618981659412384,
|
|
"num_tokens": 31990017.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.09462890625,
|
|
"epoch": 1.3633114949374627,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004826225230986851,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.21425883024930953,
|
|
"num_tokens": 32002924.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.095749998092652,
|
|
"epoch": 1.3639070875521144,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00048260609821765456,
|
|
"loss": 4.7371,
|
|
"mean_token_accuracy": 0.21493084728717804,
|
|
"num_tokens": 32017769.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.127890586853027,
|
|
"epoch": 1.364502680166766,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004825896658901308,
|
|
"loss": 4.7541,
|
|
"mean_token_accuracy": 0.213665409386158,
|
|
"num_tokens": 32031991.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.055881118774414,
|
|
"epoch": 1.3650982727814176,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048257322611670324,
|
|
"loss": 4.6776,
|
|
"mean_token_accuracy": 0.22035957872867584,
|
|
"num_tokens": 32046294.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 4.997611665725708,
|
|
"epoch": 1.365693865396069,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048255677889796157,
|
|
"loss": 4.636,
|
|
"mean_token_accuracy": 0.21870196610689163,
|
|
"num_tokens": 32059737.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.025827932357788,
|
|
"epoch": 1.3662894580107205,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004825403242344957,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.22681792974472045,
|
|
"num_tokens": 32074372.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.072030735015869,
|
|
"epoch": 1.3668850506253722,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004825238621268958,
|
|
"loss": 4.7474,
|
|
"mean_token_accuracy": 0.21266285330057144,
|
|
"num_tokens": 32089770.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.039112520217896,
|
|
"epoch": 1.367480643240024,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004825073925757524,
|
|
"loss": 4.7032,
|
|
"mean_token_accuracy": 0.2235300287604332,
|
|
"num_tokens": 32106162.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.124636030197143,
|
|
"epoch": 1.3680762358546754,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004824909155816562,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.20698558092117308,
|
|
"num_tokens": 32120103.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.053502607345581,
|
|
"epoch": 1.368671828469327,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048247443114519825,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.22013691514730455,
|
|
"num_tokens": 32133866.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.147813510894776,
|
|
"epoch": 1.3692674210839786,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004824579392669698,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.2137511342763901,
|
|
"num_tokens": 32148287.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.101438426971436,
|
|
"epoch": 1.36986301369863,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048244143994756233,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.22338877469301224,
|
|
"num_tokens": 32161838.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.035252857208252,
|
|
"epoch": 1.3704586063132818,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004824249331875677,
|
|
"loss": 4.6601,
|
|
"mean_token_accuracy": 0.22367780655622482,
|
|
"num_tokens": 32175792.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.03784966468811,
|
|
"epoch": 1.3710541989279332,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00048240841898757796,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.21913717389106752,
|
|
"num_tokens": 32189976.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.062728404998779,
|
|
"epoch": 1.371649791542585,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004823918973481855,
|
|
"loss": 4.7873,
|
|
"mean_token_accuracy": 0.21111484318971635,
|
|
"num_tokens": 32204446.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.153810024261475,
|
|
"epoch": 1.3722453841572364,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00048237536826998287,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.21085356771945954,
|
|
"num_tokens": 32218988.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.075260496139526,
|
|
"epoch": 1.372840976771888,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000482358831753563,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.21972356289625167,
|
|
"num_tokens": 32231659.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.0025146484375,
|
|
"epoch": 1.3734365693865396,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048234228779951883,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.22411320209503174,
|
|
"num_tokens": 32245026.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.066265058517456,
|
|
"epoch": 1.3740321620011913,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048232573640844407,
|
|
"loss": 4.6809,
|
|
"mean_token_accuracy": 0.22519971132278443,
|
|
"num_tokens": 32259580.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.080045223236084,
|
|
"epoch": 1.3746277546158427,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004823091775809321,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.213801509141922,
|
|
"num_tokens": 32272329.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.031409215927124,
|
|
"epoch": 1.3752233472304942,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00048229261131757707,
|
|
"loss": 4.7376,
|
|
"mean_token_accuracy": 0.21861480474472045,
|
|
"num_tokens": 32288036.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.168716287612915,
|
|
"epoch": 1.375818939845146,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048227603761897316,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.21076941937208177,
|
|
"num_tokens": 32302517.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.07962589263916,
|
|
"epoch": 1.3764145324597976,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048225945648571475,
|
|
"loss": 4.6931,
|
|
"mean_token_accuracy": 0.22622760534286498,
|
|
"num_tokens": 32315576.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.051055574417115,
|
|
"epoch": 1.377010125074449,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048224286791839657,
|
|
"loss": 4.7121,
|
|
"mean_token_accuracy": 0.22066350430250167,
|
|
"num_tokens": 32330321.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.031341934204102,
|
|
"epoch": 1.3776057176891006,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004822262719176137,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.22118569016456605,
|
|
"num_tokens": 32344397.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.1401283740997314,
|
|
"epoch": 1.3782013103037523,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048220966848396137,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.2147457167506218,
|
|
"num_tokens": 32360071.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.159193277359009,
|
|
"epoch": 1.3787969029184037,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004821930576180352,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.20695073455572127,
|
|
"num_tokens": 32375577.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.092804861068726,
|
|
"epoch": 1.3793924955330554,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004821764393204308,
|
|
"loss": 4.8046,
|
|
"mean_token_accuracy": 0.20939054489135742,
|
|
"num_tokens": 32389481.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.042354154586792,
|
|
"epoch": 1.379988088147707,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004821598135917445,
|
|
"loss": 4.7389,
|
|
"mean_token_accuracy": 0.218664513528347,
|
|
"num_tokens": 32401993.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.119625616073608,
|
|
"epoch": 1.3805836807623586,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048214318043257246,
|
|
"loss": 4.769,
|
|
"mean_token_accuracy": 0.2193256825208664,
|
|
"num_tokens": 32416074.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.089552545547486,
|
|
"epoch": 1.38117927337701,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004821265398435113,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.21464160531759263,
|
|
"num_tokens": 32430477.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.096119737625122,
|
|
"epoch": 1.3817748659916618,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000482109891825158,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.2150210291147232,
|
|
"num_tokens": 32443649.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 4.993436193466186,
|
|
"epoch": 1.3823704586063132,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004820932363781096,
|
|
"loss": 4.6255,
|
|
"mean_token_accuracy": 0.23210172355175018,
|
|
"num_tokens": 32456250.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 4.9685155868530275,
|
|
"epoch": 1.382966051220965,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048207657350296345,
|
|
"loss": 4.5979,
|
|
"mean_token_accuracy": 0.229691843688488,
|
|
"num_tokens": 32469634.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.045833539962769,
|
|
"epoch": 1.3835616438356164,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048205990320031734,
|
|
"loss": 4.6935,
|
|
"mean_token_accuracy": 0.2199987679719925,
|
|
"num_tokens": 32484222.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.115152883529663,
|
|
"epoch": 1.384157236450268,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048204322547076915,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.2213268533349037,
|
|
"num_tokens": 32498736.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.05445442199707,
|
|
"epoch": 1.3847528290649196,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048202654031491714,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.22272140085697173,
|
|
"num_tokens": 32513267.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.117616653442383,
|
|
"epoch": 1.3853484216795713,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048200984773335973,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.21458523273468016,
|
|
"num_tokens": 32527398.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.1044965267181395,
|
|
"epoch": 1.3859440142942228,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004819931477266956,
|
|
"loss": 4.732,
|
|
"mean_token_accuracy": 0.22136171609163285,
|
|
"num_tokens": 32539167.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.0567480564117435,
|
|
"epoch": 1.3865396069088742,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004819764402955239,
|
|
"loss": 4.7346,
|
|
"mean_token_accuracy": 0.21604181528091432,
|
|
"num_tokens": 32553336.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 4.9958740234375,
|
|
"epoch": 1.387135199523526,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048195972544044373,
|
|
"loss": 4.6365,
|
|
"mean_token_accuracy": 0.2300974652171135,
|
|
"num_tokens": 32567753.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.101123952865601,
|
|
"epoch": 1.3877307921381774,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048194300316205474,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.21408733278512954,
|
|
"num_tokens": 32583662.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.075639820098877,
|
|
"epoch": 1.388326384752829,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004819262734609567,
|
|
"loss": 4.7458,
|
|
"mean_token_accuracy": 0.21042614430189133,
|
|
"num_tokens": 32597430.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.029100561141968,
|
|
"epoch": 1.3889219773674806,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004819095363377496,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.21791814565658568,
|
|
"num_tokens": 32610753.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 4.973086166381836,
|
|
"epoch": 1.3895175699821323,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004818927917930339,
|
|
"loss": 4.5533,
|
|
"mean_token_accuracy": 0.22695547193288804,
|
|
"num_tokens": 32625296.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.010429000854492,
|
|
"epoch": 1.3901131625967837,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048187603982741015,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.21984317451715468,
|
|
"num_tokens": 32638333.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.02512526512146,
|
|
"epoch": 1.3907087552114354,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004818592804414792,
|
|
"loss": 4.6387,
|
|
"mean_token_accuracy": 0.22388714402914048,
|
|
"num_tokens": 32650230.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.05174765586853,
|
|
"epoch": 1.391304347826087,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004818425136358422,
|
|
"loss": 4.7189,
|
|
"mean_token_accuracy": 0.21915105134248733,
|
|
"num_tokens": 32664641.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.004005336761475,
|
|
"epoch": 1.3918999404407386,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048182573941110056,
|
|
"loss": 4.672,
|
|
"mean_token_accuracy": 0.22145168483257294,
|
|
"num_tokens": 32678576.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.066016769409179,
|
|
"epoch": 1.39249553305539,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004818089577678559,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.2222983568906784,
|
|
"num_tokens": 32692072.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.162147474288941,
|
|
"epoch": 1.3930911256700416,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004817921687067102,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.20827081203460693,
|
|
"num_tokens": 32705926.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 4.974842834472656,
|
|
"epoch": 1.3936867182846933,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004817753722282656,
|
|
"loss": 4.6448,
|
|
"mean_token_accuracy": 0.22611845880746842,
|
|
"num_tokens": 32720028.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.066312408447265,
|
|
"epoch": 1.394282310899345,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048175856833312464,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.217474864423275,
|
|
"num_tokens": 32732690.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.052346324920654,
|
|
"epoch": 1.3948779035139964,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00048174175702189,
|
|
"loss": 4.6741,
|
|
"mean_token_accuracy": 0.218348528444767,
|
|
"num_tokens": 32747239.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.005296993255615,
|
|
"epoch": 1.395473496128648,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048172493829516465,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.21931453794240952,
|
|
"num_tokens": 32760354.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.05213418006897,
|
|
"epoch": 1.3960690887432996,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004817081121535518,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.21954465508461,
|
|
"num_tokens": 32774123.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.153839540481568,
|
|
"epoch": 1.3966646813579513,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004816912785976552,
|
|
"loss": 4.7797,
|
|
"mean_token_accuracy": 0.21525011211633682,
|
|
"num_tokens": 32786507.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.0845356464385985,
|
|
"epoch": 1.3972602739726028,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048167443762807844,
|
|
"loss": 4.76,
|
|
"mean_token_accuracy": 0.20651343166828157,
|
|
"num_tokens": 32801897.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.068655490875244,
|
|
"epoch": 1.3978558665872542,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004816575892454256,
|
|
"loss": 4.6697,
|
|
"mean_token_accuracy": 0.22549413591623307,
|
|
"num_tokens": 32815177.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 4.967803430557251,
|
|
"epoch": 1.398451459201906,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000481640733450301,
|
|
"loss": 4.6686,
|
|
"mean_token_accuracy": 0.2215548887848854,
|
|
"num_tokens": 32830167.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.071217823028564,
|
|
"epoch": 1.3990470518165574,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004816238702433094,
|
|
"loss": 4.7972,
|
|
"mean_token_accuracy": 0.21310804933309554,
|
|
"num_tokens": 32844125.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.087400197982788,
|
|
"epoch": 1.3996426444312091,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00048160699962505546,
|
|
"loss": 4.7224,
|
|
"mean_token_accuracy": 0.2205464944243431,
|
|
"num_tokens": 32857939.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.058020544052124,
|
|
"epoch": 1.4002382370458606,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048159012159614434,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.21432932764291762,
|
|
"num_tokens": 32871251.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.102020215988159,
|
|
"epoch": 1.4008338296605123,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004815732361571815,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.21768440902233124,
|
|
"num_tokens": 32885202.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.145025825500488,
|
|
"epoch": 1.4014294222751638,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048155634330877253,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.22200582176446915,
|
|
"num_tokens": 32898538.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.094930648803711,
|
|
"epoch": 1.4020250148898152,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004815394430515234,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.2129603385925293,
|
|
"num_tokens": 32913902.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.0835777759552006,
|
|
"epoch": 1.402620607504467,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004815225353860402,
|
|
"loss": 4.7532,
|
|
"mean_token_accuracy": 0.21949098706245423,
|
|
"num_tokens": 32927830.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.043529224395752,
|
|
"epoch": 1.4032162001191186,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004815056203129294,
|
|
"loss": 4.7199,
|
|
"mean_token_accuracy": 0.22420599907636643,
|
|
"num_tokens": 32942808.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.120472812652588,
|
|
"epoch": 1.40381179273377,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004814886978327978,
|
|
"loss": 4.718,
|
|
"mean_token_accuracy": 0.2169526994228363,
|
|
"num_tokens": 32955300.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.0734290599823,
|
|
"epoch": 1.4044073853484216,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048147176794625235,
|
|
"loss": 4.7485,
|
|
"mean_token_accuracy": 0.22043306678533553,
|
|
"num_tokens": 32970138.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.106266736984253,
|
|
"epoch": 1.4050029779630733,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004814548306539003,
|
|
"loss": 4.7216,
|
|
"mean_token_accuracy": 0.22401514798402786,
|
|
"num_tokens": 32983476.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.063552618026733,
|
|
"epoch": 1.405598570577725,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00048143788595634917,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.22093886137008667,
|
|
"num_tokens": 32996026.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.000244665145874,
|
|
"epoch": 1.4061941631923764,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004814209338542067,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.21844443529844285,
|
|
"num_tokens": 33008470.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.027036237716675,
|
|
"epoch": 1.406789755807028,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048140397434808094,
|
|
"loss": 4.7076,
|
|
"mean_token_accuracy": 0.21541028171777726,
|
|
"num_tokens": 33022753.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.063163566589355,
|
|
"epoch": 1.4073853484216796,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048138700743858014,
|
|
"loss": 4.6998,
|
|
"mean_token_accuracy": 0.2197207659482956,
|
|
"num_tokens": 33036426.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.032067537307739,
|
|
"epoch": 1.407980941036331,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048137003312631306,
|
|
"loss": 4.6275,
|
|
"mean_token_accuracy": 0.22337885946035385,
|
|
"num_tokens": 33050906.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.081051349639893,
|
|
"epoch": 1.4085765336509828,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004813530514118884,
|
|
"loss": 4.7642,
|
|
"mean_token_accuracy": 0.2212464317679405,
|
|
"num_tokens": 33066188.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 4.976536130905151,
|
|
"epoch": 1.4091721262656343,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00048133606229591524,
|
|
"loss": 4.6019,
|
|
"mean_token_accuracy": 0.22858250588178636,
|
|
"num_tokens": 33080169.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 4.981825351715088,
|
|
"epoch": 1.409767718880286,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004813190657790031,
|
|
"loss": 4.6705,
|
|
"mean_token_accuracy": 0.22401565611362456,
|
|
"num_tokens": 33093764.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.102593851089478,
|
|
"epoch": 1.4103633114949374,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048130206186176145,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.22323435246944429,
|
|
"num_tokens": 33105689.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.061794710159302,
|
|
"epoch": 1.410958904109589,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00048128505054480036,
|
|
"loss": 4.6745,
|
|
"mean_token_accuracy": 0.21805505454540253,
|
|
"num_tokens": 33119600.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.110891199111938,
|
|
"epoch": 1.4115544967242406,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004812680318287298,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.21577504873275757,
|
|
"num_tokens": 33133531.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.044692945480347,
|
|
"epoch": 1.4121500893388923,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004812510057141603,
|
|
"loss": 4.6661,
|
|
"mean_token_accuracy": 0.2300171822309494,
|
|
"num_tokens": 33147856.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.04670524597168,
|
|
"epoch": 1.4127456819535438,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004812339722017027,
|
|
"loss": 4.6888,
|
|
"mean_token_accuracy": 0.22278024554252623,
|
|
"num_tokens": 33162842.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.059482765197754,
|
|
"epoch": 1.4133412745681952,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004812169312919677,
|
|
"loss": 4.7102,
|
|
"mean_token_accuracy": 0.22212059795856476,
|
|
"num_tokens": 33176125.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 4.991553258895874,
|
|
"epoch": 1.413936867182847,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048119988298556674,
|
|
"loss": 4.5654,
|
|
"mean_token_accuracy": 0.2313411757349968,
|
|
"num_tokens": 33188738.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.00766544342041,
|
|
"epoch": 1.4145324597974986,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004811828272831112,
|
|
"loss": 4.6343,
|
|
"mean_token_accuracy": 0.22844806909561158,
|
|
"num_tokens": 33201176.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.060025215148926,
|
|
"epoch": 1.4151280524121501,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004811657641852129,
|
|
"loss": 4.7373,
|
|
"mean_token_accuracy": 0.2174808129668236,
|
|
"num_tokens": 33216250.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.033420753479004,
|
|
"epoch": 1.4157236450268016,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048114869369248386,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.21835822761058807,
|
|
"num_tokens": 33229327.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.037370443344116,
|
|
"epoch": 1.4163192376414533,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004811316158055363,
|
|
"loss": 4.6447,
|
|
"mean_token_accuracy": 0.22662704437971115,
|
|
"num_tokens": 33241008.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.035754442214966,
|
|
"epoch": 1.4169148302561048,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004811145305249828,
|
|
"loss": 4.6885,
|
|
"mean_token_accuracy": 0.22452384680509568,
|
|
"num_tokens": 33254294.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.068304634094238,
|
|
"epoch": 1.4175104228707565,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048109743785143636,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.2278464362025261,
|
|
"num_tokens": 33265769.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.015622234344482,
|
|
"epoch": 1.418106015485408,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004810803377855098,
|
|
"loss": 4.7098,
|
|
"mean_token_accuracy": 0.21861372888088226,
|
|
"num_tokens": 33279410.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.06467981338501,
|
|
"epoch": 1.4187016081000596,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004810632303278166,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.2109507605433464,
|
|
"num_tokens": 33295324.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.119071435928345,
|
|
"epoch": 1.419297200714711,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004810461154789704,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.21444704681634902,
|
|
"num_tokens": 33308592.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.16024227142334,
|
|
"epoch": 1.4198927933293626,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000481028993239585,
|
|
"loss": 4.7852,
|
|
"mean_token_accuracy": 0.21388337910175323,
|
|
"num_tokens": 33323711.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.0415691375732425,
|
|
"epoch": 1.4204883859440143,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004810118636102747,
|
|
"loss": 4.7128,
|
|
"mean_token_accuracy": 0.21771081686019897,
|
|
"num_tokens": 33337170.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.069676113128662,
|
|
"epoch": 1.421083978558666,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004809947265916537,
|
|
"loss": 4.7669,
|
|
"mean_token_accuracy": 0.21766830682754518,
|
|
"num_tokens": 33351458.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.026064014434814,
|
|
"epoch": 1.4216795711733174,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048097758218433687,
|
|
"loss": 4.6063,
|
|
"mean_token_accuracy": 0.22939806133508683,
|
|
"num_tokens": 33364274.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.090905809402466,
|
|
"epoch": 1.422275163787969,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00048096043038893895,
|
|
"loss": 4.6854,
|
|
"mean_token_accuracy": 0.21837983876466752,
|
|
"num_tokens": 33376599.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.077727603912353,
|
|
"epoch": 1.4228707564026206,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048094327120607534,
|
|
"loss": 4.757,
|
|
"mean_token_accuracy": 0.21484435647726058,
|
|
"num_tokens": 33391350.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.0138843059539795,
|
|
"epoch": 1.4234663490172723,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048092610463636143,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.21436878889799119,
|
|
"num_tokens": 33404892.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 4.98410062789917,
|
|
"epoch": 1.4240619416319238,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000480908930680413,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.22696707248687745,
|
|
"num_tokens": 33419051.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.077661418914795,
|
|
"epoch": 1.4246575342465753,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048089174933884597,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.2174428343772888,
|
|
"num_tokens": 33430871.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.033153533935547,
|
|
"epoch": 1.425253126861227,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048087456061227666,
|
|
"loss": 4.7229,
|
|
"mean_token_accuracy": 0.21792744398117064,
|
|
"num_tokens": 33442616.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.153709363937378,
|
|
"epoch": 1.4258487194758784,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048085736450132155,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.21315640211105347,
|
|
"num_tokens": 33456087.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.110468482971191,
|
|
"epoch": 1.4264443120905301,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048084016100659755,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.21663060188293456,
|
|
"num_tokens": 33468369.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.0722737312316895,
|
|
"epoch": 1.4270399047051816,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004808229501287216,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.22649600803852082,
|
|
"num_tokens": 33482281.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.057223892211914,
|
|
"epoch": 1.4276354973198333,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048080573186831113,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.21808789074420928,
|
|
"num_tokens": 33495863.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.080247688293457,
|
|
"epoch": 1.4282310899344848,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00048078850622598355,
|
|
"loss": 4.7055,
|
|
"mean_token_accuracy": 0.21563262939453126,
|
|
"num_tokens": 33510069.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.012764644622803,
|
|
"epoch": 1.4288266825491365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048077127320235696,
|
|
"loss": 4.6419,
|
|
"mean_token_accuracy": 0.22489882707595826,
|
|
"num_tokens": 33521835.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.062993001937866,
|
|
"epoch": 1.429422275163788,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048075403279804934,
|
|
"loss": 4.778,
|
|
"mean_token_accuracy": 0.21742826253175734,
|
|
"num_tokens": 33535239.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.429422275163788,
|
|
"eval_entropy": 4.8367443293987025,
|
|
"eval_loss": 4.731573581695557,
|
|
"eval_mean_token_accuracy": 0.22793991289635812,
|
|
"eval_num_tokens": 33535239.0,
|
|
"eval_runtime": 18.5255,
|
|
"eval_samples_per_second": 1377.181,
|
|
"eval_steps_per_second": 172.195,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.038848924636841,
|
|
"epoch": 1.4300178677784396,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004807367850136791,
|
|
"loss": 4.6481,
|
|
"mean_token_accuracy": 0.22441351264715195,
|
|
"num_tokens": 33548212.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.064572525024414,
|
|
"epoch": 1.4306134603930911,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004807195298498649,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.21985796540975572,
|
|
"num_tokens": 33562316.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.148642444610596,
|
|
"epoch": 1.4312090530077426,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004807022673072257,
|
|
"loss": 4.7571,
|
|
"mean_token_accuracy": 0.20930841118097304,
|
|
"num_tokens": 33576278.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.067405271530151,
|
|
"epoch": 1.4318046456223943,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048068499738638046,
|
|
"loss": 4.745,
|
|
"mean_token_accuracy": 0.21932825893163682,
|
|
"num_tokens": 33591021.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.002247905731201,
|
|
"epoch": 1.432400238237046,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004806677200879489,
|
|
"loss": 4.7176,
|
|
"mean_token_accuracy": 0.21490338295698166,
|
|
"num_tokens": 33605225.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.152834177017212,
|
|
"epoch": 1.4329958308516975,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004806504354125505,
|
|
"loss": 4.8058,
|
|
"mean_token_accuracy": 0.21247390359640123,
|
|
"num_tokens": 33618586.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.133539009094238,
|
|
"epoch": 1.433591423466349,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048063314336080554,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.2167971670627594,
|
|
"num_tokens": 33631036.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.032905578613281,
|
|
"epoch": 1.4341870160810006,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004806158439333339,
|
|
"loss": 4.7013,
|
|
"mean_token_accuracy": 0.21670194417238237,
|
|
"num_tokens": 33644942.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 4.988222694396972,
|
|
"epoch": 1.434782608695652,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00048059853713075637,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.22054003477096557,
|
|
"num_tokens": 33659005.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.10460352897644,
|
|
"epoch": 1.4353782013103038,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048058122295369354,
|
|
"loss": 4.7228,
|
|
"mean_token_accuracy": 0.21802744269371033,
|
|
"num_tokens": 33672345.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.094517374038697,
|
|
"epoch": 1.4359737939249553,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004805639014027665,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.22004333287477493,
|
|
"num_tokens": 33686938.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.039472913742065,
|
|
"epoch": 1.436569386539607,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004805465724785966,
|
|
"loss": 4.6993,
|
|
"mean_token_accuracy": 0.21925622522830962,
|
|
"num_tokens": 33702145.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.0241481304168705,
|
|
"epoch": 1.4371649791542584,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004805292361818053,
|
|
"loss": 4.7127,
|
|
"mean_token_accuracy": 0.21017751097679138,
|
|
"num_tokens": 33716127.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.081352853775025,
|
|
"epoch": 1.4377605717689101,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048051189251301443,
|
|
"loss": 4.7289,
|
|
"mean_token_accuracy": 0.2160069540143013,
|
|
"num_tokens": 33731309.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.0329179763793945,
|
|
"epoch": 1.4383561643835616,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004804945414728461,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.21999288201332093,
|
|
"num_tokens": 33745632.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.051529407501221,
|
|
"epoch": 1.4389517569982133,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004804771830619227,
|
|
"loss": 4.6865,
|
|
"mean_token_accuracy": 0.21489603966474533,
|
|
"num_tokens": 33757623.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.139676427841186,
|
|
"epoch": 1.4395473496128648,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00048045981728086687,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.2159440979361534,
|
|
"num_tokens": 33772072.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.090579557418823,
|
|
"epoch": 1.4401429422275163,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004804424441303015,
|
|
"loss": 4.727,
|
|
"mean_token_accuracy": 0.21501891016960145,
|
|
"num_tokens": 33786548.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.040834379196167,
|
|
"epoch": 1.440738534842168,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004804250636108496,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.22031953930854797,
|
|
"num_tokens": 33800872.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.134340143203735,
|
|
"epoch": 1.4413341274568197,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004804076757231347,
|
|
"loss": 4.7302,
|
|
"mean_token_accuracy": 0.21435551941394806,
|
|
"num_tokens": 33813487.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.00128870010376,
|
|
"epoch": 1.4419297200714711,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048039028046778043,
|
|
"loss": 4.5778,
|
|
"mean_token_accuracy": 0.22630486786365508,
|
|
"num_tokens": 33827971.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.0043710231781,
|
|
"epoch": 1.4425253126861226,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004803728778454108,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.22827865779399872,
|
|
"num_tokens": 33841454.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 4.994539737701416,
|
|
"epoch": 1.4431209053007743,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00048035546785664987,
|
|
"loss": 4.5889,
|
|
"mean_token_accuracy": 0.22634148448705674,
|
|
"num_tokens": 33855893.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.078408575057983,
|
|
"epoch": 1.4437164979154258,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004803380505021222,
|
|
"loss": 4.7071,
|
|
"mean_token_accuracy": 0.21710858941078187,
|
|
"num_tokens": 33869803.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.089882898330688,
|
|
"epoch": 1.4443120905300775,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048032062578245256,
|
|
"loss": 4.693,
|
|
"mean_token_accuracy": 0.2081276521086693,
|
|
"num_tokens": 33882898.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 4.969322347640992,
|
|
"epoch": 1.444907683144729,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00048030319369826594,
|
|
"loss": 4.6605,
|
|
"mean_token_accuracy": 0.21661606431007385,
|
|
"num_tokens": 33897738.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.000808763504028,
|
|
"epoch": 1.4455032757593806,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004802857542501875,
|
|
"loss": 4.6009,
|
|
"mean_token_accuracy": 0.22510936856269836,
|
|
"num_tokens": 33911450.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.073541593551636,
|
|
"epoch": 1.4460988683740321,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048026830743884283,
|
|
"loss": 4.7383,
|
|
"mean_token_accuracy": 0.21973592787981033,
|
|
"num_tokens": 33924879.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.072075414657593,
|
|
"epoch": 1.4466944609886838,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004802508532648578,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.21973206400871276,
|
|
"num_tokens": 33938450.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.051617622375488,
|
|
"epoch": 1.4472900536033353,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004802333917288583,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.21118358224630357,
|
|
"num_tokens": 33952263.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.026338958740235,
|
|
"epoch": 1.447885646217987,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048021592283147073,
|
|
"loss": 4.6944,
|
|
"mean_token_accuracy": 0.22136543542146683,
|
|
"num_tokens": 33964501.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.003921270370483,
|
|
"epoch": 1.4484812388326385,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00048019844657332166,
|
|
"loss": 4.674,
|
|
"mean_token_accuracy": 0.2263241797685623,
|
|
"num_tokens": 33979755.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.136258172988891,
|
|
"epoch": 1.44907683144729,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000480180962955038,
|
|
"loss": 4.7978,
|
|
"mean_token_accuracy": 0.21591573655605317,
|
|
"num_tokens": 33995351.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.061842346191407,
|
|
"epoch": 1.4496724240619416,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048016347197724676,
|
|
"loss": 4.6878,
|
|
"mean_token_accuracy": 0.23008736371994018,
|
|
"num_tokens": 34008245.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.113459682464599,
|
|
"epoch": 1.4502680166765933,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004801459736405754,
|
|
"loss": 4.781,
|
|
"mean_token_accuracy": 0.21825651973485946,
|
|
"num_tokens": 34022434.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.019912624359131,
|
|
"epoch": 1.4508636092912448,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00048012846794565143,
|
|
"loss": 4.6803,
|
|
"mean_token_accuracy": 0.22168605029582977,
|
|
"num_tokens": 34036240.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.034213733673096,
|
|
"epoch": 1.4514592019058963,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004801109548931029,
|
|
"loss": 4.6779,
|
|
"mean_token_accuracy": 0.22161126434803008,
|
|
"num_tokens": 34049163.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.090777587890625,
|
|
"epoch": 1.452054794520548,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004800934344835579,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.21659142524003983,
|
|
"num_tokens": 34063121.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.074826717376709,
|
|
"epoch": 1.4526503871351995,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004800759067176448,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.22024351507425308,
|
|
"num_tokens": 34076197.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.13464617729187,
|
|
"epoch": 1.4532459797498511,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004800583715959924,
|
|
"loss": 4.8159,
|
|
"mean_token_accuracy": 0.20793148428201674,
|
|
"num_tokens": 34090273.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.082295703887939,
|
|
"epoch": 1.4538415723645026,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004800408291192297,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.215682652592659,
|
|
"num_tokens": 34104907.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.013238859176636,
|
|
"epoch": 1.4544371649791543,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004800232792879858,
|
|
"loss": 4.5957,
|
|
"mean_token_accuracy": 0.22879474759101867,
|
|
"num_tokens": 34118629.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.016242218017578,
|
|
"epoch": 1.4550327575938058,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048000572210289016,
|
|
"loss": 4.7149,
|
|
"mean_token_accuracy": 0.22256674319505693,
|
|
"num_tokens": 34132359.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.128390216827393,
|
|
"epoch": 1.4556283502084575,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047998815756457265,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.21419871747493743,
|
|
"num_tokens": 34144410.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.058671665191651,
|
|
"epoch": 1.456223942823109,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047997058567366313,
|
|
"loss": 4.7048,
|
|
"mean_token_accuracy": 0.22307963967323302,
|
|
"num_tokens": 34159462.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.02844557762146,
|
|
"epoch": 1.4568195354377607,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004799530064307921,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.22630198746919633,
|
|
"num_tokens": 34173604.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.062178754806519,
|
|
"epoch": 1.4574151280524121,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047993541983658983,
|
|
"loss": 4.6804,
|
|
"mean_token_accuracy": 0.2247128427028656,
|
|
"num_tokens": 34186378.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.065913152694702,
|
|
"epoch": 1.4580107206670636,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047991782589168724,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.21627471297979356,
|
|
"num_tokens": 34199377.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.0005405902862545,
|
|
"epoch": 1.4586063132817153,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004799002245967156,
|
|
"loss": 4.6292,
|
|
"mean_token_accuracy": 0.223649699985981,
|
|
"num_tokens": 34213081.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.101483249664307,
|
|
"epoch": 1.459201905896367,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047988261595230587,
|
|
"loss": 4.7982,
|
|
"mean_token_accuracy": 0.2096952438354492,
|
|
"num_tokens": 34228750.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.152224826812744,
|
|
"epoch": 1.4597974985110185,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047986499995908996,
|
|
"loss": 4.7896,
|
|
"mean_token_accuracy": 0.2137722283601761,
|
|
"num_tokens": 34241517.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.035707235336304,
|
|
"epoch": 1.46039309112567,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004798473766176994,
|
|
"loss": 4.7221,
|
|
"mean_token_accuracy": 0.217300084233284,
|
|
"num_tokens": 34254182.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.026213693618774,
|
|
"epoch": 1.4609886837403216,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047982974592876665,
|
|
"loss": 4.6829,
|
|
"mean_token_accuracy": 0.22711173444986343,
|
|
"num_tokens": 34267781.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.041351175308227,
|
|
"epoch": 1.4615842763549731,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047981210789292396,
|
|
"loss": 4.6791,
|
|
"mean_token_accuracy": 0.21837303787469864,
|
|
"num_tokens": 34282182.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.024718952178955,
|
|
"epoch": 1.4621798689696248,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004797944625108039,
|
|
"loss": 4.5819,
|
|
"mean_token_accuracy": 0.23182822912931442,
|
|
"num_tokens": 34296199.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.126517629623413,
|
|
"epoch": 1.4627754615842763,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047977680978303946,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.21386991441249847,
|
|
"num_tokens": 34311066.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.150609350204467,
|
|
"epoch": 1.463371054198928,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004797591497102638,
|
|
"loss": 4.8004,
|
|
"mean_token_accuracy": 0.2153276026248932,
|
|
"num_tokens": 34325910.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.122505855560303,
|
|
"epoch": 1.4639666468135795,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047974148229311034,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.22319669723510743,
|
|
"num_tokens": 34338621.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.063833379745484,
|
|
"epoch": 1.4645622394282312,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004797238075322128,
|
|
"loss": 4.6451,
|
|
"mean_token_accuracy": 0.23013430833816528,
|
|
"num_tokens": 34352895.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.039863014221192,
|
|
"epoch": 1.4651578320428826,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004797061254282052,
|
|
"loss": 4.7102,
|
|
"mean_token_accuracy": 0.22019235342741011,
|
|
"num_tokens": 34367070.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.045152854919434,
|
|
"epoch": 1.4657534246575343,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004796884359817217,
|
|
"loss": 4.6557,
|
|
"mean_token_accuracy": 0.22291092872619628,
|
|
"num_tokens": 34381080.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 4.994508266448975,
|
|
"epoch": 1.4663490172721858,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004796707391933967,
|
|
"loss": 4.63,
|
|
"mean_token_accuracy": 0.22376060485839844,
|
|
"num_tokens": 34393658.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.015311050415039,
|
|
"epoch": 1.4669446098868373,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004796530350638652,
|
|
"loss": 4.6665,
|
|
"mean_token_accuracy": 0.22007645815610885,
|
|
"num_tokens": 34406301.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.07755479812622,
|
|
"epoch": 1.467540202501489,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000479635323593762,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.21429197490215302,
|
|
"num_tokens": 34421774.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.067968511581421,
|
|
"epoch": 1.4681357951161407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047961760478372245,
|
|
"loss": 4.6949,
|
|
"mean_token_accuracy": 0.21510566174983978,
|
|
"num_tokens": 34434256.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.095862674713135,
|
|
"epoch": 1.4687313877307921,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047959987863438214,
|
|
"loss": 4.6661,
|
|
"mean_token_accuracy": 0.2246666058897972,
|
|
"num_tokens": 34447351.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.107353591918946,
|
|
"epoch": 1.4693269803454436,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004795821451463769,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.21610742211341857,
|
|
"num_tokens": 34461915.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.135250616073608,
|
|
"epoch": 1.4699225729600953,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00047956440432034265,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.20717076063156128,
|
|
"num_tokens": 34477451.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.086848354339599,
|
|
"epoch": 1.4705181655747468,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00047954665615691577,
|
|
"loss": 4.6965,
|
|
"mean_token_accuracy": 0.2158138632774353,
|
|
"num_tokens": 34492316.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.083188772201538,
|
|
"epoch": 1.4711137581893985,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004795289006567331,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.21741517782211303,
|
|
"num_tokens": 34507284.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.082559537887573,
|
|
"epoch": 1.47170935080405,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047951113782043113,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.21474091410636903,
|
|
"num_tokens": 34521149.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.098694658279419,
|
|
"epoch": 1.4723049434187017,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004794933676486472,
|
|
"loss": 4.7215,
|
|
"mean_token_accuracy": 0.22229171842336654,
|
|
"num_tokens": 34535827.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.102479076385498,
|
|
"epoch": 1.4729005360333531,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004794755901420187,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.21486248075962067,
|
|
"num_tokens": 34548726.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.029920339584351,
|
|
"epoch": 1.4734961286480048,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004794578053011833,
|
|
"loss": 4.6273,
|
|
"mean_token_accuracy": 0.22161247879266738,
|
|
"num_tokens": 34563382.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.066232109069825,
|
|
"epoch": 1.4740917212626563,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047944001312677867,
|
|
"loss": 4.7393,
|
|
"mean_token_accuracy": 0.21628425866365433,
|
|
"num_tokens": 34575887.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.044977474212646,
|
|
"epoch": 1.474687313877308,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047942221361944333,
|
|
"loss": 4.6499,
|
|
"mean_token_accuracy": 0.22140011191368103,
|
|
"num_tokens": 34589694.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.076765871047973,
|
|
"epoch": 1.4752829064919595,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047940440677981546,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.2213784262537956,
|
|
"num_tokens": 34602765.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.030516624450684,
|
|
"epoch": 1.475878499106611,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004793865926085339,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.22110765129327775,
|
|
"num_tokens": 34616633.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.109832239151001,
|
|
"epoch": 1.4764740917212626,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004793687711062376,
|
|
"loss": 4.7143,
|
|
"mean_token_accuracy": 0.21961951702833177,
|
|
"num_tokens": 34630095.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.069669961929321,
|
|
"epoch": 1.4770696843359143,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004793509422735657,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.2258353665471077,
|
|
"num_tokens": 34643838.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.036492252349854,
|
|
"epoch": 1.4776652769505658,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047933310611115776,
|
|
"loss": 4.703,
|
|
"mean_token_accuracy": 0.21946708858013153,
|
|
"num_tokens": 34658122.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.0934028148651125,
|
|
"epoch": 1.4782608695652173,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047931526261965363,
|
|
"loss": 4.725,
|
|
"mean_token_accuracy": 0.21254216879606247,
|
|
"num_tokens": 34674228.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.026575565338135,
|
|
"epoch": 1.478856462179869,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004792974117996931,
|
|
"loss": 4.6528,
|
|
"mean_token_accuracy": 0.220022751390934,
|
|
"num_tokens": 34687624.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 4.973439311981201,
|
|
"epoch": 1.4794520547945205,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004792795536519167,
|
|
"loss": 4.6032,
|
|
"mean_token_accuracy": 0.23511169254779815,
|
|
"num_tokens": 34702749.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.038418626785278,
|
|
"epoch": 1.4800476474091722,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047926168817696477,
|
|
"loss": 4.6803,
|
|
"mean_token_accuracy": 0.21732006072998047,
|
|
"num_tokens": 34716174.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 4.996209287643433,
|
|
"epoch": 1.4806432400238236,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004792438153754782,
|
|
"loss": 4.7157,
|
|
"mean_token_accuracy": 0.22008344084024428,
|
|
"num_tokens": 34731065.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.076768636703491,
|
|
"epoch": 1.4812388326384753,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047922593524809805,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.22020427137613297,
|
|
"num_tokens": 34745167.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.028683423995972,
|
|
"epoch": 1.4818344252531268,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004792080477954657,
|
|
"loss": 4.6712,
|
|
"mean_token_accuracy": 0.22186064720153809,
|
|
"num_tokens": 34758243.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.035054492950439,
|
|
"epoch": 1.4824300178677785,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047919015301822255,
|
|
"loss": 4.6939,
|
|
"mean_token_accuracy": 0.21627300679683686,
|
|
"num_tokens": 34771511.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.047708749771118,
|
|
"epoch": 1.48302561048243,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004791722509170108,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.2256920874118805,
|
|
"num_tokens": 34784480.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.062896823883056,
|
|
"epoch": 1.4836212030970817,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047915434149247224,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.21399841010570525,
|
|
"num_tokens": 34799501.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.066213178634643,
|
|
"epoch": 1.4842167957117332,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047913642474524946,
|
|
"loss": 4.7045,
|
|
"mean_token_accuracy": 0.22294598519802095,
|
|
"num_tokens": 34813020.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.086774110794067,
|
|
"epoch": 1.4848123883263846,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047911850067598494,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.2178470805287361,
|
|
"num_tokens": 34826214.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.051961898803711,
|
|
"epoch": 1.4854079809410363,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047910056928532173,
|
|
"loss": 4.71,
|
|
"mean_token_accuracy": 0.22456542104482652,
|
|
"num_tokens": 34839999.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.100859594345093,
|
|
"epoch": 1.486003573555688,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000479082630573903,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.2264939144253731,
|
|
"num_tokens": 34854272.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.083203935623169,
|
|
"epoch": 1.4865991661703395,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004790646845423721,
|
|
"loss": 4.7402,
|
|
"mean_token_accuracy": 0.21398926377296448,
|
|
"num_tokens": 34870855.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.050775051116943,
|
|
"epoch": 1.487194758784991,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004790467311913727,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.2152524933218956,
|
|
"num_tokens": 34884171.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.052988004684448,
|
|
"epoch": 1.4877903513996427,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047902877052154885,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.21835381388664246,
|
|
"num_tokens": 34897642.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.1247584342956545,
|
|
"epoch": 1.4883859440142944,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047901080253354476,
|
|
"loss": 4.7442,
|
|
"mean_token_accuracy": 0.21458456367254258,
|
|
"num_tokens": 34911737.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 4.9668248176574705,
|
|
"epoch": 1.4889815366289458,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047899282722800487,
|
|
"loss": 4.6242,
|
|
"mean_token_accuracy": 0.2245432823896408,
|
|
"num_tokens": 34925423.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.126318502426147,
|
|
"epoch": 1.4895771292435973,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047897484460557397,
|
|
"loss": 4.7805,
|
|
"mean_token_accuracy": 0.20862076431512833,
|
|
"num_tokens": 34938895.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.094141960144043,
|
|
"epoch": 1.490172721858249,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000478956854666897,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.2160513922572136,
|
|
"num_tokens": 34952365.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.09633207321167,
|
|
"epoch": 1.4907683144729005,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047893885741261924,
|
|
"loss": 4.7942,
|
|
"mean_token_accuracy": 0.21187057942152024,
|
|
"num_tokens": 34968134.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.098987579345703,
|
|
"epoch": 1.4913639070875522,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004789208528433862,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.21774201691150666,
|
|
"num_tokens": 34982572.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.079219770431519,
|
|
"epoch": 1.4919594997022037,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004789028409598438,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.22791638225317,
|
|
"num_tokens": 34995403.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.033216905593872,
|
|
"epoch": 1.4925550923168553,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047888482176263803,
|
|
"loss": 4.71,
|
|
"mean_token_accuracy": 0.22007278949022294,
|
|
"num_tokens": 35008537.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 4.9880170822143555,
|
|
"epoch": 1.4931506849315068,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047886679525241524,
|
|
"loss": 4.6216,
|
|
"mean_token_accuracy": 0.22901638448238373,
|
|
"num_tokens": 35021988.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 4.980045747756958,
|
|
"epoch": 1.4937462775461583,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004788487614298219,
|
|
"loss": 4.6455,
|
|
"mean_token_accuracy": 0.22030892521142958,
|
|
"num_tokens": 35037381.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.026953411102295,
|
|
"epoch": 1.49434187016081,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047883072029550496,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.23404313176870345,
|
|
"num_tokens": 35052556.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.115092420578003,
|
|
"epoch": 1.4949374627754617,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047881267185011147,
|
|
"loss": 4.757,
|
|
"mean_token_accuracy": 0.20755961537361145,
|
|
"num_tokens": 35066001.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.101507663726807,
|
|
"epoch": 1.4955330553901132,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00047879461609428876,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.21537595689296724,
|
|
"num_tokens": 35080733.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.079629135131836,
|
|
"epoch": 1.4961286480047646,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004787765530286846,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.22206946164369584,
|
|
"num_tokens": 35095142.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.0236976146698,
|
|
"epoch": 1.4967242406194163,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004787584826539468,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.22851618230342866,
|
|
"num_tokens": 35108151.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.041532802581787,
|
|
"epoch": 1.497319833234068,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004787404049707235,
|
|
"loss": 4.7506,
|
|
"mean_token_accuracy": 0.21733538955450057,
|
|
"num_tokens": 35125011.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.006177043914795,
|
|
"epoch": 1.4979154258487195,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047872231997966316,
|
|
"loss": 4.714,
|
|
"mean_token_accuracy": 0.22495627105236055,
|
|
"num_tokens": 35138949.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.127271413803101,
|
|
"epoch": 1.498511018463371,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004787042276814144,
|
|
"loss": 4.6975,
|
|
"mean_token_accuracy": 0.2190570667386055,
|
|
"num_tokens": 35152299.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.04735541343689,
|
|
"epoch": 1.4991066110780227,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047868612807662616,
|
|
"loss": 4.6813,
|
|
"mean_token_accuracy": 0.22378267347812653,
|
|
"num_tokens": 35165643.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.021128940582275,
|
|
"epoch": 1.4997022036926742,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047866802116594776,
|
|
"loss": 4.7178,
|
|
"mean_token_accuracy": 0.21818352341651917,
|
|
"num_tokens": 35179214.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.170724868774414,
|
|
"epoch": 1.5002977963073256,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004786499069500286,
|
|
"loss": 4.8507,
|
|
"mean_token_accuracy": 0.21167370527982712,
|
|
"num_tokens": 35194040.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.128082370758056,
|
|
"epoch": 1.5008933889219773,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047863178542951833,
|
|
"loss": 4.752,
|
|
"mean_token_accuracy": 0.21327983140945433,
|
|
"num_tokens": 35207572.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.067221450805664,
|
|
"epoch": 1.501488981536629,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000478613656605067,
|
|
"loss": 4.7504,
|
|
"mean_token_accuracy": 0.21746938079595565,
|
|
"num_tokens": 35221637.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.135350561141967,
|
|
"epoch": 1.5020845741512805,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047859552047732493,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.20962547063827514,
|
|
"num_tokens": 35234905.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.066896581649781,
|
|
"epoch": 1.502680166765932,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047857737704694255,
|
|
"loss": 4.6474,
|
|
"mean_token_accuracy": 0.22343900799751282,
|
|
"num_tokens": 35248773.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.060492849349975,
|
|
"epoch": 1.5032757593805837,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004785592263145705,
|
|
"loss": 4.7188,
|
|
"mean_token_accuracy": 0.2184842899441719,
|
|
"num_tokens": 35261978.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 4.9728310108184814,
|
|
"epoch": 1.5038713519952354,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00047854106828086016,
|
|
"loss": 4.6743,
|
|
"mean_token_accuracy": 0.2227487802505493,
|
|
"num_tokens": 35278130.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.114514446258545,
|
|
"epoch": 1.5044669446098868,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047852290294646255,
|
|
"loss": 4.7445,
|
|
"mean_token_accuracy": 0.21348223835229874,
|
|
"num_tokens": 35289988.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.071557569503784,
|
|
"epoch": 1.5050625372245383,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047850473031202937,
|
|
"loss": 4.6899,
|
|
"mean_token_accuracy": 0.22088817805051802,
|
|
"num_tokens": 35303555.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.047560214996338,
|
|
"epoch": 1.50565812983919,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004784865503782124,
|
|
"loss": 4.6444,
|
|
"mean_token_accuracy": 0.22446517795324325,
|
|
"num_tokens": 35316802.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.098956108093262,
|
|
"epoch": 1.5062537224538417,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047846836314566356,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.21964194178581237,
|
|
"num_tokens": 35329538.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.0583555698394775,
|
|
"epoch": 1.5068493150684932,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047845016861503556,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.21514799892902375,
|
|
"num_tokens": 35345213.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.05139422416687,
|
|
"epoch": 1.5074449076831447,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047843196678698063,
|
|
"loss": 4.6903,
|
|
"mean_token_accuracy": 0.2260141432285309,
|
|
"num_tokens": 35358554.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.160102701187133,
|
|
"epoch": 1.5080405002977963,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004784137576621519,
|
|
"loss": 4.841,
|
|
"mean_token_accuracy": 0.2151823341846466,
|
|
"num_tokens": 35371015.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.0670332431793215,
|
|
"epoch": 1.508636092912448,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004783955412412024,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.22420684546232222,
|
|
"num_tokens": 35384308.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.010155200958252,
|
|
"epoch": 1.5092316855270993,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004783773175247856,
|
|
"loss": 4.6515,
|
|
"mean_token_accuracy": 0.2259841188788414,
|
|
"num_tokens": 35399686.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.127276659011841,
|
|
"epoch": 1.509827278141751,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047835908651355503,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.21594522297382354,
|
|
"num_tokens": 35412809.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.129500102996826,
|
|
"epoch": 1.5104228707564027,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004783408482081646,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.22026145756244658,
|
|
"num_tokens": 35428362.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.08318943977356,
|
|
"epoch": 1.5110184633710542,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004783226026092687,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.22091893553733827,
|
|
"num_tokens": 35442381.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.011530542373658,
|
|
"epoch": 1.5116140559857056,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004783043497175215,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.22406305521726608,
|
|
"num_tokens": 35457537.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.119546890258789,
|
|
"epoch": 1.5122096486003573,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004782860895335779,
|
|
"loss": 4.7496,
|
|
"mean_token_accuracy": 0.21490985304117202,
|
|
"num_tokens": 35471970.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.0414410591125485,
|
|
"epoch": 1.512805241215009,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004782678220580928,
|
|
"loss": 4.6948,
|
|
"mean_token_accuracy": 0.21742557138204574,
|
|
"num_tokens": 35485483.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.04726128578186,
|
|
"epoch": 1.5134008338296605,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047824954729172136,
|
|
"loss": 4.6684,
|
|
"mean_token_accuracy": 0.22012364417314528,
|
|
"num_tokens": 35499766.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.101501750946045,
|
|
"epoch": 1.513996426444312,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047823126523511916,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.20416642129421234,
|
|
"num_tokens": 35514670.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.103370714187622,
|
|
"epoch": 1.5145920190589637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004782129758889419,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.2195814549922943,
|
|
"num_tokens": 35528522.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.059851169586182,
|
|
"epoch": 1.5151876116736154,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047819467925384564,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.22222503274679184,
|
|
"num_tokens": 35542328.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.101168155670166,
|
|
"epoch": 1.5157832042882668,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004781763753304866,
|
|
"loss": 4.787,
|
|
"mean_token_accuracy": 0.2130281776189804,
|
|
"num_tokens": 35556835.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.103102731704712,
|
|
"epoch": 1.5163787969029183,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004781580641195213,
|
|
"loss": 4.7601,
|
|
"mean_token_accuracy": 0.21265387535095215,
|
|
"num_tokens": 35572542.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.1349602222442625,
|
|
"epoch": 1.51697438951757,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047813974562160654,
|
|
"loss": 4.716,
|
|
"mean_token_accuracy": 0.21398045271635055,
|
|
"num_tokens": 35585620.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.087136840820312,
|
|
"epoch": 1.5175699821322217,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004781214198373994,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.2200641304254532,
|
|
"num_tokens": 35598367.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.032868909835815,
|
|
"epoch": 1.5181655747468732,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004781030867675572,
|
|
"loss": 4.7187,
|
|
"mean_token_accuracy": 0.21719938218593599,
|
|
"num_tokens": 35613098.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.1230974197387695,
|
|
"epoch": 1.5187611673615247,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00047808474641273743,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.21444327831268312,
|
|
"num_tokens": 35627243.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.011421346664429,
|
|
"epoch": 1.5193567599761764,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047806639877359805,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.2222112625837326,
|
|
"num_tokens": 35639832.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.06686749458313,
|
|
"epoch": 1.5199523525908278,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004780480438507972,
|
|
"loss": 4.7806,
|
|
"mean_token_accuracy": 0.21662741899490356,
|
|
"num_tokens": 35654045.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.10100908279419,
|
|
"epoch": 1.5205479452054793,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000478029681644993,
|
|
"loss": 4.6932,
|
|
"mean_token_accuracy": 0.21682853400707244,
|
|
"num_tokens": 35667900.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 4.996603631973267,
|
|
"epoch": 1.521143537820131,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004780113121568443,
|
|
"loss": 4.611,
|
|
"mean_token_accuracy": 0.22797945141792297,
|
|
"num_tokens": 35680751.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.053213691711425,
|
|
"epoch": 1.5217391304347827,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047799293538700993,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.22161868065595627,
|
|
"num_tokens": 35694828.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.047107172012329,
|
|
"epoch": 1.5223347230494342,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00047797455133614903,
|
|
"loss": 4.6837,
|
|
"mean_token_accuracy": 0.21701928228139877,
|
|
"num_tokens": 35711587.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.086306571960449,
|
|
"epoch": 1.5229303156640857,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047795616000492086,
|
|
"loss": 4.6657,
|
|
"mean_token_accuracy": 0.22139021903276443,
|
|
"num_tokens": 35726085.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.0421453475952145,
|
|
"epoch": 1.5235259082787374,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047793776139398535,
|
|
"loss": 4.746,
|
|
"mean_token_accuracy": 0.22239135801792145,
|
|
"num_tokens": 35739748.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.109451484680176,
|
|
"epoch": 1.524121500893389,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004779193555040023,
|
|
"loss": 4.72,
|
|
"mean_token_accuracy": 0.21749537885189058,
|
|
"num_tokens": 35752789.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.07702374458313,
|
|
"epoch": 1.5247170935080405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047790094233563185,
|
|
"loss": 4.7484,
|
|
"mean_token_accuracy": 0.21765911281108857,
|
|
"num_tokens": 35766847.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.009030866622925,
|
|
"epoch": 1.525312686122692,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047788252188953447,
|
|
"loss": 4.6434,
|
|
"mean_token_accuracy": 0.22912701070308686,
|
|
"num_tokens": 35779590.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.023820972442627,
|
|
"epoch": 1.5259082787373437,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004778640941663709,
|
|
"loss": 4.6198,
|
|
"mean_token_accuracy": 0.22654144763946532,
|
|
"num_tokens": 35792387.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.019732666015625,
|
|
"epoch": 1.5265038713519954,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047784565916680216,
|
|
"loss": 4.5924,
|
|
"mean_token_accuracy": 0.22634392082691193,
|
|
"num_tokens": 35806317.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.0161505222320555,
|
|
"epoch": 1.5270994639666469,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047782721689148936,
|
|
"loss": 4.6453,
|
|
"mean_token_accuracy": 0.2171490415930748,
|
|
"num_tokens": 35819655.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.027171897888183,
|
|
"epoch": 1.5276950565812983,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004778087673410942,
|
|
"loss": 4.7003,
|
|
"mean_token_accuracy": 0.2196763962507248,
|
|
"num_tokens": 35835502.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.085086250305176,
|
|
"epoch": 1.52829064919595,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004777903105162782,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.2215094596147537,
|
|
"num_tokens": 35849118.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.035668802261353,
|
|
"epoch": 1.5288862418106015,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004777718464177035,
|
|
"loss": 4.6765,
|
|
"mean_token_accuracy": 0.22310157269239425,
|
|
"num_tokens": 35863186.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.038232231140137,
|
|
"epoch": 1.529481834425253,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004777533750460323,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.2231476292014122,
|
|
"num_tokens": 35877221.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.043926000595093,
|
|
"epoch": 1.5300774270399047,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047773489640192724,
|
|
"loss": 4.6526,
|
|
"mean_token_accuracy": 0.21752704530954362,
|
|
"num_tokens": 35891422.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.081358242034912,
|
|
"epoch": 1.5306730196545564,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047771641048605107,
|
|
"loss": 4.757,
|
|
"mean_token_accuracy": 0.21369276642799379,
|
|
"num_tokens": 35904705.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.103006315231323,
|
|
"epoch": 1.5312686122692079,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047769791729906685,
|
|
"loss": 4.7262,
|
|
"mean_token_accuracy": 0.22643474638462066,
|
|
"num_tokens": 35920736.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.07307653427124,
|
|
"epoch": 1.5318642048838593,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000477679416841638,
|
|
"loss": 4.6848,
|
|
"mean_token_accuracy": 0.22704920917749405,
|
|
"num_tokens": 35933878.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.061606407165527,
|
|
"epoch": 1.532459797498511,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047766090911442787,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.22076048702001572,
|
|
"num_tokens": 35949478.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.121629858016968,
|
|
"epoch": 1.5330553901131627,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004776423941181005,
|
|
"loss": 4.7647,
|
|
"mean_token_accuracy": 0.21985567063093187,
|
|
"num_tokens": 35962703.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.0847399711608885,
|
|
"epoch": 1.5336509827278142,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004776238718533199,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.2202477529644966,
|
|
"num_tokens": 35976670.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.0875935554504395,
|
|
"epoch": 1.5342465753424657,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047760534232075045,
|
|
"loss": 4.7092,
|
|
"mean_token_accuracy": 0.22154531329870225,
|
|
"num_tokens": 35990274.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 4.989328336715698,
|
|
"epoch": 1.5348421679571174,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004775868055210568,
|
|
"loss": 4.6502,
|
|
"mean_token_accuracy": 0.220804463326931,
|
|
"num_tokens": 36005085.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.1291581153869625,
|
|
"epoch": 1.535437760571769,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047756826145490383,
|
|
"loss": 4.7802,
|
|
"mean_token_accuracy": 0.2157354399561882,
|
|
"num_tokens": 36018108.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.085577154159546,
|
|
"epoch": 1.5360333531864205,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047754971012295666,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.226678067445755,
|
|
"num_tokens": 36030541.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.0530009269714355,
|
|
"epoch": 1.536628945801072,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004775311515258807,
|
|
"loss": 4.7349,
|
|
"mean_token_accuracy": 0.21637245267629623,
|
|
"num_tokens": 36047250.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.106283521652221,
|
|
"epoch": 1.5372245384157237,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00047751258566434176,
|
|
"loss": 4.7977,
|
|
"mean_token_accuracy": 0.21059157699346542,
|
|
"num_tokens": 36062429.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.0291609287261965,
|
|
"epoch": 1.5378201310303752,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004774940125390055,
|
|
"loss": 4.6177,
|
|
"mean_token_accuracy": 0.23327056616544722,
|
|
"num_tokens": 36074431.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.094903802871704,
|
|
"epoch": 1.5384157236450267,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004774754321505383,
|
|
"loss": 4.7744,
|
|
"mean_token_accuracy": 0.22495987117290497,
|
|
"num_tokens": 36088323.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.044903898239136,
|
|
"epoch": 1.5390113162596784,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047745684449960655,
|
|
"loss": 4.5961,
|
|
"mean_token_accuracy": 0.22792339622974395,
|
|
"num_tokens": 36101762.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.021538209915161,
|
|
"epoch": 1.53960690887433,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047743824958687694,
|
|
"loss": 4.6705,
|
|
"mean_token_accuracy": 0.22533783465623855,
|
|
"num_tokens": 36115969.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.0385894775390625,
|
|
"epoch": 1.5402025014889815,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004774196474130165,
|
|
"loss": 4.7387,
|
|
"mean_token_accuracy": 0.22092886865139008,
|
|
"num_tokens": 36130179.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.081376647949218,
|
|
"epoch": 1.540798094103633,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047740103797869237,
|
|
"loss": 4.6264,
|
|
"mean_token_accuracy": 0.22756000608205795,
|
|
"num_tokens": 36143156.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.128387403488159,
|
|
"epoch": 1.5413936867182847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047738242128457216,
|
|
"loss": 4.7586,
|
|
"mean_token_accuracy": 0.21517050564289092,
|
|
"num_tokens": 36158073.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.096407413482666,
|
|
"epoch": 1.5419892793329364,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047736379733132343,
|
|
"loss": 4.7895,
|
|
"mean_token_accuracy": 0.211049647629261,
|
|
"num_tokens": 36172519.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.085195779800415,
|
|
"epoch": 1.5425848719475879,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047734516611961443,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.2167127400636673,
|
|
"num_tokens": 36187603.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.1171026706695555,
|
|
"epoch": 1.5431804645622393,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004773265276501133,
|
|
"loss": 4.8086,
|
|
"mean_token_accuracy": 0.21225575655698775,
|
|
"num_tokens": 36200785.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.149388170242309,
|
|
"epoch": 1.543776057176891,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047730788192348856,
|
|
"loss": 4.7487,
|
|
"mean_token_accuracy": 0.21598533987998964,
|
|
"num_tokens": 36214087.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.009466981887817,
|
|
"epoch": 1.5443716497915427,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047728922894040905,
|
|
"loss": 4.5916,
|
|
"mean_token_accuracy": 0.2259846806526184,
|
|
"num_tokens": 36228949.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.02960467338562,
|
|
"epoch": 1.5449672424061942,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004772705687015437,
|
|
"loss": 4.6879,
|
|
"mean_token_accuracy": 0.21757767647504805,
|
|
"num_tokens": 36244637.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.094267559051514,
|
|
"epoch": 1.5455628350208457,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047725190120756207,
|
|
"loss": 4.7584,
|
|
"mean_token_accuracy": 0.21601244956254959,
|
|
"num_tokens": 36257306.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.09618034362793,
|
|
"epoch": 1.5461584276354974,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047723322645913354,
|
|
"loss": 4.7396,
|
|
"mean_token_accuracy": 0.212338487803936,
|
|
"num_tokens": 36271947.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.098639392852784,
|
|
"epoch": 1.5467540202501489,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047721454445692795,
|
|
"loss": 4.6835,
|
|
"mean_token_accuracy": 0.22221672385931016,
|
|
"num_tokens": 36285883.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.083920621871949,
|
|
"epoch": 1.5473496128648003,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00047719585520161544,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.21794982850551606,
|
|
"num_tokens": 36303042.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.136064147949218,
|
|
"epoch": 1.547945205479452,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004771771586938664,
|
|
"loss": 4.7379,
|
|
"mean_token_accuracy": 0.2184961661696434,
|
|
"num_tokens": 36314837.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.0415294647216795,
|
|
"epoch": 1.5485407980941037,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047715845493435135,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.22306275516748428,
|
|
"num_tokens": 36328836.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.053057861328125,
|
|
"epoch": 1.5491363907087552,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004771397439237412,
|
|
"loss": 4.6813,
|
|
"mean_token_accuracy": 0.22091148048639297,
|
|
"num_tokens": 36342231.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 4.981278419494629,
|
|
"epoch": 1.5497319833234067,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047712102566270715,
|
|
"loss": 4.5921,
|
|
"mean_token_accuracy": 0.22417282164096833,
|
|
"num_tokens": 36357346.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.078459119796753,
|
|
"epoch": 1.5503275759380584,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00047710230015192054,
|
|
"loss": 4.7922,
|
|
"mean_token_accuracy": 0.2220919042825699,
|
|
"num_tokens": 36370476.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.097197389602661,
|
|
"epoch": 1.55092316855271,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047708356739205294,
|
|
"loss": 4.654,
|
|
"mean_token_accuracy": 0.21822237819433213,
|
|
"num_tokens": 36386519.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.018616437911987,
|
|
"epoch": 1.5515187611673615,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004770648273837764,
|
|
"loss": 4.6188,
|
|
"mean_token_accuracy": 0.22183233201503755,
|
|
"num_tokens": 36400725.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.097242259979248,
|
|
"epoch": 1.552114353782013,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000477046080127763,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.21462655514478685,
|
|
"num_tokens": 36414503.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.081587457656861,
|
|
"epoch": 1.5527099463966647,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004770273256246853,
|
|
"loss": 4.6753,
|
|
"mean_token_accuracy": 0.22045510560274123,
|
|
"num_tokens": 36428580.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.089586687088013,
|
|
"epoch": 1.5533055390113164,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047700856387521585,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.22341829240322114,
|
|
"num_tokens": 36442971.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.060001802444458,
|
|
"epoch": 1.5539011316259679,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004769897948800276,
|
|
"loss": 4.6452,
|
|
"mean_token_accuracy": 0.225729900598526,
|
|
"num_tokens": 36456335.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.0705193996429445,
|
|
"epoch": 1.5544967242406194,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.00047697101863979394,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.22085953056812285,
|
|
"num_tokens": 36472934.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.029962682723999,
|
|
"epoch": 1.555092316855271,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004769522351551882,
|
|
"loss": 4.648,
|
|
"mean_token_accuracy": 0.2296345517039299,
|
|
"num_tokens": 36485740.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.007093191146851,
|
|
"epoch": 1.5556879094699225,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004769334444268841,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.22220940440893172,
|
|
"num_tokens": 36500403.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.025922060012817,
|
|
"epoch": 1.556283502084574,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047691464645555564,
|
|
"loss": 4.704,
|
|
"mean_token_accuracy": 0.2190221905708313,
|
|
"num_tokens": 36513840.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.0598464012146,
|
|
"epoch": 1.5568790946992257,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004768958412418772,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.22848057597875596,
|
|
"num_tokens": 36526436.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 4.992478084564209,
|
|
"epoch": 1.5574746873138774,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.00047687702878652303,
|
|
"loss": 4.6358,
|
|
"mean_token_accuracy": 0.22576863914728165,
|
|
"num_tokens": 36541331.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.009912061691284,
|
|
"epoch": 1.5580702799285289,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.00047685820909016823,
|
|
"loss": 4.6567,
|
|
"mean_token_accuracy": 0.2283388614654541,
|
|
"num_tokens": 36556309.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.101260423660278,
|
|
"epoch": 1.5586658725431803,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004768393821534877,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.21516046971082686,
|
|
"num_tokens": 36571888.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.140947008132935,
|
|
"epoch": 1.559261465157832,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004768205479771566,
|
|
"loss": 4.8191,
|
|
"mean_token_accuracy": 0.21222096532583237,
|
|
"num_tokens": 36584525.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.070525693893432,
|
|
"epoch": 1.5598570577724837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004768017065618506,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.2165326789021492,
|
|
"num_tokens": 36598298.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.142951250076294,
|
|
"epoch": 1.5604526503871352,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047678285790824556,
|
|
"loss": 4.7466,
|
|
"mean_token_accuracy": 0.21673363000154494,
|
|
"num_tokens": 36611723.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.084859848022461,
|
|
"epoch": 1.5610482430017867,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004767640020170174,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.21829580515623093,
|
|
"num_tokens": 36625932.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.063218832015991,
|
|
"epoch": 1.5616438356164384,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004767451388888426,
|
|
"loss": 4.6106,
|
|
"mean_token_accuracy": 0.225425623357296,
|
|
"num_tokens": 36637604.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.1411834239959715,
|
|
"epoch": 1.56223942823109,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004767262685243976,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.21323495507240295,
|
|
"num_tokens": 36653078.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.098160982131958,
|
|
"epoch": 1.5628350208457416,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004767073909243594,
|
|
"loss": 4.7761,
|
|
"mean_token_accuracy": 0.21582639813423157,
|
|
"num_tokens": 36668593.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.101113414764404,
|
|
"epoch": 1.563430613460393,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047668850608940504,
|
|
"loss": 4.7319,
|
|
"mean_token_accuracy": 0.2174038991332054,
|
|
"num_tokens": 36680442.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.042565774917603,
|
|
"epoch": 1.5640262060750447,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004766696140202119,
|
|
"loss": 4.6945,
|
|
"mean_token_accuracy": 0.22559809386730195,
|
|
"num_tokens": 36694236.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.06461992263794,
|
|
"epoch": 1.5646217986896962,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047665071471745754,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.22476122975349427,
|
|
"num_tokens": 36709202.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.128347110748291,
|
|
"epoch": 1.5652173913043477,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047663180818181995,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.2261374667286873,
|
|
"num_tokens": 36722997.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.1125061988830565,
|
|
"epoch": 1.5658129839189994,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047661289441397724,
|
|
"loss": 4.6858,
|
|
"mean_token_accuracy": 0.2231842190027237,
|
|
"num_tokens": 36736400.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.005477380752564,
|
|
"epoch": 1.566408576533651,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004765939734146078,
|
|
"loss": 4.7093,
|
|
"mean_token_accuracy": 0.22454095184803008,
|
|
"num_tokens": 36748844.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.037631034851074,
|
|
"epoch": 1.5670041691483025,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004765750451843904,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.22645186483860016,
|
|
"num_tokens": 36761074.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.007294034957885,
|
|
"epoch": 1.567599761762954,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004765561097240037,
|
|
"loss": 4.6056,
|
|
"mean_token_accuracy": 0.2287276104092598,
|
|
"num_tokens": 36775492.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.0694561958312985,
|
|
"epoch": 1.5681953543776057,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047653716703412717,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.22093973010778428,
|
|
"num_tokens": 36789087.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.051238012313843,
|
|
"epoch": 1.5687909469922574,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004765182171154401,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.21920639872550965,
|
|
"num_tokens": 36804241.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 4.994452333450317,
|
|
"epoch": 1.5693865396069089,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004764992599686222,
|
|
"loss": 4.631,
|
|
"mean_token_accuracy": 0.22666141390800476,
|
|
"num_tokens": 36820056.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.000874137878418,
|
|
"epoch": 1.5699821322215604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004764802955943535,
|
|
"loss": 4.6947,
|
|
"mean_token_accuracy": 0.22364101707935333,
|
|
"num_tokens": 36834419.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.1516242027282715,
|
|
"epoch": 1.570577724836212,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047646132399331413,
|
|
"loss": 4.777,
|
|
"mean_token_accuracy": 0.216317318379879,
|
|
"num_tokens": 36848712.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.168609380722046,
|
|
"epoch": 1.5711733174508637,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047644234516618474,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.21369044929742814,
|
|
"num_tokens": 36861773.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.104953289031982,
|
|
"epoch": 1.5717689100655152,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047642335911364585,
|
|
"loss": 4.731,
|
|
"mean_token_accuracy": 0.21451061815023423,
|
|
"num_tokens": 36875794.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 4.963486957550049,
|
|
"epoch": 1.5723645026801667,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047640436583637865,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.2321024402976036,
|
|
"num_tokens": 36889707.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.096255970001221,
|
|
"epoch": 1.5729600952948184,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.00047638536533506424,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.2166353017091751,
|
|
"num_tokens": 36904224.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.152315950393676,
|
|
"epoch": 1.5735556879094699,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047636635761038427,
|
|
"loss": 4.7828,
|
|
"mean_token_accuracy": 0.20901697725057602,
|
|
"num_tokens": 36919757.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.1073915481567385,
|
|
"epoch": 1.5741512805241213,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047634734266302037,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.21726834326982497,
|
|
"num_tokens": 36933991.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.008155012130738,
|
|
"epoch": 1.574746873138773,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004763283204936547,
|
|
"loss": 4.6482,
|
|
"mean_token_accuracy": 0.22263571619987488,
|
|
"num_tokens": 36947546.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.099714899063111,
|
|
"epoch": 1.5753424657534247,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004763092911029695,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.21407688707113265,
|
|
"num_tokens": 36963541.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.1073376655578615,
|
|
"epoch": 1.5759380583680762,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004762902544916474,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.2208103284239769,
|
|
"num_tokens": 36977781.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.075548696517944,
|
|
"epoch": 1.5765336509827277,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004762712106603711,
|
|
"loss": 4.7368,
|
|
"mean_token_accuracy": 0.21473097652196885,
|
|
"num_tokens": 36991883.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.060984754562378,
|
|
"epoch": 1.5771292435973794,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047625215960982376,
|
|
"loss": 4.7535,
|
|
"mean_token_accuracy": 0.21840547472238542,
|
|
"num_tokens": 37006815.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.0440065383911135,
|
|
"epoch": 1.577724836212031,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047623310134068867,
|
|
"loss": 4.6483,
|
|
"mean_token_accuracy": 0.231580913066864,
|
|
"num_tokens": 37020653.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.068360280990601,
|
|
"epoch": 1.5783204288266826,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004762140358536493,
|
|
"loss": 4.7627,
|
|
"mean_token_accuracy": 0.2138925939798355,
|
|
"num_tokens": 37034906.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.073485231399536,
|
|
"epoch": 1.578916021441334,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047619496314938977,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.21391688883304597,
|
|
"num_tokens": 37049611.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.017524576187133,
|
|
"epoch": 1.5795116140559857,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047617588322859395,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.22835878729820253,
|
|
"num_tokens": 37063506.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.031564235687256,
|
|
"epoch": 1.5801072066706374,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004761567960919463,
|
|
"loss": 4.6533,
|
|
"mean_token_accuracy": 0.22250538915395737,
|
|
"num_tokens": 37077100.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.107350492477417,
|
|
"epoch": 1.580702799285289,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047613770174013146,
|
|
"loss": 4.7203,
|
|
"mean_token_accuracy": 0.21680770963430404,
|
|
"num_tokens": 37090342.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.140700197219848,
|
|
"epoch": 1.5812983918999404,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004761186001738342,
|
|
"loss": 4.8258,
|
|
"mean_token_accuracy": 0.2186319887638092,
|
|
"num_tokens": 37107377.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.069350051879883,
|
|
"epoch": 1.581893984514592,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00047609949139373994,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.21897076368331908,
|
|
"num_tokens": 37122160.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.062976598739624,
|
|
"epoch": 1.5824895771292438,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004760803754005337,
|
|
"loss": 4.6497,
|
|
"mean_token_accuracy": 0.22033861130475998,
|
|
"num_tokens": 37135762.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.089203119277954,
|
|
"epoch": 1.583085169743895,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004760612521949014,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.21477956920862198,
|
|
"num_tokens": 37150319.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.131841135025025,
|
|
"epoch": 1.5836807623585467,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047604212177752885,
|
|
"loss": 4.7363,
|
|
"mean_token_accuracy": 0.21872794777154922,
|
|
"num_tokens": 37165629.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.099305534362793,
|
|
"epoch": 1.5842763549731984,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047602298414910237,
|
|
"loss": 4.6918,
|
|
"mean_token_accuracy": 0.2192649155855179,
|
|
"num_tokens": 37179189.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.009786224365234,
|
|
"epoch": 1.5848719475878499,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047600383931030823,
|
|
"loss": 4.6215,
|
|
"mean_token_accuracy": 0.22187652587890624,
|
|
"num_tokens": 37192200.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.116224908828736,
|
|
"epoch": 1.5854675402025014,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004759846872618332,
|
|
"loss": 4.7886,
|
|
"mean_token_accuracy": 0.21303858309984208,
|
|
"num_tokens": 37205549.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.136565732955932,
|
|
"epoch": 1.586063132817153,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047596552800436426,
|
|
"loss": 4.7486,
|
|
"mean_token_accuracy": 0.22341911345720292,
|
|
"num_tokens": 37218179.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.058910846710205,
|
|
"epoch": 1.5866587254318048,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047594636153858844,
|
|
"loss": 4.7314,
|
|
"mean_token_accuracy": 0.2284415915608406,
|
|
"num_tokens": 37232078.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.061246013641357,
|
|
"epoch": 1.5872543180464562,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047592718786519347,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.21434056013822556,
|
|
"num_tokens": 37245962.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.114887475967407,
|
|
"epoch": 1.5878499106611077,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00047590800698486693,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.21307357400655746,
|
|
"num_tokens": 37262644.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.096629905700683,
|
|
"epoch": 1.5884455032757594,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004758888188982969,
|
|
"loss": 4.6712,
|
|
"mean_token_accuracy": 0.21625685691833496,
|
|
"num_tokens": 37275421.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.049310350418091,
|
|
"epoch": 1.589041095890411,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004758696236061715,
|
|
"loss": 4.635,
|
|
"mean_token_accuracy": 0.22586443722248079,
|
|
"num_tokens": 37289117.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.050957679748535,
|
|
"epoch": 1.5896366885050626,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004758504211091793,
|
|
"loss": 4.7103,
|
|
"mean_token_accuracy": 0.21386064291000367,
|
|
"num_tokens": 37303221.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.079492568969727,
|
|
"epoch": 1.590232281119714,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00047583121140800906,
|
|
"loss": 4.6785,
|
|
"mean_token_accuracy": 0.2253236785531044,
|
|
"num_tokens": 37317798.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.097005319595337,
|
|
"epoch": 1.5908278737343657,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004758119945033497,
|
|
"loss": 4.7408,
|
|
"mean_token_accuracy": 0.2115029826760292,
|
|
"num_tokens": 37333226.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.066867828369141,
|
|
"epoch": 1.5914234663490174,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004757927703958907,
|
|
"loss": 4.6369,
|
|
"mean_token_accuracy": 0.22848182618618013,
|
|
"num_tokens": 37346124.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.099727964401245,
|
|
"epoch": 1.5920190589636687,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047577353908632156,
|
|
"loss": 4.6777,
|
|
"mean_token_accuracy": 0.23092871755361558,
|
|
"num_tokens": 37359937.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.069407272338867,
|
|
"epoch": 1.5926146515783204,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004757543005753319,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.21366357505321504,
|
|
"num_tokens": 37372306.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 4.9856507778167725,
|
|
"epoch": 1.593210244192972,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047573505486361183,
|
|
"loss": 4.5957,
|
|
"mean_token_accuracy": 0.23061843067407609,
|
|
"num_tokens": 37385071.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.074825716018677,
|
|
"epoch": 1.5938058368076236,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004757158019518519,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.22730913609266282,
|
|
"num_tokens": 37397621.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.172349357604981,
|
|
"epoch": 1.594401429422275,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004756965418407424,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.21245186030864716,
|
|
"num_tokens": 37412813.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.105957984924316,
|
|
"epoch": 1.5949970220369267,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047567727453097427,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.2178368091583252,
|
|
"num_tokens": 37425664.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 4.933472156524658,
|
|
"epoch": 1.5955926146515784,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004756580000232385,
|
|
"loss": 4.5385,
|
|
"mean_token_accuracy": 0.23398573100566863,
|
|
"num_tokens": 37438600.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.036464691162109,
|
|
"epoch": 1.59618820726623,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047563871831822664,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.22475652098655702,
|
|
"num_tokens": 37453138.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.079071044921875,
|
|
"epoch": 1.5967837998808814,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004756194294166301,
|
|
"loss": 4.6518,
|
|
"mean_token_accuracy": 0.22571996599435806,
|
|
"num_tokens": 37467592.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.0213850975036625,
|
|
"epoch": 1.597379392495533,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004756001333191409,
|
|
"loss": 4.6661,
|
|
"mean_token_accuracy": 0.22457221895456314,
|
|
"num_tokens": 37480652.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.034906816482544,
|
|
"epoch": 1.5979749851101848,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047558083002645097,
|
|
"loss": 4.6551,
|
|
"mean_token_accuracy": 0.22100956588983536,
|
|
"num_tokens": 37494504.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.065073251724243,
|
|
"epoch": 1.5985705777248362,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047556151953925287,
|
|
"loss": 4.6384,
|
|
"mean_token_accuracy": 0.2246208369731903,
|
|
"num_tokens": 37507261.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.1012410640716555,
|
|
"epoch": 1.5991661703394877,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004755422018582391,
|
|
"loss": 4.731,
|
|
"mean_token_accuracy": 0.2145520731806755,
|
|
"num_tokens": 37519371.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 4.9823249816894535,
|
|
"epoch": 1.5997617629541394,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047552287698410267,
|
|
"loss": 4.6438,
|
|
"mean_token_accuracy": 0.22586606740951537,
|
|
"num_tokens": 37532659.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.035286092758179,
|
|
"epoch": 1.600357355568791,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004755035449175366,
|
|
"loss": 4.6276,
|
|
"mean_token_accuracy": 0.22706791758537292,
|
|
"num_tokens": 37545734.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.066895866394043,
|
|
"epoch": 1.6009529481834424,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004754842056592344,
|
|
"loss": 4.6991,
|
|
"mean_token_accuracy": 0.2241310104727745,
|
|
"num_tokens": 37560210.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.089844608306885,
|
|
"epoch": 1.601548540798094,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047546485920988975,
|
|
"loss": 4.7033,
|
|
"mean_token_accuracy": 0.21204846501350402,
|
|
"num_tokens": 37573937.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.06870059967041,
|
|
"epoch": 1.6021441334127458,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004754455055701965,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.22104569375514985,
|
|
"num_tokens": 37587615.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.076955938339234,
|
|
"epoch": 1.6027397260273972,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004754261447408489,
|
|
"loss": 4.7024,
|
|
"mean_token_accuracy": 0.22379032969474794,
|
|
"num_tokens": 37601394.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.114761161804199,
|
|
"epoch": 1.6033353186420487,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004754067767225413,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.21732342690229417,
|
|
"num_tokens": 37616352.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.083060932159424,
|
|
"epoch": 1.6039309112567004,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004753874015159685,
|
|
"loss": 4.7539,
|
|
"mean_token_accuracy": 0.21774326860904694,
|
|
"num_tokens": 37629669.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.140305662155152,
|
|
"epoch": 1.604526503871352,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004753680191218254,
|
|
"loss": 4.7137,
|
|
"mean_token_accuracy": 0.21936844885349274,
|
|
"num_tokens": 37645468.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.107738590240478,
|
|
"epoch": 1.6051220964860036,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004753486295408073,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.219736947119236,
|
|
"num_tokens": 37659194.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.083332490921021,
|
|
"epoch": 1.605717689100655,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004753292327736095,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.21845024079084396,
|
|
"num_tokens": 37673910.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.0599596977233885,
|
|
"epoch": 1.6063132817153067,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047530982882092794,
|
|
"loss": 4.6947,
|
|
"mean_token_accuracy": 0.2241388201713562,
|
|
"num_tokens": 37687110.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.072713136672974,
|
|
"epoch": 1.6069088743299584,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004752904176834584,
|
|
"loss": 4.7607,
|
|
"mean_token_accuracy": 0.2238481566309929,
|
|
"num_tokens": 37701175.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.035937547683716,
|
|
"epoch": 1.60750446694461,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047527099936189735,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.22693052291870117,
|
|
"num_tokens": 37715301.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.09178318977356,
|
|
"epoch": 1.6081000595592614,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000475251573856941,
|
|
"loss": 4.6771,
|
|
"mean_token_accuracy": 0.22431598007678985,
|
|
"num_tokens": 37730151.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.099605751037598,
|
|
"epoch": 1.608695652173913,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004752321411692864,
|
|
"loss": 4.7022,
|
|
"mean_token_accuracy": 0.21930088847875595,
|
|
"num_tokens": 37745682.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.078477382659912,
|
|
"epoch": 1.6092912447885648,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047521270129963043,
|
|
"loss": 4.6813,
|
|
"mean_token_accuracy": 0.21568310111761094,
|
|
"num_tokens": 37759585.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.032392978668213,
|
|
"epoch": 1.6098868374032163,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004751932542486705,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.2207431212067604,
|
|
"num_tokens": 37773881.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 4.9589142322540285,
|
|
"epoch": 1.6104824300178677,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004751738000171039,
|
|
"loss": 4.5187,
|
|
"mean_token_accuracy": 0.2345334991812706,
|
|
"num_tokens": 37787439.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.103781270980835,
|
|
"epoch": 1.6110780226325194,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047515433860562855,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.21141425967216493,
|
|
"num_tokens": 37800064.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.021913480758667,
|
|
"epoch": 1.611673615247171,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047513487001494257,
|
|
"loss": 4.5935,
|
|
"mean_token_accuracy": 0.23224812597036362,
|
|
"num_tokens": 37813484.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 4.979305219650269,
|
|
"epoch": 1.6122692078618224,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004751153942457442,
|
|
"loss": 4.6102,
|
|
"mean_token_accuracy": 0.2267513692378998,
|
|
"num_tokens": 37826039.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.025376510620117,
|
|
"epoch": 1.612864800476474,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000475095911298732,
|
|
"loss": 4.624,
|
|
"mean_token_accuracy": 0.22655612528324126,
|
|
"num_tokens": 37839940.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.068229818344117,
|
|
"epoch": 1.6134603930911258,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004750764211746048,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.22171222269535065,
|
|
"num_tokens": 37853012.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.048918008804321,
|
|
"epoch": 1.6140559857057772,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047505692387406163,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.2205553561449051,
|
|
"num_tokens": 37866594.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.085881519317627,
|
|
"epoch": 1.6146515783204287,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047503741939780195,
|
|
"loss": 4.72,
|
|
"mean_token_accuracy": 0.22124970704317093,
|
|
"num_tokens": 37880436.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.093343687057495,
|
|
"epoch": 1.6152471709350804,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004750179077465252,
|
|
"loss": 4.747,
|
|
"mean_token_accuracy": 0.221013705432415,
|
|
"num_tokens": 37895336.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.029663038253784,
|
|
"epoch": 1.615842763549732,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047499838892093134,
|
|
"loss": 4.7113,
|
|
"mean_token_accuracy": 0.22119733542203904,
|
|
"num_tokens": 37908571.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.065822792053223,
|
|
"epoch": 1.6164383561643836,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047497886292172044,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.22116253674030303,
|
|
"num_tokens": 37924330.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.087139225006103,
|
|
"epoch": 1.617033948779035,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047495932974959287,
|
|
"loss": 4.7038,
|
|
"mean_token_accuracy": 0.2211739808320999,
|
|
"num_tokens": 37937489.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.0888227939605715,
|
|
"epoch": 1.6176295413936868,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004749397894052493,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.21493701189756392,
|
|
"num_tokens": 37951875.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.032652425765991,
|
|
"epoch": 1.6182251340083385,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00047492024188939056,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.22478718608617781,
|
|
"num_tokens": 37965808.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.087445878982544,
|
|
"epoch": 1.61882072662299,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004749006872027178,
|
|
"loss": 4.7073,
|
|
"mean_token_accuracy": 0.22166934311389924,
|
|
"num_tokens": 37979244.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.039331579208374,
|
|
"epoch": 1.6194163192376414,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004748811253459324,
|
|
"loss": 4.6983,
|
|
"mean_token_accuracy": 0.22486514002084732,
|
|
"num_tokens": 37992177.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.0616601467132565,
|
|
"epoch": 1.620011911852293,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004748615563197359,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.2249644011259079,
|
|
"num_tokens": 38006221.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.119919157028198,
|
|
"epoch": 1.6206075044669446,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004748419801248304,
|
|
"loss": 4.6768,
|
|
"mean_token_accuracy": 0.22496962398290635,
|
|
"num_tokens": 38020808.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.024676942825318,
|
|
"epoch": 1.621203097081596,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004748223967619181,
|
|
"loss": 4.645,
|
|
"mean_token_accuracy": 0.23173357397317887,
|
|
"num_tokens": 38032467.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.051896715164185,
|
|
"epoch": 1.6217986896962477,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047480280623170116,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.21635828167200089,
|
|
"num_tokens": 38047784.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.087296867370606,
|
|
"epoch": 1.6223942823108994,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00047478320853488256,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.21232686042785645,
|
|
"num_tokens": 38061754.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.0691813945770265,
|
|
"epoch": 1.622989874925551,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047476360367216505,
|
|
"loss": 4.6627,
|
|
"mean_token_accuracy": 0.2253491088747978,
|
|
"num_tokens": 38076447.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.092834997177124,
|
|
"epoch": 1.6235854675402024,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004747439916442518,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.22708406746387483,
|
|
"num_tokens": 38089845.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.080404901504517,
|
|
"epoch": 1.624181060154854,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004747243724518465,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.22102883011102675,
|
|
"num_tokens": 38104180.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.030337285995484,
|
|
"epoch": 1.6247766527695058,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004747047460956525,
|
|
"loss": 4.6614,
|
|
"mean_token_accuracy": 0.21448477655649184,
|
|
"num_tokens": 38117421.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.012112236022949,
|
|
"epoch": 1.6253722453841573,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004746851125763741,
|
|
"loss": 4.6342,
|
|
"mean_token_accuracy": 0.224623242020607,
|
|
"num_tokens": 38131131.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.062898921966553,
|
|
"epoch": 1.6259678379988087,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047466547189471534,
|
|
"loss": 4.6487,
|
|
"mean_token_accuracy": 0.2228739082813263,
|
|
"num_tokens": 38143905.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.059116983413697,
|
|
"epoch": 1.6265634306134604,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004746458240513807,
|
|
"loss": 4.7367,
|
|
"mean_token_accuracy": 0.22176412492990494,
|
|
"num_tokens": 38159068.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.0956886291503904,
|
|
"epoch": 1.6271590232281121,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000474626169047075,
|
|
"loss": 4.6839,
|
|
"mean_token_accuracy": 0.22056032717227936,
|
|
"num_tokens": 38174522.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.089228820800781,
|
|
"epoch": 1.6277546158427636,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004746065068825032,
|
|
"loss": 4.6457,
|
|
"mean_token_accuracy": 0.2201528951525688,
|
|
"num_tokens": 38189376.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.068504571914673,
|
|
"epoch": 1.628350208457415,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047458683755837046,
|
|
"loss": 4.7555,
|
|
"mean_token_accuracy": 0.21750137507915496,
|
|
"num_tokens": 38203260.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.058835554122925,
|
|
"epoch": 1.6289458010720668,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004745671610753824,
|
|
"loss": 4.6746,
|
|
"mean_token_accuracy": 0.21620715260505677,
|
|
"num_tokens": 38219526.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.051362133026123,
|
|
"epoch": 1.6295413936867182,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004745474774342448,
|
|
"loss": 4.628,
|
|
"mean_token_accuracy": 0.22498565167188644,
|
|
"num_tokens": 38232957.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.052260446548462,
|
|
"epoch": 1.6301369863013697,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004745277866356636,
|
|
"loss": 4.7058,
|
|
"mean_token_accuracy": 0.22320702970027922,
|
|
"num_tokens": 38246772.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.061327505111694,
|
|
"epoch": 1.6307325789160214,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004745080886803451,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.22291142493486404,
|
|
"num_tokens": 38260680.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.015157222747803,
|
|
"epoch": 1.631328171530673,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004744883835689958,
|
|
"loss": 4.676,
|
|
"mean_token_accuracy": 0.22357630133628845,
|
|
"num_tokens": 38273666.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.064391565322876,
|
|
"epoch": 1.6319237641453246,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047446867130232257,
|
|
"loss": 4.6244,
|
|
"mean_token_accuracy": 0.22210530191659927,
|
|
"num_tokens": 38287047.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.1547956466674805,
|
|
"epoch": 1.632519356759976,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004744489518810324,
|
|
"loss": 4.7796,
|
|
"mean_token_accuracy": 0.21434920579195021,
|
|
"num_tokens": 38300622.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.133324527740479,
|
|
"epoch": 1.6331149493746278,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047442922530583265,
|
|
"loss": 4.7142,
|
|
"mean_token_accuracy": 0.21847713440656663,
|
|
"num_tokens": 38316543.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.045273303985596,
|
|
"epoch": 1.6337105419892795,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004744094915774308,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.22033434808254243,
|
|
"num_tokens": 38330217.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.120734834671021,
|
|
"epoch": 1.634306134603931,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00047438975069653475,
|
|
"loss": 4.7562,
|
|
"mean_token_accuracy": 0.22241008430719375,
|
|
"num_tokens": 38345314.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.076166343688965,
|
|
"epoch": 1.6349017272185824,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004743700026638525,
|
|
"loss": 4.643,
|
|
"mean_token_accuracy": 0.2287016674876213,
|
|
"num_tokens": 38358910.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.08471040725708,
|
|
"epoch": 1.635497319833234,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004743502474800924,
|
|
"loss": 4.7626,
|
|
"mean_token_accuracy": 0.2215890884399414,
|
|
"num_tokens": 38372039.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.068045568466187,
|
|
"epoch": 1.6360929124478858,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047433048514596303,
|
|
"loss": 4.6361,
|
|
"mean_token_accuracy": 0.22713104635477066,
|
|
"num_tokens": 38386517.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.04267954826355,
|
|
"epoch": 1.6366885050625373,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004743107156621733,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.22189828455448152,
|
|
"num_tokens": 38401884.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.037983179092407,
|
|
"epoch": 1.6372840976771887,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047429093902943227,
|
|
"loss": 4.5775,
|
|
"mean_token_accuracy": 0.23419303596019744,
|
|
"num_tokens": 38415006.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.07643756866455,
|
|
"epoch": 1.6378796902918404,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004742711552484492,
|
|
"loss": 4.6933,
|
|
"mean_token_accuracy": 0.22316697984933853,
|
|
"num_tokens": 38429914.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.085983371734619,
|
|
"epoch": 1.638475282906492,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004742513643199339,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.21132204830646514,
|
|
"num_tokens": 38443805.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.067601156234741,
|
|
"epoch": 1.6390708755211434,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000474231566244596,
|
|
"loss": 4.6543,
|
|
"mean_token_accuracy": 0.22296009808778763,
|
|
"num_tokens": 38457667.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.119910812377929,
|
|
"epoch": 1.639666468135795,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047421176102314586,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.22144586145877837,
|
|
"num_tokens": 38470560.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.105608320236206,
|
|
"epoch": 1.6402620607504468,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047419194865629366,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.2265127882361412,
|
|
"num_tokens": 38483128.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.069802713394165,
|
|
"epoch": 1.6408576533650983,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047417212914475015,
|
|
"loss": 4.7416,
|
|
"mean_token_accuracy": 0.21555184125900267,
|
|
"num_tokens": 38496237.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.051178741455078,
|
|
"epoch": 1.6414532459797497,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047415230248922625,
|
|
"loss": 4.6303,
|
|
"mean_token_accuracy": 0.22814795821905137,
|
|
"num_tokens": 38510464.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.037231588363648,
|
|
"epoch": 1.6420488385944014,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004741324686904331,
|
|
"loss": 4.619,
|
|
"mean_token_accuracy": 0.23546933382749557,
|
|
"num_tokens": 38524695.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.06313681602478,
|
|
"epoch": 1.6426444312090531,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047411262774908194,
|
|
"loss": 4.6186,
|
|
"mean_token_accuracy": 0.22275607138872147,
|
|
"num_tokens": 38540391.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.023447179794312,
|
|
"epoch": 1.6432400238237046,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004740927796658846,
|
|
"loss": 4.6042,
|
|
"mean_token_accuracy": 0.2237308770418167,
|
|
"num_tokens": 38553816.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 4.992061042785645,
|
|
"epoch": 1.643835616438356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000474072924441553,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.23826507180929185,
|
|
"num_tokens": 38567794.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.039886379241944,
|
|
"epoch": 1.6444312090530078,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047405306207679926,
|
|
"loss": 4.6616,
|
|
"mean_token_accuracy": 0.22377371042966843,
|
|
"num_tokens": 38580427.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.074953603744507,
|
|
"epoch": 1.6450268016676595,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047403319257233585,
|
|
"loss": 4.6777,
|
|
"mean_token_accuracy": 0.2227858230471611,
|
|
"num_tokens": 38593875.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.040798568725586,
|
|
"epoch": 1.645622394282311,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004740133159288753,
|
|
"loss": 4.6513,
|
|
"mean_token_accuracy": 0.21890471130609512,
|
|
"num_tokens": 38609201.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.029165267944336,
|
|
"epoch": 1.6462179868969624,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004739934321471308,
|
|
"loss": 4.6115,
|
|
"mean_token_accuracy": 0.2273232012987137,
|
|
"num_tokens": 38622953.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.058700180053711,
|
|
"epoch": 1.6468135795116141,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004739735412278154,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.22190966904163362,
|
|
"num_tokens": 38638018.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.1100996971130375,
|
|
"epoch": 1.6474091721262656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004739536431716427,
|
|
"loss": 4.7798,
|
|
"mean_token_accuracy": 0.21697996258735658,
|
|
"num_tokens": 38650546.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.079371309280395,
|
|
"epoch": 1.648004764740917,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047393373797932614,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.22292059808969497,
|
|
"num_tokens": 38667662.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.072495937347412,
|
|
"epoch": 1.6486003573555688,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047391382565157994,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.21662255376577377,
|
|
"num_tokens": 38681431.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.096959161758423,
|
|
"epoch": 1.6491959499702205,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004738939061891182,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.21545254737138747,
|
|
"num_tokens": 38694116.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.048950433731079,
|
|
"epoch": 1.649791542584872,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004738739795926554,
|
|
"loss": 4.6349,
|
|
"mean_token_accuracy": 0.2252332255244255,
|
|
"num_tokens": 38708194.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.094982147216797,
|
|
"epoch": 1.6503871351995234,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004738540458629063,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.209587761759758,
|
|
"num_tokens": 38722499.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.17686128616333,
|
|
"epoch": 1.650982727814175,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004738341050005859,
|
|
"loss": 4.8167,
|
|
"mean_token_accuracy": 0.21918147653341294,
|
|
"num_tokens": 38737231.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.131583213806152,
|
|
"epoch": 1.6515783204288268,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047381415700640953,
|
|
"loss": 4.7173,
|
|
"mean_token_accuracy": 0.21844828724861146,
|
|
"num_tokens": 38751922.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.019286680221557,
|
|
"epoch": 1.6521739130434783,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047379420188109245,
|
|
"loss": 4.6335,
|
|
"mean_token_accuracy": 0.22750917077064514,
|
|
"num_tokens": 38765039.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.060495185852051,
|
|
"epoch": 1.6527695056581297,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004737742396253506,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.2203103318810463,
|
|
"num_tokens": 38777996.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.027131462097168,
|
|
"epoch": 1.6533650982727814,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004737542702399,
|
|
"loss": 4.5888,
|
|
"mean_token_accuracy": 0.2310270994901657,
|
|
"num_tokens": 38791015.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.022165775299072,
|
|
"epoch": 1.6539606908874331,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00047373429372545695,
|
|
"loss": 4.6016,
|
|
"mean_token_accuracy": 0.23093222230672836,
|
|
"num_tokens": 38804859.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.10565414428711,
|
|
"epoch": 1.6545562835020846,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004737143100827378,
|
|
"loss": 4.7834,
|
|
"mean_token_accuracy": 0.21540358960628508,
|
|
"num_tokens": 38817352.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.050475692749023,
|
|
"epoch": 1.655151876116736,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004736943193124595,
|
|
"loss": 4.6313,
|
|
"mean_token_accuracy": 0.22819598764181137,
|
|
"num_tokens": 38830966.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.041847991943359,
|
|
"epoch": 1.6557474687313878,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000473674321415339,
|
|
"loss": 4.6363,
|
|
"mean_token_accuracy": 0.22259974032640456,
|
|
"num_tokens": 38845609.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.057607650756836,
|
|
"epoch": 1.6563430613460393,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004736543163920936,
|
|
"loss": 4.6827,
|
|
"mean_token_accuracy": 0.2226508617401123,
|
|
"num_tokens": 38859675.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.128577947616577,
|
|
"epoch": 1.6569386539606907,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004736343042434409,
|
|
"loss": 4.6718,
|
|
"mean_token_accuracy": 0.22111345529556276,
|
|
"num_tokens": 38872625.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.129309511184692,
|
|
"epoch": 1.6575342465753424,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004736142849700986,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.22252066284418107,
|
|
"num_tokens": 38886970.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.098152780532837,
|
|
"epoch": 1.6581298391899941,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047359425857278485,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.2200102061033249,
|
|
"num_tokens": 38901611.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.112901115417481,
|
|
"epoch": 1.6587254318046456,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000473574225052218,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.2131174847483635,
|
|
"num_tokens": 38917296.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.152828168869019,
|
|
"epoch": 1.659321024419297,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004735541844091165,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.22259539514780044,
|
|
"num_tokens": 38933556.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.149855852127075,
|
|
"epoch": 1.6599166170339488,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004735341366441993,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.21504420638084412,
|
|
"num_tokens": 38946598.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.098342847824097,
|
|
"epoch": 1.6605122096486005,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00047351408175818537,
|
|
"loss": 4.7134,
|
|
"mean_token_accuracy": 0.22679511308670045,
|
|
"num_tokens": 38960346.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.0709278106689455,
|
|
"epoch": 1.661107802263252,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004734940197517941,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.22090433835983275,
|
|
"num_tokens": 38973764.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.152578401565552,
|
|
"epoch": 1.6617033948779034,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000473473950625745,
|
|
"loss": 4.7715,
|
|
"mean_token_accuracy": 0.2167654186487198,
|
|
"num_tokens": 38987616.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.132358503341675,
|
|
"epoch": 1.6622989874925551,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047345387438075805,
|
|
"loss": 4.7641,
|
|
"mean_token_accuracy": 0.21627280861139297,
|
|
"num_tokens": 39000726.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.015635061264038,
|
|
"epoch": 1.6628945801072068,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004734337910175533,
|
|
"loss": 4.6277,
|
|
"mean_token_accuracy": 0.22446851879358293,
|
|
"num_tokens": 39015288.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.056862115859985,
|
|
"epoch": 1.6634901727218583,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047341370053685113,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.2237915128469467,
|
|
"num_tokens": 39028683.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.196324586868286,
|
|
"epoch": 1.6640857653365098,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004733936029393721,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.2064226284623146,
|
|
"num_tokens": 39045066.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.118253946304321,
|
|
"epoch": 1.6646813579511615,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004733734982258371,
|
|
"loss": 4.6556,
|
|
"mean_token_accuracy": 0.22216410636901857,
|
|
"num_tokens": 39059455.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.066488122940063,
|
|
"epoch": 1.665276950565813,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047335338639696724,
|
|
"loss": 4.6941,
|
|
"mean_token_accuracy": 0.23147401660680772,
|
|
"num_tokens": 39072611.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.003202295303344,
|
|
"epoch": 1.6658725431804644,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004733332674534839,
|
|
"loss": 4.5496,
|
|
"mean_token_accuracy": 0.23683178722858428,
|
|
"num_tokens": 39085790.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 4.979494094848633,
|
|
"epoch": 1.666468135795116,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004733131413961087,
|
|
"loss": 4.5826,
|
|
"mean_token_accuracy": 0.2243669480085373,
|
|
"num_tokens": 39099466.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.012187910079956,
|
|
"epoch": 1.6670637284097678,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047329300822556363,
|
|
"loss": 4.5736,
|
|
"mean_token_accuracy": 0.22526251077651976,
|
|
"num_tokens": 39114278.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.026428174972534,
|
|
"epoch": 1.6676593210244193,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004732728679425707,
|
|
"loss": 4.6907,
|
|
"mean_token_accuracy": 0.2225686177611351,
|
|
"num_tokens": 39128438.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.151434373855591,
|
|
"epoch": 1.6682549136390707,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004732527205478524,
|
|
"loss": 4.8024,
|
|
"mean_token_accuracy": 0.2115221619606018,
|
|
"num_tokens": 39143113.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.144213771820068,
|
|
"epoch": 1.6688505062537224,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004732325660421314,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.21873480528593064,
|
|
"num_tokens": 39156850.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.037568283081055,
|
|
"epoch": 1.6694460988683741,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004732124044261304,
|
|
"loss": 4.6733,
|
|
"mean_token_accuracy": 0.22882260084152223,
|
|
"num_tokens": 39169036.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.046535634994507,
|
|
"epoch": 1.6700416914830256,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00047319223570057293,
|
|
"loss": 4.631,
|
|
"mean_token_accuracy": 0.22694451361894608,
|
|
"num_tokens": 39182838.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.051830148696899,
|
|
"epoch": 1.670637284097677,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004731720598661821,
|
|
"loss": 4.6096,
|
|
"mean_token_accuracy": 0.23116818964481353,
|
|
"num_tokens": 39195369.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.061387062072754,
|
|
"epoch": 1.6712328767123288,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047315187692368167,
|
|
"loss": 4.6496,
|
|
"mean_token_accuracy": 0.2293048918247223,
|
|
"num_tokens": 39208266.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.065730285644531,
|
|
"epoch": 1.6718284693269805,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004731316868737957,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.22380347847938536,
|
|
"num_tokens": 39220947.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.119314527511596,
|
|
"epoch": 1.672424061941632,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00047311148971724816,
|
|
"loss": 4.7438,
|
|
"mean_token_accuracy": 0.2141859069466591,
|
|
"num_tokens": 39236361.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.1608928680419925,
|
|
"epoch": 1.6730196545562834,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004730912854547636,
|
|
"loss": 4.748,
|
|
"mean_token_accuracy": 0.22009506821632385,
|
|
"num_tokens": 39249879.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.029076862335205,
|
|
"epoch": 1.6736152471709351,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004730710740870667,
|
|
"loss": 4.6334,
|
|
"mean_token_accuracy": 0.22827306091785432,
|
|
"num_tokens": 39264211.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.053279972076416,
|
|
"epoch": 1.6742108397855868,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00047305085561488247,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.22567150890827178,
|
|
"num_tokens": 39277583.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.048881196975708,
|
|
"epoch": 1.674806432400238,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047303063003893605,
|
|
"loss": 4.7237,
|
|
"mean_token_accuracy": 0.2273876041173935,
|
|
"num_tokens": 39291121.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.040864276885986,
|
|
"epoch": 1.6754020250148898,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004730103973599529,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.22183876633644103,
|
|
"num_tokens": 39306386.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.091780948638916,
|
|
"epoch": 1.6759976176295415,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004729901575786588,
|
|
"loss": 4.6601,
|
|
"mean_token_accuracy": 0.22183104306459428,
|
|
"num_tokens": 39319720.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.1361777782440186,
|
|
"epoch": 1.676593210244193,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00047296991069577953,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.22120668441057206,
|
|
"num_tokens": 39334588.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.117886161804199,
|
|
"epoch": 1.6771888028588444,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004729496567120415,
|
|
"loss": 4.6686,
|
|
"mean_token_accuracy": 0.22730184644460677,
|
|
"num_tokens": 39348516.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.064745473861694,
|
|
"epoch": 1.6777843954734961,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047292939562817115,
|
|
"loss": 4.6129,
|
|
"mean_token_accuracy": 0.2227137416601181,
|
|
"num_tokens": 39362376.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.138356161117554,
|
|
"epoch": 1.6783799880881478,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004729091274448952,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.21191182881593704,
|
|
"num_tokens": 39375942.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.081694793701172,
|
|
"epoch": 1.6789755807027993,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004728888521629406,
|
|
"loss": 4.7031,
|
|
"mean_token_accuracy": 0.22297860383987428,
|
|
"num_tokens": 39389169.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.155364561080932,
|
|
"epoch": 1.6795711733174508,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047286856978303465,
|
|
"loss": 4.7486,
|
|
"mean_token_accuracy": 0.21469902992248535,
|
|
"num_tokens": 39400875.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.081697559356689,
|
|
"epoch": 1.6801667659321025,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004728482803059048,
|
|
"loss": 4.6262,
|
|
"mean_token_accuracy": 0.2210976392030716,
|
|
"num_tokens": 39415905.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 4.979950284957885,
|
|
"epoch": 1.6807623585467542,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004728279837322788,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.22595161348581314,
|
|
"num_tokens": 39428204.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.053210306167602,
|
|
"epoch": 1.6813579511614056,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004728076800628847,
|
|
"loss": 4.6387,
|
|
"mean_token_accuracy": 0.22938165813684464,
|
|
"num_tokens": 39441637.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.130769348144531,
|
|
"epoch": 1.681953543776057,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004727873692984507,
|
|
"loss": 4.6696,
|
|
"mean_token_accuracy": 0.22646723091602325,
|
|
"num_tokens": 39456018.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.0848961353302,
|
|
"epoch": 1.6825491363907088,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004727670514397054,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.21243221312761307,
|
|
"num_tokens": 39469871.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.042272090911865,
|
|
"epoch": 1.6831447290053605,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004727467264873775,
|
|
"loss": 4.8098,
|
|
"mean_token_accuracy": 0.20563363581895827,
|
|
"num_tokens": 39483749.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.218365430831909,
|
|
"epoch": 1.6837403216200117,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000472726394442196,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.22262977808713913,
|
|
"num_tokens": 39496233.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.145276737213135,
|
|
"epoch": 1.6843359142346634,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047270605530489026,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.22664231061935425,
|
|
"num_tokens": 39510240.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.039422130584716,
|
|
"epoch": 1.6849315068493151,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047268570907618967,
|
|
"loss": 4.6255,
|
|
"mean_token_accuracy": 0.23234971910715102,
|
|
"num_tokens": 39523735.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 4.968775224685669,
|
|
"epoch": 1.6855270994639666,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004726653557568242,
|
|
"loss": 4.5375,
|
|
"mean_token_accuracy": 0.24157785028219222,
|
|
"num_tokens": 39538358.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.065573358535767,
|
|
"epoch": 1.686122692078618,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047264499534752384,
|
|
"loss": 4.6303,
|
|
"mean_token_accuracy": 0.23128743022680281,
|
|
"num_tokens": 39552364.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.057020378112793,
|
|
"epoch": 1.6867182846932698,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047262462784901875,
|
|
"loss": 4.6396,
|
|
"mean_token_accuracy": 0.22391653805971146,
|
|
"num_tokens": 39563748.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.030126428604126,
|
|
"epoch": 1.6873138773079215,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047260425326203965,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.22893166095018386,
|
|
"num_tokens": 39575042.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.1644031524658205,
|
|
"epoch": 1.687909469922573,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004725838715873172,
|
|
"loss": 4.7843,
|
|
"mean_token_accuracy": 0.21917092353105544,
|
|
"num_tokens": 39589617.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.067977857589722,
|
|
"epoch": 1.6885050625372244,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047256348282558264,
|
|
"loss": 4.6448,
|
|
"mean_token_accuracy": 0.23452917784452437,
|
|
"num_tokens": 39603466.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.096775484085083,
|
|
"epoch": 1.6891006551518761,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047254308697756704,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.22058121412992476,
|
|
"num_tokens": 39616253.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.032509803771973,
|
|
"epoch": 1.6896962477665278,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004725226840440022,
|
|
"loss": 4.6691,
|
|
"mean_token_accuracy": 0.23152135759592057,
|
|
"num_tokens": 39630943.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.109173774719238,
|
|
"epoch": 1.6902918403811793,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047250227402561976,
|
|
"loss": 4.7452,
|
|
"mean_token_accuracy": 0.21115901470184326,
|
|
"num_tokens": 39645769.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.031571578979492,
|
|
"epoch": 1.6908874329958308,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004724818569231519,
|
|
"loss": 4.6214,
|
|
"mean_token_accuracy": 0.23076957315206528,
|
|
"num_tokens": 39659102.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.077780294418335,
|
|
"epoch": 1.6914830256104825,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.00047246143273733097,
|
|
"loss": 4.7398,
|
|
"mean_token_accuracy": 0.21997995525598527,
|
|
"num_tokens": 39673868.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.0241492748260494,
|
|
"epoch": 1.6920786182251342,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004724410014688894,
|
|
"loss": 4.5613,
|
|
"mean_token_accuracy": 0.2368965983390808,
|
|
"num_tokens": 39687219.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.06047739982605,
|
|
"epoch": 1.6926742108397854,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047242056311856017,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.2187872424721718,
|
|
"num_tokens": 39701535.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.097841835021972,
|
|
"epoch": 1.6932698034544371,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004724001176870764,
|
|
"loss": 4.6616,
|
|
"mean_token_accuracy": 0.22301466166973113,
|
|
"num_tokens": 39714807.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.068501329421997,
|
|
"epoch": 1.6938653960690888,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004723796651751713,
|
|
"loss": 4.634,
|
|
"mean_token_accuracy": 0.22665929645299912,
|
|
"num_tokens": 39727383.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.045538282394409,
|
|
"epoch": 1.6944609886837403,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004723592055835784,
|
|
"loss": 4.6255,
|
|
"mean_token_accuracy": 0.222190198302269,
|
|
"num_tokens": 39740919.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.074969673156739,
|
|
"epoch": 1.6950565812983918,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047233873891303193,
|
|
"loss": 4.6881,
|
|
"mean_token_accuracy": 0.21594958901405334,
|
|
"num_tokens": 39754675.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.080799198150634,
|
|
"epoch": 1.6956521739130435,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047231826516426554,
|
|
"loss": 4.6626,
|
|
"mean_token_accuracy": 0.22534708082675933,
|
|
"num_tokens": 39768277.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.130510377883911,
|
|
"epoch": 1.6962477665276952,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004722977843380139,
|
|
"loss": 4.7156,
|
|
"mean_token_accuracy": 0.22253693789243698,
|
|
"num_tokens": 39781736.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.126166248321534,
|
|
"epoch": 1.6968433591423466,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004722772964350115,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.21684023439884187,
|
|
"num_tokens": 39797715.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.100535297393799,
|
|
"epoch": 1.697438951756998,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047225680145599326,
|
|
"loss": 4.6882,
|
|
"mean_token_accuracy": 0.2296873837709427,
|
|
"num_tokens": 39811264.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.082325506210327,
|
|
"epoch": 1.6980345443716498,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004722362994016942,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.22646172493696212,
|
|
"num_tokens": 39825217.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.037418460845947,
|
|
"epoch": 1.6986301369863015,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004722157902728498,
|
|
"loss": 4.7019,
|
|
"mean_token_accuracy": 0.22011291682720185,
|
|
"num_tokens": 39839568.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.1313189506530765,
|
|
"epoch": 1.699225729600953,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047219527407019575,
|
|
"loss": 4.7462,
|
|
"mean_token_accuracy": 0.2178041085600853,
|
|
"num_tokens": 39854648.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.01146936416626,
|
|
"epoch": 1.6998213222156044,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047217475079446773,
|
|
"loss": 4.6306,
|
|
"mean_token_accuracy": 0.22833576500415803,
|
|
"num_tokens": 39868419.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.0765386581420895,
|
|
"epoch": 1.7004169148302561,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000472154220446402,
|
|
"loss": 4.6896,
|
|
"mean_token_accuracy": 0.2269895777106285,
|
|
"num_tokens": 39882105.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.112679481506348,
|
|
"epoch": 1.7010125074449078,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00047213368302673496,
|
|
"loss": 4.7279,
|
|
"mean_token_accuracy": 0.22298967838287354,
|
|
"num_tokens": 39897146.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.014979028701783,
|
|
"epoch": 1.7016081000595593,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004721131385362033,
|
|
"loss": 4.5978,
|
|
"mean_token_accuracy": 0.23144956082105636,
|
|
"num_tokens": 39909801.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.063724660873413,
|
|
"epoch": 1.7022036926742108,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004720925869755437,
|
|
"loss": 4.5981,
|
|
"mean_token_accuracy": 0.22886793911457062,
|
|
"num_tokens": 39921708.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.01027021408081,
|
|
"epoch": 1.7027992852888625,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00047207202834549357,
|
|
"loss": 4.6117,
|
|
"mean_token_accuracy": 0.22785676270723343,
|
|
"num_tokens": 39935033.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.067987585067749,
|
|
"epoch": 1.703394877903514,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00047205146264679015,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.22457403391599656,
|
|
"num_tokens": 39950212.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 4.964820718765258,
|
|
"epoch": 1.7039904705181654,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00047203088988017114,
|
|
"loss": 4.6198,
|
|
"mean_token_accuracy": 0.230758960545063,
|
|
"num_tokens": 39964091.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.114203596115113,
|
|
"epoch": 1.7045860631328171,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047201031004637445,
|
|
"loss": 4.7234,
|
|
"mean_token_accuracy": 0.21886857599020004,
|
|
"num_tokens": 39978523.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.111216688156128,
|
|
"epoch": 1.7051816557474688,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004719897231461383,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.23055000305175782,
|
|
"num_tokens": 39992741.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.075935363769531,
|
|
"epoch": 1.7057772483621203,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004719691291802011,
|
|
"loss": 4.6836,
|
|
"mean_token_accuracy": 0.21794382929801942,
|
|
"num_tokens": 40007002.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.069309139251709,
|
|
"epoch": 1.7063728409767718,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047194852814930145,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.21428143382072448,
|
|
"num_tokens": 40021516.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.031895923614502,
|
|
"epoch": 1.7069684335914235,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00047192792005417827,
|
|
"loss": 4.6314,
|
|
"mean_token_accuracy": 0.23058801293373107,
|
|
"num_tokens": 40035123.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.031788158416748,
|
|
"epoch": 1.7075640262060752,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004719073048955709,
|
|
"loss": 4.6408,
|
|
"mean_token_accuracy": 0.21948543637990953,
|
|
"num_tokens": 40047985.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.007802295684814,
|
|
"epoch": 1.7081596188207266,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004718866826742185,
|
|
"loss": 4.6294,
|
|
"mean_token_accuracy": 0.23266545534133912,
|
|
"num_tokens": 40064974.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.070239877700805,
|
|
"epoch": 1.7087552114353781,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000471866053390861,
|
|
"loss": 4.6364,
|
|
"mean_token_accuracy": 0.2223280906677246,
|
|
"num_tokens": 40077737.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.085991048812867,
|
|
"epoch": 1.7093508040500298,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047184541704623823,
|
|
"loss": 4.6383,
|
|
"mean_token_accuracy": 0.22529711425304413,
|
|
"num_tokens": 40091183.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.040211009979248,
|
|
"epoch": 1.7099463966646815,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047182477364109045,
|
|
"loss": 4.6038,
|
|
"mean_token_accuracy": 0.2311077520251274,
|
|
"num_tokens": 40103992.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.042794513702392,
|
|
"epoch": 1.710541989279333,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000471804123176158,
|
|
"loss": 4.6225,
|
|
"mean_token_accuracy": 0.21876481771469117,
|
|
"num_tokens": 40118916.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.023737812042237,
|
|
"epoch": 1.7111375818939845,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004717834656521816,
|
|
"loss": 4.6779,
|
|
"mean_token_accuracy": 0.22360279113054277,
|
|
"num_tokens": 40132953.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.021018362045288,
|
|
"epoch": 1.7117331745086362,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047176280106990233,
|
|
"loss": 4.6544,
|
|
"mean_token_accuracy": 0.21453473269939421,
|
|
"num_tokens": 40148570.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.121182537078857,
|
|
"epoch": 1.7123287671232876,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004717421294300612,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.2145558178424835,
|
|
"num_tokens": 40162295.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.013561058044433,
|
|
"epoch": 1.712924359737939,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004717214507333999,
|
|
"loss": 4.6175,
|
|
"mean_token_accuracy": 0.22347043454647064,
|
|
"num_tokens": 40176972.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.055509901046753,
|
|
"epoch": 1.7135199523525908,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047170076498066,
|
|
"loss": 4.6639,
|
|
"mean_token_accuracy": 0.22760914266109467,
|
|
"num_tokens": 40191152.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.026268529891968,
|
|
"epoch": 1.7141155449672425,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004716800721725834,
|
|
"loss": 4.5798,
|
|
"mean_token_accuracy": 0.22637320011854173,
|
|
"num_tokens": 40205526.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.061535501480103,
|
|
"epoch": 1.714711137581894,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004716593723099124,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.22152921110391616,
|
|
"num_tokens": 40219365.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.128917264938354,
|
|
"epoch": 1.7153067301965454,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.00047163866539338945,
|
|
"loss": 4.7487,
|
|
"mean_token_accuracy": 0.21849056780338288,
|
|
"num_tokens": 40234505.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.058815431594849,
|
|
"epoch": 1.7159023228111971,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047161795142375735,
|
|
"loss": 4.7029,
|
|
"mean_token_accuracy": 0.22250208556652068,
|
|
"num_tokens": 40249041.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.049796390533447,
|
|
"epoch": 1.7164979154258488,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047159723040175896,
|
|
"loss": 4.6527,
|
|
"mean_token_accuracy": 0.2251900091767311,
|
|
"num_tokens": 40263718.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 4.94970932006836,
|
|
"epoch": 1.7170935080405003,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004715765023281376,
|
|
"loss": 4.5197,
|
|
"mean_token_accuracy": 0.24385487884283066,
|
|
"num_tokens": 40276478.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.013146638870239,
|
|
"epoch": 1.7176891006551518,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004715557672036367,
|
|
"loss": 4.6105,
|
|
"mean_token_accuracy": 0.23117339611053467,
|
|
"num_tokens": 40288176.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.063272905349732,
|
|
"epoch": 1.7182846932698035,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047153502502899995,
|
|
"loss": 4.6835,
|
|
"mean_token_accuracy": 0.22431018352508544,
|
|
"num_tokens": 40302483.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.090257024765014,
|
|
"epoch": 1.7188802858844552,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047151427580497155,
|
|
"loss": 4.6327,
|
|
"mean_token_accuracy": 0.22395631968975066,
|
|
"num_tokens": 40314927.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.088172101974488,
|
|
"epoch": 1.7194758784991067,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004714935195322954,
|
|
"loss": 4.7549,
|
|
"mean_token_accuracy": 0.21616952270269393,
|
|
"num_tokens": 40328327.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.055940628051758,
|
|
"epoch": 1.7200714711137581,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004714727562117163,
|
|
"loss": 4.6429,
|
|
"mean_token_accuracy": 0.21769565343856812,
|
|
"num_tokens": 40344616.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.165597772598266,
|
|
"epoch": 1.7206670637284098,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00047145198584397884,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.2177763044834137,
|
|
"num_tokens": 40358804.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.114166212081909,
|
|
"epoch": 1.7212626563430613,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004714312084298281,
|
|
"loss": 4.6417,
|
|
"mean_token_accuracy": 0.22439996153116226,
|
|
"num_tokens": 40372527.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.016893482208252,
|
|
"epoch": 1.7218582489577128,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004714104239700093,
|
|
"loss": 4.67,
|
|
"mean_token_accuracy": 0.2187953844666481,
|
|
"num_tokens": 40387115.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.118768501281738,
|
|
"epoch": 1.7224538415723645,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004713896324652679,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.21145153939723968,
|
|
"num_tokens": 40401657.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.062459325790405,
|
|
"epoch": 1.7230494341870162,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047136883391634966,
|
|
"loss": 4.6655,
|
|
"mean_token_accuracy": 0.2249577522277832,
|
|
"num_tokens": 40416283.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.053873014450073,
|
|
"epoch": 1.7236450268016676,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004713480283240007,
|
|
"loss": 4.6864,
|
|
"mean_token_accuracy": 0.2255982607603073,
|
|
"num_tokens": 40432132.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.0287885665893555,
|
|
"epoch": 1.7242406194163191,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004713272156889672,
|
|
"loss": 4.5978,
|
|
"mean_token_accuracy": 0.23533716946840286,
|
|
"num_tokens": 40446105.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.028334665298462,
|
|
"epoch": 1.7248362120309708,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004713063960119956,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.2265758365392685,
|
|
"num_tokens": 40460152.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.089952373504639,
|
|
"epoch": 1.7254318046456225,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047128556929383283,
|
|
"loss": 4.7032,
|
|
"mean_token_accuracy": 0.22008780837059022,
|
|
"num_tokens": 40474934.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.0275983810424805,
|
|
"epoch": 1.726027397260274,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00047126473553522576,
|
|
"loss": 4.6702,
|
|
"mean_token_accuracy": 0.23112818896770476,
|
|
"num_tokens": 40488966.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.158887720108032,
|
|
"epoch": 1.7266229898749255,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004712438947369218,
|
|
"loss": 4.8259,
|
|
"mean_token_accuracy": 0.22002892196178436,
|
|
"num_tokens": 40504380.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.100732898712158,
|
|
"epoch": 1.7272185824895772,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004712230468996684,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.2346934571862221,
|
|
"num_tokens": 40517230.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.023535490036011,
|
|
"epoch": 1.7278141751042289,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004712021920242133,
|
|
"loss": 4.6369,
|
|
"mean_token_accuracy": 0.22964367866516114,
|
|
"num_tokens": 40530029.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 4.92939977645874,
|
|
"epoch": 1.7284097677188803,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00047118133011130465,
|
|
"loss": 4.5925,
|
|
"mean_token_accuracy": 0.22908610850572586,
|
|
"num_tokens": 40542863.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.106359577178955,
|
|
"epoch": 1.7290053603335318,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004711604611616905,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.21487234383821488,
|
|
"num_tokens": 40557112.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.089048385620117,
|
|
"epoch": 1.7296009529481835,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004711395851761198,
|
|
"loss": 4.6398,
|
|
"mean_token_accuracy": 0.22254507392644882,
|
|
"num_tokens": 40570374.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.075007343292237,
|
|
"epoch": 1.730196545562835,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004711187021553409,
|
|
"loss": 4.6435,
|
|
"mean_token_accuracy": 0.22354071885347365,
|
|
"num_tokens": 40583814.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.064160490036011,
|
|
"epoch": 1.7307921381774864,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00047109781210010306,
|
|
"loss": 4.7001,
|
|
"mean_token_accuracy": 0.21656229496002197,
|
|
"num_tokens": 40600054.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.113918685913086,
|
|
"epoch": 1.7313877307921381,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00047107691501115556,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.21284466981887817,
|
|
"num_tokens": 40614727.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.056104516983032,
|
|
"epoch": 1.7319833234067898,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004710560108892479,
|
|
"loss": 4.688,
|
|
"mean_token_accuracy": 0.22089471518993378,
|
|
"num_tokens": 40630103.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.065558195114136,
|
|
"epoch": 1.7325789160214413,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00047103509973513,
|
|
"loss": 4.6118,
|
|
"mean_token_accuracy": 0.22638222724199294,
|
|
"num_tokens": 40642148.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.047674369812012,
|
|
"epoch": 1.7331745086360928,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047101418154955166,
|
|
"loss": 4.5759,
|
|
"mean_token_accuracy": 0.22636962682008743,
|
|
"num_tokens": 40655324.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.060694456100464,
|
|
"epoch": 1.7337701012507445,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004709932563332633,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.22344247698783876,
|
|
"num_tokens": 40669709.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.015408277511597,
|
|
"epoch": 1.7343656938653962,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047097232408701564,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.21946806013584136,
|
|
"num_tokens": 40684829.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.110058879852295,
|
|
"epoch": 1.7349612864800477,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047095138481155924,
|
|
"loss": 4.7207,
|
|
"mean_token_accuracy": 0.22421374619007112,
|
|
"num_tokens": 40698737.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.144685363769531,
|
|
"epoch": 1.7355568790946991,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047093043850764533,
|
|
"loss": 4.694,
|
|
"mean_token_accuracy": 0.2248048037290573,
|
|
"num_tokens": 40713550.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.091194915771484,
|
|
"epoch": 1.7361524717093508,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004709094851760251,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.216465924680233,
|
|
"num_tokens": 40726023.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.024123239517212,
|
|
"epoch": 1.7367480643240025,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004708885248174503,
|
|
"loss": 4.6052,
|
|
"mean_token_accuracy": 0.2260633647441864,
|
|
"num_tokens": 40739053.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.064187335968017,
|
|
"epoch": 1.737343656938654,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004708675574326724,
|
|
"loss": 4.6136,
|
|
"mean_token_accuracy": 0.228203883767128,
|
|
"num_tokens": 40752146.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.086608362197876,
|
|
"epoch": 1.7379392495533055,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004708465830224438,
|
|
"loss": 4.6582,
|
|
"mean_token_accuracy": 0.22527477592229844,
|
|
"num_tokens": 40766266.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 4.984359979629517,
|
|
"epoch": 1.7385348421679572,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00047082560158751675,
|
|
"loss": 4.572,
|
|
"mean_token_accuracy": 0.23541899174451827,
|
|
"num_tokens": 40780362.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 4.955444240570069,
|
|
"epoch": 1.7391304347826086,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00047080461312864363,
|
|
"loss": 4.5601,
|
|
"mean_token_accuracy": 0.2330958753824234,
|
|
"num_tokens": 40793929.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 4.986877822875977,
|
|
"epoch": 1.7397260273972601,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00047078361764657745,
|
|
"loss": 4.6222,
|
|
"mean_token_accuracy": 0.2299342483282089,
|
|
"num_tokens": 40807401.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.126983976364135,
|
|
"epoch": 1.7403216200119118,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004707626151420713,
|
|
"loss": 4.7365,
|
|
"mean_token_accuracy": 0.2243405684828758,
|
|
"num_tokens": 40820223.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.033646202087402,
|
|
"epoch": 1.7409172126265635,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00047074160561587835,
|
|
"loss": 4.6397,
|
|
"mean_token_accuracy": 0.23269426077604294,
|
|
"num_tokens": 40833736.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.040551614761353,
|
|
"epoch": 1.741512805241215,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004707205890687523,
|
|
"loss": 4.5869,
|
|
"mean_token_accuracy": 0.2321416586637497,
|
|
"num_tokens": 40848448.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.062770223617553,
|
|
"epoch": 1.7421083978558665,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004706995655014469,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.21913468986749648,
|
|
"num_tokens": 40863316.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.099873733520508,
|
|
"epoch": 1.7427039904705182,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004706785349147163,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.2258136451244354,
|
|
"num_tokens": 40877946.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.128020763397217,
|
|
"epoch": 1.7432995830851699,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.00047065749730931485,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.22412840127944947,
|
|
"num_tokens": 40893388.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.103132963180542,
|
|
"epoch": 1.7438951756998213,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004706364526859971,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.2201618880033493,
|
|
"num_tokens": 40908878.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.092348575592041,
|
|
"epoch": 1.7444907683144728,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004706154010455178,
|
|
"loss": 4.7102,
|
|
"mean_token_accuracy": 0.2228354960680008,
|
|
"num_tokens": 40921226.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.01282901763916,
|
|
"epoch": 1.7450863609291245,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00047059434238863206,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.22966694086790085,
|
|
"num_tokens": 40935508.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.059240627288818,
|
|
"epoch": 1.7456819535437762,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004705732767160954,
|
|
"loss": 4.6203,
|
|
"mean_token_accuracy": 0.22631587386131286,
|
|
"num_tokens": 40949167.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.14123306274414,
|
|
"epoch": 1.7462775461584277,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004705522040286632,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.22007144689559938,
|
|
"num_tokens": 40962359.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.09924840927124,
|
|
"epoch": 1.7468731387730791,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004705311243270915,
|
|
"loss": 4.6264,
|
|
"mean_token_accuracy": 0.22786857336759567,
|
|
"num_tokens": 40977964.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.095379495620728,
|
|
"epoch": 1.7474687313877308,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004705100376121362,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.2149938628077507,
|
|
"num_tokens": 40990565.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.025889778137207,
|
|
"epoch": 1.7480643240023823,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004704889438845537,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.2171628952026367,
|
|
"num_tokens": 41003701.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.0784563541412355,
|
|
"epoch": 1.7486599166170338,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00047046784314510074,
|
|
"loss": 4.6779,
|
|
"mean_token_accuracy": 0.22167378216981887,
|
|
"num_tokens": 41017646.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.108058118820191,
|
|
"epoch": 1.7492555092316855,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000470446735394534,
|
|
"loss": 4.7343,
|
|
"mean_token_accuracy": 0.2234089568257332,
|
|
"num_tokens": 41030933.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.016938257217407,
|
|
"epoch": 1.7498511018463372,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004704256206336106,
|
|
"loss": 4.5751,
|
|
"mean_token_accuracy": 0.22909269034862517,
|
|
"num_tokens": 41045412.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.068511724472046,
|
|
"epoch": 1.7504466944609887,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000470404498863088,
|
|
"loss": 4.7332,
|
|
"mean_token_accuracy": 0.22142210602760315,
|
|
"num_tokens": 41058870.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.101626253128051,
|
|
"epoch": 1.7510422870756401,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00047038337008372365,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.22468630522489547,
|
|
"num_tokens": 41072210.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.065725994110108,
|
|
"epoch": 1.7516378796902918,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047036223429627557,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.22939190715551377,
|
|
"num_tokens": 41084996.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.1513114929199215,
|
|
"epoch": 1.7522334723049435,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00047034109150150184,
|
|
"loss": 4.7602,
|
|
"mean_token_accuracy": 0.21562915593385695,
|
|
"num_tokens": 41100190.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.079957914352417,
|
|
"epoch": 1.752829064919595,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004703199417001607,
|
|
"loss": 4.6581,
|
|
"mean_token_accuracy": 0.22925779670476915,
|
|
"num_tokens": 41114560.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.098266315460205,
|
|
"epoch": 1.7534246575342465,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00047029878489301074,
|
|
"loss": 4.7379,
|
|
"mean_token_accuracy": 0.2262647345662117,
|
|
"num_tokens": 41128110.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.078231239318848,
|
|
"epoch": 1.7540202501488982,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004702776210808109,
|
|
"loss": 4.6381,
|
|
"mean_token_accuracy": 0.22668613493442535,
|
|
"num_tokens": 41142519.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.058174419403076,
|
|
"epoch": 1.7546158427635499,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004702564502643204,
|
|
"loss": 4.6432,
|
|
"mean_token_accuracy": 0.22863660007715225,
|
|
"num_tokens": 41156671.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.067593622207641,
|
|
"epoch": 1.7552114353782013,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00047023527244429846,
|
|
"loss": 4.7116,
|
|
"mean_token_accuracy": 0.22426455318927765,
|
|
"num_tokens": 41169406.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.0522215366363525,
|
|
"epoch": 1.7558070279928528,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004702140876215047,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.2263709142804146,
|
|
"num_tokens": 41183183.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.055236577987671,
|
|
"epoch": 1.7564026206075045,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004701928957966991,
|
|
"loss": 4.6363,
|
|
"mean_token_accuracy": 0.2249064952135086,
|
|
"num_tokens": 41198550.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.068450689315796,
|
|
"epoch": 1.756998213222156,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004701716969706416,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.22135837972164155,
|
|
"num_tokens": 41211231.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.056083917617798,
|
|
"epoch": 1.7575938058368075,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004701504911440927,
|
|
"loss": 4.6475,
|
|
"mean_token_accuracy": 0.22187213599681854,
|
|
"num_tokens": 41224934.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.103833293914795,
|
|
"epoch": 1.7581893984514592,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004701292783178129,
|
|
"loss": 4.7101,
|
|
"mean_token_accuracy": 0.22383518815040587,
|
|
"num_tokens": 41238615.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.061211156845093,
|
|
"epoch": 1.7587849910661109,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004701080584925633,
|
|
"loss": 4.6056,
|
|
"mean_token_accuracy": 0.22857502549886705,
|
|
"num_tokens": 41252952.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.05607385635376,
|
|
"epoch": 1.7593805836807623,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00047008683166910477,
|
|
"loss": 4.6243,
|
|
"mean_token_accuracy": 0.22557025253772736,
|
|
"num_tokens": 41265141.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.065696477890015,
|
|
"epoch": 1.7599761762954138,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004700655978481988,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.21747844964265822,
|
|
"num_tokens": 41277544.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.14878101348877,
|
|
"epoch": 1.7605717689100655,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000470044357030607,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.21846948117017745,
|
|
"num_tokens": 41289500.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.143591594696045,
|
|
"epoch": 1.7611673615247172,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00047002310921709123,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.22030377089977266,
|
|
"num_tokens": 41304148.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.10150294303894,
|
|
"epoch": 1.7617629541393687,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004700018544084136,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.2171715959906578,
|
|
"num_tokens": 41319423.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.042368793487549,
|
|
"epoch": 1.7623585467540201,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004699805926053365,
|
|
"loss": 4.6213,
|
|
"mean_token_accuracy": 0.228112530708313,
|
|
"num_tokens": 41334503.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.037022399902344,
|
|
"epoch": 1.7629541393686718,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046995932380862254,
|
|
"loss": 4.6216,
|
|
"mean_token_accuracy": 0.22710645347833633,
|
|
"num_tokens": 41347486.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.14074387550354,
|
|
"epoch": 1.7635497319833235,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046993804801903475,
|
|
"loss": 4.6604,
|
|
"mean_token_accuracy": 0.22626938819885253,
|
|
"num_tokens": 41360917.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.085980796813965,
|
|
"epoch": 1.764145324597975,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046991676523733603,
|
|
"loss": 4.6635,
|
|
"mean_token_accuracy": 0.22098232954740524,
|
|
"num_tokens": 41374212.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.04309115409851,
|
|
"epoch": 1.7647409172126265,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046989547546428986,
|
|
"loss": 4.6587,
|
|
"mean_token_accuracy": 0.2240084871649742,
|
|
"num_tokens": 41389444.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.0206522941589355,
|
|
"epoch": 1.7653365098272782,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00046987417870065985,
|
|
"loss": 4.535,
|
|
"mean_token_accuracy": 0.23243484348058702,
|
|
"num_tokens": 41403262.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.086266422271729,
|
|
"epoch": 1.7659321024419299,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004698528749472099,
|
|
"loss": 4.6611,
|
|
"mean_token_accuracy": 0.2244456946849823,
|
|
"num_tokens": 41416756.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.114090156555176,
|
|
"epoch": 1.7665276950565811,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004698315642047042,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.21674084961414336,
|
|
"num_tokens": 41431321.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.074222087860107,
|
|
"epoch": 1.7671232876712328,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000469810246473907,
|
|
"loss": 4.6719,
|
|
"mean_token_accuracy": 0.2170201137661934,
|
|
"num_tokens": 41446845.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.100681447982788,
|
|
"epoch": 1.7677188802858845,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046978892175558295,
|
|
"loss": 4.74,
|
|
"mean_token_accuracy": 0.21886888444423674,
|
|
"num_tokens": 41460601.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.0925665378570555,
|
|
"epoch": 1.768314472900536,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004697675900504971,
|
|
"loss": 4.6311,
|
|
"mean_token_accuracy": 0.2255154073238373,
|
|
"num_tokens": 41475361.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.084483957290649,
|
|
"epoch": 1.7689100655151875,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046974625135941445,
|
|
"loss": 4.7158,
|
|
"mean_token_accuracy": 0.2259893909096718,
|
|
"num_tokens": 41489400.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.040751266479492,
|
|
"epoch": 1.7695056581298392,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00046972490568310043,
|
|
"loss": 4.5977,
|
|
"mean_token_accuracy": 0.23034130185842513,
|
|
"num_tokens": 41504791.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.109254264831543,
|
|
"epoch": 1.7701012507444909,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046970355302232056,
|
|
"loss": 4.665,
|
|
"mean_token_accuracy": 0.23008036911487578,
|
|
"num_tokens": 41516570.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.092003345489502,
|
|
"epoch": 1.7706968433591423,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046968219337784083,
|
|
"loss": 4.7067,
|
|
"mean_token_accuracy": 0.21870611757040023,
|
|
"num_tokens": 41530112.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.062737321853637,
|
|
"epoch": 1.7712924359737938,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046966082675042745,
|
|
"loss": 4.6834,
|
|
"mean_token_accuracy": 0.2255871281027794,
|
|
"num_tokens": 41543429.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.064500522613526,
|
|
"epoch": 1.7718880285884455,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004696394531408466,
|
|
"loss": 4.6327,
|
|
"mean_token_accuracy": 0.2294671654701233,
|
|
"num_tokens": 41555705.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.041132497787475,
|
|
"epoch": 1.7724836212030972,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046961807254986503,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.22191834300756455,
|
|
"num_tokens": 41570084.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.151406621932983,
|
|
"epoch": 1.7730792138177487,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004695966849782497,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.2178856447339058,
|
|
"num_tokens": 41583394.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.088976526260376,
|
|
"epoch": 1.7736748064324002,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004695752904267676,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.22077191174030303,
|
|
"num_tokens": 41595183.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.101545953750611,
|
|
"epoch": 1.7742703990470519,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004695538888961862,
|
|
"loss": 4.6427,
|
|
"mean_token_accuracy": 0.2276032969355583,
|
|
"num_tokens": 41609180.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.053702116012573,
|
|
"epoch": 1.7748659916617036,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004695324803872732,
|
|
"loss": 4.5536,
|
|
"mean_token_accuracy": 0.23387987464666365,
|
|
"num_tokens": 41622249.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.053941345214843,
|
|
"epoch": 1.7754615842763548,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00046951106490079636,
|
|
"loss": 4.706,
|
|
"mean_token_accuracy": 0.2278085693717003,
|
|
"num_tokens": 41636393.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.087303543090821,
|
|
"epoch": 1.7760571768910065,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046948964243752393,
|
|
"loss": 4.7008,
|
|
"mean_token_accuracy": 0.22337742894887924,
|
|
"num_tokens": 41650391.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.138614463806152,
|
|
"epoch": 1.7766527695056582,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046946821299822416,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.21743589341640474,
|
|
"num_tokens": 41664690.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.102104663848877,
|
|
"epoch": 1.7772483621203097,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004694467765836659,
|
|
"loss": 4.6816,
|
|
"mean_token_accuracy": 0.22647924721240997,
|
|
"num_tokens": 41679299.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.024739217758179,
|
|
"epoch": 1.7778439547349612,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004694253331946178,
|
|
"loss": 4.5681,
|
|
"mean_token_accuracy": 0.23371808975934982,
|
|
"num_tokens": 41692567.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.037281322479248,
|
|
"epoch": 1.7784395473496128,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004694038828318492,
|
|
"loss": 4.6328,
|
|
"mean_token_accuracy": 0.2312968537211418,
|
|
"num_tokens": 41705335.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.097643709182739,
|
|
"epoch": 1.7790351399642645,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004693824254961294,
|
|
"loss": 4.7161,
|
|
"mean_token_accuracy": 0.22086361050605774,
|
|
"num_tokens": 41718991.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.004123878479004,
|
|
"epoch": 1.779630732578916,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046936096118822796,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.22753028869628905,
|
|
"num_tokens": 41732196.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.057462406158447,
|
|
"epoch": 1.7802263251935675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004693394899089149,
|
|
"loss": 4.6662,
|
|
"mean_token_accuracy": 0.22359130829572677,
|
|
"num_tokens": 41743850.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.059765815734863,
|
|
"epoch": 1.7808219178082192,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046931801165896035,
|
|
"loss": 4.668,
|
|
"mean_token_accuracy": 0.23071486353874207,
|
|
"num_tokens": 41756440.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.081653070449829,
|
|
"epoch": 1.7814175104228709,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004692965264391346,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.22601867020130156,
|
|
"num_tokens": 41770858.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.035954713821411,
|
|
"epoch": 1.7820131030375224,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046927503425020847,
|
|
"loss": 4.6241,
|
|
"mean_token_accuracy": 0.22257047146558762,
|
|
"num_tokens": 41786116.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 4.978058290481568,
|
|
"epoch": 1.7826086956521738,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004692535350929525,
|
|
"loss": 4.5954,
|
|
"mean_token_accuracy": 0.23166283518075942,
|
|
"num_tokens": 41801457.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.049128293991089,
|
|
"epoch": 1.7832042882668255,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046923202896813825,
|
|
"loss": 4.646,
|
|
"mean_token_accuracy": 0.21684490144252777,
|
|
"num_tokens": 41815603.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.091625738143921,
|
|
"epoch": 1.7837998808814772,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004692105158765369,
|
|
"loss": 4.687,
|
|
"mean_token_accuracy": 0.2239569753408432,
|
|
"num_tokens": 41829977.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 4.927270984649658,
|
|
"epoch": 1.7843954734961287,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004691889958189201,
|
|
"loss": 4.5342,
|
|
"mean_token_accuracy": 0.23852441906929017,
|
|
"num_tokens": 41842340.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.066445350646973,
|
|
"epoch": 1.7849910661107802,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00046916746879605974,
|
|
"loss": 4.6924,
|
|
"mean_token_accuracy": 0.21931281685829163,
|
|
"num_tokens": 41857040.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.053009510040283,
|
|
"epoch": 1.7855866587254319,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000469145934808728,
|
|
"loss": 4.5711,
|
|
"mean_token_accuracy": 0.23580411523580552,
|
|
"num_tokens": 41871827.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.090873098373413,
|
|
"epoch": 1.7861822513400833,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046912439385769723,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.2267092138528824,
|
|
"num_tokens": 41885845.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.006196546554565,
|
|
"epoch": 1.7867778439547348,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004691028459437401,
|
|
"loss": 4.5955,
|
|
"mean_token_accuracy": 0.22868838757276536,
|
|
"num_tokens": 41900057.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.7867778439547348,
|
|
"eval_entropy": 4.807819321611459,
|
|
"eval_loss": 4.663021564483643,
|
|
"eval_mean_token_accuracy": 0.2353114187390453,
|
|
"eval_num_tokens": 41900057.0,
|
|
"eval_runtime": 18.4626,
|
|
"eval_samples_per_second": 1381.877,
|
|
"eval_steps_per_second": 172.782,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.10032958984375,
|
|
"epoch": 1.7873734365693865,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004690812910676294,
|
|
"loss": 4.7584,
|
|
"mean_token_accuracy": 0.21796216070652008,
|
|
"num_tokens": 41913983.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.060779809951782,
|
|
"epoch": 1.7879690291840382,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004690597292301384,
|
|
"loss": 4.6431,
|
|
"mean_token_accuracy": 0.22641909420490264,
|
|
"num_tokens": 41927554.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.156938219070435,
|
|
"epoch": 1.7885646217986897,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046903816043204045,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.2132396101951599,
|
|
"num_tokens": 41941367.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.1997192859649655,
|
|
"epoch": 1.7891602144133412,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004690165846741092,
|
|
"loss": 4.8629,
|
|
"mean_token_accuracy": 0.20932962596416474,
|
|
"num_tokens": 41956173.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.063211441040039,
|
|
"epoch": 1.7897558070279929,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046899500195711843,
|
|
"loss": 4.6427,
|
|
"mean_token_accuracy": 0.22140477746725082,
|
|
"num_tokens": 41969788.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.011654901504516,
|
|
"epoch": 1.7903513996426446,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046897341228184237,
|
|
"loss": 4.5665,
|
|
"mean_token_accuracy": 0.22914109230041504,
|
|
"num_tokens": 41982369.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.120100641250611,
|
|
"epoch": 1.790946992257296,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004689518156490554,
|
|
"loss": 4.7608,
|
|
"mean_token_accuracy": 0.2205112248659134,
|
|
"num_tokens": 41995143.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.036790132522583,
|
|
"epoch": 1.7915425848719475,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004689302120595322,
|
|
"loss": 4.6529,
|
|
"mean_token_accuracy": 0.22319983094930648,
|
|
"num_tokens": 42009290.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.089780664443969,
|
|
"epoch": 1.7921381774865992,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046890860151404753,
|
|
"loss": 4.652,
|
|
"mean_token_accuracy": 0.22450165301561356,
|
|
"num_tokens": 42024164.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.063192749023438,
|
|
"epoch": 1.792733770101251,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046888698401337665,
|
|
"loss": 4.6292,
|
|
"mean_token_accuracy": 0.22777922600507736,
|
|
"num_tokens": 42039738.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.036126661300659,
|
|
"epoch": 1.7933293627159024,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046886535955829487,
|
|
"loss": 4.6511,
|
|
"mean_token_accuracy": 0.2301958128809929,
|
|
"num_tokens": 42054853.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.146411037445068,
|
|
"epoch": 1.7939249553305538,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004688437281495779,
|
|
"loss": 4.7502,
|
|
"mean_token_accuracy": 0.22019417136907576,
|
|
"num_tokens": 42069926.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 4.973195600509643,
|
|
"epoch": 1.7945205479452055,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004688220897880015,
|
|
"loss": 4.5443,
|
|
"mean_token_accuracy": 0.2305596500635147,
|
|
"num_tokens": 42084072.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.0360236167907715,
|
|
"epoch": 1.795116140559857,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004688004444743419,
|
|
"loss": 4.6078,
|
|
"mean_token_accuracy": 0.22712961435317994,
|
|
"num_tokens": 42098212.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 4.983701515197754,
|
|
"epoch": 1.7957117331745085,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046877879220937546,
|
|
"loss": 4.6099,
|
|
"mean_token_accuracy": 0.22347670197486877,
|
|
"num_tokens": 42111402.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.130743360519409,
|
|
"epoch": 1.7963073257891602,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004687571329938788,
|
|
"loss": 4.7264,
|
|
"mean_token_accuracy": 0.22445931732654573,
|
|
"num_tokens": 42124724.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.089619827270508,
|
|
"epoch": 1.7969029184038119,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.00046873546682862883,
|
|
"loss": 4.644,
|
|
"mean_token_accuracy": 0.23100375682115554,
|
|
"num_tokens": 42141562.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.0057137966156,
|
|
"epoch": 1.7974985110184634,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046871379371440263,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.21615242063999177,
|
|
"num_tokens": 42155455.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.032132720947265,
|
|
"epoch": 1.7980941036331148,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004686921136519777,
|
|
"loss": 4.6662,
|
|
"mean_token_accuracy": 0.22491751611232758,
|
|
"num_tokens": 42170207.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.098636436462402,
|
|
"epoch": 1.7986896962477665,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004686704266421314,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.2293178141117096,
|
|
"num_tokens": 42183723.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.007307434082032,
|
|
"epoch": 1.7992852888624182,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004686487326856419,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.23079910576343537,
|
|
"num_tokens": 42198651.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.0498768329620365,
|
|
"epoch": 1.7998808814770697,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004686270317832872,
|
|
"loss": 4.6465,
|
|
"mean_token_accuracy": 0.22343513667583464,
|
|
"num_tokens": 42212736.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.000961637496948,
|
|
"epoch": 1.8004764740917212,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004686053239358457,
|
|
"loss": 4.644,
|
|
"mean_token_accuracy": 0.21970755755901336,
|
|
"num_tokens": 42228573.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.049583625793457,
|
|
"epoch": 1.8010720667063729,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046858360914409596,
|
|
"loss": 4.6777,
|
|
"mean_token_accuracy": 0.22231945842504502,
|
|
"num_tokens": 42244736.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.032198286056518,
|
|
"epoch": 1.8016676593210246,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000468561887408817,
|
|
"loss": 4.6165,
|
|
"mean_token_accuracy": 0.2319652870297432,
|
|
"num_tokens": 42260131.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.049109983444214,
|
|
"epoch": 1.802263251935676,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004685401587307879,
|
|
"loss": 4.5878,
|
|
"mean_token_accuracy": 0.22084570974111556,
|
|
"num_tokens": 42274928.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.111190748214722,
|
|
"epoch": 1.8028588445503275,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004685184231107878,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.2235766753554344,
|
|
"num_tokens": 42289245.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.136297416687012,
|
|
"epoch": 1.8034544371649792,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004684966805495966,
|
|
"loss": 4.7119,
|
|
"mean_token_accuracy": 0.22516084015369414,
|
|
"num_tokens": 42302964.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.084043502807617,
|
|
"epoch": 1.8040500297796307,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000468474931047994,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.22549379169940947,
|
|
"num_tokens": 42315456.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.015380430221557,
|
|
"epoch": 1.8046456223942822,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046845317460676033,
|
|
"loss": 4.6311,
|
|
"mean_token_accuracy": 0.22655314952135086,
|
|
"num_tokens": 42328628.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.035491275787353,
|
|
"epoch": 1.8052412150089339,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046843141122667576,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.22531727999448775,
|
|
"num_tokens": 42341166.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.0493474960327145,
|
|
"epoch": 1.8058368076235856,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046840964090852095,
|
|
"loss": 4.6002,
|
|
"mean_token_accuracy": 0.23390955924987794,
|
|
"num_tokens": 42356235.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.0415367603302,
|
|
"epoch": 1.806432400238237,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004683878636530768,
|
|
"loss": 4.6274,
|
|
"mean_token_accuracy": 0.23271116763353347,
|
|
"num_tokens": 42369457.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.043390607833862,
|
|
"epoch": 1.8070279928528885,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004683660794611244,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.22121772915124893,
|
|
"num_tokens": 42383857.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.1870721817016605,
|
|
"epoch": 1.8076235854675402,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004683442883334451,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.21535043716430663,
|
|
"num_tokens": 42399035.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.066761875152588,
|
|
"epoch": 1.808219178082192,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004683224902708206,
|
|
"loss": 4.6754,
|
|
"mean_token_accuracy": 0.22359429597854613,
|
|
"num_tokens": 42415048.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.05049409866333,
|
|
"epoch": 1.8088147706968434,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004683006852740326,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.22972106635570527,
|
|
"num_tokens": 42429295.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.0457006931304935,
|
|
"epoch": 1.8094103633114949,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004682788733438634,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.23927891701459886,
|
|
"num_tokens": 42442584.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 4.994569396972656,
|
|
"epoch": 1.8100059559261465,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004682570544810952,
|
|
"loss": 4.5816,
|
|
"mean_token_accuracy": 0.229194176197052,
|
|
"num_tokens": 42455953.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.1028587341308596,
|
|
"epoch": 1.8106015485407982,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046823522868651076,
|
|
"loss": 4.6839,
|
|
"mean_token_accuracy": 0.22704125046730042,
|
|
"num_tokens": 42470331.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.115265512466431,
|
|
"epoch": 1.8111971411554497,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004682133959608928,
|
|
"loss": 4.6979,
|
|
"mean_token_accuracy": 0.2175461992621422,
|
|
"num_tokens": 42482987.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.119931554794311,
|
|
"epoch": 1.8117927337701012,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004681915563050245,
|
|
"loss": 4.7548,
|
|
"mean_token_accuracy": 0.2137817233800888,
|
|
"num_tokens": 42496947.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.081532907485962,
|
|
"epoch": 1.812388326384753,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046816970971968916,
|
|
"loss": 4.6451,
|
|
"mean_token_accuracy": 0.2245487317442894,
|
|
"num_tokens": 42512003.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 4.97630763053894,
|
|
"epoch": 1.8129839189994044,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046814785620567036,
|
|
"loss": 4.5341,
|
|
"mean_token_accuracy": 0.23607628643512726,
|
|
"num_tokens": 42524776.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.106459522247315,
|
|
"epoch": 1.8135795116140558,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046812599576375206,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.21966501772403718,
|
|
"num_tokens": 42537767.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.152529668807984,
|
|
"epoch": 1.8141751042287075,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004681041283947182,
|
|
"loss": 4.7506,
|
|
"mean_token_accuracy": 0.2189010724425316,
|
|
"num_tokens": 42551611.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.059060287475586,
|
|
"epoch": 1.8147706968433592,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004680822540993534,
|
|
"loss": 4.6471,
|
|
"mean_token_accuracy": 0.23005294799804688,
|
|
"num_tokens": 42565183.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.080784940719605,
|
|
"epoch": 1.8153662894580107,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046806037287844195,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.2200620502233505,
|
|
"num_tokens": 42579001.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.136834573745728,
|
|
"epoch": 1.8159618820726622,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004680384847327689,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.22564557939767838,
|
|
"num_tokens": 42593549.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.068949365615845,
|
|
"epoch": 1.8165574746873139,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046801658966311914,
|
|
"loss": 4.7022,
|
|
"mean_token_accuracy": 0.21821531504392624,
|
|
"num_tokens": 42607610.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.067285680770874,
|
|
"epoch": 1.8171530673019656,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046799468767027826,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.22036987245082856,
|
|
"num_tokens": 42621239.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.177839612960815,
|
|
"epoch": 1.817748659916617,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046797277875503164,
|
|
"loss": 4.8245,
|
|
"mean_token_accuracy": 0.20916315466165541,
|
|
"num_tokens": 42635350.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.101936960220337,
|
|
"epoch": 1.8183442525312685,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046795086291816516,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.23261772394180297,
|
|
"num_tokens": 42650718.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.1472419738769535,
|
|
"epoch": 1.8189398451459202,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004679289401604651,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.2143886774778366,
|
|
"num_tokens": 42663615.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.121792030334473,
|
|
"epoch": 1.819535437760572,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004679070104827176,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.21972316950559617,
|
|
"num_tokens": 42677661.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.109287452697754,
|
|
"epoch": 1.8201310303752234,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004678850738857092,
|
|
"loss": 4.6521,
|
|
"mean_token_accuracy": 0.22761479914188384,
|
|
"num_tokens": 42692499.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.0309230327606205,
|
|
"epoch": 1.8207266229898749,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004678631303702268,
|
|
"loss": 4.6072,
|
|
"mean_token_accuracy": 0.2266168400645256,
|
|
"num_tokens": 42707501.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.077274942398072,
|
|
"epoch": 1.8213222156045266,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046784117993705753,
|
|
"loss": 4.69,
|
|
"mean_token_accuracy": 0.22067772895097731,
|
|
"num_tokens": 42720703.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.123341417312622,
|
|
"epoch": 1.821917808219178,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004678192225869888,
|
|
"loss": 4.6829,
|
|
"mean_token_accuracy": 0.2240080639719963,
|
|
"num_tokens": 42735839.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.11329460144043,
|
|
"epoch": 1.8225134008338295,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00046779725832080793,
|
|
"loss": 4.7054,
|
|
"mean_token_accuracy": 0.22352062314748763,
|
|
"num_tokens": 42750631.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.184581995010376,
|
|
"epoch": 1.8231089934484812,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046777528713930287,
|
|
"loss": 4.7915,
|
|
"mean_token_accuracy": 0.21869789063930511,
|
|
"num_tokens": 42763972.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.093825435638427,
|
|
"epoch": 1.823704586063133,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004677533090432617,
|
|
"loss": 4.7119,
|
|
"mean_token_accuracy": 0.2208342060446739,
|
|
"num_tokens": 42778087.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.065647792816162,
|
|
"epoch": 1.8243001786777844,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004677313240334727,
|
|
"loss": 4.6769,
|
|
"mean_token_accuracy": 0.22416457384824753,
|
|
"num_tokens": 42793447.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.192695617675781,
|
|
"epoch": 1.8248957712924359,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004677093321107245,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.220870740711689,
|
|
"num_tokens": 42809930.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.0660124778747555,
|
|
"epoch": 1.8254913639070875,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046768733327580593,
|
|
"loss": 4.6595,
|
|
"mean_token_accuracy": 0.22665696144104003,
|
|
"num_tokens": 42822469.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 4.986540985107422,
|
|
"epoch": 1.8260869565217392,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046766532752950604,
|
|
"loss": 4.5557,
|
|
"mean_token_accuracy": 0.2306226372718811,
|
|
"num_tokens": 42837857.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.107793617248535,
|
|
"epoch": 1.8266825491363907,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000467643314872614,
|
|
"loss": 4.6815,
|
|
"mean_token_accuracy": 0.22355640530586243,
|
|
"num_tokens": 42852251.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.096291875839233,
|
|
"epoch": 1.8272781417510422,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004676212953059195,
|
|
"loss": 4.6593,
|
|
"mean_token_accuracy": 0.2263022094964981,
|
|
"num_tokens": 42864792.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.07637505531311,
|
|
"epoch": 1.827873734365694,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00046759926883021234,
|
|
"loss": 4.6711,
|
|
"mean_token_accuracy": 0.22351654171943663,
|
|
"num_tokens": 42880172.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.003985595703125,
|
|
"epoch": 1.8284693269803456,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00046757723544628253,
|
|
"loss": 4.5306,
|
|
"mean_token_accuracy": 0.23244720250368117,
|
|
"num_tokens": 42894265.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.054661464691162,
|
|
"epoch": 1.829064919594997,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004675551951549204,
|
|
"loss": 4.6525,
|
|
"mean_token_accuracy": 0.2229400098323822,
|
|
"num_tokens": 42907656.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.027427721023559,
|
|
"epoch": 1.8296605122096485,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00046753314795691653,
|
|
"loss": 4.5958,
|
|
"mean_token_accuracy": 0.2298469841480255,
|
|
"num_tokens": 42920913.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.003618955612183,
|
|
"epoch": 1.8302561048243002,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004675110938530617,
|
|
"loss": 4.5141,
|
|
"mean_token_accuracy": 0.2328539028763771,
|
|
"num_tokens": 42934377.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.01810131072998,
|
|
"epoch": 1.8308516974389517,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004674890328441469,
|
|
"loss": 4.6554,
|
|
"mean_token_accuracy": 0.2216088205575943,
|
|
"num_tokens": 42947270.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.079060029983521,
|
|
"epoch": 1.8314472900536032,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004674669649309634,
|
|
"loss": 4.6998,
|
|
"mean_token_accuracy": 0.22225678116083145,
|
|
"num_tokens": 42961767.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.154794454574585,
|
|
"epoch": 1.8320428826682549,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004674448901143029,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.22226914167404174,
|
|
"num_tokens": 42977319.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.093659734725952,
|
|
"epoch": 1.8326384752829066,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004674228083949571,
|
|
"loss": 4.6335,
|
|
"mean_token_accuracy": 0.23067758679389955,
|
|
"num_tokens": 42990124.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.074593591690063,
|
|
"epoch": 1.833234067897558,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004674007197737179,
|
|
"loss": 4.6368,
|
|
"mean_token_accuracy": 0.22458430379629135,
|
|
"num_tokens": 43004445.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.0445221900939945,
|
|
"epoch": 1.8338296605122095,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004673786242513778,
|
|
"loss": 4.6448,
|
|
"mean_token_accuracy": 0.22381134629249572,
|
|
"num_tokens": 43018872.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.036621236801148,
|
|
"epoch": 1.8344252531268612,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046735652182872925,
|
|
"loss": 4.5765,
|
|
"mean_token_accuracy": 0.23644060045480728,
|
|
"num_tokens": 43030747.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 4.9881407737731935,
|
|
"epoch": 1.835020845741513,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046733441250656495,
|
|
"loss": 4.6142,
|
|
"mean_token_accuracy": 0.22602391988039017,
|
|
"num_tokens": 43045409.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.072007942199707,
|
|
"epoch": 1.8356164383561644,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000467312296285678,
|
|
"loss": 4.5744,
|
|
"mean_token_accuracy": 0.22881849855184555,
|
|
"num_tokens": 43058336.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.093471336364746,
|
|
"epoch": 1.8362120309708159,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004672901731668617,
|
|
"loss": 4.6079,
|
|
"mean_token_accuracy": 0.22804616540670394,
|
|
"num_tokens": 43071065.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 4.997619342803955,
|
|
"epoch": 1.8368076235854676,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046726804315090956,
|
|
"loss": 4.6359,
|
|
"mean_token_accuracy": 0.22948029041290283,
|
|
"num_tokens": 43083751.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.0067438125610355,
|
|
"epoch": 1.8374032162001193,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004672459062386152,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.22870012372732162,
|
|
"num_tokens": 43096494.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.052894115447998,
|
|
"epoch": 1.8379988088147707,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004672237624307729,
|
|
"loss": 4.6392,
|
|
"mean_token_accuracy": 0.22305799275636673,
|
|
"num_tokens": 43109988.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.068482732772827,
|
|
"epoch": 1.8385944014294222,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004672016117281767,
|
|
"loss": 4.6223,
|
|
"mean_token_accuracy": 0.2271920159459114,
|
|
"num_tokens": 43123152.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.019932794570923,
|
|
"epoch": 1.839189994044074,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004671794541316212,
|
|
"loss": 4.6564,
|
|
"mean_token_accuracy": 0.22583796083927155,
|
|
"num_tokens": 43137531.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.150904417037964,
|
|
"epoch": 1.8397855866587254,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004671572896419011,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.21455447375774384,
|
|
"num_tokens": 43150127.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.05850739479065,
|
|
"epoch": 1.8403811792733769,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004671351182598116,
|
|
"loss": 4.6689,
|
|
"mean_token_accuracy": 0.22816789299249648,
|
|
"num_tokens": 43165499.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.152992820739746,
|
|
"epoch": 1.8409767718880286,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004671129399861476,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.21213721483945847,
|
|
"num_tokens": 43179701.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.084904575347901,
|
|
"epoch": 1.8415723645026802,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046709075482170495,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.22859992384910582,
|
|
"num_tokens": 43194285.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.057315444946289,
|
|
"epoch": 1.8421679571173317,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004670685627672792,
|
|
"loss": 4.6908,
|
|
"mean_token_accuracy": 0.21965562254190446,
|
|
"num_tokens": 43209741.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.008931970596313,
|
|
"epoch": 1.8427635497319832,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046704636382366633,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.22564248144626617,
|
|
"num_tokens": 43223183.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.086136293411255,
|
|
"epoch": 1.843359142346635,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004670241579916627,
|
|
"loss": 4.6384,
|
|
"mean_token_accuracy": 0.228272445499897,
|
|
"num_tokens": 43236767.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.042649126052856,
|
|
"epoch": 1.8439547349612866,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046700194527206476,
|
|
"loss": 4.6543,
|
|
"mean_token_accuracy": 0.2274438887834549,
|
|
"num_tokens": 43250288.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.031025552749634,
|
|
"epoch": 1.844550327575938,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046697972566566917,
|
|
"loss": 4.7187,
|
|
"mean_token_accuracy": 0.21476932168006896,
|
|
"num_tokens": 43264137.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.041021823883057,
|
|
"epoch": 1.8451459201905895,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046695749917327297,
|
|
"loss": 4.6257,
|
|
"mean_token_accuracy": 0.22960401624441146,
|
|
"num_tokens": 43278662.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.112893533706665,
|
|
"epoch": 1.8457415128052412,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046693526579567337,
|
|
"loss": 4.7141,
|
|
"mean_token_accuracy": 0.2211147129535675,
|
|
"num_tokens": 43293818.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.057319593429566,
|
|
"epoch": 1.846337105419893,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046691302553366785,
|
|
"loss": 4.6916,
|
|
"mean_token_accuracy": 0.22477119714021682,
|
|
"num_tokens": 43307333.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.186435222625732,
|
|
"epoch": 1.8469326980345444,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004668907783880542,
|
|
"loss": 4.8194,
|
|
"mean_token_accuracy": 0.21766295582056044,
|
|
"num_tokens": 43321440.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.061244344711303,
|
|
"epoch": 1.8475282906491959,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00046686852435963016,
|
|
"loss": 4.5963,
|
|
"mean_token_accuracy": 0.22896338850259781,
|
|
"num_tokens": 43335918.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.075038862228394,
|
|
"epoch": 1.8481238832638476,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004668462634491943,
|
|
"loss": 4.6897,
|
|
"mean_token_accuracy": 0.21752977818250657,
|
|
"num_tokens": 43351816.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.037514877319336,
|
|
"epoch": 1.848719475878499,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004668239956575448,
|
|
"loss": 4.6168,
|
|
"mean_token_accuracy": 0.22946168333292008,
|
|
"num_tokens": 43365693.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.0803789615631105,
|
|
"epoch": 1.8493150684931505,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.00046680172098548044,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.22300214767456056,
|
|
"num_tokens": 43380780.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.099450302124024,
|
|
"epoch": 1.8499106611078022,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046677943943380023,
|
|
"loss": 4.7205,
|
|
"mean_token_accuracy": 0.2295170471072197,
|
|
"num_tokens": 43394625.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.0417684555053714,
|
|
"epoch": 1.850506253722454,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004667571510033034,
|
|
"loss": 4.6788,
|
|
"mean_token_accuracy": 0.22642443776130677,
|
|
"num_tokens": 43407844.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.056759548187256,
|
|
"epoch": 1.8511018463371054,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004667348556947893,
|
|
"loss": 4.6088,
|
|
"mean_token_accuracy": 0.22790326923131943,
|
|
"num_tokens": 43420553.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.1055577278137205,
|
|
"epoch": 1.8516974389517569,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004667125535090577,
|
|
"loss": 4.6977,
|
|
"mean_token_accuracy": 0.23065914064645768,
|
|
"num_tokens": 43434333.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.18114857673645,
|
|
"epoch": 1.8522930315664086,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004666902444469084,
|
|
"loss": 4.8069,
|
|
"mean_token_accuracy": 0.21717001348733903,
|
|
"num_tokens": 43449504.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.066530704498291,
|
|
"epoch": 1.8528886241810603,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004666679285091418,
|
|
"loss": 4.6563,
|
|
"mean_token_accuracy": 0.22349935919046401,
|
|
"num_tokens": 43463875.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.0729820251464846,
|
|
"epoch": 1.8534842167957117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046664560569655825,
|
|
"loss": 4.6459,
|
|
"mean_token_accuracy": 0.22946286648511888,
|
|
"num_tokens": 43476051.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.119633340835572,
|
|
"epoch": 1.8540798094103632,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004666232760099583,
|
|
"loss": 4.7162,
|
|
"mean_token_accuracy": 0.21372703611850738,
|
|
"num_tokens": 43491117.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.062397623062134,
|
|
"epoch": 1.854675402025015,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046660093945014307,
|
|
"loss": 4.699,
|
|
"mean_token_accuracy": 0.2200190782546997,
|
|
"num_tokens": 43505312.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.0718484878540036,
|
|
"epoch": 1.8552709946396666,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046657859601791367,
|
|
"loss": 4.6107,
|
|
"mean_token_accuracy": 0.22948730885982513,
|
|
"num_tokens": 43521038.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.172955751419067,
|
|
"epoch": 1.855866587254318,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004665562457140715,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.2171638086438179,
|
|
"num_tokens": 43534204.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.026592254638672,
|
|
"epoch": 1.8564621798689696,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004665338885394183,
|
|
"loss": 4.6046,
|
|
"mean_token_accuracy": 0.2418590635061264,
|
|
"num_tokens": 43548346.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.047203207015992,
|
|
"epoch": 1.8570577724836212,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004665115244947559,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.22710949629545213,
|
|
"num_tokens": 43562796.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.083824634552002,
|
|
"epoch": 1.857653365098273,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004664891535808865,
|
|
"loss": 4.6571,
|
|
"mean_token_accuracy": 0.2220303386449814,
|
|
"num_tokens": 43576460.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.049974584579468,
|
|
"epoch": 1.8582489577129242,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046646677579861254,
|
|
"loss": 4.6394,
|
|
"mean_token_accuracy": 0.2265828236937523,
|
|
"num_tokens": 43591090.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.21042308807373,
|
|
"epoch": 1.858844550327576,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004664443911487366,
|
|
"loss": 4.7723,
|
|
"mean_token_accuracy": 0.21025258600711821,
|
|
"num_tokens": 43605190.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.11155333518982,
|
|
"epoch": 1.8594401429422276,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046642199963206155,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.2240433320403099,
|
|
"num_tokens": 43619432.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 4.979401445388794,
|
|
"epoch": 1.860035735556879,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046639960124939076,
|
|
"loss": 4.5354,
|
|
"mean_token_accuracy": 0.23411523550748825,
|
|
"num_tokens": 43631677.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.058555030822754,
|
|
"epoch": 1.8606313281715305,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046637719600152737,
|
|
"loss": 4.6197,
|
|
"mean_token_accuracy": 0.2298182874917984,
|
|
"num_tokens": 43646838.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.094174861907959,
|
|
"epoch": 1.8612269207861822,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004663547838892751,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.22529516667127608,
|
|
"num_tokens": 43660533.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.043539667129517,
|
|
"epoch": 1.861822513400834,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004663323649134379,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.21481929272413253,
|
|
"num_tokens": 43675232.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.138433122634888,
|
|
"epoch": 1.8624181060154854,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004663099390748199,
|
|
"loss": 4.6527,
|
|
"mean_token_accuracy": 0.22121678441762924,
|
|
"num_tokens": 43687189.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.0957365989685055,
|
|
"epoch": 1.8630136986301369,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046628750637422534,
|
|
"loss": 4.6984,
|
|
"mean_token_accuracy": 0.2220250815153122,
|
|
"num_tokens": 43700783.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.087554454803467,
|
|
"epoch": 1.8636092912447886,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000466265066812459,
|
|
"loss": 4.658,
|
|
"mean_token_accuracy": 0.2262882485985756,
|
|
"num_tokens": 43713110.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.058700656890869,
|
|
"epoch": 1.8642048838594403,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046624262039032566,
|
|
"loss": 4.6509,
|
|
"mean_token_accuracy": 0.23065108358860015,
|
|
"num_tokens": 43726163.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.144887256622314,
|
|
"epoch": 1.8648004764740918,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046622016710863053,
|
|
"loss": 4.7734,
|
|
"mean_token_accuracy": 0.21711737662553787,
|
|
"num_tokens": 43740571.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.147554636001587,
|
|
"epoch": 1.8653960690887432,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004661977069681789,
|
|
"loss": 4.6901,
|
|
"mean_token_accuracy": 0.22933114618062972,
|
|
"num_tokens": 43752930.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.046763181686401,
|
|
"epoch": 1.865991661703395,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004661752399697763,
|
|
"loss": 4.5813,
|
|
"mean_token_accuracy": 0.23438411951065063,
|
|
"num_tokens": 43765626.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.088607978820801,
|
|
"epoch": 1.8665872543180466,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046615276611422876,
|
|
"loss": 4.6949,
|
|
"mean_token_accuracy": 0.21928978711366653,
|
|
"num_tokens": 43779281.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.154713296890259,
|
|
"epoch": 1.8671828469326979,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046613028540234226,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.2255584254860878,
|
|
"num_tokens": 43792809.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.079297065734863,
|
|
"epoch": 1.8677784395473496,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004661077978349232,
|
|
"loss": 4.6687,
|
|
"mean_token_accuracy": 0.2254912108182907,
|
|
"num_tokens": 43806416.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.043526458740234,
|
|
"epoch": 1.8683740321620013,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004660853034127781,
|
|
"loss": 4.65,
|
|
"mean_token_accuracy": 0.2311052918434143,
|
|
"num_tokens": 43822068.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.098816013336181,
|
|
"epoch": 1.8689696247766527,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004660628021367139,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.22459686249494554,
|
|
"num_tokens": 43837166.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.069987440109253,
|
|
"epoch": 1.8695652173913042,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004660402940075377,
|
|
"loss": 4.6352,
|
|
"mean_token_accuracy": 0.22366237491369248,
|
|
"num_tokens": 43850432.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.0327009677886965,
|
|
"epoch": 1.870160810005956,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004660177790260567,
|
|
"loss": 4.6513,
|
|
"mean_token_accuracy": 0.22735928148031234,
|
|
"num_tokens": 43866508.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 4.991403245925904,
|
|
"epoch": 1.8707564026206076,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004659952571930785,
|
|
"loss": 4.5041,
|
|
"mean_token_accuracy": 0.24299030005931854,
|
|
"num_tokens": 43880188.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.115719842910766,
|
|
"epoch": 1.871351995235259,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046597272850941104,
|
|
"loss": 4.6996,
|
|
"mean_token_accuracy": 0.22547523379325868,
|
|
"num_tokens": 43892869.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.051752614974975,
|
|
"epoch": 1.8719475878499106,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046595019297586226,
|
|
"loss": 4.6539,
|
|
"mean_token_accuracy": 0.22971319705247878,
|
|
"num_tokens": 43905989.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.111358022689819,
|
|
"epoch": 1.8725431804645623,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004659276505932405,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.2148301601409912,
|
|
"num_tokens": 43919478.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.074608564376831,
|
|
"epoch": 1.873138773079214,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046590510136235435,
|
|
"loss": 4.5856,
|
|
"mean_token_accuracy": 0.23045262694358826,
|
|
"num_tokens": 43933724.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.102158927917481,
|
|
"epoch": 1.8737343656938654,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046588254528401264,
|
|
"loss": 4.6847,
|
|
"mean_token_accuracy": 0.22550387382507325,
|
|
"num_tokens": 43947770.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.054721260070801,
|
|
"epoch": 1.874329958308517,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00046585998235902437,
|
|
"loss": 4.6748,
|
|
"mean_token_accuracy": 0.22168690264225005,
|
|
"num_tokens": 43963126.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.1134344100952145,
|
|
"epoch": 1.8749255509231686,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046583741258819894,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.22231462150812148,
|
|
"num_tokens": 43975767.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.121735715866089,
|
|
"epoch": 1.8755211435378203,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004658148359723457,
|
|
"loss": 4.6239,
|
|
"mean_token_accuracy": 0.23226717859506607,
|
|
"num_tokens": 43987772.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.028067398071289,
|
|
"epoch": 1.8761167361524718,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004657922525122746,
|
|
"loss": 4.5865,
|
|
"mean_token_accuracy": 0.233673594892025,
|
|
"num_tokens": 44001441.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.10662841796875,
|
|
"epoch": 1.8767123287671232,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004657696622087955,
|
|
"loss": 4.6618,
|
|
"mean_token_accuracy": 0.21928305327892303,
|
|
"num_tokens": 44015503.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.088253211975098,
|
|
"epoch": 1.877307921381775,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004657470650627189,
|
|
"loss": 4.6465,
|
|
"mean_token_accuracy": 0.2272554486989975,
|
|
"num_tokens": 44031106.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.0838641166687015,
|
|
"epoch": 1.8779035139964264,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046572446107485515,
|
|
"loss": 4.6385,
|
|
"mean_token_accuracy": 0.23252159208059311,
|
|
"num_tokens": 44043449.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.040552425384521,
|
|
"epoch": 1.8784991066110779,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004657018502460152,
|
|
"loss": 4.6076,
|
|
"mean_token_accuracy": 0.2270626574754715,
|
|
"num_tokens": 44056475.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.091608572006225,
|
|
"epoch": 1.8790946992257296,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046567923257700983,
|
|
"loss": 4.669,
|
|
"mean_token_accuracy": 0.22641556113958358,
|
|
"num_tokens": 44070143.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.126645183563232,
|
|
"epoch": 1.8796902918403813,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004656566080686504,
|
|
"loss": 4.7158,
|
|
"mean_token_accuracy": 0.21917902082204818,
|
|
"num_tokens": 44084800.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.071900510787964,
|
|
"epoch": 1.8802858844550328,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004656339767217485,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.22529279738664626,
|
|
"num_tokens": 44098784.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.010284900665283,
|
|
"epoch": 1.8808814770696842,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046561133853711576,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.22805796414613724,
|
|
"num_tokens": 44111708.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.048554992675781,
|
|
"epoch": 1.881477069684336,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004655886935155643,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.23181355893611907,
|
|
"num_tokens": 44126219.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.081300449371338,
|
|
"epoch": 1.8820726622989876,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004655660416579062,
|
|
"loss": 4.6659,
|
|
"mean_token_accuracy": 0.22491847425699235,
|
|
"num_tokens": 44141723.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.029343509674073,
|
|
"epoch": 1.882668254913639,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000465543382964954,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.23132635653018951,
|
|
"num_tokens": 44155410.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.020584583282471,
|
|
"epoch": 1.8832638475282906,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046552071743752055,
|
|
"loss": 4.64,
|
|
"mean_token_accuracy": 0.22721545845270158,
|
|
"num_tokens": 44170626.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.046386241912842,
|
|
"epoch": 1.8838594401429423,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004654980450764186,
|
|
"loss": 4.6379,
|
|
"mean_token_accuracy": 0.22791404277086258,
|
|
"num_tokens": 44182342.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.009099531173706,
|
|
"epoch": 1.884455032757594,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046547536588246167,
|
|
"loss": 4.5159,
|
|
"mean_token_accuracy": 0.23386928737163543,
|
|
"num_tokens": 44195903.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.11922025680542,
|
|
"epoch": 1.8850506253722454,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046545267985646294,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.22089696377515794,
|
|
"num_tokens": 44210024.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.070305347442627,
|
|
"epoch": 1.885646217986897,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046542998699923625,
|
|
"loss": 4.6804,
|
|
"mean_token_accuracy": 0.22317606955766678,
|
|
"num_tokens": 44222847.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.018018817901611,
|
|
"epoch": 1.8862418106015486,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004654072873115956,
|
|
"loss": 4.5852,
|
|
"mean_token_accuracy": 0.2272934451699257,
|
|
"num_tokens": 44236547.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.10158486366272,
|
|
"epoch": 1.8868374032162,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046538458079435516,
|
|
"loss": 4.6596,
|
|
"mean_token_accuracy": 0.22498546689748763,
|
|
"num_tokens": 44250192.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.068787622451782,
|
|
"epoch": 1.8874329958308516,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004653618674483293,
|
|
"loss": 4.6214,
|
|
"mean_token_accuracy": 0.22657045871019363,
|
|
"num_tokens": 44264834.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.055758333206176,
|
|
"epoch": 1.8880285884455033,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046533914727433276,
|
|
"loss": 4.6145,
|
|
"mean_token_accuracy": 0.22515795677900313,
|
|
"num_tokens": 44280375.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.073367357254028,
|
|
"epoch": 1.888624181060155,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004653164202731804,
|
|
"loss": 4.5834,
|
|
"mean_token_accuracy": 0.24239900410175325,
|
|
"num_tokens": 44294670.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.036703157424927,
|
|
"epoch": 1.8892197736748064,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046529368644568765,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.22902009785175323,
|
|
"num_tokens": 44306709.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 4.960673809051514,
|
|
"epoch": 1.889815366289458,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004652709457926697,
|
|
"loss": 4.5842,
|
|
"mean_token_accuracy": 0.23209407329559326,
|
|
"num_tokens": 44320902.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.052673101425171,
|
|
"epoch": 1.8904109589041096,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046524819831494224,
|
|
"loss": 4.5817,
|
|
"mean_token_accuracy": 0.22633625268936158,
|
|
"num_tokens": 44334524.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.050085115432739,
|
|
"epoch": 1.8910065515187613,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004652254440133213,
|
|
"loss": 4.6115,
|
|
"mean_token_accuracy": 0.22788889110088348,
|
|
"num_tokens": 44349278.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.010201358795166,
|
|
"epoch": 1.8916021441334128,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004652026828886229,
|
|
"loss": 4.5899,
|
|
"mean_token_accuracy": 0.22770281434059142,
|
|
"num_tokens": 44364295.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.046708488464356,
|
|
"epoch": 1.8921977367480642,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004651799149416636,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.22936270833015443,
|
|
"num_tokens": 44376551.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.103025817871094,
|
|
"epoch": 1.892793329362716,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004651571401732599,
|
|
"loss": 4.6814,
|
|
"mean_token_accuracy": 0.22727414667606355,
|
|
"num_tokens": 44391378.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.124289464950562,
|
|
"epoch": 1.8933889219773676,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004651343585842287,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.22008326947689055,
|
|
"num_tokens": 44406164.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.080617952346802,
|
|
"epoch": 1.893984514592019,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004651115701753873,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.22742972075939177,
|
|
"num_tokens": 44420567.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.129200077056884,
|
|
"epoch": 1.8945801072066706,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046508877494755296,
|
|
"loss": 4.6974,
|
|
"mean_token_accuracy": 0.22233187556266784,
|
|
"num_tokens": 44434170.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.16191258430481,
|
|
"epoch": 1.8951756998213223,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046506597290154337,
|
|
"loss": 4.7256,
|
|
"mean_token_accuracy": 0.22030123174190522,
|
|
"num_tokens": 44448067.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.095756101608276,
|
|
"epoch": 1.8957712924359738,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046504316403817627,
|
|
"loss": 4.6527,
|
|
"mean_token_accuracy": 0.21975816190242767,
|
|
"num_tokens": 44462266.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.054777956008911,
|
|
"epoch": 1.8963668850506252,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004650203483582699,
|
|
"loss": 4.6768,
|
|
"mean_token_accuracy": 0.22406341284513473,
|
|
"num_tokens": 44476180.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.09316201210022,
|
|
"epoch": 1.896962477665277,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046499752586264264,
|
|
"loss": 4.7186,
|
|
"mean_token_accuracy": 0.2121872693300247,
|
|
"num_tokens": 44490682.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.105399894714355,
|
|
"epoch": 1.8975580702799286,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004649746965521129,
|
|
"loss": 4.6152,
|
|
"mean_token_accuracy": 0.22740958482027054,
|
|
"num_tokens": 44506128.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.106967163085938,
|
|
"epoch": 1.89815366289458,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004649518604274999,
|
|
"loss": 4.6632,
|
|
"mean_token_accuracy": 0.22460057437419892,
|
|
"num_tokens": 44520435.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.120270538330078,
|
|
"epoch": 1.8987492555092316,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004649290174896223,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.21743544787168503,
|
|
"num_tokens": 44533852.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.168941783905029,
|
|
"epoch": 1.8993448481238833,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004649061677392998,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.22065930515527726,
|
|
"num_tokens": 44548523.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.059612131118774,
|
|
"epoch": 1.899940440738535,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046488331117735176,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.23651450872421265,
|
|
"num_tokens": 44562411.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.10548586845398,
|
|
"epoch": 1.9005360333531864,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004648604478045981,
|
|
"loss": 4.7174,
|
|
"mean_token_accuracy": 0.22103039175271988,
|
|
"num_tokens": 44574831.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.04508490562439,
|
|
"epoch": 1.901131625967838,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.00046483757762185877,
|
|
"loss": 4.593,
|
|
"mean_token_accuracy": 0.22595378756523132,
|
|
"num_tokens": 44591353.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.095437479019165,
|
|
"epoch": 1.9017272185824896,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004648147006299543,
|
|
"loss": 4.6199,
|
|
"mean_token_accuracy": 0.2303212359547615,
|
|
"num_tokens": 44605498.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.069763851165772,
|
|
"epoch": 1.9023228111971413,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004647918168297051,
|
|
"loss": 4.6315,
|
|
"mean_token_accuracy": 0.2314986288547516,
|
|
"num_tokens": 44621042.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.086034345626831,
|
|
"epoch": 1.9029184038117928,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046476892622193206,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.2223871096968651,
|
|
"num_tokens": 44635819.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.1198585510253904,
|
|
"epoch": 1.9035139964264443,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004647460288074562,
|
|
"loss": 4.6822,
|
|
"mean_token_accuracy": 0.22024568617343904,
|
|
"num_tokens": 44649578.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.144062471389771,
|
|
"epoch": 1.904109589041096,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004647231245870987,
|
|
"loss": 4.6548,
|
|
"mean_token_accuracy": 0.22583383023738862,
|
|
"num_tokens": 44662788.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.058896160125732,
|
|
"epoch": 1.9047051816557474,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046470021356168116,
|
|
"loss": 4.7356,
|
|
"mean_token_accuracy": 0.21908967494964598,
|
|
"num_tokens": 44675976.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.109310674667358,
|
|
"epoch": 1.905300774270399,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046467729573202555,
|
|
"loss": 4.7005,
|
|
"mean_token_accuracy": 0.21811317056417465,
|
|
"num_tokens": 44690350.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.17639651298523,
|
|
"epoch": 1.9058963668850506,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046465437109895365,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.21541172713041307,
|
|
"num_tokens": 44703959.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.0907494068145756,
|
|
"epoch": 1.9064919594997023,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004646314396632878,
|
|
"loss": 4.6543,
|
|
"mean_token_accuracy": 0.2259025201201439,
|
|
"num_tokens": 44719925.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.0236168384552,
|
|
"epoch": 1.9070875521143538,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004646085014258506,
|
|
"loss": 4.648,
|
|
"mean_token_accuracy": 0.22498809695243835,
|
|
"num_tokens": 44735039.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.0288948059082035,
|
|
"epoch": 1.9076831447290052,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046458555638746464,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.22386348396539688,
|
|
"num_tokens": 44749194.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.100249814987182,
|
|
"epoch": 1.908278737343657,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046456260454895307,
|
|
"loss": 4.6717,
|
|
"mean_token_accuracy": 0.22505851238965988,
|
|
"num_tokens": 44762177.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.07866358757019,
|
|
"epoch": 1.9088743299583086,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046453964591113906,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.2236534148454666,
|
|
"num_tokens": 44776524.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.07014570236206,
|
|
"epoch": 1.90946992257296,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004645166804748462,
|
|
"loss": 4.5933,
|
|
"mean_token_accuracy": 0.22874058037996292,
|
|
"num_tokens": 44789657.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.055823612213135,
|
|
"epoch": 1.9100655151876116,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046449370824089807,
|
|
"loss": 4.6179,
|
|
"mean_token_accuracy": 0.2289431571960449,
|
|
"num_tokens": 44804121.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.032233953475952,
|
|
"epoch": 1.9106611078022633,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046447072921011875,
|
|
"loss": 4.6197,
|
|
"mean_token_accuracy": 0.23169029206037522,
|
|
"num_tokens": 44816181.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.075803518295288,
|
|
"epoch": 1.911256700416915,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046444774338333253,
|
|
"loss": 4.6668,
|
|
"mean_token_accuracy": 0.22787985652685167,
|
|
"num_tokens": 44828430.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.087020635604858,
|
|
"epoch": 1.9118522930315665,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004644247507613636,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.2253232404589653,
|
|
"num_tokens": 44842711.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.093190860748291,
|
|
"epoch": 1.912447885646218,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000464401751345037,
|
|
"loss": 4.6292,
|
|
"mean_token_accuracy": 0.23506798595190048,
|
|
"num_tokens": 44855890.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.036006879806519,
|
|
"epoch": 1.9130434782608696,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004643787451351774,
|
|
"loss": 4.7001,
|
|
"mean_token_accuracy": 0.22769124060869217,
|
|
"num_tokens": 44869982.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.043065595626831,
|
|
"epoch": 1.913639070875521,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004643557321326102,
|
|
"loss": 4.6494,
|
|
"mean_token_accuracy": 0.23268600404262543,
|
|
"num_tokens": 44882799.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.109873247146607,
|
|
"epoch": 1.9142346634901726,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004643327123381607,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.2246732920408249,
|
|
"num_tokens": 44898309.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 4.977136468887329,
|
|
"epoch": 1.9148302561048243,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004643096857526547,
|
|
"loss": 4.5037,
|
|
"mean_token_accuracy": 0.24544624090194703,
|
|
"num_tokens": 44909869.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.083748626708984,
|
|
"epoch": 1.915425848719476,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046428665237691806,
|
|
"loss": 4.7047,
|
|
"mean_token_accuracy": 0.21977930665016174,
|
|
"num_tokens": 44925134.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.049134826660156,
|
|
"epoch": 1.9160214413341274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000464263612211777,
|
|
"loss": 4.5693,
|
|
"mean_token_accuracy": 0.23174022138118744,
|
|
"num_tokens": 44938599.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.04080719947815,
|
|
"epoch": 1.916617033948779,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004642405652580578,
|
|
"loss": 4.5615,
|
|
"mean_token_accuracy": 0.23729632496833802,
|
|
"num_tokens": 44953313.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.077568483352661,
|
|
"epoch": 1.9172126265634306,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004642175115165873,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.21658745408058167,
|
|
"num_tokens": 44966850.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.0982434272766115,
|
|
"epoch": 1.9178082191780823,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046419445098819223,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.22684727162122725,
|
|
"num_tokens": 44979661.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.0454247951507565,
|
|
"epoch": 1.9184038117927338,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00046417138367369995,
|
|
"loss": 4.6525,
|
|
"mean_token_accuracy": 0.22973860502243043,
|
|
"num_tokens": 44994530.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.117128896713257,
|
|
"epoch": 1.9189994044073853,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046414830957393756,
|
|
"loss": 4.6354,
|
|
"mean_token_accuracy": 0.22753543853759767,
|
|
"num_tokens": 45007605.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.101123332977295,
|
|
"epoch": 1.919594997022037,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046412522868973297,
|
|
"loss": 4.6715,
|
|
"mean_token_accuracy": 0.22663708180189132,
|
|
"num_tokens": 45022057.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.077655982971192,
|
|
"epoch": 1.9201905896366886,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004641021410219138,
|
|
"loss": 4.6277,
|
|
"mean_token_accuracy": 0.22890898287296296,
|
|
"num_tokens": 45035430.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.012116765975952,
|
|
"epoch": 1.9207861822513401,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046407904657130833,
|
|
"loss": 4.5908,
|
|
"mean_token_accuracy": 0.2289596289396286,
|
|
"num_tokens": 45049741.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.050002527236939,
|
|
"epoch": 1.9213817748659916,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004640559453387449,
|
|
"loss": 4.5728,
|
|
"mean_token_accuracy": 0.23289928287267686,
|
|
"num_tokens": 45063430.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.034178829193115,
|
|
"epoch": 1.9219773674806433,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004640328373250521,
|
|
"loss": 4.637,
|
|
"mean_token_accuracy": 0.229897403717041,
|
|
"num_tokens": 45078367.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.069398593902588,
|
|
"epoch": 1.9225729600952948,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046400972253105884,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.22374327927827836,
|
|
"num_tokens": 45091908.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.048649692535401,
|
|
"epoch": 1.9231685527099462,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000463986600957594,
|
|
"loss": 4.6244,
|
|
"mean_token_accuracy": 0.22727618962526322,
|
|
"num_tokens": 45105557.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.143972110748291,
|
|
"epoch": 1.923764145324598,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046396347260548715,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.21927523314952851,
|
|
"num_tokens": 45118462.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.1005286693573,
|
|
"epoch": 1.9243597379392496,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004639403374755678,
|
|
"loss": 4.6403,
|
|
"mean_token_accuracy": 0.2313067451119423,
|
|
"num_tokens": 45131594.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.059807395935058,
|
|
"epoch": 1.9249553305539011,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004639171955686657,
|
|
"loss": 4.5432,
|
|
"mean_token_accuracy": 0.2390546679496765,
|
|
"num_tokens": 45144524.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.005846881866455,
|
|
"epoch": 1.9255509231685526,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004638940468856109,
|
|
"loss": 4.5848,
|
|
"mean_token_accuracy": 0.23743375837802888,
|
|
"num_tokens": 45159979.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.104305410385132,
|
|
"epoch": 1.9261465157832043,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046387089142723386,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.2281411424279213,
|
|
"num_tokens": 45174134.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.096845436096191,
|
|
"epoch": 1.926742108397856,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046384772919436497,
|
|
"loss": 4.6787,
|
|
"mean_token_accuracy": 0.23040724992752076,
|
|
"num_tokens": 45187648.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.124722242355347,
|
|
"epoch": 1.9273377010125075,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046382456018783513,
|
|
"loss": 4.6216,
|
|
"mean_token_accuracy": 0.22685131877660752,
|
|
"num_tokens": 45202000.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.10207896232605,
|
|
"epoch": 1.927933293627159,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004638013844084753,
|
|
"loss": 4.7394,
|
|
"mean_token_accuracy": 0.21833471953868866,
|
|
"num_tokens": 45218379.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.109726333618164,
|
|
"epoch": 1.9285288862418106,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004637782018571167,
|
|
"loss": 4.7285,
|
|
"mean_token_accuracy": 0.21321893483400345,
|
|
"num_tokens": 45233571.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.108045387268066,
|
|
"epoch": 1.9291244788564623,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004637550125345911,
|
|
"loss": 4.6103,
|
|
"mean_token_accuracy": 0.22551104426383972,
|
|
"num_tokens": 45247322.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.083254289627075,
|
|
"epoch": 1.9297200714711138,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046373181644173,
|
|
"loss": 4.6916,
|
|
"mean_token_accuracy": 0.23351074010133743,
|
|
"num_tokens": 45259496.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.039320182800293,
|
|
"epoch": 1.9303156640857653,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004637086135793655,
|
|
"loss": 4.6278,
|
|
"mean_token_accuracy": 0.22658121436834336,
|
|
"num_tokens": 45274661.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.100236988067627,
|
|
"epoch": 1.930911256700417,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004636854039483299,
|
|
"loss": 4.6476,
|
|
"mean_token_accuracy": 0.2233669266104698,
|
|
"num_tokens": 45289166.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.061280918121338,
|
|
"epoch": 1.9315068493150684,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046366218754945556,
|
|
"loss": 4.6637,
|
|
"mean_token_accuracy": 0.22434571534395217,
|
|
"num_tokens": 45302220.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.119090270996094,
|
|
"epoch": 1.93210244192972,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004636389643835754,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.22039810717105865,
|
|
"num_tokens": 45316299.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.034946775436401,
|
|
"epoch": 1.9326980345443716,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046361573445152224,
|
|
"loss": 4.5891,
|
|
"mean_token_accuracy": 0.2319201037287712,
|
|
"num_tokens": 45330176.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.124848651885986,
|
|
"epoch": 1.9332936271590233,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046359249775412934,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.22033510655164718,
|
|
"num_tokens": 45344243.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.0139929294586185,
|
|
"epoch": 1.9338892197736748,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004635692542922302,
|
|
"loss": 4.5829,
|
|
"mean_token_accuracy": 0.22703004032373428,
|
|
"num_tokens": 45360093.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.028004550933838,
|
|
"epoch": 1.9344848123883263,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046354600406665853,
|
|
"loss": 4.6142,
|
|
"mean_token_accuracy": 0.23039684891700746,
|
|
"num_tokens": 45373990.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.043817520141602,
|
|
"epoch": 1.935080405002978,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046352274707824823,
|
|
"loss": 4.5666,
|
|
"mean_token_accuracy": 0.23766089975833893,
|
|
"num_tokens": 45386842.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.119889593124389,
|
|
"epoch": 1.9356759976176297,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004634994833278334,
|
|
"loss": 4.7324,
|
|
"mean_token_accuracy": 0.2213699385523796,
|
|
"num_tokens": 45400629.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.037499475479126,
|
|
"epoch": 1.9362715902322811,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004634762128162487,
|
|
"loss": 4.6037,
|
|
"mean_token_accuracy": 0.2282119005918503,
|
|
"num_tokens": 45413228.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.058671712875366,
|
|
"epoch": 1.9368671828469326,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004634529355443287,
|
|
"loss": 4.6481,
|
|
"mean_token_accuracy": 0.2223133459687233,
|
|
"num_tokens": 45426773.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.139435720443726,
|
|
"epoch": 1.9374627754615843,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046342965151290836,
|
|
"loss": 4.6562,
|
|
"mean_token_accuracy": 0.22810433059930801,
|
|
"num_tokens": 45440241.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.117543029785156,
|
|
"epoch": 1.938058368076236,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046340636072282273,
|
|
"loss": 4.6889,
|
|
"mean_token_accuracy": 0.22416270077228545,
|
|
"num_tokens": 45453788.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 4.984877729415894,
|
|
"epoch": 1.9386539606908875,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004633830631749072,
|
|
"loss": 4.5799,
|
|
"mean_token_accuracy": 0.23137529492378234,
|
|
"num_tokens": 45468679.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.008860874176025,
|
|
"epoch": 1.939249553305539,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046335975886999754,
|
|
"loss": 4.5761,
|
|
"mean_token_accuracy": 0.23310661166906357,
|
|
"num_tokens": 45482821.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.040655183792114,
|
|
"epoch": 1.9398451459201906,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004633364478089296,
|
|
"loss": 4.56,
|
|
"mean_token_accuracy": 0.23544852286577225,
|
|
"num_tokens": 45495936.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.028565073013306,
|
|
"epoch": 1.9404407385348421,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004633131299925395,
|
|
"loss": 4.653,
|
|
"mean_token_accuracy": 0.2256349429488182,
|
|
"num_tokens": 45510839.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.061375904083252,
|
|
"epoch": 1.9410363311494936,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004632898054216636,
|
|
"loss": 4.6099,
|
|
"mean_token_accuracy": 0.23176367282867433,
|
|
"num_tokens": 45523901.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.057660341262817,
|
|
"epoch": 1.9416319237641453,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046326647409713844,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.22747770100831985,
|
|
"num_tokens": 45538796.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.00176773071289,
|
|
"epoch": 1.942227516378797,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046324313601980106,
|
|
"loss": 4.4968,
|
|
"mean_token_accuracy": 0.23970059752464296,
|
|
"num_tokens": 45551641.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.005001831054687,
|
|
"epoch": 1.9428231089934485,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004632197911904884,
|
|
"loss": 4.5692,
|
|
"mean_token_accuracy": 0.23496777713298797,
|
|
"num_tokens": 45566275.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.123357152938842,
|
|
"epoch": 1.9434187016081,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00046319643961003785,
|
|
"loss": 4.7328,
|
|
"mean_token_accuracy": 0.23058443665504455,
|
|
"num_tokens": 45581035.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.1042563915252686,
|
|
"epoch": 1.9440142942227516,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00046317308127928706,
|
|
"loss": 4.6536,
|
|
"mean_token_accuracy": 0.2301807075738907,
|
|
"num_tokens": 45593791.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.05157961845398,
|
|
"epoch": 1.9446098868374033,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004631497161990738,
|
|
"loss": 4.6539,
|
|
"mean_token_accuracy": 0.2380486935377121,
|
|
"num_tokens": 45607840.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.062038326263428,
|
|
"epoch": 1.9452054794520548,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004631263443702361,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.2312809184193611,
|
|
"num_tokens": 45623360.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.103239297866821,
|
|
"epoch": 1.9458010720667063,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046310296579361225,
|
|
"loss": 4.6711,
|
|
"mean_token_accuracy": 0.21699499785900117,
|
|
"num_tokens": 45635794.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.062123107910156,
|
|
"epoch": 1.946396664681358,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004630795804700409,
|
|
"loss": 4.6598,
|
|
"mean_token_accuracy": 0.2218403086066246,
|
|
"num_tokens": 45650348.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.095920085906982,
|
|
"epoch": 1.9469922572960097,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004630561884003608,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.2236633002758026,
|
|
"num_tokens": 45665295.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 4.976531076431274,
|
|
"epoch": 1.9475878499106611,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000463032789585411,
|
|
"loss": 4.5882,
|
|
"mean_token_accuracy": 0.2299206957221031,
|
|
"num_tokens": 45681510.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.065512752532959,
|
|
"epoch": 1.9481834425253126,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004630093840260307,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.22390858232975006,
|
|
"num_tokens": 45696459.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.07672643661499,
|
|
"epoch": 1.9487790351399643,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046298597172305956,
|
|
"loss": 4.6438,
|
|
"mean_token_accuracy": 0.23227883875370026,
|
|
"num_tokens": 45709989.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.0516242504119875,
|
|
"epoch": 1.949374627754616,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004629625526773372,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.23085530251264572,
|
|
"num_tokens": 45723090.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.041744947433472,
|
|
"epoch": 1.9499702203692673,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004629391268897037,
|
|
"loss": 4.5898,
|
|
"mean_token_accuracy": 0.23338296711444856,
|
|
"num_tokens": 45736406.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 4.929829502105713,
|
|
"epoch": 1.950565812983919,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004629156943609993,
|
|
"loss": 4.5555,
|
|
"mean_token_accuracy": 0.2361198127269745,
|
|
"num_tokens": 45749730.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.034812593460083,
|
|
"epoch": 1.9511614055985707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046289225509206445,
|
|
"loss": 4.5982,
|
|
"mean_token_accuracy": 0.2335621565580368,
|
|
"num_tokens": 45762124.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.069738960266113,
|
|
"epoch": 1.9517569982132221,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004628688090837399,
|
|
"loss": 4.58,
|
|
"mean_token_accuracy": 0.23284066766500472,
|
|
"num_tokens": 45777749.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.082984495162964,
|
|
"epoch": 1.9523525908278736,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004628453563368666,
|
|
"loss": 4.6451,
|
|
"mean_token_accuracy": 0.2249053731560707,
|
|
"num_tokens": 45792944.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.129673957824707,
|
|
"epoch": 1.9529481834425253,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004628218968522859,
|
|
"loss": 4.7204,
|
|
"mean_token_accuracy": 0.22072557359933853,
|
|
"num_tokens": 45807909.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.054094648361206,
|
|
"epoch": 1.953543776057177,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004627984306308391,
|
|
"loss": 4.6825,
|
|
"mean_token_accuracy": 0.22719351798295975,
|
|
"num_tokens": 45819735.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.0592974662780765,
|
|
"epoch": 1.9541393686718285,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046277495767336785,
|
|
"loss": 4.5604,
|
|
"mean_token_accuracy": 0.226110976934433,
|
|
"num_tokens": 45833552.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 4.970073795318603,
|
|
"epoch": 1.95473496128648,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004627514779807142,
|
|
"loss": 4.5192,
|
|
"mean_token_accuracy": 0.2367810294032097,
|
|
"num_tokens": 45845984.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.066500282287597,
|
|
"epoch": 1.9553305539011316,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004627279915537204,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.22466661483049394,
|
|
"num_tokens": 45859035.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.132785081863403,
|
|
"epoch": 1.9559261465157833,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00046270449839322863,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.22131331115961075,
|
|
"num_tokens": 45872507.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.077828741073608,
|
|
"epoch": 1.9565217391304348,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046268099850008175,
|
|
"loss": 4.6237,
|
|
"mean_token_accuracy": 0.2298969104886055,
|
|
"num_tokens": 45884352.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.149636077880859,
|
|
"epoch": 1.9571173317450863,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004626574918751226,
|
|
"loss": 4.6818,
|
|
"mean_token_accuracy": 0.23329648226499558,
|
|
"num_tokens": 45897390.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.045100212097168,
|
|
"epoch": 1.957712924359738,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004626339785191944,
|
|
"loss": 4.6385,
|
|
"mean_token_accuracy": 0.22265289425849916,
|
|
"num_tokens": 45911371.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.058071708679199,
|
|
"epoch": 1.9583085169743897,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004626104584331404,
|
|
"loss": 4.6861,
|
|
"mean_token_accuracy": 0.22547050565481186,
|
|
"num_tokens": 45924228.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.103696203231811,
|
|
"epoch": 1.958904109589041,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004625869316178043,
|
|
"loss": 4.7102,
|
|
"mean_token_accuracy": 0.21950169503688813,
|
|
"num_tokens": 45938951.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.091867971420288,
|
|
"epoch": 1.9594997022036926,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046256339807403,
|
|
"loss": 4.6157,
|
|
"mean_token_accuracy": 0.22806516289710999,
|
|
"num_tokens": 45953344.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.049438428878784,
|
|
"epoch": 1.9600952948183443,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004625398578026615,
|
|
"loss": 4.6177,
|
|
"mean_token_accuracy": 0.22659689337015151,
|
|
"num_tokens": 45968007.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.0499327182769775,
|
|
"epoch": 1.9606908874329958,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046251631080454324,
|
|
"loss": 4.6556,
|
|
"mean_token_accuracy": 0.22705909609794617,
|
|
"num_tokens": 45981016.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.11383204460144,
|
|
"epoch": 1.9612864800476473,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004624927570805198,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.21914307475090028,
|
|
"num_tokens": 45995711.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.146003723144531,
|
|
"epoch": 1.961882072662299,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046246919663143603,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.22719553112983704,
|
|
"num_tokens": 46010430.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.107041645050049,
|
|
"epoch": 1.9624776652769507,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000462445629458137,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.2190193608403206,
|
|
"num_tokens": 46026069.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.099158477783203,
|
|
"epoch": 1.9630732578916021,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046242205556146795,
|
|
"loss": 4.6246,
|
|
"mean_token_accuracy": 0.22230280041694642,
|
|
"num_tokens": 46039988.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 4.97959713935852,
|
|
"epoch": 1.9636688505062536,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004623984749422745,
|
|
"loss": 4.525,
|
|
"mean_token_accuracy": 0.2332230180501938,
|
|
"num_tokens": 46052854.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.022222185134888,
|
|
"epoch": 1.9642644431209053,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004623748876014025,
|
|
"loss": 4.5898,
|
|
"mean_token_accuracy": 0.2358792319893837,
|
|
"num_tokens": 46066199.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.072830629348755,
|
|
"epoch": 1.964860035735557,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004623512935396979,
|
|
"loss": 4.6197,
|
|
"mean_token_accuracy": 0.23002227693796157,
|
|
"num_tokens": 46079817.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.0473285675048825,
|
|
"epoch": 1.9654556283502085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000462327692758007,
|
|
"loss": 4.6486,
|
|
"mean_token_accuracy": 0.23112584203481673,
|
|
"num_tokens": 46096088.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.084996700286865,
|
|
"epoch": 1.96605122096486,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004623040852571764,
|
|
"loss": 4.7072,
|
|
"mean_token_accuracy": 0.22012656033039094,
|
|
"num_tokens": 46110493.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.026456069946289,
|
|
"epoch": 1.9666468135795117,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046228047103805277,
|
|
"loss": 4.595,
|
|
"mean_token_accuracy": 0.23132424503564836,
|
|
"num_tokens": 46123671.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.103517723083496,
|
|
"epoch": 1.9672424061941634,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004622568501014831,
|
|
"loss": 4.6688,
|
|
"mean_token_accuracy": 0.22473679333925248,
|
|
"num_tokens": 46138491.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.0676380634307865,
|
|
"epoch": 1.9678379988088148,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046223322244831475,
|
|
"loss": 4.6134,
|
|
"mean_token_accuracy": 0.23020377159118652,
|
|
"num_tokens": 46151391.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.014071130752564,
|
|
"epoch": 1.9684335914234663,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000462209588079395,
|
|
"loss": 4.5856,
|
|
"mean_token_accuracy": 0.23531708717346192,
|
|
"num_tokens": 46165061.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.144772291183472,
|
|
"epoch": 1.969029184038118,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004621859469955718,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.22761491388082505,
|
|
"num_tokens": 46179753.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 4.971538734436035,
|
|
"epoch": 1.9696247766527695,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00046216229919769305,
|
|
"loss": 4.5289,
|
|
"mean_token_accuracy": 0.2427573546767235,
|
|
"num_tokens": 46194928.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.040869092941284,
|
|
"epoch": 1.970220369267421,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000462138644686607,
|
|
"loss": 4.5736,
|
|
"mean_token_accuracy": 0.233428755402565,
|
|
"num_tokens": 46208380.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.076733493804932,
|
|
"epoch": 1.9708159618820726,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046211498346316194,
|
|
"loss": 4.6475,
|
|
"mean_token_accuracy": 0.22926898449659347,
|
|
"num_tokens": 46222224.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.069233751296997,
|
|
"epoch": 1.9714115544967243,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004620913155282066,
|
|
"loss": 4.6216,
|
|
"mean_token_accuracy": 0.23378496021032333,
|
|
"num_tokens": 46234198.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.032105875015259,
|
|
"epoch": 1.9720071471113758,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00046206764088259003,
|
|
"loss": 4.6766,
|
|
"mean_token_accuracy": 0.22238166779279708,
|
|
"num_tokens": 46252100.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.130256128311157,
|
|
"epoch": 1.9726027397260273,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004620439595271613,
|
|
"loss": 4.7022,
|
|
"mean_token_accuracy": 0.2204693928360939,
|
|
"num_tokens": 46267789.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.06022081375122,
|
|
"epoch": 1.973198332340679,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004620202714627699,
|
|
"loss": 4.606,
|
|
"mean_token_accuracy": 0.2288425326347351,
|
|
"num_tokens": 46280966.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.150487470626831,
|
|
"epoch": 1.9737939249553307,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004619965766902654,
|
|
"loss": 4.743,
|
|
"mean_token_accuracy": 0.22318739593029022,
|
|
"num_tokens": 46295252.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.084901237487793,
|
|
"epoch": 1.9743895175699822,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046197287521049777,
|
|
"loss": 4.6992,
|
|
"mean_token_accuracy": 0.22678439915180207,
|
|
"num_tokens": 46310567.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.076849269866943,
|
|
"epoch": 1.9749851101846336,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004619491670243171,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.22888846546411515,
|
|
"num_tokens": 46324294.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.196983718872071,
|
|
"epoch": 1.9755807027992853,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00046192545213257375,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.21859004497528076,
|
|
"num_tokens": 46338259.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 4.9924232006073,
|
|
"epoch": 1.976176295413937,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004619017305361184,
|
|
"loss": 4.5349,
|
|
"mean_token_accuracy": 0.24065904915332795,
|
|
"num_tokens": 46350719.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.049792718887329,
|
|
"epoch": 1.9767718880285885,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004618780022358018,
|
|
"loss": 4.6466,
|
|
"mean_token_accuracy": 0.23283140659332274,
|
|
"num_tokens": 46365059.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.081716108322143,
|
|
"epoch": 1.97736748064324,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004618542672324751,
|
|
"loss": 4.6065,
|
|
"mean_token_accuracy": 0.2315231129527092,
|
|
"num_tokens": 46379567.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.083631229400635,
|
|
"epoch": 1.9779630732578917,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046183052552698975,
|
|
"loss": 4.6129,
|
|
"mean_token_accuracy": 0.23235762119293213,
|
|
"num_tokens": 46393578.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.088383054733276,
|
|
"epoch": 1.9785586658725431,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00046180677712019707,
|
|
"loss": 4.7228,
|
|
"mean_token_accuracy": 0.2205110877752304,
|
|
"num_tokens": 46409534.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.1761538028717045,
|
|
"epoch": 1.9791542584871946,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004617830220129491,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.21312197893857956,
|
|
"num_tokens": 46422022.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.0443648338317875,
|
|
"epoch": 1.9797498511018463,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004617592602060979,
|
|
"loss": 4.6144,
|
|
"mean_token_accuracy": 0.230525204539299,
|
|
"num_tokens": 46435061.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.102219486236573,
|
|
"epoch": 1.980345443716498,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046173549170049554,
|
|
"loss": 4.6366,
|
|
"mean_token_accuracy": 0.2327728047966957,
|
|
"num_tokens": 46448593.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.149979448318481,
|
|
"epoch": 1.9809410363311495,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004617117164969948,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.2156909316778183,
|
|
"num_tokens": 46463356.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.120338821411133,
|
|
"epoch": 1.981536628945801,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046168793459644837,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.218472483754158,
|
|
"num_tokens": 46475858.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.209310388565063,
|
|
"epoch": 1.9821322215604527,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004616641459997092,
|
|
"loss": 4.795,
|
|
"mean_token_accuracy": 0.21443324238061906,
|
|
"num_tokens": 46489482.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.07002010345459,
|
|
"epoch": 1.9827278141751044,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004616403507076306,
|
|
"loss": 4.6138,
|
|
"mean_token_accuracy": 0.22790686637163163,
|
|
"num_tokens": 46504203.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.053429746627808,
|
|
"epoch": 1.9833234067897558,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004616165487210661,
|
|
"loss": 4.5776,
|
|
"mean_token_accuracy": 0.2299404576420784,
|
|
"num_tokens": 46518373.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.000697326660156,
|
|
"epoch": 1.9839189994044073,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004615927400408695,
|
|
"loss": 4.607,
|
|
"mean_token_accuracy": 0.23077029436826707,
|
|
"num_tokens": 46531823.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 4.982889080047608,
|
|
"epoch": 1.984514592019059,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004615689246678946,
|
|
"loss": 4.5663,
|
|
"mean_token_accuracy": 0.2261618822813034,
|
|
"num_tokens": 46547138.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.082600545883179,
|
|
"epoch": 1.9851101846337107,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004615451026029957,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.23018018156290054,
|
|
"num_tokens": 46560732.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.040882873535156,
|
|
"epoch": 1.9857057772483622,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004615212738470273,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.22705053836107253,
|
|
"num_tokens": 46574186.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.008348083496093,
|
|
"epoch": 1.9863013698630136,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046149743840084406,
|
|
"loss": 4.5809,
|
|
"mean_token_accuracy": 0.23753033727407455,
|
|
"num_tokens": 46590389.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.13654670715332,
|
|
"epoch": 1.9868969624776653,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046147359626530103,
|
|
"loss": 4.6698,
|
|
"mean_token_accuracy": 0.2288126677274704,
|
|
"num_tokens": 46603010.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 4.987072896957398,
|
|
"epoch": 1.9874925550923168,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004614497474412532,
|
|
"loss": 4.5521,
|
|
"mean_token_accuracy": 0.23525268584489822,
|
|
"num_tokens": 46617840.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.071940851211548,
|
|
"epoch": 1.9880881477069683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004614258919295561,
|
|
"loss": 4.6294,
|
|
"mean_token_accuracy": 0.23271493911743163,
|
|
"num_tokens": 46631601.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.094979000091553,
|
|
"epoch": 1.98868374032162,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004614020297310654,
|
|
"loss": 4.6336,
|
|
"mean_token_accuracy": 0.2287750229239464,
|
|
"num_tokens": 46644565.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.098227596282959,
|
|
"epoch": 1.9892793329362717,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004613781608466369,
|
|
"loss": 4.6539,
|
|
"mean_token_accuracy": 0.22800484895706177,
|
|
"num_tokens": 46658200.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.16741943359375,
|
|
"epoch": 1.9898749255509232,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004613542852771269,
|
|
"loss": 4.7687,
|
|
"mean_token_accuracy": 0.22047432214021684,
|
|
"num_tokens": 46673480.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.083724403381348,
|
|
"epoch": 1.9904705181655746,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046133040302339155,
|
|
"loss": 4.6167,
|
|
"mean_token_accuracy": 0.2283388689160347,
|
|
"num_tokens": 46687451.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.125500440597534,
|
|
"epoch": 1.9910661107802263,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004613065140862877,
|
|
"loss": 4.7402,
|
|
"mean_token_accuracy": 0.21411267518997193,
|
|
"num_tokens": 46702821.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.215173578262329,
|
|
"epoch": 1.991661703394878,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000461282618466672,
|
|
"loss": 4.7432,
|
|
"mean_token_accuracy": 0.21827719509601592,
|
|
"num_tokens": 46718505.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.074452018737793,
|
|
"epoch": 1.9922572960095295,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046125871616540165,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.23375326693058013,
|
|
"num_tokens": 46733689.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.039164400100708,
|
|
"epoch": 1.992852888624181,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004612348071833341,
|
|
"loss": 4.5904,
|
|
"mean_token_accuracy": 0.2308359444141388,
|
|
"num_tokens": 46749255.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.140502452850342,
|
|
"epoch": 1.9934484812388327,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004612108915213268,
|
|
"loss": 4.7412,
|
|
"mean_token_accuracy": 0.2208992213010788,
|
|
"num_tokens": 46762916.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.1416823387146,
|
|
"epoch": 1.9940440738534844,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00046118696918023757,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.2227096974849701,
|
|
"num_tokens": 46777640.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.079245948791504,
|
|
"epoch": 1.9946396664681358,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00046116304016092445,
|
|
"loss": 4.6225,
|
|
"mean_token_accuracy": 0.22412045300006866,
|
|
"num_tokens": 46792077.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.05625433921814,
|
|
"epoch": 1.9952352590827873,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004611391044642458,
|
|
"loss": 4.64,
|
|
"mean_token_accuracy": 0.23041943609714508,
|
|
"num_tokens": 46807922.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.069281530380249,
|
|
"epoch": 1.995830851697439,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046111516209106004,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.2321515828371048,
|
|
"num_tokens": 46822514.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.1508160591125485,
|
|
"epoch": 1.9964264443120905,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046109121304222607,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.22291825860738754,
|
|
"num_tokens": 46835152.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.030114316940308,
|
|
"epoch": 1.997022036926742,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004610672573186029,
|
|
"loss": 4.6034,
|
|
"mean_token_accuracy": 0.2339877337217331,
|
|
"num_tokens": 46848297.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.078372049331665,
|
|
"epoch": 1.9976176295413937,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00046104329492104967,
|
|
"loss": 4.6446,
|
|
"mean_token_accuracy": 0.22905392199754715,
|
|
"num_tokens": 46860651.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.050597429275513,
|
|
"epoch": 1.9982132221560454,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046101932585042597,
|
|
"loss": 4.6011,
|
|
"mean_token_accuracy": 0.2240794226527214,
|
|
"num_tokens": 46876456.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.095714473724366,
|
|
"epoch": 1.9988088147706968,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004609953501075915,
|
|
"loss": 4.6619,
|
|
"mean_token_accuracy": 0.22741691619157792,
|
|
"num_tokens": 46890883.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.093476963043213,
|
|
"epoch": 1.9994044073853483,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004609713676934062,
|
|
"loss": 4.7505,
|
|
"mean_token_accuracy": 0.21810384690761567,
|
|
"num_tokens": 46906179.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.141530132293701,
|
|
"epoch": 2.0,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004609473786087303,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.2123733252286911,
|
|
"num_tokens": 46922024.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.0529073715209964,
|
|
"epoch": 2.0005955926146517,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004609233828544243,
|
|
"loss": 4.5201,
|
|
"mean_token_accuracy": 0.23483363091945647,
|
|
"num_tokens": 46936943.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.138359260559082,
|
|
"epoch": 2.001191185229303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004608993804313489,
|
|
"loss": 4.6572,
|
|
"mean_token_accuracy": 0.22239042073488235,
|
|
"num_tokens": 46950048.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.05815486907959,
|
|
"epoch": 2.0017867778439546,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046087537134036484,
|
|
"loss": 4.4994,
|
|
"mean_token_accuracy": 0.238849937915802,
|
|
"num_tokens": 46963398.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.130130434036255,
|
|
"epoch": 2.0023823704586063,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046085135558233357,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.22365089058876036,
|
|
"num_tokens": 46976496.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.031624269485474,
|
|
"epoch": 2.002977963073258,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046082733315811625,
|
|
"loss": 4.5009,
|
|
"mean_token_accuracy": 0.23648834377527236,
|
|
"num_tokens": 46990688.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.104819869995117,
|
|
"epoch": 2.0035735556879093,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046080330406857465,
|
|
"loss": 4.5529,
|
|
"mean_token_accuracy": 0.2394546553492546,
|
|
"num_tokens": 47005028.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.126836919784546,
|
|
"epoch": 2.004169148302561,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00046077926831457073,
|
|
"loss": 4.5422,
|
|
"mean_token_accuracy": 0.2350806251168251,
|
|
"num_tokens": 47020503.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.002790451049805,
|
|
"epoch": 2.0047647409172127,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00046075522589696636,
|
|
"loss": 4.4674,
|
|
"mean_token_accuracy": 0.23446178883314134,
|
|
"num_tokens": 47035091.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.057918548583984,
|
|
"epoch": 2.0053603335318644,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00046073117681662414,
|
|
"loss": 4.5328,
|
|
"mean_token_accuracy": 0.23811173737049102,
|
|
"num_tokens": 47048193.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.08016529083252,
|
|
"epoch": 2.0059559261465156,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004607071210744066,
|
|
"loss": 4.445,
|
|
"mean_token_accuracy": 0.2382444679737091,
|
|
"num_tokens": 47061703.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.0549413681030275,
|
|
"epoch": 2.0065515187611673,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046068305867117657,
|
|
"loss": 4.613,
|
|
"mean_token_accuracy": 0.22375122010707854,
|
|
"num_tokens": 47074990.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.012023496627807,
|
|
"epoch": 2.007147111375819,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046065898960779704,
|
|
"loss": 4.5122,
|
|
"mean_token_accuracy": 0.24279254972934722,
|
|
"num_tokens": 47089686.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.0019701480865475,
|
|
"epoch": 2.0077427039904707,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00046063491388513144,
|
|
"loss": 4.4958,
|
|
"mean_token_accuracy": 0.24338088184595108,
|
|
"num_tokens": 47102011.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.074423789978027,
|
|
"epoch": 2.008338296605122,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004606108315040434,
|
|
"loss": 4.6047,
|
|
"mean_token_accuracy": 0.22626852244138718,
|
|
"num_tokens": 47115599.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.078626680374145,
|
|
"epoch": 2.0089338892197737,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046058674246539653,
|
|
"loss": 4.5653,
|
|
"mean_token_accuracy": 0.23921276926994323,
|
|
"num_tokens": 47128902.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 4.987219619750976,
|
|
"epoch": 2.0095294818344254,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004605626467700551,
|
|
"loss": 4.5217,
|
|
"mean_token_accuracy": 0.2347672015428543,
|
|
"num_tokens": 47144218.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.0639012336730955,
|
|
"epoch": 2.0101250744490766,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046053854441888305,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.2369910642504692,
|
|
"num_tokens": 47157710.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.094415283203125,
|
|
"epoch": 2.0107206670637283,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004605144354127451,
|
|
"loss": 4.6195,
|
|
"mean_token_accuracy": 0.22900074124336242,
|
|
"num_tokens": 47173073.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.015122699737549,
|
|
"epoch": 2.01131625967838,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000460490319752506,
|
|
"loss": 4.461,
|
|
"mean_token_accuracy": 0.24028982520103453,
|
|
"num_tokens": 47186303.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.085547304153442,
|
|
"epoch": 2.0119118522930317,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00046046619743903087,
|
|
"loss": 4.6151,
|
|
"mean_token_accuracy": 0.22160424590110778,
|
|
"num_tokens": 47199954.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.039252138137817,
|
|
"epoch": 2.012507444907683,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00046044206847318457,
|
|
"loss": 4.5345,
|
|
"mean_token_accuracy": 0.23864744007587432,
|
|
"num_tokens": 47214366.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.013772106170654,
|
|
"epoch": 2.0131030375223347,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004604179328558329,
|
|
"loss": 4.5255,
|
|
"mean_token_accuracy": 0.23868568390607833,
|
|
"num_tokens": 47229144.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.086824131011963,
|
|
"epoch": 2.0136986301369864,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004603937905878414,
|
|
"loss": 4.5725,
|
|
"mean_token_accuracy": 0.23679173439741136,
|
|
"num_tokens": 47244043.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.08000226020813,
|
|
"epoch": 2.014294222751638,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00046036964167007615,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.2339544489979744,
|
|
"num_tokens": 47256255.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.036416721343994,
|
|
"epoch": 2.0148898153662893,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00046034548610340316,
|
|
"loss": 4.5487,
|
|
"mean_token_accuracy": 0.23442045003175735,
|
|
"num_tokens": 47270379.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.0546801567077635,
|
|
"epoch": 2.015485407980941,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00046032132388868895,
|
|
"loss": 4.5702,
|
|
"mean_token_accuracy": 0.2254816010594368,
|
|
"num_tokens": 47285927.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.091352033615112,
|
|
"epoch": 2.0160810005955927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004602971550268002,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.23009366542100906,
|
|
"num_tokens": 47299791.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.100305414199829,
|
|
"epoch": 2.0166765932102444,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004602729795186038,
|
|
"loss": 4.5845,
|
|
"mean_token_accuracy": 0.23220238834619522,
|
|
"num_tokens": 47313388.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.060167074203491,
|
|
"epoch": 2.0172721858248956,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00046024879736496677,
|
|
"loss": 4.5531,
|
|
"mean_token_accuracy": 0.23419663012027742,
|
|
"num_tokens": 47325690.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.055860900878907,
|
|
"epoch": 2.0178677784395473,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00046022460856675663,
|
|
"loss": 4.5797,
|
|
"mean_token_accuracy": 0.23389909714460372,
|
|
"num_tokens": 47340137.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.093301105499267,
|
|
"epoch": 2.018463371054199,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004602004131248409,
|
|
"loss": 4.6286,
|
|
"mean_token_accuracy": 0.22657535672187806,
|
|
"num_tokens": 47354451.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.129325914382934,
|
|
"epoch": 2.0190589636688503,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004601762110400875,
|
|
"loss": 4.676,
|
|
"mean_token_accuracy": 0.21986384689807892,
|
|
"num_tokens": 47368621.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.115187788009644,
|
|
"epoch": 2.019654556283502,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00046015200231336453,
|
|
"loss": 4.552,
|
|
"mean_token_accuracy": 0.2329590529203415,
|
|
"num_tokens": 47383476.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.204034090042114,
|
|
"epoch": 2.0202501488981537,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004601277869455402,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.21799875050783157,
|
|
"num_tokens": 47398009.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.044721555709839,
|
|
"epoch": 2.0208457415128054,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00046010356493748325,
|
|
"loss": 4.5309,
|
|
"mean_token_accuracy": 0.2312389940023422,
|
|
"num_tokens": 47411898.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.025452518463135,
|
|
"epoch": 2.0214413341274566,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00046007933629006227,
|
|
"loss": 4.5512,
|
|
"mean_token_accuracy": 0.230832277238369,
|
|
"num_tokens": 47428020.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.076907444000244,
|
|
"epoch": 2.0220369267421083,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004600551010041464,
|
|
"loss": 4.6121,
|
|
"mean_token_accuracy": 0.22890362441539763,
|
|
"num_tokens": 47440316.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.105307769775391,
|
|
"epoch": 2.02263251935676,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046003085908060505,
|
|
"loss": 4.6231,
|
|
"mean_token_accuracy": 0.2238751769065857,
|
|
"num_tokens": 47455793.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.096549654006958,
|
|
"epoch": 2.0232281119714117,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00046000661052030765,
|
|
"loss": 4.6323,
|
|
"mean_token_accuracy": 0.23198020905256272,
|
|
"num_tokens": 47470149.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.04519739151001,
|
|
"epoch": 2.023823704586063,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004599823553241238,
|
|
"loss": 4.4714,
|
|
"mean_token_accuracy": 0.24207262694835663,
|
|
"num_tokens": 47481372.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.042618131637573,
|
|
"epoch": 2.0244192972007147,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004599580934929237,
|
|
"loss": 4.5692,
|
|
"mean_token_accuracy": 0.23741540610790252,
|
|
"num_tokens": 47494672.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.073964405059814,
|
|
"epoch": 2.0250148898153664,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004599338250275775,
|
|
"loss": 4.5719,
|
|
"mean_token_accuracy": 0.23117638528347015,
|
|
"num_tokens": 47510225.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.073203897476196,
|
|
"epoch": 2.025610482430018,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045990954992895566,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.22699231952428817,
|
|
"num_tokens": 47524969.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.009320163726807,
|
|
"epoch": 2.0262060750446693,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045988526819792897,
|
|
"loss": 4.4536,
|
|
"mean_token_accuracy": 0.23991093933582305,
|
|
"num_tokens": 47539013.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.10173225402832,
|
|
"epoch": 2.026801667659321,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004598609798353683,
|
|
"loss": 4.6703,
|
|
"mean_token_accuracy": 0.22563050240278243,
|
|
"num_tokens": 47553905.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 4.995487642288208,
|
|
"epoch": 2.0273972602739727,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004598366848421447,
|
|
"loss": 4.5235,
|
|
"mean_token_accuracy": 0.23513252437114715,
|
|
"num_tokens": 47569788.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 4.983822154998779,
|
|
"epoch": 2.027992852888624,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004598123832191299,
|
|
"loss": 4.5018,
|
|
"mean_token_accuracy": 0.23997486382722855,
|
|
"num_tokens": 47586553.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.1157914161682125,
|
|
"epoch": 2.0285884455032757,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004597880749671954,
|
|
"loss": 4.6299,
|
|
"mean_token_accuracy": 0.22331550270318984,
|
|
"num_tokens": 47602275.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.033107423782349,
|
|
"epoch": 2.0291840381179274,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045976376008721303,
|
|
"loss": 4.5481,
|
|
"mean_token_accuracy": 0.23381753265857697,
|
|
"num_tokens": 47615354.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.06568922996521,
|
|
"epoch": 2.029779630732579,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000459739438580055,
|
|
"loss": 4.6131,
|
|
"mean_token_accuracy": 0.22695790678262712,
|
|
"num_tokens": 47629619.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.0331946849823,
|
|
"epoch": 2.0303752233472303,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045971511044659374,
|
|
"loss": 4.6261,
|
|
"mean_token_accuracy": 0.2276727244257927,
|
|
"num_tokens": 47642923.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 4.959511852264404,
|
|
"epoch": 2.030970815961882,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004596907756877018,
|
|
"loss": 4.4332,
|
|
"mean_token_accuracy": 0.23862120658159255,
|
|
"num_tokens": 47656768.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.075307607650757,
|
|
"epoch": 2.0315664085765337,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045966643430425197,
|
|
"loss": 4.5835,
|
|
"mean_token_accuracy": 0.2314362496137619,
|
|
"num_tokens": 47673391.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.017787170410156,
|
|
"epoch": 2.0321620011911854,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004596420862971174,
|
|
"loss": 4.511,
|
|
"mean_token_accuracy": 0.23766788393259047,
|
|
"num_tokens": 47688986.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.083296251296997,
|
|
"epoch": 2.0327575938058366,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004596177316671714,
|
|
"loss": 4.5428,
|
|
"mean_token_accuracy": 0.23422352969646454,
|
|
"num_tokens": 47702761.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.066502618789673,
|
|
"epoch": 2.0333531864204883,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045959337041528753,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.222515244781971,
|
|
"num_tokens": 47716940.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.14029221534729,
|
|
"epoch": 2.03394877903514,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004595690025423396,
|
|
"loss": 4.6533,
|
|
"mean_token_accuracy": 0.22761996537446977,
|
|
"num_tokens": 47732587.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.122018241882325,
|
|
"epoch": 2.0345443716497917,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004595446280492017,
|
|
"loss": 4.6075,
|
|
"mean_token_accuracy": 0.22751201838254928,
|
|
"num_tokens": 47746536.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.032704830169678,
|
|
"epoch": 2.035139964264443,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045952024693674795,
|
|
"loss": 4.5802,
|
|
"mean_token_accuracy": 0.23030130118131636,
|
|
"num_tokens": 47761095.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.086714601516723,
|
|
"epoch": 2.0357355568790947,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045949585920585304,
|
|
"loss": 4.6608,
|
|
"mean_token_accuracy": 0.22893784940242767,
|
|
"num_tokens": 47775841.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.054878091812133,
|
|
"epoch": 2.0363311494937464,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045947146485739155,
|
|
"loss": 4.5364,
|
|
"mean_token_accuracy": 0.23956526666879654,
|
|
"num_tokens": 47789385.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.134906435012818,
|
|
"epoch": 2.036926742108398,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045944706389223854,
|
|
"loss": 4.6175,
|
|
"mean_token_accuracy": 0.22698390632867813,
|
|
"num_tokens": 47803207.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.048177862167359,
|
|
"epoch": 2.0375223347230493,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045942265631126935,
|
|
"loss": 4.5475,
|
|
"mean_token_accuracy": 0.23307146579027177,
|
|
"num_tokens": 47816706.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.066162157058716,
|
|
"epoch": 2.038117927337701,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045939824211535925,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.2294682964682579,
|
|
"num_tokens": 47831052.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.1032651424407955,
|
|
"epoch": 2.0387135199523527,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000459373821305384,
|
|
"loss": 4.5745,
|
|
"mean_token_accuracy": 0.23589357137680053,
|
|
"num_tokens": 47843563.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.0828042984008786,
|
|
"epoch": 2.039309112567004,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045934939388221966,
|
|
"loss": 4.567,
|
|
"mean_token_accuracy": 0.22589924037456513,
|
|
"num_tokens": 47856928.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.0382004737854,
|
|
"epoch": 2.0399047051816557,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045932495984674223,
|
|
"loss": 4.6219,
|
|
"mean_token_accuracy": 0.227127568423748,
|
|
"num_tokens": 47870240.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.074550485610962,
|
|
"epoch": 2.0405002977963074,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045930051919982815,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.21863386631011963,
|
|
"num_tokens": 47882640.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.089707517623902,
|
|
"epoch": 2.041095890410959,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004592760719423541,
|
|
"loss": 4.5932,
|
|
"mean_token_accuracy": 0.22700148820877075,
|
|
"num_tokens": 47896192.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.078296136856079,
|
|
"epoch": 2.0416914830256103,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000459251618075197,
|
|
"loss": 4.5735,
|
|
"mean_token_accuracy": 0.22835236340761184,
|
|
"num_tokens": 47911283.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.107473707199096,
|
|
"epoch": 2.042287075640262,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045922715759923394,
|
|
"loss": 4.5761,
|
|
"mean_token_accuracy": 0.22859821915626527,
|
|
"num_tokens": 47928171.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.05329442024231,
|
|
"epoch": 2.0428826682549137,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045920269051534225,
|
|
"loss": 4.55,
|
|
"mean_token_accuracy": 0.23260037750005721,
|
|
"num_tokens": 47943368.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.041169309616089,
|
|
"epoch": 2.0434782608695654,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045917821682439955,
|
|
"loss": 4.587,
|
|
"mean_token_accuracy": 0.23331649005413055,
|
|
"num_tokens": 47956729.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.074505138397217,
|
|
"epoch": 2.0440738534842167,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004591537365272837,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.23911492377519608,
|
|
"num_tokens": 47970324.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.0996849060058596,
|
|
"epoch": 2.0446694460988684,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045912924962487276,
|
|
"loss": 4.574,
|
|
"mean_token_accuracy": 0.2335047349333763,
|
|
"num_tokens": 47982218.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.071066951751709,
|
|
"epoch": 2.04526503871352,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045910475611804486,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.225531467795372,
|
|
"num_tokens": 47996193.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.107188272476196,
|
|
"epoch": 2.0458606313281713,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00045908025600767887,
|
|
"loss": 4.5793,
|
|
"mean_token_accuracy": 0.23049094825983046,
|
|
"num_tokens": 48010320.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.092112255096436,
|
|
"epoch": 2.046456223942823,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004590557492946533,
|
|
"loss": 4.5941,
|
|
"mean_token_accuracy": 0.22947379797697068,
|
|
"num_tokens": 48026207.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.039409160614014,
|
|
"epoch": 2.0470518165574747,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045903123597984725,
|
|
"loss": 4.4933,
|
|
"mean_token_accuracy": 0.24106006920337678,
|
|
"num_tokens": 48040102.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.078585767745972,
|
|
"epoch": 2.0476474091721264,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045900671606414003,
|
|
"loss": 4.6518,
|
|
"mean_token_accuracy": 0.22701595425605775,
|
|
"num_tokens": 48053488.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.094822597503662,
|
|
"epoch": 2.0482430017867777,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000458982189548411,
|
|
"loss": 4.6473,
|
|
"mean_token_accuracy": 0.23051494657993316,
|
|
"num_tokens": 48068061.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.1394062519073485,
|
|
"epoch": 2.0488385944014293,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004589576564335401,
|
|
"loss": 4.6192,
|
|
"mean_token_accuracy": 0.2325916990637779,
|
|
"num_tokens": 48080633.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.049937582015991,
|
|
"epoch": 2.049434187016081,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004589331167204071,
|
|
"loss": 4.5189,
|
|
"mean_token_accuracy": 0.24328821152448654,
|
|
"num_tokens": 48093567.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.016260099411011,
|
|
"epoch": 2.0500297796307327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004589085704098922,
|
|
"loss": 4.542,
|
|
"mean_token_accuracy": 0.23655907809734344,
|
|
"num_tokens": 48105859.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.0743170261383055,
|
|
"epoch": 2.050625372245384,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000458884017502876,
|
|
"loss": 4.6214,
|
|
"mean_token_accuracy": 0.22778882533311845,
|
|
"num_tokens": 48120950.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.049698305130005,
|
|
"epoch": 2.0512209648600357,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00045885945800023896,
|
|
"loss": 4.491,
|
|
"mean_token_accuracy": 0.236894129216671,
|
|
"num_tokens": 48136708.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 4.96685824394226,
|
|
"epoch": 2.0518165574746874,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045883489190286214,
|
|
"loss": 4.4821,
|
|
"mean_token_accuracy": 0.24405397921800615,
|
|
"num_tokens": 48150485.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 4.941489028930664,
|
|
"epoch": 2.052412150089339,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004588103192116267,
|
|
"loss": 4.4613,
|
|
"mean_token_accuracy": 0.23640287667512894,
|
|
"num_tokens": 48164349.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.054111385345459,
|
|
"epoch": 2.0530077427039903,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004587857399274139,
|
|
"loss": 4.5511,
|
|
"mean_token_accuracy": 0.23184149861335754,
|
|
"num_tokens": 48175436.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.0590733051300045,
|
|
"epoch": 2.053603335318642,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004587611540511055,
|
|
"loss": 4.5723,
|
|
"mean_token_accuracy": 0.23075493425130844,
|
|
"num_tokens": 48189731.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.097777938842773,
|
|
"epoch": 2.0541989279332937,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004587365615835832,
|
|
"loss": 4.572,
|
|
"mean_token_accuracy": 0.23162893056869507,
|
|
"num_tokens": 48202435.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.053265523910523,
|
|
"epoch": 2.0547945205479454,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004587119625257292,
|
|
"loss": 4.5815,
|
|
"mean_token_accuracy": 0.23262700140476228,
|
|
"num_tokens": 48213821.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.126945495605469,
|
|
"epoch": 2.0553901131625967,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045868735687842584,
|
|
"loss": 4.6515,
|
|
"mean_token_accuracy": 0.22301355749368668,
|
|
"num_tokens": 48227201.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.0945594787597654,
|
|
"epoch": 2.0559857057772484,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004586627446425556,
|
|
"loss": 4.5927,
|
|
"mean_token_accuracy": 0.23206903785467148,
|
|
"num_tokens": 48241888.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.086732387542725,
|
|
"epoch": 2.0565812983919,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004586381258190013,
|
|
"loss": 4.5311,
|
|
"mean_token_accuracy": 0.23339892625808717,
|
|
"num_tokens": 48256518.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.125735092163086,
|
|
"epoch": 2.0571768910065513,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004586135004086461,
|
|
"loss": 4.6185,
|
|
"mean_token_accuracy": 0.22965662628412248,
|
|
"num_tokens": 48270570.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 4.986038541793823,
|
|
"epoch": 2.057772483621203,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004585888684123731,
|
|
"loss": 4.4944,
|
|
"mean_token_accuracy": 0.2407351091504097,
|
|
"num_tokens": 48283977.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.1182457447052006,
|
|
"epoch": 2.0583680762358547,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004585642298310659,
|
|
"loss": 4.6119,
|
|
"mean_token_accuracy": 0.2229074388742447,
|
|
"num_tokens": 48298306.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.03633599281311,
|
|
"epoch": 2.0589636688505064,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004585395846656083,
|
|
"loss": 4.5789,
|
|
"mean_token_accuracy": 0.22784317582845687,
|
|
"num_tokens": 48312983.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.047849845886231,
|
|
"epoch": 2.0595592614651577,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004585149329168842,
|
|
"loss": 4.587,
|
|
"mean_token_accuracy": 0.2426915779709816,
|
|
"num_tokens": 48325877.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.0170440673828125,
|
|
"epoch": 2.0601548540798094,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045849027458577776,
|
|
"loss": 4.5428,
|
|
"mean_token_accuracy": 0.23710273057222367,
|
|
"num_tokens": 48340601.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.04347825050354,
|
|
"epoch": 2.060750446694461,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004584656096731735,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.22686161249876022,
|
|
"num_tokens": 48354315.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.057076406478882,
|
|
"epoch": 2.0613460393091128,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045844093817995615,
|
|
"loss": 4.6054,
|
|
"mean_token_accuracy": 0.2286385789513588,
|
|
"num_tokens": 48368107.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.100273895263672,
|
|
"epoch": 2.061941631923764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045841626010701065,
|
|
"loss": 4.5879,
|
|
"mean_token_accuracy": 0.2330087050795555,
|
|
"num_tokens": 48380892.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.065182065963745,
|
|
"epoch": 2.0625372245384157,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004583915754552221,
|
|
"loss": 4.5705,
|
|
"mean_token_accuracy": 0.23780856877565384,
|
|
"num_tokens": 48394222.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.10246844291687,
|
|
"epoch": 2.0631328171530674,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004583668842254759,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.22093602567911147,
|
|
"num_tokens": 48408816.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.1308787822723385,
|
|
"epoch": 2.0637284097677187,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004583421864186577,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.22748123109340668,
|
|
"num_tokens": 48422992.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 4.999481868743897,
|
|
"epoch": 2.0643240023823703,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045831748203565333,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.2268027901649475,
|
|
"num_tokens": 48436832.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.092475414276123,
|
|
"epoch": 2.064919594997022,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045829277107734895,
|
|
"loss": 4.6119,
|
|
"mean_token_accuracy": 0.23405147194862366,
|
|
"num_tokens": 48450406.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.078521060943603,
|
|
"epoch": 2.0655151876116737,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004582680535446309,
|
|
"loss": 4.5213,
|
|
"mean_token_accuracy": 0.2342005968093872,
|
|
"num_tokens": 48464665.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.049551057815552,
|
|
"epoch": 2.066110780226325,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004582433294383858,
|
|
"loss": 4.5793,
|
|
"mean_token_accuracy": 0.2319861203432083,
|
|
"num_tokens": 48478794.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.06715989112854,
|
|
"epoch": 2.0667063728409767,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00045821859875950035,
|
|
"loss": 4.6303,
|
|
"mean_token_accuracy": 0.2271825209259987,
|
|
"num_tokens": 48494371.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.027512836456299,
|
|
"epoch": 2.0673019654556284,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045819386150886167,
|
|
"loss": 4.4768,
|
|
"mean_token_accuracy": 0.24535641819238663,
|
|
"num_tokens": 48507362.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.034812021255493,
|
|
"epoch": 2.06789755807028,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000458169117687357,
|
|
"loss": 4.5764,
|
|
"mean_token_accuracy": 0.23054691404104233,
|
|
"num_tokens": 48522667.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.048539924621582,
|
|
"epoch": 2.0684931506849313,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004581443672958739,
|
|
"loss": 4.5975,
|
|
"mean_token_accuracy": 0.2322992905974388,
|
|
"num_tokens": 48537316.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.117557239532471,
|
|
"epoch": 2.069088743299583,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045811961033530014,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.23686113357543945,
|
|
"num_tokens": 48552012.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.089766216278076,
|
|
"epoch": 2.0696843359142347,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045809484680652376,
|
|
"loss": 4.5659,
|
|
"mean_token_accuracy": 0.2361498773097992,
|
|
"num_tokens": 48564919.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.060856723785401,
|
|
"epoch": 2.0702799285288864,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004580700767104328,
|
|
"loss": 4.5589,
|
|
"mean_token_accuracy": 0.23464168161153792,
|
|
"num_tokens": 48580149.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.1296240329742435,
|
|
"epoch": 2.0708755211435377,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045804530004791595,
|
|
"loss": 4.6637,
|
|
"mean_token_accuracy": 0.23232266008853913,
|
|
"num_tokens": 48593130.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.058204078674317,
|
|
"epoch": 2.0714711137581894,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004580205168198617,
|
|
"loss": 4.5327,
|
|
"mean_token_accuracy": 0.2404569536447525,
|
|
"num_tokens": 48607426.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 4.993661737442016,
|
|
"epoch": 2.072066706372841,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004579957270271592,
|
|
"loss": 4.5055,
|
|
"mean_token_accuracy": 0.24361638873815536,
|
|
"num_tokens": 48621195.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.075657224655151,
|
|
"epoch": 2.0726622989874928,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045797093067069734,
|
|
"loss": 4.5723,
|
|
"mean_token_accuracy": 0.23232936561107637,
|
|
"num_tokens": 48637311.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.03188190460205,
|
|
"epoch": 2.073257891602144,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045794612775136584,
|
|
"loss": 4.4938,
|
|
"mean_token_accuracy": 0.23661171197891234,
|
|
"num_tokens": 48650312.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.060662794113159,
|
|
"epoch": 2.0738534842167957,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004579213182700541,
|
|
"loss": 4.5929,
|
|
"mean_token_accuracy": 0.2251037836074829,
|
|
"num_tokens": 48663762.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.07426347732544,
|
|
"epoch": 2.0744490768314474,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004578965022276521,
|
|
"loss": 4.6695,
|
|
"mean_token_accuracy": 0.22399986833333968,
|
|
"num_tokens": 48678565.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.026019430160522,
|
|
"epoch": 2.0750446694460987,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004578716796250501,
|
|
"loss": 4.5357,
|
|
"mean_token_accuracy": 0.23727331161499024,
|
|
"num_tokens": 48692527.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.137022638320923,
|
|
"epoch": 2.0756402620607504,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045784685046313804,
|
|
"loss": 4.6969,
|
|
"mean_token_accuracy": 0.22345040887594222,
|
|
"num_tokens": 48707023.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.109988451004028,
|
|
"epoch": 2.076235854675402,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045782201474280684,
|
|
"loss": 4.6491,
|
|
"mean_token_accuracy": 0.22686385214328766,
|
|
"num_tokens": 48719796.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.0522754192352295,
|
|
"epoch": 2.0768314472900538,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045779717246494724,
|
|
"loss": 4.5371,
|
|
"mean_token_accuracy": 0.23686339408159257,
|
|
"num_tokens": 48732902.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.099559640884399,
|
|
"epoch": 2.077427039904705,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004577723236304503,
|
|
"loss": 4.5848,
|
|
"mean_token_accuracy": 0.2309410512447357,
|
|
"num_tokens": 48748891.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.09339075088501,
|
|
"epoch": 2.0780226325193567,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004577474682402072,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.22737406194210052,
|
|
"num_tokens": 48763008.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.140409517288208,
|
|
"epoch": 2.0786182251340084,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004577226062951096,
|
|
"loss": 4.6621,
|
|
"mean_token_accuracy": 0.2291030317544937,
|
|
"num_tokens": 48776999.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.115877246856689,
|
|
"epoch": 2.07921381774866,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004576977377960492,
|
|
"loss": 4.6635,
|
|
"mean_token_accuracy": 0.22120339572429656,
|
|
"num_tokens": 48790859.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.020076942443848,
|
|
"epoch": 2.0798094103633114,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004576728627439179,
|
|
"loss": 4.478,
|
|
"mean_token_accuracy": 0.2436722680926323,
|
|
"num_tokens": 48803438.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.033577299118042,
|
|
"epoch": 2.080405002977963,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004576479811396082,
|
|
"loss": 4.5718,
|
|
"mean_token_accuracy": 0.23027619421482087,
|
|
"num_tokens": 48821044.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.019600582122803,
|
|
"epoch": 2.0810005955926147,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004576230929840123,
|
|
"loss": 4.4978,
|
|
"mean_token_accuracy": 0.23183832168579102,
|
|
"num_tokens": 48834968.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.068585681915283,
|
|
"epoch": 2.0815961882072664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004575981982780229,
|
|
"loss": 4.5797,
|
|
"mean_token_accuracy": 0.22818371653556824,
|
|
"num_tokens": 48847857.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.055041122436523,
|
|
"epoch": 2.0821917808219177,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004575732970225331,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.24043502509593964,
|
|
"num_tokens": 48863459.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.051139974594117,
|
|
"epoch": 2.0827873734365694,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045754838921843597,
|
|
"loss": 4.5531,
|
|
"mean_token_accuracy": 0.2304827943444252,
|
|
"num_tokens": 48877281.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.052931880950927,
|
|
"epoch": 2.083382966051221,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004575234748666249,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.23764803111553193,
|
|
"num_tokens": 48891269.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.0300463199615475,
|
|
"epoch": 2.0839785586658723,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004574985539679936,
|
|
"loss": 4.5129,
|
|
"mean_token_accuracy": 0.2392883062362671,
|
|
"num_tokens": 48905319.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.040356969833374,
|
|
"epoch": 2.084574151280524,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045747362652343585,
|
|
"loss": 4.5947,
|
|
"mean_token_accuracy": 0.22595180422067643,
|
|
"num_tokens": 48920393.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.089717769622803,
|
|
"epoch": 2.0851697438951757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004574486925338458,
|
|
"loss": 4.6191,
|
|
"mean_token_accuracy": 0.2224609822034836,
|
|
"num_tokens": 48935249.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.047974872589111,
|
|
"epoch": 2.0857653365098274,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004574237520001178,
|
|
"loss": 4.4936,
|
|
"mean_token_accuracy": 0.23701461255550385,
|
|
"num_tokens": 48950039.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.072237491607666,
|
|
"epoch": 2.0863609291244787,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045739880492314645,
|
|
"loss": 4.5868,
|
|
"mean_token_accuracy": 0.23556814938783646,
|
|
"num_tokens": 48963517.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.181007337570191,
|
|
"epoch": 2.0869565217391304,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004573738513038265,
|
|
"loss": 4.6635,
|
|
"mean_token_accuracy": 0.2342011108994484,
|
|
"num_tokens": 48975014.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.068695783615112,
|
|
"epoch": 2.087552114353782,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000457348891143053,
|
|
"loss": 4.5972,
|
|
"mean_token_accuracy": 0.22890432476997374,
|
|
"num_tokens": 48989289.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.091715621948242,
|
|
"epoch": 2.0881477069684338,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004573239244417213,
|
|
"loss": 4.6312,
|
|
"mean_token_accuracy": 0.23037443310022354,
|
|
"num_tokens": 49002157.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.108976793289185,
|
|
"epoch": 2.088743299583085,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004572989512007268,
|
|
"loss": 4.583,
|
|
"mean_token_accuracy": 0.23340716809034348,
|
|
"num_tokens": 49015381.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.0643391609191895,
|
|
"epoch": 2.0893388921977367,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045727397142096543,
|
|
"loss": 4.5224,
|
|
"mean_token_accuracy": 0.2411584660410881,
|
|
"num_tokens": 49032492.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.09845609664917,
|
|
"epoch": 2.0899344848123884,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000457248985103333,
|
|
"loss": 4.6854,
|
|
"mean_token_accuracy": 0.22586144655942916,
|
|
"num_tokens": 49045259.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.093830871582031,
|
|
"epoch": 2.09053007742704,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004572239922487259,
|
|
"loss": 4.5304,
|
|
"mean_token_accuracy": 0.23290108889341354,
|
|
"num_tokens": 49059493.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.03593864440918,
|
|
"epoch": 2.0911256700416914,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00045719899285804027,
|
|
"loss": 4.5568,
|
|
"mean_token_accuracy": 0.2384294494986534,
|
|
"num_tokens": 49073731.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.069857740402222,
|
|
"epoch": 2.091721262656343,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045717398693217315,
|
|
"loss": 4.5362,
|
|
"mean_token_accuracy": 0.2302304685115814,
|
|
"num_tokens": 49088534.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.003640651702881,
|
|
"epoch": 2.0923168552709948,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045714897447202125,
|
|
"loss": 4.4868,
|
|
"mean_token_accuracy": 0.2337938889861107,
|
|
"num_tokens": 49102257.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.034655046463013,
|
|
"epoch": 2.092912447885646,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045712395547848185,
|
|
"loss": 4.5725,
|
|
"mean_token_accuracy": 0.23187680393457413,
|
|
"num_tokens": 49117186.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.061504697799682,
|
|
"epoch": 2.0935080405002977,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004570989299524523,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.22606121450662614,
|
|
"num_tokens": 49132402.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.141278314590454,
|
|
"epoch": 2.0941036331149494,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045707389789483016,
|
|
"loss": 4.5421,
|
|
"mean_token_accuracy": 0.2331027701497078,
|
|
"num_tokens": 49144891.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.020317935943604,
|
|
"epoch": 2.094699225729601,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004570488593065133,
|
|
"loss": 4.5137,
|
|
"mean_token_accuracy": 0.23855364322662354,
|
|
"num_tokens": 49158424.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.018871641159057,
|
|
"epoch": 2.0952948183442524,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004570238141883999,
|
|
"loss": 4.5759,
|
|
"mean_token_accuracy": 0.23990731239318847,
|
|
"num_tokens": 49172217.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.063541507720947,
|
|
"epoch": 2.095890410958904,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045699876254138823,
|
|
"loss": 4.5884,
|
|
"mean_token_accuracy": 0.23450950682163238,
|
|
"num_tokens": 49186164.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 4.996161365509034,
|
|
"epoch": 2.0964860035735557,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004569737043663768,
|
|
"loss": 4.5352,
|
|
"mean_token_accuracy": 0.2362589105963707,
|
|
"num_tokens": 49199880.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.1407664775848385,
|
|
"epoch": 2.0970815961882074,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004569486396642645,
|
|
"loss": 4.651,
|
|
"mean_token_accuracy": 0.2303270325064659,
|
|
"num_tokens": 49211813.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.123605632781983,
|
|
"epoch": 2.0976771888028587,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004569235684359504,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.23138294368982315,
|
|
"num_tokens": 49227780.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 4.9848902225494385,
|
|
"epoch": 2.0982727814175104,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004568984906823337,
|
|
"loss": 4.4848,
|
|
"mean_token_accuracy": 0.24204363077878951,
|
|
"num_tokens": 49241499.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.180425119400025,
|
|
"epoch": 2.098868374032162,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045687340640431374,
|
|
"loss": 4.6831,
|
|
"mean_token_accuracy": 0.227830970287323,
|
|
"num_tokens": 49254706.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.045681667327881,
|
|
"epoch": 2.099463966646814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004568483156027905,
|
|
"loss": 4.5374,
|
|
"mean_token_accuracy": 0.23475686758756636,
|
|
"num_tokens": 49268278.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.080250310897827,
|
|
"epoch": 2.100059559261465,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045682321827866383,
|
|
"loss": 4.6114,
|
|
"mean_token_accuracy": 0.235031920671463,
|
|
"num_tokens": 49282001.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.060113048553466,
|
|
"epoch": 2.1006551518761167,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000456798114432834,
|
|
"loss": 4.5594,
|
|
"mean_token_accuracy": 0.23171952068805696,
|
|
"num_tokens": 49294152.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 4.995019149780274,
|
|
"epoch": 2.1012507444907684,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004567730040662013,
|
|
"loss": 4.4448,
|
|
"mean_token_accuracy": 0.24083685725927353,
|
|
"num_tokens": 49309501.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.037392473220825,
|
|
"epoch": 2.1018463371054197,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004567478871796665,
|
|
"loss": 4.5261,
|
|
"mean_token_accuracy": 0.23095164448022842,
|
|
"num_tokens": 49325663.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.02610411643982,
|
|
"epoch": 2.1024419297200714,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045672276377413054,
|
|
"loss": 4.55,
|
|
"mean_token_accuracy": 0.23000458627939224,
|
|
"num_tokens": 49339976.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 4.987092733383179,
|
|
"epoch": 2.103037522334723,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004566976338504945,
|
|
"loss": 4.4947,
|
|
"mean_token_accuracy": 0.24282919019460678,
|
|
"num_tokens": 49353706.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.063581132888794,
|
|
"epoch": 2.1036331149493748,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004566724974096597,
|
|
"loss": 4.5604,
|
|
"mean_token_accuracy": 0.2301536202430725,
|
|
"num_tokens": 49366331.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.050300073623657,
|
|
"epoch": 2.104228707564026,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004566473544525279,
|
|
"loss": 4.5485,
|
|
"mean_token_accuracy": 0.2339072898030281,
|
|
"num_tokens": 49379870.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 4.990108346939087,
|
|
"epoch": 2.1048243001786777,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004566222049800008,
|
|
"loss": 4.5154,
|
|
"mean_token_accuracy": 0.23792072236537934,
|
|
"num_tokens": 49394294.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.064607763290406,
|
|
"epoch": 2.1054198927933294,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045659704899298045,
|
|
"loss": 4.5706,
|
|
"mean_token_accuracy": 0.22828245609998704,
|
|
"num_tokens": 49409546.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.075016117095947,
|
|
"epoch": 2.106015485407981,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004565718864923693,
|
|
"loss": 4.6041,
|
|
"mean_token_accuracy": 0.23024596720933915,
|
|
"num_tokens": 49424712.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.105943202972412,
|
|
"epoch": 2.1066110780226324,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004565467174790697,
|
|
"loss": 4.6697,
|
|
"mean_token_accuracy": 0.22970298081636428,
|
|
"num_tokens": 49438958.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.08026123046875,
|
|
"epoch": 2.107206670637284,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004565215419539846,
|
|
"loss": 4.5939,
|
|
"mean_token_accuracy": 0.2311571940779686,
|
|
"num_tokens": 49452643.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.034146785736084,
|
|
"epoch": 2.1078022632519358,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045649635991801686,
|
|
"loss": 4.4835,
|
|
"mean_token_accuracy": 0.24227486401796341,
|
|
"num_tokens": 49465133.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.088418483734131,
|
|
"epoch": 2.1083978558665875,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004564711713720698,
|
|
"loss": 4.6054,
|
|
"mean_token_accuracy": 0.22763876467943192,
|
|
"num_tokens": 49479230.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.019331598281861,
|
|
"epoch": 2.1089934484812387,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004564459763170469,
|
|
"loss": 4.5299,
|
|
"mean_token_accuracy": 0.23205972462892532,
|
|
"num_tokens": 49493461.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.059644603729248,
|
|
"epoch": 2.1095890410958904,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045642077475385186,
|
|
"loss": 4.6248,
|
|
"mean_token_accuracy": 0.2291144073009491,
|
|
"num_tokens": 49505919.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.095066356658935,
|
|
"epoch": 2.110184633710542,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045639556668338854,
|
|
"loss": 4.5607,
|
|
"mean_token_accuracy": 0.23450403660535812,
|
|
"num_tokens": 49520411.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 4.920881652832032,
|
|
"epoch": 2.1107802263251934,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045637035210656124,
|
|
"loss": 4.4163,
|
|
"mean_token_accuracy": 0.24978860467672348,
|
|
"num_tokens": 49533689.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.013450241088867,
|
|
"epoch": 2.111375818939845,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045634513102427426,
|
|
"loss": 4.5551,
|
|
"mean_token_accuracy": 0.23271492570638658,
|
|
"num_tokens": 49546938.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.058868551254273,
|
|
"epoch": 2.1119714115544967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004563199034374323,
|
|
"loss": 4.5562,
|
|
"mean_token_accuracy": 0.23301343321800233,
|
|
"num_tokens": 49561202.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.102551126480103,
|
|
"epoch": 2.1125670041691484,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004562946693469402,
|
|
"loss": 4.591,
|
|
"mean_token_accuracy": 0.23577438592910765,
|
|
"num_tokens": 49574704.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.076964712142944,
|
|
"epoch": 2.1131625967837997,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004562694287537031,
|
|
"loss": 4.5907,
|
|
"mean_token_accuracy": 0.23021039217710496,
|
|
"num_tokens": 49588764.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 4.97689847946167,
|
|
"epoch": 2.1137581893984514,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045624418165862626,
|
|
"loss": 4.5564,
|
|
"mean_token_accuracy": 0.2454288735985756,
|
|
"num_tokens": 49601830.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.080901861190796,
|
|
"epoch": 2.114353782013103,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004562189280626154,
|
|
"loss": 4.6013,
|
|
"mean_token_accuracy": 0.22946424782276154,
|
|
"num_tokens": 49616855.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.099197340011597,
|
|
"epoch": 2.114949374627755,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004561936679665761,
|
|
"loss": 4.6907,
|
|
"mean_token_accuracy": 0.2236390843987465,
|
|
"num_tokens": 49632013.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.092054033279419,
|
|
"epoch": 2.115544967242406,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004561684013714147,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.23236455470323564,
|
|
"num_tokens": 49645420.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.122833251953125,
|
|
"epoch": 2.1161405598570577,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004561431282780372,
|
|
"loss": 4.6366,
|
|
"mean_token_accuracy": 0.23114838749170302,
|
|
"num_tokens": 49660063.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.064624929428101,
|
|
"epoch": 2.1167361524717094,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045611784868735024,
|
|
"loss": 4.5263,
|
|
"mean_token_accuracy": 0.23746096044778825,
|
|
"num_tokens": 49674054.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.05062313079834,
|
|
"epoch": 2.117331745086361,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004560925626002605,
|
|
"loss": 4.5328,
|
|
"mean_token_accuracy": 0.23740915805101395,
|
|
"num_tokens": 49687603.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 4.989220094680786,
|
|
"epoch": 2.1179273377010124,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000456067270017675,
|
|
"loss": 4.5471,
|
|
"mean_token_accuracy": 0.2369333729147911,
|
|
"num_tokens": 49702559.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.063387441635132,
|
|
"epoch": 2.118522930315664,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045604197094050087,
|
|
"loss": 4.6106,
|
|
"mean_token_accuracy": 0.2359846442937851,
|
|
"num_tokens": 49717358.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.000358629226684,
|
|
"epoch": 2.1191185229303158,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004560166653696457,
|
|
"loss": 4.5319,
|
|
"mean_token_accuracy": 0.23114360719919205,
|
|
"num_tokens": 49731643.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.06860466003418,
|
|
"epoch": 2.1197141155449675,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000455991353306017,
|
|
"loss": 4.5756,
|
|
"mean_token_accuracy": 0.23120578974485398,
|
|
"num_tokens": 49744535.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.059130430221558,
|
|
"epoch": 2.1203097081596187,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004559660347505228,
|
|
"loss": 4.5874,
|
|
"mean_token_accuracy": 0.23057915419340133,
|
|
"num_tokens": 49758287.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.114139223098755,
|
|
"epoch": 2.1209053007742704,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000455940709704071,
|
|
"loss": 4.6433,
|
|
"mean_token_accuracy": 0.22673242241144181,
|
|
"num_tokens": 49773062.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.0162310123443605,
|
|
"epoch": 2.121500893388922,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045591537816757027,
|
|
"loss": 4.5845,
|
|
"mean_token_accuracy": 0.22947801947593688,
|
|
"num_tokens": 49786320.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 4.997435855865478,
|
|
"epoch": 2.1220964860035734,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045589004014192903,
|
|
"loss": 4.4682,
|
|
"mean_token_accuracy": 0.2420662134885788,
|
|
"num_tokens": 49799765.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.043676424026489,
|
|
"epoch": 2.122692078618225,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045586469562805624,
|
|
"loss": 4.5601,
|
|
"mean_token_accuracy": 0.23974284082651137,
|
|
"num_tokens": 49813382.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.087973403930664,
|
|
"epoch": 2.1232876712328768,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004558393446268608,
|
|
"loss": 4.5506,
|
|
"mean_token_accuracy": 0.23517700284719467,
|
|
"num_tokens": 49826000.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.063232946395874,
|
|
"epoch": 2.1238832638475285,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004558139871392521,
|
|
"loss": 4.6314,
|
|
"mean_token_accuracy": 0.2318678081035614,
|
|
"num_tokens": 49840725.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.072955751419068,
|
|
"epoch": 2.1244788564621797,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004557886231661396,
|
|
"loss": 4.5644,
|
|
"mean_token_accuracy": 0.2268071323633194,
|
|
"num_tokens": 49854400.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.099449920654297,
|
|
"epoch": 2.1250744490768314,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045576325270843326,
|
|
"loss": 4.5886,
|
|
"mean_token_accuracy": 0.22896184921264648,
|
|
"num_tokens": 49868724.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.056263494491577,
|
|
"epoch": 2.125670041691483,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004557378757670429,
|
|
"loss": 4.5954,
|
|
"mean_token_accuracy": 0.2285956248641014,
|
|
"num_tokens": 49883103.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.034786128997803,
|
|
"epoch": 2.126265634306135,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004557124923428788,
|
|
"loss": 4.539,
|
|
"mean_token_accuracy": 0.23648015260696412,
|
|
"num_tokens": 49896179.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.0493114471435545,
|
|
"epoch": 2.126861226920786,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004556871024368514,
|
|
"loss": 4.5679,
|
|
"mean_token_accuracy": 0.23465656638145446,
|
|
"num_tokens": 49911524.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.148996067047119,
|
|
"epoch": 2.1274568195354377,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045566170604987145,
|
|
"loss": 4.6442,
|
|
"mean_token_accuracy": 0.2279566526412964,
|
|
"num_tokens": 49925970.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.16656346321106,
|
|
"epoch": 2.1280524121500894,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004556363031828498,
|
|
"loss": 4.6339,
|
|
"mean_token_accuracy": 0.2286172866821289,
|
|
"num_tokens": 49940184.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.06922926902771,
|
|
"epoch": 2.1286480047647407,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045561089383669776,
|
|
"loss": 4.5967,
|
|
"mean_token_accuracy": 0.23340363502502443,
|
|
"num_tokens": 49953995.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.020604848861694,
|
|
"epoch": 2.1292435973793924,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004555854780123265,
|
|
"loss": 4.5671,
|
|
"mean_token_accuracy": 0.23321855664253235,
|
|
"num_tokens": 49967243.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.138209629058838,
|
|
"epoch": 2.129839189994044,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004555600557106477,
|
|
"loss": 4.6549,
|
|
"mean_token_accuracy": 0.23246657401323317,
|
|
"num_tokens": 49981431.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.163127470016479,
|
|
"epoch": 2.130434782608696,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004555346269325734,
|
|
"loss": 4.6596,
|
|
"mean_token_accuracy": 0.21815578490495682,
|
|
"num_tokens": 49994984.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.014172172546386,
|
|
"epoch": 2.131030375223347,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045550919167901553,
|
|
"loss": 4.5172,
|
|
"mean_token_accuracy": 0.2335176169872284,
|
|
"num_tokens": 50007028.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.001415681838989,
|
|
"epoch": 2.1316259678379987,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004554837499508864,
|
|
"loss": 4.4574,
|
|
"mean_token_accuracy": 0.24015415459871292,
|
|
"num_tokens": 50020302.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.048899364471436,
|
|
"epoch": 2.1322215604526504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004554583017490987,
|
|
"loss": 4.5454,
|
|
"mean_token_accuracy": 0.2350949913263321,
|
|
"num_tokens": 50033923.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.0849347591400145,
|
|
"epoch": 2.132817153067302,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045543284707456514,
|
|
"loss": 4.6298,
|
|
"mean_token_accuracy": 0.22718213498592377,
|
|
"num_tokens": 50047118.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.051455354690551,
|
|
"epoch": 2.1334127456819534,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004554073859281986,
|
|
"loss": 4.6301,
|
|
"mean_token_accuracy": 0.22977480590343474,
|
|
"num_tokens": 50061020.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.086539173126221,
|
|
"epoch": 2.134008338296605,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004553819183109125,
|
|
"loss": 4.5652,
|
|
"mean_token_accuracy": 0.23175314217805862,
|
|
"num_tokens": 50075226.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.063194608688354,
|
|
"epoch": 2.1346039309112568,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045535644422362026,
|
|
"loss": 4.6215,
|
|
"mean_token_accuracy": 0.23024062365293502,
|
|
"num_tokens": 50091552.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.0348135471344,
|
|
"epoch": 2.1351995235259085,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00045533096366723563,
|
|
"loss": 4.5422,
|
|
"mean_token_accuracy": 0.23243680149316787,
|
|
"num_tokens": 50105657.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.032689094543457,
|
|
"epoch": 2.1357951161405597,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004553054766426725,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.23663522601127623,
|
|
"num_tokens": 50121410.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.036223936080932,
|
|
"epoch": 2.1363907087552114,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045527998315084513,
|
|
"loss": 4.5967,
|
|
"mean_token_accuracy": 0.2369163900613785,
|
|
"num_tokens": 50135149.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.09993987083435,
|
|
"epoch": 2.136986301369863,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004552544831926679,
|
|
"loss": 4.5931,
|
|
"mean_token_accuracy": 0.23190954178571702,
|
|
"num_tokens": 50148342.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.055096387863159,
|
|
"epoch": 2.137581893984515,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00045522897676905535,
|
|
"loss": 4.5095,
|
|
"mean_token_accuracy": 0.23923056274652482,
|
|
"num_tokens": 50164010.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 4.999916028976441,
|
|
"epoch": 2.138177486599166,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004552034638809225,
|
|
"loss": 4.5508,
|
|
"mean_token_accuracy": 0.23477760702371597,
|
|
"num_tokens": 50178175.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 4.9986354351043705,
|
|
"epoch": 2.1387730792138178,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004551779445291843,
|
|
"loss": 4.4265,
|
|
"mean_token_accuracy": 0.23890797793865204,
|
|
"num_tokens": 50191411.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.138413906097412,
|
|
"epoch": 2.1393686718284695,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045515241871475634,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.22032149583101274,
|
|
"num_tokens": 50204029.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.037301349639892,
|
|
"epoch": 2.1399642644431207,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004551268864385539,
|
|
"loss": 4.5282,
|
|
"mean_token_accuracy": 0.23887151777744292,
|
|
"num_tokens": 50219742.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.059378290176392,
|
|
"epoch": 2.1405598570577724,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000455101347701493,
|
|
"loss": 4.5327,
|
|
"mean_token_accuracy": 0.23149173706769943,
|
|
"num_tokens": 50234470.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.0729796409606935,
|
|
"epoch": 2.141155449672424,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045507580250448955,
|
|
"loss": 4.5923,
|
|
"mean_token_accuracy": 0.22968601435422897,
|
|
"num_tokens": 50247814.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.0671838283538815,
|
|
"epoch": 2.141751042287076,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004550502508484598,
|
|
"loss": 4.5597,
|
|
"mean_token_accuracy": 0.23079947531223297,
|
|
"num_tokens": 50260656.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.078120279312134,
|
|
"epoch": 2.142346634901727,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004550246927343203,
|
|
"loss": 4.5862,
|
|
"mean_token_accuracy": 0.2336001217365265,
|
|
"num_tokens": 50276685.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.086450576782227,
|
|
"epoch": 2.1429422275163788,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004549991281629879,
|
|
"loss": 4.5318,
|
|
"mean_token_accuracy": 0.2317384287714958,
|
|
"num_tokens": 50289521.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.03934907913208,
|
|
"epoch": 2.1435378201310304,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004549735571353793,
|
|
"loss": 4.5544,
|
|
"mean_token_accuracy": 0.23707142919301988,
|
|
"num_tokens": 50303275.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.042974996566772,
|
|
"epoch": 2.144133412745682,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004549479796524119,
|
|
"loss": 4.6192,
|
|
"mean_token_accuracy": 0.22325256764888762,
|
|
"num_tokens": 50317613.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 2.144133412745682,
|
|
"eval_entropy": 4.780485389150422,
|
|
"eval_loss": 4.624568939208984,
|
|
"eval_mean_token_accuracy": 0.23937355613213349,
|
|
"eval_num_tokens": 50317613.0,
|
|
"eval_runtime": 18.6509,
|
|
"eval_samples_per_second": 1367.922,
|
|
"eval_steps_per_second": 171.037,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.057237052917481,
|
|
"epoch": 2.1447290053603334,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045492239571500305,
|
|
"loss": 4.5477,
|
|
"mean_token_accuracy": 0.23309866487979888,
|
|
"num_tokens": 50330682.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.124571800231934,
|
|
"epoch": 2.145324597974985,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004548968053240703,
|
|
"loss": 4.6565,
|
|
"mean_token_accuracy": 0.22001907974481583,
|
|
"num_tokens": 50347646.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.069941806793213,
|
|
"epoch": 2.145920190589637,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045487120848053175,
|
|
"loss": 4.5477,
|
|
"mean_token_accuracy": 0.2327919065952301,
|
|
"num_tokens": 50364245.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.061341094970703,
|
|
"epoch": 2.146515783204288,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004548456051853053,
|
|
"loss": 4.539,
|
|
"mean_token_accuracy": 0.2419222980737686,
|
|
"num_tokens": 50377278.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.066163349151611,
|
|
"epoch": 2.1471113758189397,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004548199954393095,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.23068902194499968,
|
|
"num_tokens": 50392052.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.1523744583129885,
|
|
"epoch": 2.1477069684335914,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045479437924346276,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.22821815311908722,
|
|
"num_tokens": 50407560.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.063224124908447,
|
|
"epoch": 2.148302561048243,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004547687565986841,
|
|
"loss": 4.5751,
|
|
"mean_token_accuracy": 0.22824729084968567,
|
|
"num_tokens": 50419195.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.07848539352417,
|
|
"epoch": 2.1488981536628944,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00045474312750589226,
|
|
"loss": 4.5933,
|
|
"mean_token_accuracy": 0.22978967130184175,
|
|
"num_tokens": 50433059.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 4.987894105911255,
|
|
"epoch": 2.149493746277546,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045471749196600677,
|
|
"loss": 4.4793,
|
|
"mean_token_accuracy": 0.2339960142970085,
|
|
"num_tokens": 50447177.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.079951524734497,
|
|
"epoch": 2.1500893388921978,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045469184997994706,
|
|
"loss": 4.6026,
|
|
"mean_token_accuracy": 0.2252620652318001,
|
|
"num_tokens": 50460294.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.029221725463867,
|
|
"epoch": 2.1506849315068495,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045466620154863276,
|
|
"loss": 4.5442,
|
|
"mean_token_accuracy": 0.23661143630743026,
|
|
"num_tokens": 50475176.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.121424055099487,
|
|
"epoch": 2.1512805241215007,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000454640546672984,
|
|
"loss": 4.6833,
|
|
"mean_token_accuracy": 0.23015536665916442,
|
|
"num_tokens": 50488618.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.050982570648193,
|
|
"epoch": 2.1518761167361524,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004546148853539209,
|
|
"loss": 4.5806,
|
|
"mean_token_accuracy": 0.24099683463573457,
|
|
"num_tokens": 50501269.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.036437606811523,
|
|
"epoch": 2.152471709350804,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045458921759236387,
|
|
"loss": 4.58,
|
|
"mean_token_accuracy": 0.23200255036354064,
|
|
"num_tokens": 50515551.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.086877346038818,
|
|
"epoch": 2.153067301965456,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004545635433892337,
|
|
"loss": 4.5689,
|
|
"mean_token_accuracy": 0.23360471427440643,
|
|
"num_tokens": 50531127.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.061339473724365,
|
|
"epoch": 2.153662894580107,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045453786274545106,
|
|
"loss": 4.605,
|
|
"mean_token_accuracy": 0.22926411628723145,
|
|
"num_tokens": 50544193.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 4.986808395385742,
|
|
"epoch": 2.1542584871947588,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045451217566193727,
|
|
"loss": 4.4905,
|
|
"mean_token_accuracy": 0.2352915644645691,
|
|
"num_tokens": 50557141.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.092573404312134,
|
|
"epoch": 2.1548540798094105,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004544864821396136,
|
|
"loss": 4.6206,
|
|
"mean_token_accuracy": 0.23883188664913177,
|
|
"num_tokens": 50572318.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.110547494888306,
|
|
"epoch": 2.155449672424062,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045446078217940155,
|
|
"loss": 4.6193,
|
|
"mean_token_accuracy": 0.22818220555782318,
|
|
"num_tokens": 50585985.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.095678043365479,
|
|
"epoch": 2.1560452650387134,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045443507578222316,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.22898730188608168,
|
|
"num_tokens": 50600135.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.046214771270752,
|
|
"epoch": 2.156640857653365,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045440936294900025,
|
|
"loss": 4.5294,
|
|
"mean_token_accuracy": 0.23333984464406968,
|
|
"num_tokens": 50613429.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.122585296630859,
|
|
"epoch": 2.157236450268017,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045438364368065526,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.21938171684741975,
|
|
"num_tokens": 50627261.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.025570917129516,
|
|
"epoch": 2.157832042882668,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004543579179781106,
|
|
"loss": 4.5274,
|
|
"mean_token_accuracy": 0.23367620259523392,
|
|
"num_tokens": 50643612.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.104268407821655,
|
|
"epoch": 2.1584276354973198,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045433218584228904,
|
|
"loss": 4.5647,
|
|
"mean_token_accuracy": 0.2309139296412468,
|
|
"num_tokens": 50654963.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.071575736999511,
|
|
"epoch": 2.1590232281119714,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004543064472741136,
|
|
"loss": 4.5557,
|
|
"mean_token_accuracy": 0.2398848921060562,
|
|
"num_tokens": 50668908.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.073831605911255,
|
|
"epoch": 2.159618820726623,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004542807022745073,
|
|
"loss": 4.5551,
|
|
"mean_token_accuracy": 0.23935801684856414,
|
|
"num_tokens": 50682572.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.032403659820557,
|
|
"epoch": 2.1602144133412744,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004542549508443938,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.2290667936205864,
|
|
"num_tokens": 50697235.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.104017210006714,
|
|
"epoch": 2.160810005955926,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045422919298469664,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.23170202672481538,
|
|
"num_tokens": 50710696.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.174843645095825,
|
|
"epoch": 2.161405598570578,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004542034286963398,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.21593621969223023,
|
|
"num_tokens": 50724625.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.018508768081665,
|
|
"epoch": 2.1620011911852295,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045417765798024716,
|
|
"loss": 4.5406,
|
|
"mean_token_accuracy": 0.23538408428430557,
|
|
"num_tokens": 50738277.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.063919925689698,
|
|
"epoch": 2.1625967837998807,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045415188083734346,
|
|
"loss": 4.5684,
|
|
"mean_token_accuracy": 0.24295099675655366,
|
|
"num_tokens": 50751020.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.160611534118653,
|
|
"epoch": 2.1631923764145324,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000454126097268553,
|
|
"loss": 4.7091,
|
|
"mean_token_accuracy": 0.2321023777127266,
|
|
"num_tokens": 50765589.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.153327941894531,
|
|
"epoch": 2.163787969029184,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045410030727480063,
|
|
"loss": 4.6305,
|
|
"mean_token_accuracy": 0.22940256893634797,
|
|
"num_tokens": 50777488.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.035337305068969,
|
|
"epoch": 2.1643835616438354,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045407451085701154,
|
|
"loss": 4.5532,
|
|
"mean_token_accuracy": 0.23042624145746232,
|
|
"num_tokens": 50789917.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.122010993957519,
|
|
"epoch": 2.164979154258487,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004540487080161108,
|
|
"loss": 4.6181,
|
|
"mean_token_accuracy": 0.22376373857259751,
|
|
"num_tokens": 50803948.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.094397974014282,
|
|
"epoch": 2.165574746873139,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045402289875302404,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.23128741085529328,
|
|
"num_tokens": 50816753.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.08295087814331,
|
|
"epoch": 2.1661703394877905,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000453997083068677,
|
|
"loss": 4.5707,
|
|
"mean_token_accuracy": 0.22840842753648757,
|
|
"num_tokens": 50831271.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.002707481384277,
|
|
"epoch": 2.1667659321024417,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004539712609639956,
|
|
"loss": 4.526,
|
|
"mean_token_accuracy": 0.23526899367570878,
|
|
"num_tokens": 50845097.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.012673091888428,
|
|
"epoch": 2.1673615247170934,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004539454324399061,
|
|
"loss": 4.5245,
|
|
"mean_token_accuracy": 0.24010564684867858,
|
|
"num_tokens": 50857856.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.105396556854248,
|
|
"epoch": 2.167957117331745,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004539195974973348,
|
|
"loss": 4.6247,
|
|
"mean_token_accuracy": 0.2271365448832512,
|
|
"num_tokens": 50871461.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 4.9857621669769285,
|
|
"epoch": 2.168552709946397,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004538937561372086,
|
|
"loss": 4.5002,
|
|
"mean_token_accuracy": 0.24269666224718095,
|
|
"num_tokens": 50884414.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.098526573181152,
|
|
"epoch": 2.169148302561048,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045386790836045407,
|
|
"loss": 4.5885,
|
|
"mean_token_accuracy": 0.228512704372406,
|
|
"num_tokens": 50898597.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.026455497741699,
|
|
"epoch": 2.1697438951756998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004538420541679986,
|
|
"loss": 4.5153,
|
|
"mean_token_accuracy": 0.2387027233839035,
|
|
"num_tokens": 50912131.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.0789612293243405,
|
|
"epoch": 2.1703394877903515,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004538161935607693,
|
|
"loss": 4.5734,
|
|
"mean_token_accuracy": 0.2363380417227745,
|
|
"num_tokens": 50926955.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.061646795272827,
|
|
"epoch": 2.170935080405003,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004537903265396939,
|
|
"loss": 4.6024,
|
|
"mean_token_accuracy": 0.2297322630882263,
|
|
"num_tokens": 50940448.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.101152181625366,
|
|
"epoch": 2.1715306730196544,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004537644531057003,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.23354478627443315,
|
|
"num_tokens": 50953924.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.022262763977051,
|
|
"epoch": 2.172126265634306,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045373857325971636,
|
|
"loss": 4.5031,
|
|
"mean_token_accuracy": 0.23669251501560212,
|
|
"num_tokens": 50966641.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.059750556945801,
|
|
"epoch": 2.172721858248958,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045371268700267035,
|
|
"loss": 4.5885,
|
|
"mean_token_accuracy": 0.22940776199102403,
|
|
"num_tokens": 50980539.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.053710174560547,
|
|
"epoch": 2.1733174508636095,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004536867943354909,
|
|
"loss": 4.5816,
|
|
"mean_token_accuracy": 0.23431239873170853,
|
|
"num_tokens": 50993718.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.067972707748413,
|
|
"epoch": 2.1739130434782608,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045366089525910664,
|
|
"loss": 4.6572,
|
|
"mean_token_accuracy": 0.22691750228405,
|
|
"num_tokens": 51008219.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.0914044857025145,
|
|
"epoch": 2.1745086360929125,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045363498977444655,
|
|
"loss": 4.5539,
|
|
"mean_token_accuracy": 0.2316535994410515,
|
|
"num_tokens": 51022642.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.062910366058349,
|
|
"epoch": 2.175104228707564,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004536090778824398,
|
|
"loss": 4.5815,
|
|
"mean_token_accuracy": 0.2324182540178299,
|
|
"num_tokens": 51035892.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.084800434112549,
|
|
"epoch": 2.1756998213222154,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045358315958401584,
|
|
"loss": 4.687,
|
|
"mean_token_accuracy": 0.22568533569574356,
|
|
"num_tokens": 51049679.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.1561057567596436,
|
|
"epoch": 2.176295413936867,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045355723488010435,
|
|
"loss": 4.6649,
|
|
"mean_token_accuracy": 0.2232262223958969,
|
|
"num_tokens": 51063968.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.076283979415893,
|
|
"epoch": 2.176891006551519,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045353130377163514,
|
|
"loss": 4.551,
|
|
"mean_token_accuracy": 0.2382476359605789,
|
|
"num_tokens": 51077003.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.097772169113159,
|
|
"epoch": 2.1774865991661705,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004535053662595383,
|
|
"loss": 4.6408,
|
|
"mean_token_accuracy": 0.23363529294729232,
|
|
"num_tokens": 51091832.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.051648426055908,
|
|
"epoch": 2.1780821917808217,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045347942234474426,
|
|
"loss": 4.656,
|
|
"mean_token_accuracy": 0.22494877576828004,
|
|
"num_tokens": 51106062.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.137237691879273,
|
|
"epoch": 2.1786777843954734,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004534534720281835,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.2220644474029541,
|
|
"num_tokens": 51119885.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.069929456710815,
|
|
"epoch": 2.179273377010125,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004534275153107868,
|
|
"loss": 4.5475,
|
|
"mean_token_accuracy": 0.24420253932476044,
|
|
"num_tokens": 51132341.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.07485990524292,
|
|
"epoch": 2.179868969624777,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045340155219348536,
|
|
"loss": 4.5689,
|
|
"mean_token_accuracy": 0.2329817831516266,
|
|
"num_tokens": 51146867.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 4.986395454406738,
|
|
"epoch": 2.180464562239428,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004533755826772102,
|
|
"loss": 4.5261,
|
|
"mean_token_accuracy": 0.2350584462285042,
|
|
"num_tokens": 51161525.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.13584942817688,
|
|
"epoch": 2.18106015485408,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004533496067628929,
|
|
"loss": 4.6081,
|
|
"mean_token_accuracy": 0.2238225519657135,
|
|
"num_tokens": 51175430.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.115877723693847,
|
|
"epoch": 2.1816557474687315,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004533236244514652,
|
|
"loss": 4.5622,
|
|
"mean_token_accuracy": 0.23714480847120284,
|
|
"num_tokens": 51189316.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.004168939590454,
|
|
"epoch": 2.182251340083383,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00045329763574385905,
|
|
"loss": 4.4742,
|
|
"mean_token_accuracy": 0.23669355511665344,
|
|
"num_tokens": 51201489.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.062097597122192,
|
|
"epoch": 2.1828469326980344,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00045327164064100654,
|
|
"loss": 4.5934,
|
|
"mean_token_accuracy": 0.22631790339946747,
|
|
"num_tokens": 51217170.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.113543176651001,
|
|
"epoch": 2.183442525312686,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045324563914384024,
|
|
"loss": 4.6278,
|
|
"mean_token_accuracy": 0.2299240455031395,
|
|
"num_tokens": 51231583.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.030544233322144,
|
|
"epoch": 2.184038117927338,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004532196312532926,
|
|
"loss": 4.5091,
|
|
"mean_token_accuracy": 0.24109900146722793,
|
|
"num_tokens": 51245253.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.050997543334961,
|
|
"epoch": 2.184633710541989,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004531936169702966,
|
|
"loss": 4.5916,
|
|
"mean_token_accuracy": 0.2246204361319542,
|
|
"num_tokens": 51259543.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.134110069274902,
|
|
"epoch": 2.1852293031566408,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004531675962957853,
|
|
"loss": 4.6262,
|
|
"mean_token_accuracy": 0.226420596241951,
|
|
"num_tokens": 51274244.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.04359450340271,
|
|
"epoch": 2.1858248957712925,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004531415692306919,
|
|
"loss": 4.5575,
|
|
"mean_token_accuracy": 0.237829552590847,
|
|
"num_tokens": 51288074.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.063855695724487,
|
|
"epoch": 2.186420488385944,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004531155357759501,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.23627980649471284,
|
|
"num_tokens": 51301377.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.068798303604126,
|
|
"epoch": 2.1870160810005954,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004530894959324937,
|
|
"loss": 4.5369,
|
|
"mean_token_accuracy": 0.2393062248826027,
|
|
"num_tokens": 51314711.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 4.9747058868408205,
|
|
"epoch": 2.187611673615247,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045306344970125656,
|
|
"loss": 4.5378,
|
|
"mean_token_accuracy": 0.23810890316963196,
|
|
"num_tokens": 51329324.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.100292778015136,
|
|
"epoch": 2.188207266229899,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045303739708317303,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.22392429560422897,
|
|
"num_tokens": 51341833.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.110960912704468,
|
|
"epoch": 2.1888028588445505,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004530113380791775,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.22516638040542603,
|
|
"num_tokens": 51357893.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.065338945388794,
|
|
"epoch": 2.1893984514592018,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004529852726902047,
|
|
"loss": 4.5724,
|
|
"mean_token_accuracy": 0.23427535593509674,
|
|
"num_tokens": 51372260.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.102686643600464,
|
|
"epoch": 2.1899940440738535,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004529592009171896,
|
|
"loss": 4.613,
|
|
"mean_token_accuracy": 0.2352802038192749,
|
|
"num_tokens": 51387176.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 4.994309329986573,
|
|
"epoch": 2.190589636688505,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045293312276106735,
|
|
"loss": 4.4868,
|
|
"mean_token_accuracy": 0.23070544004440308,
|
|
"num_tokens": 51399944.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.021578073501587,
|
|
"epoch": 2.191185229303157,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004529070382227732,
|
|
"loss": 4.5369,
|
|
"mean_token_accuracy": 0.23359726816415788,
|
|
"num_tokens": 51414411.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.1207709312438965,
|
|
"epoch": 2.191780821917808,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004528809473032428,
|
|
"loss": 4.6375,
|
|
"mean_token_accuracy": 0.22005428671836852,
|
|
"num_tokens": 51428433.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.069715690612793,
|
|
"epoch": 2.19237641453246,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045285485000341215,
|
|
"loss": 4.586,
|
|
"mean_token_accuracy": 0.23189448416233063,
|
|
"num_tokens": 51441159.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.082336282730102,
|
|
"epoch": 2.1929720071471115,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00045282874632421717,
|
|
"loss": 4.6351,
|
|
"mean_token_accuracy": 0.22409642338752747,
|
|
"num_tokens": 51457792.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.049672842025757,
|
|
"epoch": 2.1935675997617627,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004528026362665942,
|
|
"loss": 4.6011,
|
|
"mean_token_accuracy": 0.22815934866666793,
|
|
"num_tokens": 51472293.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.091569137573242,
|
|
"epoch": 2.1941631923764144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004527765198314798,
|
|
"loss": 4.5708,
|
|
"mean_token_accuracy": 0.22745165079832078,
|
|
"num_tokens": 51487323.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.166643571853638,
|
|
"epoch": 2.194758784991066,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004527503970198105,
|
|
"loss": 4.6797,
|
|
"mean_token_accuracy": 0.22587578147649764,
|
|
"num_tokens": 51500243.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.057397890090942,
|
|
"epoch": 2.195354377605718,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004527242678325236,
|
|
"loss": 4.5474,
|
|
"mean_token_accuracy": 0.23494790643453597,
|
|
"num_tokens": 51514691.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 4.99830641746521,
|
|
"epoch": 2.195949970220369,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004526981322705562,
|
|
"loss": 4.5169,
|
|
"mean_token_accuracy": 0.23789770603179933,
|
|
"num_tokens": 51529808.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.023060512542725,
|
|
"epoch": 2.196545562835021,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004526719903348457,
|
|
"loss": 4.5509,
|
|
"mean_token_accuracy": 0.231656776368618,
|
|
"num_tokens": 51543927.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.06020565032959,
|
|
"epoch": 2.1971411554496725,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004526458420263297,
|
|
"loss": 4.6078,
|
|
"mean_token_accuracy": 0.22961436212062836,
|
|
"num_tokens": 51557270.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.06563286781311,
|
|
"epoch": 2.197736748064324,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00045261968734594624,
|
|
"loss": 4.6209,
|
|
"mean_token_accuracy": 0.22956433445215224,
|
|
"num_tokens": 51569559.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.147322511672973,
|
|
"epoch": 2.1983323406789754,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045259352629463336,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.22309376746416093,
|
|
"num_tokens": 51582464.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.0119870662689205,
|
|
"epoch": 2.198927933293627,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004525673588733295,
|
|
"loss": 4.471,
|
|
"mean_token_accuracy": 0.2411394774913788,
|
|
"num_tokens": 51596461.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.025464391708374,
|
|
"epoch": 2.199523525908279,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004525411850829732,
|
|
"loss": 4.4871,
|
|
"mean_token_accuracy": 0.236033596098423,
|
|
"num_tokens": 51610453.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.06985821723938,
|
|
"epoch": 2.2001191185229305,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004525150049245032,
|
|
"loss": 4.5502,
|
|
"mean_token_accuracy": 0.23820949494838714,
|
|
"num_tokens": 51625338.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.026498794555664,
|
|
"epoch": 2.2007147111375818,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004524888183988586,
|
|
"loss": 4.5373,
|
|
"mean_token_accuracy": 0.23321059942245484,
|
|
"num_tokens": 51638530.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.054878425598145,
|
|
"epoch": 2.2013103037522335,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004524626255069786,
|
|
"loss": 4.5981,
|
|
"mean_token_accuracy": 0.2337049275636673,
|
|
"num_tokens": 51651531.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.065001583099365,
|
|
"epoch": 2.201905896366885,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045243642624980283,
|
|
"loss": 4.6392,
|
|
"mean_token_accuracy": 0.22498417794704437,
|
|
"num_tokens": 51665648.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.072051620483398,
|
|
"epoch": 2.202501488981537,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004524102206282709,
|
|
"loss": 4.529,
|
|
"mean_token_accuracy": 0.23953165709972382,
|
|
"num_tokens": 51678894.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.091199445724487,
|
|
"epoch": 2.203097081596188,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004523840086433229,
|
|
"loss": 4.6199,
|
|
"mean_token_accuracy": 0.22705853283405303,
|
|
"num_tokens": 51694617.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.088074159622193,
|
|
"epoch": 2.20369267421084,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00045235779029589884,
|
|
"loss": 4.595,
|
|
"mean_token_accuracy": 0.23023827970027924,
|
|
"num_tokens": 51710340.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.067034149169922,
|
|
"epoch": 2.2042882668254915,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045233156558693925,
|
|
"loss": 4.5652,
|
|
"mean_token_accuracy": 0.23025643229484558,
|
|
"num_tokens": 51724190.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.086471271514893,
|
|
"epoch": 2.2048838594401428,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004523053345173848,
|
|
"loss": 4.5779,
|
|
"mean_token_accuracy": 0.2326805219054222,
|
|
"num_tokens": 51737702.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.018223762512207,
|
|
"epoch": 2.2054794520547945,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045227909708817613,
|
|
"loss": 4.5198,
|
|
"mean_token_accuracy": 0.24501131027936934,
|
|
"num_tokens": 51750266.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.066118335723877,
|
|
"epoch": 2.206075044669446,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004522528533002545,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.2350664973258972,
|
|
"num_tokens": 51763875.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.088377857208252,
|
|
"epoch": 2.206670637284098,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045222660315456125,
|
|
"loss": 4.5739,
|
|
"mean_token_accuracy": 0.23118337839841843,
|
|
"num_tokens": 51777515.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 4.96267032623291,
|
|
"epoch": 2.207266229898749,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00045220034665203795,
|
|
"loss": 4.4432,
|
|
"mean_token_accuracy": 0.24756379425525665,
|
|
"num_tokens": 51790993.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.0706840515136715,
|
|
"epoch": 2.207861822513401,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045217408379362635,
|
|
"loss": 4.555,
|
|
"mean_token_accuracy": 0.23687397092580795,
|
|
"num_tokens": 51806636.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 4.979137563705445,
|
|
"epoch": 2.2084574151280525,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00045214781458026833,
|
|
"loss": 4.5244,
|
|
"mean_token_accuracy": 0.24084154814481734,
|
|
"num_tokens": 51820832.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.04384183883667,
|
|
"epoch": 2.209053007742704,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004521215390129063,
|
|
"loss": 4.5903,
|
|
"mean_token_accuracy": 0.22252153009176254,
|
|
"num_tokens": 51835845.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.037207078933716,
|
|
"epoch": 2.2096486003573554,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00045209525709248257,
|
|
"loss": 4.4466,
|
|
"mean_token_accuracy": 0.24319990128278732,
|
|
"num_tokens": 51850665.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 4.977944993972779,
|
|
"epoch": 2.210244192972007,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00045206896881994,
|
|
"loss": 4.4798,
|
|
"mean_token_accuracy": 0.2419770210981369,
|
|
"num_tokens": 51865369.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.027566528320312,
|
|
"epoch": 2.210839785586659,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004520426741962213,
|
|
"loss": 4.5959,
|
|
"mean_token_accuracy": 0.23168510496616362,
|
|
"num_tokens": 51880589.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.106928825378418,
|
|
"epoch": 2.21143537820131,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045201637322226984,
|
|
"loss": 4.6431,
|
|
"mean_token_accuracy": 0.22534869611263275,
|
|
"num_tokens": 51894682.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.148609638214111,
|
|
"epoch": 2.212030970815962,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045199006589902884,
|
|
"loss": 4.6632,
|
|
"mean_token_accuracy": 0.2252534344792366,
|
|
"num_tokens": 51905381.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.060933589935303,
|
|
"epoch": 2.2126265634306135,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045196375222744195,
|
|
"loss": 4.6446,
|
|
"mean_token_accuracy": 0.22662620842456818,
|
|
"num_tokens": 51920613.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.139051151275635,
|
|
"epoch": 2.213222156045265,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000451937432208453,
|
|
"loss": 4.6476,
|
|
"mean_token_accuracy": 0.2255278691649437,
|
|
"num_tokens": 51934197.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.023745346069336,
|
|
"epoch": 2.2138177486599164,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000451911105843006,
|
|
"loss": 4.5304,
|
|
"mean_token_accuracy": 0.2333206281065941,
|
|
"num_tokens": 51947983.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 4.98829345703125,
|
|
"epoch": 2.214413341274568,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045188477313204536,
|
|
"loss": 4.5188,
|
|
"mean_token_accuracy": 0.234802770614624,
|
|
"num_tokens": 51961081.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.063410520553589,
|
|
"epoch": 2.21500893388922,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045185843407651537,
|
|
"loss": 4.5813,
|
|
"mean_token_accuracy": 0.2331221029162407,
|
|
"num_tokens": 51975213.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.065647745132447,
|
|
"epoch": 2.2156045265038715,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00045183208867736097,
|
|
"loss": 4.5798,
|
|
"mean_token_accuracy": 0.234152914583683,
|
|
"num_tokens": 51992564.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.063126039505005,
|
|
"epoch": 2.2162001191185228,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045180573693552714,
|
|
"loss": 4.5174,
|
|
"mean_token_accuracy": 0.22684621512889863,
|
|
"num_tokens": 52007652.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.055744695663452,
|
|
"epoch": 2.2167957117331745,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045177937885195884,
|
|
"loss": 4.5689,
|
|
"mean_token_accuracy": 0.23163047134876252,
|
|
"num_tokens": 52021845.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.0638823986053465,
|
|
"epoch": 2.217391304347826,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004517530144276018,
|
|
"loss": 4.5009,
|
|
"mean_token_accuracy": 0.24015730768442153,
|
|
"num_tokens": 52034786.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.077210760116577,
|
|
"epoch": 2.217986896962478,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004517266436634014,
|
|
"loss": 4.56,
|
|
"mean_token_accuracy": 0.2342678889632225,
|
|
"num_tokens": 52047685.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.017942619323731,
|
|
"epoch": 2.218582489577129,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004517002665603037,
|
|
"loss": 4.5711,
|
|
"mean_token_accuracy": 0.23465372025966644,
|
|
"num_tokens": 52060729.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.105124855041504,
|
|
"epoch": 2.219178082191781,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004516738831192547,
|
|
"loss": 4.5801,
|
|
"mean_token_accuracy": 0.23015250712633134,
|
|
"num_tokens": 52074145.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.094186067581177,
|
|
"epoch": 2.2197736748064325,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045164749334120074,
|
|
"loss": 4.6391,
|
|
"mean_token_accuracy": 0.22168687582015992,
|
|
"num_tokens": 52088717.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.160942411422729,
|
|
"epoch": 2.220369267421084,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004516210972270885,
|
|
"loss": 4.6303,
|
|
"mean_token_accuracy": 0.22514767944812775,
|
|
"num_tokens": 52103048.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.107061433792114,
|
|
"epoch": 2.2209648600357355,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045159469477786457,
|
|
"loss": 4.6095,
|
|
"mean_token_accuracy": 0.22057023048400878,
|
|
"num_tokens": 52116508.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.043984699249267,
|
|
"epoch": 2.221560452650387,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004515682859944762,
|
|
"loss": 4.5136,
|
|
"mean_token_accuracy": 0.23357127010822296,
|
|
"num_tokens": 52130549.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.074154090881348,
|
|
"epoch": 2.222156045265039,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004515418708778704,
|
|
"loss": 4.6779,
|
|
"mean_token_accuracy": 0.22274327427148818,
|
|
"num_tokens": 52144114.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.092698955535889,
|
|
"epoch": 2.22275163787969,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004515154494289947,
|
|
"loss": 4.5943,
|
|
"mean_token_accuracy": 0.23407687544822692,
|
|
"num_tokens": 52157564.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.056818199157715,
|
|
"epoch": 2.223347230494342,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00045148902164879686,
|
|
"loss": 4.5329,
|
|
"mean_token_accuracy": 0.23313214480876923,
|
|
"num_tokens": 52172882.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.022477722167968,
|
|
"epoch": 2.2239428231089935,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045146258753822475,
|
|
"loss": 4.5048,
|
|
"mean_token_accuracy": 0.24183158427476883,
|
|
"num_tokens": 52187698.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.058338260650634,
|
|
"epoch": 2.224538415723645,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004514361470982266,
|
|
"loss": 4.6161,
|
|
"mean_token_accuracy": 0.22869666516780854,
|
|
"num_tokens": 52199823.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.041254901885987,
|
|
"epoch": 2.2251340083382964,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045140970032975057,
|
|
"loss": 4.5734,
|
|
"mean_token_accuracy": 0.23039279133081436,
|
|
"num_tokens": 52214875.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.048872709274292,
|
|
"epoch": 2.225729600952948,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045138324723374565,
|
|
"loss": 4.588,
|
|
"mean_token_accuracy": 0.22493463158607482,
|
|
"num_tokens": 52228631.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.022264099121093,
|
|
"epoch": 2.2263251935676,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045135678781116025,
|
|
"loss": 4.5201,
|
|
"mean_token_accuracy": 0.23709056079387664,
|
|
"num_tokens": 52241160.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.029909610748291,
|
|
"epoch": 2.2269207861822515,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045133032206294365,
|
|
"loss": 4.589,
|
|
"mean_token_accuracy": 0.23227032870054246,
|
|
"num_tokens": 52254586.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.1250707626342775,
|
|
"epoch": 2.227516378796903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004513038499900451,
|
|
"loss": 4.6747,
|
|
"mean_token_accuracy": 0.22831626683473588,
|
|
"num_tokens": 52268435.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.074467945098877,
|
|
"epoch": 2.2281119714115545,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045127737159341406,
|
|
"loss": 4.5547,
|
|
"mean_token_accuracy": 0.2318175718188286,
|
|
"num_tokens": 52283312.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 4.994687843322754,
|
|
"epoch": 2.228707564026206,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004512508868740004,
|
|
"loss": 4.5045,
|
|
"mean_token_accuracy": 0.24617589861154557,
|
|
"num_tokens": 52298128.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.085499954223633,
|
|
"epoch": 2.2293031566408574,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000451224395832754,
|
|
"loss": 4.5872,
|
|
"mean_token_accuracy": 0.23157862573862076,
|
|
"num_tokens": 52313385.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.0651021003723145,
|
|
"epoch": 2.229898749255509,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045119789847062496,
|
|
"loss": 4.5617,
|
|
"mean_token_accuracy": 0.23244232386350633,
|
|
"num_tokens": 52326370.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.141936302185059,
|
|
"epoch": 2.230494341870161,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045117139478856376,
|
|
"loss": 4.6411,
|
|
"mean_token_accuracy": 0.22723085284233094,
|
|
"num_tokens": 52339959.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.019714260101319,
|
|
"epoch": 2.2310899344848125,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004511448847875212,
|
|
"loss": 4.5253,
|
|
"mean_token_accuracy": 0.23258240818977355,
|
|
"num_tokens": 52353694.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.087067985534668,
|
|
"epoch": 2.2316855270994638,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045111836846844795,
|
|
"loss": 4.5503,
|
|
"mean_token_accuracy": 0.23346790671348572,
|
|
"num_tokens": 52368889.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.032775020599365,
|
|
"epoch": 2.2322811197141155,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045109184583229514,
|
|
"loss": 4.5003,
|
|
"mean_token_accuracy": 0.2383194997906685,
|
|
"num_tokens": 52380883.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.024731969833374,
|
|
"epoch": 2.232876712328767,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045106531688001415,
|
|
"loss": 4.5411,
|
|
"mean_token_accuracy": 0.23157986253499985,
|
|
"num_tokens": 52394155.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.0227617740631105,
|
|
"epoch": 2.233472304943419,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004510387816125566,
|
|
"loss": 4.5119,
|
|
"mean_token_accuracy": 0.23850639462471007,
|
|
"num_tokens": 52408978.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.09028172492981,
|
|
"epoch": 2.23406789755807,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000451012240030874,
|
|
"loss": 4.6184,
|
|
"mean_token_accuracy": 0.23075831532478333,
|
|
"num_tokens": 52422733.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.03890471458435,
|
|
"epoch": 2.234663490172722,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004509856921359186,
|
|
"loss": 4.5544,
|
|
"mean_token_accuracy": 0.23992990255355834,
|
|
"num_tokens": 52437377.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.112738418579101,
|
|
"epoch": 2.2352590827873735,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045095913792864265,
|
|
"loss": 4.5993,
|
|
"mean_token_accuracy": 0.2382930502295494,
|
|
"num_tokens": 52450610.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.040819406509399,
|
|
"epoch": 2.235854675402025,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004509325774099984,
|
|
"loss": 4.5071,
|
|
"mean_token_accuracy": 0.24070213735103607,
|
|
"num_tokens": 52464478.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 4.995719480514526,
|
|
"epoch": 2.2364502680166765,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045090601058093874,
|
|
"loss": 4.536,
|
|
"mean_token_accuracy": 0.2406015530228615,
|
|
"num_tokens": 52477100.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.008011770248413,
|
|
"epoch": 2.237045860631328,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004508794374424164,
|
|
"loss": 4.5229,
|
|
"mean_token_accuracy": 0.23306275010108948,
|
|
"num_tokens": 52491332.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.1573244571685795,
|
|
"epoch": 2.23764145324598,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004508528579953846,
|
|
"loss": 4.6871,
|
|
"mean_token_accuracy": 0.22389931380748748,
|
|
"num_tokens": 52506472.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.102776384353637,
|
|
"epoch": 2.2382370458606315,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004508262722407968,
|
|
"loss": 4.6109,
|
|
"mean_token_accuracy": 0.22530000805854797,
|
|
"num_tokens": 52520021.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.073018407821655,
|
|
"epoch": 2.238832638475283,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045079968017960637,
|
|
"loss": 4.572,
|
|
"mean_token_accuracy": 0.2305218204855919,
|
|
"num_tokens": 52532894.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.0966733455657955,
|
|
"epoch": 2.2394282310899345,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00045077308181276735,
|
|
"loss": 4.6376,
|
|
"mean_token_accuracy": 0.22059040516614914,
|
|
"num_tokens": 52547298.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.107471895217896,
|
|
"epoch": 2.240023823704586,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004507464771412336,
|
|
"loss": 4.5916,
|
|
"mean_token_accuracy": 0.22644041031599044,
|
|
"num_tokens": 52561398.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.089951467514038,
|
|
"epoch": 2.2406194163192374,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00045071986616595946,
|
|
"loss": 4.605,
|
|
"mean_token_accuracy": 0.23171088099479675,
|
|
"num_tokens": 52577892.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.088606500625611,
|
|
"epoch": 2.241215008933889,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045069324888789955,
|
|
"loss": 4.6109,
|
|
"mean_token_accuracy": 0.23066114783287048,
|
|
"num_tokens": 52592265.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.1378826141357425,
|
|
"epoch": 2.241810601548541,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045066662530800835,
|
|
"loss": 4.6293,
|
|
"mean_token_accuracy": 0.23017880618572234,
|
|
"num_tokens": 52605898.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.14456353187561,
|
|
"epoch": 2.2424061941631925,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004506399954272409,
|
|
"loss": 4.6911,
|
|
"mean_token_accuracy": 0.2211127907037735,
|
|
"num_tokens": 52619524.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.122465181350708,
|
|
"epoch": 2.243001786777844,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00045061335924655236,
|
|
"loss": 4.5815,
|
|
"mean_token_accuracy": 0.22792281657457353,
|
|
"num_tokens": 52633816.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.092729997634888,
|
|
"epoch": 2.2435973793924955,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004505867167668983,
|
|
"loss": 4.5753,
|
|
"mean_token_accuracy": 0.23342272639274597,
|
|
"num_tokens": 52646935.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.062460994720459,
|
|
"epoch": 2.244192972007147,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004505600679892341,
|
|
"loss": 4.5967,
|
|
"mean_token_accuracy": 0.22577974945306778,
|
|
"num_tokens": 52662459.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.103669357299805,
|
|
"epoch": 2.244788564621799,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045053341291451565,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.23140206784009934,
|
|
"num_tokens": 52674700.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.066592836380005,
|
|
"epoch": 2.24538415723645,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045050675154369917,
|
|
"loss": 4.5637,
|
|
"mean_token_accuracy": 0.23665804266929627,
|
|
"num_tokens": 52689312.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.010497188568115,
|
|
"epoch": 2.245979749851102,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004504800838777408,
|
|
"loss": 4.5371,
|
|
"mean_token_accuracy": 0.2390068680047989,
|
|
"num_tokens": 52702589.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.076924133300781,
|
|
"epoch": 2.2465753424657535,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004504534099175972,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.2282981738448143,
|
|
"num_tokens": 52716742.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.055105924606323,
|
|
"epoch": 2.2471709350804048,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00045042672966422506,
|
|
"loss": 4.5193,
|
|
"mean_token_accuracy": 0.2324731782078743,
|
|
"num_tokens": 52730484.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.066760110855102,
|
|
"epoch": 2.2477665276950565,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004504000431185813,
|
|
"loss": 4.5597,
|
|
"mean_token_accuracy": 0.2402890220284462,
|
|
"num_tokens": 52743667.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.081312894821167,
|
|
"epoch": 2.248362120309708,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045037335028162327,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.23438475281000137,
|
|
"num_tokens": 52757426.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.086762857437134,
|
|
"epoch": 2.24895771292436,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045034665115430817,
|
|
"loss": 4.5406,
|
|
"mean_token_accuracy": 0.23802728205919266,
|
|
"num_tokens": 52770333.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.03978705406189,
|
|
"epoch": 2.249553305539011,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004503199457375939,
|
|
"loss": 4.6462,
|
|
"mean_token_accuracy": 0.2238456442952156,
|
|
"num_tokens": 52786514.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.095294427871704,
|
|
"epoch": 2.250148898153663,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045029323403243817,
|
|
"loss": 4.5192,
|
|
"mean_token_accuracy": 0.24079206287860871,
|
|
"num_tokens": 52800985.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.113240098953247,
|
|
"epoch": 2.2507444907683145,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004502665160397991,
|
|
"loss": 4.6579,
|
|
"mean_token_accuracy": 0.22381236255168915,
|
|
"num_tokens": 52814739.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 4.996947288513184,
|
|
"epoch": 2.251340083382966,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004502397917606352,
|
|
"loss": 4.5282,
|
|
"mean_token_accuracy": 0.23426194339990616,
|
|
"num_tokens": 52828310.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.063540983200073,
|
|
"epoch": 2.2519356759976175,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004502130611959048,
|
|
"loss": 4.5503,
|
|
"mean_token_accuracy": 0.23624750822782517,
|
|
"num_tokens": 52843460.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.122108411788941,
|
|
"epoch": 2.252531268612269,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004501863243465668,
|
|
"loss": 4.6373,
|
|
"mean_token_accuracy": 0.2308359697461128,
|
|
"num_tokens": 52857162.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.053860998153686,
|
|
"epoch": 2.253126861226921,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045015958121358014,
|
|
"loss": 4.5348,
|
|
"mean_token_accuracy": 0.24429564476013182,
|
|
"num_tokens": 52868462.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 4.977369737625122,
|
|
"epoch": 2.2537224538415725,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004501328317979041,
|
|
"loss": 4.4839,
|
|
"mean_token_accuracy": 0.24747624844312668,
|
|
"num_tokens": 52881797.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 4.9794751644134525,
|
|
"epoch": 2.254318046456224,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004501060761004982,
|
|
"loss": 4.4241,
|
|
"mean_token_accuracy": 0.2496974691748619,
|
|
"num_tokens": 52894782.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.067622375488281,
|
|
"epoch": 2.2549136390708755,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000450079314122322,
|
|
"loss": 4.5313,
|
|
"mean_token_accuracy": 0.23747537434101104,
|
|
"num_tokens": 52907339.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.074425983428955,
|
|
"epoch": 2.255509231685527,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004500525458643355,
|
|
"loss": 4.6063,
|
|
"mean_token_accuracy": 0.23198252171278,
|
|
"num_tokens": 52919909.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.056458616256714,
|
|
"epoch": 2.256104824300179,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004500257713274988,
|
|
"loss": 4.5555,
|
|
"mean_token_accuracy": 0.24205615669488906,
|
|
"num_tokens": 52935664.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.099501514434815,
|
|
"epoch": 2.25670041691483,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044999899051277213,
|
|
"loss": 4.5301,
|
|
"mean_token_accuracy": 0.2401907339692116,
|
|
"num_tokens": 52950296.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 4.992406225204467,
|
|
"epoch": 2.257296009529482,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044997220342111636,
|
|
"loss": 4.5027,
|
|
"mean_token_accuracy": 0.23879167288541794,
|
|
"num_tokens": 52962887.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.088126134872437,
|
|
"epoch": 2.2578916021441335,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044994541005349207,
|
|
"loss": 4.615,
|
|
"mean_token_accuracy": 0.22489040791988374,
|
|
"num_tokens": 52976260.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.064387321472168,
|
|
"epoch": 2.258487194758785,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004499186104108604,
|
|
"loss": 4.5844,
|
|
"mean_token_accuracy": 0.22962815165519715,
|
|
"num_tokens": 52990564.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.0791291236877445,
|
|
"epoch": 2.2590827873734365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044989180449418254,
|
|
"loss": 4.5849,
|
|
"mean_token_accuracy": 0.22474919259548187,
|
|
"num_tokens": 53005986.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.081491327285766,
|
|
"epoch": 2.259678379988088,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044986499230442,
|
|
"loss": 4.6252,
|
|
"mean_token_accuracy": 0.22606904357671737,
|
|
"num_tokens": 53018294.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.0995909690856935,
|
|
"epoch": 2.26027397260274,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004498381738425346,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.2332818999886513,
|
|
"num_tokens": 53031099.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.052261543273926,
|
|
"epoch": 2.260869565217391,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044981134910948806,
|
|
"loss": 4.478,
|
|
"mean_token_accuracy": 0.23659885823726653,
|
|
"num_tokens": 53042648.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.0423108577728275,
|
|
"epoch": 2.261465157832043,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044978451810624264,
|
|
"loss": 4.5716,
|
|
"mean_token_accuracy": 0.2300386145710945,
|
|
"num_tokens": 53055082.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.156754398345948,
|
|
"epoch": 2.2620607504466945,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044975768083376085,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.23097164630889894,
|
|
"num_tokens": 53068508.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.073275375366211,
|
|
"epoch": 2.262656343061346,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044973083729300513,
|
|
"loss": 4.5461,
|
|
"mean_token_accuracy": 0.23397697508335114,
|
|
"num_tokens": 53082218.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.021144104003906,
|
|
"epoch": 2.2632519356759975,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044970398748493836,
|
|
"loss": 4.5274,
|
|
"mean_token_accuracy": 0.2357435867190361,
|
|
"num_tokens": 53095558.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.029192972183227,
|
|
"epoch": 2.263847528290649,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044967713141052363,
|
|
"loss": 4.5084,
|
|
"mean_token_accuracy": 0.24650365561246873,
|
|
"num_tokens": 53108364.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 4.999338006973266,
|
|
"epoch": 2.264443120905301,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004496502690707242,
|
|
"loss": 4.4946,
|
|
"mean_token_accuracy": 0.2377009078860283,
|
|
"num_tokens": 53122471.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.04717698097229,
|
|
"epoch": 2.265038713519952,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044962340046650356,
|
|
"loss": 4.5614,
|
|
"mean_token_accuracy": 0.23659193217754365,
|
|
"num_tokens": 53137391.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.07610445022583,
|
|
"epoch": 2.265634306134604,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004495965255988255,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.24235764145851135,
|
|
"num_tokens": 53148815.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.096362924575805,
|
|
"epoch": 2.2662298987492555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004495696444686539,
|
|
"loss": 4.6021,
|
|
"mean_token_accuracy": 0.2258543401956558,
|
|
"num_tokens": 53163620.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.042815780639648,
|
|
"epoch": 2.266825491363907,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044954275707695304,
|
|
"loss": 4.5335,
|
|
"mean_token_accuracy": 0.23787132948637008,
|
|
"num_tokens": 53176496.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.083411502838135,
|
|
"epoch": 2.267421083978559,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044951586342468727,
|
|
"loss": 4.6111,
|
|
"mean_token_accuracy": 0.22669852077960967,
|
|
"num_tokens": 53189916.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.156814193725586,
|
|
"epoch": 2.26801667659321,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004494889635128211,
|
|
"loss": 4.6384,
|
|
"mean_token_accuracy": 0.22002936750650406,
|
|
"num_tokens": 53202080.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.107727527618408,
|
|
"epoch": 2.268612269207862,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044946205734231967,
|
|
"loss": 4.5955,
|
|
"mean_token_accuracy": 0.23259353041648864,
|
|
"num_tokens": 53217887.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.107077884674072,
|
|
"epoch": 2.2692078618225136,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044943514491414783,
|
|
"loss": 4.7,
|
|
"mean_token_accuracy": 0.22741527557373048,
|
|
"num_tokens": 53232331.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.043246603012085,
|
|
"epoch": 2.269803454437165,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044940822622927093,
|
|
"loss": 4.5161,
|
|
"mean_token_accuracy": 0.23351078480482101,
|
|
"num_tokens": 53245292.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.112556076049804,
|
|
"epoch": 2.2703990470518165,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044938130128865456,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.2257265940308571,
|
|
"num_tokens": 53260605.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.105084037780761,
|
|
"epoch": 2.270994639666468,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004493543700932645,
|
|
"loss": 4.5119,
|
|
"mean_token_accuracy": 0.24361786544322966,
|
|
"num_tokens": 53271837.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.140193700790405,
|
|
"epoch": 2.27159023228112,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004493274326440666,
|
|
"loss": 4.6316,
|
|
"mean_token_accuracy": 0.22869040817022324,
|
|
"num_tokens": 53285903.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.148447847366333,
|
|
"epoch": 2.272185824895771,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004493004889420271,
|
|
"loss": 4.619,
|
|
"mean_token_accuracy": 0.23356834203004836,
|
|
"num_tokens": 53301832.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.04939751625061,
|
|
"epoch": 2.272781417510423,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004492735389881125,
|
|
"loss": 4.4765,
|
|
"mean_token_accuracy": 0.2426481381058693,
|
|
"num_tokens": 53315059.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.009445333480835,
|
|
"epoch": 2.2733770101250745,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004492465827832894,
|
|
"loss": 4.5339,
|
|
"mean_token_accuracy": 0.2379133254289627,
|
|
"num_tokens": 53327993.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.061383247375488,
|
|
"epoch": 2.2739726027397262,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044921962032852466,
|
|
"loss": 4.5771,
|
|
"mean_token_accuracy": 0.22894901484251023,
|
|
"num_tokens": 53341306.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.087491893768311,
|
|
"epoch": 2.2745681953543775,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004491926516247854,
|
|
"loss": 4.5498,
|
|
"mean_token_accuracy": 0.23182876408100128,
|
|
"num_tokens": 53354900.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.029242086410522,
|
|
"epoch": 2.275163787969029,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000449165676673039,
|
|
"loss": 4.5532,
|
|
"mean_token_accuracy": 0.23296460509300232,
|
|
"num_tokens": 53367027.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.017651653289795,
|
|
"epoch": 2.275759380583681,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004491386954742529,
|
|
"loss": 4.4989,
|
|
"mean_token_accuracy": 0.2413872703909874,
|
|
"num_tokens": 53381436.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.10001540184021,
|
|
"epoch": 2.276354973198332,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000449111708029395,
|
|
"loss": 4.6149,
|
|
"mean_token_accuracy": 0.23078205138444902,
|
|
"num_tokens": 53394671.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.040878963470459,
|
|
"epoch": 2.276950565812984,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004490847143394332,
|
|
"loss": 4.5691,
|
|
"mean_token_accuracy": 0.23583964258432388,
|
|
"num_tokens": 53407987.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.076965427398681,
|
|
"epoch": 2.2775461584276355,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004490577144053357,
|
|
"loss": 4.5812,
|
|
"mean_token_accuracy": 0.2316889688372612,
|
|
"num_tokens": 53422100.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.135751628875733,
|
|
"epoch": 2.278141751042287,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000449030708228071,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.22605866938829422,
|
|
"num_tokens": 53436815.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.143073797225952,
|
|
"epoch": 2.2787373436569385,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004490036958086078,
|
|
"loss": 4.5906,
|
|
"mean_token_accuracy": 0.23580220490694045,
|
|
"num_tokens": 53450145.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.114277458190918,
|
|
"epoch": 2.27933293627159,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004489766771479148,
|
|
"loss": 4.5982,
|
|
"mean_token_accuracy": 0.22815500646829606,
|
|
"num_tokens": 53463138.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.01121973991394,
|
|
"epoch": 2.279928528886242,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044894965224696144,
|
|
"loss": 4.5202,
|
|
"mean_token_accuracy": 0.2336248442530632,
|
|
"num_tokens": 53478026.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 4.9658561706542965,
|
|
"epoch": 2.2805241215008936,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044892262110671677,
|
|
"loss": 4.484,
|
|
"mean_token_accuracy": 0.24017037749290465,
|
|
"num_tokens": 53492794.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.0634510040283205,
|
|
"epoch": 2.281119714115545,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004488955837281505,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.23724694401025773,
|
|
"num_tokens": 53508334.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.149303913116455,
|
|
"epoch": 2.2817153067301965,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044886854011223234,
|
|
"loss": 4.6508,
|
|
"mean_token_accuracy": 0.2252122074365616,
|
|
"num_tokens": 53521425.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.072942543029785,
|
|
"epoch": 2.282310899344848,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004488414902599323,
|
|
"loss": 4.5919,
|
|
"mean_token_accuracy": 0.23267848938703536,
|
|
"num_tokens": 53536500.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.065595245361328,
|
|
"epoch": 2.2829064919594995,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044881443417222076,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.23571256548166275,
|
|
"num_tokens": 53550147.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.0209966659545895,
|
|
"epoch": 2.283502084574151,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00044878737185006807,
|
|
"loss": 4.557,
|
|
"mean_token_accuracy": 0.2359226867556572,
|
|
"num_tokens": 53565546.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.120116424560547,
|
|
"epoch": 2.284097677188803,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004487603032944448,
|
|
"loss": 4.6283,
|
|
"mean_token_accuracy": 0.2374287411570549,
|
|
"num_tokens": 53578640.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.07807149887085,
|
|
"epoch": 2.2846932698034546,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004487332285063221,
|
|
"loss": 4.5517,
|
|
"mean_token_accuracy": 0.238398040831089,
|
|
"num_tokens": 53594075.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.155978441238403,
|
|
"epoch": 2.2852888624181062,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004487061474866709,
|
|
"loss": 4.682,
|
|
"mean_token_accuracy": 0.22315700203180314,
|
|
"num_tokens": 53608331.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.049230861663818,
|
|
"epoch": 2.2858844550327575,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044867906023646263,
|
|
"loss": 4.5293,
|
|
"mean_token_accuracy": 0.23985606282949448,
|
|
"num_tokens": 53622206.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.060871219635009,
|
|
"epoch": 2.286480047647409,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044865196675666886,
|
|
"loss": 4.5915,
|
|
"mean_token_accuracy": 0.23589107841253282,
|
|
"num_tokens": 53635958.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.098032236099243,
|
|
"epoch": 2.287075640262061,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004486248670482613,
|
|
"loss": 4.5702,
|
|
"mean_token_accuracy": 0.22948090136051177,
|
|
"num_tokens": 53649433.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.0696124076843265,
|
|
"epoch": 2.287671232876712,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00044859776111221217,
|
|
"loss": 4.5342,
|
|
"mean_token_accuracy": 0.23819900751113893,
|
|
"num_tokens": 53663312.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.040183687210083,
|
|
"epoch": 2.288266825491364,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044857064894949356,
|
|
"loss": 4.5258,
|
|
"mean_token_accuracy": 0.2438308760523796,
|
|
"num_tokens": 53677810.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.000240135192871,
|
|
"epoch": 2.2888624181060155,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000448543530561078,
|
|
"loss": 4.513,
|
|
"mean_token_accuracy": 0.24176617115736007,
|
|
"num_tokens": 53693671.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.105381059646606,
|
|
"epoch": 2.2894580107206672,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004485164059479381,
|
|
"loss": 4.6542,
|
|
"mean_token_accuracy": 0.2309111922979355,
|
|
"num_tokens": 53708809.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.07250943183899,
|
|
"epoch": 2.2900536033353185,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044848927511104695,
|
|
"loss": 4.5165,
|
|
"mean_token_accuracy": 0.24432669281959535,
|
|
"num_tokens": 53722680.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.063211393356323,
|
|
"epoch": 2.29064919594997,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044846213805137746,
|
|
"loss": 4.5527,
|
|
"mean_token_accuracy": 0.23229168057441713,
|
|
"num_tokens": 53735857.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.056261157989502,
|
|
"epoch": 2.291244788564622,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044843499476990317,
|
|
"loss": 4.5456,
|
|
"mean_token_accuracy": 0.2325738027691841,
|
|
"num_tokens": 53749447.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.1156669616699215,
|
|
"epoch": 2.2918403811792736,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004484078452675977,
|
|
"loss": 4.6122,
|
|
"mean_token_accuracy": 0.2320915073156357,
|
|
"num_tokens": 53762495.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.067594909667969,
|
|
"epoch": 2.292435973793925,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004483806895454346,
|
|
"loss": 4.5766,
|
|
"mean_token_accuracy": 0.23398135006427764,
|
|
"num_tokens": 53777635.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.061829900741577,
|
|
"epoch": 2.2930315664085765,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004483535276043881,
|
|
"loss": 4.5542,
|
|
"mean_token_accuracy": 0.23661678433418273,
|
|
"num_tokens": 53791089.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.070746612548828,
|
|
"epoch": 2.2936271590232282,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044832635944543243,
|
|
"loss": 4.6389,
|
|
"mean_token_accuracy": 0.229728040099144,
|
|
"num_tokens": 53805875.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.026918363571167,
|
|
"epoch": 2.2942227516378795,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044829918506954214,
|
|
"loss": 4.4854,
|
|
"mean_token_accuracy": 0.23835707306861878,
|
|
"num_tokens": 53821055.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.058599138259888,
|
|
"epoch": 2.294818344252531,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004482720044776918,
|
|
"loss": 4.5903,
|
|
"mean_token_accuracy": 0.22417047321796418,
|
|
"num_tokens": 53836854.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.055183267593383,
|
|
"epoch": 2.295413936867183,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004482448176708563,
|
|
"loss": 4.5739,
|
|
"mean_token_accuracy": 0.23291443437337875,
|
|
"num_tokens": 53851652.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.164247703552246,
|
|
"epoch": 2.2960095294818346,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044821762465001096,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.22655151784420013,
|
|
"num_tokens": 53865359.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.157844495773316,
|
|
"epoch": 2.296605122096486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044819042541613104,
|
|
"loss": 4.6825,
|
|
"mean_token_accuracy": 0.22737330496311187,
|
|
"num_tokens": 53878972.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.094297218322754,
|
|
"epoch": 2.2972007147111375,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004481632199701921,
|
|
"loss": 4.6238,
|
|
"mean_token_accuracy": 0.22500439435243608,
|
|
"num_tokens": 53892717.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.111785888671875,
|
|
"epoch": 2.297796307325789,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044813600831317016,
|
|
"loss": 4.5601,
|
|
"mean_token_accuracy": 0.2333872064948082,
|
|
"num_tokens": 53907880.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.118169736862183,
|
|
"epoch": 2.298391899940441,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044810879044604094,
|
|
"loss": 4.6804,
|
|
"mean_token_accuracy": 0.22692694067955016,
|
|
"num_tokens": 53920776.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.095930051803589,
|
|
"epoch": 2.298987492555092,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00044808156636978085,
|
|
"loss": 4.6429,
|
|
"mean_token_accuracy": 0.22259890884160996,
|
|
"num_tokens": 53935152.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.079894113540649,
|
|
"epoch": 2.299583085169744,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004480543360853665,
|
|
"loss": 4.5564,
|
|
"mean_token_accuracy": 0.22864099740982055,
|
|
"num_tokens": 53947852.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.062316226959228,
|
|
"epoch": 2.3001786777843956,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00044802709959377446,
|
|
"loss": 4.5848,
|
|
"mean_token_accuracy": 0.235524582862854,
|
|
"num_tokens": 53964008.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.109946632385254,
|
|
"epoch": 2.300774270399047,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044799985689598167,
|
|
"loss": 4.5224,
|
|
"mean_token_accuracy": 0.23237295746803283,
|
|
"num_tokens": 53976874.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.051653575897217,
|
|
"epoch": 2.3013698630136985,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044797260799296526,
|
|
"loss": 4.5339,
|
|
"mean_token_accuracy": 0.23407452702522277,
|
|
"num_tokens": 53991501.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.0569833278656,
|
|
"epoch": 2.30196545562835,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044794535288570264,
|
|
"loss": 4.6441,
|
|
"mean_token_accuracy": 0.22894293665885926,
|
|
"num_tokens": 54003841.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.1847496509552,
|
|
"epoch": 2.302561048243002,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004479180915751715,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.22581912577152252,
|
|
"num_tokens": 54017699.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.059309577941894,
|
|
"epoch": 2.3031566408576536,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00044789082406234944,
|
|
"loss": 4.5963,
|
|
"mean_token_accuracy": 0.23204599618911742,
|
|
"num_tokens": 54032715.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.175173616409301,
|
|
"epoch": 2.303752233472305,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004478635503482147,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.21912991553544997,
|
|
"num_tokens": 54046206.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.145601797103882,
|
|
"epoch": 2.3043478260869565,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004478362704337454,
|
|
"loss": 4.6324,
|
|
"mean_token_accuracy": 0.23190165162086487,
|
|
"num_tokens": 54060530.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.0548947811126705,
|
|
"epoch": 2.3049434187016082,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004478089843199202,
|
|
"loss": 4.5272,
|
|
"mean_token_accuracy": 0.23108620643615724,
|
|
"num_tokens": 54076691.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.056315279006958,
|
|
"epoch": 2.3055390113162595,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044778169200771764,
|
|
"loss": 4.5068,
|
|
"mean_token_accuracy": 0.2404621049761772,
|
|
"num_tokens": 54090983.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.097817850112915,
|
|
"epoch": 2.306134603930911,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004477543934981167,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.2313151091337204,
|
|
"num_tokens": 54103458.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.0777841091156,
|
|
"epoch": 2.306730196545563,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044772708879209654,
|
|
"loss": 4.5959,
|
|
"mean_token_accuracy": 0.22722413390874863,
|
|
"num_tokens": 54118032.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.038385581970215,
|
|
"epoch": 2.3073257891602146,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004476997778906366,
|
|
"loss": 4.5324,
|
|
"mean_token_accuracy": 0.24095408469438553,
|
|
"num_tokens": 54132328.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.064468193054199,
|
|
"epoch": 2.307921381774866,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004476724607947164,
|
|
"loss": 4.5207,
|
|
"mean_token_accuracy": 0.23700617700815202,
|
|
"num_tokens": 54146845.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.059358406066894,
|
|
"epoch": 2.3085169743895175,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004476451375053157,
|
|
"loss": 4.5055,
|
|
"mean_token_accuracy": 0.24179990589618683,
|
|
"num_tokens": 54159142.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.050774097442627,
|
|
"epoch": 2.3091125670041692,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004476178080234147,
|
|
"loss": 4.6081,
|
|
"mean_token_accuracy": 0.2344145119190216,
|
|
"num_tokens": 54173634.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.166724348068238,
|
|
"epoch": 2.309708159618821,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044759047234999363,
|
|
"loss": 4.6644,
|
|
"mean_token_accuracy": 0.23158954381942748,
|
|
"num_tokens": 54188384.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.109900760650635,
|
|
"epoch": 2.310303752233472,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004475631304860328,
|
|
"loss": 4.5564,
|
|
"mean_token_accuracy": 0.23068079650402068,
|
|
"num_tokens": 54200543.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.071242475509644,
|
|
"epoch": 2.310899344848124,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044753578243251314,
|
|
"loss": 4.5967,
|
|
"mean_token_accuracy": 0.22834558337926864,
|
|
"num_tokens": 54213043.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.088108110427856,
|
|
"epoch": 2.3114949374627756,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044750842819041547,
|
|
"loss": 4.6337,
|
|
"mean_token_accuracy": 0.22330473363399506,
|
|
"num_tokens": 54227607.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.1178923606872555,
|
|
"epoch": 2.312090530077427,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044748106776072103,
|
|
"loss": 4.657,
|
|
"mean_token_accuracy": 0.2322338655591011,
|
|
"num_tokens": 54242593.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.160980463027954,
|
|
"epoch": 2.3126861226920785,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044745370114441103,
|
|
"loss": 4.694,
|
|
"mean_token_accuracy": 0.2224160075187683,
|
|
"num_tokens": 54256466.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.063320922851562,
|
|
"epoch": 2.31328171530673,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044742632834246716,
|
|
"loss": 4.522,
|
|
"mean_token_accuracy": 0.24755734354257583,
|
|
"num_tokens": 54269622.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 4.968282747268677,
|
|
"epoch": 2.313877307921382,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00044739894935587126,
|
|
"loss": 4.5034,
|
|
"mean_token_accuracy": 0.23960719555616378,
|
|
"num_tokens": 54285317.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.144816589355469,
|
|
"epoch": 2.314472900536033,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044737156418560536,
|
|
"loss": 4.719,
|
|
"mean_token_accuracy": 0.22219311743974685,
|
|
"num_tokens": 54300146.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.077959871292114,
|
|
"epoch": 2.315068493150685,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004473441728326518,
|
|
"loss": 4.4824,
|
|
"mean_token_accuracy": 0.23747051805257796,
|
|
"num_tokens": 54314292.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.02169361114502,
|
|
"epoch": 2.3156640857653366,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044731677529799286,
|
|
"loss": 4.5059,
|
|
"mean_token_accuracy": 0.23761115968227386,
|
|
"num_tokens": 54327344.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.099502849578857,
|
|
"epoch": 2.3162596783799883,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004472893715826114,
|
|
"loss": 4.62,
|
|
"mean_token_accuracy": 0.22760480642318726,
|
|
"num_tokens": 54341551.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.053305053710938,
|
|
"epoch": 2.3168552709946395,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004472619616874903,
|
|
"loss": 4.5327,
|
|
"mean_token_accuracy": 0.23316018879413605,
|
|
"num_tokens": 54356370.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.114757108688354,
|
|
"epoch": 2.317450863609291,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004472345456136127,
|
|
"loss": 4.6299,
|
|
"mean_token_accuracy": 0.22985255271196364,
|
|
"num_tokens": 54371147.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.063430070877075,
|
|
"epoch": 2.318046456223943,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044720712336196195,
|
|
"loss": 4.5757,
|
|
"mean_token_accuracy": 0.23767773061990738,
|
|
"num_tokens": 54385410.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.121000671386719,
|
|
"epoch": 2.3186420488385946,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004471796949335217,
|
|
"loss": 4.5953,
|
|
"mean_token_accuracy": 0.22775168418884278,
|
|
"num_tokens": 54398872.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.134946537017822,
|
|
"epoch": 2.319237641453246,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00044715226032927585,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.2219112530350685,
|
|
"num_tokens": 54414563.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.136515045166016,
|
|
"epoch": 2.3198332340678975,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004471248195502082,
|
|
"loss": 4.6755,
|
|
"mean_token_accuracy": 0.2225308820605278,
|
|
"num_tokens": 54428630.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.059210014343262,
|
|
"epoch": 2.3204288266825492,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044709737259730314,
|
|
"loss": 4.5278,
|
|
"mean_token_accuracy": 0.23735435009002687,
|
|
"num_tokens": 54443095.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.0593877792358395,
|
|
"epoch": 2.321024419297201,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004470699194715452,
|
|
"loss": 4.5066,
|
|
"mean_token_accuracy": 0.23678527325391768,
|
|
"num_tokens": 54458000.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.074975824356079,
|
|
"epoch": 2.321620011911852,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044704246017391897,
|
|
"loss": 4.5641,
|
|
"mean_token_accuracy": 0.22753656953573226,
|
|
"num_tokens": 54471383.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.056534242630005,
|
|
"epoch": 2.322215604526504,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004470149947054095,
|
|
"loss": 4.6192,
|
|
"mean_token_accuracy": 0.23454184085130692,
|
|
"num_tokens": 54483466.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.098339939117432,
|
|
"epoch": 2.3228111971411556,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044698752306700175,
|
|
"loss": 4.5569,
|
|
"mean_token_accuracy": 0.2240780159831047,
|
|
"num_tokens": 54499004.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.08621768951416,
|
|
"epoch": 2.323406789755807,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004469600452596812,
|
|
"loss": 4.5896,
|
|
"mean_token_accuracy": 0.2285356491804123,
|
|
"num_tokens": 54514165.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.113810443878174,
|
|
"epoch": 2.3240023823704585,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044693256128443336,
|
|
"loss": 4.6008,
|
|
"mean_token_accuracy": 0.23478385508060456,
|
|
"num_tokens": 54528512.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.093349599838257,
|
|
"epoch": 2.3245979749851102,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004469050711422442,
|
|
"loss": 4.5724,
|
|
"mean_token_accuracy": 0.2364364594221115,
|
|
"num_tokens": 54543289.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.049811601638794,
|
|
"epoch": 2.325193567599762,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.00044687757483409963,
|
|
"loss": 4.5065,
|
|
"mean_token_accuracy": 0.23610431402921678,
|
|
"num_tokens": 54558257.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.082894945144654,
|
|
"epoch": 2.325789160214413,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004468500723609859,
|
|
"loss": 4.5283,
|
|
"mean_token_accuracy": 0.23933172076940537,
|
|
"num_tokens": 54573842.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.085173034667969,
|
|
"epoch": 2.326384752829065,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004468225637238894,
|
|
"loss": 4.6109,
|
|
"mean_token_accuracy": 0.23079707771539687,
|
|
"num_tokens": 54590513.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.1391619682312015,
|
|
"epoch": 2.3269803454437166,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000446795048923797,
|
|
"loss": 4.6469,
|
|
"mean_token_accuracy": 0.23104346841573714,
|
|
"num_tokens": 54603940.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.051429748535156,
|
|
"epoch": 2.3275759380583683,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004467675279616955,
|
|
"loss": 4.5304,
|
|
"mean_token_accuracy": 0.23799682706594466,
|
|
"num_tokens": 54618031.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.133725786209107,
|
|
"epoch": 2.3281715306730195,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044674000083857205,
|
|
"loss": 4.6535,
|
|
"mean_token_accuracy": 0.22462476193904876,
|
|
"num_tokens": 54631228.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.142106676101685,
|
|
"epoch": 2.328767123287671,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044671246755541397,
|
|
"loss": 4.6885,
|
|
"mean_token_accuracy": 0.22380707710981368,
|
|
"num_tokens": 54645220.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.029877710342407,
|
|
"epoch": 2.329362715902323,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004466849281132089,
|
|
"loss": 4.4589,
|
|
"mean_token_accuracy": 0.24596380144357682,
|
|
"num_tokens": 54658039.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.086935806274414,
|
|
"epoch": 2.329958308516974,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004466573825129446,
|
|
"loss": 4.5569,
|
|
"mean_token_accuracy": 0.23206789195537567,
|
|
"num_tokens": 54670084.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.0120710849761965,
|
|
"epoch": 2.330553901131626,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044662983075560904,
|
|
"loss": 4.5149,
|
|
"mean_token_accuracy": 0.2361779659986496,
|
|
"num_tokens": 54682217.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.060960483551026,
|
|
"epoch": 2.3311494937462776,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044660227284219056,
|
|
"loss": 4.5626,
|
|
"mean_token_accuracy": 0.23274201154708862,
|
|
"num_tokens": 54695532.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.0806605339050295,
|
|
"epoch": 2.3317450863609293,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004465747087736775,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.23228947073221207,
|
|
"num_tokens": 54710650.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.0372837543487545,
|
|
"epoch": 2.332340678975581,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00044654713855105864,
|
|
"loss": 4.5581,
|
|
"mean_token_accuracy": 0.23111099004745483,
|
|
"num_tokens": 54726872.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.074177312850952,
|
|
"epoch": 2.332936271590232,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004465195621753229,
|
|
"loss": 4.532,
|
|
"mean_token_accuracy": 0.2396409183740616,
|
|
"num_tokens": 54741606.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.013687419891357,
|
|
"epoch": 2.333531864204884,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044649197964745927,
|
|
"loss": 4.5356,
|
|
"mean_token_accuracy": 0.23190334737300872,
|
|
"num_tokens": 54758674.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.035836315155029,
|
|
"epoch": 2.3341274568195356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004464643909684571,
|
|
"loss": 4.4834,
|
|
"mean_token_accuracy": 0.24914540350437164,
|
|
"num_tokens": 54771079.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.078677749633789,
|
|
"epoch": 2.334723049434187,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004464367961393061,
|
|
"loss": 4.5206,
|
|
"mean_token_accuracy": 0.23745046257972718,
|
|
"num_tokens": 54785286.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.022913646697998,
|
|
"epoch": 2.3353186420488385,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004464091951609959,
|
|
"loss": 4.5583,
|
|
"mean_token_accuracy": 0.23882507532835007,
|
|
"num_tokens": 54798634.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.043626070022583,
|
|
"epoch": 2.3359142346634902,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004463815880345166,
|
|
"loss": 4.5665,
|
|
"mean_token_accuracy": 0.23188290297985076,
|
|
"num_tokens": 54811166.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.08647518157959,
|
|
"epoch": 2.336509827278142,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044635397476085843,
|
|
"loss": 4.531,
|
|
"mean_token_accuracy": 0.23475041836500168,
|
|
"num_tokens": 54825052.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.119930124282837,
|
|
"epoch": 2.337105419892793,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044632635534101175,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.2334539994597435,
|
|
"num_tokens": 54839613.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.071180438995361,
|
|
"epoch": 2.337701012507445,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044629872977596717,
|
|
"loss": 4.5756,
|
|
"mean_token_accuracy": 0.23602954894304276,
|
|
"num_tokens": 54852127.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 4.978808164596558,
|
|
"epoch": 2.3382966051220966,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004462710980667158,
|
|
"loss": 4.4583,
|
|
"mean_token_accuracy": 0.24644404351711274,
|
|
"num_tokens": 54865632.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.037345457077026,
|
|
"epoch": 2.3388921977367483,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004462434602142486,
|
|
"loss": 4.6034,
|
|
"mean_token_accuracy": 0.23168475478887557,
|
|
"num_tokens": 54880309.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.072272205352784,
|
|
"epoch": 2.3394877903513995,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044621581621955686,
|
|
"loss": 4.5533,
|
|
"mean_token_accuracy": 0.23798981606960296,
|
|
"num_tokens": 54893696.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.101032638549805,
|
|
"epoch": 2.3400833829660512,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004461881660836322,
|
|
"loss": 4.6064,
|
|
"mean_token_accuracy": 0.23122487217187881,
|
|
"num_tokens": 54908755.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.031666707992554,
|
|
"epoch": 2.340678975580703,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044616050980746634,
|
|
"loss": 4.5144,
|
|
"mean_token_accuracy": 0.2346455931663513,
|
|
"num_tokens": 54922765.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.081279230117798,
|
|
"epoch": 2.341274568195354,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044613284739205124,
|
|
"loss": 4.6114,
|
|
"mean_token_accuracy": 0.23260679692029954,
|
|
"num_tokens": 54937380.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.090221929550171,
|
|
"epoch": 2.341870160810006,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044610517883837924,
|
|
"loss": 4.6114,
|
|
"mean_token_accuracy": 0.23495318591594697,
|
|
"num_tokens": 54952568.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.107948923110962,
|
|
"epoch": 2.3424657534246576,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004460775041474426,
|
|
"loss": 4.6126,
|
|
"mean_token_accuracy": 0.2298486724495888,
|
|
"num_tokens": 54965380.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.047975969314575,
|
|
"epoch": 2.3430613460393093,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004460498233202341,
|
|
"loss": 4.5249,
|
|
"mean_token_accuracy": 0.23900175243616104,
|
|
"num_tokens": 54979038.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.045284223556519,
|
|
"epoch": 2.3436569386539605,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004460221363577465,
|
|
"loss": 4.6219,
|
|
"mean_token_accuracy": 0.22606783509254455,
|
|
"num_tokens": 54995644.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.050836277008057,
|
|
"epoch": 2.344252531268612,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044599444326097297,
|
|
"loss": 4.5636,
|
|
"mean_token_accuracy": 0.23729010075330734,
|
|
"num_tokens": 55010334.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.12149453163147,
|
|
"epoch": 2.344848123883264,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044596674403090677,
|
|
"loss": 4.6017,
|
|
"mean_token_accuracy": 0.2347991168498993,
|
|
"num_tokens": 55022635.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.052515459060669,
|
|
"epoch": 2.3454437164979156,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004459390386685414,
|
|
"loss": 4.5271,
|
|
"mean_token_accuracy": 0.2401259124279022,
|
|
"num_tokens": 55035337.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.0760032653808596,
|
|
"epoch": 2.346039309112567,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004459113271748707,
|
|
"loss": 4.6216,
|
|
"mean_token_accuracy": 0.2251528412103653,
|
|
"num_tokens": 55049144.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.125048446655273,
|
|
"epoch": 2.3466349017272186,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004458836095508886,
|
|
"loss": 4.6341,
|
|
"mean_token_accuracy": 0.22483593374490737,
|
|
"num_tokens": 55063071.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.060525274276733,
|
|
"epoch": 2.3472304943418703,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004458558857975892,
|
|
"loss": 4.4975,
|
|
"mean_token_accuracy": 0.24330146312713624,
|
|
"num_tokens": 55076678.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.094007396697998,
|
|
"epoch": 2.3478260869565215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000445828155915967,
|
|
"loss": 4.5568,
|
|
"mean_token_accuracy": 0.23273534178733826,
|
|
"num_tokens": 55088485.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.088552951812744,
|
|
"epoch": 2.348421679571173,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044580041990701654,
|
|
"loss": 4.6126,
|
|
"mean_token_accuracy": 0.22912203073501586,
|
|
"num_tokens": 55101515.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.142376661300659,
|
|
"epoch": 2.349017272185825,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004457726777717328,
|
|
"loss": 4.6027,
|
|
"mean_token_accuracy": 0.23321468532085418,
|
|
"num_tokens": 55113777.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.0936079025268555,
|
|
"epoch": 2.3496128648004766,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004457449295111108,
|
|
"loss": 4.5525,
|
|
"mean_token_accuracy": 0.23659100830554963,
|
|
"num_tokens": 55127537.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.086538648605346,
|
|
"epoch": 2.3502084574151283,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044571717512614567,
|
|
"loss": 4.6566,
|
|
"mean_token_accuracy": 0.23162892311811448,
|
|
"num_tokens": 55141172.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.028966903686523,
|
|
"epoch": 2.3508040500297795,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004456894146178331,
|
|
"loss": 4.564,
|
|
"mean_token_accuracy": 0.235654017329216,
|
|
"num_tokens": 55155661.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.0740499019622805,
|
|
"epoch": 2.3513996426444312,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004456616479871687,
|
|
"loss": 4.5988,
|
|
"mean_token_accuracy": 0.228631192445755,
|
|
"num_tokens": 55169421.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.1049569606781,
|
|
"epoch": 2.351995235259083,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044563387523514854,
|
|
"loss": 4.595,
|
|
"mean_token_accuracy": 0.2304403841495514,
|
|
"num_tokens": 55182809.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.091424036026001,
|
|
"epoch": 2.352590827873734,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004456060963627687,
|
|
"loss": 4.6186,
|
|
"mean_token_accuracy": 0.23366935551166534,
|
|
"num_tokens": 55195257.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.021163654327393,
|
|
"epoch": 2.353186420488386,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044557831137102556,
|
|
"loss": 4.4757,
|
|
"mean_token_accuracy": 0.23961297273635865,
|
|
"num_tokens": 55207930.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.06404447555542,
|
|
"epoch": 2.3537820131030376,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044555052026091574,
|
|
"loss": 4.5674,
|
|
"mean_token_accuracy": 0.23963918387889863,
|
|
"num_tokens": 55220764.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.0206746578216555,
|
|
"epoch": 2.3543776057176893,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044552272303343603,
|
|
"loss": 4.4587,
|
|
"mean_token_accuracy": 0.24180100560188295,
|
|
"num_tokens": 55233357.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.058024835586548,
|
|
"epoch": 2.3549731983323405,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044549491968958355,
|
|
"loss": 4.5477,
|
|
"mean_token_accuracy": 0.2294281914830208,
|
|
"num_tokens": 55246809.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.028335809707642,
|
|
"epoch": 2.3555687909469922,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044546711023035545,
|
|
"loss": 4.4762,
|
|
"mean_token_accuracy": 0.24142054468393326,
|
|
"num_tokens": 55262060.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.1298106670379635,
|
|
"epoch": 2.356164383561644,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044543929465674925,
|
|
"loss": 4.5368,
|
|
"mean_token_accuracy": 0.2351163759827614,
|
|
"num_tokens": 55275714.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.032845783233642,
|
|
"epoch": 2.3567599761762956,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044541147296976274,
|
|
"loss": 4.4705,
|
|
"mean_token_accuracy": 0.2462046280503273,
|
|
"num_tokens": 55289299.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.020444536209107,
|
|
"epoch": 2.357355568790947,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004453836451703937,
|
|
"loss": 4.5661,
|
|
"mean_token_accuracy": 0.22995360046625138,
|
|
"num_tokens": 55302991.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.0585071563720705,
|
|
"epoch": 2.3579511614055986,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044535581125964045,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.22756482809782028,
|
|
"num_tokens": 55315907.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.080620670318604,
|
|
"epoch": 2.3585467540202503,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004453279712385011,
|
|
"loss": 4.6178,
|
|
"mean_token_accuracy": 0.23361134380102158,
|
|
"num_tokens": 55330364.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.091986131668091,
|
|
"epoch": 2.3591423466349015,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044530012510797447,
|
|
"loss": 4.5532,
|
|
"mean_token_accuracy": 0.23899431377649308,
|
|
"num_tokens": 55344731.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.082302570343018,
|
|
"epoch": 2.359737939249553,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044527227286905914,
|
|
"loss": 4.5109,
|
|
"mean_token_accuracy": 0.24238798320293425,
|
|
"num_tokens": 55358310.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.079770946502686,
|
|
"epoch": 2.360333531864205,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044524441452275425,
|
|
"loss": 4.5433,
|
|
"mean_token_accuracy": 0.2364349454641342,
|
|
"num_tokens": 55372277.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.0973954677581785,
|
|
"epoch": 2.3609291244788566,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044521655007005907,
|
|
"loss": 4.5764,
|
|
"mean_token_accuracy": 0.23555588722229004,
|
|
"num_tokens": 55386728.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 4.971767616271973,
|
|
"epoch": 2.361524717093508,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044518867951197296,
|
|
"loss": 4.4332,
|
|
"mean_token_accuracy": 0.2441408097743988,
|
|
"num_tokens": 55400542.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.008729457855225,
|
|
"epoch": 2.3621203097081596,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004451608028494956,
|
|
"loss": 4.5295,
|
|
"mean_token_accuracy": 0.23864567130804062,
|
|
"num_tokens": 55413216.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 4.942079067230225,
|
|
"epoch": 2.3627159023228113,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044513292008362696,
|
|
"loss": 4.3849,
|
|
"mean_token_accuracy": 0.24811531454324723,
|
|
"num_tokens": 55426969.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.062953186035156,
|
|
"epoch": 2.363311494937463,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004451050312153671,
|
|
"loss": 4.5095,
|
|
"mean_token_accuracy": 0.24043276458978652,
|
|
"num_tokens": 55441141.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.033006238937378,
|
|
"epoch": 2.363907087552114,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044507713624571626,
|
|
"loss": 4.5045,
|
|
"mean_token_accuracy": 0.23843698650598527,
|
|
"num_tokens": 55456082.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.060943460464477,
|
|
"epoch": 2.364502680166766,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044504923517567515,
|
|
"loss": 4.5791,
|
|
"mean_token_accuracy": 0.2320140078663826,
|
|
"num_tokens": 55469763.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.11803092956543,
|
|
"epoch": 2.3650982727814176,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004450213280062444,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.22270302325487137,
|
|
"num_tokens": 55484386.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.094095373153687,
|
|
"epoch": 2.365693865396069,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004449934147384251,
|
|
"loss": 4.5844,
|
|
"mean_token_accuracy": 0.23609329462051393,
|
|
"num_tokens": 55498674.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.1258628368377686,
|
|
"epoch": 2.3662894580107205,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004449654953732183,
|
|
"loss": 4.6649,
|
|
"mean_token_accuracy": 0.23455294519662856,
|
|
"num_tokens": 55510088.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.070241641998291,
|
|
"epoch": 2.3668850506253722,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004449375699116257,
|
|
"loss": 4.5697,
|
|
"mean_token_accuracy": 0.23201158195734023,
|
|
"num_tokens": 55524020.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 4.983276891708374,
|
|
"epoch": 2.367480643240024,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004449096383546487,
|
|
"loss": 4.4127,
|
|
"mean_token_accuracy": 0.239760060608387,
|
|
"num_tokens": 55536534.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 4.9705760955810545,
|
|
"epoch": 2.3680762358546756,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004448817007032892,
|
|
"loss": 4.4635,
|
|
"mean_token_accuracy": 0.24368521422147751,
|
|
"num_tokens": 55550928.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.061886596679687,
|
|
"epoch": 2.368671828469327,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044485375695854927,
|
|
"loss": 4.5463,
|
|
"mean_token_accuracy": 0.22998583763837815,
|
|
"num_tokens": 55564728.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.125076580047607,
|
|
"epoch": 2.3692674210839786,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00044482580712143136,
|
|
"loss": 4.59,
|
|
"mean_token_accuracy": 0.22764191925525665,
|
|
"num_tokens": 55579933.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.036573266983032,
|
|
"epoch": 2.3698630136986303,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044479785119293783,
|
|
"loss": 4.5758,
|
|
"mean_token_accuracy": 0.23779261410236358,
|
|
"num_tokens": 55593013.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.061506128311157,
|
|
"epoch": 2.3704586063132815,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044476988917407136,
|
|
"loss": 4.5573,
|
|
"mean_token_accuracy": 0.2390846148133278,
|
|
"num_tokens": 55606520.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.145701742172241,
|
|
"epoch": 2.3710541989279332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004447419210658351,
|
|
"loss": 4.5471,
|
|
"mean_token_accuracy": 0.23317745476961135,
|
|
"num_tokens": 55620021.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.086800909042358,
|
|
"epoch": 2.371649791542585,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044471394686923206,
|
|
"loss": 4.5544,
|
|
"mean_token_accuracy": 0.23897402882575988,
|
|
"num_tokens": 55633800.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 4.989410018920898,
|
|
"epoch": 2.3722453841572366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044468596658526566,
|
|
"loss": 4.5508,
|
|
"mean_token_accuracy": 0.23677262365818025,
|
|
"num_tokens": 55649466.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.07503342628479,
|
|
"epoch": 2.372840976771888,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004446579802149396,
|
|
"loss": 4.6387,
|
|
"mean_token_accuracy": 0.2306916281580925,
|
|
"num_tokens": 55664613.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.096070289611816,
|
|
"epoch": 2.3734365693865396,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044462998775925757,
|
|
"loss": 4.5688,
|
|
"mean_token_accuracy": 0.24035333544015886,
|
|
"num_tokens": 55679768.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.067763566970825,
|
|
"epoch": 2.3740321620011913,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004446019892192237,
|
|
"loss": 4.4936,
|
|
"mean_token_accuracy": 0.23959020525217056,
|
|
"num_tokens": 55693572.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.025058937072754,
|
|
"epoch": 2.374627754615843,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004445739845958423,
|
|
"loss": 4.5653,
|
|
"mean_token_accuracy": 0.23669537007808686,
|
|
"num_tokens": 55708095.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.077809810638428,
|
|
"epoch": 2.375223347230494,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004445459738901177,
|
|
"loss": 4.5725,
|
|
"mean_token_accuracy": 0.22821950763463975,
|
|
"num_tokens": 55721685.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.062441062927246,
|
|
"epoch": 2.375818939845146,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044451795710305476,
|
|
"loss": 4.5399,
|
|
"mean_token_accuracy": 0.2281383231282234,
|
|
"num_tokens": 55733476.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.066604328155518,
|
|
"epoch": 2.3764145324597976,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00044448993423565824,
|
|
"loss": 4.5511,
|
|
"mean_token_accuracy": 0.2374675914645195,
|
|
"num_tokens": 55746325.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.110773515701294,
|
|
"epoch": 2.377010125074449,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004444619052889334,
|
|
"loss": 4.6572,
|
|
"mean_token_accuracy": 0.22847194373607635,
|
|
"num_tokens": 55760643.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.1512572288513185,
|
|
"epoch": 2.3776057176891006,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004444338702638855,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.22378394156694412,
|
|
"num_tokens": 55774569.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.071790552139282,
|
|
"epoch": 2.3782013103037523,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004444058291615202,
|
|
"loss": 4.5737,
|
|
"mean_token_accuracy": 0.23068513423204423,
|
|
"num_tokens": 55789289.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.122916173934937,
|
|
"epoch": 2.378796902918404,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004443777819828432,
|
|
"loss": 4.6132,
|
|
"mean_token_accuracy": 0.23188162595033646,
|
|
"num_tokens": 55802450.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.078219890594482,
|
|
"epoch": 2.379392495533055,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004443497287288606,
|
|
"loss": 4.5353,
|
|
"mean_token_accuracy": 0.23669990450143813,
|
|
"num_tokens": 55815112.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.083079767227173,
|
|
"epoch": 2.379988088147707,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044432166940057855,
|
|
"loss": 4.529,
|
|
"mean_token_accuracy": 0.2389659732580185,
|
|
"num_tokens": 55829140.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.078144884109497,
|
|
"epoch": 2.3805836807623586,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044429360399900355,
|
|
"loss": 4.6118,
|
|
"mean_token_accuracy": 0.22400336861610412,
|
|
"num_tokens": 55843164.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.061775588989258,
|
|
"epoch": 2.3811792733770103,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004442655325251422,
|
|
"loss": 4.5767,
|
|
"mean_token_accuracy": 0.23484386801719664,
|
|
"num_tokens": 55856634.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.019436979293824,
|
|
"epoch": 2.3817748659916615,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004442374549800014,
|
|
"loss": 4.5506,
|
|
"mean_token_accuracy": 0.23080208152532578,
|
|
"num_tokens": 55871810.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.150190210342407,
|
|
"epoch": 2.3823704586063132,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044420937136458827,
|
|
"loss": 4.6459,
|
|
"mean_token_accuracy": 0.22450108230113983,
|
|
"num_tokens": 55886274.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.091080570220948,
|
|
"epoch": 2.382966051220965,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004441812816799101,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.22899341434240342,
|
|
"num_tokens": 55899858.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.0810832500457765,
|
|
"epoch": 2.383561643835616,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004441531859269745,
|
|
"loss": 4.5573,
|
|
"mean_token_accuracy": 0.23884093165397643,
|
|
"num_tokens": 55913720.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.03473129272461,
|
|
"epoch": 2.384157236450268,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000444125084106789,
|
|
"loss": 4.4981,
|
|
"mean_token_accuracy": 0.23246958404779433,
|
|
"num_tokens": 55927169.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.094771909713745,
|
|
"epoch": 2.3847528290649196,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004440969762203618,
|
|
"loss": 4.5594,
|
|
"mean_token_accuracy": 0.23796003460884094,
|
|
"num_tokens": 55939317.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.033287906646729,
|
|
"epoch": 2.3853484216795713,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000444068862268701,
|
|
"loss": 4.5309,
|
|
"mean_token_accuracy": 0.23167342841625213,
|
|
"num_tokens": 55952185.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.085063314437866,
|
|
"epoch": 2.385944014294223,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000444040742252815,
|
|
"loss": 4.5614,
|
|
"mean_token_accuracy": 0.23602416068315507,
|
|
"num_tokens": 55966406.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.1299680233001705,
|
|
"epoch": 2.3865396069088742,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044401261617371234,
|
|
"loss": 4.6231,
|
|
"mean_token_accuracy": 0.22671091109514235,
|
|
"num_tokens": 55980929.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 4.971714496612549,
|
|
"epoch": 2.387135199523526,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00044398448403240213,
|
|
"loss": 4.4152,
|
|
"mean_token_accuracy": 0.2457886040210724,
|
|
"num_tokens": 55995056.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.034382295608521,
|
|
"epoch": 2.3877307921381776,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044395634582989306,
|
|
"loss": 4.5333,
|
|
"mean_token_accuracy": 0.24048662185668945,
|
|
"num_tokens": 56008030.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.040601062774658,
|
|
"epoch": 2.388326384752829,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004439282015671946,
|
|
"loss": 4.4983,
|
|
"mean_token_accuracy": 0.23918453603982925,
|
|
"num_tokens": 56021101.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.0438028335571286,
|
|
"epoch": 2.3889219773674806,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00044390005124531626,
|
|
"loss": 4.5478,
|
|
"mean_token_accuracy": 0.2399110570549965,
|
|
"num_tokens": 56036154.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.0035071849823,
|
|
"epoch": 2.3895175699821323,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004438718948652676,
|
|
"loss": 4.52,
|
|
"mean_token_accuracy": 0.24302373230457305,
|
|
"num_tokens": 56051849.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.122143411636353,
|
|
"epoch": 2.390113162596784,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004438437324280587,
|
|
"loss": 4.5893,
|
|
"mean_token_accuracy": 0.23744116574525834,
|
|
"num_tokens": 56064970.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.150155019760132,
|
|
"epoch": 2.390708755211435,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004438155639346997,
|
|
"loss": 4.6148,
|
|
"mean_token_accuracy": 0.23284883052110672,
|
|
"num_tokens": 56077576.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.054148483276367,
|
|
"epoch": 2.391304347826087,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004437873893862008,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.24218623340129852,
|
|
"num_tokens": 56091035.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.058997726440429,
|
|
"epoch": 2.3918999404407386,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044375920878357274,
|
|
"loss": 4.5971,
|
|
"mean_token_accuracy": 0.2330559641122818,
|
|
"num_tokens": 56106178.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.064040756225586,
|
|
"epoch": 2.3924955330553903,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004437310221278262,
|
|
"loss": 4.607,
|
|
"mean_token_accuracy": 0.2286352649331093,
|
|
"num_tokens": 56120045.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.087781763076782,
|
|
"epoch": 2.3930911256700416,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004437028294199723,
|
|
"loss": 4.6362,
|
|
"mean_token_accuracy": 0.22870297133922576,
|
|
"num_tokens": 56133710.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.069624137878418,
|
|
"epoch": 2.3936867182846933,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044367463066102207,
|
|
"loss": 4.5978,
|
|
"mean_token_accuracy": 0.23135696947574616,
|
|
"num_tokens": 56146863.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.149431943893433,
|
|
"epoch": 2.394282310899345,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004436464258519872,
|
|
"loss": 4.6555,
|
|
"mean_token_accuracy": 0.22453474402427673,
|
|
"num_tokens": 56161897.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.076029062271118,
|
|
"epoch": 2.394877903513996,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004436182149938792,
|
|
"loss": 4.5918,
|
|
"mean_token_accuracy": 0.22813937664031983,
|
|
"num_tokens": 56176253.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.084535551071167,
|
|
"epoch": 2.395473496128648,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00044358999808771007,
|
|
"loss": 4.5646,
|
|
"mean_token_accuracy": 0.2379052072763443,
|
|
"num_tokens": 56190794.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.0848325252532955,
|
|
"epoch": 2.3960690887432996,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004435617751344917,
|
|
"loss": 4.5324,
|
|
"mean_token_accuracy": 0.23813031166791915,
|
|
"num_tokens": 56203879.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.096937036514282,
|
|
"epoch": 2.3966646813579513,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004435335461352366,
|
|
"loss": 4.6246,
|
|
"mean_token_accuracy": 0.2256928488612175,
|
|
"num_tokens": 56218481.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.07773756980896,
|
|
"epoch": 2.3972602739726026,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004435053110909572,
|
|
"loss": 4.6115,
|
|
"mean_token_accuracy": 0.22781467586755752,
|
|
"num_tokens": 56233338.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.037910127639771,
|
|
"epoch": 2.3978558665872542,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044347707000266627,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.2344769924879074,
|
|
"num_tokens": 56245839.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.061928558349609,
|
|
"epoch": 2.398451459201906,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044344882287137676,
|
|
"loss": 4.532,
|
|
"mean_token_accuracy": 0.23268016427755356,
|
|
"num_tokens": 56259592.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.0639289855957035,
|
|
"epoch": 2.3990470518165576,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004434205696981018,
|
|
"loss": 4.5824,
|
|
"mean_token_accuracy": 0.22800221145153046,
|
|
"num_tokens": 56273891.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.054754734039307,
|
|
"epoch": 2.399642644431209,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00044339231048385485,
|
|
"loss": 4.5344,
|
|
"mean_token_accuracy": 0.2337525635957718,
|
|
"num_tokens": 56290135.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.083070611953735,
|
|
"epoch": 2.4002382370458606,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044336404522964963,
|
|
"loss": 4.5453,
|
|
"mean_token_accuracy": 0.23038324266672133,
|
|
"num_tokens": 56305041.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.128826761245728,
|
|
"epoch": 2.4008338296605123,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004433357739364998,
|
|
"loss": 4.6313,
|
|
"mean_token_accuracy": 0.22527991682291032,
|
|
"num_tokens": 56319983.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.056576585769653,
|
|
"epoch": 2.4014294222751635,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00044330749660541943,
|
|
"loss": 4.5188,
|
|
"mean_token_accuracy": 0.23818998485803605,
|
|
"num_tokens": 56333647.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.039674758911133,
|
|
"epoch": 2.4020250148898152,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044327921323742276,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.23664844036102295,
|
|
"num_tokens": 56345709.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.148887872695923,
|
|
"epoch": 2.402620607504467,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044325092383352434,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.2338250994682312,
|
|
"num_tokens": 56358102.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.091456747055053,
|
|
"epoch": 2.4032162001191186,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004432226283947388,
|
|
"loss": 4.5863,
|
|
"mean_token_accuracy": 0.23065387904644014,
|
|
"num_tokens": 56370338.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.129602670669556,
|
|
"epoch": 2.4038117927337703,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044319432692208115,
|
|
"loss": 4.6471,
|
|
"mean_token_accuracy": 0.2291956514120102,
|
|
"num_tokens": 56384574.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.068959045410156,
|
|
"epoch": 2.4044073853484216,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00044316601941656655,
|
|
"loss": 4.5638,
|
|
"mean_token_accuracy": 0.23288798928260804,
|
|
"num_tokens": 56400269.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.071285438537598,
|
|
"epoch": 2.4050029779630733,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004431377058792101,
|
|
"loss": 4.5284,
|
|
"mean_token_accuracy": 0.24059825837612153,
|
|
"num_tokens": 56414514.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.139170551300049,
|
|
"epoch": 2.405598570577725,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004431093863110276,
|
|
"loss": 4.6426,
|
|
"mean_token_accuracy": 0.23124519735574722,
|
|
"num_tokens": 56427754.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.015479516983032,
|
|
"epoch": 2.4061941631923762,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004430810607130347,
|
|
"loss": 4.472,
|
|
"mean_token_accuracy": 0.24299398064613342,
|
|
"num_tokens": 56441622.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.14301381111145,
|
|
"epoch": 2.406789755807028,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044305272908624747,
|
|
"loss": 4.6769,
|
|
"mean_token_accuracy": 0.22027444690465928,
|
|
"num_tokens": 56454238.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.103564834594726,
|
|
"epoch": 2.4073853484216796,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044302439143168213,
|
|
"loss": 4.5565,
|
|
"mean_token_accuracy": 0.23115642368793488,
|
|
"num_tokens": 56468222.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.103624296188355,
|
|
"epoch": 2.4079809410363313,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044299604775035497,
|
|
"loss": 4.5849,
|
|
"mean_token_accuracy": 0.23100200146436692,
|
|
"num_tokens": 56482824.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.066068267822265,
|
|
"epoch": 2.4085765336509826,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044296769804328274,
|
|
"loss": 4.6192,
|
|
"mean_token_accuracy": 0.23517584204673767,
|
|
"num_tokens": 56496910.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.163017082214355,
|
|
"epoch": 2.4091721262656343,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004429393423114824,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.2212651327252388,
|
|
"num_tokens": 56509603.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.044951772689819,
|
|
"epoch": 2.409767718880286,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044291098055597076,
|
|
"loss": 4.5318,
|
|
"mean_token_accuracy": 0.22909082174301149,
|
|
"num_tokens": 56523105.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.10917100906372,
|
|
"epoch": 2.4103633114949377,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044288261277776524,
|
|
"loss": 4.6501,
|
|
"mean_token_accuracy": 0.2247503489255905,
|
|
"num_tokens": 56539066.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.080957984924316,
|
|
"epoch": 2.410958904109589,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004428542389778834,
|
|
"loss": 4.4966,
|
|
"mean_token_accuracy": 0.24330883622169494,
|
|
"num_tokens": 56551629.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.052044343948364,
|
|
"epoch": 2.4115544967242406,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044282585915734297,
|
|
"loss": 4.5514,
|
|
"mean_token_accuracy": 0.2307101607322693,
|
|
"num_tokens": 56565318.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.056414079666138,
|
|
"epoch": 2.4121500893388923,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004427974733171618,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.2368614062666893,
|
|
"num_tokens": 56578894.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.1099724769592285,
|
|
"epoch": 2.4127456819535436,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004427690814583581,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.22974440455436707,
|
|
"num_tokens": 56591765.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 4.987047386169434,
|
|
"epoch": 2.4133412745681952,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004427406835819502,
|
|
"loss": 4.5089,
|
|
"mean_token_accuracy": 0.24002399295568466,
|
|
"num_tokens": 56604751.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.016168117523193,
|
|
"epoch": 2.413936867182847,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004427122796889567,
|
|
"loss": 4.5786,
|
|
"mean_token_accuracy": 0.23438838571310044,
|
|
"num_tokens": 56618934.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.116227149963379,
|
|
"epoch": 2.4145324597974986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004426838697803965,
|
|
"loss": 4.5806,
|
|
"mean_token_accuracy": 0.23638410717248917,
|
|
"num_tokens": 56632118.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.087141132354736,
|
|
"epoch": 2.4151280524121503,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044265545385728847,
|
|
"loss": 4.5331,
|
|
"mean_token_accuracy": 0.24069354087114334,
|
|
"num_tokens": 56646627.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.0685625076293945,
|
|
"epoch": 2.4157236450268016,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044262703192065185,
|
|
"loss": 4.5702,
|
|
"mean_token_accuracy": 0.2365619421005249,
|
|
"num_tokens": 56660715.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.049057054519653,
|
|
"epoch": 2.4163192376414533,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044259860397150616,
|
|
"loss": 4.5732,
|
|
"mean_token_accuracy": 0.23572006225585937,
|
|
"num_tokens": 56673887.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.089197111129761,
|
|
"epoch": 2.416914830256105,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044257017001087114,
|
|
"loss": 4.5963,
|
|
"mean_token_accuracy": 0.2290463387966156,
|
|
"num_tokens": 56686183.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.0987794399261475,
|
|
"epoch": 2.4175104228707562,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004425417300397665,
|
|
"loss": 4.5634,
|
|
"mean_token_accuracy": 0.23443934172391892,
|
|
"num_tokens": 56699935.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.114593362808227,
|
|
"epoch": 2.418106015485408,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00044251328405921236,
|
|
"loss": 4.6,
|
|
"mean_token_accuracy": 0.23195214867591857,
|
|
"num_tokens": 56713723.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.039874935150147,
|
|
"epoch": 2.4187016081000596,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004424848320702291,
|
|
"loss": 4.548,
|
|
"mean_token_accuracy": 0.2312001556158066,
|
|
"num_tokens": 56729002.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.130760431289673,
|
|
"epoch": 2.4192972007147113,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004424563740738373,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.21608262956142427,
|
|
"num_tokens": 56747040.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.1290185928344725,
|
|
"epoch": 2.4198927933293626,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044242791007105764,
|
|
"loss": 4.6262,
|
|
"mean_token_accuracy": 0.22295186370611192,
|
|
"num_tokens": 56760523.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.081168174743652,
|
|
"epoch": 2.4204883859440143,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000442399440062911,
|
|
"loss": 4.5478,
|
|
"mean_token_accuracy": 0.23236979693174362,
|
|
"num_tokens": 56773007.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.0799342632293705,
|
|
"epoch": 2.421083978558666,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044237096405041863,
|
|
"loss": 4.5415,
|
|
"mean_token_accuracy": 0.23837780356407165,
|
|
"num_tokens": 56787542.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.070208263397217,
|
|
"epoch": 2.4216795711733177,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044234248203460193,
|
|
"loss": 4.6029,
|
|
"mean_token_accuracy": 0.23588740229606628,
|
|
"num_tokens": 56802218.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.026461935043335,
|
|
"epoch": 2.422275163787969,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044231399401648247,
|
|
"loss": 4.464,
|
|
"mean_token_accuracy": 0.23838363885879515,
|
|
"num_tokens": 56815868.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.077147960662842,
|
|
"epoch": 2.4228707564026206,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044228549999708204,
|
|
"loss": 4.5369,
|
|
"mean_token_accuracy": 0.23578144907951354,
|
|
"num_tokens": 56831378.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.051888847351075,
|
|
"epoch": 2.4234663490172723,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004422569999774228,
|
|
"loss": 4.4774,
|
|
"mean_token_accuracy": 0.2365758538246155,
|
|
"num_tokens": 56843688.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.031074142456054,
|
|
"epoch": 2.4240619416319236,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044222849395852683,
|
|
"loss": 4.5518,
|
|
"mean_token_accuracy": 0.2425076112151146,
|
|
"num_tokens": 56859235.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.0849871158599855,
|
|
"epoch": 2.4246575342465753,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004421999819414167,
|
|
"loss": 4.6135,
|
|
"mean_token_accuracy": 0.23366761207580566,
|
|
"num_tokens": 56871972.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.054441976547241,
|
|
"epoch": 2.425253126861227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004421714639271151,
|
|
"loss": 4.5354,
|
|
"mean_token_accuracy": 0.23449959307909013,
|
|
"num_tokens": 56885779.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.148586416244507,
|
|
"epoch": 2.4258487194758787,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004421429399166449,
|
|
"loss": 4.6414,
|
|
"mean_token_accuracy": 0.22879848033189773,
|
|
"num_tokens": 56899830.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.038065004348755,
|
|
"epoch": 2.42644431209053,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004421144099110292,
|
|
"loss": 4.4843,
|
|
"mean_token_accuracy": 0.2370082288980484,
|
|
"num_tokens": 56914418.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.068083238601685,
|
|
"epoch": 2.4270399047051816,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004420858739112913,
|
|
"loss": 4.5431,
|
|
"mean_token_accuracy": 0.23968988806009292,
|
|
"num_tokens": 56927859.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.050847053527832,
|
|
"epoch": 2.4276354973198333,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00044205733191845473,
|
|
"loss": 4.5947,
|
|
"mean_token_accuracy": 0.23131843507289887,
|
|
"num_tokens": 56943574.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.135045099258423,
|
|
"epoch": 2.428231089934485,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004420287839335434,
|
|
"loss": 4.6323,
|
|
"mean_token_accuracy": 0.22030874341726303,
|
|
"num_tokens": 56959934.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.070237064361573,
|
|
"epoch": 2.4288266825491363,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00044200022995758104,
|
|
"loss": 4.5687,
|
|
"mean_token_accuracy": 0.2297144651412964,
|
|
"num_tokens": 56976021.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.109052419662476,
|
|
"epoch": 2.429422275163788,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00044197166999159203,
|
|
"loss": 4.6306,
|
|
"mean_token_accuracy": 0.2287459447979927,
|
|
"num_tokens": 56990685.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.167840957641602,
|
|
"epoch": 2.4300178677784396,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004419431040366007,
|
|
"loss": 4.7223,
|
|
"mean_token_accuracy": 0.2224510818719864,
|
|
"num_tokens": 57003442.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.0467729568481445,
|
|
"epoch": 2.430613460393091,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044191453209363165,
|
|
"loss": 4.5536,
|
|
"mean_token_accuracy": 0.23133797347545623,
|
|
"num_tokens": 57017148.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.070024919509888,
|
|
"epoch": 2.4312090530077426,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004418859541637097,
|
|
"loss": 4.5041,
|
|
"mean_token_accuracy": 0.24576156586408615,
|
|
"num_tokens": 57031246.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.066012573242188,
|
|
"epoch": 2.4318046456223943,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00044185737024785986,
|
|
"loss": 4.6111,
|
|
"mean_token_accuracy": 0.2283359006047249,
|
|
"num_tokens": 57046144.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.025941801071167,
|
|
"epoch": 2.432400238237046,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044182878034710753,
|
|
"loss": 4.5318,
|
|
"mean_token_accuracy": 0.23664937615394593,
|
|
"num_tokens": 57060124.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.069641637802124,
|
|
"epoch": 2.4329958308516977,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044180018446247807,
|
|
"loss": 4.55,
|
|
"mean_token_accuracy": 0.23294271975755693,
|
|
"num_tokens": 57073477.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.0588208675384525,
|
|
"epoch": 2.433591423466349,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004417715825949972,
|
|
"loss": 4.5721,
|
|
"mean_token_accuracy": 0.23370405286550522,
|
|
"num_tokens": 57086969.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.026556396484375,
|
|
"epoch": 2.4341870160810006,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004417429747456908,
|
|
"loss": 4.4751,
|
|
"mean_token_accuracy": 0.24472673386335372,
|
|
"num_tokens": 57100529.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.109577798843384,
|
|
"epoch": 2.4347826086956523,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000441714360915585,
|
|
"loss": 4.6164,
|
|
"mean_token_accuracy": 0.22420689314603806,
|
|
"num_tokens": 57115017.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.054792356491089,
|
|
"epoch": 2.4353782013103036,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004416857411057062,
|
|
"loss": 4.6047,
|
|
"mean_token_accuracy": 0.23465330451726912,
|
|
"num_tokens": 57129392.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 4.9744478225708,
|
|
"epoch": 2.4359737939249553,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00044165711531708073,
|
|
"loss": 4.449,
|
|
"mean_token_accuracy": 0.24007988274097442,
|
|
"num_tokens": 57142321.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.108478736877442,
|
|
"epoch": 2.436569386539607,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044162848355073565,
|
|
"loss": 4.5748,
|
|
"mean_token_accuracy": 0.2330855131149292,
|
|
"num_tokens": 57156623.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.116736555099488,
|
|
"epoch": 2.4371649791542587,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004415998458076978,
|
|
"loss": 4.6131,
|
|
"mean_token_accuracy": 0.2308479979634285,
|
|
"num_tokens": 57170569.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.046771764755249,
|
|
"epoch": 2.43776057176891,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004415712020889943,
|
|
"loss": 4.5102,
|
|
"mean_token_accuracy": 0.23641644567251205,
|
|
"num_tokens": 57183007.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.0467119216918945,
|
|
"epoch": 2.4383561643835616,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044154255239565256,
|
|
"loss": 4.591,
|
|
"mean_token_accuracy": 0.23388708531856536,
|
|
"num_tokens": 57196460.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.141020679473877,
|
|
"epoch": 2.4389517569982133,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004415138967287003,
|
|
"loss": 4.6753,
|
|
"mean_token_accuracy": 0.22641689330339432,
|
|
"num_tokens": 57211856.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.079180431365967,
|
|
"epoch": 2.439547349612865,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004414852350891653,
|
|
"loss": 4.5297,
|
|
"mean_token_accuracy": 0.2339162677526474,
|
|
"num_tokens": 57224915.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.0751605987548825,
|
|
"epoch": 2.4401429422275163,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004414565674780756,
|
|
"loss": 4.5996,
|
|
"mean_token_accuracy": 0.23765594214200975,
|
|
"num_tokens": 57239213.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.104438209533692,
|
|
"epoch": 2.440738534842168,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00044142789389645944,
|
|
"loss": 4.5778,
|
|
"mean_token_accuracy": 0.23103312104940416,
|
|
"num_tokens": 57253996.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.0070521354675295,
|
|
"epoch": 2.4413341274568197,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004413992143453453,
|
|
"loss": 4.5809,
|
|
"mean_token_accuracy": 0.2343176409602165,
|
|
"num_tokens": 57268280.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.106292200088501,
|
|
"epoch": 2.441929720071471,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000441370528825762,
|
|
"loss": 4.6075,
|
|
"mean_token_accuracy": 0.22859732061624527,
|
|
"num_tokens": 57282202.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.155791187286377,
|
|
"epoch": 2.4425253126861226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044134183733873827,
|
|
"loss": 4.6358,
|
|
"mean_token_accuracy": 0.22666917592287064,
|
|
"num_tokens": 57296338.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.042172574996949,
|
|
"epoch": 2.4431209053007743,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044131313988530325,
|
|
"loss": 4.5771,
|
|
"mean_token_accuracy": 0.2337867483496666,
|
|
"num_tokens": 57308675.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.067158031463623,
|
|
"epoch": 2.443716497915426,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044128443646648634,
|
|
"loss": 4.5884,
|
|
"mean_token_accuracy": 0.23639001101255416,
|
|
"num_tokens": 57324287.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.080599737167359,
|
|
"epoch": 2.4443120905300773,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044125572708331705,
|
|
"loss": 4.5815,
|
|
"mean_token_accuracy": 0.22994384914636612,
|
|
"num_tokens": 57336793.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.089668226242066,
|
|
"epoch": 2.444907683144729,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00044122701173682514,
|
|
"loss": 4.5381,
|
|
"mean_token_accuracy": 0.23424625694751738,
|
|
"num_tokens": 57351270.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.127063131332397,
|
|
"epoch": 2.4455032757593806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004411982904280407,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.2218359276652336,
|
|
"num_tokens": 57364126.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.042270565032959,
|
|
"epoch": 2.4460988683740323,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004411695631579936,
|
|
"loss": 4.5777,
|
|
"mean_token_accuracy": 0.22971232533454894,
|
|
"num_tokens": 57379319.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.140580368041992,
|
|
"epoch": 2.4466944609886836,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044114082992771457,
|
|
"loss": 4.5954,
|
|
"mean_token_accuracy": 0.22868584245443344,
|
|
"num_tokens": 57391848.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.089814281463623,
|
|
"epoch": 2.4472900536033353,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044111209073823416,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.23472370505332946,
|
|
"num_tokens": 57405991.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.070598459243774,
|
|
"epoch": 2.447885646217987,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000441083345590583,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.23932817876338958,
|
|
"num_tokens": 57420030.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.065906095504761,
|
|
"epoch": 2.4484812388326382,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004410545944857923,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.23796301782131196,
|
|
"num_tokens": 57434167.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.06714768409729,
|
|
"epoch": 2.44907683144729,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044102583742489337,
|
|
"loss": 4.5587,
|
|
"mean_token_accuracy": 0.2384706437587738,
|
|
"num_tokens": 57447180.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.1040794372558596,
|
|
"epoch": 2.4496724240619416,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004409970744089175,
|
|
"loss": 4.6423,
|
|
"mean_token_accuracy": 0.2271284893155098,
|
|
"num_tokens": 57461584.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.058843803405762,
|
|
"epoch": 2.4502680166765933,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044096830543889653,
|
|
"loss": 4.5575,
|
|
"mean_token_accuracy": 0.23819792568683623,
|
|
"num_tokens": 57475976.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.0267082214355465,
|
|
"epoch": 2.450863609291245,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044093953051586225,
|
|
"loss": 4.495,
|
|
"mean_token_accuracy": 0.2425808787345886,
|
|
"num_tokens": 57491882.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.131326913833618,
|
|
"epoch": 2.4514592019058963,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004409107496408468,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.22931206375360488,
|
|
"num_tokens": 57506994.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.037816095352173,
|
|
"epoch": 2.452054794520548,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00044088196281488257,
|
|
"loss": 4.5448,
|
|
"mean_token_accuracy": 0.2406519427895546,
|
|
"num_tokens": 57521192.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.040510082244873,
|
|
"epoch": 2.4526503871351997,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000440853170039002,
|
|
"loss": 4.5322,
|
|
"mean_token_accuracy": 0.23737748414278032,
|
|
"num_tokens": 57536846.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.0642335414886475,
|
|
"epoch": 2.453245979749851,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044082437131423785,
|
|
"loss": 4.5353,
|
|
"mean_token_accuracy": 0.2345140278339386,
|
|
"num_tokens": 57551640.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.116881799697876,
|
|
"epoch": 2.4538415723645026,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00044079556664162323,
|
|
"loss": 4.5902,
|
|
"mean_token_accuracy": 0.23112950772047042,
|
|
"num_tokens": 57567568.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.133766746520996,
|
|
"epoch": 2.4544371649791543,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004407667560221911,
|
|
"loss": 4.6158,
|
|
"mean_token_accuracy": 0.22783315181732178,
|
|
"num_tokens": 57581191.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.051500654220581,
|
|
"epoch": 2.455032757593806,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000440737939456975,
|
|
"loss": 4.5784,
|
|
"mean_token_accuracy": 0.23738009184598924,
|
|
"num_tokens": 57593773.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.058558082580566,
|
|
"epoch": 2.4556283502084573,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044070911694700846,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.23364706188440323,
|
|
"num_tokens": 57608109.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.051830911636353,
|
|
"epoch": 2.456223942823109,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004406802884933253,
|
|
"loss": 4.5171,
|
|
"mean_token_accuracy": 0.24261028170585633,
|
|
"num_tokens": 57622407.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.088241481781006,
|
|
"epoch": 2.4568195354377607,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004406514540969596,
|
|
"loss": 4.5387,
|
|
"mean_token_accuracy": 0.23561513423919678,
|
|
"num_tokens": 57637204.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.0242890357971195,
|
|
"epoch": 2.4574151280524124,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00044062261375894563,
|
|
"loss": 4.5118,
|
|
"mean_token_accuracy": 0.24305209666490554,
|
|
"num_tokens": 57652214.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.095351600646973,
|
|
"epoch": 2.4580107206670636,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004405937674803177,
|
|
"loss": 4.5665,
|
|
"mean_token_accuracy": 0.23927595019340514,
|
|
"num_tokens": 57665081.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.050530290603637,
|
|
"epoch": 2.4586063132817153,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00044056491526211063,
|
|
"loss": 4.554,
|
|
"mean_token_accuracy": 0.23697410821914672,
|
|
"num_tokens": 57678909.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.03584303855896,
|
|
"epoch": 2.459201905896367,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004405360571053592,
|
|
"loss": 4.498,
|
|
"mean_token_accuracy": 0.23527469038963317,
|
|
"num_tokens": 57690998.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.042243528366089,
|
|
"epoch": 2.4597974985110183,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00044050719301109856,
|
|
"loss": 4.5406,
|
|
"mean_token_accuracy": 0.23893511891365052,
|
|
"num_tokens": 57704453.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.11863751411438,
|
|
"epoch": 2.46039309112567,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000440478322980364,
|
|
"loss": 4.5827,
|
|
"mean_token_accuracy": 0.23215913027524948,
|
|
"num_tokens": 57718653.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.007312965393067,
|
|
"epoch": 2.4609886837403216,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044044944701419105,
|
|
"loss": 4.5133,
|
|
"mean_token_accuracy": 0.24885137379169464,
|
|
"num_tokens": 57733209.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.043221282958984,
|
|
"epoch": 2.4615842763549733,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004404205651136155,
|
|
"loss": 4.5175,
|
|
"mean_token_accuracy": 0.23615385293960572,
|
|
"num_tokens": 57747012.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.088767242431641,
|
|
"epoch": 2.4621798689696246,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004403916772796731,
|
|
"loss": 4.6155,
|
|
"mean_token_accuracy": 0.23304421007633208,
|
|
"num_tokens": 57761046.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.066314029693603,
|
|
"epoch": 2.4627754615842763,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044036278351340023,
|
|
"loss": 4.5196,
|
|
"mean_token_accuracy": 0.23755654245615004,
|
|
"num_tokens": 57774141.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.042482185363769,
|
|
"epoch": 2.463371054198928,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044033388381583324,
|
|
"loss": 4.5275,
|
|
"mean_token_accuracy": 0.23231873363256456,
|
|
"num_tokens": 57789219.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.038028240203857,
|
|
"epoch": 2.4639666468135797,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004403049781880086,
|
|
"loss": 4.5494,
|
|
"mean_token_accuracy": 0.23537393510341645,
|
|
"num_tokens": 57803595.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.064097785949707,
|
|
"epoch": 2.464562239428231,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004402760666309631,
|
|
"loss": 4.5938,
|
|
"mean_token_accuracy": 0.22956006973981857,
|
|
"num_tokens": 57817477.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.028336715698242,
|
|
"epoch": 2.4651578320428826,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004402471491457339,
|
|
"loss": 4.4996,
|
|
"mean_token_accuracy": 0.24020849764347077,
|
|
"num_tokens": 57833099.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.044256258010864,
|
|
"epoch": 2.4657534246575343,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004402182257333581,
|
|
"loss": 4.5553,
|
|
"mean_token_accuracy": 0.23181984573602676,
|
|
"num_tokens": 57849128.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.110422420501709,
|
|
"epoch": 2.4663490172721856,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004401892963948732,
|
|
"loss": 4.579,
|
|
"mean_token_accuracy": 0.23599661737680436,
|
|
"num_tokens": 57862160.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.042505550384521,
|
|
"epoch": 2.4669446098868373,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00044016036113131673,
|
|
"loss": 4.5357,
|
|
"mean_token_accuracy": 0.23980133533477782,
|
|
"num_tokens": 57875332.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.103843116760254,
|
|
"epoch": 2.467540202501489,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044013141994372673,
|
|
"loss": 4.5596,
|
|
"mean_token_accuracy": 0.23861711323261262,
|
|
"num_tokens": 57887511.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.124207210540772,
|
|
"epoch": 2.4681357951161407,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004401024728331411,
|
|
"loss": 4.6332,
|
|
"mean_token_accuracy": 0.2292139708995819,
|
|
"num_tokens": 57901981.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.016034936904907,
|
|
"epoch": 2.4687313877307924,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00044007351980059826,
|
|
"loss": 4.5473,
|
|
"mean_token_accuracy": 0.22707288414239885,
|
|
"num_tokens": 57917085.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.060470771789551,
|
|
"epoch": 2.4693269803454436,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004400445608471367,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.23294161409139633,
|
|
"num_tokens": 57929871.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.0609778881073,
|
|
"epoch": 2.4699225729600953,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044001559597379503,
|
|
"loss": 4.6039,
|
|
"mean_token_accuracy": 0.2378079265356064,
|
|
"num_tokens": 57943552.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.118277215957642,
|
|
"epoch": 2.470518165574747,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00043998662518161233,
|
|
"loss": 4.5972,
|
|
"mean_token_accuracy": 0.22770550847053528,
|
|
"num_tokens": 57958740.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.165237617492676,
|
|
"epoch": 2.4711137581893983,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043995764847162757,
|
|
"loss": 4.6251,
|
|
"mean_token_accuracy": 0.22839780449867247,
|
|
"num_tokens": 57971795.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.068223237991333,
|
|
"epoch": 2.47170935080405,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043992866584488007,
|
|
"loss": 4.5284,
|
|
"mean_token_accuracy": 0.2473151847720146,
|
|
"num_tokens": 57985077.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.030482387542724,
|
|
"epoch": 2.4723049434187017,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004398996773024096,
|
|
"loss": 4.5486,
|
|
"mean_token_accuracy": 0.2301516830921173,
|
|
"num_tokens": 57998784.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.105006694793701,
|
|
"epoch": 2.4729005360333534,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004398706828452558,
|
|
"loss": 4.5958,
|
|
"mean_token_accuracy": 0.23082298636436463,
|
|
"num_tokens": 58010775.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.157600450515747,
|
|
"epoch": 2.4734961286480046,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004398416824744586,
|
|
"loss": 4.6036,
|
|
"mean_token_accuracy": 0.230515193939209,
|
|
"num_tokens": 58024122.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.123574876785279,
|
|
"epoch": 2.4740917212626563,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043981267619105837,
|
|
"loss": 4.556,
|
|
"mean_token_accuracy": 0.23517775237560273,
|
|
"num_tokens": 58036899.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.030764102935791,
|
|
"epoch": 2.474687313877308,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004397836639960953,
|
|
"loss": 4.5451,
|
|
"mean_token_accuracy": 0.23182165920734404,
|
|
"num_tokens": 58049870.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.1081156730651855,
|
|
"epoch": 2.4752829064919597,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004397546458906102,
|
|
"loss": 4.659,
|
|
"mean_token_accuracy": 0.22399420887231827,
|
|
"num_tokens": 58064376.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.126155519485474,
|
|
"epoch": 2.475878499106611,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00043972562187564383,
|
|
"loss": 4.6114,
|
|
"mean_token_accuracy": 0.2287345364689827,
|
|
"num_tokens": 58078573.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.07257194519043,
|
|
"epoch": 2.4764740917212626,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004396965919522373,
|
|
"loss": 4.5592,
|
|
"mean_token_accuracy": 0.23274453580379487,
|
|
"num_tokens": 58093348.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 4.954734516143799,
|
|
"epoch": 2.4770696843359143,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043966755612143165,
|
|
"loss": 4.4218,
|
|
"mean_token_accuracy": 0.25009713023900987,
|
|
"num_tokens": 58107360.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.1446997165679935,
|
|
"epoch": 2.4776652769505656,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043963851438426853,
|
|
"loss": 4.613,
|
|
"mean_token_accuracy": 0.23386565893888472,
|
|
"num_tokens": 58120243.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.14212999343872,
|
|
"epoch": 2.4782608695652173,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004396094667417896,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.22867144793272018,
|
|
"num_tokens": 58134575.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.093614292144776,
|
|
"epoch": 2.478856462179869,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004395804131950368,
|
|
"loss": 4.5752,
|
|
"mean_token_accuracy": 0.2398836687207222,
|
|
"num_tokens": 58147048.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.029257154464721,
|
|
"epoch": 2.4794520547945207,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043955135374505207,
|
|
"loss": 4.4985,
|
|
"mean_token_accuracy": 0.23806435763835906,
|
|
"num_tokens": 58161140.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.124203634262085,
|
|
"epoch": 2.480047647409172,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004395222883928779,
|
|
"loss": 4.5756,
|
|
"mean_token_accuracy": 0.2289655551314354,
|
|
"num_tokens": 58175480.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.113166475296021,
|
|
"epoch": 2.4806432400238236,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00043949321713955677,
|
|
"loss": 4.5821,
|
|
"mean_token_accuracy": 0.23541579097509385,
|
|
"num_tokens": 58189983.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.061442708969116,
|
|
"epoch": 2.4812388326384753,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004394641399861313,
|
|
"loss": 4.5757,
|
|
"mean_token_accuracy": 0.2332845076918602,
|
|
"num_tokens": 58204789.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.120978116989136,
|
|
"epoch": 2.481834425253127,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004394350569336445,
|
|
"loss": 4.5608,
|
|
"mean_token_accuracy": 0.22782225161790848,
|
|
"num_tokens": 58219696.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.06911153793335,
|
|
"epoch": 2.4824300178677783,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043940596798313963,
|
|
"loss": 4.5312,
|
|
"mean_token_accuracy": 0.24281378984451293,
|
|
"num_tokens": 58232525.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 4.948224210739136,
|
|
"epoch": 2.48302561048243,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043937687313565997,
|
|
"loss": 4.4815,
|
|
"mean_token_accuracy": 0.24401138871908187,
|
|
"num_tokens": 58246126.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.069966173171997,
|
|
"epoch": 2.4836212030970817,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004393477723922492,
|
|
"loss": 4.6376,
|
|
"mean_token_accuracy": 0.23067272156476976,
|
|
"num_tokens": 58259876.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.124540328979492,
|
|
"epoch": 2.484216795711733,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000439318665753951,
|
|
"loss": 4.5945,
|
|
"mean_token_accuracy": 0.2365388810634613,
|
|
"num_tokens": 58273678.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.058492231369018,
|
|
"epoch": 2.4848123883263846,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043928955322180944,
|
|
"loss": 4.5386,
|
|
"mean_token_accuracy": 0.23928502947092056,
|
|
"num_tokens": 58288937.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.0056946754455565,
|
|
"epoch": 2.4854079809410363,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004392604347968687,
|
|
"loss": 4.5142,
|
|
"mean_token_accuracy": 0.24426874071359633,
|
|
"num_tokens": 58300409.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.042967510223389,
|
|
"epoch": 2.486003573555688,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043923131048017325,
|
|
"loss": 4.501,
|
|
"mean_token_accuracy": 0.23665116876363754,
|
|
"num_tokens": 58314456.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.0106940269470215,
|
|
"epoch": 2.4865991661703397,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043920218027276777,
|
|
"loss": 4.4696,
|
|
"mean_token_accuracy": 0.24944036900997163,
|
|
"num_tokens": 58328451.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.085086488723755,
|
|
"epoch": 2.487194758784991,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043917304417569696,
|
|
"loss": 4.6545,
|
|
"mean_token_accuracy": 0.2217035099864006,
|
|
"num_tokens": 58343989.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.102277994155884,
|
|
"epoch": 2.4877903513996427,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043914390219000605,
|
|
"loss": 4.5852,
|
|
"mean_token_accuracy": 0.2375747337937355,
|
|
"num_tokens": 58357741.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.126475381851196,
|
|
"epoch": 2.4883859440142944,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043911475431674025,
|
|
"loss": 4.5753,
|
|
"mean_token_accuracy": 0.2341158226132393,
|
|
"num_tokens": 58371073.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.08840160369873,
|
|
"epoch": 2.4889815366289456,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000439085600556945,
|
|
"loss": 4.5863,
|
|
"mean_token_accuracy": 0.23549655824899673,
|
|
"num_tokens": 58384875.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.0709620952606205,
|
|
"epoch": 2.4895771292435973,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004390564409116661,
|
|
"loss": 4.5297,
|
|
"mean_token_accuracy": 0.23182347118854524,
|
|
"num_tokens": 58398460.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.084938383102417,
|
|
"epoch": 2.490172721858249,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004390272753819494,
|
|
"loss": 4.6179,
|
|
"mean_token_accuracy": 0.23429961502552032,
|
|
"num_tokens": 58412044.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.109334278106689,
|
|
"epoch": 2.4907683144729007,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000438998103968841,
|
|
"loss": 4.5556,
|
|
"mean_token_accuracy": 0.23310301154851915,
|
|
"num_tokens": 58426957.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.084893083572387,
|
|
"epoch": 2.491363907087552,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043896892667338725,
|
|
"loss": 4.5653,
|
|
"mean_token_accuracy": 0.23239441066980362,
|
|
"num_tokens": 58440563.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.058266687393188,
|
|
"epoch": 2.4919594997022037,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043893974349663465,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.23226772099733353,
|
|
"num_tokens": 58454998.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.061844062805176,
|
|
"epoch": 2.4925550923168553,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004389105544396301,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.23933925330638886,
|
|
"num_tokens": 58467433.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.053534746170044,
|
|
"epoch": 2.493150684931507,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004388813595034204,
|
|
"loss": 4.5803,
|
|
"mean_token_accuracy": 0.23027774542570115,
|
|
"num_tokens": 58484082.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.065201759338379,
|
|
"epoch": 2.4937462775461583,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043885215868905283,
|
|
"loss": 4.532,
|
|
"mean_token_accuracy": 0.23287817984819412,
|
|
"num_tokens": 58497528.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.148356246948242,
|
|
"epoch": 2.49434187016081,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043882295199757464,
|
|
"loss": 4.6052,
|
|
"mean_token_accuracy": 0.2273487329483032,
|
|
"num_tokens": 58511759.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.006237125396728,
|
|
"epoch": 2.4949374627754617,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004387937394300336,
|
|
"loss": 4.4758,
|
|
"mean_token_accuracy": 0.2414473131299019,
|
|
"num_tokens": 58525904.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.003000259399414,
|
|
"epoch": 2.495533055390113,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004387645209874775,
|
|
"loss": 4.4949,
|
|
"mean_token_accuracy": 0.23903674483299256,
|
|
"num_tokens": 58539847.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.018260860443116,
|
|
"epoch": 2.4961286480047646,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00043873529667095423,
|
|
"loss": 4.4787,
|
|
"mean_token_accuracy": 0.2403329074382782,
|
|
"num_tokens": 58554082.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.066868638992309,
|
|
"epoch": 2.4967242406194163,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043870606648151205,
|
|
"loss": 4.5393,
|
|
"mean_token_accuracy": 0.2415312945842743,
|
|
"num_tokens": 58567066.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.027576017379761,
|
|
"epoch": 2.497319833234068,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004386768304201995,
|
|
"loss": 4.5018,
|
|
"mean_token_accuracy": 0.23958740681409835,
|
|
"num_tokens": 58580992.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.034001970291138,
|
|
"epoch": 2.4979154258487193,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043864758848806515,
|
|
"loss": 4.5815,
|
|
"mean_token_accuracy": 0.23155609518289566,
|
|
"num_tokens": 58595381.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.0478818893432615,
|
|
"epoch": 2.498511018463371,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004386183406861579,
|
|
"loss": 4.4922,
|
|
"mean_token_accuracy": 0.238054858148098,
|
|
"num_tokens": 58607677.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.022114229202271,
|
|
"epoch": 2.4991066110780227,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004385890870155267,
|
|
"loss": 4.5051,
|
|
"mean_token_accuracy": 0.24260545670986175,
|
|
"num_tokens": 58621140.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.131330108642578,
|
|
"epoch": 2.4997022036926744,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000438559827477221,
|
|
"loss": 4.6636,
|
|
"mean_token_accuracy": 0.22471540421247482,
|
|
"num_tokens": 58632659.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.0800025939941404,
|
|
"epoch": 2.5002977963073256,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004385305620722902,
|
|
"loss": 4.6042,
|
|
"mean_token_accuracy": 0.2291974112391472,
|
|
"num_tokens": 58647726.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.173647260665893,
|
|
"epoch": 2.5008933889219773,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000438501290801784,
|
|
"loss": 4.6544,
|
|
"mean_token_accuracy": 0.22770085632801057,
|
|
"num_tokens": 58662439.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.159307384490967,
|
|
"epoch": 2.501488981536629,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043847201366675243,
|
|
"loss": 4.5946,
|
|
"mean_token_accuracy": 0.23456383794546126,
|
|
"num_tokens": 58674539.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.501488981536629,
|
|
"eval_entropy": 4.828639030904979,
|
|
"eval_loss": 4.593270778656006,
|
|
"eval_mean_token_accuracy": 0.2437069545929148,
|
|
"eval_num_tokens": 58674539.0,
|
|
"eval_runtime": 18.6435,
|
|
"eval_samples_per_second": 1368.466,
|
|
"eval_steps_per_second": 171.105,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.003877449035644,
|
|
"epoch": 2.5020845741512803,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004384427306682454,
|
|
"loss": 4.427,
|
|
"mean_token_accuracy": 0.24180034995079042,
|
|
"num_tokens": 58687658.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.137868213653564,
|
|
"epoch": 2.502680166765932,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043841344180731346,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.21942989826202391,
|
|
"num_tokens": 58702288.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.088444375991822,
|
|
"epoch": 2.5032757593805837,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00043838414708500704,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.23718532919883728,
|
|
"num_tokens": 58717221.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.072278356552124,
|
|
"epoch": 2.5038713519952354,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043835484650237683,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.23849416971206666,
|
|
"num_tokens": 58729342.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.070396852493286,
|
|
"epoch": 2.504466944609887,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000438325540060474,
|
|
"loss": 4.5207,
|
|
"mean_token_accuracy": 0.23710004836320878,
|
|
"num_tokens": 58742924.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.082920837402344,
|
|
"epoch": 2.5050625372245383,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004382962277603495,
|
|
"loss": 4.5792,
|
|
"mean_token_accuracy": 0.2331218719482422,
|
|
"num_tokens": 58757226.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.170083808898926,
|
|
"epoch": 2.50565812983919,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004382669096030548,
|
|
"loss": 4.6909,
|
|
"mean_token_accuracy": 0.22367616146802902,
|
|
"num_tokens": 58772420.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.080898475646973,
|
|
"epoch": 2.5062537224538417,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004382375855896416,
|
|
"loss": 4.592,
|
|
"mean_token_accuracy": 0.23067263662815093,
|
|
"num_tokens": 58787639.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.072718620300293,
|
|
"epoch": 2.506849315068493,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004382082557211615,
|
|
"loss": 4.5304,
|
|
"mean_token_accuracy": 0.23493798822164536,
|
|
"num_tokens": 58803106.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.129506635665893,
|
|
"epoch": 2.5074449076831447,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004381789199986667,
|
|
"loss": 4.5979,
|
|
"mean_token_accuracy": 0.2300224408507347,
|
|
"num_tokens": 58820492.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.062422513961792,
|
|
"epoch": 2.5080405002977963,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004381495784232093,
|
|
"loss": 4.5622,
|
|
"mean_token_accuracy": 0.23378824591636657,
|
|
"num_tokens": 58834171.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.117579698562622,
|
|
"epoch": 2.508636092912448,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00043812023099584193,
|
|
"loss": 4.5743,
|
|
"mean_token_accuracy": 0.23744726032018662,
|
|
"num_tokens": 58847489.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.0928943157196045,
|
|
"epoch": 2.5092316855270993,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000438090877717617,
|
|
"loss": 4.5655,
|
|
"mean_token_accuracy": 0.23057376742362976,
|
|
"num_tokens": 58860991.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.041617488861084,
|
|
"epoch": 2.509827278141751,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004380615185895874,
|
|
"loss": 4.5725,
|
|
"mean_token_accuracy": 0.24096277356147766,
|
|
"num_tokens": 58874212.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 4.998946905136108,
|
|
"epoch": 2.5104228707564027,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00043803215361280627,
|
|
"loss": 4.4784,
|
|
"mean_token_accuracy": 0.24232857227325438,
|
|
"num_tokens": 58888177.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.070224857330322,
|
|
"epoch": 2.5110184633710544,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043800278278832694,
|
|
"loss": 4.5909,
|
|
"mean_token_accuracy": 0.234701007604599,
|
|
"num_tokens": 58901915.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.1136250495910645,
|
|
"epoch": 2.5116140559857056,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043797340611720283,
|
|
"loss": 4.5795,
|
|
"mean_token_accuracy": 0.2291426807641983,
|
|
"num_tokens": 58916661.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.132445001602173,
|
|
"epoch": 2.5122096486003573,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004379440236004875,
|
|
"loss": 4.6498,
|
|
"mean_token_accuracy": 0.22957195937633515,
|
|
"num_tokens": 58929938.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.1174239158630375,
|
|
"epoch": 2.512805241215009,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004379146352392351,
|
|
"loss": 4.5604,
|
|
"mean_token_accuracy": 0.2366030588746071,
|
|
"num_tokens": 58945511.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.096964931488037,
|
|
"epoch": 2.5134008338296603,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004378852410344995,
|
|
"loss": 4.5636,
|
|
"mean_token_accuracy": 0.23511942774057387,
|
|
"num_tokens": 58958843.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.112220573425293,
|
|
"epoch": 2.513996426444312,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043785584098733523,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.23706321120262147,
|
|
"num_tokens": 58971968.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.142891263961792,
|
|
"epoch": 2.5145920190589637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043782643509879666,
|
|
"loss": 4.6569,
|
|
"mean_token_accuracy": 0.22650120109319688,
|
|
"num_tokens": 58986123.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.059323930740357,
|
|
"epoch": 2.5151876116736154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043779702336993866,
|
|
"loss": 4.5475,
|
|
"mean_token_accuracy": 0.24258133322000502,
|
|
"num_tokens": 58998748.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.150871276855469,
|
|
"epoch": 2.515783204288267,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004377676058018161,
|
|
"loss": 4.5875,
|
|
"mean_token_accuracy": 0.2385619252920151,
|
|
"num_tokens": 59011224.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.131374549865723,
|
|
"epoch": 2.5163787969029183,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043773818239548415,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.2284655064344406,
|
|
"num_tokens": 59024919.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.0653523921966555,
|
|
"epoch": 2.51697438951757,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043770875315199816,
|
|
"loss": 4.5329,
|
|
"mean_token_accuracy": 0.23976321667432784,
|
|
"num_tokens": 59037672.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.051724576950074,
|
|
"epoch": 2.5175699821322217,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004376793180724138,
|
|
"loss": 4.5606,
|
|
"mean_token_accuracy": 0.24227397739887238,
|
|
"num_tokens": 59049772.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.11537389755249,
|
|
"epoch": 2.518165574746873,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004376498771577868,
|
|
"loss": 4.625,
|
|
"mean_token_accuracy": 0.2294245630502701,
|
|
"num_tokens": 59065522.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.157521772384643,
|
|
"epoch": 2.5187611673615247,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043762043040917315,
|
|
"loss": 4.6324,
|
|
"mean_token_accuracy": 0.22830579578876495,
|
|
"num_tokens": 59080980.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.092924785614014,
|
|
"epoch": 2.5193567599761764,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043759097782762905,
|
|
"loss": 4.535,
|
|
"mean_token_accuracy": 0.2366210326552391,
|
|
"num_tokens": 59093333.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.06143593788147,
|
|
"epoch": 2.5199523525908276,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043756151941421096,
|
|
"loss": 4.5385,
|
|
"mean_token_accuracy": 0.2360214874148369,
|
|
"num_tokens": 59107559.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.060519409179688,
|
|
"epoch": 2.5205479452054793,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004375320551699755,
|
|
"loss": 4.514,
|
|
"mean_token_accuracy": 0.2385438710451126,
|
|
"num_tokens": 59121151.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.155673503875732,
|
|
"epoch": 2.521143537820131,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043750258509597947,
|
|
"loss": 4.6565,
|
|
"mean_token_accuracy": 0.22182601541280747,
|
|
"num_tokens": 59135765.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.094907903671265,
|
|
"epoch": 2.5217391304347827,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00043747310919327987,
|
|
"loss": 4.5743,
|
|
"mean_token_accuracy": 0.23334505259990693,
|
|
"num_tokens": 59150236.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.027568197250366,
|
|
"epoch": 2.5223347230494344,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004374436274629341,
|
|
"loss": 4.4991,
|
|
"mean_token_accuracy": 0.23893103152513503,
|
|
"num_tokens": 59163840.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.1230066299438475,
|
|
"epoch": 2.5229303156640857,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043741413990599945,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.2248583808541298,
|
|
"num_tokens": 59179875.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.171139144897461,
|
|
"epoch": 2.5235259082787374,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004373846465235337,
|
|
"loss": 4.684,
|
|
"mean_token_accuracy": 0.21800865978002548,
|
|
"num_tokens": 59194579.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.166898250579834,
|
|
"epoch": 2.524121500893389,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043735514731659464,
|
|
"loss": 4.638,
|
|
"mean_token_accuracy": 0.22603953033685684,
|
|
"num_tokens": 59209232.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.024533796310425,
|
|
"epoch": 2.5247170935080403,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004373256422862405,
|
|
"loss": 4.5113,
|
|
"mean_token_accuracy": 0.24338838905096055,
|
|
"num_tokens": 59223544.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.04810676574707,
|
|
"epoch": 2.525312686122692,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004372961314335295,
|
|
"loss": 4.4641,
|
|
"mean_token_accuracy": 0.25058150142431257,
|
|
"num_tokens": 59235713.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.089370489120483,
|
|
"epoch": 2.5259082787373437,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043726661475952005,
|
|
"loss": 4.5717,
|
|
"mean_token_accuracy": 0.24043233841657638,
|
|
"num_tokens": 59248990.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.120279264450073,
|
|
"epoch": 2.5265038713519954,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00043723709226527104,
|
|
"loss": 4.6383,
|
|
"mean_token_accuracy": 0.23851612359285354,
|
|
"num_tokens": 59264852.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.134570360183716,
|
|
"epoch": 2.527099463966647,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004372075639518413,
|
|
"loss": 4.6117,
|
|
"mean_token_accuracy": 0.23879265189170837,
|
|
"num_tokens": 59279562.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.142243909835815,
|
|
"epoch": 2.5276950565812983,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043717802982029,
|
|
"loss": 4.6604,
|
|
"mean_token_accuracy": 0.22475575506687165,
|
|
"num_tokens": 59293741.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.083489847183228,
|
|
"epoch": 2.52829064919595,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004371484898716763,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.23892344534397125,
|
|
"num_tokens": 59306644.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.121494960784912,
|
|
"epoch": 2.5288862418106017,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004371189441070602,
|
|
"loss": 4.621,
|
|
"mean_token_accuracy": 0.2278077095746994,
|
|
"num_tokens": 59323307.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.160308170318603,
|
|
"epoch": 2.529481834425253,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043708939252750094,
|
|
"loss": 4.596,
|
|
"mean_token_accuracy": 0.2243281736969948,
|
|
"num_tokens": 59336323.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.009163856506348,
|
|
"epoch": 2.5300774270399047,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004370598351340587,
|
|
"loss": 4.4956,
|
|
"mean_token_accuracy": 0.2509544566273689,
|
|
"num_tokens": 59349228.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.12316665649414,
|
|
"epoch": 2.5306730196545564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004370302719277937,
|
|
"loss": 4.6361,
|
|
"mean_token_accuracy": 0.22806573808193206,
|
|
"num_tokens": 59361606.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.097031927108764,
|
|
"epoch": 2.5312686122692076,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004370007029097664,
|
|
"loss": 4.5469,
|
|
"mean_token_accuracy": 0.23667978048324584,
|
|
"num_tokens": 59374573.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.0333458423614506,
|
|
"epoch": 2.5318642048838593,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004369711280810372,
|
|
"loss": 4.4751,
|
|
"mean_token_accuracy": 0.24187831431627274,
|
|
"num_tokens": 59388670.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.024616479873657,
|
|
"epoch": 2.532459797498511,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000436941547442667,
|
|
"loss": 4.4939,
|
|
"mean_token_accuracy": 0.2448647364974022,
|
|
"num_tokens": 59402693.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.173381328582764,
|
|
"epoch": 2.5330553901131627,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043691196099571676,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.21514038890600204,
|
|
"num_tokens": 59417728.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.055438280105591,
|
|
"epoch": 2.5336509827278144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043688236874124775,
|
|
"loss": 4.5407,
|
|
"mean_token_accuracy": 0.23995423763990403,
|
|
"num_tokens": 59432732.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.0743001937866214,
|
|
"epoch": 2.5342465753424657,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043685277068032137,
|
|
"loss": 4.6042,
|
|
"mean_token_accuracy": 0.23612942546606064,
|
|
"num_tokens": 59445881.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.133719158172608,
|
|
"epoch": 2.5348421679571174,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043682316681399933,
|
|
"loss": 4.5204,
|
|
"mean_token_accuracy": 0.2371627539396286,
|
|
"num_tokens": 59459112.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.08178482055664,
|
|
"epoch": 2.535437760571769,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004367935571433433,
|
|
"loss": 4.622,
|
|
"mean_token_accuracy": 0.23182844668626784,
|
|
"num_tokens": 59473913.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.032625961303711,
|
|
"epoch": 2.5360333531864203,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043676394166941546,
|
|
"loss": 4.512,
|
|
"mean_token_accuracy": 0.23762426823377608,
|
|
"num_tokens": 59488749.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.078756427764892,
|
|
"epoch": 2.536628945801072,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004367343203932781,
|
|
"loss": 4.5453,
|
|
"mean_token_accuracy": 0.23251588344573976,
|
|
"num_tokens": 59501393.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.116570949554443,
|
|
"epoch": 2.5372245384157237,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004367046933159936,
|
|
"loss": 4.5823,
|
|
"mean_token_accuracy": 0.2353233814239502,
|
|
"num_tokens": 59515122.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.197037887573242,
|
|
"epoch": 2.537820131030375,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043667506043862473,
|
|
"loss": 4.6442,
|
|
"mean_token_accuracy": 0.23175435215234758,
|
|
"num_tokens": 59529510.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 4.982205009460449,
|
|
"epoch": 2.5384157236450267,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043664542176223423,
|
|
"loss": 4.4642,
|
|
"mean_token_accuracy": 0.2472601428627968,
|
|
"num_tokens": 59543351.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.031127500534057,
|
|
"epoch": 2.5390113162596784,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043661577728788527,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.23669613301753997,
|
|
"num_tokens": 59555657.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.017908382415771,
|
|
"epoch": 2.53960690887433,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004365861270166411,
|
|
"loss": 4.486,
|
|
"mean_token_accuracy": 0.24403742998838424,
|
|
"num_tokens": 59569536.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.159979343414307,
|
|
"epoch": 2.5402025014889817,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004365564709495654,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.22927819043397904,
|
|
"num_tokens": 59581934.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.049368619918823,
|
|
"epoch": 2.540798094103633,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004365268090877217,
|
|
"loss": 4.452,
|
|
"mean_token_accuracy": 0.24418260604143144,
|
|
"num_tokens": 59595325.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.029075670242309,
|
|
"epoch": 2.5413936867182847,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000436497141432174,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.23609669953584672,
|
|
"num_tokens": 59609444.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.103188467025757,
|
|
"epoch": 2.5419892793329364,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004364674679839864,
|
|
"loss": 4.6276,
|
|
"mean_token_accuracy": 0.23493991047143936,
|
|
"num_tokens": 59624410.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.054197072982788,
|
|
"epoch": 2.5425848719475876,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004364377887442233,
|
|
"loss": 4.5977,
|
|
"mean_token_accuracy": 0.23335371166467667,
|
|
"num_tokens": 59637880.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.040956687927246,
|
|
"epoch": 2.5431804645622393,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004364081037139491,
|
|
"loss": 4.5242,
|
|
"mean_token_accuracy": 0.23902446180582046,
|
|
"num_tokens": 59650848.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.0589364528656,
|
|
"epoch": 2.543776057176891,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004363784128942288,
|
|
"loss": 4.4707,
|
|
"mean_token_accuracy": 0.2391003668308258,
|
|
"num_tokens": 59664612.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.095729637145996,
|
|
"epoch": 2.5443716497915427,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004363487162861271,
|
|
"loss": 4.5803,
|
|
"mean_token_accuracy": 0.23448960930109025,
|
|
"num_tokens": 59677317.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.060554027557373,
|
|
"epoch": 2.5449672424061944,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004363190138907093,
|
|
"loss": 4.5502,
|
|
"mean_token_accuracy": 0.23984301537275315,
|
|
"num_tokens": 59692509.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.101949024200439,
|
|
"epoch": 2.5455628350208457,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004362893057090408,
|
|
"loss": 4.629,
|
|
"mean_token_accuracy": 0.2317572683095932,
|
|
"num_tokens": 59706111.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.131328296661377,
|
|
"epoch": 2.5461584276354974,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004362595917421871,
|
|
"loss": 4.5695,
|
|
"mean_token_accuracy": 0.23312873393297195,
|
|
"num_tokens": 59721391.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.069727611541748,
|
|
"epoch": 2.546754020250149,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00043622987199121404,
|
|
"loss": 4.5901,
|
|
"mean_token_accuracy": 0.23009430021047592,
|
|
"num_tokens": 59736554.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.125925970077515,
|
|
"epoch": 2.5473496128648003,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043620014645718766,
|
|
"loss": 4.6426,
|
|
"mean_token_accuracy": 0.22771448642015457,
|
|
"num_tokens": 59752122.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.113964176177978,
|
|
"epoch": 2.547945205479452,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043617041514117403,
|
|
"loss": 4.6144,
|
|
"mean_token_accuracy": 0.2276206433773041,
|
|
"num_tokens": 59766886.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.094589805603027,
|
|
"epoch": 2.5485407980941037,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004361406780442398,
|
|
"loss": 4.5302,
|
|
"mean_token_accuracy": 0.23890201300382613,
|
|
"num_tokens": 59780153.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.075913000106811,
|
|
"epoch": 2.549136390708755,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004361109351674513,
|
|
"loss": 4.5298,
|
|
"mean_token_accuracy": 0.23498012274503707,
|
|
"num_tokens": 59793831.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.08947377204895,
|
|
"epoch": 2.5497319833234067,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043608118651187555,
|
|
"loss": 4.5964,
|
|
"mean_token_accuracy": 0.2373789817094803,
|
|
"num_tokens": 59806670.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.098564004898071,
|
|
"epoch": 2.5503275759380584,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00043605143207857964,
|
|
"loss": 4.6249,
|
|
"mean_token_accuracy": 0.23136703073978424,
|
|
"num_tokens": 59821479.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.071043300628662,
|
|
"epoch": 2.55092316855271,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004360216718686306,
|
|
"loss": 4.5671,
|
|
"mean_token_accuracy": 0.23564990609884262,
|
|
"num_tokens": 59833738.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.043741750717163,
|
|
"epoch": 2.5515187611673618,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043599190588309607,
|
|
"loss": 4.5518,
|
|
"mean_token_accuracy": 0.23789855539798738,
|
|
"num_tokens": 59847180.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.222225475311279,
|
|
"epoch": 2.552114353782013,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043596213412304353,
|
|
"loss": 4.7376,
|
|
"mean_token_accuracy": 0.22402110695838928,
|
|
"num_tokens": 59862048.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.113676691055298,
|
|
"epoch": 2.5527099463966647,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043593235658954103,
|
|
"loss": 4.5572,
|
|
"mean_token_accuracy": 0.23425617814064026,
|
|
"num_tokens": 59875052.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.118869924545288,
|
|
"epoch": 2.5533055390113164,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043590257328365655,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.2264431357383728,
|
|
"num_tokens": 59889661.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.178004503250122,
|
|
"epoch": 2.5539011316259677,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043587278420645836,
|
|
"loss": 4.6353,
|
|
"mean_token_accuracy": 0.2234416350722313,
|
|
"num_tokens": 59904747.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.087746238708496,
|
|
"epoch": 2.5544967242406194,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00043584298935901494,
|
|
"loss": 4.5932,
|
|
"mean_token_accuracy": 0.22711877524852753,
|
|
"num_tokens": 59919542.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.046759366989136,
|
|
"epoch": 2.555092316855271,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043581318874239504,
|
|
"loss": 4.5662,
|
|
"mean_token_accuracy": 0.23016445636749266,
|
|
"num_tokens": 59935747.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.169422006607055,
|
|
"epoch": 2.5556879094699223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043578338235766763,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.21874013245105745,
|
|
"num_tokens": 59948720.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.10393877029419,
|
|
"epoch": 2.556283502084574,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004357535702059016,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.23469303399324418,
|
|
"num_tokens": 59962729.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.072308921813965,
|
|
"epoch": 2.5568790946992257,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043572375228816633,
|
|
"loss": 4.5425,
|
|
"mean_token_accuracy": 0.23787947595119477,
|
|
"num_tokens": 59976497.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.042929935455322,
|
|
"epoch": 2.5574746873138774,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043569392860553146,
|
|
"loss": 4.5521,
|
|
"mean_token_accuracy": 0.23598915189504624,
|
|
"num_tokens": 59988509.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.128220844268799,
|
|
"epoch": 2.558070279928529,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043566409915906664,
|
|
"loss": 4.5683,
|
|
"mean_token_accuracy": 0.24219875335693358,
|
|
"num_tokens": 60002888.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.019978952407837,
|
|
"epoch": 2.5586658725431803,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004356342639498418,
|
|
"loss": 4.5291,
|
|
"mean_token_accuracy": 0.2361796662211418,
|
|
"num_tokens": 60016859.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.094130277633667,
|
|
"epoch": 2.559261465157832,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043560442297892703,
|
|
"loss": 4.6147,
|
|
"mean_token_accuracy": 0.23385422080755233,
|
|
"num_tokens": 60031484.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.090047883987427,
|
|
"epoch": 2.5598570577724837,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043557457624739283,
|
|
"loss": 4.5144,
|
|
"mean_token_accuracy": 0.24387562721967698,
|
|
"num_tokens": 60045565.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.006288385391235,
|
|
"epoch": 2.560452650387135,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004355447237563096,
|
|
"loss": 4.486,
|
|
"mean_token_accuracy": 0.24013617336750032,
|
|
"num_tokens": 60059521.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.134345769882202,
|
|
"epoch": 2.5610482430017867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043551486550674816,
|
|
"loss": 4.6356,
|
|
"mean_token_accuracy": 0.23206757456064225,
|
|
"num_tokens": 60072552.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.061921072006226,
|
|
"epoch": 2.5616438356164384,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043548500149977946,
|
|
"loss": 4.5273,
|
|
"mean_token_accuracy": 0.2379668340086937,
|
|
"num_tokens": 60087266.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.163265323638916,
|
|
"epoch": 2.56223942823109,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043545513173647477,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.23227358758449554,
|
|
"num_tokens": 60100703.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.073162317276001,
|
|
"epoch": 2.5628350208457418,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004354252562179053,
|
|
"loss": 4.547,
|
|
"mean_token_accuracy": 0.23227959573268891,
|
|
"num_tokens": 60114816.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.063989162445068,
|
|
"epoch": 2.563430613460393,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043539537494514274,
|
|
"loss": 4.4998,
|
|
"mean_token_accuracy": 0.23769820481538773,
|
|
"num_tokens": 60127766.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.022269153594971,
|
|
"epoch": 2.5640262060750447,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004353654879192589,
|
|
"loss": 4.4701,
|
|
"mean_token_accuracy": 0.252098248898983,
|
|
"num_tokens": 60140899.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.087997007369995,
|
|
"epoch": 2.5646217986896964,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004353355951413258,
|
|
"loss": 4.5906,
|
|
"mean_token_accuracy": 0.23289644867181777,
|
|
"num_tokens": 60154278.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.123388385772705,
|
|
"epoch": 2.5652173913043477,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00043530569661241546,
|
|
"loss": 4.6044,
|
|
"mean_token_accuracy": 0.23150542229413987,
|
|
"num_tokens": 60169206.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.134875631332397,
|
|
"epoch": 2.5658129839189994,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043527579233360047,
|
|
"loss": 4.6414,
|
|
"mean_token_accuracy": 0.2283541291952133,
|
|
"num_tokens": 60181912.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.074839162826538,
|
|
"epoch": 2.566408576533651,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043524588230595346,
|
|
"loss": 4.487,
|
|
"mean_token_accuracy": 0.24267045110464097,
|
|
"num_tokens": 60195507.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 4.989754247665405,
|
|
"epoch": 2.5670041691483023,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00043521596653054714,
|
|
"loss": 4.3839,
|
|
"mean_token_accuracy": 0.2525931313633919,
|
|
"num_tokens": 60209673.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.02708945274353,
|
|
"epoch": 2.567599761762954,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004351860450084546,
|
|
"loss": 4.4908,
|
|
"mean_token_accuracy": 0.24146877080202103,
|
|
"num_tokens": 60223169.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.083266925811768,
|
|
"epoch": 2.5681953543776057,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004351561177407491,
|
|
"loss": 4.5997,
|
|
"mean_token_accuracy": 0.23173953592777252,
|
|
"num_tokens": 60237691.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.108076286315918,
|
|
"epoch": 2.5687909469922574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043512618472850407,
|
|
"loss": 4.5828,
|
|
"mean_token_accuracy": 0.23594460487365723,
|
|
"num_tokens": 60251676.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.011328220367432,
|
|
"epoch": 2.569386539606909,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043509624597279313,
|
|
"loss": 4.5226,
|
|
"mean_token_accuracy": 0.2412903979420662,
|
|
"num_tokens": 60265943.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.038205671310425,
|
|
"epoch": 2.5699821322215604,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043506630147469006,
|
|
"loss": 4.5734,
|
|
"mean_token_accuracy": 0.2304222032427788,
|
|
"num_tokens": 60281152.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.046356439590454,
|
|
"epoch": 2.570577724836212,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043503635123526914,
|
|
"loss": 4.5301,
|
|
"mean_token_accuracy": 0.23379631340503693,
|
|
"num_tokens": 60295362.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.0709004402160645,
|
|
"epoch": 2.5711733174508637,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043500639525560444,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.24479360282421112,
|
|
"num_tokens": 60307865.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.087337684631348,
|
|
"epoch": 2.571768910065515,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043497643353677045,
|
|
"loss": 4.5009,
|
|
"mean_token_accuracy": 0.23509415090084076,
|
|
"num_tokens": 60321497.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.020341110229492,
|
|
"epoch": 2.5723645026801667,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043494646607984195,
|
|
"loss": 4.477,
|
|
"mean_token_accuracy": 0.24007881581783294,
|
|
"num_tokens": 60336198.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.120306491851807,
|
|
"epoch": 2.5729600952948184,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004349164928858938,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.2343399241566658,
|
|
"num_tokens": 60350378.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 4.99675498008728,
|
|
"epoch": 2.5735556879094696,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043488651395600096,
|
|
"loss": 4.4893,
|
|
"mean_token_accuracy": 0.2330490157008171,
|
|
"num_tokens": 60364072.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.045504426956176,
|
|
"epoch": 2.5741512805241213,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00043485652929123894,
|
|
"loss": 4.5122,
|
|
"mean_token_accuracy": 0.23583224564790725,
|
|
"num_tokens": 60377798.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.101381015777588,
|
|
"epoch": 2.574746873138773,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004348265388926831,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.2287004128098488,
|
|
"num_tokens": 60391929.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.114292049407959,
|
|
"epoch": 2.5753424657534247,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004347965427614091,
|
|
"loss": 4.6964,
|
|
"mean_token_accuracy": 0.23162875175476075,
|
|
"num_tokens": 60405025.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.141757822036743,
|
|
"epoch": 2.5759380583680764,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043476654089849294,
|
|
"loss": 4.5692,
|
|
"mean_token_accuracy": 0.23267938941717148,
|
|
"num_tokens": 60417367.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.059617805480957,
|
|
"epoch": 2.5765336509827277,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004347365333050108,
|
|
"loss": 4.5477,
|
|
"mean_token_accuracy": 0.2349252834916115,
|
|
"num_tokens": 60430908.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.126807594299317,
|
|
"epoch": 2.5771292435973794,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00043470651998203885,
|
|
"loss": 4.611,
|
|
"mean_token_accuracy": 0.22851548343896866,
|
|
"num_tokens": 60445186.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.125193119049072,
|
|
"epoch": 2.577724836212031,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00043467650093065367,
|
|
"loss": 4.6321,
|
|
"mean_token_accuracy": 0.2302968367934227,
|
|
"num_tokens": 60458803.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.082190227508545,
|
|
"epoch": 2.5783204288266823,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004346464761519321,
|
|
"loss": 4.5359,
|
|
"mean_token_accuracy": 0.2336919352412224,
|
|
"num_tokens": 60471137.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.100859546661377,
|
|
"epoch": 2.578916021441334,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043461644564695096,
|
|
"loss": 4.6067,
|
|
"mean_token_accuracy": 0.23313932716846467,
|
|
"num_tokens": 60484520.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.088193082809449,
|
|
"epoch": 2.5795116140559857,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004345864094167875,
|
|
"loss": 4.5132,
|
|
"mean_token_accuracy": 0.243619205057621,
|
|
"num_tokens": 60499432.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 4.992111158370972,
|
|
"epoch": 2.5801072066706374,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004345563674625189,
|
|
"loss": 4.4778,
|
|
"mean_token_accuracy": 0.24282346963882445,
|
|
"num_tokens": 60513350.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.133827972412109,
|
|
"epoch": 2.580702799285289,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004345263197852229,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.22856493145227433,
|
|
"num_tokens": 60528701.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.145834875106812,
|
|
"epoch": 2.5812983918999404,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004344962663859771,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.22886393070220948,
|
|
"num_tokens": 60540988.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.129021692276001,
|
|
"epoch": 2.581893984514592,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004344662072658597,
|
|
"loss": 4.5909,
|
|
"mean_token_accuracy": 0.23221517652273177,
|
|
"num_tokens": 60555126.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.05598464012146,
|
|
"epoch": 2.5824895771292438,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004344361424259486,
|
|
"loss": 4.5578,
|
|
"mean_token_accuracy": 0.23567702919244765,
|
|
"num_tokens": 60567871.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.0691228866577145,
|
|
"epoch": 2.583085169743895,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043440607186732234,
|
|
"loss": 4.5412,
|
|
"mean_token_accuracy": 0.23903018236160278,
|
|
"num_tokens": 60581845.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.050803375244141,
|
|
"epoch": 2.5836807623585467,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043437599559105944,
|
|
"loss": 4.48,
|
|
"mean_token_accuracy": 0.24630707651376724,
|
|
"num_tokens": 60594834.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 4.9939932346344,
|
|
"epoch": 2.5842763549731984,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004343459135982387,
|
|
"loss": 4.4394,
|
|
"mean_token_accuracy": 0.24093263298273088,
|
|
"num_tokens": 60609353.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 4.995176887512207,
|
|
"epoch": 2.5848719475878497,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004343158258899391,
|
|
"loss": 4.4479,
|
|
"mean_token_accuracy": 0.2419835790991783,
|
|
"num_tokens": 60623221.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.059962320327759,
|
|
"epoch": 2.5854675402025014,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004342857324672399,
|
|
"loss": 4.4991,
|
|
"mean_token_accuracy": 0.24428183138370513,
|
|
"num_tokens": 60636875.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.053663921356201,
|
|
"epoch": 2.586063132817153,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004342556333312204,
|
|
"loss": 4.5271,
|
|
"mean_token_accuracy": 0.23585651814937592,
|
|
"num_tokens": 60651587.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.027995967864991,
|
|
"epoch": 2.5866587254318048,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043422552848296035,
|
|
"loss": 4.5161,
|
|
"mean_token_accuracy": 0.24412049651145934,
|
|
"num_tokens": 60663845.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.003875112533569,
|
|
"epoch": 2.5872543180464564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004341954179235395,
|
|
"loss": 4.5169,
|
|
"mean_token_accuracy": 0.2375095307826996,
|
|
"num_tokens": 60678048.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.0792444229125975,
|
|
"epoch": 2.5878499106611077,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043416530165403777,
|
|
"loss": 4.5099,
|
|
"mean_token_accuracy": 0.24321947395801544,
|
|
"num_tokens": 60690855.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.141361999511719,
|
|
"epoch": 2.5884455032757594,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00043413517967553545,
|
|
"loss": 4.6197,
|
|
"mean_token_accuracy": 0.2252134934067726,
|
|
"num_tokens": 60704710.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.0945662498474125,
|
|
"epoch": 2.589041095890411,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043410505198911305,
|
|
"loss": 4.5767,
|
|
"mean_token_accuracy": 0.23007665276527406,
|
|
"num_tokens": 60718024.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.064867734909058,
|
|
"epoch": 2.5896366885050623,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004340749185958511,
|
|
"loss": 4.5106,
|
|
"mean_token_accuracy": 0.24047605991363524,
|
|
"num_tokens": 60731534.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.139178943634033,
|
|
"epoch": 2.590232281119714,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043404477949683033,
|
|
"loss": 4.6223,
|
|
"mean_token_accuracy": 0.22259349524974822,
|
|
"num_tokens": 60745562.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.154233741760254,
|
|
"epoch": 2.5908278737343657,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043401463469313207,
|
|
"loss": 4.6323,
|
|
"mean_token_accuracy": 0.22572512030601502,
|
|
"num_tokens": 60759992.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.0680437088012695,
|
|
"epoch": 2.5914234663490174,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00043398448418583736,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.23060574233531952,
|
|
"num_tokens": 60773438.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.075634574890136,
|
|
"epoch": 2.5920190589636687,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00043395432797602764,
|
|
"loss": 4.537,
|
|
"mean_token_accuracy": 0.2350611701607704,
|
|
"num_tokens": 60787656.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.015216588973999,
|
|
"epoch": 2.5926146515783204,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004339241660647847,
|
|
"loss": 4.4855,
|
|
"mean_token_accuracy": 0.23887004554271699,
|
|
"num_tokens": 60801685.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.113731861114502,
|
|
"epoch": 2.593210244192972,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004338939984531903,
|
|
"loss": 4.5779,
|
|
"mean_token_accuracy": 0.2331674128770828,
|
|
"num_tokens": 60817265.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.093456220626831,
|
|
"epoch": 2.5938058368076238,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043386382514232647,
|
|
"loss": 4.5668,
|
|
"mean_token_accuracy": 0.23062367141246795,
|
|
"num_tokens": 60832301.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.022631978988647,
|
|
"epoch": 2.594401429422275,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004338336461332756,
|
|
"loss": 4.4618,
|
|
"mean_token_accuracy": 0.23434789776802062,
|
|
"num_tokens": 60844748.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.0824967384338375,
|
|
"epoch": 2.5949970220369267,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043380346142712,
|
|
"loss": 4.6167,
|
|
"mean_token_accuracy": 0.23550035506486894,
|
|
"num_tokens": 60860211.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.16381049156189,
|
|
"epoch": 2.5955926146515784,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.00043377327102494254,
|
|
"loss": 4.7131,
|
|
"mean_token_accuracy": 0.2226525515317917,
|
|
"num_tokens": 60876532.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.075867319107056,
|
|
"epoch": 2.5961882072662297,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00043374307492782593,
|
|
"loss": 4.4322,
|
|
"mean_token_accuracy": 0.24738011807203292,
|
|
"num_tokens": 60889351.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.035023355484009,
|
|
"epoch": 2.5967837998808814,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004337128731368533,
|
|
"loss": 4.4678,
|
|
"mean_token_accuracy": 0.24693223983049392,
|
|
"num_tokens": 60904695.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.055956220626831,
|
|
"epoch": 2.597379392495533,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043368266565310806,
|
|
"loss": 4.5789,
|
|
"mean_token_accuracy": 0.241170971095562,
|
|
"num_tokens": 60919782.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.051449918746949,
|
|
"epoch": 2.5979749851101848,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004336524524776735,
|
|
"loss": 4.5487,
|
|
"mean_token_accuracy": 0.2375857338309288,
|
|
"num_tokens": 60933424.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.084298706054687,
|
|
"epoch": 2.5985705777248365,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043362223361163355,
|
|
"loss": 4.6085,
|
|
"mean_token_accuracy": 0.2304306983947754,
|
|
"num_tokens": 60946592.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.1258673667907715,
|
|
"epoch": 2.5991661703394877,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043359200905607187,
|
|
"loss": 4.6064,
|
|
"mean_token_accuracy": 0.23430186212062837,
|
|
"num_tokens": 60961025.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.047580814361572,
|
|
"epoch": 2.5997617629541394,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004335617788120728,
|
|
"loss": 4.4904,
|
|
"mean_token_accuracy": 0.24146863371133803,
|
|
"num_tokens": 60973970.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.044494104385376,
|
|
"epoch": 2.600357355568791,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004335315428807203,
|
|
"loss": 4.5296,
|
|
"mean_token_accuracy": 0.23635321408510207,
|
|
"num_tokens": 60986459.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.083955526351929,
|
|
"epoch": 2.6009529481834424,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043350130126309936,
|
|
"loss": 4.5256,
|
|
"mean_token_accuracy": 0.23529436886310579,
|
|
"num_tokens": 61001777.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.094144821166992,
|
|
"epoch": 2.601548540798094,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004334710539602943,
|
|
"loss": 4.5563,
|
|
"mean_token_accuracy": 0.23761992603540422,
|
|
"num_tokens": 61016624.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.04386420249939,
|
|
"epoch": 2.6021441334127458,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043344080097339026,
|
|
"loss": 4.5545,
|
|
"mean_token_accuracy": 0.23504728823900223,
|
|
"num_tokens": 61032064.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 4.989689350128174,
|
|
"epoch": 2.602739726027397,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043341054230347227,
|
|
"loss": 4.4229,
|
|
"mean_token_accuracy": 0.24799211025238038,
|
|
"num_tokens": 61046569.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.028564691543579,
|
|
"epoch": 2.6033353186420487,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004333802779516257,
|
|
"loss": 4.5011,
|
|
"mean_token_accuracy": 0.24138183146715164,
|
|
"num_tokens": 61060620.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.071060657501221,
|
|
"epoch": 2.6039309112567004,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043335000791893606,
|
|
"loss": 4.5145,
|
|
"mean_token_accuracy": 0.24285790473222732,
|
|
"num_tokens": 61073787.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.134967803955078,
|
|
"epoch": 2.604526503871352,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004333197322064891,
|
|
"loss": 4.6015,
|
|
"mean_token_accuracy": 0.23624477088451384,
|
|
"num_tokens": 61085559.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.053632211685181,
|
|
"epoch": 2.605122096486004,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043328945081537077,
|
|
"loss": 4.4991,
|
|
"mean_token_accuracy": 0.23552219420671464,
|
|
"num_tokens": 61099803.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.071411752700806,
|
|
"epoch": 2.605717689100655,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004332591637466672,
|
|
"loss": 4.5524,
|
|
"mean_token_accuracy": 0.2394865036010742,
|
|
"num_tokens": 61113567.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.056804752349853,
|
|
"epoch": 2.6063132817153067,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004332288710014648,
|
|
"loss": 4.4812,
|
|
"mean_token_accuracy": 0.24636550843715668,
|
|
"num_tokens": 61125914.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.059226083755493,
|
|
"epoch": 2.6069088743299584,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043319857258084996,
|
|
"loss": 4.5503,
|
|
"mean_token_accuracy": 0.2289672464132309,
|
|
"num_tokens": 61140276.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.045401525497437,
|
|
"epoch": 2.6075044669446097,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043316826848590955,
|
|
"loss": 4.4717,
|
|
"mean_token_accuracy": 0.24245670139789582,
|
|
"num_tokens": 61153989.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.1372483253479,
|
|
"epoch": 2.6081000595592614,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004331379587177305,
|
|
"loss": 4.6659,
|
|
"mean_token_accuracy": 0.22672856897115706,
|
|
"num_tokens": 61167272.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.0660491466522215,
|
|
"epoch": 2.608695652173913,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004331076432774001,
|
|
"loss": 4.5846,
|
|
"mean_token_accuracy": 0.24029256850481034,
|
|
"num_tokens": 61182315.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.1044059753417965,
|
|
"epoch": 2.609291244788565,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004330773221660055,
|
|
"loss": 4.5639,
|
|
"mean_token_accuracy": 0.23649014234542848,
|
|
"num_tokens": 61196850.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.090944480895996,
|
|
"epoch": 2.6098868374032165,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00043304699538463445,
|
|
"loss": 4.5682,
|
|
"mean_token_accuracy": 0.24115297347307205,
|
|
"num_tokens": 61212434.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.200237083435058,
|
|
"epoch": 2.6104824300178677,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004330166629343746,
|
|
"loss": 4.6579,
|
|
"mean_token_accuracy": 0.22795660942792892,
|
|
"num_tokens": 61224801.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.0970080375671385,
|
|
"epoch": 2.6110780226325194,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00043298632481631393,
|
|
"loss": 4.5779,
|
|
"mean_token_accuracy": 0.23804902732372285,
|
|
"num_tokens": 61240222.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.185603427886963,
|
|
"epoch": 2.611673615247171,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043295598103154073,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.22818158119916915,
|
|
"num_tokens": 61254393.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.090083408355713,
|
|
"epoch": 2.6122692078618224,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043292563158114325,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.23088673651218414,
|
|
"num_tokens": 61268610.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.049964714050293,
|
|
"epoch": 2.612864800476474,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004328952764662102,
|
|
"loss": 4.5275,
|
|
"mean_token_accuracy": 0.23674681037664413,
|
|
"num_tokens": 61283827.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.006986379623413,
|
|
"epoch": 2.6134603930911258,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004328649156878303,
|
|
"loss": 4.5172,
|
|
"mean_token_accuracy": 0.23461198359727858,
|
|
"num_tokens": 61298815.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.112349557876587,
|
|
"epoch": 2.614055985705777,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004328345492470924,
|
|
"loss": 4.5393,
|
|
"mean_token_accuracy": 0.23600494712591172,
|
|
"num_tokens": 61313000.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.0794761180877686,
|
|
"epoch": 2.6146515783204287,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043280417714508605,
|
|
"loss": 4.5809,
|
|
"mean_token_accuracy": 0.231119105219841,
|
|
"num_tokens": 61327877.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.055061292648316,
|
|
"epoch": 2.6152471709350804,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00043277379938290027,
|
|
"loss": 4.5263,
|
|
"mean_token_accuracy": 0.23591383695602416,
|
|
"num_tokens": 61342592.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.130186080932617,
|
|
"epoch": 2.615842763549732,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000432743415961625,
|
|
"loss": 4.672,
|
|
"mean_token_accuracy": 0.22649701237678527,
|
|
"num_tokens": 61356056.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.061581563949585,
|
|
"epoch": 2.616438356164384,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004327130268823497,
|
|
"loss": 4.5034,
|
|
"mean_token_accuracy": 0.2440333366394043,
|
|
"num_tokens": 61368057.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.06592812538147,
|
|
"epoch": 2.617033948779035,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043268263214616467,
|
|
"loss": 4.5694,
|
|
"mean_token_accuracy": 0.2344486966729164,
|
|
"num_tokens": 61381025.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.0670215606689455,
|
|
"epoch": 2.6176295413936868,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043265223175416,
|
|
"loss": 4.5366,
|
|
"mean_token_accuracy": 0.23778428733348847,
|
|
"num_tokens": 61395804.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.124547863006592,
|
|
"epoch": 2.6182251340083385,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043262182570742605,
|
|
"loss": 4.5776,
|
|
"mean_token_accuracy": 0.2337148979306221,
|
|
"num_tokens": 61408671.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.132773303985596,
|
|
"epoch": 2.6188207266229897,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004325914140070535,
|
|
"loss": 4.6343,
|
|
"mean_token_accuracy": 0.23023077398538588,
|
|
"num_tokens": 61423255.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.133450889587403,
|
|
"epoch": 2.6194163192376414,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043256099665413316,
|
|
"loss": 4.5374,
|
|
"mean_token_accuracy": 0.2362454801797867,
|
|
"num_tokens": 61437039.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.101576709747315,
|
|
"epoch": 2.620011911852293,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00043253057364975604,
|
|
"loss": 4.5407,
|
|
"mean_token_accuracy": 0.23198602646589278,
|
|
"num_tokens": 61451244.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.212032985687256,
|
|
"epoch": 2.6206075044669443,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004325001449950134,
|
|
"loss": 4.7318,
|
|
"mean_token_accuracy": 0.23269144594669341,
|
|
"num_tokens": 61465536.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.066612100601196,
|
|
"epoch": 2.621203097081596,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004324697106909966,
|
|
"loss": 4.5321,
|
|
"mean_token_accuracy": 0.22426074743270874,
|
|
"num_tokens": 61479144.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.064020204544067,
|
|
"epoch": 2.6217986896962477,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043243927073879733,
|
|
"loss": 4.5481,
|
|
"mean_token_accuracy": 0.23744122684001923,
|
|
"num_tokens": 61494605.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.1075334548950195,
|
|
"epoch": 2.6223942823108994,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004324088251395074,
|
|
"loss": 4.5637,
|
|
"mean_token_accuracy": 0.23353676795959472,
|
|
"num_tokens": 61508298.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.105794858932495,
|
|
"epoch": 2.622989874925551,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043237837389421884,
|
|
"loss": 4.533,
|
|
"mean_token_accuracy": 0.23854102194309235,
|
|
"num_tokens": 61521675.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.154510068893432,
|
|
"epoch": 2.6235854675402024,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043234791700402396,
|
|
"loss": 4.6299,
|
|
"mean_token_accuracy": 0.2340027391910553,
|
|
"num_tokens": 61534119.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.044458818435669,
|
|
"epoch": 2.624181060154854,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004323174544700151,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.23704305589199065,
|
|
"num_tokens": 61549165.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.049388122558594,
|
|
"epoch": 2.624776652769506,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004322869862932848,
|
|
"loss": 4.4998,
|
|
"mean_token_accuracy": 0.24891482889652253,
|
|
"num_tokens": 61564195.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.113644313812256,
|
|
"epoch": 2.625372245384157,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043225651247492616,
|
|
"loss": 4.5515,
|
|
"mean_token_accuracy": 0.2391020879149437,
|
|
"num_tokens": 61577668.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.00606894493103,
|
|
"epoch": 2.6259678379988087,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004322260330160321,
|
|
"loss": 4.5245,
|
|
"mean_token_accuracy": 0.2399856835603714,
|
|
"num_tokens": 61591571.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.05083384513855,
|
|
"epoch": 2.6265634306134604,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004321955479176958,
|
|
"loss": 4.6269,
|
|
"mean_token_accuracy": 0.22607678472995757,
|
|
"num_tokens": 61606273.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.053680038452148,
|
|
"epoch": 2.627159023228112,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004321650571810109,
|
|
"loss": 4.5115,
|
|
"mean_token_accuracy": 0.2430110454559326,
|
|
"num_tokens": 61621498.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.133700180053711,
|
|
"epoch": 2.627754615842764,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043213456080707074,
|
|
"loss": 4.6227,
|
|
"mean_token_accuracy": 0.23806361109018326,
|
|
"num_tokens": 61636889.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.0606574535369875,
|
|
"epoch": 2.628350208457415,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043210405879696957,
|
|
"loss": 4.5142,
|
|
"mean_token_accuracy": 0.2359112486243248,
|
|
"num_tokens": 61651033.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.104794836044311,
|
|
"epoch": 2.6289458010720668,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004320735511518011,
|
|
"loss": 4.5185,
|
|
"mean_token_accuracy": 0.23404511064291,
|
|
"num_tokens": 61663642.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.071895027160645,
|
|
"epoch": 2.6295413936867185,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004320430378726598,
|
|
"loss": 4.4892,
|
|
"mean_token_accuracy": 0.23838600367307664,
|
|
"num_tokens": 61677911.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 4.99324107170105,
|
|
"epoch": 2.6301369863013697,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004320125189606401,
|
|
"loss": 4.497,
|
|
"mean_token_accuracy": 0.2401368424296379,
|
|
"num_tokens": 61691499.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.082080078125,
|
|
"epoch": 2.6307325789160214,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043198199441683654,
|
|
"loss": 4.5894,
|
|
"mean_token_accuracy": 0.23708130419254303,
|
|
"num_tokens": 61706802.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.034438133239746,
|
|
"epoch": 2.631328171530673,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004319514642423442,
|
|
"loss": 4.4994,
|
|
"mean_token_accuracy": 0.243905408680439,
|
|
"num_tokens": 61720120.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.06504077911377,
|
|
"epoch": 2.6319237641453244,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043192092843825794,
|
|
"loss": 4.4869,
|
|
"mean_token_accuracy": 0.25022110939025877,
|
|
"num_tokens": 61733583.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 4.977686738967895,
|
|
"epoch": 2.632519356759976,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043189038700567315,
|
|
"loss": 4.4485,
|
|
"mean_token_accuracy": 0.2417871907353401,
|
|
"num_tokens": 61746990.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.055812883377075,
|
|
"epoch": 2.6331149493746278,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004318598399456852,
|
|
"loss": 4.5598,
|
|
"mean_token_accuracy": 0.23681632429361343,
|
|
"num_tokens": 61762330.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.149723100662231,
|
|
"epoch": 2.6337105419892795,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004318292872593899,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.2397893562912941,
|
|
"num_tokens": 61776573.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.183510875701904,
|
|
"epoch": 2.634306134603931,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000431798728947883,
|
|
"loss": 4.6406,
|
|
"mean_token_accuracy": 0.23315047174692155,
|
|
"num_tokens": 61790579.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.063746213912964,
|
|
"epoch": 2.6349017272185824,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004317681650122607,
|
|
"loss": 4.4832,
|
|
"mean_token_accuracy": 0.23723435550928115,
|
|
"num_tokens": 61803925.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.079684162139893,
|
|
"epoch": 2.635497319833234,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043173759545361915,
|
|
"loss": 4.5803,
|
|
"mean_token_accuracy": 0.2309301495552063,
|
|
"num_tokens": 61816964.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.066161060333252,
|
|
"epoch": 2.636092912447886,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043170702027305497,
|
|
"loss": 4.4888,
|
|
"mean_token_accuracy": 0.23913387954235077,
|
|
"num_tokens": 61830301.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.125633239746094,
|
|
"epoch": 2.636688505062537,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043167643947166466,
|
|
"loss": 4.569,
|
|
"mean_token_accuracy": 0.23068742901086808,
|
|
"num_tokens": 61843992.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.000118780136108,
|
|
"epoch": 2.6372840976771887,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004316458530505453,
|
|
"loss": 4.4989,
|
|
"mean_token_accuracy": 0.24159859418869017,
|
|
"num_tokens": 61858140.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.090306138992309,
|
|
"epoch": 2.6378796902918404,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00043161526101079386,
|
|
"loss": 4.5843,
|
|
"mean_token_accuracy": 0.22952743619680405,
|
|
"num_tokens": 61872190.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.1066296100616455,
|
|
"epoch": 2.6384752829064917,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004315846633535076,
|
|
"loss": 4.5495,
|
|
"mean_token_accuracy": 0.23934488594532013,
|
|
"num_tokens": 61885054.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.090112400054932,
|
|
"epoch": 2.6390708755211434,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004315540600797841,
|
|
"loss": 4.508,
|
|
"mean_token_accuracy": 0.24404258728027345,
|
|
"num_tokens": 61899715.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.08075966835022,
|
|
"epoch": 2.639666468135795,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000431523451190721,
|
|
"loss": 4.5662,
|
|
"mean_token_accuracy": 0.23133593499660493,
|
|
"num_tokens": 61912103.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.115781497955322,
|
|
"epoch": 2.640262060750447,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004314928366874162,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.22269611209630966,
|
|
"num_tokens": 61925007.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.062567663192749,
|
|
"epoch": 2.6408576533650985,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004314622165709678,
|
|
"loss": 4.552,
|
|
"mean_token_accuracy": 0.23863725811243058,
|
|
"num_tokens": 61939581.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.0759669780731205,
|
|
"epoch": 2.6414532459797497,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000431431590842474,
|
|
"loss": 4.6087,
|
|
"mean_token_accuracy": 0.23538561761379242,
|
|
"num_tokens": 61953857.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.040545558929443,
|
|
"epoch": 2.6420488385944014,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004314009595030335,
|
|
"loss": 4.5021,
|
|
"mean_token_accuracy": 0.23988530188798904,
|
|
"num_tokens": 61969410.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.0328937530517575,
|
|
"epoch": 2.642644431209053,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043137032255374477,
|
|
"loss": 4.4969,
|
|
"mean_token_accuracy": 0.24440397173166276,
|
|
"num_tokens": 61982161.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.1358945846557615,
|
|
"epoch": 2.6432400238237044,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004313396799957069,
|
|
"loss": 4.5361,
|
|
"mean_token_accuracy": 0.2328850343823433,
|
|
"num_tokens": 61997467.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 4.9817534446716305,
|
|
"epoch": 2.643835616438356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043130903183001887,
|
|
"loss": 4.4353,
|
|
"mean_token_accuracy": 0.2492193102836609,
|
|
"num_tokens": 62011760.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.039276933670044,
|
|
"epoch": 2.6444312090530078,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004312783780577799,
|
|
"loss": 4.4646,
|
|
"mean_token_accuracy": 0.24528899192810058,
|
|
"num_tokens": 62024778.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.046154594421386,
|
|
"epoch": 2.6450268016676595,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004312477186800898,
|
|
"loss": 4.5528,
|
|
"mean_token_accuracy": 0.2398811861872673,
|
|
"num_tokens": 62037192.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.070957660675049,
|
|
"epoch": 2.645622394282311,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004312170536980479,
|
|
"loss": 4.5337,
|
|
"mean_token_accuracy": 0.24628912657499313,
|
|
"num_tokens": 62051195.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.064628553390503,
|
|
"epoch": 2.6462179868969624,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00043118638311275437,
|
|
"loss": 4.578,
|
|
"mean_token_accuracy": 0.23076509982347487,
|
|
"num_tokens": 62066627.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.063533687591553,
|
|
"epoch": 2.646813579511614,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004311557069253092,
|
|
"loss": 4.5543,
|
|
"mean_token_accuracy": 0.23632974028587342,
|
|
"num_tokens": 62082122.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.122617483139038,
|
|
"epoch": 2.647409172126266,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004311250251368128,
|
|
"loss": 4.6,
|
|
"mean_token_accuracy": 0.23753491044044495,
|
|
"num_tokens": 62097592.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.125777864456177,
|
|
"epoch": 2.648004764740917,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043109433774836544,
|
|
"loss": 4.5719,
|
|
"mean_token_accuracy": 0.23480899333953859,
|
|
"num_tokens": 62112610.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.069112348556518,
|
|
"epoch": 2.6486003573555688,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004310636447610681,
|
|
"loss": 4.5659,
|
|
"mean_token_accuracy": 0.23357025384902955,
|
|
"num_tokens": 62126558.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.029138994216919,
|
|
"epoch": 2.6491959499702205,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004310329461760215,
|
|
"loss": 4.5251,
|
|
"mean_token_accuracy": 0.23284168690443038,
|
|
"num_tokens": 62139617.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.035804510116577,
|
|
"epoch": 2.6497915425848717,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004310022419943268,
|
|
"loss": 4.5347,
|
|
"mean_token_accuracy": 0.2351992204785347,
|
|
"num_tokens": 62154059.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.15699610710144,
|
|
"epoch": 2.6503871351995234,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043097153221708534,
|
|
"loss": 4.5897,
|
|
"mean_token_accuracy": 0.23610083609819413,
|
|
"num_tokens": 62167892.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.075070810317993,
|
|
"epoch": 2.650982727814175,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043094081684539866,
|
|
"loss": 4.5124,
|
|
"mean_token_accuracy": 0.24259361773729324,
|
|
"num_tokens": 62180788.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.033870029449463,
|
|
"epoch": 2.651578320428827,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004309100958803684,
|
|
"loss": 4.5144,
|
|
"mean_token_accuracy": 0.23196543604135514,
|
|
"num_tokens": 62195954.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.060959815979004,
|
|
"epoch": 2.6521739130434785,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004308793693230965,
|
|
"loss": 4.5196,
|
|
"mean_token_accuracy": 0.2374729573726654,
|
|
"num_tokens": 62211737.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.027676439285278,
|
|
"epoch": 2.6527695056581297,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00043084863717468504,
|
|
"loss": 4.5078,
|
|
"mean_token_accuracy": 0.24049434214830398,
|
|
"num_tokens": 62225898.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.180849170684814,
|
|
"epoch": 2.6533650982727814,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004308178994362364,
|
|
"loss": 4.6671,
|
|
"mean_token_accuracy": 0.23842693567276002,
|
|
"num_tokens": 62239517.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.108656978607177,
|
|
"epoch": 2.653960690887433,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043078715610885297,
|
|
"loss": 4.5582,
|
|
"mean_token_accuracy": 0.23212075531482695,
|
|
"num_tokens": 62254476.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.062070083618164,
|
|
"epoch": 2.6545562835020844,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004307564071936376,
|
|
"loss": 4.5185,
|
|
"mean_token_accuracy": 0.23536267429590224,
|
|
"num_tokens": 62268025.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.0417177200317385,
|
|
"epoch": 2.655151876116736,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043072565269169325,
|
|
"loss": 4.5099,
|
|
"mean_token_accuracy": 0.2499135911464691,
|
|
"num_tokens": 62279831.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.029863166809082,
|
|
"epoch": 2.655747468731388,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00043069489260412274,
|
|
"loss": 4.445,
|
|
"mean_token_accuracy": 0.24275769293308258,
|
|
"num_tokens": 62293685.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 4.982222175598144,
|
|
"epoch": 2.656343061346039,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004306641269320297,
|
|
"loss": 4.4896,
|
|
"mean_token_accuracy": 0.24869597256183623,
|
|
"num_tokens": 62305514.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.088778877258301,
|
|
"epoch": 2.6569386539606907,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043063335567651757,
|
|
"loss": 4.5558,
|
|
"mean_token_accuracy": 0.24478897601366043,
|
|
"num_tokens": 62318948.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.135190486907959,
|
|
"epoch": 2.6575342465753424,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043060257883868985,
|
|
"loss": 4.5541,
|
|
"mean_token_accuracy": 0.23258906602859497,
|
|
"num_tokens": 62331851.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.072243928909302,
|
|
"epoch": 2.658129839189994,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004305717964196507,
|
|
"loss": 4.5471,
|
|
"mean_token_accuracy": 0.23642919063568116,
|
|
"num_tokens": 62347323.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 4.993904781341553,
|
|
"epoch": 2.658725431804646,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004305410084205042,
|
|
"loss": 4.4817,
|
|
"mean_token_accuracy": 0.23361253142356872,
|
|
"num_tokens": 62360278.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.157584095001221,
|
|
"epoch": 2.659321024419297,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043051021484235457,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.22256481796503066,
|
|
"num_tokens": 62373410.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.094797658920288,
|
|
"epoch": 2.6599166170339488,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043047941568630644,
|
|
"loss": 4.5352,
|
|
"mean_token_accuracy": 0.2345601424574852,
|
|
"num_tokens": 62387575.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.018604469299317,
|
|
"epoch": 2.6605122096486005,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004304486109534644,
|
|
"loss": 4.4934,
|
|
"mean_token_accuracy": 0.2451677843928337,
|
|
"num_tokens": 62400849.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.084223699569702,
|
|
"epoch": 2.6611078022632517,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004304178006449335,
|
|
"loss": 4.6374,
|
|
"mean_token_accuracy": 0.2318843573331833,
|
|
"num_tokens": 62416778.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.178111410140991,
|
|
"epoch": 2.6617033948779034,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004303869847618187,
|
|
"loss": 4.6298,
|
|
"mean_token_accuracy": 0.2308650642633438,
|
|
"num_tokens": 62431001.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.093616724014282,
|
|
"epoch": 2.662298987492555,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004303561633052254,
|
|
"loss": 4.4974,
|
|
"mean_token_accuracy": 0.24340314269065857,
|
|
"num_tokens": 62448125.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.0367146015167235,
|
|
"epoch": 2.662894580107207,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043032533627625913,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.2363588809967041,
|
|
"num_tokens": 62463126.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.111554479598999,
|
|
"epoch": 2.6634901727218585,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004302945036760257,
|
|
"loss": 4.5999,
|
|
"mean_token_accuracy": 0.22895850688219072,
|
|
"num_tokens": 62476924.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.117081594467163,
|
|
"epoch": 2.6640857653365098,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004302636655056308,
|
|
"loss": 4.6219,
|
|
"mean_token_accuracy": 0.23029489070177078,
|
|
"num_tokens": 62492824.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.134328842163086,
|
|
"epoch": 2.6646813579511615,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043023282176618067,
|
|
"loss": 4.6233,
|
|
"mean_token_accuracy": 0.23219598978757858,
|
|
"num_tokens": 62505788.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.10077657699585,
|
|
"epoch": 2.665276950565813,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004302019724587817,
|
|
"loss": 4.5733,
|
|
"mean_token_accuracy": 0.2282026529312134,
|
|
"num_tokens": 62520433.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.081422138214111,
|
|
"epoch": 2.6658725431804644,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004301711175845402,
|
|
"loss": 4.6051,
|
|
"mean_token_accuracy": 0.2343330055475235,
|
|
"num_tokens": 62534854.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.015148115158081,
|
|
"epoch": 2.666468135795116,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00043014025714456305,
|
|
"loss": 4.4297,
|
|
"mean_token_accuracy": 0.25319105982780454,
|
|
"num_tokens": 62549693.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.105466842651367,
|
|
"epoch": 2.667063728409768,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004301093911399571,
|
|
"loss": 4.6033,
|
|
"mean_token_accuracy": 0.23407425433397294,
|
|
"num_tokens": 62563131.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.038512325286865,
|
|
"epoch": 2.667659321024419,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043007851957182954,
|
|
"loss": 4.5928,
|
|
"mean_token_accuracy": 0.23125656098127365,
|
|
"num_tokens": 62575447.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.1040864944458,
|
|
"epoch": 2.6682549136390707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043004764244128764,
|
|
"loss": 4.469,
|
|
"mean_token_accuracy": 0.24509472846984864,
|
|
"num_tokens": 62587654.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.094750499725341,
|
|
"epoch": 2.6688505062537224,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043001675974943884,
|
|
"loss": 4.5773,
|
|
"mean_token_accuracy": 0.2347065895795822,
|
|
"num_tokens": 62601510.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.082871389389038,
|
|
"epoch": 2.669446098868374,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042998587149739093,
|
|
"loss": 4.5758,
|
|
"mean_token_accuracy": 0.2329028457403183,
|
|
"num_tokens": 62616322.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.087058162689209,
|
|
"epoch": 2.670041691483026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004299549776862518,
|
|
"loss": 4.5892,
|
|
"mean_token_accuracy": 0.22896584570407869,
|
|
"num_tokens": 62631676.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.030644702911377,
|
|
"epoch": 2.670637284097677,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042992407831712957,
|
|
"loss": 4.4638,
|
|
"mean_token_accuracy": 0.23998889476060867,
|
|
"num_tokens": 62644876.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.095163249969483,
|
|
"epoch": 2.671232876712329,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004298931733911325,
|
|
"loss": 4.6026,
|
|
"mean_token_accuracy": 0.23276150226593018,
|
|
"num_tokens": 62657940.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.07121090888977,
|
|
"epoch": 2.6718284693269805,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004298622629093692,
|
|
"loss": 4.5939,
|
|
"mean_token_accuracy": 0.23459563553333282,
|
|
"num_tokens": 62673477.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.172899961471558,
|
|
"epoch": 2.6724240619416317,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004298313468729482,
|
|
"loss": 4.5859,
|
|
"mean_token_accuracy": 0.2366752043366432,
|
|
"num_tokens": 62687921.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.1053379535675045,
|
|
"epoch": 2.6730196545562834,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004298004252829787,
|
|
"loss": 4.5909,
|
|
"mean_token_accuracy": 0.23847360163927078,
|
|
"num_tokens": 62702562.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.038621044158935,
|
|
"epoch": 2.673615247170935,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004297694981405695,
|
|
"loss": 4.477,
|
|
"mean_token_accuracy": 0.24178456366062165,
|
|
"num_tokens": 62716124.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.0642212390899655,
|
|
"epoch": 2.674210839785587,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004297385654468301,
|
|
"loss": 4.5076,
|
|
"mean_token_accuracy": 0.24115408211946487,
|
|
"num_tokens": 62730775.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.0764275074005125,
|
|
"epoch": 2.674806432400238,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042970762720287,
|
|
"loss": 4.5888,
|
|
"mean_token_accuracy": 0.22457906752824783,
|
|
"num_tokens": 62745325.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.115174102783203,
|
|
"epoch": 2.6754020250148898,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004296766834097988,
|
|
"loss": 4.5745,
|
|
"mean_token_accuracy": 0.23047389537096025,
|
|
"num_tokens": 62758243.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.090630292892456,
|
|
"epoch": 2.6759976176295415,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004296457340687264,
|
|
"loss": 4.5389,
|
|
"mean_token_accuracy": 0.233713698387146,
|
|
"num_tokens": 62772177.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.056078863143921,
|
|
"epoch": 2.676593210244193,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000429614779180763,
|
|
"loss": 4.4292,
|
|
"mean_token_accuracy": 0.24921342730522156,
|
|
"num_tokens": 62786290.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.093964767456055,
|
|
"epoch": 2.6771888028588444,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004295838187470189,
|
|
"loss": 4.607,
|
|
"mean_token_accuracy": 0.22964996546506883,
|
|
"num_tokens": 62799795.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.03357081413269,
|
|
"epoch": 2.677784395473496,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004295528527686046,
|
|
"loss": 4.519,
|
|
"mean_token_accuracy": 0.2408207416534424,
|
|
"num_tokens": 62813336.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.062534952163697,
|
|
"epoch": 2.678379988088148,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004295218812466306,
|
|
"loss": 4.5099,
|
|
"mean_token_accuracy": 0.24444999396800995,
|
|
"num_tokens": 62825607.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.146382570266724,
|
|
"epoch": 2.678975580702799,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042949090418220804,
|
|
"loss": 4.6064,
|
|
"mean_token_accuracy": 0.2300449639558792,
|
|
"num_tokens": 62838747.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.041362190246582,
|
|
"epoch": 2.6795711733174508,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000429459921576448,
|
|
"loss": 4.4974,
|
|
"mean_token_accuracy": 0.23901982307434083,
|
|
"num_tokens": 62854289.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.098433971405029,
|
|
"epoch": 2.6801667659321025,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042942893343046165,
|
|
"loss": 4.5525,
|
|
"mean_token_accuracy": 0.23465299010276794,
|
|
"num_tokens": 62868534.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.076390409469605,
|
|
"epoch": 2.680762358546754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042939793974536045,
|
|
"loss": 4.5844,
|
|
"mean_token_accuracy": 0.23721134066581726,
|
|
"num_tokens": 62882755.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.063237857818604,
|
|
"epoch": 2.681357951161406,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042936694052225636,
|
|
"loss": 4.5681,
|
|
"mean_token_accuracy": 0.2344736188650131,
|
|
"num_tokens": 62898983.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.100280666351319,
|
|
"epoch": 2.681953543776057,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000429335935762261,
|
|
"loss": 4.5296,
|
|
"mean_token_accuracy": 0.23856528103351593,
|
|
"num_tokens": 62910904.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.173539447784424,
|
|
"epoch": 2.682549136390709,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004293049254664865,
|
|
"loss": 4.6522,
|
|
"mean_token_accuracy": 0.22599072605371476,
|
|
"num_tokens": 62926441.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.067302417755127,
|
|
"epoch": 2.6831447290053605,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042927390963604534,
|
|
"loss": 4.6081,
|
|
"mean_token_accuracy": 0.2297718808054924,
|
|
"num_tokens": 62941467.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.073219585418701,
|
|
"epoch": 2.6837403216200117,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004292428882720498,
|
|
"loss": 4.5443,
|
|
"mean_token_accuracy": 0.24015409797430037,
|
|
"num_tokens": 62956936.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.12854380607605,
|
|
"epoch": 2.6843359142346634,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004292118613756127,
|
|
"loss": 4.6385,
|
|
"mean_token_accuracy": 0.22997228503227235,
|
|
"num_tokens": 62970954.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.127965259552002,
|
|
"epoch": 2.684931506849315,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042918082894784676,
|
|
"loss": 4.6428,
|
|
"mean_token_accuracy": 0.23003698587417604,
|
|
"num_tokens": 62984624.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.082998132705688,
|
|
"epoch": 2.6855270994639664,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004291497909898653,
|
|
"loss": 4.5044,
|
|
"mean_token_accuracy": 0.23885841816663742,
|
|
"num_tokens": 62998183.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.126983213424682,
|
|
"epoch": 2.686122692078618,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042911874750278133,
|
|
"loss": 4.6068,
|
|
"mean_token_accuracy": 0.23092994689941407,
|
|
"num_tokens": 63011919.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.145924425125122,
|
|
"epoch": 2.68671828469327,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042908769848770857,
|
|
"loss": 4.631,
|
|
"mean_token_accuracy": 0.23065856397151946,
|
|
"num_tokens": 63026474.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.13604588508606,
|
|
"epoch": 2.6873138773079215,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004290566439457606,
|
|
"loss": 4.586,
|
|
"mean_token_accuracy": 0.23228020519018172,
|
|
"num_tokens": 63039191.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.026449489593506,
|
|
"epoch": 2.687909469922573,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042902558387805125,
|
|
"loss": 4.4725,
|
|
"mean_token_accuracy": 0.2450250506401062,
|
|
"num_tokens": 63054366.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.107707738876343,
|
|
"epoch": 2.6885050625372244,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004289945182856946,
|
|
"loss": 4.5511,
|
|
"mean_token_accuracy": 0.23919252008199693,
|
|
"num_tokens": 63068362.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.031225204467773,
|
|
"epoch": 2.689100655151876,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042896344716980507,
|
|
"loss": 4.4215,
|
|
"mean_token_accuracy": 0.2483064576983452,
|
|
"num_tokens": 63083725.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.043649578094483,
|
|
"epoch": 2.689696247766528,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004289323705314969,
|
|
"loss": 4.6274,
|
|
"mean_token_accuracy": 0.2299491733312607,
|
|
"num_tokens": 63098802.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.208697080612183,
|
|
"epoch": 2.690291840381179,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004289012883718849,
|
|
"loss": 4.709,
|
|
"mean_token_accuracy": 0.22531795203685762,
|
|
"num_tokens": 63112247.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.181109857559204,
|
|
"epoch": 2.6908874329958308,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042887020069208397,
|
|
"loss": 4.5869,
|
|
"mean_token_accuracy": 0.23846510350704192,
|
|
"num_tokens": 63125353.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.1954645156860355,
|
|
"epoch": 2.6914830256104825,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042883910749320914,
|
|
"loss": 4.7647,
|
|
"mean_token_accuracy": 0.2171659991145134,
|
|
"num_tokens": 63138875.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.096430349349975,
|
|
"epoch": 2.692078618225134,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042880800877637555,
|
|
"loss": 4.5738,
|
|
"mean_token_accuracy": 0.23869656026363373,
|
|
"num_tokens": 63152785.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.103035593032837,
|
|
"epoch": 2.6926742108397854,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042877690454269884,
|
|
"loss": 4.5423,
|
|
"mean_token_accuracy": 0.23647053837776183,
|
|
"num_tokens": 63167076.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.03149905204773,
|
|
"epoch": 2.693269803454437,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004287457947932946,
|
|
"loss": 4.5488,
|
|
"mean_token_accuracy": 0.23697677999734879,
|
|
"num_tokens": 63181206.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.058865690231324,
|
|
"epoch": 2.693865396069089,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004287146795292787,
|
|
"loss": 4.5348,
|
|
"mean_token_accuracy": 0.2412963703274727,
|
|
"num_tokens": 63194259.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.038896369934082,
|
|
"epoch": 2.6944609886837405,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004286835587517671,
|
|
"loss": 4.4051,
|
|
"mean_token_accuracy": 0.24485152512788771,
|
|
"num_tokens": 63208325.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.030784749984742,
|
|
"epoch": 2.6950565812983918,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004286524324618761,
|
|
"loss": 4.5374,
|
|
"mean_token_accuracy": 0.239194655418396,
|
|
"num_tokens": 63221535.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.121603727340698,
|
|
"epoch": 2.6956521739130435,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042862130066072225,
|
|
"loss": 4.5936,
|
|
"mean_token_accuracy": 0.23283600807189941,
|
|
"num_tokens": 63236279.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.077310562133789,
|
|
"epoch": 2.696247766527695,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000428590163349422,
|
|
"loss": 4.5385,
|
|
"mean_token_accuracy": 0.23959601670503616,
|
|
"num_tokens": 63250524.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.1429585933685305,
|
|
"epoch": 2.6968433591423464,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042855902052909244,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.22585505694150926,
|
|
"num_tokens": 63264898.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.119723272323609,
|
|
"epoch": 2.697438951756998,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00042852787220085044,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.22995912730693818,
|
|
"num_tokens": 63279756.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.089417028427124,
|
|
"epoch": 2.69803454437165,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042849671836581323,
|
|
"loss": 4.5764,
|
|
"mean_token_accuracy": 0.24052852690219878,
|
|
"num_tokens": 63292758.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.038211727142334,
|
|
"epoch": 2.6986301369863015,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042846555902509845,
|
|
"loss": 4.4796,
|
|
"mean_token_accuracy": 0.2421066015958786,
|
|
"num_tokens": 63307663.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.123705291748047,
|
|
"epoch": 2.699225729600953,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042843439417982344,
|
|
"loss": 4.6215,
|
|
"mean_token_accuracy": 0.23025379031896592,
|
|
"num_tokens": 63322258.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.047705936431885,
|
|
"epoch": 2.6998213222156044,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042840322383110626,
|
|
"loss": 4.5472,
|
|
"mean_token_accuracy": 0.2429155722260475,
|
|
"num_tokens": 63338095.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.08509669303894,
|
|
"epoch": 2.700416914830256,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004283720479800648,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.22749079316854476,
|
|
"num_tokens": 63354156.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.091250801086426,
|
|
"epoch": 2.701012507444908,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004283408666278174,
|
|
"loss": 4.5356,
|
|
"mean_token_accuracy": 0.241907100379467,
|
|
"num_tokens": 63367327.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.059023714065551,
|
|
"epoch": 2.701608100059559,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042830967977548236,
|
|
"loss": 4.507,
|
|
"mean_token_accuracy": 0.2407245397567749,
|
|
"num_tokens": 63381551.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.07986421585083,
|
|
"epoch": 2.702203692674211,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004282784874241785,
|
|
"loss": 4.5717,
|
|
"mean_token_accuracy": 0.23754940629005433,
|
|
"num_tokens": 63395185.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.022988653182983,
|
|
"epoch": 2.7027992852888625,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042824728957502437,
|
|
"loss": 4.5036,
|
|
"mean_token_accuracy": 0.23741064369678497,
|
|
"num_tokens": 63408879.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.084809446334839,
|
|
"epoch": 2.7033948779035137,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004282160862291392,
|
|
"loss": 4.5126,
|
|
"mean_token_accuracy": 0.231196029484272,
|
|
"num_tokens": 63421982.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.068216562271118,
|
|
"epoch": 2.7039904705181654,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004281848773876421,
|
|
"loss": 4.5461,
|
|
"mean_token_accuracy": 0.23607117384672166,
|
|
"num_tokens": 63435168.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.191574001312256,
|
|
"epoch": 2.704586063132817,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042815366305165256,
|
|
"loss": 4.628,
|
|
"mean_token_accuracy": 0.23399531543254853,
|
|
"num_tokens": 63448998.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.067345857620239,
|
|
"epoch": 2.705181655747469,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004281224432222901,
|
|
"loss": 4.5098,
|
|
"mean_token_accuracy": 0.23508832454681397,
|
|
"num_tokens": 63462662.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.12678894996643,
|
|
"epoch": 2.7057772483621205,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004280912179006746,
|
|
"loss": 4.6709,
|
|
"mean_token_accuracy": 0.22884011417627334,
|
|
"num_tokens": 63476799.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.0781590938568115,
|
|
"epoch": 2.7063728409767718,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000428059987087926,
|
|
"loss": 4.563,
|
|
"mean_token_accuracy": 0.2401687353849411,
|
|
"num_tokens": 63490349.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.103396606445313,
|
|
"epoch": 2.7069684335914235,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042802875078516446,
|
|
"loss": 4.5569,
|
|
"mean_token_accuracy": 0.23977499604225158,
|
|
"num_tokens": 63504940.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.069579839706421,
|
|
"epoch": 2.707564026206075,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004279975089935106,
|
|
"loss": 4.4857,
|
|
"mean_token_accuracy": 0.2377207398414612,
|
|
"num_tokens": 63518280.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.056358289718628,
|
|
"epoch": 2.7081596188207264,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004279662617140847,
|
|
"loss": 4.5378,
|
|
"mean_token_accuracy": 0.23384436964988708,
|
|
"num_tokens": 63533379.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.168994426727295,
|
|
"epoch": 2.708755211435378,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042793500894800776,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.22937921285629273,
|
|
"num_tokens": 63546219.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.046578216552734,
|
|
"epoch": 2.70935080405003,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004279037506964007,
|
|
"loss": 4.469,
|
|
"mean_token_accuracy": 0.24253455698490142,
|
|
"num_tokens": 63557793.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.1014526844024655,
|
|
"epoch": 2.7099463966646815,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004278724869603847,
|
|
"loss": 4.5374,
|
|
"mean_token_accuracy": 0.23715200126171113,
|
|
"num_tokens": 63571949.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.150273132324219,
|
|
"epoch": 2.710541989279333,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042784121774108117,
|
|
"loss": 4.6423,
|
|
"mean_token_accuracy": 0.23232463449239732,
|
|
"num_tokens": 63586166.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.141101980209351,
|
|
"epoch": 2.7111375818939845,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042780994303961165,
|
|
"loss": 4.6472,
|
|
"mean_token_accuracy": 0.22286111861467361,
|
|
"num_tokens": 63599903.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.128673791885376,
|
|
"epoch": 2.711733174508636,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004277786628570979,
|
|
"loss": 4.5805,
|
|
"mean_token_accuracy": 0.22636838555335997,
|
|
"num_tokens": 63613260.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.132739019393921,
|
|
"epoch": 2.712328767123288,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000427747377194662,
|
|
"loss": 4.583,
|
|
"mean_token_accuracy": 0.2329339861869812,
|
|
"num_tokens": 63626208.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.115505409240723,
|
|
"epoch": 2.712924359737939,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042771608605342596,
|
|
"loss": 4.5596,
|
|
"mean_token_accuracy": 0.23413416743278503,
|
|
"num_tokens": 63639173.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.149775552749634,
|
|
"epoch": 2.713519952352591,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042768478943451223,
|
|
"loss": 4.5401,
|
|
"mean_token_accuracy": 0.2380968302488327,
|
|
"num_tokens": 63652683.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.088391923904419,
|
|
"epoch": 2.7141155449672425,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00042765348733904337,
|
|
"loss": 4.5979,
|
|
"mean_token_accuracy": 0.22790025025606156,
|
|
"num_tokens": 63667617.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.0075586318969725,
|
|
"epoch": 2.7147111375818938,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004276221797681421,
|
|
"loss": 4.495,
|
|
"mean_token_accuracy": 0.24103093445301055,
|
|
"num_tokens": 63679990.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.153512001037598,
|
|
"epoch": 2.7153067301965454,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004275908667229314,
|
|
"loss": 4.6718,
|
|
"mean_token_accuracy": 0.2266104519367218,
|
|
"num_tokens": 63696320.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.098016881942749,
|
|
"epoch": 2.715902322811197,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042755954820453433,
|
|
"loss": 4.5277,
|
|
"mean_token_accuracy": 0.23756900429725647,
|
|
"num_tokens": 63710800.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.08601975440979,
|
|
"epoch": 2.716497915425849,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042752822421407443,
|
|
"loss": 4.5849,
|
|
"mean_token_accuracy": 0.24110344052314758,
|
|
"num_tokens": 63723812.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.08651123046875,
|
|
"epoch": 2.7170935080405005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042749689475267514,
|
|
"loss": 4.6147,
|
|
"mean_token_accuracy": 0.23845599740743637,
|
|
"num_tokens": 63737559.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.123579454421997,
|
|
"epoch": 2.717689100655152,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042746555982146,
|
|
"loss": 4.6074,
|
|
"mean_token_accuracy": 0.23419202566146852,
|
|
"num_tokens": 63752524.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.137304639816284,
|
|
"epoch": 2.7182846932698035,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004274342194215533,
|
|
"loss": 4.5676,
|
|
"mean_token_accuracy": 0.231210158765316,
|
|
"num_tokens": 63765694.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.013597869873047,
|
|
"epoch": 2.718880285884455,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004274028735540789,
|
|
"loss": 4.5074,
|
|
"mean_token_accuracy": 0.2404363438487053,
|
|
"num_tokens": 63779252.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.140696573257446,
|
|
"epoch": 2.7194758784991064,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004273715222201613,
|
|
"loss": 4.6345,
|
|
"mean_token_accuracy": 0.22580750286579132,
|
|
"num_tokens": 63792267.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.089345788955688,
|
|
"epoch": 2.720071471113758,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00042734016542092485,
|
|
"loss": 4.5809,
|
|
"mean_token_accuracy": 0.23437791913747788,
|
|
"num_tokens": 63804775.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.0413744926452635,
|
|
"epoch": 2.72066706372841,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042730880315749445,
|
|
"loss": 4.4773,
|
|
"mean_token_accuracy": 0.25100981444120407,
|
|
"num_tokens": 63819521.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.020859956741333,
|
|
"epoch": 2.721262656343061,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004272774354309948,
|
|
"loss": 4.4915,
|
|
"mean_token_accuracy": 0.2415880396962166,
|
|
"num_tokens": 63835485.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.126900768280029,
|
|
"epoch": 2.721858248957713,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042724606224255117,
|
|
"loss": 4.5998,
|
|
"mean_token_accuracy": 0.2329126015305519,
|
|
"num_tokens": 63848467.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.054073333740234,
|
|
"epoch": 2.7224538415723645,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00042721468359328883,
|
|
"loss": 4.5109,
|
|
"mean_token_accuracy": 0.23878805339336395,
|
|
"num_tokens": 63863540.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.0380536079406735,
|
|
"epoch": 2.723049434187016,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00042718329948433336,
|
|
"loss": 4.5012,
|
|
"mean_token_accuracy": 0.2383572652935982,
|
|
"num_tokens": 63875973.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.084241104125977,
|
|
"epoch": 2.723645026801668,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004271519099168103,
|
|
"loss": 4.5447,
|
|
"mean_token_accuracy": 0.2394036442041397,
|
|
"num_tokens": 63891217.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.091781425476074,
|
|
"epoch": 2.724240619416319,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004271205148918456,
|
|
"loss": 4.5953,
|
|
"mean_token_accuracy": 0.2281499058008194,
|
|
"num_tokens": 63904666.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.14048137664795,
|
|
"epoch": 2.724836212030971,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004270891144105654,
|
|
"loss": 4.5883,
|
|
"mean_token_accuracy": 0.23646706491708755,
|
|
"num_tokens": 63918950.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.117878198623657,
|
|
"epoch": 2.7254318046456225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042705770847409596,
|
|
"loss": 4.5697,
|
|
"mean_token_accuracy": 0.23211640864610672,
|
|
"num_tokens": 63932312.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 4.984489059448242,
|
|
"epoch": 2.7260273972602738,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004270262970835637,
|
|
"loss": 4.4926,
|
|
"mean_token_accuracy": 0.2442118138074875,
|
|
"num_tokens": 63943764.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.079328632354736,
|
|
"epoch": 2.7266229898749255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042699488024009537,
|
|
"loss": 4.5597,
|
|
"mean_token_accuracy": 0.23172975778579713,
|
|
"num_tokens": 63957768.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.15991063117981,
|
|
"epoch": 2.727218582489577,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042696345794481785,
|
|
"loss": 4.5861,
|
|
"mean_token_accuracy": 0.2350366547703743,
|
|
"num_tokens": 63971514.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.120537185668946,
|
|
"epoch": 2.727814175104229,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004269320301988581,
|
|
"loss": 4.5584,
|
|
"mean_token_accuracy": 0.23663115501403809,
|
|
"num_tokens": 63984868.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.0425153255462645,
|
|
"epoch": 2.7284097677188806,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004269005970033435,
|
|
"loss": 4.5682,
|
|
"mean_token_accuracy": 0.2348833739757538,
|
|
"num_tokens": 63999935.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.07809476852417,
|
|
"epoch": 2.729005360333532,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004268691583594014,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.23688274770975112,
|
|
"num_tokens": 64014181.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.121262168884277,
|
|
"epoch": 2.7296009529481835,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004268377142681596,
|
|
"loss": 4.5515,
|
|
"mean_token_accuracy": 0.2353332221508026,
|
|
"num_tokens": 64029041.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.010901069641113,
|
|
"epoch": 2.730196545562835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042680626473074585,
|
|
"loss": 4.4718,
|
|
"mean_token_accuracy": 0.23682076185941697,
|
|
"num_tokens": 64042310.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.030213499069214,
|
|
"epoch": 2.7307921381774864,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042677480974828816,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.24500638097524643,
|
|
"num_tokens": 64055947.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.053042888641357,
|
|
"epoch": 2.731387730792138,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042674334932191475,
|
|
"loss": 4.4897,
|
|
"mean_token_accuracy": 0.2388372078537941,
|
|
"num_tokens": 64071107.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.154867029190063,
|
|
"epoch": 2.73198332340679,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042671188345275423,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.2294144630432129,
|
|
"num_tokens": 64084938.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.087760925292969,
|
|
"epoch": 2.732578916021441,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042668041214193514,
|
|
"loss": 4.5886,
|
|
"mean_token_accuracy": 0.2360007271170616,
|
|
"num_tokens": 64099260.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.108751964569092,
|
|
"epoch": 2.733174508636093,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004266489353905862,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.2271900460124016,
|
|
"num_tokens": 64113449.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.136045694351196,
|
|
"epoch": 2.7337701012507445,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004266174531998365,
|
|
"loss": 4.5691,
|
|
"mean_token_accuracy": 0.22988448292016983,
|
|
"num_tokens": 64127779.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.085590410232544,
|
|
"epoch": 2.734365693865396,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042658596557081536,
|
|
"loss": 4.5535,
|
|
"mean_token_accuracy": 0.23699902445077897,
|
|
"num_tokens": 64141805.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.178335046768188,
|
|
"epoch": 2.734961286480048,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042655447250465205,
|
|
"loss": 4.6388,
|
|
"mean_token_accuracy": 0.22928952425718307,
|
|
"num_tokens": 64155492.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.134626579284668,
|
|
"epoch": 2.735556879094699,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042652297400247625,
|
|
"loss": 4.6213,
|
|
"mean_token_accuracy": 0.23388029187917708,
|
|
"num_tokens": 64170471.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.011634111404419,
|
|
"epoch": 2.736152471709351,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004264914700654177,
|
|
"loss": 4.4824,
|
|
"mean_token_accuracy": 0.243955659866333,
|
|
"num_tokens": 64185322.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.107969188690186,
|
|
"epoch": 2.7367480643240025,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004264599606946065,
|
|
"loss": 4.6042,
|
|
"mean_token_accuracy": 0.2308307707309723,
|
|
"num_tokens": 64199903.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.064512825012207,
|
|
"epoch": 2.737343656938654,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004264284458911727,
|
|
"loss": 4.5675,
|
|
"mean_token_accuracy": 0.23730240911245346,
|
|
"num_tokens": 64213090.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.0625317096710205,
|
|
"epoch": 2.7379392495533055,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042639692565624675,
|
|
"loss": 4.5295,
|
|
"mean_token_accuracy": 0.2349582001566887,
|
|
"num_tokens": 64227797.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.08428955078125,
|
|
"epoch": 2.738534842167957,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004263653999909593,
|
|
"loss": 4.562,
|
|
"mean_token_accuracy": 0.23601909428834916,
|
|
"num_tokens": 64241840.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.108221340179443,
|
|
"epoch": 2.7391304347826084,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042633386889644095,
|
|
"loss": 4.5722,
|
|
"mean_token_accuracy": 0.23722259551286698,
|
|
"num_tokens": 64255897.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.031377172470092,
|
|
"epoch": 2.73972602739726,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042630233237382284,
|
|
"loss": 4.4643,
|
|
"mean_token_accuracy": 0.24646001756191255,
|
|
"num_tokens": 64269479.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.101531076431274,
|
|
"epoch": 2.740321620011912,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042627079042423607,
|
|
"loss": 4.6318,
|
|
"mean_token_accuracy": 0.23337089866399766,
|
|
"num_tokens": 64282042.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.0867222309112545,
|
|
"epoch": 2.7409172126265635,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00042623924304881195,
|
|
"loss": 4.4949,
|
|
"mean_token_accuracy": 0.23897680789232253,
|
|
"num_tokens": 64297363.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.036734342575073,
|
|
"epoch": 2.741512805241215,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042620769024868217,
|
|
"loss": 4.5249,
|
|
"mean_token_accuracy": 0.24171288758516313,
|
|
"num_tokens": 64310843.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.137611627578735,
|
|
"epoch": 2.7421083978558665,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00042617613202497836,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.23176204562187194,
|
|
"num_tokens": 64327904.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.116103601455689,
|
|
"epoch": 2.742703990470518,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042614456837883243,
|
|
"loss": 4.5696,
|
|
"mean_token_accuracy": 0.23388483971357346,
|
|
"num_tokens": 64342823.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.131014204025268,
|
|
"epoch": 2.74329958308517,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042611299931137657,
|
|
"loss": 4.6108,
|
|
"mean_token_accuracy": 0.22724425792694092,
|
|
"num_tokens": 64356501.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.031408405303955,
|
|
"epoch": 2.743895175699821,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004260814248237432,
|
|
"loss": 4.5332,
|
|
"mean_token_accuracy": 0.23230879455804826,
|
|
"num_tokens": 64370564.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.069030237197876,
|
|
"epoch": 2.744490768314473,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042604984491706477,
|
|
"loss": 4.4851,
|
|
"mean_token_accuracy": 0.23938264101743698,
|
|
"num_tokens": 64385830.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.088080501556396,
|
|
"epoch": 2.7450863609291245,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000426018259592474,
|
|
"loss": 4.5722,
|
|
"mean_token_accuracy": 0.2315507113933563,
|
|
"num_tokens": 64401019.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.063361787796021,
|
|
"epoch": 2.745681953543776,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00042598666885110373,
|
|
"loss": 4.5557,
|
|
"mean_token_accuracy": 0.23553070574998855,
|
|
"num_tokens": 64414945.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.062522602081299,
|
|
"epoch": 2.746277546158428,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004259550726940872,
|
|
"loss": 4.5064,
|
|
"mean_token_accuracy": 0.2369772657752037,
|
|
"num_tokens": 64429837.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.094611597061157,
|
|
"epoch": 2.746873138773079,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042592347112255756,
|
|
"loss": 4.6432,
|
|
"mean_token_accuracy": 0.22720303982496262,
|
|
"num_tokens": 64442993.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.048162126541138,
|
|
"epoch": 2.747468731387731,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042589186413764845,
|
|
"loss": 4.4831,
|
|
"mean_token_accuracy": 0.24017060697078704,
|
|
"num_tokens": 64457373.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.0369141578674315,
|
|
"epoch": 2.7480643240023825,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042586025174049354,
|
|
"loss": 4.4693,
|
|
"mean_token_accuracy": 0.24502431303262712,
|
|
"num_tokens": 64471020.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.043959474563598,
|
|
"epoch": 2.748659916617034,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004258286339322266,
|
|
"loss": 4.5128,
|
|
"mean_token_accuracy": 0.24210004210472108,
|
|
"num_tokens": 64484403.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 4.99142050743103,
|
|
"epoch": 2.7492555092316855,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004257970107139819,
|
|
"loss": 4.5762,
|
|
"mean_token_accuracy": 0.23520198166370393,
|
|
"num_tokens": 64497405.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.066852569580078,
|
|
"epoch": 2.749851101846337,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004257653820868935,
|
|
"loss": 4.572,
|
|
"mean_token_accuracy": 0.23324215561151504,
|
|
"num_tokens": 64511072.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.105407619476319,
|
|
"epoch": 2.7504466944609884,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004257337480520961,
|
|
"loss": 4.5736,
|
|
"mean_token_accuracy": 0.22977769672870635,
|
|
"num_tokens": 64526546.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.100863409042359,
|
|
"epoch": 2.75104228707564,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004257021086107241,
|
|
"loss": 4.6065,
|
|
"mean_token_accuracy": 0.23507222831249236,
|
|
"num_tokens": 64541735.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.096945667266846,
|
|
"epoch": 2.751637879690292,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004256704637639126,
|
|
"loss": 4.4572,
|
|
"mean_token_accuracy": 0.23734420388936997,
|
|
"num_tokens": 64555902.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.091366815567016,
|
|
"epoch": 2.7522334723049435,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004256388135127965,
|
|
"loss": 4.5272,
|
|
"mean_token_accuracy": 0.23878768980503082,
|
|
"num_tokens": 64570415.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.052606678009033,
|
|
"epoch": 2.7528290649195952,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004256071578585111,
|
|
"loss": 4.4935,
|
|
"mean_token_accuracy": 0.24131642132997513,
|
|
"num_tokens": 64583314.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.100707149505615,
|
|
"epoch": 2.7534246575342465,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004255754968021918,
|
|
"loss": 4.626,
|
|
"mean_token_accuracy": 0.22985349595546722,
|
|
"num_tokens": 64598459.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.076352596282959,
|
|
"epoch": 2.754020250148898,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004255438303449742,
|
|
"loss": 4.5582,
|
|
"mean_token_accuracy": 0.23608618825674058,
|
|
"num_tokens": 64613152.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.064296293258667,
|
|
"epoch": 2.75461584276355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042551215848799423,
|
|
"loss": 4.5428,
|
|
"mean_token_accuracy": 0.23787155747413635,
|
|
"num_tokens": 64627877.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.125106239318848,
|
|
"epoch": 2.755211435378201,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00042548048123238787,
|
|
"loss": 4.547,
|
|
"mean_token_accuracy": 0.23159880042076111,
|
|
"num_tokens": 64641841.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.092001247406006,
|
|
"epoch": 2.755807027992853,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042544879857929133,
|
|
"loss": 4.5238,
|
|
"mean_token_accuracy": 0.2441907122731209,
|
|
"num_tokens": 64654174.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.071040058135987,
|
|
"epoch": 2.7564026206075045,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042541711052984096,
|
|
"loss": 4.5717,
|
|
"mean_token_accuracy": 0.23917652368545533,
|
|
"num_tokens": 64667914.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.03658013343811,
|
|
"epoch": 2.7569982132221558,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042538541708517344,
|
|
"loss": 4.5171,
|
|
"mean_token_accuracy": 0.2414022535085678,
|
|
"num_tokens": 64681786.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.052269363403321,
|
|
"epoch": 2.7575938058368075,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042535371824642545,
|
|
"loss": 4.5419,
|
|
"mean_token_accuracy": 0.24239104986190796,
|
|
"num_tokens": 64697781.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.0269927978515625,
|
|
"epoch": 2.758189398451459,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004253220140147341,
|
|
"loss": 4.4501,
|
|
"mean_token_accuracy": 0.2480457082390785,
|
|
"num_tokens": 64709604.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.105495834350586,
|
|
"epoch": 2.758784991066111,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004252903043912365,
|
|
"loss": 4.5669,
|
|
"mean_token_accuracy": 0.2280277967453003,
|
|
"num_tokens": 64725059.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.095717239379883,
|
|
"epoch": 2.7593805836807626,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042525858937707,
|
|
"loss": 4.5239,
|
|
"mean_token_accuracy": 0.23769508600234984,
|
|
"num_tokens": 64739192.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 4.956442356109619,
|
|
"epoch": 2.759976176295414,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004252268689733722,
|
|
"loss": 4.4346,
|
|
"mean_token_accuracy": 0.24995840936899186,
|
|
"num_tokens": 64754037.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.066587638854981,
|
|
"epoch": 2.7605717689100655,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042519514318128086,
|
|
"loss": 4.5338,
|
|
"mean_token_accuracy": 0.2333672448992729,
|
|
"num_tokens": 64769417.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.159424734115601,
|
|
"epoch": 2.761167361524717,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042516341200193403,
|
|
"loss": 4.6024,
|
|
"mean_token_accuracy": 0.24125330597162248,
|
|
"num_tokens": 64782725.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.050954866409302,
|
|
"epoch": 2.7617629541393685,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042513167543646975,
|
|
"loss": 4.4905,
|
|
"mean_token_accuracy": 0.2410503014922142,
|
|
"num_tokens": 64796522.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.073007822036743,
|
|
"epoch": 2.76235854675402,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042509993348602634,
|
|
"loss": 4.5021,
|
|
"mean_token_accuracy": 0.2443617671728134,
|
|
"num_tokens": 64810276.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.101093769073486,
|
|
"epoch": 2.762954139368672,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042506818615174237,
|
|
"loss": 4.6315,
|
|
"mean_token_accuracy": 0.2264831319451332,
|
|
"num_tokens": 64825661.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.064677906036377,
|
|
"epoch": 2.7635497319833235,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004250364334347565,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.2342449575662613,
|
|
"num_tokens": 64839183.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.082584953308105,
|
|
"epoch": 2.7641453245979752,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042500467533620773,
|
|
"loss": 4.57,
|
|
"mean_token_accuracy": 0.23739833235740662,
|
|
"num_tokens": 64853568.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.025637006759643,
|
|
"epoch": 2.7647409172126265,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004249729118572352,
|
|
"loss": 4.4943,
|
|
"mean_token_accuracy": 0.2472066655755043,
|
|
"num_tokens": 64868340.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.080069923400879,
|
|
"epoch": 2.765336509827278,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042494114299897813,
|
|
"loss": 4.5663,
|
|
"mean_token_accuracy": 0.23243776559829712,
|
|
"num_tokens": 64881547.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.10986704826355,
|
|
"epoch": 2.76593210244193,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004249093687625761,
|
|
"loss": 4.5273,
|
|
"mean_token_accuracy": 0.2398738220334053,
|
|
"num_tokens": 64895570.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.108273363113403,
|
|
"epoch": 2.766527695056581,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004248775891491686,
|
|
"loss": 4.5653,
|
|
"mean_token_accuracy": 0.2332261472940445,
|
|
"num_tokens": 64909113.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.012200450897216,
|
|
"epoch": 2.767123287671233,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004248458041598958,
|
|
"loss": 4.4789,
|
|
"mean_token_accuracy": 0.24066567420959473,
|
|
"num_tokens": 64922077.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.047546100616455,
|
|
"epoch": 2.7677188802858845,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004248140137958976,
|
|
"loss": 4.4899,
|
|
"mean_token_accuracy": 0.23413894921541215,
|
|
"num_tokens": 64936456.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.188952493667602,
|
|
"epoch": 2.768314472900536,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042478221805831437,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.22404478043317794,
|
|
"num_tokens": 64951545.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.21210126876831,
|
|
"epoch": 2.7689100655151875,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042475041694828644,
|
|
"loss": 4.7014,
|
|
"mean_token_accuracy": 0.22493351250886917,
|
|
"num_tokens": 64965234.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.032357549667358,
|
|
"epoch": 2.769505658129839,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042471861046695453,
|
|
"loss": 4.4283,
|
|
"mean_token_accuracy": 0.25677364468574526,
|
|
"num_tokens": 64979585.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.040942192077637,
|
|
"epoch": 2.770101250744491,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004246867986154595,
|
|
"loss": 4.5321,
|
|
"mean_token_accuracy": 0.24292662888765335,
|
|
"num_tokens": 64993503.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.047360420227051,
|
|
"epoch": 2.7706968433591426,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004246549813949424,
|
|
"loss": 4.5277,
|
|
"mean_token_accuracy": 0.24097055047750474,
|
|
"num_tokens": 65007808.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.060472583770752,
|
|
"epoch": 2.771292435973794,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004246231588065444,
|
|
"loss": 4.5049,
|
|
"mean_token_accuracy": 0.23469975739717483,
|
|
"num_tokens": 65021721.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.088231801986694,
|
|
"epoch": 2.7718880285884455,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000424591330851407,
|
|
"loss": 4.5691,
|
|
"mean_token_accuracy": 0.23756039142608643,
|
|
"num_tokens": 65034133.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.075837516784668,
|
|
"epoch": 2.772483621203097,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004245594975306718,
|
|
"loss": 4.5526,
|
|
"mean_token_accuracy": 0.23047067373991012,
|
|
"num_tokens": 65047918.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.171376800537109,
|
|
"epoch": 2.7730792138177485,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042452765884548057,
|
|
"loss": 4.7159,
|
|
"mean_token_accuracy": 0.22302288860082625,
|
|
"num_tokens": 65062368.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.088457012176514,
|
|
"epoch": 2.7736748064324,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042449581479697527,
|
|
"loss": 4.4829,
|
|
"mean_token_accuracy": 0.24217704981565474,
|
|
"num_tokens": 65076808.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.066197633743286,
|
|
"epoch": 2.774270399047052,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004244639653862983,
|
|
"loss": 4.5029,
|
|
"mean_token_accuracy": 0.2404577225446701,
|
|
"num_tokens": 65088860.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.019446802139282,
|
|
"epoch": 2.7748659916617036,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042443211061459185,
|
|
"loss": 4.4843,
|
|
"mean_token_accuracy": 0.2471271649003029,
|
|
"num_tokens": 65102953.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.089361047744751,
|
|
"epoch": 2.775461584276355,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042440025048299845,
|
|
"loss": 4.5163,
|
|
"mean_token_accuracy": 0.2471410095691681,
|
|
"num_tokens": 65116466.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.084244632720948,
|
|
"epoch": 2.7760571768910065,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042436838499266107,
|
|
"loss": 4.5251,
|
|
"mean_token_accuracy": 0.24816068410873413,
|
|
"num_tokens": 65129571.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 4.985368728637695,
|
|
"epoch": 2.776652769505658,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00042433651414472255,
|
|
"loss": 4.494,
|
|
"mean_token_accuracy": 0.23964752852916718,
|
|
"num_tokens": 65142890.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.080405902862549,
|
|
"epoch": 2.77724836212031,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042430463794032613,
|
|
"loss": 4.5328,
|
|
"mean_token_accuracy": 0.23765770345926285,
|
|
"num_tokens": 65158375.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.130095195770264,
|
|
"epoch": 2.777843954734961,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000424272756380615,
|
|
"loss": 4.6364,
|
|
"mean_token_accuracy": 0.23106836080551146,
|
|
"num_tokens": 65172249.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.086625337600708,
|
|
"epoch": 2.778439547349613,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004242408694667329,
|
|
"loss": 4.5344,
|
|
"mean_token_accuracy": 0.23936173170804978,
|
|
"num_tokens": 65186895.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.037617826461792,
|
|
"epoch": 2.7790351399642645,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004242089771998234,
|
|
"loss": 4.5397,
|
|
"mean_token_accuracy": 0.2411547914147377,
|
|
"num_tokens": 65199923.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.075797414779663,
|
|
"epoch": 2.779630732578916,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042417707958103054,
|
|
"loss": 4.5075,
|
|
"mean_token_accuracy": 0.23253221958875656,
|
|
"num_tokens": 65213038.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.101133060455322,
|
|
"epoch": 2.7802263251935675,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004241451766114984,
|
|
"loss": 4.5321,
|
|
"mean_token_accuracy": 0.24029485434293746,
|
|
"num_tokens": 65227138.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.059375476837158,
|
|
"epoch": 2.780821917808219,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042411326829237117,
|
|
"loss": 4.5248,
|
|
"mean_token_accuracy": 0.23530125319957734,
|
|
"num_tokens": 65240015.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.168545389175415,
|
|
"epoch": 2.781417510422871,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042408135462479354,
|
|
"loss": 4.6412,
|
|
"mean_token_accuracy": 0.22974630445241928,
|
|
"num_tokens": 65253793.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.0419331073760985,
|
|
"epoch": 2.7820131030375226,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004240494356099101,
|
|
"loss": 4.5079,
|
|
"mean_token_accuracy": 0.24015427082777024,
|
|
"num_tokens": 65266238.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.0291706085205075,
|
|
"epoch": 2.782608695652174,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004240175112488657,
|
|
"loss": 4.5514,
|
|
"mean_token_accuracy": 0.24319675266742707,
|
|
"num_tokens": 65278141.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.113671350479126,
|
|
"epoch": 2.7832042882668255,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004239855815428055,
|
|
"loss": 4.5895,
|
|
"mean_token_accuracy": 0.22847835421562196,
|
|
"num_tokens": 65292535.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.103194332122802,
|
|
"epoch": 2.7837998808814772,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004239536464928747,
|
|
"loss": 4.5513,
|
|
"mean_token_accuracy": 0.24079431891441344,
|
|
"num_tokens": 65305801.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.0636927604675295,
|
|
"epoch": 2.7843954734961285,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004239217061002188,
|
|
"loss": 4.5284,
|
|
"mean_token_accuracy": 0.24342069625854493,
|
|
"num_tokens": 65319322.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.146034193038941,
|
|
"epoch": 2.78499106611078,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004238897603659834,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.23132820278406144,
|
|
"num_tokens": 65333135.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.146565246582031,
|
|
"epoch": 2.785586658725432,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004238578092913144,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.23562348634004593,
|
|
"num_tokens": 65347224.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.025237226486206,
|
|
"epoch": 2.786182251340083,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004238258528773578,
|
|
"loss": 4.4527,
|
|
"mean_token_accuracy": 0.24451925605535507,
|
|
"num_tokens": 65361053.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.039666366577149,
|
|
"epoch": 2.786777843954735,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042379389112525985,
|
|
"loss": 4.4885,
|
|
"mean_token_accuracy": 0.2411073178052902,
|
|
"num_tokens": 65373340.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.058377122879028,
|
|
"epoch": 2.7873734365693865,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004237619240361669,
|
|
"loss": 4.5329,
|
|
"mean_token_accuracy": 0.23196056634187698,
|
|
"num_tokens": 65389546.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.152851295471192,
|
|
"epoch": 2.787969029184038,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042372995161122566,
|
|
"loss": 4.5484,
|
|
"mean_token_accuracy": 0.23922085464000703,
|
|
"num_tokens": 65402354.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 4.975656795501709,
|
|
"epoch": 2.78856462179869,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00042369797385158293,
|
|
"loss": 4.4534,
|
|
"mean_token_accuracy": 0.24237369000911713,
|
|
"num_tokens": 65417822.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.104886817932129,
|
|
"epoch": 2.789160214413341,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042366599075838553,
|
|
"loss": 4.5881,
|
|
"mean_token_accuracy": 0.2329345554113388,
|
|
"num_tokens": 65431633.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.041503095626831,
|
|
"epoch": 2.789755807027993,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042363400233278077,
|
|
"loss": 4.5267,
|
|
"mean_token_accuracy": 0.24113010466098786,
|
|
"num_tokens": 65445766.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.132372283935547,
|
|
"epoch": 2.7903513996426446,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004236020085759161,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.23252860754728316,
|
|
"num_tokens": 65459672.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.084062147140503,
|
|
"epoch": 2.790946992257296,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00042357000948893894,
|
|
"loss": 4.5379,
|
|
"mean_token_accuracy": 0.24226084202528,
|
|
"num_tokens": 65473980.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.085795831680298,
|
|
"epoch": 2.7915425848719475,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004235380050729971,
|
|
"loss": 4.5469,
|
|
"mean_token_accuracy": 0.23815842121839523,
|
|
"num_tokens": 65487635.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.048689270019532,
|
|
"epoch": 2.792138177486599,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004235059953292385,
|
|
"loss": 4.4769,
|
|
"mean_token_accuracy": 0.24907441288232804,
|
|
"num_tokens": 65502258.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 4.9884003639221195,
|
|
"epoch": 2.792733770101251,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042347398025881135,
|
|
"loss": 4.4521,
|
|
"mean_token_accuracy": 0.24349856823682786,
|
|
"num_tokens": 65515224.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.058638238906861,
|
|
"epoch": 2.7933293627159026,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004234419598628639,
|
|
"loss": 4.5251,
|
|
"mean_token_accuracy": 0.23738726526498793,
|
|
"num_tokens": 65528033.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.1638366222381595,
|
|
"epoch": 2.793924955330554,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004234099341425447,
|
|
"loss": 4.645,
|
|
"mean_token_accuracy": 0.2304448589682579,
|
|
"num_tokens": 65544541.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.124899291992188,
|
|
"epoch": 2.7945205479452055,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042337790309900254,
|
|
"loss": 4.5481,
|
|
"mean_token_accuracy": 0.2412203073501587,
|
|
"num_tokens": 65558444.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.104028940200806,
|
|
"epoch": 2.7951161405598572,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042334586673338623,
|
|
"loss": 4.599,
|
|
"mean_token_accuracy": 0.23516627550125122,
|
|
"num_tokens": 65572156.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.0631214618682865,
|
|
"epoch": 2.7957117331745085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042331382504684473,
|
|
"loss": 4.5045,
|
|
"mean_token_accuracy": 0.24494083523750304,
|
|
"num_tokens": 65587607.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.0929868698120115,
|
|
"epoch": 2.79630732578916,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004232817780405276,
|
|
"loss": 4.549,
|
|
"mean_token_accuracy": 0.24248005598783492,
|
|
"num_tokens": 65600574.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.042966890335083,
|
|
"epoch": 2.796902918403812,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042324972571558414,
|
|
"loss": 4.442,
|
|
"mean_token_accuracy": 0.2437410369515419,
|
|
"num_tokens": 65614136.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.067831516265869,
|
|
"epoch": 2.797498511018463,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042321766807316405,
|
|
"loss": 4.5183,
|
|
"mean_token_accuracy": 0.2470456227660179,
|
|
"num_tokens": 65627204.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.077822732925415,
|
|
"epoch": 2.798094103633115,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004231856051144172,
|
|
"loss": 4.5988,
|
|
"mean_token_accuracy": 0.22928511649370192,
|
|
"num_tokens": 65642938.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.109726142883301,
|
|
"epoch": 2.7986896962477665,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004231535368404936,
|
|
"loss": 4.5868,
|
|
"mean_token_accuracy": 0.2365230917930603,
|
|
"num_tokens": 65656932.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.059664344787597,
|
|
"epoch": 2.7992852888624182,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004231214632525436,
|
|
"loss": 4.4721,
|
|
"mean_token_accuracy": 0.23881175071001054,
|
|
"num_tokens": 65671207.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.016842222213745,
|
|
"epoch": 2.79988088147707,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00042308938435171753,
|
|
"loss": 4.5,
|
|
"mean_token_accuracy": 0.2394246816635132,
|
|
"num_tokens": 65684485.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.03699254989624,
|
|
"epoch": 2.800476474091721,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004230573001391659,
|
|
"loss": 4.5404,
|
|
"mean_token_accuracy": 0.23630037754774094,
|
|
"num_tokens": 65698413.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.110697793960571,
|
|
"epoch": 2.801072066706373,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042302521061603985,
|
|
"loss": 4.5915,
|
|
"mean_token_accuracy": 0.23584084808826447,
|
|
"num_tokens": 65711991.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.116149759292602,
|
|
"epoch": 2.8016676593210246,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.00042299311578349003,
|
|
"loss": 4.5869,
|
|
"mean_token_accuracy": 0.22762480229139329,
|
|
"num_tokens": 65727943.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.142168617248535,
|
|
"epoch": 2.802263251935676,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042296101564266774,
|
|
"loss": 4.62,
|
|
"mean_token_accuracy": 0.2292432054877281,
|
|
"num_tokens": 65740241.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.0592752456665036,
|
|
"epoch": 2.8028588445503275,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004229289101947245,
|
|
"loss": 4.5207,
|
|
"mean_token_accuracy": 0.23191618919372559,
|
|
"num_tokens": 65754725.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.095709180831909,
|
|
"epoch": 2.803454437164979,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042289679944081164,
|
|
"loss": 4.5788,
|
|
"mean_token_accuracy": 0.23618328273296357,
|
|
"num_tokens": 65769211.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.085983562469482,
|
|
"epoch": 2.8040500297796305,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042286468338208113,
|
|
"loss": 4.5288,
|
|
"mean_token_accuracy": 0.2443808615207672,
|
|
"num_tokens": 65781263.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.070012998580933,
|
|
"epoch": 2.804645622394282,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042283256201968485,
|
|
"loss": 4.5409,
|
|
"mean_token_accuracy": 0.2411185696721077,
|
|
"num_tokens": 65793427.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.114204454421997,
|
|
"epoch": 2.805241215008934,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004228004353547749,
|
|
"loss": 4.5951,
|
|
"mean_token_accuracy": 0.23735248297452927,
|
|
"num_tokens": 65807704.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.024253559112549,
|
|
"epoch": 2.8058368076235856,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004227683033885036,
|
|
"loss": 4.4766,
|
|
"mean_token_accuracy": 0.24401229172945021,
|
|
"num_tokens": 65821562.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.01686840057373,
|
|
"epoch": 2.8064324002382373,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042273616612202363,
|
|
"loss": 4.5298,
|
|
"mean_token_accuracy": 0.23938104510307312,
|
|
"num_tokens": 65834747.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.078171348571777,
|
|
"epoch": 2.8070279928528885,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004227040235564875,
|
|
"loss": 4.5504,
|
|
"mean_token_accuracy": 0.23135354220867158,
|
|
"num_tokens": 65849206.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.09304027557373,
|
|
"epoch": 2.80762358546754,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042267187569304825,
|
|
"loss": 4.4685,
|
|
"mean_token_accuracy": 0.2443467989563942,
|
|
"num_tokens": 65862708.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.044584274291992,
|
|
"epoch": 2.808219178082192,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004226397225328589,
|
|
"loss": 4.5093,
|
|
"mean_token_accuracy": 0.24714939594268798,
|
|
"num_tokens": 65877385.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.1494731426239015,
|
|
"epoch": 2.808814770696843,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042260756407707273,
|
|
"loss": 4.6294,
|
|
"mean_token_accuracy": 0.22995150089263916,
|
|
"num_tokens": 65890088.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.172087526321411,
|
|
"epoch": 2.809410363311495,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042257540032684325,
|
|
"loss": 4.635,
|
|
"mean_token_accuracy": 0.23435349613428116,
|
|
"num_tokens": 65903013.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.093374967575073,
|
|
"epoch": 2.8100059559261465,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042254323128332403,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.23064738810062407,
|
|
"num_tokens": 65917461.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 4.995479726791382,
|
|
"epoch": 2.8106015485407982,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004225110569476691,
|
|
"loss": 4.4605,
|
|
"mean_token_accuracy": 0.2440460979938507,
|
|
"num_tokens": 65930799.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.060097503662109,
|
|
"epoch": 2.81119714115545,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042247887732103234,
|
|
"loss": 4.4871,
|
|
"mean_token_accuracy": 0.25048753023147585,
|
|
"num_tokens": 65944274.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.123497247695923,
|
|
"epoch": 2.811792733770101,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00042244669240456813,
|
|
"loss": 4.6519,
|
|
"mean_token_accuracy": 0.22539805769920349,
|
|
"num_tokens": 65958587.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.116505146026611,
|
|
"epoch": 2.812388326384753,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042241450219943067,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.2318308725953102,
|
|
"num_tokens": 65972926.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 4.997248792648316,
|
|
"epoch": 2.8129839189994046,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042238230670677473,
|
|
"loss": 4.476,
|
|
"mean_token_accuracy": 0.24516168087720872,
|
|
"num_tokens": 65986497.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.060296535491943,
|
|
"epoch": 2.813579511614056,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042235010592775506,
|
|
"loss": 4.5563,
|
|
"mean_token_accuracy": 0.23628408908843995,
|
|
"num_tokens": 66001930.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.082201528549194,
|
|
"epoch": 2.8141751042287075,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004223178998635267,
|
|
"loss": 4.5466,
|
|
"mean_token_accuracy": 0.23760530799627305,
|
|
"num_tokens": 66016909.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.051365900039673,
|
|
"epoch": 2.8147706968433592,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042228568851524487,
|
|
"loss": 4.5114,
|
|
"mean_token_accuracy": 0.24096843898296355,
|
|
"num_tokens": 66031226.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.067908382415771,
|
|
"epoch": 2.8153662894580105,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004222534718840647,
|
|
"loss": 4.5195,
|
|
"mean_token_accuracy": 0.24504014402627944,
|
|
"num_tokens": 66045267.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.069293880462647,
|
|
"epoch": 2.815961882072662,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000422221249971142,
|
|
"loss": 4.5027,
|
|
"mean_token_accuracy": 0.23978046476840972,
|
|
"num_tokens": 66057783.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.095493316650391,
|
|
"epoch": 2.816557474687314,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042218902277763254,
|
|
"loss": 4.5728,
|
|
"mean_token_accuracy": 0.2351909413933754,
|
|
"num_tokens": 66071239.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.044680643081665,
|
|
"epoch": 2.8171530673019656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000422156790304692,
|
|
"loss": 4.5069,
|
|
"mean_token_accuracy": 0.24007516652345656,
|
|
"num_tokens": 66085565.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.182492351531982,
|
|
"epoch": 2.8177486599166173,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00042212455255347673,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.22355135828256606,
|
|
"num_tokens": 66099699.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.195232105255127,
|
|
"epoch": 2.8183442525312685,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042209230952514287,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.2181736022233963,
|
|
"num_tokens": 66114802.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.150606679916382,
|
|
"epoch": 2.81893984514592,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004220600612208471,
|
|
"loss": 4.6233,
|
|
"mean_token_accuracy": 0.2392570748925209,
|
|
"num_tokens": 66127186.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.12133297920227,
|
|
"epoch": 2.819535437760572,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004220278076417461,
|
|
"loss": 4.6165,
|
|
"mean_token_accuracy": 0.23165937066078185,
|
|
"num_tokens": 66140619.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.070711708068847,
|
|
"epoch": 2.820131030375223,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00042199554878899655,
|
|
"loss": 4.5448,
|
|
"mean_token_accuracy": 0.23917608559131623,
|
|
"num_tokens": 66154003.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.063355827331543,
|
|
"epoch": 2.820726622989875,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004219632846637557,
|
|
"loss": 4.5557,
|
|
"mean_token_accuracy": 0.23354282826185227,
|
|
"num_tokens": 66168928.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.054548978805542,
|
|
"epoch": 2.8213222156045266,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042193101526718087,
|
|
"loss": 4.4451,
|
|
"mean_token_accuracy": 0.24239537715911866,
|
|
"num_tokens": 66183630.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.085477066040039,
|
|
"epoch": 2.821917808219178,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004218987406004293,
|
|
"loss": 4.5875,
|
|
"mean_token_accuracy": 0.22678568810224534,
|
|
"num_tokens": 66196232.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.110872220993042,
|
|
"epoch": 2.8225134008338295,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042186646066465883,
|
|
"loss": 4.522,
|
|
"mean_token_accuracy": 0.23549179881811141,
|
|
"num_tokens": 66211779.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.147295522689819,
|
|
"epoch": 2.823108993448481,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004218341754610272,
|
|
"loss": 4.5803,
|
|
"mean_token_accuracy": 0.23159435391426086,
|
|
"num_tokens": 66222965.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.084526062011719,
|
|
"epoch": 2.823704586063133,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00042180188499069246,
|
|
"loss": 4.5869,
|
|
"mean_token_accuracy": 0.23273449391126633,
|
|
"num_tokens": 66236824.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.082537889480591,
|
|
"epoch": 2.8243001786777846,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042176958925481276,
|
|
"loss": 4.5294,
|
|
"mean_token_accuracy": 0.2342223346233368,
|
|
"num_tokens": 66249972.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.115764427185058,
|
|
"epoch": 2.824895771292436,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042173728825454647,
|
|
"loss": 4.5729,
|
|
"mean_token_accuracy": 0.23227329850196837,
|
|
"num_tokens": 66263187.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.059374237060547,
|
|
"epoch": 2.8254913639070875,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00042170498199105234,
|
|
"loss": 4.554,
|
|
"mean_token_accuracy": 0.23777745813131332,
|
|
"num_tokens": 66277497.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.219828510284424,
|
|
"epoch": 2.8260869565217392,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004216726704654889,
|
|
"loss": 4.7259,
|
|
"mean_token_accuracy": 0.22671761959791184,
|
|
"num_tokens": 66293007.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.14613561630249,
|
|
"epoch": 2.8266825491363905,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004216403536790153,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.24293994307518005,
|
|
"num_tokens": 66307491.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.036679220199585,
|
|
"epoch": 2.827278141751042,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004216080316327907,
|
|
"loss": 4.4914,
|
|
"mean_token_accuracy": 0.24160969704389573,
|
|
"num_tokens": 66321569.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.016202163696289,
|
|
"epoch": 2.827873734365694,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004215757043279743,
|
|
"loss": 4.4512,
|
|
"mean_token_accuracy": 0.2476077452301979,
|
|
"num_tokens": 66335279.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.123103094100952,
|
|
"epoch": 2.8284693269803456,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042154337176572576,
|
|
"loss": 4.5596,
|
|
"mean_token_accuracy": 0.23557770103216172,
|
|
"num_tokens": 66349539.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.116551446914673,
|
|
"epoch": 2.8290649195949973,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004215110339472047,
|
|
"loss": 4.4983,
|
|
"mean_token_accuracy": 0.24065980911254883,
|
|
"num_tokens": 66363598.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.055631446838379,
|
|
"epoch": 2.8296605122096485,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004214786908735711,
|
|
"loss": 4.5836,
|
|
"mean_token_accuracy": 0.24002829045057297,
|
|
"num_tokens": 66377374.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.112863922119141,
|
|
"epoch": 2.8302561048243002,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000421446342545985,
|
|
"loss": 4.6373,
|
|
"mean_token_accuracy": 0.24084480702877045,
|
|
"num_tokens": 66391783.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.216368198394775,
|
|
"epoch": 2.830851697438952,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00042141398896560666,
|
|
"loss": 4.6214,
|
|
"mean_token_accuracy": 0.22904982566833496,
|
|
"num_tokens": 66405956.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.112695217132568,
|
|
"epoch": 2.831447290053603,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042138163013359664,
|
|
"loss": 4.5823,
|
|
"mean_token_accuracy": 0.2301565945148468,
|
|
"num_tokens": 66420738.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.076078462600708,
|
|
"epoch": 2.832042882668255,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004213492660511155,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.23643368780612944,
|
|
"num_tokens": 66433722.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.058025169372558,
|
|
"epoch": 2.8326384752829066,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004213168967193242,
|
|
"loss": 4.5723,
|
|
"mean_token_accuracy": 0.22919428646564483,
|
|
"num_tokens": 66449356.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.2483278751373295,
|
|
"epoch": 2.833234067897558,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042128452213938366,
|
|
"loss": 4.6864,
|
|
"mean_token_accuracy": 0.22984248250722886,
|
|
"num_tokens": 66462583.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.1486695289611815,
|
|
"epoch": 2.8338296605122095,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004212521423124552,
|
|
"loss": 4.5678,
|
|
"mean_token_accuracy": 0.2350080907344818,
|
|
"num_tokens": 66477531.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.01705961227417,
|
|
"epoch": 2.834425253126861,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004212197572397001,
|
|
"loss": 4.4887,
|
|
"mean_token_accuracy": 0.24698918759822847,
|
|
"num_tokens": 66492997.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.044863033294678,
|
|
"epoch": 2.835020845741513,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042118736692228016,
|
|
"loss": 4.5191,
|
|
"mean_token_accuracy": 0.24733312726020812,
|
|
"num_tokens": 66506018.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.089696073532105,
|
|
"epoch": 2.8356164383561646,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000421154971361357,
|
|
"loss": 4.596,
|
|
"mean_token_accuracy": 0.23124073445796967,
|
|
"num_tokens": 66519403.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.1179440975189205,
|
|
"epoch": 2.836212030970816,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042112257055809264,
|
|
"loss": 4.5999,
|
|
"mean_token_accuracy": 0.23486046344041825,
|
|
"num_tokens": 66533796.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.076002931594848,
|
|
"epoch": 2.8368076235854676,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042109016451364933,
|
|
"loss": 4.4903,
|
|
"mean_token_accuracy": 0.2475315362215042,
|
|
"num_tokens": 66546922.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.137234926223755,
|
|
"epoch": 2.8374032162001193,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042105775322918927,
|
|
"loss": 4.5569,
|
|
"mean_token_accuracy": 0.23675210177898406,
|
|
"num_tokens": 66561933.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.04607629776001,
|
|
"epoch": 2.8379988088147705,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004210253367058751,
|
|
"loss": 4.5101,
|
|
"mean_token_accuracy": 0.24512802809476852,
|
|
"num_tokens": 66578215.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.06509370803833,
|
|
"epoch": 2.838594401429422,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042099291494486946,
|
|
"loss": 4.5308,
|
|
"mean_token_accuracy": 0.2388026550412178,
|
|
"num_tokens": 66592153.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.150548124313355,
|
|
"epoch": 2.839189994044074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042096048794733543,
|
|
"loss": 4.5646,
|
|
"mean_token_accuracy": 0.24022510796785354,
|
|
"num_tokens": 66605003.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.05014328956604,
|
|
"epoch": 2.839785586658725,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000420928055714436,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.23599257320165634,
|
|
"num_tokens": 66619466.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.123056507110595,
|
|
"epoch": 2.840381179273377,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004208956182473344,
|
|
"loss": 4.6153,
|
|
"mean_token_accuracy": 0.23154897391796112,
|
|
"num_tokens": 66632355.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.043539714813233,
|
|
"epoch": 2.8409767718880286,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00042086317554719424,
|
|
"loss": 4.4549,
|
|
"mean_token_accuracy": 0.2416701003909111,
|
|
"num_tokens": 66648107.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.0727039813995365,
|
|
"epoch": 2.8415723645026802,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004208307276151792,
|
|
"loss": 4.4851,
|
|
"mean_token_accuracy": 0.2390936493873596,
|
|
"num_tokens": 66662922.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.0990983009338375,
|
|
"epoch": 2.842167957117332,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000420798274452453,
|
|
"loss": 4.5745,
|
|
"mean_token_accuracy": 0.23846384435892104,
|
|
"num_tokens": 66675928.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.071858835220337,
|
|
"epoch": 2.842763549731983,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042076581606017964,
|
|
"loss": 4.5767,
|
|
"mean_token_accuracy": 0.2395972192287445,
|
|
"num_tokens": 66689858.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.081563472747803,
|
|
"epoch": 2.843359142346635,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042073335243952354,
|
|
"loss": 4.5378,
|
|
"mean_token_accuracy": 0.24181730300188065,
|
|
"num_tokens": 66705225.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.14077844619751,
|
|
"epoch": 2.8439547349612866,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042070088359164916,
|
|
"loss": 4.5987,
|
|
"mean_token_accuracy": 0.23072456270456315,
|
|
"num_tokens": 66719751.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.109568786621094,
|
|
"epoch": 2.844550327575938,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042066840951772086,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.2320491209626198,
|
|
"num_tokens": 66734576.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.1042875289917,
|
|
"epoch": 2.8451459201905895,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004206359302189036,
|
|
"loss": 4.5838,
|
|
"mean_token_accuracy": 0.23228788524866104,
|
|
"num_tokens": 66749096.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.029713821411133,
|
|
"epoch": 2.8457415128052412,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004206034456963623,
|
|
"loss": 4.5707,
|
|
"mean_token_accuracy": 0.23598251193761827,
|
|
"num_tokens": 66764849.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.144252490997315,
|
|
"epoch": 2.846337105419893,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004205709559512621,
|
|
"loss": 4.6177,
|
|
"mean_token_accuracy": 0.22847779989242553,
|
|
"num_tokens": 66777793.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.069332218170166,
|
|
"epoch": 2.8469326980345446,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004205384609847684,
|
|
"loss": 4.495,
|
|
"mean_token_accuracy": 0.23921375572681428,
|
|
"num_tokens": 66790465.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.042599391937256,
|
|
"epoch": 2.847528290649196,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004205059607980467,
|
|
"loss": 4.5198,
|
|
"mean_token_accuracy": 0.23919636160135269,
|
|
"num_tokens": 66804593.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.025151205062866,
|
|
"epoch": 2.8481238832638476,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004204734553922629,
|
|
"loss": 4.5027,
|
|
"mean_token_accuracy": 0.23824898451566695,
|
|
"num_tokens": 66817999.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.082077550888061,
|
|
"epoch": 2.8487194758784993,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00042044094476858266,
|
|
"loss": 4.5344,
|
|
"mean_token_accuracy": 0.23686589300632477,
|
|
"num_tokens": 66830547.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.104467153549194,
|
|
"epoch": 2.8493150684931505,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042040842892817227,
|
|
"loss": 4.5693,
|
|
"mean_token_accuracy": 0.23830384612083436,
|
|
"num_tokens": 66843502.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.118842315673828,
|
|
"epoch": 2.8499106611078022,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004203759078721979,
|
|
"loss": 4.5678,
|
|
"mean_token_accuracy": 0.2400350332260132,
|
|
"num_tokens": 66858202.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.09826807975769,
|
|
"epoch": 2.850506253722454,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004203433816018261,
|
|
"loss": 4.5741,
|
|
"mean_token_accuracy": 0.2291431173682213,
|
|
"num_tokens": 66872940.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.115887546539307,
|
|
"epoch": 2.851101846337105,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042031085011822356,
|
|
"loss": 4.6278,
|
|
"mean_token_accuracy": 0.23819318860769273,
|
|
"num_tokens": 66885989.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.073829269409179,
|
|
"epoch": 2.851697438951757,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000420278313422557,
|
|
"loss": 4.545,
|
|
"mean_token_accuracy": 0.23538491278886794,
|
|
"num_tokens": 66899104.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.080007648468017,
|
|
"epoch": 2.8522930315664086,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004202457715159936,
|
|
"loss": 4.5475,
|
|
"mean_token_accuracy": 0.24306994974613189,
|
|
"num_tokens": 66914768.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.119881534576416,
|
|
"epoch": 2.8528886241810603,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004202132243997005,
|
|
"loss": 4.5822,
|
|
"mean_token_accuracy": 0.23392175883054733,
|
|
"num_tokens": 66927428.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.106862163543701,
|
|
"epoch": 2.853484216795712,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042018067207484524,
|
|
"loss": 4.5716,
|
|
"mean_token_accuracy": 0.24085193276405334,
|
|
"num_tokens": 66941507.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.0720648765563965,
|
|
"epoch": 2.854079809410363,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004201481145425952,
|
|
"loss": 4.472,
|
|
"mean_token_accuracy": 0.2415819898247719,
|
|
"num_tokens": 66954986.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.1005627632141115,
|
|
"epoch": 2.854675402025015,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004201155518041184,
|
|
"loss": 4.6256,
|
|
"mean_token_accuracy": 0.22859593480825424,
|
|
"num_tokens": 66969061.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.078666687011719,
|
|
"epoch": 2.8552709946396666,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042008298386058264,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.23488316237926482,
|
|
"num_tokens": 66981953.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.078921556472778,
|
|
"epoch": 2.855866587254318,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004200504107131561,
|
|
"loss": 4.5203,
|
|
"mean_token_accuracy": 0.24117085933685303,
|
|
"num_tokens": 66995096.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.0837053775787355,
|
|
"epoch": 2.8564621798689696,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004200178323630072,
|
|
"loss": 4.5093,
|
|
"mean_token_accuracy": 0.24262769967317582,
|
|
"num_tokens": 67008491.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.078900671005249,
|
|
"epoch": 2.8570577724836212,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041998524881130446,
|
|
"loss": 4.4927,
|
|
"mean_token_accuracy": 0.25655444115400317,
|
|
"num_tokens": 67021068.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.065000438690186,
|
|
"epoch": 2.857653365098273,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041995266005921656,
|
|
"loss": 4.5732,
|
|
"mean_token_accuracy": 0.23638160824775695,
|
|
"num_tokens": 67034450.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.14638466835022,
|
|
"epoch": 2.858248957712924,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004199200661079124,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.23071217238903047,
|
|
"num_tokens": 67048007.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.13138861656189,
|
|
"epoch": 2.858844550327576,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041988746695856115,
|
|
"loss": 4.5375,
|
|
"mean_token_accuracy": 0.23557782620191575,
|
|
"num_tokens": 67063278.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.858844550327576,
|
|
"eval_entropy": 4.8170669528757895,
|
|
"eval_loss": 4.571159839630127,
|
|
"eval_mean_token_accuracy": 0.24645793221213602,
|
|
"eval_num_tokens": 67063278.0,
|
|
"eval_runtime": 18.4849,
|
|
"eval_samples_per_second": 1380.206,
|
|
"eval_steps_per_second": 172.573,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"entropy": 5.065574789047242,
|
|
"epoch": 2.8594401429422276,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041985486261233204,
|
|
"loss": 4.4901,
|
|
"mean_token_accuracy": 0.23964236974716185,
|
|
"num_tokens": 67077291.0,
|
|
"step": 24005
|
|
},
|
|
{
|
|
"entropy": 5.00985803604126,
|
|
"epoch": 2.8600357355568793,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004198222530703944,
|
|
"loss": 4.4638,
|
|
"mean_token_accuracy": 0.24369621574878692,
|
|
"num_tokens": 67091238.0,
|
|
"step": 24010
|
|
},
|
|
{
|
|
"entropy": 5.077258634567261,
|
|
"epoch": 2.8606313281715305,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041978963833391817,
|
|
"loss": 4.5189,
|
|
"mean_token_accuracy": 0.23765470832586288,
|
|
"num_tokens": 67105543.0,
|
|
"step": 24015
|
|
},
|
|
{
|
|
"entropy": 5.07120451927185,
|
|
"epoch": 2.8612269207861822,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041975701840407296,
|
|
"loss": 4.5659,
|
|
"mean_token_accuracy": 0.23600239008665086,
|
|
"num_tokens": 67120971.0,
|
|
"step": 24020
|
|
},
|
|
{
|
|
"entropy": 5.086171293258667,
|
|
"epoch": 2.861822513400834,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004197243932820288,
|
|
"loss": 4.4962,
|
|
"mean_token_accuracy": 0.24269102960824968,
|
|
"num_tokens": 67133531.0,
|
|
"step": 24025
|
|
},
|
|
{
|
|
"entropy": 5.095920705795288,
|
|
"epoch": 2.862418106015485,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000419691762968956,
|
|
"loss": 4.5974,
|
|
"mean_token_accuracy": 0.23197037428617479,
|
|
"num_tokens": 67148043.0,
|
|
"step": 24030
|
|
},
|
|
{
|
|
"entropy": 5.144214057922364,
|
|
"epoch": 2.863013698630137,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041965912746602495,
|
|
"loss": 4.5517,
|
|
"mean_token_accuracy": 0.23514681905508042,
|
|
"num_tokens": 67163308.0,
|
|
"step": 24035
|
|
},
|
|
{
|
|
"entropy": 5.089741182327271,
|
|
"epoch": 2.8636092912447886,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004196264867744062,
|
|
"loss": 4.5698,
|
|
"mean_token_accuracy": 0.23747506886720657,
|
|
"num_tokens": 67179212.0,
|
|
"step": 24040
|
|
},
|
|
{
|
|
"entropy": 5.117527818679809,
|
|
"epoch": 2.8642048838594403,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004195938408952704,
|
|
"loss": 4.6479,
|
|
"mean_token_accuracy": 0.23557428419589996,
|
|
"num_tokens": 67194970.0,
|
|
"step": 24045
|
|
},
|
|
{
|
|
"entropy": 5.115648651123047,
|
|
"epoch": 2.864800476474092,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004195611898297888,
|
|
"loss": 4.5125,
|
|
"mean_token_accuracy": 0.24213880747556688,
|
|
"num_tokens": 67208859.0,
|
|
"step": 24050
|
|
},
|
|
{
|
|
"entropy": 5.152409934997559,
|
|
"epoch": 2.8653960690887432,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004195285335791323,
|
|
"loss": 4.6676,
|
|
"mean_token_accuracy": 0.2216177299618721,
|
|
"num_tokens": 67222698.0,
|
|
"step": 24055
|
|
},
|
|
{
|
|
"entropy": 5.153220129013062,
|
|
"epoch": 2.865991661703395,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041949587214447224,
|
|
"loss": 4.572,
|
|
"mean_token_accuracy": 0.23082401901483535,
|
|
"num_tokens": 67236992.0,
|
|
"step": 24060
|
|
},
|
|
{
|
|
"entropy": 5.0876136302948,
|
|
"epoch": 2.8665872543180466,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004194632055269802,
|
|
"loss": 4.5537,
|
|
"mean_token_accuracy": 0.23485918045043946,
|
|
"num_tokens": 67249786.0,
|
|
"step": 24065
|
|
},
|
|
{
|
|
"entropy": 5.100263261795044,
|
|
"epoch": 2.867182846932698,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004194305337278279,
|
|
"loss": 4.5278,
|
|
"mean_token_accuracy": 0.23277901709079743,
|
|
"num_tokens": 67262938.0,
|
|
"step": 24070
|
|
},
|
|
{
|
|
"entropy": 4.9640661716461185,
|
|
"epoch": 2.8677784395473496,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041939785674818716,
|
|
"loss": 4.4048,
|
|
"mean_token_accuracy": 0.25133723616600034,
|
|
"num_tokens": 67276824.0,
|
|
"step": 24075
|
|
},
|
|
{
|
|
"entropy": 5.093726110458374,
|
|
"epoch": 2.8683740321620013,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041936517458923006,
|
|
"loss": 4.6048,
|
|
"mean_token_accuracy": 0.22477316856384277,
|
|
"num_tokens": 67292639.0,
|
|
"step": 24080
|
|
},
|
|
{
|
|
"entropy": 5.099959468841552,
|
|
"epoch": 2.8689696247766525,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004193324872521289,
|
|
"loss": 4.4989,
|
|
"mean_token_accuracy": 0.2446732297539711,
|
|
"num_tokens": 67305626.0,
|
|
"step": 24085
|
|
},
|
|
{
|
|
"entropy": 5.002741193771362,
|
|
"epoch": 2.869565217391304,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041929979473805606,
|
|
"loss": 4.4499,
|
|
"mean_token_accuracy": 0.2408558025956154,
|
|
"num_tokens": 67318806.0,
|
|
"step": 24090
|
|
},
|
|
{
|
|
"entropy": 5.002957153320312,
|
|
"epoch": 2.870160810005956,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004192670970481843,
|
|
"loss": 4.4764,
|
|
"mean_token_accuracy": 0.2471690908074379,
|
|
"num_tokens": 67333382.0,
|
|
"step": 24095
|
|
},
|
|
{
|
|
"entropy": 5.158579874038696,
|
|
"epoch": 2.8707564026206076,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004192343941836861,
|
|
"loss": 4.5962,
|
|
"mean_token_accuracy": 0.23252985179424285,
|
|
"num_tokens": 67347437.0,
|
|
"step": 24100
|
|
},
|
|
{
|
|
"entropy": 5.09338960647583,
|
|
"epoch": 2.8713519952352593,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000419201686145735,
|
|
"loss": 4.5399,
|
|
"mean_token_accuracy": 0.23920968770980836,
|
|
"num_tokens": 67361094.0,
|
|
"step": 24105
|
|
},
|
|
{
|
|
"entropy": 5.118738508224487,
|
|
"epoch": 2.8719475878499106,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004191689729355037,
|
|
"loss": 4.6431,
|
|
"mean_token_accuracy": 0.22918802499771118,
|
|
"num_tokens": 67375695.0,
|
|
"step": 24110
|
|
},
|
|
{
|
|
"entropy": 5.1351714611053465,
|
|
"epoch": 2.8725431804645623,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041913625455416564,
|
|
"loss": 4.6303,
|
|
"mean_token_accuracy": 0.23310965299606323,
|
|
"num_tokens": 67387958.0,
|
|
"step": 24115
|
|
},
|
|
{
|
|
"entropy": 5.159222888946533,
|
|
"epoch": 2.873138773079214,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004191035310028947,
|
|
"loss": 4.6238,
|
|
"mean_token_accuracy": 0.23314548432826995,
|
|
"num_tokens": 67403511.0,
|
|
"step": 24120
|
|
},
|
|
{
|
|
"entropy": 5.147854518890381,
|
|
"epoch": 2.873734365693865,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004190708022828643,
|
|
"loss": 4.6258,
|
|
"mean_token_accuracy": 0.22863434106111527,
|
|
"num_tokens": 67416214.0,
|
|
"step": 24125
|
|
},
|
|
{
|
|
"entropy": 5.089010095596313,
|
|
"epoch": 2.874329958308517,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041903806839524844,
|
|
"loss": 4.5705,
|
|
"mean_token_accuracy": 0.23296553641557693,
|
|
"num_tokens": 67430323.0,
|
|
"step": 24130
|
|
},
|
|
{
|
|
"entropy": 5.123608112335205,
|
|
"epoch": 2.8749255509231686,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004190053293412213,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.23798863142728804,
|
|
"num_tokens": 67443465.0,
|
|
"step": 24135
|
|
},
|
|
{
|
|
"entropy": 5.055103778839111,
|
|
"epoch": 2.8755211435378203,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004189725851219571,
|
|
"loss": 4.4877,
|
|
"mean_token_accuracy": 0.24162827879190446,
|
|
"num_tokens": 67456176.0,
|
|
"step": 24140
|
|
},
|
|
{
|
|
"entropy": 5.0105115413665775,
|
|
"epoch": 2.876116736152472,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041893983573863044,
|
|
"loss": 4.4318,
|
|
"mean_token_accuracy": 0.2510700449347496,
|
|
"num_tokens": 67468939.0,
|
|
"step": 24145
|
|
},
|
|
{
|
|
"entropy": 5.083252859115601,
|
|
"epoch": 2.8767123287671232,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041890708119241585,
|
|
"loss": 4.6149,
|
|
"mean_token_accuracy": 0.23003380596637726,
|
|
"num_tokens": 67483180.0,
|
|
"step": 24150
|
|
},
|
|
{
|
|
"entropy": 5.06475043296814,
|
|
"epoch": 2.877307921381775,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004188743214844882,
|
|
"loss": 4.5726,
|
|
"mean_token_accuracy": 0.23488814532756805,
|
|
"num_tokens": 67499827.0,
|
|
"step": 24155
|
|
},
|
|
{
|
|
"entropy": 5.120594024658203,
|
|
"epoch": 2.8779035139964266,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041884155661602257,
|
|
"loss": 4.6083,
|
|
"mean_token_accuracy": 0.23435541689395906,
|
|
"num_tokens": 67512214.0,
|
|
"step": 24160
|
|
},
|
|
{
|
|
"entropy": 5.153059291839599,
|
|
"epoch": 2.878499106611078,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041880878658819427,
|
|
"loss": 4.6036,
|
|
"mean_token_accuracy": 0.23157523423433304,
|
|
"num_tokens": 67528197.0,
|
|
"step": 24165
|
|
},
|
|
{
|
|
"entropy": 5.038412427902221,
|
|
"epoch": 2.8790946992257296,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041877601140217845,
|
|
"loss": 4.4809,
|
|
"mean_token_accuracy": 0.24304617047309876,
|
|
"num_tokens": 67541686.0,
|
|
"step": 24170
|
|
},
|
|
{
|
|
"entropy": 4.989509391784668,
|
|
"epoch": 2.8796902918403813,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004187432310591511,
|
|
"loss": 4.4457,
|
|
"mean_token_accuracy": 0.24622450917959213,
|
|
"num_tokens": 67556302.0,
|
|
"step": 24175
|
|
},
|
|
{
|
|
"entropy": 5.108074140548706,
|
|
"epoch": 2.8802858844550325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004187104455602875,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.24125680923461915,
|
|
"num_tokens": 67570652.0,
|
|
"step": 24180
|
|
},
|
|
{
|
|
"entropy": 5.111768102645874,
|
|
"epoch": 2.8808814770696842,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000418677654906764,
|
|
"loss": 4.5292,
|
|
"mean_token_accuracy": 0.23652785569429396,
|
|
"num_tokens": 67585727.0,
|
|
"step": 24185
|
|
},
|
|
{
|
|
"entropy": 5.0945656299591064,
|
|
"epoch": 2.881477069684336,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004186448590997567,
|
|
"loss": 4.5196,
|
|
"mean_token_accuracy": 0.2359107956290245,
|
|
"num_tokens": 67599836.0,
|
|
"step": 24190
|
|
},
|
|
{
|
|
"entropy": 5.040383958816529,
|
|
"epoch": 2.8820726622989876,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041861205814044174,
|
|
"loss": 4.4955,
|
|
"mean_token_accuracy": 0.2399111956357956,
|
|
"num_tokens": 67613652.0,
|
|
"step": 24195
|
|
},
|
|
{
|
|
"entropy": 5.165356969833374,
|
|
"epoch": 2.8826682549136393,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041857925202999586,
|
|
"loss": 4.6573,
|
|
"mean_token_accuracy": 0.22600957304239272,
|
|
"num_tokens": 67627081.0,
|
|
"step": 24200
|
|
},
|
|
{
|
|
"entropy": 5.07870626449585,
|
|
"epoch": 2.8832638475282906,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004185464407695956,
|
|
"loss": 4.5612,
|
|
"mean_token_accuracy": 0.24239958375692366,
|
|
"num_tokens": 67640716.0,
|
|
"step": 24205
|
|
},
|
|
{
|
|
"entropy": 5.1358874320983885,
|
|
"epoch": 2.8838594401429423,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004185136243604178,
|
|
"loss": 4.6024,
|
|
"mean_token_accuracy": 0.23012492805719376,
|
|
"num_tokens": 67654802.0,
|
|
"step": 24210
|
|
},
|
|
{
|
|
"entropy": 5.1000665664672855,
|
|
"epoch": 2.884455032757594,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004184808028036398,
|
|
"loss": 4.5663,
|
|
"mean_token_accuracy": 0.23438635766506194,
|
|
"num_tokens": 67668034.0,
|
|
"step": 24215
|
|
},
|
|
{
|
|
"entropy": 5.046010303497314,
|
|
"epoch": 2.885050625372245,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004184479761004386,
|
|
"loss": 4.4719,
|
|
"mean_token_accuracy": 0.2490328311920166,
|
|
"num_tokens": 67683407.0,
|
|
"step": 24220
|
|
},
|
|
{
|
|
"entropy": 5.141486167907715,
|
|
"epoch": 2.885646217986897,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041841514425199175,
|
|
"loss": 4.6606,
|
|
"mean_token_accuracy": 0.22667501866817474,
|
|
"num_tokens": 67698042.0,
|
|
"step": 24225
|
|
},
|
|
{
|
|
"entropy": 5.113983011245727,
|
|
"epoch": 2.8862418106015486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041838230725947683,
|
|
"loss": 4.5018,
|
|
"mean_token_accuracy": 0.23899227231740952,
|
|
"num_tokens": 67710802.0,
|
|
"step": 24230
|
|
},
|
|
{
|
|
"entropy": 5.1247107028961185,
|
|
"epoch": 2.8868374032162,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041834946512407173,
|
|
"loss": 4.6225,
|
|
"mean_token_accuracy": 0.23114656656980515,
|
|
"num_tokens": 67723933.0,
|
|
"step": 24235
|
|
},
|
|
{
|
|
"entropy": 5.0263612270355225,
|
|
"epoch": 2.8874329958308516,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004183166178469543,
|
|
"loss": 4.533,
|
|
"mean_token_accuracy": 0.24150590598583221,
|
|
"num_tokens": 67738354.0,
|
|
"step": 24240
|
|
},
|
|
{
|
|
"entropy": 5.078142881393433,
|
|
"epoch": 2.8880285884455033,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004182837654293029,
|
|
"loss": 4.6109,
|
|
"mean_token_accuracy": 0.238280688226223,
|
|
"num_tokens": 67751484.0,
|
|
"step": 24245
|
|
},
|
|
{
|
|
"entropy": 5.137964200973511,
|
|
"epoch": 2.888624181060155,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041825090787229574,
|
|
"loss": 4.5268,
|
|
"mean_token_accuracy": 0.23933922201395036,
|
|
"num_tokens": 67766959.0,
|
|
"step": 24250
|
|
},
|
|
{
|
|
"entropy": 5.048208999633789,
|
|
"epoch": 2.8892197736748066,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004182180451771115,
|
|
"loss": 4.5182,
|
|
"mean_token_accuracy": 0.23618070632219315,
|
|
"num_tokens": 67782171.0,
|
|
"step": 24255
|
|
},
|
|
{
|
|
"entropy": 5.138451814651489,
|
|
"epoch": 2.889815366289458,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041818517734492874,
|
|
"loss": 4.5953,
|
|
"mean_token_accuracy": 0.23168872743844987,
|
|
"num_tokens": 67796934.0,
|
|
"step": 24260
|
|
},
|
|
{
|
|
"entropy": 5.129188680648804,
|
|
"epoch": 2.8904109589041096,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041815230437692647,
|
|
"loss": 4.5894,
|
|
"mean_token_accuracy": 0.22995952367782593,
|
|
"num_tokens": 67810269.0,
|
|
"step": 24265
|
|
},
|
|
{
|
|
"entropy": 5.073572397232056,
|
|
"epoch": 2.8910065515187613,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004181194262742839,
|
|
"loss": 4.5688,
|
|
"mean_token_accuracy": 0.24266298860311508,
|
|
"num_tokens": 67823432.0,
|
|
"step": 24270
|
|
},
|
|
{
|
|
"entropy": 5.089761781692505,
|
|
"epoch": 2.8916021441334125,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041808654303818004,
|
|
"loss": 4.5831,
|
|
"mean_token_accuracy": 0.2351744756102562,
|
|
"num_tokens": 67835164.0,
|
|
"step": 24275
|
|
},
|
|
{
|
|
"entropy": 5.104305267333984,
|
|
"epoch": 2.8921977367480642,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004180536546697947,
|
|
"loss": 4.6329,
|
|
"mean_token_accuracy": 0.22533594965934753,
|
|
"num_tokens": 67848130.0,
|
|
"step": 24280
|
|
},
|
|
{
|
|
"entropy": 5.101497745513916,
|
|
"epoch": 2.892793329362716,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004180207611703073,
|
|
"loss": 4.5853,
|
|
"mean_token_accuracy": 0.23140751868486403,
|
|
"num_tokens": 67860686.0,
|
|
"step": 24285
|
|
},
|
|
{
|
|
"entropy": 5.156475257873535,
|
|
"epoch": 2.8933889219773676,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041798786254089774,
|
|
"loss": 4.5572,
|
|
"mean_token_accuracy": 0.24244628101587296,
|
|
"num_tokens": 67874176.0,
|
|
"step": 24290
|
|
},
|
|
{
|
|
"entropy": 5.1258257865905765,
|
|
"epoch": 2.8939845145920193,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041795495878274596,
|
|
"loss": 4.5761,
|
|
"mean_token_accuracy": 0.23637939989566803,
|
|
"num_tokens": 67887995.0,
|
|
"step": 24295
|
|
},
|
|
{
|
|
"entropy": 5.067194271087646,
|
|
"epoch": 2.8945801072066706,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004179220498970323,
|
|
"loss": 4.48,
|
|
"mean_token_accuracy": 0.24319615066051484,
|
|
"num_tokens": 67902056.0,
|
|
"step": 24300
|
|
},
|
|
{
|
|
"entropy": 5.104501008987427,
|
|
"epoch": 2.8951756998213223,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041788913588493716,
|
|
"loss": 4.5578,
|
|
"mean_token_accuracy": 0.24320828020572663,
|
|
"num_tokens": 67916666.0,
|
|
"step": 24305
|
|
},
|
|
{
|
|
"entropy": 5.042879724502564,
|
|
"epoch": 2.895771292435974,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004178562167476409,
|
|
"loss": 4.4506,
|
|
"mean_token_accuracy": 0.24482694864273072,
|
|
"num_tokens": 67930938.0,
|
|
"step": 24310
|
|
},
|
|
{
|
|
"entropy": 5.170782852172851,
|
|
"epoch": 2.8963668850506252,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004178232924863245,
|
|
"loss": 4.6461,
|
|
"mean_token_accuracy": 0.22954428642988206,
|
|
"num_tokens": 67945527.0,
|
|
"step": 24315
|
|
},
|
|
{
|
|
"entropy": 5.117460870742798,
|
|
"epoch": 2.896962477665277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004177903631021688,
|
|
"loss": 4.5509,
|
|
"mean_token_accuracy": 0.24317234009504318,
|
|
"num_tokens": 67958285.0,
|
|
"step": 24320
|
|
},
|
|
{
|
|
"entropy": 5.11009726524353,
|
|
"epoch": 2.8975580702799286,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004177574285963549,
|
|
"loss": 4.5926,
|
|
"mean_token_accuracy": 0.23536286652088165,
|
|
"num_tokens": 67970498.0,
|
|
"step": 24325
|
|
},
|
|
{
|
|
"entropy": 5.0935266494750975,
|
|
"epoch": 2.89815366289458,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004177244889700642,
|
|
"loss": 4.503,
|
|
"mean_token_accuracy": 0.2419282913208008,
|
|
"num_tokens": 67984290.0,
|
|
"step": 24330
|
|
},
|
|
{
|
|
"entropy": 5.115455770492554,
|
|
"epoch": 2.8987492555092316,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041769154422447813,
|
|
"loss": 4.5811,
|
|
"mean_token_accuracy": 0.23372956365346909,
|
|
"num_tokens": 67997854.0,
|
|
"step": 24335
|
|
},
|
|
{
|
|
"entropy": 5.0932904243469235,
|
|
"epoch": 2.8993448481238833,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041765859436077837,
|
|
"loss": 4.5362,
|
|
"mean_token_accuracy": 0.23881837576627732,
|
|
"num_tokens": 68012388.0,
|
|
"step": 24340
|
|
},
|
|
{
|
|
"entropy": 5.051183986663818,
|
|
"epoch": 2.899940440738535,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041762563938014673,
|
|
"loss": 4.4903,
|
|
"mean_token_accuracy": 0.24241654425859452,
|
|
"num_tokens": 68026504.0,
|
|
"step": 24345
|
|
},
|
|
{
|
|
"entropy": 5.036718654632568,
|
|
"epoch": 2.9005360333531867,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004175926792837653,
|
|
"loss": 4.5005,
|
|
"mean_token_accuracy": 0.2396565094590187,
|
|
"num_tokens": 68039678.0,
|
|
"step": 24350
|
|
},
|
|
{
|
|
"entropy": 5.093848133087159,
|
|
"epoch": 2.901131625967838,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004175597140728164,
|
|
"loss": 4.5684,
|
|
"mean_token_accuracy": 0.23880522847175598,
|
|
"num_tokens": 68052944.0,
|
|
"step": 24355
|
|
},
|
|
{
|
|
"entropy": 5.025130033493042,
|
|
"epoch": 2.9017272185824896,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004175267437484823,
|
|
"loss": 4.4389,
|
|
"mean_token_accuracy": 0.2470148205757141,
|
|
"num_tokens": 68067153.0,
|
|
"step": 24360
|
|
},
|
|
{
|
|
"entropy": 5.07536563873291,
|
|
"epoch": 2.9023228111971413,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041749376831194565,
|
|
"loss": 4.5814,
|
|
"mean_token_accuracy": 0.23496901690959932,
|
|
"num_tokens": 68079974.0,
|
|
"step": 24365
|
|
},
|
|
{
|
|
"entropy": 5.126134824752808,
|
|
"epoch": 2.9029184038117926,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004174607877643892,
|
|
"loss": 4.6478,
|
|
"mean_token_accuracy": 0.22161248177289963,
|
|
"num_tokens": 68094823.0,
|
|
"step": 24370
|
|
},
|
|
{
|
|
"entropy": 5.133097982406616,
|
|
"epoch": 2.9035139964264443,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041742780210699584,
|
|
"loss": 4.5533,
|
|
"mean_token_accuracy": 0.23253776431083678,
|
|
"num_tokens": 68109112.0,
|
|
"step": 24375
|
|
},
|
|
{
|
|
"entropy": 5.072058534622192,
|
|
"epoch": 2.904109589041096,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004173948113409488,
|
|
"loss": 4.5337,
|
|
"mean_token_accuracy": 0.24293812066316606,
|
|
"num_tokens": 68122657.0,
|
|
"step": 24380
|
|
},
|
|
{
|
|
"entropy": 5.100731372833252,
|
|
"epoch": 2.904705181655747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004173618154674316,
|
|
"loss": 4.5842,
|
|
"mean_token_accuracy": 0.2323631078004837,
|
|
"num_tokens": 68138551.0,
|
|
"step": 24385
|
|
},
|
|
{
|
|
"entropy": 5.067598628997803,
|
|
"epoch": 2.905300774270399,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004173288144876273,
|
|
"loss": 4.5281,
|
|
"mean_token_accuracy": 0.2500699177384377,
|
|
"num_tokens": 68152946.0,
|
|
"step": 24390
|
|
},
|
|
{
|
|
"entropy": 5.123769950866699,
|
|
"epoch": 2.9058963668850506,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004172958084027199,
|
|
"loss": 4.513,
|
|
"mean_token_accuracy": 0.24299073964357376,
|
|
"num_tokens": 68168137.0,
|
|
"step": 24395
|
|
},
|
|
{
|
|
"entropy": 5.091378450393677,
|
|
"epoch": 2.9064919594997023,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004172627972138933,
|
|
"loss": 4.5649,
|
|
"mean_token_accuracy": 0.23228583931922914,
|
|
"num_tokens": 68184105.0,
|
|
"step": 24400
|
|
},
|
|
{
|
|
"entropy": 5.07243595123291,
|
|
"epoch": 2.907087552114354,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00041722978092233144,
|
|
"loss": 4.5079,
|
|
"mean_token_accuracy": 0.24550326764583588,
|
|
"num_tokens": 68197363.0,
|
|
"step": 24405
|
|
},
|
|
{
|
|
"entropy": 5.096792268753052,
|
|
"epoch": 2.9076831447290052,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041719675952921854,
|
|
"loss": 4.5648,
|
|
"mean_token_accuracy": 0.23672513514757157,
|
|
"num_tokens": 68210806.0,
|
|
"step": 24410
|
|
},
|
|
{
|
|
"entropy": 5.074089813232422,
|
|
"epoch": 2.908278737343657,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004171637330357391,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.2333671435713768,
|
|
"num_tokens": 68225402.0,
|
|
"step": 24415
|
|
},
|
|
{
|
|
"entropy": 5.094043397903443,
|
|
"epoch": 2.9088743299583086,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004171307014430777,
|
|
"loss": 4.5776,
|
|
"mean_token_accuracy": 0.23402400463819503,
|
|
"num_tokens": 68238849.0,
|
|
"step": 24420
|
|
},
|
|
{
|
|
"entropy": 5.0422553539276125,
|
|
"epoch": 2.90946992257296,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004170976647524192,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.2377272441983223,
|
|
"num_tokens": 68252924.0,
|
|
"step": 24425
|
|
},
|
|
{
|
|
"entropy": 5.1108039855957035,
|
|
"epoch": 2.9100655151876116,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004170646229649484,
|
|
"loss": 4.6082,
|
|
"mean_token_accuracy": 0.22971602380275727,
|
|
"num_tokens": 68266800.0,
|
|
"step": 24430
|
|
},
|
|
{
|
|
"entropy": 5.174791479110718,
|
|
"epoch": 2.9106611078022633,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041703157608185057,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.23529850840568542,
|
|
"num_tokens": 68280253.0,
|
|
"step": 24435
|
|
},
|
|
{
|
|
"entropy": 5.0624017238616945,
|
|
"epoch": 2.911256700416915,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000416998524104311,
|
|
"loss": 4.5288,
|
|
"mean_token_accuracy": 0.24446408152580262,
|
|
"num_tokens": 68293396.0,
|
|
"step": 24440
|
|
},
|
|
{
|
|
"entropy": 5.1107604026794435,
|
|
"epoch": 2.9118522930315667,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00041696546703351537,
|
|
"loss": 4.5764,
|
|
"mean_token_accuracy": 0.23205572217702866,
|
|
"num_tokens": 68309011.0,
|
|
"step": 24445
|
|
},
|
|
{
|
|
"entropy": 5.03616623878479,
|
|
"epoch": 2.912447885646218,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041693240487064917,
|
|
"loss": 4.4827,
|
|
"mean_token_accuracy": 0.24474563747644423,
|
|
"num_tokens": 68325093.0,
|
|
"step": 24450
|
|
},
|
|
{
|
|
"entropy": 5.0518464088439945,
|
|
"epoch": 2.9130434782608696,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004168993376168984,
|
|
"loss": 4.5211,
|
|
"mean_token_accuracy": 0.23942269682884215,
|
|
"num_tokens": 68338913.0,
|
|
"step": 24455
|
|
},
|
|
{
|
|
"entropy": 5.057774400711059,
|
|
"epoch": 2.9136390708755213,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041686626527344904,
|
|
"loss": 4.5052,
|
|
"mean_token_accuracy": 0.2403748795390129,
|
|
"num_tokens": 68353051.0,
|
|
"step": 24460
|
|
},
|
|
{
|
|
"entropy": 5.161046123504638,
|
|
"epoch": 2.9142346634901726,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004168331878414875,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.2359470397233963,
|
|
"num_tokens": 68369312.0,
|
|
"step": 24465
|
|
},
|
|
{
|
|
"entropy": 5.086872243881226,
|
|
"epoch": 2.9148302561048243,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041680010532220007,
|
|
"loss": 4.5184,
|
|
"mean_token_accuracy": 0.23547097593545913,
|
|
"num_tokens": 68385151.0,
|
|
"step": 24470
|
|
},
|
|
{
|
|
"entropy": 5.1630573749542235,
|
|
"epoch": 2.915425848719476,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041676701771677343,
|
|
"loss": 4.5355,
|
|
"mean_token_accuracy": 0.238381963968277,
|
|
"num_tokens": 68396776.0,
|
|
"step": 24475
|
|
},
|
|
{
|
|
"entropy": 5.142997932434082,
|
|
"epoch": 2.916021441334127,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004167339250263943,
|
|
"loss": 4.6872,
|
|
"mean_token_accuracy": 0.22390399128198624,
|
|
"num_tokens": 68411625.0,
|
|
"step": 24480
|
|
},
|
|
{
|
|
"entropy": 5.212140703201294,
|
|
"epoch": 2.916617033948779,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004167008272522498,
|
|
"loss": 4.6757,
|
|
"mean_token_accuracy": 0.2272736668586731,
|
|
"num_tokens": 68426032.0,
|
|
"step": 24485
|
|
},
|
|
{
|
|
"entropy": 5.162073755264283,
|
|
"epoch": 2.9172126265634306,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041666772439552703,
|
|
"loss": 4.6422,
|
|
"mean_token_accuracy": 0.2313435360789299,
|
|
"num_tokens": 68438601.0,
|
|
"step": 24490
|
|
},
|
|
{
|
|
"entropy": 5.1032593727111815,
|
|
"epoch": 2.9178082191780823,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041663461645741336,
|
|
"loss": 4.5342,
|
|
"mean_token_accuracy": 0.23747145235538483,
|
|
"num_tokens": 68453429.0,
|
|
"step": 24495
|
|
},
|
|
{
|
|
"entropy": 5.072541093826294,
|
|
"epoch": 2.918403811792734,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041660150343909613,
|
|
"loss": 4.4955,
|
|
"mean_token_accuracy": 0.24006802290678025,
|
|
"num_tokens": 68466783.0,
|
|
"step": 24500
|
|
},
|
|
{
|
|
"entropy": 5.131043577194214,
|
|
"epoch": 2.9189994044073853,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041656838534176335,
|
|
"loss": 4.5739,
|
|
"mean_token_accuracy": 0.23447984755039214,
|
|
"num_tokens": 68480590.0,
|
|
"step": 24505
|
|
},
|
|
{
|
|
"entropy": 5.052449035644531,
|
|
"epoch": 2.919594997022037,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004165352621666027,
|
|
"loss": 4.458,
|
|
"mean_token_accuracy": 0.23711756765842437,
|
|
"num_tokens": 68494778.0,
|
|
"step": 24510
|
|
},
|
|
{
|
|
"entropy": 5.083688163757325,
|
|
"epoch": 2.9201905896366886,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004165021339148023,
|
|
"loss": 4.5098,
|
|
"mean_token_accuracy": 0.24099230766296387,
|
|
"num_tokens": 68507360.0,
|
|
"step": 24515
|
|
},
|
|
{
|
|
"entropy": 5.094009304046631,
|
|
"epoch": 2.92078618225134,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041646900058755045,
|
|
"loss": 4.4587,
|
|
"mean_token_accuracy": 0.24872280210256575,
|
|
"num_tokens": 68520410.0,
|
|
"step": 24520
|
|
},
|
|
{
|
|
"entropy": 5.079051113128662,
|
|
"epoch": 2.9213817748659916,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041643586218603556,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.2372228428721428,
|
|
"num_tokens": 68534186.0,
|
|
"step": 24525
|
|
},
|
|
{
|
|
"entropy": 5.123928594589233,
|
|
"epoch": 2.9219773674806433,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004164027187114463,
|
|
"loss": 4.6364,
|
|
"mean_token_accuracy": 0.23803171664476394,
|
|
"num_tokens": 68547947.0,
|
|
"step": 24530
|
|
},
|
|
{
|
|
"entropy": 5.068834972381592,
|
|
"epoch": 2.9225729600952945,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004163695701649713,
|
|
"loss": 4.481,
|
|
"mean_token_accuracy": 0.24707140773534775,
|
|
"num_tokens": 68561360.0,
|
|
"step": 24535
|
|
},
|
|
{
|
|
"entropy": 5.086171054840088,
|
|
"epoch": 2.9231685527099462,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004163364165477998,
|
|
"loss": 4.5937,
|
|
"mean_token_accuracy": 0.2377607688307762,
|
|
"num_tokens": 68574613.0,
|
|
"step": 24540
|
|
},
|
|
{
|
|
"entropy": 5.042692089080811,
|
|
"epoch": 2.923764145324598,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004163032578611208,
|
|
"loss": 4.4689,
|
|
"mean_token_accuracy": 0.24562032371759415,
|
|
"num_tokens": 68590159.0,
|
|
"step": 24545
|
|
},
|
|
{
|
|
"entropy": 5.105303573608398,
|
|
"epoch": 2.9243597379392496,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041627009410612366,
|
|
"loss": 4.5306,
|
|
"mean_token_accuracy": 0.23759897351264953,
|
|
"num_tokens": 68603927.0,
|
|
"step": 24550
|
|
},
|
|
{
|
|
"entropy": 5.111356401443482,
|
|
"epoch": 2.9249553305539013,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004162369252839979,
|
|
"loss": 4.5399,
|
|
"mean_token_accuracy": 0.23448289632797242,
|
|
"num_tokens": 68618925.0,
|
|
"step": 24555
|
|
},
|
|
{
|
|
"entropy": 5.030804777145386,
|
|
"epoch": 2.9255509231685526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041620375139593335,
|
|
"loss": 4.4502,
|
|
"mean_token_accuracy": 0.24099384397268295,
|
|
"num_tokens": 68632906.0,
|
|
"step": 24560
|
|
},
|
|
{
|
|
"entropy": 5.103380012512207,
|
|
"epoch": 2.9261465157832043,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004161705724431198,
|
|
"loss": 4.6237,
|
|
"mean_token_accuracy": 0.23569790422916412,
|
|
"num_tokens": 68644431.0,
|
|
"step": 24565
|
|
},
|
|
{
|
|
"entropy": 5.050802373886109,
|
|
"epoch": 2.926742108397856,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004161373884267473,
|
|
"loss": 4.4836,
|
|
"mean_token_accuracy": 0.2419577956199646,
|
|
"num_tokens": 68658352.0,
|
|
"step": 24570
|
|
},
|
|
{
|
|
"entropy": 5.087498664855957,
|
|
"epoch": 2.9273377010125072,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041610419934800624,
|
|
"loss": 4.5299,
|
|
"mean_token_accuracy": 0.23696579039096832,
|
|
"num_tokens": 68672562.0,
|
|
"step": 24575
|
|
},
|
|
{
|
|
"entropy": 5.085306024551391,
|
|
"epoch": 2.927933293627159,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004160710052080869,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.2364051893353462,
|
|
"num_tokens": 68688449.0,
|
|
"step": 24580
|
|
},
|
|
{
|
|
"entropy": 5.097812461853027,
|
|
"epoch": 2.9285288862418106,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041603780600818,
|
|
"loss": 4.5966,
|
|
"mean_token_accuracy": 0.24046106934547423,
|
|
"num_tokens": 68702273.0,
|
|
"step": 24585
|
|
},
|
|
{
|
|
"entropy": 5.014613628387451,
|
|
"epoch": 2.9291244788564623,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004160046017494763,
|
|
"loss": 4.4537,
|
|
"mean_token_accuracy": 0.2456842303276062,
|
|
"num_tokens": 68714432.0,
|
|
"step": 24590
|
|
},
|
|
{
|
|
"entropy": 5.096839857101441,
|
|
"epoch": 2.929720071471114,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004159713924331668,
|
|
"loss": 4.5324,
|
|
"mean_token_accuracy": 0.23809123933315277,
|
|
"num_tokens": 68729864.0,
|
|
"step": 24595
|
|
},
|
|
{
|
|
"entropy": 5.190138530731201,
|
|
"epoch": 2.9303156640857653,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041593817806044267,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.22952055931091309,
|
|
"num_tokens": 68745306.0,
|
|
"step": 24600
|
|
},
|
|
{
|
|
"entropy": 5.121111011505127,
|
|
"epoch": 2.930911256700417,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004159049586324952,
|
|
"loss": 4.5417,
|
|
"mean_token_accuracy": 0.2358580619096756,
|
|
"num_tokens": 68759939.0,
|
|
"step": 24605
|
|
},
|
|
{
|
|
"entropy": 5.059925651550293,
|
|
"epoch": 2.9315068493150687,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000415871734150516,
|
|
"loss": 4.5104,
|
|
"mean_token_accuracy": 0.2355437159538269,
|
|
"num_tokens": 68774834.0,
|
|
"step": 24610
|
|
},
|
|
{
|
|
"entropy": 5.076224136352539,
|
|
"epoch": 2.93210244192972,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041583850461569675,
|
|
"loss": 4.5769,
|
|
"mean_token_accuracy": 0.23692088723182678,
|
|
"num_tokens": 68788317.0,
|
|
"step": 24615
|
|
},
|
|
{
|
|
"entropy": 5.112606763839722,
|
|
"epoch": 2.9326980345443716,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004158052700292292,
|
|
"loss": 4.5823,
|
|
"mean_token_accuracy": 0.23614400029182434,
|
|
"num_tokens": 68802142.0,
|
|
"step": 24620
|
|
},
|
|
{
|
|
"entropy": 5.085671472549438,
|
|
"epoch": 2.9332936271590233,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041577203039230577,
|
|
"loss": 4.5275,
|
|
"mean_token_accuracy": 0.2405554473400116,
|
|
"num_tokens": 68816996.0,
|
|
"step": 24625
|
|
},
|
|
{
|
|
"entropy": 5.10002179145813,
|
|
"epoch": 2.9338892197736746,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041573878570611835,
|
|
"loss": 4.5186,
|
|
"mean_token_accuracy": 0.2453383594751358,
|
|
"num_tokens": 68830122.0,
|
|
"step": 24630
|
|
},
|
|
{
|
|
"entropy": 5.070194101333618,
|
|
"epoch": 2.9344848123883263,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004157055359718595,
|
|
"loss": 4.464,
|
|
"mean_token_accuracy": 0.24809301346540452,
|
|
"num_tokens": 68843924.0,
|
|
"step": 24635
|
|
},
|
|
{
|
|
"entropy": 5.046384477615357,
|
|
"epoch": 2.935080405002978,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004156722811907219,
|
|
"loss": 4.4897,
|
|
"mean_token_accuracy": 0.24366266280412674,
|
|
"num_tokens": 68856186.0,
|
|
"step": 24640
|
|
},
|
|
{
|
|
"entropy": 5.074902629852295,
|
|
"epoch": 2.9356759976176297,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004156390213638983,
|
|
"loss": 4.5764,
|
|
"mean_token_accuracy": 0.24140592962503432,
|
|
"num_tokens": 68870609.0,
|
|
"step": 24645
|
|
},
|
|
{
|
|
"entropy": 5.117352533340454,
|
|
"epoch": 2.9362715902322813,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004156057564925816,
|
|
"loss": 4.5734,
|
|
"mean_token_accuracy": 0.24556306451559068,
|
|
"num_tokens": 68885748.0,
|
|
"step": 24650
|
|
},
|
|
{
|
|
"entropy": 5.072795104980469,
|
|
"epoch": 2.9368671828469326,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004155724865779652,
|
|
"loss": 4.4835,
|
|
"mean_token_accuracy": 0.23748041987419127,
|
|
"num_tokens": 68899726.0,
|
|
"step": 24655
|
|
},
|
|
{
|
|
"entropy": 5.094720792770386,
|
|
"epoch": 2.9374627754615843,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004155392116212421,
|
|
"loss": 4.5907,
|
|
"mean_token_accuracy": 0.23288565278053283,
|
|
"num_tokens": 68914742.0,
|
|
"step": 24660
|
|
},
|
|
{
|
|
"entropy": 5.0481208801269535,
|
|
"epoch": 2.938058368076236,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000415505931623606,
|
|
"loss": 4.4791,
|
|
"mean_token_accuracy": 0.24206144809722902,
|
|
"num_tokens": 68928411.0,
|
|
"step": 24665
|
|
},
|
|
{
|
|
"entropy": 5.056937408447266,
|
|
"epoch": 2.9386539606908872,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004154726465862506,
|
|
"loss": 4.44,
|
|
"mean_token_accuracy": 0.2463078334927559,
|
|
"num_tokens": 68940951.0,
|
|
"step": 24670
|
|
},
|
|
{
|
|
"entropy": 5.093835878372192,
|
|
"epoch": 2.939249553305539,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041543935651036976,
|
|
"loss": 4.5373,
|
|
"mean_token_accuracy": 0.23233958929777146,
|
|
"num_tokens": 68955562.0,
|
|
"step": 24675
|
|
},
|
|
{
|
|
"entropy": 5.08575119972229,
|
|
"epoch": 2.9398451459201906,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004154060613971576,
|
|
"loss": 4.5894,
|
|
"mean_token_accuracy": 0.23166747242212296,
|
|
"num_tokens": 68970122.0,
|
|
"step": 24680
|
|
},
|
|
{
|
|
"entropy": 5.059365463256836,
|
|
"epoch": 2.940440738534842,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004153727612478083,
|
|
"loss": 4.4986,
|
|
"mean_token_accuracy": 0.23732393682003022,
|
|
"num_tokens": 68982638.0,
|
|
"step": 24685
|
|
},
|
|
{
|
|
"entropy": 5.137355995178223,
|
|
"epoch": 2.9410363311494936,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004153394560635162,
|
|
"loss": 4.6059,
|
|
"mean_token_accuracy": 0.23039528876543044,
|
|
"num_tokens": 68996533.0,
|
|
"step": 24690
|
|
},
|
|
{
|
|
"entropy": 5.131608152389527,
|
|
"epoch": 2.9416319237641453,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041530614584547594,
|
|
"loss": 4.5528,
|
|
"mean_token_accuracy": 0.241154682636261,
|
|
"num_tokens": 69011480.0,
|
|
"step": 24695
|
|
},
|
|
{
|
|
"entropy": 5.1585510730743405,
|
|
"epoch": 2.942227516378797,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004152728305948825,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.22937409430742264,
|
|
"num_tokens": 69026159.0,
|
|
"step": 24700
|
|
},
|
|
{
|
|
"entropy": 5.0849957942962645,
|
|
"epoch": 2.9428231089934487,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004152395103129306,
|
|
"loss": 4.5974,
|
|
"mean_token_accuracy": 0.23353374749422073,
|
|
"num_tokens": 69042849.0,
|
|
"step": 24705
|
|
},
|
|
{
|
|
"entropy": 5.080613851547241,
|
|
"epoch": 2.9434187016081,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00041520618500081555,
|
|
"loss": 4.5608,
|
|
"mean_token_accuracy": 0.23195417523384093,
|
|
"num_tokens": 69056063.0,
|
|
"step": 24710
|
|
},
|
|
{
|
|
"entropy": 5.141990804672242,
|
|
"epoch": 2.9440142942227516,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041517285465973253,
|
|
"loss": 4.6487,
|
|
"mean_token_accuracy": 0.22637827396392823,
|
|
"num_tokens": 69070388.0,
|
|
"step": 24715
|
|
},
|
|
{
|
|
"entropy": 5.098562335968017,
|
|
"epoch": 2.9446098868374033,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041513951929087725,
|
|
"loss": 4.5606,
|
|
"mean_token_accuracy": 0.23390020579099655,
|
|
"num_tokens": 69084858.0,
|
|
"step": 24720
|
|
},
|
|
{
|
|
"entropy": 5.086099004745483,
|
|
"epoch": 2.9452054794520546,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041510617889544516,
|
|
"loss": 4.5496,
|
|
"mean_token_accuracy": 0.2349219247698784,
|
|
"num_tokens": 69098735.0,
|
|
"step": 24725
|
|
},
|
|
{
|
|
"entropy": 5.1626650333404545,
|
|
"epoch": 2.9458010720667063,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004150728334746322,
|
|
"loss": 4.5978,
|
|
"mean_token_accuracy": 0.23397936224937438,
|
|
"num_tokens": 69111668.0,
|
|
"step": 24730
|
|
},
|
|
{
|
|
"entropy": 5.053854608535767,
|
|
"epoch": 2.946396664681358,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041503948302963454,
|
|
"loss": 4.5003,
|
|
"mean_token_accuracy": 0.23949357867240906,
|
|
"num_tokens": 69125834.0,
|
|
"step": 24735
|
|
},
|
|
{
|
|
"entropy": 5.064891910552978,
|
|
"epoch": 2.9469922572960097,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041500612756164825,
|
|
"loss": 4.4853,
|
|
"mean_token_accuracy": 0.24377887398004533,
|
|
"num_tokens": 69139332.0,
|
|
"step": 24740
|
|
},
|
|
{
|
|
"entropy": 5.0424720287323,
|
|
"epoch": 2.9475878499106614,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041497276707186983,
|
|
"loss": 4.4796,
|
|
"mean_token_accuracy": 0.24695736318826675,
|
|
"num_tokens": 69153756.0,
|
|
"step": 24745
|
|
},
|
|
{
|
|
"entropy": 5.09010124206543,
|
|
"epoch": 2.9481834425253126,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041493940156149577,
|
|
"loss": 4.5355,
|
|
"mean_token_accuracy": 0.23413731753826142,
|
|
"num_tokens": 69169120.0,
|
|
"step": 24750
|
|
},
|
|
{
|
|
"entropy": 5.127086114883423,
|
|
"epoch": 2.9487790351399643,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041490603103172297,
|
|
"loss": 4.5261,
|
|
"mean_token_accuracy": 0.2404510885477066,
|
|
"num_tokens": 69181610.0,
|
|
"step": 24755
|
|
},
|
|
{
|
|
"entropy": 5.084095811843872,
|
|
"epoch": 2.949374627754616,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004148726554837484,
|
|
"loss": 4.5043,
|
|
"mean_token_accuracy": 0.24082765579223633,
|
|
"num_tokens": 69196051.0,
|
|
"step": 24760
|
|
},
|
|
{
|
|
"entropy": 5.084544849395752,
|
|
"epoch": 2.9499702203692673,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041483927491876887,
|
|
"loss": 4.5042,
|
|
"mean_token_accuracy": 0.24036861956119537,
|
|
"num_tokens": 69210712.0,
|
|
"step": 24765
|
|
},
|
|
{
|
|
"entropy": 5.100607585906983,
|
|
"epoch": 2.950565812983919,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004148058893379821,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.23401213586330413,
|
|
"num_tokens": 69225822.0,
|
|
"step": 24770
|
|
},
|
|
{
|
|
"entropy": 5.1883642196655275,
|
|
"epoch": 2.9511614055985707,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004147724987425853,
|
|
"loss": 4.6411,
|
|
"mean_token_accuracy": 0.22684765458106995,
|
|
"num_tokens": 69240352.0,
|
|
"step": 24775
|
|
},
|
|
{
|
|
"entropy": 5.0959179401397705,
|
|
"epoch": 2.951756998213222,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041473910313377633,
|
|
"loss": 4.5809,
|
|
"mean_token_accuracy": 0.2371016651391983,
|
|
"num_tokens": 69255776.0,
|
|
"step": 24780
|
|
},
|
|
{
|
|
"entropy": 5.162813377380371,
|
|
"epoch": 2.9523525908278736,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041470570251275285,
|
|
"loss": 4.585,
|
|
"mean_token_accuracy": 0.23829781413078308,
|
|
"num_tokens": 69268841.0,
|
|
"step": 24785
|
|
},
|
|
{
|
|
"entropy": 5.184308052062988,
|
|
"epoch": 2.9529481834425253,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041467229688071293,
|
|
"loss": 4.6208,
|
|
"mean_token_accuracy": 0.23479978889226913,
|
|
"num_tokens": 69281884.0,
|
|
"step": 24790
|
|
},
|
|
{
|
|
"entropy": 5.0395112991333,
|
|
"epoch": 2.953543776057177,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004146388862388549,
|
|
"loss": 4.5148,
|
|
"mean_token_accuracy": 0.24433660358190537,
|
|
"num_tokens": 69297444.0,
|
|
"step": 24795
|
|
},
|
|
{
|
|
"entropy": 5.193215274810791,
|
|
"epoch": 2.9541393686718287,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041460547058837704,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.23602031618356706,
|
|
"num_tokens": 69310361.0,
|
|
"step": 24800
|
|
},
|
|
{
|
|
"entropy": 4.984582185745239,
|
|
"epoch": 2.95473496128648,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000414572049930478,
|
|
"loss": 4.3681,
|
|
"mean_token_accuracy": 0.2537931650876999,
|
|
"num_tokens": 69322781.0,
|
|
"step": 24805
|
|
},
|
|
{
|
|
"entropy": 5.097261047363281,
|
|
"epoch": 2.9553305539011316,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004145386242663563,
|
|
"loss": 4.5719,
|
|
"mean_token_accuracy": 0.23653981685638428,
|
|
"num_tokens": 69336445.0,
|
|
"step": 24810
|
|
},
|
|
{
|
|
"entropy": 5.146959543228149,
|
|
"epoch": 2.9559261465157833,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004145051935972111,
|
|
"loss": 4.6019,
|
|
"mean_token_accuracy": 0.23560803532600402,
|
|
"num_tokens": 69349889.0,
|
|
"step": 24815
|
|
},
|
|
{
|
|
"entropy": 5.124263858795166,
|
|
"epoch": 2.9565217391304346,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004144717579242414,
|
|
"loss": 4.5098,
|
|
"mean_token_accuracy": 0.23825100660324097,
|
|
"num_tokens": 69362839.0,
|
|
"step": 24820
|
|
},
|
|
{
|
|
"entropy": 5.036801052093506,
|
|
"epoch": 2.9571173317450863,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041443831724864656,
|
|
"loss": 4.494,
|
|
"mean_token_accuracy": 0.2439000651240349,
|
|
"num_tokens": 69376530.0,
|
|
"step": 24825
|
|
},
|
|
{
|
|
"entropy": 5.073825407028198,
|
|
"epoch": 2.957712924359738,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041440487157162596,
|
|
"loss": 4.5696,
|
|
"mean_token_accuracy": 0.23467544764280318,
|
|
"num_tokens": 69388547.0,
|
|
"step": 24830
|
|
},
|
|
{
|
|
"entropy": 5.022338962554931,
|
|
"epoch": 2.9583085169743897,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041437142089437927,
|
|
"loss": 4.4987,
|
|
"mean_token_accuracy": 0.2434135913848877,
|
|
"num_tokens": 69402199.0,
|
|
"step": 24835
|
|
},
|
|
{
|
|
"entropy": 5.134946680068969,
|
|
"epoch": 2.958904109589041,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004143379652181064,
|
|
"loss": 4.5787,
|
|
"mean_token_accuracy": 0.23294742703437804,
|
|
"num_tokens": 69416253.0,
|
|
"step": 24840
|
|
},
|
|
{
|
|
"entropy": 5.063924837112427,
|
|
"epoch": 2.9594997022036926,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041430450454400716,
|
|
"loss": 4.5104,
|
|
"mean_token_accuracy": 0.2404744252562523,
|
|
"num_tokens": 69431033.0,
|
|
"step": 24845
|
|
},
|
|
{
|
|
"entropy": 5.052759599685669,
|
|
"epoch": 2.9600952948183443,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004142710388732819,
|
|
"loss": 4.4818,
|
|
"mean_token_accuracy": 0.24591125696897506,
|
|
"num_tokens": 69444723.0,
|
|
"step": 24850
|
|
},
|
|
{
|
|
"entropy": 5.17925500869751,
|
|
"epoch": 2.960690887432996,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004142375682071309,
|
|
"loss": 4.6677,
|
|
"mean_token_accuracy": 0.22608399987220765,
|
|
"num_tokens": 69458260.0,
|
|
"step": 24855
|
|
},
|
|
{
|
|
"entropy": 5.092427349090576,
|
|
"epoch": 2.9612864800476473,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00041420409254675465,
|
|
"loss": 4.5565,
|
|
"mean_token_accuracy": 0.23859583586454391,
|
|
"num_tokens": 69473241.0,
|
|
"step": 24860
|
|
},
|
|
{
|
|
"entropy": 5.132681894302368,
|
|
"epoch": 2.961882072662299,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000414170611893354,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.23246971815824508,
|
|
"num_tokens": 69486453.0,
|
|
"step": 24865
|
|
},
|
|
{
|
|
"entropy": 5.084941148757935,
|
|
"epoch": 2.9624776652769507,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004141371262481298,
|
|
"loss": 4.5182,
|
|
"mean_token_accuracy": 0.2385103613138199,
|
|
"num_tokens": 69502063.0,
|
|
"step": 24870
|
|
},
|
|
{
|
|
"entropy": 5.086522912979126,
|
|
"epoch": 2.963073257891602,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00041410363561228316,
|
|
"loss": 4.5029,
|
|
"mean_token_accuracy": 0.2422377124428749,
|
|
"num_tokens": 69515807.0,
|
|
"step": 24875
|
|
},
|
|
{
|
|
"entropy": 5.079001712799072,
|
|
"epoch": 2.9636688505062536,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004140701399870151,
|
|
"loss": 4.5065,
|
|
"mean_token_accuracy": 0.2389187216758728,
|
|
"num_tokens": 69530014.0,
|
|
"step": 24880
|
|
},
|
|
{
|
|
"entropy": 5.113999700546264,
|
|
"epoch": 2.9642644431209053,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004140366393735274,
|
|
"loss": 4.5811,
|
|
"mean_token_accuracy": 0.23534793257713318,
|
|
"num_tokens": 69542558.0,
|
|
"step": 24885
|
|
},
|
|
{
|
|
"entropy": 5.080617475509643,
|
|
"epoch": 2.964860035735557,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041400313377302144,
|
|
"loss": 4.5163,
|
|
"mean_token_accuracy": 0.24342491179704667,
|
|
"num_tokens": 69554583.0,
|
|
"step": 24890
|
|
},
|
|
{
|
|
"entropy": 5.158694219589234,
|
|
"epoch": 2.9654556283502087,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000413969623186699,
|
|
"loss": 4.5643,
|
|
"mean_token_accuracy": 0.23490039855241776,
|
|
"num_tokens": 69568003.0,
|
|
"step": 24895
|
|
},
|
|
{
|
|
"entropy": 5.073746919631958,
|
|
"epoch": 2.96605122096486,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004139361076157622,
|
|
"loss": 4.4793,
|
|
"mean_token_accuracy": 0.24118960350751878,
|
|
"num_tokens": 69581698.0,
|
|
"step": 24900
|
|
},
|
|
{
|
|
"entropy": 5.033059597015381,
|
|
"epoch": 2.9666468135795117,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004139025870614131,
|
|
"loss": 4.4501,
|
|
"mean_token_accuracy": 0.25206656008958817,
|
|
"num_tokens": 69594959.0,
|
|
"step": 24905
|
|
},
|
|
{
|
|
"entropy": 5.072538661956787,
|
|
"epoch": 2.9672424061941634,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004138690615248541,
|
|
"loss": 4.5087,
|
|
"mean_token_accuracy": 0.2457405999302864,
|
|
"num_tokens": 69609569.0,
|
|
"step": 24910
|
|
},
|
|
{
|
|
"entropy": 5.064161539077759,
|
|
"epoch": 2.9678379988088146,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004138355310072876,
|
|
"loss": 4.4962,
|
|
"mean_token_accuracy": 0.23721452802419662,
|
|
"num_tokens": 69624102.0,
|
|
"step": 24915
|
|
},
|
|
{
|
|
"entropy": 5.10995078086853,
|
|
"epoch": 2.9684335914234663,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00041380199550991635,
|
|
"loss": 4.5588,
|
|
"mean_token_accuracy": 0.2403255358338356,
|
|
"num_tokens": 69639403.0,
|
|
"step": 24920
|
|
},
|
|
{
|
|
"entropy": 5.130537748336792,
|
|
"epoch": 2.969029184038118,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004137684550339432,
|
|
"loss": 4.5765,
|
|
"mean_token_accuracy": 0.23960770815610885,
|
|
"num_tokens": 69653079.0,
|
|
"step": 24925
|
|
},
|
|
{
|
|
"entropy": 5.105968189239502,
|
|
"epoch": 2.9696247766527692,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004137349095805712,
|
|
"loss": 4.6166,
|
|
"mean_token_accuracy": 0.22974403500556945,
|
|
"num_tokens": 69669008.0,
|
|
"step": 24930
|
|
},
|
|
{
|
|
"entropy": 5.193576860427856,
|
|
"epoch": 2.970220369267421,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004137013591510035,
|
|
"loss": 4.674,
|
|
"mean_token_accuracy": 0.2197754442691803,
|
|
"num_tokens": 69681915.0,
|
|
"step": 24935
|
|
},
|
|
{
|
|
"entropy": 5.14147539138794,
|
|
"epoch": 2.9708159618820726,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004136678037464437,
|
|
"loss": 4.5378,
|
|
"mean_token_accuracy": 0.2386598616838455,
|
|
"num_tokens": 69696699.0,
|
|
"step": 24940
|
|
},
|
|
{
|
|
"entropy": 5.066253519058227,
|
|
"epoch": 2.9714115544967243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004136342433680951,
|
|
"loss": 4.6201,
|
|
"mean_token_accuracy": 0.22495026588439943,
|
|
"num_tokens": 69712675.0,
|
|
"step": 24945
|
|
},
|
|
{
|
|
"entropy": 5.100515413284302,
|
|
"epoch": 2.972007147111376,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041360067801716165,
|
|
"loss": 4.5281,
|
|
"mean_token_accuracy": 0.23620210886001586,
|
|
"num_tokens": 69727965.0,
|
|
"step": 24950
|
|
},
|
|
{
|
|
"entropy": 5.058931016921997,
|
|
"epoch": 2.9726027397260273,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004135671076948472,
|
|
"loss": 4.4443,
|
|
"mean_token_accuracy": 0.24686574041843415,
|
|
"num_tokens": 69741179.0,
|
|
"step": 24955
|
|
},
|
|
{
|
|
"entropy": 5.0692534923553465,
|
|
"epoch": 2.973198332340679,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004135335324023559,
|
|
"loss": 4.4914,
|
|
"mean_token_accuracy": 0.23798879981040955,
|
|
"num_tokens": 69755066.0,
|
|
"step": 24960
|
|
},
|
|
{
|
|
"entropy": 4.999352693557739,
|
|
"epoch": 2.9737939249553307,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041349995214089207,
|
|
"loss": 4.4033,
|
|
"mean_token_accuracy": 0.2538206458091736,
|
|
"num_tokens": 69769821.0,
|
|
"step": 24965
|
|
},
|
|
{
|
|
"entropy": 4.991926574707032,
|
|
"epoch": 2.974389517569982,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041346636691166015,
|
|
"loss": 4.3453,
|
|
"mean_token_accuracy": 0.24917495101690293,
|
|
"num_tokens": 69782113.0,
|
|
"step": 24970
|
|
},
|
|
{
|
|
"entropy": 5.074076128005982,
|
|
"epoch": 2.9749851101846336,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004134327767158648,
|
|
"loss": 4.5844,
|
|
"mean_token_accuracy": 0.2359134867787361,
|
|
"num_tokens": 69795953.0,
|
|
"step": 24975
|
|
},
|
|
{
|
|
"entropy": 5.028626775741577,
|
|
"epoch": 2.9755807027992853,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004133991815547108,
|
|
"loss": 4.4709,
|
|
"mean_token_accuracy": 0.24213553816080094,
|
|
"num_tokens": 69810282.0,
|
|
"step": 24980
|
|
},
|
|
{
|
|
"entropy": 4.9979266166687015,
|
|
"epoch": 2.976176295413937,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004133655814294031,
|
|
"loss": 4.4637,
|
|
"mean_token_accuracy": 0.24556418657302856,
|
|
"num_tokens": 69824473.0,
|
|
"step": 24985
|
|
},
|
|
{
|
|
"entropy": 5.050501728057862,
|
|
"epoch": 2.9767718880285887,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000413331976341147,
|
|
"loss": 4.5157,
|
|
"mean_token_accuracy": 0.2387314334511757,
|
|
"num_tokens": 69837903.0,
|
|
"step": 24990
|
|
},
|
|
{
|
|
"entropy": 5.079523372650146,
|
|
"epoch": 2.97736748064324,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00041329836629114784,
|
|
"loss": 4.5076,
|
|
"mean_token_accuracy": 0.2394447311758995,
|
|
"num_tokens": 69851076.0,
|
|
"step": 24995
|
|
},
|
|
{
|
|
"entropy": 5.055651044845581,
|
|
"epoch": 2.9779630732578917,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004132647512806112,
|
|
"loss": 4.5147,
|
|
"mean_token_accuracy": 0.23589736372232437,
|
|
"num_tokens": 69865134.0,
|
|
"step": 25000
|
|
},
|
|
{
|
|
"entropy": 5.11888017654419,
|
|
"epoch": 2.9785586658725434,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004132311313107427,
|
|
"loss": 4.5989,
|
|
"mean_token_accuracy": 0.23658497333526612,
|
|
"num_tokens": 69879399.0,
|
|
"step": 25005
|
|
},
|
|
{
|
|
"entropy": 5.079950904846191,
|
|
"epoch": 2.9791542584871946,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004131975063827482,
|
|
"loss": 4.4831,
|
|
"mean_token_accuracy": 0.2463008239865303,
|
|
"num_tokens": 69892070.0,
|
|
"step": 25010
|
|
},
|
|
{
|
|
"entropy": 5.073730564117431,
|
|
"epoch": 2.9797498511018463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000413163876497834,
|
|
"loss": 4.5325,
|
|
"mean_token_accuracy": 0.2366888090968132,
|
|
"num_tokens": 69906320.0,
|
|
"step": 25015
|
|
},
|
|
{
|
|
"entropy": 5.137524271011353,
|
|
"epoch": 2.980345443716498,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000413130241657206,
|
|
"loss": 4.5586,
|
|
"mean_token_accuracy": 0.23402435779571534,
|
|
"num_tokens": 69918450.0,
|
|
"step": 25020
|
|
},
|
|
{
|
|
"entropy": 5.108385801315308,
|
|
"epoch": 2.9809410363311493,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041309660186207093,
|
|
"loss": 4.5774,
|
|
"mean_token_accuracy": 0.23381391167640686,
|
|
"num_tokens": 69932990.0,
|
|
"step": 25025
|
|
},
|
|
{
|
|
"entropy": 5.115176486968994,
|
|
"epoch": 2.981536628945801,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00041306295711363526,
|
|
"loss": 4.6218,
|
|
"mean_token_accuracy": 0.2341161772608757,
|
|
"num_tokens": 69947469.0,
|
|
"step": 25030
|
|
},
|
|
{
|
|
"entropy": 5.0594898700714115,
|
|
"epoch": 2.9821322215604527,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00041302930741310585,
|
|
"loss": 4.5452,
|
|
"mean_token_accuracy": 0.24304286688566207,
|
|
"num_tokens": 69963049.0,
|
|
"step": 25035
|
|
},
|
|
{
|
|
"entropy": 5.146502542495727,
|
|
"epoch": 2.9827278141751044,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004129956527616895,
|
|
"loss": 4.5833,
|
|
"mean_token_accuracy": 0.2308567315340042,
|
|
"num_tokens": 69978278.0,
|
|
"step": 25040
|
|
},
|
|
{
|
|
"entropy": 5.087097072601319,
|
|
"epoch": 2.983323406789756,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004129619931605935,
|
|
"loss": 4.5028,
|
|
"mean_token_accuracy": 0.23547306656837463,
|
|
"num_tokens": 69992113.0,
|
|
"step": 25045
|
|
},
|
|
{
|
|
"entropy": 5.0496964931488035,
|
|
"epoch": 2.9839189994044073,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004129283286110251,
|
|
"loss": 4.5092,
|
|
"mean_token_accuracy": 0.2415752351284027,
|
|
"num_tokens": 70005916.0,
|
|
"step": 25050
|
|
},
|
|
{
|
|
"entropy": 5.150510597229004,
|
|
"epoch": 2.984514592019059,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041289465911419196,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.22771500647068024,
|
|
"num_tokens": 70021123.0,
|
|
"step": 25055
|
|
},
|
|
{
|
|
"entropy": 5.119111156463623,
|
|
"epoch": 2.9851101846337107,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004128609846713014,
|
|
"loss": 4.5214,
|
|
"mean_token_accuracy": 0.2321985185146332,
|
|
"num_tokens": 70035628.0,
|
|
"step": 25060
|
|
},
|
|
{
|
|
"entropy": 5.198595571517944,
|
|
"epoch": 2.985705777248362,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004128273052835616,
|
|
"loss": 4.6348,
|
|
"mean_token_accuracy": 0.23358179330825807,
|
|
"num_tokens": 70050964.0,
|
|
"step": 25065
|
|
},
|
|
{
|
|
"entropy": 5.090951538085937,
|
|
"epoch": 2.9863013698630136,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004127936209521803,
|
|
"loss": 4.5223,
|
|
"mean_token_accuracy": 0.2370297446846962,
|
|
"num_tokens": 70066325.0,
|
|
"step": 25070
|
|
},
|
|
{
|
|
"entropy": 5.0275129795074465,
|
|
"epoch": 2.9868969624776653,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000412759931678366,
|
|
"loss": 4.4644,
|
|
"mean_token_accuracy": 0.23980284184217454,
|
|
"num_tokens": 70080010.0,
|
|
"step": 25075
|
|
},
|
|
{
|
|
"entropy": 5.096774911880493,
|
|
"epoch": 2.9874925550923166,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041272623746332687,
|
|
"loss": 4.553,
|
|
"mean_token_accuracy": 0.24061693549156188,
|
|
"num_tokens": 70095623.0,
|
|
"step": 25080
|
|
},
|
|
{
|
|
"entropy": 5.059111261367798,
|
|
"epoch": 2.9880881477069683,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004126925383082716,
|
|
"loss": 4.5418,
|
|
"mean_token_accuracy": 0.2388956531882286,
|
|
"num_tokens": 70108951.0,
|
|
"step": 25085
|
|
},
|
|
{
|
|
"entropy": 5.0800087451934814,
|
|
"epoch": 2.98868374032162,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00041265883421440875,
|
|
"loss": 4.5446,
|
|
"mean_token_accuracy": 0.23810476660728455,
|
|
"num_tokens": 70122742.0,
|
|
"step": 25090
|
|
},
|
|
{
|
|
"entropy": 5.14818549156189,
|
|
"epoch": 2.9892793329362717,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041262512518294736,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.23691435158252716,
|
|
"num_tokens": 70135244.0,
|
|
"step": 25095
|
|
},
|
|
{
|
|
"entropy": 5.133173656463623,
|
|
"epoch": 2.9898749255509234,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041259141121509655,
|
|
"loss": 4.5324,
|
|
"mean_token_accuracy": 0.24189985692501068,
|
|
"num_tokens": 70148946.0,
|
|
"step": 25100
|
|
},
|
|
{
|
|
"entropy": 5.140398645401001,
|
|
"epoch": 2.9904705181655746,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004125576923120655,
|
|
"loss": 4.617,
|
|
"mean_token_accuracy": 0.23146902322769164,
|
|
"num_tokens": 70163250.0,
|
|
"step": 25105
|
|
},
|
|
{
|
|
"entropy": 5.126958417892456,
|
|
"epoch": 2.9910661107802263,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041252396847506374,
|
|
"loss": 4.5651,
|
|
"mean_token_accuracy": 0.23380821645259858,
|
|
"num_tokens": 70176393.0,
|
|
"step": 25110
|
|
},
|
|
{
|
|
"entropy": 5.053048324584961,
|
|
"epoch": 2.991661703394878,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041249023970530075,
|
|
"loss": 4.4931,
|
|
"mean_token_accuracy": 0.2424229845404625,
|
|
"num_tokens": 70190830.0,
|
|
"step": 25115
|
|
},
|
|
{
|
|
"entropy": 5.068418073654175,
|
|
"epoch": 2.9922572960095293,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041245650600398644,
|
|
"loss": 4.5417,
|
|
"mean_token_accuracy": 0.24019312113523483,
|
|
"num_tokens": 70204245.0,
|
|
"step": 25120
|
|
},
|
|
{
|
|
"entropy": 5.14423394203186,
|
|
"epoch": 2.992852888624181,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00041242276737233073,
|
|
"loss": 4.5842,
|
|
"mean_token_accuracy": 0.22937319427728653,
|
|
"num_tokens": 70219782.0,
|
|
"step": 25125
|
|
},
|
|
{
|
|
"entropy": 5.105996417999267,
|
|
"epoch": 2.9934484812388327,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041238902381154376,
|
|
"loss": 4.5371,
|
|
"mean_token_accuracy": 0.2357850566506386,
|
|
"num_tokens": 70232522.0,
|
|
"step": 25130
|
|
},
|
|
{
|
|
"entropy": 5.048750400543213,
|
|
"epoch": 2.9940440738534844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041235527532283603,
|
|
"loss": 4.4997,
|
|
"mean_token_accuracy": 0.24356047213077545,
|
|
"num_tokens": 70245959.0,
|
|
"step": 25135
|
|
},
|
|
{
|
|
"entropy": 5.096183490753174,
|
|
"epoch": 2.994639666468136,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004123215219074177,
|
|
"loss": 4.604,
|
|
"mean_token_accuracy": 0.23692889660596847,
|
|
"num_tokens": 70260508.0,
|
|
"step": 25140
|
|
},
|
|
{
|
|
"entropy": 5.08719916343689,
|
|
"epoch": 2.9952352590827873,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041228776356649975,
|
|
"loss": 4.4718,
|
|
"mean_token_accuracy": 0.24399055391550065,
|
|
"num_tokens": 70273501.0,
|
|
"step": 25145
|
|
},
|
|
{
|
|
"entropy": 5.067587375640869,
|
|
"epoch": 2.995830851697439,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00041225400030129304,
|
|
"loss": 4.5261,
|
|
"mean_token_accuracy": 0.25543999671936035,
|
|
"num_tokens": 70285714.0,
|
|
"step": 25150
|
|
},
|
|
{
|
|
"entropy": 5.083327007293701,
|
|
"epoch": 2.9964264443120907,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00041222023211300837,
|
|
"loss": 4.5221,
|
|
"mean_token_accuracy": 0.23986044228076936,
|
|
"num_tokens": 70299889.0,
|
|
"step": 25155
|
|
},
|
|
{
|
|
"entropy": 5.094454288482666,
|
|
"epoch": 2.997022036926742,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004121864590028571,
|
|
"loss": 4.5093,
|
|
"mean_token_accuracy": 0.2397127255797386,
|
|
"num_tokens": 70314231.0,
|
|
"step": 25160
|
|
},
|
|
{
|
|
"entropy": 5.130092191696167,
|
|
"epoch": 2.9976176295413937,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004121526809720506,
|
|
"loss": 4.5984,
|
|
"mean_token_accuracy": 0.2338034674525261,
|
|
"num_tokens": 70328803.0,
|
|
"step": 25165
|
|
},
|
|
{
|
|
"entropy": 5.087918758392334,
|
|
"epoch": 2.9982132221560454,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004121188980218004,
|
|
"loss": 4.5727,
|
|
"mean_token_accuracy": 0.2323555752635002,
|
|
"num_tokens": 70341672.0,
|
|
"step": 25170
|
|
},
|
|
{
|
|
"entropy": 5.115515422821045,
|
|
"epoch": 2.9988088147706966,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004120851101533183,
|
|
"loss": 4.5079,
|
|
"mean_token_accuracy": 0.23964306116104125,
|
|
"num_tokens": 70354111.0,
|
|
"step": 25175
|
|
},
|
|
{
|
|
"entropy": 5.200827360153198,
|
|
"epoch": 2.9994044073853483,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004120513173678162,
|
|
"loss": 4.619,
|
|
"mean_token_accuracy": 0.23315396159887314,
|
|
"num_tokens": 70369986.0,
|
|
"step": 25180
|
|
},
|
|
{
|
|
"entropy": 5.160596323013306,
|
|
"epoch": 3.0,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004120175196665062,
|
|
"loss": 4.607,
|
|
"mean_token_accuracy": 0.2329641044139862,
|
|
"num_tokens": 70383036.0,
|
|
"step": 25185
|
|
},
|
|
{
|
|
"entropy": 5.050224018096924,
|
|
"epoch": 3.0005955926146517,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004119837170506005,
|
|
"loss": 4.4586,
|
|
"mean_token_accuracy": 0.2457107871770859,
|
|
"num_tokens": 70398648.0,
|
|
"step": 25190
|
|
},
|
|
{
|
|
"entropy": 5.143838834762573,
|
|
"epoch": 3.001191185229303,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004119499095213116,
|
|
"loss": 4.5405,
|
|
"mean_token_accuracy": 0.2404778480529785,
|
|
"num_tokens": 70412789.0,
|
|
"step": 25195
|
|
},
|
|
{
|
|
"entropy": 5.010136318206787,
|
|
"epoch": 3.0017867778439546,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041191609707985215,
|
|
"loss": 4.3777,
|
|
"mean_token_accuracy": 0.25033225417137145,
|
|
"num_tokens": 70426036.0,
|
|
"step": 25200
|
|
},
|
|
{
|
|
"entropy": 5.02396183013916,
|
|
"epoch": 3.0023823704586063,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041188227972743487,
|
|
"loss": 4.4397,
|
|
"mean_token_accuracy": 0.24678760170936584,
|
|
"num_tokens": 70440758.0,
|
|
"step": 25205
|
|
},
|
|
{
|
|
"entropy": 5.130111598968506,
|
|
"epoch": 3.002977963073258,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004118484574652728,
|
|
"loss": 4.5679,
|
|
"mean_token_accuracy": 0.23895447552204133,
|
|
"num_tokens": 70454664.0,
|
|
"step": 25210
|
|
},
|
|
{
|
|
"entropy": 5.047907781600952,
|
|
"epoch": 3.0035735556879093,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041181463029457905,
|
|
"loss": 4.4281,
|
|
"mean_token_accuracy": 0.24378843903541564,
|
|
"num_tokens": 70468705.0,
|
|
"step": 25215
|
|
},
|
|
{
|
|
"entropy": 5.085370492935181,
|
|
"epoch": 3.004169148302561,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041178079821656695,
|
|
"loss": 4.4729,
|
|
"mean_token_accuracy": 0.24182780236005783,
|
|
"num_tokens": 70482032.0,
|
|
"step": 25220
|
|
},
|
|
{
|
|
"entropy": 5.0102653980255125,
|
|
"epoch": 3.0047647409172127,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041174696123245,
|
|
"loss": 4.453,
|
|
"mean_token_accuracy": 0.24663888812065124,
|
|
"num_tokens": 70493583.0,
|
|
"step": 25225
|
|
},
|
|
{
|
|
"entropy": 4.995967626571655,
|
|
"epoch": 3.0053603335318644,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004117131193434419,
|
|
"loss": 4.4109,
|
|
"mean_token_accuracy": 0.25363615304231646,
|
|
"num_tokens": 70508187.0,
|
|
"step": 25230
|
|
},
|
|
{
|
|
"entropy": 5.147590208053589,
|
|
"epoch": 3.0059559261465156,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004116792725507565,
|
|
"loss": 4.5512,
|
|
"mean_token_accuracy": 0.2400110274553299,
|
|
"num_tokens": 70523279.0,
|
|
"step": 25235
|
|
},
|
|
{
|
|
"entropy": 5.078269195556641,
|
|
"epoch": 3.0065515187611673,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004116454208556078,
|
|
"loss": 4.4768,
|
|
"mean_token_accuracy": 0.24144981652498246,
|
|
"num_tokens": 70538988.0,
|
|
"step": 25240
|
|
},
|
|
{
|
|
"entropy": 5.003624105453492,
|
|
"epoch": 3.007147111375819,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041161156425921004,
|
|
"loss": 4.3833,
|
|
"mean_token_accuracy": 0.2523159831762314,
|
|
"num_tokens": 70553957.0,
|
|
"step": 25245
|
|
},
|
|
{
|
|
"entropy": 5.103939437866211,
|
|
"epoch": 3.0077427039904707,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041157770276277754,
|
|
"loss": 4.506,
|
|
"mean_token_accuracy": 0.2375418648123741,
|
|
"num_tokens": 70567225.0,
|
|
"step": 25250
|
|
},
|
|
{
|
|
"entropy": 5.0036979675292965,
|
|
"epoch": 3.008338296605122,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041154383636752493,
|
|
"loss": 4.3908,
|
|
"mean_token_accuracy": 0.2471398025751114,
|
|
"num_tokens": 70581277.0,
|
|
"step": 25255
|
|
},
|
|
{
|
|
"entropy": 5.033769416809082,
|
|
"epoch": 3.0089338892197737,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000411509965074667,
|
|
"loss": 4.4303,
|
|
"mean_token_accuracy": 0.24799794256687163,
|
|
"num_tokens": 70595286.0,
|
|
"step": 25260
|
|
},
|
|
{
|
|
"entropy": 5.135784721374511,
|
|
"epoch": 3.0095294818344254,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041147608888541853,
|
|
"loss": 4.4956,
|
|
"mean_token_accuracy": 0.23809933364391328,
|
|
"num_tokens": 70609366.0,
|
|
"step": 25265
|
|
},
|
|
{
|
|
"entropy": 5.057107448577881,
|
|
"epoch": 3.0101250744490766,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004114422078009946,
|
|
"loss": 4.4903,
|
|
"mean_token_accuracy": 0.24245519787073136,
|
|
"num_tokens": 70623882.0,
|
|
"step": 25270
|
|
},
|
|
{
|
|
"entropy": 5.087855195999145,
|
|
"epoch": 3.0107206670637283,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004114083218226105,
|
|
"loss": 4.5113,
|
|
"mean_token_accuracy": 0.24228008091449738,
|
|
"num_tokens": 70636878.0,
|
|
"step": 25275
|
|
},
|
|
{
|
|
"entropy": 5.138953638076782,
|
|
"epoch": 3.01131625967838,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00041137443095148174,
|
|
"loss": 4.5404,
|
|
"mean_token_accuracy": 0.24100581258535386,
|
|
"num_tokens": 70652660.0,
|
|
"step": 25280
|
|
},
|
|
{
|
|
"entropy": 5.1012468338012695,
|
|
"epoch": 3.0119118522930317,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00041134053518882387,
|
|
"loss": 4.4712,
|
|
"mean_token_accuracy": 0.24186257272958755,
|
|
"num_tokens": 70666342.0,
|
|
"step": 25285
|
|
},
|
|
{
|
|
"entropy": 5.029444217681885,
|
|
"epoch": 3.012507444907683,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004113066345358527,
|
|
"loss": 4.3931,
|
|
"mean_token_accuracy": 0.2551344111561775,
|
|
"num_tokens": 70679301.0,
|
|
"step": 25290
|
|
},
|
|
{
|
|
"entropy": 4.989445734024048,
|
|
"epoch": 3.0131030375223347,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041127272899378414,
|
|
"loss": 4.3752,
|
|
"mean_token_accuracy": 0.25085505545139314,
|
|
"num_tokens": 70692647.0,
|
|
"step": 25295
|
|
},
|
|
{
|
|
"entropy": 5.0779016494750975,
|
|
"epoch": 3.0136986301369864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041123881856383436,
|
|
"loss": 4.4582,
|
|
"mean_token_accuracy": 0.24702000319957734,
|
|
"num_tokens": 70706345.0,
|
|
"step": 25300
|
|
},
|
|
{
|
|
"entropy": 5.113903474807739,
|
|
"epoch": 3.014294222751638,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041120490324721967,
|
|
"loss": 4.4905,
|
|
"mean_token_accuracy": 0.24226545691490173,
|
|
"num_tokens": 70720688.0,
|
|
"step": 25305
|
|
},
|
|
{
|
|
"entropy": 5.0558919429779055,
|
|
"epoch": 3.0148898153662893,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004111709830451566,
|
|
"loss": 4.4557,
|
|
"mean_token_accuracy": 0.24291908442974092,
|
|
"num_tokens": 70734365.0,
|
|
"step": 25310
|
|
},
|
|
{
|
|
"entropy": 5.0260721206665036,
|
|
"epoch": 3.015485407980941,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041113705795886167,
|
|
"loss": 4.3891,
|
|
"mean_token_accuracy": 0.24911382496356965,
|
|
"num_tokens": 70747730.0,
|
|
"step": 25315
|
|
},
|
|
{
|
|
"entropy": 5.1111743450164795,
|
|
"epoch": 3.0160810005955927,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041110312798955186,
|
|
"loss": 4.4903,
|
|
"mean_token_accuracy": 0.24092113524675368,
|
|
"num_tokens": 70759838.0,
|
|
"step": 25320
|
|
},
|
|
{
|
|
"entropy": 5.13877763748169,
|
|
"epoch": 3.0166765932102444,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041106919313844417,
|
|
"loss": 4.6085,
|
|
"mean_token_accuracy": 0.2333862692117691,
|
|
"num_tokens": 70774308.0,
|
|
"step": 25325
|
|
},
|
|
{
|
|
"entropy": 5.082631635665893,
|
|
"epoch": 3.0172721858248956,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004110352534067557,
|
|
"loss": 4.4828,
|
|
"mean_token_accuracy": 0.24029806405305862,
|
|
"num_tokens": 70790585.0,
|
|
"step": 25330
|
|
},
|
|
{
|
|
"entropy": 5.04525203704834,
|
|
"epoch": 3.0178677784395473,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041100130879570394,
|
|
"loss": 4.4425,
|
|
"mean_token_accuracy": 0.24739214926958084,
|
|
"num_tokens": 70803245.0,
|
|
"step": 25335
|
|
},
|
|
{
|
|
"entropy": 5.118955135345459,
|
|
"epoch": 3.018463371054199,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004109673593065063,
|
|
"loss": 4.5268,
|
|
"mean_token_accuracy": 0.23251271843910218,
|
|
"num_tokens": 70814321.0,
|
|
"step": 25340
|
|
},
|
|
{
|
|
"entropy": 5.086463689804077,
|
|
"epoch": 3.0190589636688503,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004109334049403806,
|
|
"loss": 4.4932,
|
|
"mean_token_accuracy": 0.24247309565544128,
|
|
"num_tokens": 70829562.0,
|
|
"step": 25345
|
|
},
|
|
{
|
|
"entropy": 5.1499382019042965,
|
|
"epoch": 3.019654556283502,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004108994456985446,
|
|
"loss": 4.5327,
|
|
"mean_token_accuracy": 0.238053035736084,
|
|
"num_tokens": 70842957.0,
|
|
"step": 25350
|
|
},
|
|
{
|
|
"entropy": 5.150203371047974,
|
|
"epoch": 3.0202501488981537,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004108654815822165,
|
|
"loss": 4.6074,
|
|
"mean_token_accuracy": 0.22586818933486938,
|
|
"num_tokens": 70857367.0,
|
|
"step": 25355
|
|
},
|
|
{
|
|
"entropy": 5.1526435852050785,
|
|
"epoch": 3.0208457415128054,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004108315125926145,
|
|
"loss": 4.5327,
|
|
"mean_token_accuracy": 0.2437130942940712,
|
|
"num_tokens": 70870555.0,
|
|
"step": 25360
|
|
},
|
|
{
|
|
"entropy": 5.079288196563721,
|
|
"epoch": 3.0214413341274566,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000410797538730957,
|
|
"loss": 4.4872,
|
|
"mean_token_accuracy": 0.23707534074783326,
|
|
"num_tokens": 70885546.0,
|
|
"step": 25365
|
|
},
|
|
{
|
|
"entropy": 5.032179069519043,
|
|
"epoch": 3.0220369267421083,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00041076355999846256,
|
|
"loss": 4.4931,
|
|
"mean_token_accuracy": 0.24121877551078796,
|
|
"num_tokens": 70899618.0,
|
|
"step": 25370
|
|
},
|
|
{
|
|
"entropy": 5.122150516510009,
|
|
"epoch": 3.02263251935676,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00041072957639634984,
|
|
"loss": 4.5204,
|
|
"mean_token_accuracy": 0.24306539595127105,
|
|
"num_tokens": 70912422.0,
|
|
"step": 25375
|
|
},
|
|
{
|
|
"entropy": 5.064097833633423,
|
|
"epoch": 3.0232281119714117,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041069558792583804,
|
|
"loss": 4.4545,
|
|
"mean_token_accuracy": 0.24211226105690004,
|
|
"num_tokens": 70926399.0,
|
|
"step": 25380
|
|
},
|
|
{
|
|
"entropy": 5.136578130722046,
|
|
"epoch": 3.023823704586063,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00041066159458814607,
|
|
"loss": 4.4683,
|
|
"mean_token_accuracy": 0.24212680160999298,
|
|
"num_tokens": 70940532.0,
|
|
"step": 25385
|
|
},
|
|
{
|
|
"entropy": 5.109817838668823,
|
|
"epoch": 3.0244192972007147,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041062759638449333,
|
|
"loss": 4.5481,
|
|
"mean_token_accuracy": 0.23401915580034255,
|
|
"num_tokens": 70955490.0,
|
|
"step": 25390
|
|
},
|
|
{
|
|
"entropy": 5.162940740585327,
|
|
"epoch": 3.0250148898153664,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00041059359331609916,
|
|
"loss": 4.6266,
|
|
"mean_token_accuracy": 0.22944642305374147,
|
|
"num_tokens": 70971659.0,
|
|
"step": 25395
|
|
},
|
|
{
|
|
"entropy": 5.1800731182098385,
|
|
"epoch": 3.025610482430018,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004105595853841833,
|
|
"loss": 4.5733,
|
|
"mean_token_accuracy": 0.23157300502061845,
|
|
"num_tokens": 70985042.0,
|
|
"step": 25400
|
|
},
|
|
{
|
|
"entropy": 5.144244766235351,
|
|
"epoch": 3.0262060750446693,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041052557258996553,
|
|
"loss": 4.551,
|
|
"mean_token_accuracy": 0.23806194812059403,
|
|
"num_tokens": 70998503.0,
|
|
"step": 25405
|
|
},
|
|
{
|
|
"entropy": 5.10755729675293,
|
|
"epoch": 3.026801667659321,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004104915549346658,
|
|
"loss": 4.505,
|
|
"mean_token_accuracy": 0.24269995093345642,
|
|
"num_tokens": 71011955.0,
|
|
"step": 25410
|
|
},
|
|
{
|
|
"entropy": 5.099449825286865,
|
|
"epoch": 3.0273972602739727,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004104575324195043,
|
|
"loss": 4.4156,
|
|
"mean_token_accuracy": 0.24575676023960114,
|
|
"num_tokens": 71025247.0,
|
|
"step": 25415
|
|
},
|
|
{
|
|
"entropy": 5.100922536849976,
|
|
"epoch": 3.027992852888624,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00041042350504570137,
|
|
"loss": 4.532,
|
|
"mean_token_accuracy": 0.24138726741075517,
|
|
"num_tokens": 71039398.0,
|
|
"step": 25420
|
|
},
|
|
{
|
|
"entropy": 5.049982738494873,
|
|
"epoch": 3.0285884455032757,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00041038947281447745,
|
|
"loss": 4.4839,
|
|
"mean_token_accuracy": 0.24758935272693633,
|
|
"num_tokens": 71054936.0,
|
|
"step": 25425
|
|
},
|
|
{
|
|
"entropy": 5.093175888061523,
|
|
"epoch": 3.0291840381179274,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004103554357270533,
|
|
"loss": 4.4753,
|
|
"mean_token_accuracy": 0.242467500269413,
|
|
"num_tokens": 71069829.0,
|
|
"step": 25430
|
|
},
|
|
{
|
|
"entropy": 5.0584534168243405,
|
|
"epoch": 3.029779630732579,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004103213937846497,
|
|
"loss": 4.4195,
|
|
"mean_token_accuracy": 0.25107551664114,
|
|
"num_tokens": 71084794.0,
|
|
"step": 25435
|
|
},
|
|
{
|
|
"entropy": 5.042823600769043,
|
|
"epoch": 3.0303752233472303,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004102873469884878,
|
|
"loss": 4.4311,
|
|
"mean_token_accuracy": 0.24262865632772446,
|
|
"num_tokens": 71097378.0,
|
|
"step": 25440
|
|
},
|
|
{
|
|
"entropy": 5.123275709152222,
|
|
"epoch": 3.030970815961882,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004102532953397887,
|
|
"loss": 4.5403,
|
|
"mean_token_accuracy": 0.23926394879817964,
|
|
"num_tokens": 71111491.0,
|
|
"step": 25445
|
|
},
|
|
{
|
|
"entropy": 5.073666429519653,
|
|
"epoch": 3.0315664085765337,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004102192388397737,
|
|
"loss": 4.4818,
|
|
"mean_token_accuracy": 0.2420491337776184,
|
|
"num_tokens": 71126869.0,
|
|
"step": 25450
|
|
},
|
|
{
|
|
"entropy": 5.111230659484863,
|
|
"epoch": 3.0321620011911854,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004101851774896646,
|
|
"loss": 4.5483,
|
|
"mean_token_accuracy": 0.23449926674365998,
|
|
"num_tokens": 71140122.0,
|
|
"step": 25455
|
|
},
|
|
{
|
|
"entropy": 5.06532039642334,
|
|
"epoch": 3.0327575938058366,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000410151111290683,
|
|
"loss": 4.4744,
|
|
"mean_token_accuracy": 0.2515972524881363,
|
|
"num_tokens": 71155244.0,
|
|
"step": 25460
|
|
},
|
|
{
|
|
"entropy": 5.055946302413941,
|
|
"epoch": 3.0333531864204883,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041011704024405065,
|
|
"loss": 4.4464,
|
|
"mean_token_accuracy": 0.24883803427219392,
|
|
"num_tokens": 71169614.0,
|
|
"step": 25465
|
|
},
|
|
{
|
|
"entropy": 5.0346005916595455,
|
|
"epoch": 3.03394877903514,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041008296435098983,
|
|
"loss": 4.4439,
|
|
"mean_token_accuracy": 0.25140823870897294,
|
|
"num_tokens": 71182532.0,
|
|
"step": 25470
|
|
},
|
|
{
|
|
"entropy": 5.077674055099488,
|
|
"epoch": 3.0345443716497917,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00041004888361272275,
|
|
"loss": 4.4474,
|
|
"mean_token_accuracy": 0.24727903306484222,
|
|
"num_tokens": 71195243.0,
|
|
"step": 25475
|
|
},
|
|
{
|
|
"entropy": 5.097877025604248,
|
|
"epoch": 3.035139964264443,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00041001479803047167,
|
|
"loss": 4.5472,
|
|
"mean_token_accuracy": 0.23469592928886412,
|
|
"num_tokens": 71210993.0,
|
|
"step": 25480
|
|
},
|
|
{
|
|
"entropy": 5.0632000923156735,
|
|
"epoch": 3.0357355568790947,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004099807076054594,
|
|
"loss": 4.4643,
|
|
"mean_token_accuracy": 0.24615895748138428,
|
|
"num_tokens": 71224222.0,
|
|
"step": 25485
|
|
},
|
|
{
|
|
"entropy": 5.101269102096557,
|
|
"epoch": 3.0363311494937464,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004099466123389086,
|
|
"loss": 4.6066,
|
|
"mean_token_accuracy": 0.24583932310342788,
|
|
"num_tokens": 71236750.0,
|
|
"step": 25490
|
|
},
|
|
{
|
|
"entropy": 5.103125476837159,
|
|
"epoch": 3.036926742108398,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040991251223204217,
|
|
"loss": 4.5697,
|
|
"mean_token_accuracy": 0.23340411633253097,
|
|
"num_tokens": 71251729.0,
|
|
"step": 25495
|
|
},
|
|
{
|
|
"entropy": 5.061790037155151,
|
|
"epoch": 3.0375223347230493,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040987840728608335,
|
|
"loss": 4.4834,
|
|
"mean_token_accuracy": 0.23894943296909332,
|
|
"num_tokens": 71265530.0,
|
|
"step": 25500
|
|
},
|
|
{
|
|
"entropy": 5.0575682640075685,
|
|
"epoch": 3.038117927337701,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040984429750225534,
|
|
"loss": 4.4951,
|
|
"mean_token_accuracy": 0.24760018140077591,
|
|
"num_tokens": 71278173.0,
|
|
"step": 25505
|
|
},
|
|
{
|
|
"entropy": 5.139754915237427,
|
|
"epoch": 3.0387135199523527,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040981018288178164,
|
|
"loss": 4.5657,
|
|
"mean_token_accuracy": 0.24102517515420913,
|
|
"num_tokens": 71291606.0,
|
|
"step": 25510
|
|
},
|
|
{
|
|
"entropy": 5.133041572570801,
|
|
"epoch": 3.039309112567004,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004097760634258858,
|
|
"loss": 4.5245,
|
|
"mean_token_accuracy": 0.23775904774665832,
|
|
"num_tokens": 71306713.0,
|
|
"step": 25515
|
|
},
|
|
{
|
|
"entropy": 5.078140926361084,
|
|
"epoch": 3.0399047051816557,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040974193913579174,
|
|
"loss": 4.4769,
|
|
"mean_token_accuracy": 0.24389201849699021,
|
|
"num_tokens": 71321791.0,
|
|
"step": 25520
|
|
},
|
|
{
|
|
"entropy": 5.066292238235474,
|
|
"epoch": 3.0405002977963074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004097078100127234,
|
|
"loss": 4.4252,
|
|
"mean_token_accuracy": 0.24985451996326447,
|
|
"num_tokens": 71335251.0,
|
|
"step": 25525
|
|
},
|
|
{
|
|
"entropy": 5.0521234512329105,
|
|
"epoch": 3.041095890410959,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040967367605790496,
|
|
"loss": 4.4466,
|
|
"mean_token_accuracy": 0.24425414204597473,
|
|
"num_tokens": 71350148.0,
|
|
"step": 25530
|
|
},
|
|
{
|
|
"entropy": 5.062023258209228,
|
|
"epoch": 3.0416914830256103,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040963953727256064,
|
|
"loss": 4.5085,
|
|
"mean_token_accuracy": 0.24362489432096482,
|
|
"num_tokens": 71364009.0,
|
|
"step": 25535
|
|
},
|
|
{
|
|
"entropy": 5.130236577987671,
|
|
"epoch": 3.042287075640262,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004096053936579151,
|
|
"loss": 4.5044,
|
|
"mean_token_accuracy": 0.23857638537883757,
|
|
"num_tokens": 71379752.0,
|
|
"step": 25540
|
|
},
|
|
{
|
|
"entropy": 5.067452621459961,
|
|
"epoch": 3.0428826682549137,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040957124521519294,
|
|
"loss": 4.5067,
|
|
"mean_token_accuracy": 0.24305106997489928,
|
|
"num_tokens": 71394815.0,
|
|
"step": 25545
|
|
},
|
|
{
|
|
"entropy": 5.117384529113769,
|
|
"epoch": 3.0434782608695654,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000409537091945619,
|
|
"loss": 4.5045,
|
|
"mean_token_accuracy": 0.23859951943159102,
|
|
"num_tokens": 71409214.0,
|
|
"step": 25550
|
|
},
|
|
{
|
|
"entropy": 5.115316390991211,
|
|
"epoch": 3.0440738534842167,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004095029338504184,
|
|
"loss": 4.5361,
|
|
"mean_token_accuracy": 0.23734699934720993,
|
|
"num_tokens": 71423640.0,
|
|
"step": 25555
|
|
},
|
|
{
|
|
"entropy": 5.068821763992309,
|
|
"epoch": 3.0446694460988684,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004094687709308161,
|
|
"loss": 4.4441,
|
|
"mean_token_accuracy": 0.25251784920692444,
|
|
"num_tokens": 71437600.0,
|
|
"step": 25560
|
|
},
|
|
{
|
|
"entropy": 5.121246099472046,
|
|
"epoch": 3.04526503871352,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040943460318803774,
|
|
"loss": 4.4824,
|
|
"mean_token_accuracy": 0.25345215797424314,
|
|
"num_tokens": 71451539.0,
|
|
"step": 25565
|
|
},
|
|
{
|
|
"entropy": 4.9916298389434814,
|
|
"epoch": 3.0458606313281713,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004094004306233087,
|
|
"loss": 4.3685,
|
|
"mean_token_accuracy": 0.24931777864694596,
|
|
"num_tokens": 71465688.0,
|
|
"step": 25570
|
|
},
|
|
{
|
|
"entropy": 5.05459623336792,
|
|
"epoch": 3.046456223942823,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004093662532378547,
|
|
"loss": 4.476,
|
|
"mean_token_accuracy": 0.24290498197078705,
|
|
"num_tokens": 71480431.0,
|
|
"step": 25575
|
|
},
|
|
{
|
|
"entropy": 5.089606428146363,
|
|
"epoch": 3.0470518165574747,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004093320710329017,
|
|
"loss": 4.4988,
|
|
"mean_token_accuracy": 0.23839650601148604,
|
|
"num_tokens": 71493040.0,
|
|
"step": 25580
|
|
},
|
|
{
|
|
"entropy": 5.089047145843506,
|
|
"epoch": 3.0476474091721264,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00040929788400967566,
|
|
"loss": 4.5037,
|
|
"mean_token_accuracy": 0.24418821781873704,
|
|
"num_tokens": 71506988.0,
|
|
"step": 25585
|
|
},
|
|
{
|
|
"entropy": 5.0827775478363035,
|
|
"epoch": 3.0482430017867777,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000409263692169403,
|
|
"loss": 4.4783,
|
|
"mean_token_accuracy": 0.23957302868366243,
|
|
"num_tokens": 71521812.0,
|
|
"step": 25590
|
|
},
|
|
{
|
|
"entropy": 5.075420999526978,
|
|
"epoch": 3.0488385944014293,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040922949551330985,
|
|
"loss": 4.452,
|
|
"mean_token_accuracy": 0.2418997198343277,
|
|
"num_tokens": 71535450.0,
|
|
"step": 25595
|
|
},
|
|
{
|
|
"entropy": 5.083686685562133,
|
|
"epoch": 3.049434187016081,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004091952940426231,
|
|
"loss": 4.5091,
|
|
"mean_token_accuracy": 0.23820895254611968,
|
|
"num_tokens": 71549298.0,
|
|
"step": 25600
|
|
},
|
|
{
|
|
"entropy": 5.04533634185791,
|
|
"epoch": 3.0500297796307327,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040916108775856925,
|
|
"loss": 4.4397,
|
|
"mean_token_accuracy": 0.2470813512802124,
|
|
"num_tokens": 71563099.0,
|
|
"step": 25605
|
|
},
|
|
{
|
|
"entropy": 5.079395055770874,
|
|
"epoch": 3.050625372245384,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004091268766623753,
|
|
"loss": 4.4706,
|
|
"mean_token_accuracy": 0.24436980336904526,
|
|
"num_tokens": 71576870.0,
|
|
"step": 25610
|
|
},
|
|
{
|
|
"entropy": 5.133411979675293,
|
|
"epoch": 3.0512209648600357,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004090926607552684,
|
|
"loss": 4.5225,
|
|
"mean_token_accuracy": 0.23801273256540298,
|
|
"num_tokens": 71590239.0,
|
|
"step": 25615
|
|
},
|
|
{
|
|
"entropy": 5.105058908462524,
|
|
"epoch": 3.0518165574746874,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004090584400384758,
|
|
"loss": 4.4495,
|
|
"mean_token_accuracy": 0.24203855097293853,
|
|
"num_tokens": 71602846.0,
|
|
"step": 25620
|
|
},
|
|
{
|
|
"entropy": 5.0324492931365965,
|
|
"epoch": 3.052412150089339,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040902421451322486,
|
|
"loss": 4.3919,
|
|
"mean_token_accuracy": 0.2540401592850685,
|
|
"num_tokens": 71615462.0,
|
|
"step": 25625
|
|
},
|
|
{
|
|
"entropy": 5.10157880783081,
|
|
"epoch": 3.0530077427039903,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004089899841807433,
|
|
"loss": 4.431,
|
|
"mean_token_accuracy": 0.24819420278072357,
|
|
"num_tokens": 71629119.0,
|
|
"step": 25630
|
|
},
|
|
{
|
|
"entropy": 5.080780935287476,
|
|
"epoch": 3.053603335318642,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004089557490422588,
|
|
"loss": 4.5744,
|
|
"mean_token_accuracy": 0.23495301604270935,
|
|
"num_tokens": 71642014.0,
|
|
"step": 25635
|
|
},
|
|
{
|
|
"entropy": 5.131546401977539,
|
|
"epoch": 3.0541989279332937,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004089215090989994,
|
|
"loss": 4.5322,
|
|
"mean_token_accuracy": 0.23743051886558533,
|
|
"num_tokens": 71654981.0,
|
|
"step": 25640
|
|
},
|
|
{
|
|
"entropy": 5.118680381774903,
|
|
"epoch": 3.0547945205479454,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004088872643521933,
|
|
"loss": 4.4597,
|
|
"mean_token_accuracy": 0.23886379301548005,
|
|
"num_tokens": 71668788.0,
|
|
"step": 25645
|
|
},
|
|
{
|
|
"entropy": 5.098317241668701,
|
|
"epoch": 3.0553901131625967,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004088530148030687,
|
|
"loss": 4.5066,
|
|
"mean_token_accuracy": 0.23990036845207213,
|
|
"num_tokens": 71683210.0,
|
|
"step": 25650
|
|
},
|
|
{
|
|
"entropy": 4.9697507381439205,
|
|
"epoch": 3.0559857057772484,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000408818760452854,
|
|
"loss": 4.4197,
|
|
"mean_token_accuracy": 0.25555475801229477,
|
|
"num_tokens": 71696654.0,
|
|
"step": 25655
|
|
},
|
|
{
|
|
"entropy": 5.073353624343872,
|
|
"epoch": 3.0565812983919,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040878450130277797,
|
|
"loss": 4.4491,
|
|
"mean_token_accuracy": 0.2459988698363304,
|
|
"num_tokens": 71710055.0,
|
|
"step": 25660
|
|
},
|
|
{
|
|
"entropy": 5.1193013191223145,
|
|
"epoch": 3.0571768910065513,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004087502373540694,
|
|
"loss": 4.5627,
|
|
"mean_token_accuracy": 0.2360934153199196,
|
|
"num_tokens": 71725180.0,
|
|
"step": 25665
|
|
},
|
|
{
|
|
"entropy": 5.14248628616333,
|
|
"epoch": 3.057772483621203,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040871596860795733,
|
|
"loss": 4.5139,
|
|
"mean_token_accuracy": 0.2409682273864746,
|
|
"num_tokens": 71737026.0,
|
|
"step": 25670
|
|
},
|
|
{
|
|
"entropy": 5.079840517044067,
|
|
"epoch": 3.0583680762358547,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004086816950656708,
|
|
"loss": 4.4574,
|
|
"mean_token_accuracy": 0.24948541820049286,
|
|
"num_tokens": 71751007.0,
|
|
"step": 25675
|
|
},
|
|
{
|
|
"entropy": 4.996305274963379,
|
|
"epoch": 3.0589636688505064,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004086474167284393,
|
|
"loss": 4.4406,
|
|
"mean_token_accuracy": 0.24362394213676453,
|
|
"num_tokens": 71764702.0,
|
|
"step": 25680
|
|
},
|
|
{
|
|
"entropy": 5.0835919857025145,
|
|
"epoch": 3.0595592614651577,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040861313359749217,
|
|
"loss": 4.5331,
|
|
"mean_token_accuracy": 0.23911748975515365,
|
|
"num_tokens": 71778589.0,
|
|
"step": 25685
|
|
},
|
|
{
|
|
"entropy": 5.146605491638184,
|
|
"epoch": 3.0601548540798094,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004085788456740593,
|
|
"loss": 4.4698,
|
|
"mean_token_accuracy": 0.24989103227853776,
|
|
"num_tokens": 71792471.0,
|
|
"step": 25690
|
|
},
|
|
{
|
|
"entropy": 5.019780492782592,
|
|
"epoch": 3.060750446694461,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004085445529593703,
|
|
"loss": 4.4426,
|
|
"mean_token_accuracy": 0.24824171364307404,
|
|
"num_tokens": 71805326.0,
|
|
"step": 25695
|
|
},
|
|
{
|
|
"entropy": 4.991769599914551,
|
|
"epoch": 3.0613460393091128,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040851025545465537,
|
|
"loss": 4.5298,
|
|
"mean_token_accuracy": 0.2415030851960182,
|
|
"num_tokens": 71818615.0,
|
|
"step": 25700
|
|
},
|
|
{
|
|
"entropy": 5.1349340915679935,
|
|
"epoch": 3.061941631923764,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004084759531611447,
|
|
"loss": 4.5054,
|
|
"mean_token_accuracy": 0.23859769403934478,
|
|
"num_tokens": 71834271.0,
|
|
"step": 25705
|
|
},
|
|
{
|
|
"entropy": 5.128323078155518,
|
|
"epoch": 3.0625372245384157,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040844164608006857,
|
|
"loss": 4.5171,
|
|
"mean_token_accuracy": 0.2418232426047325,
|
|
"num_tokens": 71850118.0,
|
|
"step": 25710
|
|
},
|
|
{
|
|
"entropy": 5.07162036895752,
|
|
"epoch": 3.0631328171530674,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004084073342126575,
|
|
"loss": 4.5107,
|
|
"mean_token_accuracy": 0.23889428824186326,
|
|
"num_tokens": 71863501.0,
|
|
"step": 25715
|
|
},
|
|
{
|
|
"entropy": 5.0944067478179935,
|
|
"epoch": 3.0637284097677187,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040837301756014227,
|
|
"loss": 4.4834,
|
|
"mean_token_accuracy": 0.24730803370475768,
|
|
"num_tokens": 71876084.0,
|
|
"step": 25720
|
|
},
|
|
{
|
|
"entropy": 5.119391393661499,
|
|
"epoch": 3.0643240023823703,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004083386961237538,
|
|
"loss": 4.502,
|
|
"mean_token_accuracy": 0.24474132508039476,
|
|
"num_tokens": 71890371.0,
|
|
"step": 25725
|
|
},
|
|
{
|
|
"entropy": 5.043339967727661,
|
|
"epoch": 3.064919594997022,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004083043699047231,
|
|
"loss": 4.4546,
|
|
"mean_token_accuracy": 0.24593719989061355,
|
|
"num_tokens": 71904510.0,
|
|
"step": 25730
|
|
},
|
|
{
|
|
"entropy": 5.105076456069947,
|
|
"epoch": 3.0655151876116737,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004082700389042814,
|
|
"loss": 4.4845,
|
|
"mean_token_accuracy": 0.25163762718439103,
|
|
"num_tokens": 71917896.0,
|
|
"step": 25735
|
|
},
|
|
{
|
|
"entropy": 5.145244073867798,
|
|
"epoch": 3.066110780226325,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040823570312366005,
|
|
"loss": 4.556,
|
|
"mean_token_accuracy": 0.23893628567457198,
|
|
"num_tokens": 71932085.0,
|
|
"step": 25740
|
|
},
|
|
{
|
|
"entropy": 5.071639156341552,
|
|
"epoch": 3.0667063728409767,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040820136256409064,
|
|
"loss": 4.4884,
|
|
"mean_token_accuracy": 0.23726659268140793,
|
|
"num_tokens": 71945408.0,
|
|
"step": 25745
|
|
},
|
|
{
|
|
"entropy": 5.068197917938233,
|
|
"epoch": 3.0673019654556284,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004081670172268049,
|
|
"loss": 4.5233,
|
|
"mean_token_accuracy": 0.2389603391289711,
|
|
"num_tokens": 71960027.0,
|
|
"step": 25750
|
|
},
|
|
{
|
|
"entropy": 5.115889024734497,
|
|
"epoch": 3.06789755807028,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040813266711303486,
|
|
"loss": 4.5449,
|
|
"mean_token_accuracy": 0.23635246306657792,
|
|
"num_tokens": 71975105.0,
|
|
"step": 25755
|
|
},
|
|
{
|
|
"entropy": 5.102536058425903,
|
|
"epoch": 3.0684931506849313,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004080983122240125,
|
|
"loss": 4.5324,
|
|
"mean_token_accuracy": 0.23715818524360657,
|
|
"num_tokens": 71990267.0,
|
|
"step": 25760
|
|
},
|
|
{
|
|
"entropy": 5.0997124195098875,
|
|
"epoch": 3.069088743299583,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040806395256097,
|
|
"loss": 4.4945,
|
|
"mean_token_accuracy": 0.24479685127735137,
|
|
"num_tokens": 72005439.0,
|
|
"step": 25765
|
|
},
|
|
{
|
|
"entropy": 5.013428974151611,
|
|
"epoch": 3.0696843359142347,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040802958812513997,
|
|
"loss": 4.4137,
|
|
"mean_token_accuracy": 0.2488723948597908,
|
|
"num_tokens": 72019738.0,
|
|
"step": 25770
|
|
},
|
|
{
|
|
"entropy": 5.049116706848144,
|
|
"epoch": 3.0702799285288864,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004079952189177549,
|
|
"loss": 4.4641,
|
|
"mean_token_accuracy": 0.24571973085403442,
|
|
"num_tokens": 72033148.0,
|
|
"step": 25775
|
|
},
|
|
{
|
|
"entropy": 5.061774444580078,
|
|
"epoch": 3.0708755211435377,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040796084494004747,
|
|
"loss": 4.4436,
|
|
"mean_token_accuracy": 0.24491746425628663,
|
|
"num_tokens": 72045940.0,
|
|
"step": 25780
|
|
},
|
|
{
|
|
"entropy": 5.095720100402832,
|
|
"epoch": 3.0714711137581894,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040792646619325086,
|
|
"loss": 4.5102,
|
|
"mean_token_accuracy": 0.23821404129266738,
|
|
"num_tokens": 72059682.0,
|
|
"step": 25785
|
|
},
|
|
{
|
|
"entropy": 5.063157463073731,
|
|
"epoch": 3.072066706372841,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004078920826785979,
|
|
"loss": 4.4376,
|
|
"mean_token_accuracy": 0.2392820119857788,
|
|
"num_tokens": 72076664.0,
|
|
"step": 25790
|
|
},
|
|
{
|
|
"entropy": 5.077863168716431,
|
|
"epoch": 3.0726622989874928,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000407857694397322,
|
|
"loss": 4.4911,
|
|
"mean_token_accuracy": 0.24493597894907,
|
|
"num_tokens": 72090231.0,
|
|
"step": 25795
|
|
},
|
|
{
|
|
"entropy": 5.061792087554932,
|
|
"epoch": 3.073257891602144,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004078233013506567,
|
|
"loss": 4.4857,
|
|
"mean_token_accuracy": 0.24284300506114959,
|
|
"num_tokens": 72105510.0,
|
|
"step": 25800
|
|
},
|
|
{
|
|
"entropy": 5.1181567192077635,
|
|
"epoch": 3.0738534842167957,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040778890353983547,
|
|
"loss": 4.528,
|
|
"mean_token_accuracy": 0.24069002121686936,
|
|
"num_tokens": 72119679.0,
|
|
"step": 25805
|
|
},
|
|
{
|
|
"entropy": 5.120247030258179,
|
|
"epoch": 3.0744490768314474,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040775450096609226,
|
|
"loss": 4.532,
|
|
"mean_token_accuracy": 0.23712978959083558,
|
|
"num_tokens": 72133613.0,
|
|
"step": 25810
|
|
},
|
|
{
|
|
"entropy": 5.042589569091797,
|
|
"epoch": 3.0750446694460987,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004077200936306609,
|
|
"loss": 4.474,
|
|
"mean_token_accuracy": 0.24071348756551741,
|
|
"num_tokens": 72147993.0,
|
|
"step": 25815
|
|
},
|
|
{
|
|
"entropy": 5.186399650573731,
|
|
"epoch": 3.0756402620607504,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004076856815347756,
|
|
"loss": 4.6577,
|
|
"mean_token_accuracy": 0.23343245238065718,
|
|
"num_tokens": 72162990.0,
|
|
"step": 25820
|
|
},
|
|
{
|
|
"entropy": 5.0912059307098385,
|
|
"epoch": 3.076235854675402,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004076512646796705,
|
|
"loss": 4.5084,
|
|
"mean_token_accuracy": 0.24045445173978805,
|
|
"num_tokens": 72179284.0,
|
|
"step": 25825
|
|
},
|
|
{
|
|
"entropy": 5.078854179382324,
|
|
"epoch": 3.0768314472900538,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004076168430665804,
|
|
"loss": 4.4839,
|
|
"mean_token_accuracy": 0.24224714040756226,
|
|
"num_tokens": 72191964.0,
|
|
"step": 25830
|
|
},
|
|
{
|
|
"entropy": 4.998257350921631,
|
|
"epoch": 3.077427039904705,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004075824166967396,
|
|
"loss": 4.4322,
|
|
"mean_token_accuracy": 0.24762616753578187,
|
|
"num_tokens": 72207480.0,
|
|
"step": 25835
|
|
},
|
|
{
|
|
"entropy": 5.006147670745849,
|
|
"epoch": 3.0780226325193567,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040754798557138315,
|
|
"loss": 4.4582,
|
|
"mean_token_accuracy": 0.24853430390357972,
|
|
"num_tokens": 72222598.0,
|
|
"step": 25840
|
|
},
|
|
{
|
|
"entropy": 5.075466918945312,
|
|
"epoch": 3.0786182251340084,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000407513549691746,
|
|
"loss": 4.4447,
|
|
"mean_token_accuracy": 0.24105487614870072,
|
|
"num_tokens": 72238409.0,
|
|
"step": 25845
|
|
},
|
|
{
|
|
"entropy": 5.1617332935333256,
|
|
"epoch": 3.07921381774866,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004074791090590632,
|
|
"loss": 4.492,
|
|
"mean_token_accuracy": 0.24047064930200576,
|
|
"num_tokens": 72251153.0,
|
|
"step": 25850
|
|
},
|
|
{
|
|
"entropy": 5.0671569347381595,
|
|
"epoch": 3.0798094103633114,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004074446636745703,
|
|
"loss": 4.494,
|
|
"mean_token_accuracy": 0.2465898260474205,
|
|
"num_tokens": 72263697.0,
|
|
"step": 25855
|
|
},
|
|
{
|
|
"entropy": 5.092056083679199,
|
|
"epoch": 3.080405002977963,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040741021353950246,
|
|
"loss": 4.5031,
|
|
"mean_token_accuracy": 0.24255772978067397,
|
|
"num_tokens": 72277455.0,
|
|
"step": 25860
|
|
},
|
|
{
|
|
"entropy": 5.143745231628418,
|
|
"epoch": 3.0810005955926147,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004073757586550957,
|
|
"loss": 4.5408,
|
|
"mean_token_accuracy": 0.23710167557001113,
|
|
"num_tokens": 72292376.0,
|
|
"step": 25865
|
|
},
|
|
{
|
|
"entropy": 5.141100597381592,
|
|
"epoch": 3.0815961882072664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004073412990225856,
|
|
"loss": 4.5773,
|
|
"mean_token_accuracy": 0.23613757342100145,
|
|
"num_tokens": 72307592.0,
|
|
"step": 25870
|
|
},
|
|
{
|
|
"entropy": 5.171010065078735,
|
|
"epoch": 3.0821917808219177,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040730683464320835,
|
|
"loss": 4.6187,
|
|
"mean_token_accuracy": 0.2364494249224663,
|
|
"num_tokens": 72322207.0,
|
|
"step": 25875
|
|
},
|
|
{
|
|
"entropy": 5.15423436164856,
|
|
"epoch": 3.0827873734365694,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004072723655182001,
|
|
"loss": 4.4733,
|
|
"mean_token_accuracy": 0.24434876143932344,
|
|
"num_tokens": 72337368.0,
|
|
"step": 25880
|
|
},
|
|
{
|
|
"entropy": 5.060317087173462,
|
|
"epoch": 3.083382966051221,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040723789164879697,
|
|
"loss": 4.505,
|
|
"mean_token_accuracy": 0.2377910226583481,
|
|
"num_tokens": 72353505.0,
|
|
"step": 25885
|
|
},
|
|
{
|
|
"entropy": 5.0773993015289305,
|
|
"epoch": 3.0839785586658723,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040720341303623593,
|
|
"loss": 4.5243,
|
|
"mean_token_accuracy": 0.23290600329637529,
|
|
"num_tokens": 72368406.0,
|
|
"step": 25890
|
|
},
|
|
{
|
|
"entropy": 5.176541471481324,
|
|
"epoch": 3.084574151280524,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040716892968175325,
|
|
"loss": 4.6202,
|
|
"mean_token_accuracy": 0.23139411211013794,
|
|
"num_tokens": 72384033.0,
|
|
"step": 25895
|
|
},
|
|
{
|
|
"entropy": 5.036301898956299,
|
|
"epoch": 3.0851697438951757,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004071344415865859,
|
|
"loss": 4.381,
|
|
"mean_token_accuracy": 0.26130250543355943,
|
|
"num_tokens": 72396431.0,
|
|
"step": 25900
|
|
},
|
|
{
|
|
"entropy": 5.083875608444214,
|
|
"epoch": 3.0857653365098274,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004070999487519711,
|
|
"loss": 4.5278,
|
|
"mean_token_accuracy": 0.24220990538597106,
|
|
"num_tokens": 72411153.0,
|
|
"step": 25905
|
|
},
|
|
{
|
|
"entropy": 5.051872062683105,
|
|
"epoch": 3.0863609291244787,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004070654511791459,
|
|
"loss": 4.4558,
|
|
"mean_token_accuracy": 0.24910281896591185,
|
|
"num_tokens": 72423837.0,
|
|
"step": 25910
|
|
},
|
|
{
|
|
"entropy": 5.152746343612671,
|
|
"epoch": 3.0869565217391304,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040703094886934763,
|
|
"loss": 4.4865,
|
|
"mean_token_accuracy": 0.23529632687568663,
|
|
"num_tokens": 72438611.0,
|
|
"step": 25915
|
|
},
|
|
{
|
|
"entropy": 5.101933336257934,
|
|
"epoch": 3.087552114353782,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040699644182381394,
|
|
"loss": 4.4985,
|
|
"mean_token_accuracy": 0.2438198521733284,
|
|
"num_tokens": 72452136.0,
|
|
"step": 25920
|
|
},
|
|
{
|
|
"entropy": 5.1267389297485355,
|
|
"epoch": 3.0881477069684338,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004069619300437825,
|
|
"loss": 4.5925,
|
|
"mean_token_accuracy": 0.23581320345401763,
|
|
"num_tokens": 72467143.0,
|
|
"step": 25925
|
|
},
|
|
{
|
|
"entropy": 5.083582782745362,
|
|
"epoch": 3.088743299583085,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004069274135304912,
|
|
"loss": 4.4643,
|
|
"mean_token_accuracy": 0.24581337720155716,
|
|
"num_tokens": 72481894.0,
|
|
"step": 25930
|
|
},
|
|
{
|
|
"entropy": 5.065255975723266,
|
|
"epoch": 3.0893388921977367,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000406892892285178,
|
|
"loss": 4.4996,
|
|
"mean_token_accuracy": 0.2361950844526291,
|
|
"num_tokens": 72494732.0,
|
|
"step": 25935
|
|
},
|
|
{
|
|
"entropy": 5.033489990234375,
|
|
"epoch": 3.0899344848123884,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004068583663090813,
|
|
"loss": 4.5129,
|
|
"mean_token_accuracy": 0.23445872366428375,
|
|
"num_tokens": 72509339.0,
|
|
"step": 25940
|
|
},
|
|
{
|
|
"entropy": 5.139102935791016,
|
|
"epoch": 3.09053007742704,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004068238356034393,
|
|
"loss": 4.5469,
|
|
"mean_token_accuracy": 0.23503446727991104,
|
|
"num_tokens": 72524170.0,
|
|
"step": 25945
|
|
},
|
|
{
|
|
"entropy": 5.073051929473877,
|
|
"epoch": 3.0911256700416914,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040678930016949073,
|
|
"loss": 4.4081,
|
|
"mean_token_accuracy": 0.24442546367645263,
|
|
"num_tokens": 72538026.0,
|
|
"step": 25950
|
|
},
|
|
{
|
|
"entropy": 5.151241493225098,
|
|
"epoch": 3.091721262656343,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040675476000847423,
|
|
"loss": 4.5767,
|
|
"mean_token_accuracy": 0.23721367567777635,
|
|
"num_tokens": 72553264.0,
|
|
"step": 25955
|
|
},
|
|
{
|
|
"entropy": 5.12592134475708,
|
|
"epoch": 3.0923168552709948,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040672021512162864,
|
|
"loss": 4.5767,
|
|
"mean_token_accuracy": 0.236482635140419,
|
|
"num_tokens": 72566245.0,
|
|
"step": 25960
|
|
},
|
|
{
|
|
"entropy": 5.057488679885864,
|
|
"epoch": 3.092912447885646,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004066856655101931,
|
|
"loss": 4.4525,
|
|
"mean_token_accuracy": 0.24805279672145844,
|
|
"num_tokens": 72579865.0,
|
|
"step": 25965
|
|
},
|
|
{
|
|
"entropy": 5.080236530303955,
|
|
"epoch": 3.0935080405002977,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004066511111754069,
|
|
"loss": 4.4914,
|
|
"mean_token_accuracy": 0.23600220531225205,
|
|
"num_tokens": 72593376.0,
|
|
"step": 25970
|
|
},
|
|
{
|
|
"entropy": 5.029973840713501,
|
|
"epoch": 3.0941036331149494,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004066165521185094,
|
|
"loss": 4.4447,
|
|
"mean_token_accuracy": 0.24904996752738953,
|
|
"num_tokens": 72605938.0,
|
|
"step": 25975
|
|
},
|
|
{
|
|
"entropy": 5.101863098144531,
|
|
"epoch": 3.094699225729601,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004065819883407402,
|
|
"loss": 4.4928,
|
|
"mean_token_accuracy": 0.24137211292982103,
|
|
"num_tokens": 72618519.0,
|
|
"step": 25980
|
|
},
|
|
{
|
|
"entropy": 5.137702322006225,
|
|
"epoch": 3.0952948183442524,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040654741984333886,
|
|
"loss": 4.4883,
|
|
"mean_token_accuracy": 0.2339778184890747,
|
|
"num_tokens": 72630696.0,
|
|
"step": 25985
|
|
},
|
|
{
|
|
"entropy": 5.092793655395508,
|
|
"epoch": 3.095890410958904,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004065128466275456,
|
|
"loss": 4.5148,
|
|
"mean_token_accuracy": 0.23406256437301637,
|
|
"num_tokens": 72645130.0,
|
|
"step": 25990
|
|
},
|
|
{
|
|
"entropy": 5.075616550445557,
|
|
"epoch": 3.0964860035735557,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004064782686946003,
|
|
"loss": 4.4314,
|
|
"mean_token_accuracy": 0.24667421281337737,
|
|
"num_tokens": 72660422.0,
|
|
"step": 25995
|
|
},
|
|
{
|
|
"entropy": 5.12741117477417,
|
|
"epoch": 3.0970815961882074,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004064436860457433,
|
|
"loss": 4.5723,
|
|
"mean_token_accuracy": 0.23188523203134537,
|
|
"num_tokens": 72675688.0,
|
|
"step": 26000
|
|
},
|
|
{
|
|
"entropy": 5.077751350402832,
|
|
"epoch": 3.0976771888028587,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000406409098682215,
|
|
"loss": 4.4182,
|
|
"mean_token_accuracy": 0.24797862619161606,
|
|
"num_tokens": 72689219.0,
|
|
"step": 26005
|
|
},
|
|
{
|
|
"entropy": 5.102068090438843,
|
|
"epoch": 3.0982727814175104,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040637450660525594,
|
|
"loss": 4.4974,
|
|
"mean_token_accuracy": 0.24750819951295852,
|
|
"num_tokens": 72703395.0,
|
|
"step": 26010
|
|
},
|
|
{
|
|
"entropy": 5.074117136001587,
|
|
"epoch": 3.098868374032162,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000406339909816107,
|
|
"loss": 4.5454,
|
|
"mean_token_accuracy": 0.2406905323266983,
|
|
"num_tokens": 72718732.0,
|
|
"step": 26015
|
|
},
|
|
{
|
|
"entropy": 5.105768346786499,
|
|
"epoch": 3.099463966646814,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040630530831600904,
|
|
"loss": 4.4471,
|
|
"mean_token_accuracy": 0.24888161569833755,
|
|
"num_tokens": 72732035.0,
|
|
"step": 26020
|
|
},
|
|
{
|
|
"entropy": 5.075644016265869,
|
|
"epoch": 3.100059559261465,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040627070210620306,
|
|
"loss": 4.4816,
|
|
"mean_token_accuracy": 0.24154882431030272,
|
|
"num_tokens": 72745537.0,
|
|
"step": 26025
|
|
},
|
|
{
|
|
"entropy": 5.050447654724121,
|
|
"epoch": 3.1006551518761167,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004062360911879305,
|
|
"loss": 4.4482,
|
|
"mean_token_accuracy": 0.24840064346790314,
|
|
"num_tokens": 72759096.0,
|
|
"step": 26030
|
|
},
|
|
{
|
|
"entropy": 5.091935396194458,
|
|
"epoch": 3.1012507444907684,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004062014755624327,
|
|
"loss": 4.456,
|
|
"mean_token_accuracy": 0.2466948315501213,
|
|
"num_tokens": 72771932.0,
|
|
"step": 26035
|
|
},
|
|
{
|
|
"entropy": 5.081960010528564,
|
|
"epoch": 3.1018463371054197,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040616685523095134,
|
|
"loss": 4.5082,
|
|
"mean_token_accuracy": 0.23901523798704147,
|
|
"num_tokens": 72786203.0,
|
|
"step": 26040
|
|
},
|
|
{
|
|
"entropy": 5.019140768051147,
|
|
"epoch": 3.1024419297200714,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004061322301947281,
|
|
"loss": 4.4078,
|
|
"mean_token_accuracy": 0.24631969928741454,
|
|
"num_tokens": 72799570.0,
|
|
"step": 26045
|
|
},
|
|
{
|
|
"entropy": 5.022371578216553,
|
|
"epoch": 3.103037522334723,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040609760045500496,
|
|
"loss": 4.4181,
|
|
"mean_token_accuracy": 0.25005168169736863,
|
|
"num_tokens": 72813604.0,
|
|
"step": 26050
|
|
},
|
|
{
|
|
"entropy": 5.082355785369873,
|
|
"epoch": 3.1036331149493748,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004060629660130241,
|
|
"loss": 4.4867,
|
|
"mean_token_accuracy": 0.24150870591402054,
|
|
"num_tokens": 72825149.0,
|
|
"step": 26055
|
|
},
|
|
{
|
|
"entropy": 5.041746187210083,
|
|
"epoch": 3.104228707564026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00040602832687002774,
|
|
"loss": 4.4623,
|
|
"mean_token_accuracy": 0.24297174513339997,
|
|
"num_tokens": 72838581.0,
|
|
"step": 26060
|
|
},
|
|
{
|
|
"entropy": 5.113269805908203,
|
|
"epoch": 3.1048243001786777,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004059936830272583,
|
|
"loss": 4.4928,
|
|
"mean_token_accuracy": 0.2433074250817299,
|
|
"num_tokens": 72852425.0,
|
|
"step": 26065
|
|
},
|
|
{
|
|
"entropy": 5.117368507385254,
|
|
"epoch": 3.1054198927933294,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004059590344859584,
|
|
"loss": 4.511,
|
|
"mean_token_accuracy": 0.24291674494743348,
|
|
"num_tokens": 72868551.0,
|
|
"step": 26070
|
|
},
|
|
{
|
|
"entropy": 5.14689040184021,
|
|
"epoch": 3.106015485407981,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040592438124737086,
|
|
"loss": 4.5199,
|
|
"mean_token_accuracy": 0.2461355671286583,
|
|
"num_tokens": 72882043.0,
|
|
"step": 26075
|
|
},
|
|
{
|
|
"entropy": 5.125029850006103,
|
|
"epoch": 3.1066110780226324,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004058897233127387,
|
|
"loss": 4.5093,
|
|
"mean_token_accuracy": 0.23707508742809297,
|
|
"num_tokens": 72895935.0,
|
|
"step": 26080
|
|
},
|
|
{
|
|
"entropy": 5.020610332489014,
|
|
"epoch": 3.107206670637284,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040585506068330495,
|
|
"loss": 4.4631,
|
|
"mean_token_accuracy": 0.24906434267759323,
|
|
"num_tokens": 72908833.0,
|
|
"step": 26085
|
|
},
|
|
{
|
|
"entropy": 5.061150550842285,
|
|
"epoch": 3.1078022632519358,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040582039336031295,
|
|
"loss": 4.5266,
|
|
"mean_token_accuracy": 0.24354325532913207,
|
|
"num_tokens": 72923339.0,
|
|
"step": 26090
|
|
},
|
|
{
|
|
"entropy": 5.099464702606201,
|
|
"epoch": 3.1083978558665875,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004057857213450061,
|
|
"loss": 4.5024,
|
|
"mean_token_accuracy": 0.24071168750524521,
|
|
"num_tokens": 72936608.0,
|
|
"step": 26095
|
|
},
|
|
{
|
|
"entropy": 5.1332649230957035,
|
|
"epoch": 3.1089934484812387,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004057510446386282,
|
|
"loss": 4.4892,
|
|
"mean_token_accuracy": 0.2381812885403633,
|
|
"num_tokens": 72952254.0,
|
|
"step": 26100
|
|
},
|
|
{
|
|
"entropy": 5.131029319763184,
|
|
"epoch": 3.1095890410958904,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004057163632424227,
|
|
"loss": 4.5649,
|
|
"mean_token_accuracy": 0.23777791112661362,
|
|
"num_tokens": 72966968.0,
|
|
"step": 26105
|
|
},
|
|
{
|
|
"entropy": 5.041188049316406,
|
|
"epoch": 3.110184633710542,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004056816771576339,
|
|
"loss": 4.4317,
|
|
"mean_token_accuracy": 0.24921647310256959,
|
|
"num_tokens": 72981691.0,
|
|
"step": 26110
|
|
},
|
|
{
|
|
"entropy": 5.055379486083984,
|
|
"epoch": 3.1107802263251934,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040564698638550584,
|
|
"loss": 4.4364,
|
|
"mean_token_accuracy": 0.24776877611875534,
|
|
"num_tokens": 72994259.0,
|
|
"step": 26115
|
|
},
|
|
{
|
|
"entropy": 5.094375944137573,
|
|
"epoch": 3.111375818939845,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040561229092728277,
|
|
"loss": 4.5136,
|
|
"mean_token_accuracy": 0.2369936600327492,
|
|
"num_tokens": 73006542.0,
|
|
"step": 26120
|
|
},
|
|
{
|
|
"entropy": 5.066015148162842,
|
|
"epoch": 3.1119714115544967,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004055775907842092,
|
|
"loss": 4.4069,
|
|
"mean_token_accuracy": 0.25073810666799545,
|
|
"num_tokens": 73020969.0,
|
|
"step": 26125
|
|
},
|
|
{
|
|
"entropy": 5.106659746170044,
|
|
"epoch": 3.1125670041691484,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004055428859575297,
|
|
"loss": 4.5546,
|
|
"mean_token_accuracy": 0.23627356737852095,
|
|
"num_tokens": 73034207.0,
|
|
"step": 26130
|
|
},
|
|
{
|
|
"entropy": 5.045945072174073,
|
|
"epoch": 3.1131625967837997,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004055081764484892,
|
|
"loss": 4.4944,
|
|
"mean_token_accuracy": 0.24139091968536378,
|
|
"num_tokens": 73048923.0,
|
|
"step": 26135
|
|
},
|
|
{
|
|
"entropy": 5.057210063934326,
|
|
"epoch": 3.1137581893984514,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004054734622583325,
|
|
"loss": 4.4378,
|
|
"mean_token_accuracy": 0.25314039289951323,
|
|
"num_tokens": 73061837.0,
|
|
"step": 26140
|
|
},
|
|
{
|
|
"entropy": 5.029109048843384,
|
|
"epoch": 3.114353782013103,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000405438743388305,
|
|
"loss": 4.4378,
|
|
"mean_token_accuracy": 0.246403369307518,
|
|
"num_tokens": 73073743.0,
|
|
"step": 26145
|
|
},
|
|
{
|
|
"entropy": 5.0646203517913815,
|
|
"epoch": 3.114949374627755,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040540401983965173,
|
|
"loss": 4.4264,
|
|
"mean_token_accuracy": 0.25058003813028334,
|
|
"num_tokens": 73086717.0,
|
|
"step": 26150
|
|
},
|
|
{
|
|
"entropy": 5.039657926559448,
|
|
"epoch": 3.115544967242406,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040536929161361833,
|
|
"loss": 4.3896,
|
|
"mean_token_accuracy": 0.25212371796369554,
|
|
"num_tokens": 73100408.0,
|
|
"step": 26155
|
|
},
|
|
{
|
|
"entropy": 5.0713776588439945,
|
|
"epoch": 3.1161405598570577,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040533455871145046,
|
|
"loss": 4.5206,
|
|
"mean_token_accuracy": 0.23286020904779434,
|
|
"num_tokens": 73115429.0,
|
|
"step": 26160
|
|
},
|
|
{
|
|
"entropy": 5.098609542846679,
|
|
"epoch": 3.1167361524717094,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040529982113439385,
|
|
"loss": 4.5085,
|
|
"mean_token_accuracy": 0.24295735955238343,
|
|
"num_tokens": 73129952.0,
|
|
"step": 26165
|
|
},
|
|
{
|
|
"entropy": 5.144722175598145,
|
|
"epoch": 3.117331745086361,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040526507888369453,
|
|
"loss": 4.6032,
|
|
"mean_token_accuracy": 0.23667218089103698,
|
|
"num_tokens": 73143578.0,
|
|
"step": 26170
|
|
},
|
|
{
|
|
"entropy": 5.102858257293701,
|
|
"epoch": 3.1179273377010124,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040523033196059857,
|
|
"loss": 4.5271,
|
|
"mean_token_accuracy": 0.23776136934757233,
|
|
"num_tokens": 73156662.0,
|
|
"step": 26175
|
|
},
|
|
{
|
|
"entropy": 5.044158601760865,
|
|
"epoch": 3.118522930315664,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004051955803663523,
|
|
"loss": 4.4326,
|
|
"mean_token_accuracy": 0.24581895023584366,
|
|
"num_tokens": 73168740.0,
|
|
"step": 26180
|
|
},
|
|
{
|
|
"entropy": 5.193027496337891,
|
|
"epoch": 3.1191185229303158,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004051608241022024,
|
|
"loss": 4.6844,
|
|
"mean_token_accuracy": 0.22936591506004333,
|
|
"num_tokens": 73184648.0,
|
|
"step": 26185
|
|
},
|
|
{
|
|
"entropy": 5.196038770675659,
|
|
"epoch": 3.1197141155449675,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00040512606316939524,
|
|
"loss": 4.5912,
|
|
"mean_token_accuracy": 0.23155171871185304,
|
|
"num_tokens": 73199520.0,
|
|
"step": 26190
|
|
},
|
|
{
|
|
"entropy": 5.087829446792602,
|
|
"epoch": 3.1203097081596187,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00040509129756917785,
|
|
"loss": 4.5319,
|
|
"mean_token_accuracy": 0.23958443403244017,
|
|
"num_tokens": 73213595.0,
|
|
"step": 26195
|
|
},
|
|
{
|
|
"entropy": 5.12515606880188,
|
|
"epoch": 3.1209053007742704,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000405056527302797,
|
|
"loss": 4.565,
|
|
"mean_token_accuracy": 0.23117154687643052,
|
|
"num_tokens": 73225378.0,
|
|
"step": 26200
|
|
},
|
|
{
|
|
"entropy": 5.018010473251342,
|
|
"epoch": 3.121500893388922,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004050217523715002,
|
|
"loss": 4.4037,
|
|
"mean_token_accuracy": 0.25019543021917345,
|
|
"num_tokens": 73240038.0,
|
|
"step": 26205
|
|
},
|
|
{
|
|
"entropy": 5.065742063522339,
|
|
"epoch": 3.1220964860035734,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004049869727765343,
|
|
"loss": 4.397,
|
|
"mean_token_accuracy": 0.2461743026971817,
|
|
"num_tokens": 73254795.0,
|
|
"step": 26210
|
|
},
|
|
{
|
|
"entropy": 5.031217622756958,
|
|
"epoch": 3.122692078618225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040495218851914716,
|
|
"loss": 4.4248,
|
|
"mean_token_accuracy": 0.24424369037151336,
|
|
"num_tokens": 73268060.0,
|
|
"step": 26215
|
|
},
|
|
{
|
|
"entropy": 5.032956790924072,
|
|
"epoch": 3.1232876712328768,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004049173996005863,
|
|
"loss": 4.4555,
|
|
"mean_token_accuracy": 0.2457206130027771,
|
|
"num_tokens": 73279379.0,
|
|
"step": 26220
|
|
},
|
|
{
|
|
"entropy": 5.1785201072692875,
|
|
"epoch": 3.1238832638475285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004048826060220996,
|
|
"loss": 4.6487,
|
|
"mean_token_accuracy": 0.22563905417919158,
|
|
"num_tokens": 73295611.0,
|
|
"step": 26225
|
|
},
|
|
{
|
|
"entropy": 5.144776391983032,
|
|
"epoch": 3.1244788564621797,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004048478077849349,
|
|
"loss": 4.5625,
|
|
"mean_token_accuracy": 0.23493460863828658,
|
|
"num_tokens": 73312737.0,
|
|
"step": 26230
|
|
},
|
|
{
|
|
"entropy": 5.042306709289551,
|
|
"epoch": 3.1250744490768314,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004048130048903404,
|
|
"loss": 4.4512,
|
|
"mean_token_accuracy": 0.2450860396027565,
|
|
"num_tokens": 73328376.0,
|
|
"step": 26235
|
|
},
|
|
{
|
|
"entropy": 5.046360206604004,
|
|
"epoch": 3.125670041691483,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040477819733956467,
|
|
"loss": 4.4568,
|
|
"mean_token_accuracy": 0.24170706421136856,
|
|
"num_tokens": 73341163.0,
|
|
"step": 26240
|
|
},
|
|
{
|
|
"entropy": 5.090980005264282,
|
|
"epoch": 3.126265634306135,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004047433851338559,
|
|
"loss": 4.4978,
|
|
"mean_token_accuracy": 0.24298369884490967,
|
|
"num_tokens": 73354365.0,
|
|
"step": 26245
|
|
},
|
|
{
|
|
"entropy": 5.01835355758667,
|
|
"epoch": 3.126861226920786,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040470856827446285,
|
|
"loss": 4.4025,
|
|
"mean_token_accuracy": 0.25332150161266326,
|
|
"num_tokens": 73368337.0,
|
|
"step": 26250
|
|
},
|
|
{
|
|
"entropy": 5.064474630355835,
|
|
"epoch": 3.1274568195354377,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040467374676263435,
|
|
"loss": 4.4672,
|
|
"mean_token_accuracy": 0.24606344550848008,
|
|
"num_tokens": 73382921.0,
|
|
"step": 26255
|
|
},
|
|
{
|
|
"entropy": 5.007767963409424,
|
|
"epoch": 3.1280524121500894,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040463892059961946,
|
|
"loss": 4.3997,
|
|
"mean_token_accuracy": 0.24705345332622528,
|
|
"num_tokens": 73396883.0,
|
|
"step": 26260
|
|
},
|
|
{
|
|
"entropy": 5.1397181987762455,
|
|
"epoch": 3.1286480047647407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004046040897866671,
|
|
"loss": 4.5508,
|
|
"mean_token_accuracy": 0.23371068984270096,
|
|
"num_tokens": 73410431.0,
|
|
"step": 26265
|
|
},
|
|
{
|
|
"entropy": 5.081578063964844,
|
|
"epoch": 3.1292435973793924,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040456925432502694,
|
|
"loss": 4.4917,
|
|
"mean_token_accuracy": 0.24328383207321166,
|
|
"num_tokens": 73424371.0,
|
|
"step": 26270
|
|
},
|
|
{
|
|
"entropy": 5.094103193283081,
|
|
"epoch": 3.129839189994044,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040453441421594823,
|
|
"loss": 4.5276,
|
|
"mean_token_accuracy": 0.2328118324279785,
|
|
"num_tokens": 73438295.0,
|
|
"step": 26275
|
|
},
|
|
{
|
|
"entropy": 4.962074565887451,
|
|
"epoch": 3.130434782608696,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040449956946068065,
|
|
"loss": 4.3688,
|
|
"mean_token_accuracy": 0.25415376424789426,
|
|
"num_tokens": 73450260.0,
|
|
"step": 26280
|
|
},
|
|
{
|
|
"entropy": 5.039414119720459,
|
|
"epoch": 3.131030375223347,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040446472006047413,
|
|
"loss": 4.47,
|
|
"mean_token_accuracy": 0.2426438108086586,
|
|
"num_tokens": 73462985.0,
|
|
"step": 26285
|
|
},
|
|
{
|
|
"entropy": 5.190620183944702,
|
|
"epoch": 3.1316259678379987,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004044298660165786,
|
|
"loss": 4.6418,
|
|
"mean_token_accuracy": 0.2326260194182396,
|
|
"num_tokens": 73477552.0,
|
|
"step": 26290
|
|
},
|
|
{
|
|
"entropy": 5.105003881454468,
|
|
"epoch": 3.1322215604526504,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004043950073302442,
|
|
"loss": 4.4888,
|
|
"mean_token_accuracy": 0.24326582252979279,
|
|
"num_tokens": 73491034.0,
|
|
"step": 26295
|
|
},
|
|
{
|
|
"entropy": 5.02942910194397,
|
|
"epoch": 3.132817153067302,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004043601440027213,
|
|
"loss": 4.4808,
|
|
"mean_token_accuracy": 0.24165779054164888,
|
|
"num_tokens": 73504875.0,
|
|
"step": 26300
|
|
},
|
|
{
|
|
"entropy": 5.091132259368896,
|
|
"epoch": 3.1334127456819534,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040432527603526027,
|
|
"loss": 4.4879,
|
|
"mean_token_accuracy": 0.24055831432342528,
|
|
"num_tokens": 73518987.0,
|
|
"step": 26305
|
|
},
|
|
{
|
|
"entropy": 5.081867599487305,
|
|
"epoch": 3.134008338296605,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040429040342911186,
|
|
"loss": 4.475,
|
|
"mean_token_accuracy": 0.24013615101575853,
|
|
"num_tokens": 73533636.0,
|
|
"step": 26310
|
|
},
|
|
{
|
|
"entropy": 5.063881206512451,
|
|
"epoch": 3.1346039309112568,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000404255526185527,
|
|
"loss": 4.4436,
|
|
"mean_token_accuracy": 0.2489823505282402,
|
|
"num_tokens": 73547119.0,
|
|
"step": 26315
|
|
},
|
|
{
|
|
"entropy": 5.125768423080444,
|
|
"epoch": 3.1351995235259085,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004042206443057565,
|
|
"loss": 4.5989,
|
|
"mean_token_accuracy": 0.2335863396525383,
|
|
"num_tokens": 73562209.0,
|
|
"step": 26320
|
|
},
|
|
{
|
|
"entropy": 5.136957740783691,
|
|
"epoch": 3.1357951161405597,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004041857577910516,
|
|
"loss": 4.541,
|
|
"mean_token_accuracy": 0.24501162469387056,
|
|
"num_tokens": 73574327.0,
|
|
"step": 26325
|
|
},
|
|
{
|
|
"entropy": 5.171213817596436,
|
|
"epoch": 3.1363907087552114,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004041508666426636,
|
|
"loss": 4.592,
|
|
"mean_token_accuracy": 0.23436564803123475,
|
|
"num_tokens": 73588601.0,
|
|
"step": 26330
|
|
},
|
|
{
|
|
"entropy": 5.066804599761963,
|
|
"epoch": 3.136986301369863,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000404115970861844,
|
|
"loss": 4.4819,
|
|
"mean_token_accuracy": 0.2441025823354721,
|
|
"num_tokens": 73602351.0,
|
|
"step": 26335
|
|
},
|
|
{
|
|
"entropy": 5.111307525634766,
|
|
"epoch": 3.137581893984515,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040408107044984456,
|
|
"loss": 4.5037,
|
|
"mean_token_accuracy": 0.2425532504916191,
|
|
"num_tokens": 73614051.0,
|
|
"step": 26340
|
|
},
|
|
{
|
|
"entropy": 5.086661767959595,
|
|
"epoch": 3.138177486599166,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040404616540791683,
|
|
"loss": 4.4548,
|
|
"mean_token_accuracy": 0.24539873450994493,
|
|
"num_tokens": 73629356.0,
|
|
"step": 26345
|
|
},
|
|
{
|
|
"entropy": 5.037607908248901,
|
|
"epoch": 3.1387730792138178,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040401125573731307,
|
|
"loss": 4.426,
|
|
"mean_token_accuracy": 0.2528513863682747,
|
|
"num_tokens": 73642332.0,
|
|
"step": 26350
|
|
},
|
|
{
|
|
"entropy": 4.993711948394775,
|
|
"epoch": 3.1393686718284695,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004039763414392853,
|
|
"loss": 4.4729,
|
|
"mean_token_accuracy": 0.2441414475440979,
|
|
"num_tokens": 73655744.0,
|
|
"step": 26355
|
|
},
|
|
{
|
|
"entropy": 5.1461340427398685,
|
|
"epoch": 3.1399642644431207,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040394142251508585,
|
|
"loss": 4.6047,
|
|
"mean_token_accuracy": 0.23342137187719345,
|
|
"num_tokens": 73672546.0,
|
|
"step": 26360
|
|
},
|
|
{
|
|
"entropy": 5.097298955917358,
|
|
"epoch": 3.1405598570577724,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004039064989659672,
|
|
"loss": 4.5054,
|
|
"mean_token_accuracy": 0.24443179070949556,
|
|
"num_tokens": 73687451.0,
|
|
"step": 26365
|
|
},
|
|
{
|
|
"entropy": 5.1092634201049805,
|
|
"epoch": 3.141155449672424,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040387157079318207,
|
|
"loss": 4.478,
|
|
"mean_token_accuracy": 0.2494858369231224,
|
|
"num_tokens": 73699192.0,
|
|
"step": 26370
|
|
},
|
|
{
|
|
"entropy": 5.102211952209473,
|
|
"epoch": 3.141751042287076,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040383663799798325,
|
|
"loss": 4.5843,
|
|
"mean_token_accuracy": 0.22924577593803405,
|
|
"num_tokens": 73714518.0,
|
|
"step": 26375
|
|
},
|
|
{
|
|
"entropy": 5.143618869781494,
|
|
"epoch": 3.142346634901727,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004038017005816237,
|
|
"loss": 4.5116,
|
|
"mean_token_accuracy": 0.24230280965566636,
|
|
"num_tokens": 73727046.0,
|
|
"step": 26380
|
|
},
|
|
{
|
|
"entropy": 5.111461210250854,
|
|
"epoch": 3.1429422275163788,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004037667585453565,
|
|
"loss": 4.5356,
|
|
"mean_token_accuracy": 0.2372051805257797,
|
|
"num_tokens": 73742078.0,
|
|
"step": 26385
|
|
},
|
|
{
|
|
"entropy": 5.044286251068115,
|
|
"epoch": 3.1435378201310304,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000403731811890435,
|
|
"loss": 4.4146,
|
|
"mean_token_accuracy": 0.25507012009620667,
|
|
"num_tokens": 73755324.0,
|
|
"step": 26390
|
|
},
|
|
{
|
|
"entropy": 5.073716306686402,
|
|
"epoch": 3.144133412745682,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004036968606181129,
|
|
"loss": 4.5356,
|
|
"mean_token_accuracy": 0.2392561823129654,
|
|
"num_tokens": 73768457.0,
|
|
"step": 26395
|
|
},
|
|
{
|
|
"entropy": 5.099937582015992,
|
|
"epoch": 3.1447290053603334,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004036619047296435,
|
|
"loss": 4.4995,
|
|
"mean_token_accuracy": 0.24050374329090118,
|
|
"num_tokens": 73781821.0,
|
|
"step": 26400
|
|
},
|
|
{
|
|
"entropy": 5.1492232322692875,
|
|
"epoch": 3.145324597974985,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004036269442262808,
|
|
"loss": 4.5187,
|
|
"mean_token_accuracy": 0.2387622520327568,
|
|
"num_tokens": 73796199.0,
|
|
"step": 26405
|
|
},
|
|
{
|
|
"entropy": 5.082683324813843,
|
|
"epoch": 3.145920190589637,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004035919791092787,
|
|
"loss": 4.4707,
|
|
"mean_token_accuracy": 0.2409462660551071,
|
|
"num_tokens": 73811032.0,
|
|
"step": 26410
|
|
},
|
|
{
|
|
"entropy": 5.00369610786438,
|
|
"epoch": 3.146515783204288,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004035570093798914,
|
|
"loss": 4.4067,
|
|
"mean_token_accuracy": 0.2546832948923111,
|
|
"num_tokens": 73823862.0,
|
|
"step": 26415
|
|
},
|
|
{
|
|
"entropy": 5.104601001739502,
|
|
"epoch": 3.1471113758189397,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004035220350393732,
|
|
"loss": 4.511,
|
|
"mean_token_accuracy": 0.23843295276165008,
|
|
"num_tokens": 73837246.0,
|
|
"step": 26420
|
|
},
|
|
{
|
|
"entropy": 5.187044429779053,
|
|
"epoch": 3.1477069684335914,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004034870560889787,
|
|
"loss": 4.6101,
|
|
"mean_token_accuracy": 0.23948598355054856,
|
|
"num_tokens": 73850491.0,
|
|
"step": 26425
|
|
},
|
|
{
|
|
"entropy": 5.141530752182007,
|
|
"epoch": 3.148302561048243,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004034520725299623,
|
|
"loss": 4.5141,
|
|
"mean_token_accuracy": 0.23792515248060225,
|
|
"num_tokens": 73863712.0,
|
|
"step": 26430
|
|
},
|
|
{
|
|
"entropy": 4.989873313903809,
|
|
"epoch": 3.1488981536628944,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004034170843635789,
|
|
"loss": 4.3967,
|
|
"mean_token_accuracy": 0.24686028808355331,
|
|
"num_tokens": 73878033.0,
|
|
"step": 26435
|
|
},
|
|
{
|
|
"entropy": 5.125340127944947,
|
|
"epoch": 3.149493746277546,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040338209159108355,
|
|
"loss": 4.5773,
|
|
"mean_token_accuracy": 0.23727768510580063,
|
|
"num_tokens": 73892868.0,
|
|
"step": 26440
|
|
},
|
|
{
|
|
"entropy": 5.10286693572998,
|
|
"epoch": 3.1500893388921978,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004033470942137312,
|
|
"loss": 4.4899,
|
|
"mean_token_accuracy": 0.24829744994640351,
|
|
"num_tokens": 73907840.0,
|
|
"step": 26445
|
|
},
|
|
{
|
|
"entropy": 5.049997568130493,
|
|
"epoch": 3.1506849315068495,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004033120922327773,
|
|
"loss": 4.4646,
|
|
"mean_token_accuracy": 0.2430409625172615,
|
|
"num_tokens": 73922112.0,
|
|
"step": 26450
|
|
},
|
|
{
|
|
"entropy": 5.057100534439087,
|
|
"epoch": 3.1512805241215007,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004032770856494772,
|
|
"loss": 4.4883,
|
|
"mean_token_accuracy": 0.2467679038643837,
|
|
"num_tokens": 73935692.0,
|
|
"step": 26455
|
|
},
|
|
{
|
|
"entropy": 5.075810480117798,
|
|
"epoch": 3.1518761167361524,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004032420744650867,
|
|
"loss": 4.4642,
|
|
"mean_token_accuracy": 0.24253490269184114,
|
|
"num_tokens": 73949260.0,
|
|
"step": 26460
|
|
},
|
|
{
|
|
"entropy": 5.070923089981079,
|
|
"epoch": 3.152471709350804,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040320705868086154,
|
|
"loss": 4.4698,
|
|
"mean_token_accuracy": 0.24263256937265396,
|
|
"num_tokens": 73962237.0,
|
|
"step": 26465
|
|
},
|
|
{
|
|
"entropy": 5.086651039123535,
|
|
"epoch": 3.153067301965456,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004031720382980576,
|
|
"loss": 4.5311,
|
|
"mean_token_accuracy": 0.2384930968284607,
|
|
"num_tokens": 73977181.0,
|
|
"step": 26470
|
|
},
|
|
{
|
|
"entropy": 5.107464790344238,
|
|
"epoch": 3.153662894580107,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000403137013317931,
|
|
"loss": 4.5663,
|
|
"mean_token_accuracy": 0.2342556819319725,
|
|
"num_tokens": 73991971.0,
|
|
"step": 26475
|
|
},
|
|
{
|
|
"entropy": 5.120551633834839,
|
|
"epoch": 3.1542584871947588,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040310198374173814,
|
|
"loss": 4.5553,
|
|
"mean_token_accuracy": 0.2355814442038536,
|
|
"num_tokens": 74005698.0,
|
|
"step": 26480
|
|
},
|
|
{
|
|
"entropy": 5.114950370788574,
|
|
"epoch": 3.1548540798094105,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040306694957073535,
|
|
"loss": 4.5102,
|
|
"mean_token_accuracy": 0.23453992903232573,
|
|
"num_tokens": 74018106.0,
|
|
"step": 26485
|
|
},
|
|
{
|
|
"entropy": 5.025418329238891,
|
|
"epoch": 3.155449672424062,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040303191080617927,
|
|
"loss": 4.4269,
|
|
"mean_token_accuracy": 0.25126081705093384,
|
|
"num_tokens": 74032148.0,
|
|
"step": 26490
|
|
},
|
|
{
|
|
"entropy": 5.060943698883056,
|
|
"epoch": 3.1560452650387134,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004029968674493268,
|
|
"loss": 4.4504,
|
|
"mean_token_accuracy": 0.23813644498586656,
|
|
"num_tokens": 74046304.0,
|
|
"step": 26495
|
|
},
|
|
{
|
|
"entropy": 5.042262268066406,
|
|
"epoch": 3.156640857653365,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004029618195014347,
|
|
"loss": 4.4448,
|
|
"mean_token_accuracy": 0.2478194147348404,
|
|
"num_tokens": 74058720.0,
|
|
"step": 26500
|
|
},
|
|
{
|
|
"entropy": 5.086773204803467,
|
|
"epoch": 3.157236450268017,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004029267669637603,
|
|
"loss": 4.5101,
|
|
"mean_token_accuracy": 0.23703486174345018,
|
|
"num_tokens": 74073479.0,
|
|
"step": 26505
|
|
},
|
|
{
|
|
"entropy": 5.146349382400513,
|
|
"epoch": 3.157832042882668,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040289170983756075,
|
|
"loss": 4.5756,
|
|
"mean_token_accuracy": 0.2420608475804329,
|
|
"num_tokens": 74088847.0,
|
|
"step": 26510
|
|
},
|
|
{
|
|
"entropy": 5.091612434387207,
|
|
"epoch": 3.1584276354973198,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040285664812409345,
|
|
"loss": 4.514,
|
|
"mean_token_accuracy": 0.24090432822704316,
|
|
"num_tokens": 74103621.0,
|
|
"step": 26515
|
|
},
|
|
{
|
|
"entropy": 5.014477920532227,
|
|
"epoch": 3.1590232281119714,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004028215818246161,
|
|
"loss": 4.47,
|
|
"mean_token_accuracy": 0.23950593322515487,
|
|
"num_tokens": 74117277.0,
|
|
"step": 26520
|
|
},
|
|
{
|
|
"entropy": 5.129214715957642,
|
|
"epoch": 3.159618820726623,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004027865109403864,
|
|
"loss": 4.4915,
|
|
"mean_token_accuracy": 0.24225781708955765,
|
|
"num_tokens": 74130564.0,
|
|
"step": 26525
|
|
},
|
|
{
|
|
"entropy": 5.0635120391845705,
|
|
"epoch": 3.1602144133412744,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00040275143547266235,
|
|
"loss": 4.459,
|
|
"mean_token_accuracy": 0.24220805317163469,
|
|
"num_tokens": 74144231.0,
|
|
"step": 26530
|
|
},
|
|
{
|
|
"entropy": 5.161339330673218,
|
|
"epoch": 3.160810005955926,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000402716355422702,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.23626852929592132,
|
|
"num_tokens": 74158305.0,
|
|
"step": 26535
|
|
},
|
|
{
|
|
"entropy": 5.064867115020752,
|
|
"epoch": 3.161405598570578,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040268127079176364,
|
|
"loss": 4.4931,
|
|
"mean_token_accuracy": 0.23725424855947494,
|
|
"num_tokens": 74171200.0,
|
|
"step": 26540
|
|
},
|
|
{
|
|
"entropy": 5.028655910491944,
|
|
"epoch": 3.1620011911852295,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004026461815811057,
|
|
"loss": 4.3436,
|
|
"mean_token_accuracy": 0.2575677573680878,
|
|
"num_tokens": 74184792.0,
|
|
"step": 26545
|
|
},
|
|
{
|
|
"entropy": 5.0890051364898685,
|
|
"epoch": 3.1625967837998807,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004026110877919867,
|
|
"loss": 4.4905,
|
|
"mean_token_accuracy": 0.24132090508937837,
|
|
"num_tokens": 74198971.0,
|
|
"step": 26550
|
|
},
|
|
{
|
|
"entropy": 5.184808778762817,
|
|
"epoch": 3.1631923764145324,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040257598942566565,
|
|
"loss": 4.6443,
|
|
"mean_token_accuracy": 0.22409225553274154,
|
|
"num_tokens": 74214083.0,
|
|
"step": 26555
|
|
},
|
|
{
|
|
"entropy": 5.079130840301514,
|
|
"epoch": 3.163787969029184,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040254088648340107,
|
|
"loss": 4.4479,
|
|
"mean_token_accuracy": 0.24920179843902587,
|
|
"num_tokens": 74228258.0,
|
|
"step": 26560
|
|
},
|
|
{
|
|
"entropy": 5.116072368621826,
|
|
"epoch": 3.1643835616438354,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004025057789664524,
|
|
"loss": 4.5687,
|
|
"mean_token_accuracy": 0.2372838467359543,
|
|
"num_tokens": 74241910.0,
|
|
"step": 26565
|
|
},
|
|
{
|
|
"entropy": 5.143530559539795,
|
|
"epoch": 3.164979154258487,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004024706668760787,
|
|
"loss": 4.5656,
|
|
"mean_token_accuracy": 0.23341609239578248,
|
|
"num_tokens": 74256326.0,
|
|
"step": 26570
|
|
},
|
|
{
|
|
"entropy": 5.045047092437744,
|
|
"epoch": 3.165574746873139,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004024355502135394,
|
|
"loss": 4.4544,
|
|
"mean_token_accuracy": 0.2420723855495453,
|
|
"num_tokens": 74270957.0,
|
|
"step": 26575
|
|
},
|
|
{
|
|
"entropy": 5.086093235015869,
|
|
"epoch": 3.1661703394877905,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040240042898009425,
|
|
"loss": 4.4352,
|
|
"mean_token_accuracy": 0.24967764168977738,
|
|
"num_tokens": 74285974.0,
|
|
"step": 26580
|
|
},
|
|
{
|
|
"entropy": 5.104531574249267,
|
|
"epoch": 3.1667659321024417,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004023653031770028,
|
|
"loss": 4.529,
|
|
"mean_token_accuracy": 0.23805822134017945,
|
|
"num_tokens": 74298952.0,
|
|
"step": 26585
|
|
},
|
|
{
|
|
"entropy": 5.10663857460022,
|
|
"epoch": 3.1673615247170934,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040233017280552494,
|
|
"loss": 4.5798,
|
|
"mean_token_accuracy": 0.23278166800737382,
|
|
"num_tokens": 74314677.0,
|
|
"step": 26590
|
|
},
|
|
{
|
|
"entropy": 5.066676187515259,
|
|
"epoch": 3.167957117331745,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004022950378669208,
|
|
"loss": 4.4581,
|
|
"mean_token_accuracy": 0.23837199360132216,
|
|
"num_tokens": 74328974.0,
|
|
"step": 26595
|
|
},
|
|
{
|
|
"entropy": 5.034441661834717,
|
|
"epoch": 3.168552709946397,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040225989836245064,
|
|
"loss": 4.4228,
|
|
"mean_token_accuracy": 0.2498618870973587,
|
|
"num_tokens": 74344035.0,
|
|
"step": 26600
|
|
},
|
|
{
|
|
"entropy": 5.065248632431031,
|
|
"epoch": 3.169148302561048,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004022247542933749,
|
|
"loss": 4.4046,
|
|
"mean_token_accuracy": 0.2482934281229973,
|
|
"num_tokens": 74357844.0,
|
|
"step": 26605
|
|
},
|
|
{
|
|
"entropy": 5.0534247875213625,
|
|
"epoch": 3.1697438951756998,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000402189605660954,
|
|
"loss": 4.4417,
|
|
"mean_token_accuracy": 0.2433118626475334,
|
|
"num_tokens": 74371924.0,
|
|
"step": 26610
|
|
},
|
|
{
|
|
"entropy": 5.032461786270142,
|
|
"epoch": 3.1703394877903515,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040215445246644875,
|
|
"loss": 4.4702,
|
|
"mean_token_accuracy": 0.24765416234731674,
|
|
"num_tokens": 74386620.0,
|
|
"step": 26615
|
|
},
|
|
{
|
|
"entropy": 5.025233173370362,
|
|
"epoch": 3.170935080405003,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004021192947111201,
|
|
"loss": 4.4205,
|
|
"mean_token_accuracy": 0.2424151197075844,
|
|
"num_tokens": 74401946.0,
|
|
"step": 26620
|
|
},
|
|
{
|
|
"entropy": 5.025446033477783,
|
|
"epoch": 3.1715306730196544,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00040208413239622894,
|
|
"loss": 4.4374,
|
|
"mean_token_accuracy": 0.2469365566968918,
|
|
"num_tokens": 74417435.0,
|
|
"step": 26625
|
|
},
|
|
{
|
|
"entropy": 5.1500404357910154,
|
|
"epoch": 3.172126265634306,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004020489655230366,
|
|
"loss": 4.5264,
|
|
"mean_token_accuracy": 0.23727734088897706,
|
|
"num_tokens": 74435450.0,
|
|
"step": 26630
|
|
},
|
|
{
|
|
"entropy": 5.147134160995483,
|
|
"epoch": 3.172721858248958,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004020137940928045,
|
|
"loss": 4.5197,
|
|
"mean_token_accuracy": 0.24214298725128175,
|
|
"num_tokens": 74447444.0,
|
|
"step": 26635
|
|
},
|
|
{
|
|
"entropy": 5.12725305557251,
|
|
"epoch": 3.1733174508636095,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004019786181067941,
|
|
"loss": 4.5688,
|
|
"mean_token_accuracy": 0.2403496965765953,
|
|
"num_tokens": 74461822.0,
|
|
"step": 26640
|
|
},
|
|
{
|
|
"entropy": 5.0723466873168945,
|
|
"epoch": 3.1739130434782608,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00040194343756626706,
|
|
"loss": 4.4757,
|
|
"mean_token_accuracy": 0.24789280742406844,
|
|
"num_tokens": 74475178.0,
|
|
"step": 26645
|
|
},
|
|
{
|
|
"entropy": 5.060490703582763,
|
|
"epoch": 3.1745086360929125,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040190825247248544,
|
|
"loss": 4.4003,
|
|
"mean_token_accuracy": 0.2453344762325287,
|
|
"num_tokens": 74488725.0,
|
|
"step": 26650
|
|
},
|
|
{
|
|
"entropy": 5.021632099151612,
|
|
"epoch": 3.175104228707564,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000401873062826711,
|
|
"loss": 4.4583,
|
|
"mean_token_accuracy": 0.24282455444335938,
|
|
"num_tokens": 74502467.0,
|
|
"step": 26655
|
|
},
|
|
{
|
|
"entropy": 5.08139934539795,
|
|
"epoch": 3.1756998213222154,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00040183786863020617,
|
|
"loss": 4.5143,
|
|
"mean_token_accuracy": 0.24157058000564574,
|
|
"num_tokens": 74516495.0,
|
|
"step": 26660
|
|
},
|
|
{
|
|
"entropy": 5.12956919670105,
|
|
"epoch": 3.176295413936867,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040180266988423314,
|
|
"loss": 4.4968,
|
|
"mean_token_accuracy": 0.2406951069831848,
|
|
"num_tokens": 74531025.0,
|
|
"step": 26665
|
|
},
|
|
{
|
|
"entropy": 5.125797414779663,
|
|
"epoch": 3.176891006551519,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040176746659005455,
|
|
"loss": 4.536,
|
|
"mean_token_accuracy": 0.2353868827223778,
|
|
"num_tokens": 74544503.0,
|
|
"step": 26670
|
|
},
|
|
{
|
|
"entropy": 5.056195020675659,
|
|
"epoch": 3.1774865991661705,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040173225874893305,
|
|
"loss": 4.4362,
|
|
"mean_token_accuracy": 0.24322928339242936,
|
|
"num_tokens": 74558071.0,
|
|
"step": 26675
|
|
},
|
|
{
|
|
"entropy": 5.057573699951172,
|
|
"epoch": 3.1780821917808217,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00040169704636213143,
|
|
"loss": 4.4718,
|
|
"mean_token_accuracy": 0.24259331524372102,
|
|
"num_tokens": 74571171.0,
|
|
"step": 26680
|
|
},
|
|
{
|
|
"entropy": 5.119961071014404,
|
|
"epoch": 3.1786777843954734,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040166182943091283,
|
|
"loss": 4.5383,
|
|
"mean_token_accuracy": 0.2393883228302002,
|
|
"num_tokens": 74586303.0,
|
|
"step": 26685
|
|
},
|
|
{
|
|
"entropy": 5.141018533706665,
|
|
"epoch": 3.179273377010125,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040162660795654034,
|
|
"loss": 4.5552,
|
|
"mean_token_accuracy": 0.24441532641649247,
|
|
"num_tokens": 74598355.0,
|
|
"step": 26690
|
|
},
|
|
{
|
|
"entropy": 5.096330833435059,
|
|
"epoch": 3.179868969624777,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004015913819402773,
|
|
"loss": 4.4904,
|
|
"mean_token_accuracy": 0.24291736036539077,
|
|
"num_tokens": 74611738.0,
|
|
"step": 26695
|
|
},
|
|
{
|
|
"entropy": 5.119182348251343,
|
|
"epoch": 3.180464562239428,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004015561513833872,
|
|
"loss": 4.5686,
|
|
"mean_token_accuracy": 0.23360999971628188,
|
|
"num_tokens": 74625401.0,
|
|
"step": 26700
|
|
},
|
|
{
|
|
"entropy": 5.137380170822143,
|
|
"epoch": 3.18106015485408,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004015209162871337,
|
|
"loss": 4.5427,
|
|
"mean_token_accuracy": 0.2360779419541359,
|
|
"num_tokens": 74640615.0,
|
|
"step": 26705
|
|
},
|
|
{
|
|
"entropy": 5.166721677780151,
|
|
"epoch": 3.1816557474687315,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040148567665278066,
|
|
"loss": 4.5648,
|
|
"mean_token_accuracy": 0.23352273553609848,
|
|
"num_tokens": 74654292.0,
|
|
"step": 26710
|
|
},
|
|
{
|
|
"entropy": 5.060494041442871,
|
|
"epoch": 3.182251340083383,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040145043248159207,
|
|
"loss": 4.466,
|
|
"mean_token_accuracy": 0.24643132388591765,
|
|
"num_tokens": 74667013.0,
|
|
"step": 26715
|
|
},
|
|
{
|
|
"entropy": 5.209156656265259,
|
|
"epoch": 3.1828469326980344,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004014151837748321,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.22532249242067337,
|
|
"num_tokens": 74682704.0,
|
|
"step": 26720
|
|
},
|
|
{
|
|
"entropy": 5.097080659866333,
|
|
"epoch": 3.183442525312686,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00040137993053376494,
|
|
"loss": 4.4668,
|
|
"mean_token_accuracy": 0.2425903245806694,
|
|
"num_tokens": 74695210.0,
|
|
"step": 26725
|
|
},
|
|
{
|
|
"entropy": 5.119524526596069,
|
|
"epoch": 3.184038117927338,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040134467275965515,
|
|
"loss": 4.4918,
|
|
"mean_token_accuracy": 0.2467359334230423,
|
|
"num_tokens": 74710464.0,
|
|
"step": 26730
|
|
},
|
|
{
|
|
"entropy": 5.059909057617188,
|
|
"epoch": 3.184633710541989,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004013094104537674,
|
|
"loss": 4.4882,
|
|
"mean_token_accuracy": 0.23865606188774108,
|
|
"num_tokens": 74724284.0,
|
|
"step": 26735
|
|
},
|
|
{
|
|
"entropy": 5.062332391738892,
|
|
"epoch": 3.1852293031566408,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004012741436173665,
|
|
"loss": 4.4176,
|
|
"mean_token_accuracy": 0.24579187333583832,
|
|
"num_tokens": 74738253.0,
|
|
"step": 26740
|
|
},
|
|
{
|
|
"entropy": 5.085606575012207,
|
|
"epoch": 3.1858248957712925,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00040123887225171736,
|
|
"loss": 4.4976,
|
|
"mean_token_accuracy": 0.25051808804273606,
|
|
"num_tokens": 74752990.0,
|
|
"step": 26745
|
|
},
|
|
{
|
|
"entropy": 5.169383335113525,
|
|
"epoch": 3.186420488385944,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004012035963580851,
|
|
"loss": 4.5609,
|
|
"mean_token_accuracy": 0.23894966691732406,
|
|
"num_tokens": 74766563.0,
|
|
"step": 26750
|
|
},
|
|
{
|
|
"entropy": 5.1613513946533205,
|
|
"epoch": 3.1870160810005954,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004011683159377351,
|
|
"loss": 4.5783,
|
|
"mean_token_accuracy": 0.2343097522854805,
|
|
"num_tokens": 74783441.0,
|
|
"step": 26755
|
|
},
|
|
{
|
|
"entropy": 5.0605216979980465,
|
|
"epoch": 3.187611673615247,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004011330309919326,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.24140226244926452,
|
|
"num_tokens": 74797925.0,
|
|
"step": 26760
|
|
},
|
|
{
|
|
"entropy": 5.065389680862427,
|
|
"epoch": 3.188207266229899,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004010977415219435,
|
|
"loss": 4.4752,
|
|
"mean_token_accuracy": 0.2498265787959099,
|
|
"num_tokens": 74811690.0,
|
|
"step": 26765
|
|
},
|
|
{
|
|
"entropy": 5.126344680786133,
|
|
"epoch": 3.1888028588445505,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040106244752903335,
|
|
"loss": 4.5251,
|
|
"mean_token_accuracy": 0.2383376806974411,
|
|
"num_tokens": 74824646.0,
|
|
"step": 26770
|
|
},
|
|
{
|
|
"entropy": 5.042925405502319,
|
|
"epoch": 3.1893984514592018,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040102714901446817,
|
|
"loss": 4.3941,
|
|
"mean_token_accuracy": 0.24773081988096238,
|
|
"num_tokens": 74838133.0,
|
|
"step": 26775
|
|
},
|
|
{
|
|
"entropy": 5.109745121002197,
|
|
"epoch": 3.1899940440738535,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040099184597951415,
|
|
"loss": 4.5291,
|
|
"mean_token_accuracy": 0.24102879613637923,
|
|
"num_tokens": 74852966.0,
|
|
"step": 26780
|
|
},
|
|
{
|
|
"entropy": 5.1802146434783936,
|
|
"epoch": 3.190589636688505,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004009565384254374,
|
|
"loss": 4.5474,
|
|
"mean_token_accuracy": 0.24038898199796677,
|
|
"num_tokens": 74864840.0,
|
|
"step": 26785
|
|
},
|
|
{
|
|
"entropy": 5.0698206424713135,
|
|
"epoch": 3.191185229303157,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004009212263535044,
|
|
"loss": 4.4234,
|
|
"mean_token_accuracy": 0.2476589247584343,
|
|
"num_tokens": 74877368.0,
|
|
"step": 26790
|
|
},
|
|
{
|
|
"entropy": 5.068578767776489,
|
|
"epoch": 3.191780821917808,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004008859097649818,
|
|
"loss": 4.5329,
|
|
"mean_token_accuracy": 0.24231014400720596,
|
|
"num_tokens": 74890818.0,
|
|
"step": 26795
|
|
},
|
|
{
|
|
"entropy": 5.0657947063446045,
|
|
"epoch": 3.19237641453246,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004008505886611363,
|
|
"loss": 4.4348,
|
|
"mean_token_accuracy": 0.24536082595586778,
|
|
"num_tokens": 74904731.0,
|
|
"step": 26800
|
|
},
|
|
{
|
|
"entropy": 5.176091957092285,
|
|
"epoch": 3.1929720071471115,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004008152630432347,
|
|
"loss": 4.5787,
|
|
"mean_token_accuracy": 0.23352962881326675,
|
|
"num_tokens": 74918557.0,
|
|
"step": 26805
|
|
},
|
|
{
|
|
"entropy": 5.113551425933838,
|
|
"epoch": 3.1935675997617627,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004007799329125443,
|
|
"loss": 4.4557,
|
|
"mean_token_accuracy": 0.24132437705993653,
|
|
"num_tokens": 74930553.0,
|
|
"step": 26810
|
|
},
|
|
{
|
|
"entropy": 5.09881558418274,
|
|
"epoch": 3.1941631923764144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040074459827033217,
|
|
"loss": 4.5898,
|
|
"mean_token_accuracy": 0.2356791913509369,
|
|
"num_tokens": 74943984.0,
|
|
"step": 26815
|
|
},
|
|
{
|
|
"entropy": 5.127982950210571,
|
|
"epoch": 3.194758784991066,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040070925911786563,
|
|
"loss": 4.5418,
|
|
"mean_token_accuracy": 0.23739525079727172,
|
|
"num_tokens": 74958959.0,
|
|
"step": 26820
|
|
},
|
|
{
|
|
"entropy": 5.077558803558349,
|
|
"epoch": 3.195354377605718,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004006739154564126,
|
|
"loss": 4.4722,
|
|
"mean_token_accuracy": 0.24733031690120696,
|
|
"num_tokens": 74972163.0,
|
|
"step": 26825
|
|
},
|
|
{
|
|
"entropy": 5.06124324798584,
|
|
"epoch": 3.195949970220369,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00040063856728724033,
|
|
"loss": 4.4668,
|
|
"mean_token_accuracy": 0.24640252739191054,
|
|
"num_tokens": 74988308.0,
|
|
"step": 26830
|
|
},
|
|
{
|
|
"entropy": 5.129936647415161,
|
|
"epoch": 3.196545562835021,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004006032146116171,
|
|
"loss": 4.5378,
|
|
"mean_token_accuracy": 0.2369121089577675,
|
|
"num_tokens": 75001806.0,
|
|
"step": 26835
|
|
},
|
|
{
|
|
"entropy": 5.086763668060303,
|
|
"epoch": 3.1971411554496725,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040056785743081065,
|
|
"loss": 4.5449,
|
|
"mean_token_accuracy": 0.24237937182188035,
|
|
"num_tokens": 75016591.0,
|
|
"step": 26840
|
|
},
|
|
{
|
|
"entropy": 5.164052295684814,
|
|
"epoch": 3.197736748064324,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040053249574608935,
|
|
"loss": 4.5685,
|
|
"mean_token_accuracy": 0.238641457259655,
|
|
"num_tokens": 75031656.0,
|
|
"step": 26845
|
|
},
|
|
{
|
|
"entropy": 5.0789800643920895,
|
|
"epoch": 3.1983323406789754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004004971295587216,
|
|
"loss": 4.4255,
|
|
"mean_token_accuracy": 0.2555207371711731,
|
|
"num_tokens": 75045950.0,
|
|
"step": 26850
|
|
},
|
|
{
|
|
"entropy": 5.040074205398559,
|
|
"epoch": 3.198927933293627,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040046175886997577,
|
|
"loss": 4.4112,
|
|
"mean_token_accuracy": 0.24929349422454833,
|
|
"num_tokens": 75058112.0,
|
|
"step": 26855
|
|
},
|
|
{
|
|
"entropy": 5.019503402709961,
|
|
"epoch": 3.199523525908279,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004004263836811207,
|
|
"loss": 4.4764,
|
|
"mean_token_accuracy": 0.24503481835126878,
|
|
"num_tokens": 75073510.0,
|
|
"step": 26860
|
|
},
|
|
{
|
|
"entropy": 5.099796772003174,
|
|
"epoch": 3.2001191185229305,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004003910039934251,
|
|
"loss": 4.4547,
|
|
"mean_token_accuracy": 0.24807756245136262,
|
|
"num_tokens": 75085091.0,
|
|
"step": 26865
|
|
},
|
|
{
|
|
"entropy": 5.033207368850708,
|
|
"epoch": 3.2007147111375818,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040035561980815816,
|
|
"loss": 4.4815,
|
|
"mean_token_accuracy": 0.2453518733382225,
|
|
"num_tokens": 75098767.0,
|
|
"step": 26870
|
|
},
|
|
{
|
|
"entropy": 5.106944799423218,
|
|
"epoch": 3.2013103037522335,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004003202311265888,
|
|
"loss": 4.5152,
|
|
"mean_token_accuracy": 0.23586121648550035,
|
|
"num_tokens": 75113366.0,
|
|
"step": 26875
|
|
},
|
|
{
|
|
"entropy": 5.087978744506836,
|
|
"epoch": 3.201905896366885,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004002848379499866,
|
|
"loss": 4.4841,
|
|
"mean_token_accuracy": 0.24448749274015427,
|
|
"num_tokens": 75127765.0,
|
|
"step": 26880
|
|
},
|
|
{
|
|
"entropy": 5.027889442443848,
|
|
"epoch": 3.202501488981537,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040024944027962107,
|
|
"loss": 4.4197,
|
|
"mean_token_accuracy": 0.249857360124588,
|
|
"num_tokens": 75141567.0,
|
|
"step": 26885
|
|
},
|
|
{
|
|
"entropy": 5.129234409332275,
|
|
"epoch": 3.203097081596188,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004002140381167616,
|
|
"loss": 4.5385,
|
|
"mean_token_accuracy": 0.24193118810653685,
|
|
"num_tokens": 75155006.0,
|
|
"step": 26890
|
|
},
|
|
{
|
|
"entropy": 5.129135036468506,
|
|
"epoch": 3.20369267421084,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004001786314626783,
|
|
"loss": 4.4382,
|
|
"mean_token_accuracy": 0.24143352061510087,
|
|
"num_tokens": 75168386.0,
|
|
"step": 26895
|
|
},
|
|
{
|
|
"entropy": 5.030296897888183,
|
|
"epoch": 3.2042882668254915,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040014322031864093,
|
|
"loss": 4.4157,
|
|
"mean_token_accuracy": 0.25230312198400495,
|
|
"num_tokens": 75182091.0,
|
|
"step": 26900
|
|
},
|
|
{
|
|
"entropy": 5.059232378005982,
|
|
"epoch": 3.2048838594401428,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040010780468591975,
|
|
"loss": 4.4779,
|
|
"mean_token_accuracy": 0.24705824851989747,
|
|
"num_tokens": 75195359.0,
|
|
"step": 26905
|
|
},
|
|
{
|
|
"entropy": 5.105259037017822,
|
|
"epoch": 3.2054794520547945,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040007238456578494,
|
|
"loss": 4.4616,
|
|
"mean_token_accuracy": 0.24817587435245514,
|
|
"num_tokens": 75208893.0,
|
|
"step": 26910
|
|
},
|
|
{
|
|
"entropy": 5.045695400238037,
|
|
"epoch": 3.206075044669446,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040003695995950717,
|
|
"loss": 4.4037,
|
|
"mean_token_accuracy": 0.2492915377020836,
|
|
"num_tokens": 75222575.0,
|
|
"step": 26915
|
|
},
|
|
{
|
|
"entropy": 5.0455986022949215,
|
|
"epoch": 3.206670637284098,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004000015308683569,
|
|
"loss": 4.509,
|
|
"mean_token_accuracy": 0.2397433713078499,
|
|
"num_tokens": 75236782.0,
|
|
"step": 26920
|
|
},
|
|
{
|
|
"entropy": 5.153099727630615,
|
|
"epoch": 3.207266229898749,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039996609729360495,
|
|
"loss": 4.5795,
|
|
"mean_token_accuracy": 0.23458230793476104,
|
|
"num_tokens": 75249912.0,
|
|
"step": 26925
|
|
},
|
|
{
|
|
"entropy": 5.096022319793701,
|
|
"epoch": 3.207861822513401,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039993065923652225,
|
|
"loss": 4.4629,
|
|
"mean_token_accuracy": 0.2533779263496399,
|
|
"num_tokens": 75266224.0,
|
|
"step": 26930
|
|
},
|
|
{
|
|
"entropy": 5.079147863388061,
|
|
"epoch": 3.2084574151280525,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039989521669838004,
|
|
"loss": 4.4506,
|
|
"mean_token_accuracy": 0.2440759062767029,
|
|
"num_tokens": 75279363.0,
|
|
"step": 26935
|
|
},
|
|
{
|
|
"entropy": 5.0727184295654295,
|
|
"epoch": 3.209053007742704,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039985976968044933,
|
|
"loss": 4.4433,
|
|
"mean_token_accuracy": 0.24683190137147903,
|
|
"num_tokens": 75292655.0,
|
|
"step": 26940
|
|
},
|
|
{
|
|
"entropy": 5.097094774246216,
|
|
"epoch": 3.2096486003573554,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003998243181840018,
|
|
"loss": 4.467,
|
|
"mean_token_accuracy": 0.25050691664218905,
|
|
"num_tokens": 75305130.0,
|
|
"step": 26945
|
|
},
|
|
{
|
|
"entropy": 4.967849493026733,
|
|
"epoch": 3.210244192972007,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003997888622103088,
|
|
"loss": 4.297,
|
|
"mean_token_accuracy": 0.25618179589509965,
|
|
"num_tokens": 75318713.0,
|
|
"step": 26950
|
|
},
|
|
{
|
|
"entropy": 5.096483755111694,
|
|
"epoch": 3.210839785586659,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039975340176064237,
|
|
"loss": 4.553,
|
|
"mean_token_accuracy": 0.23761917650699615,
|
|
"num_tokens": 75333137.0,
|
|
"step": 26955
|
|
},
|
|
{
|
|
"entropy": 5.08335657119751,
|
|
"epoch": 3.21143537820131,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039971793683627415,
|
|
"loss": 4.4622,
|
|
"mean_token_accuracy": 0.2443619579076767,
|
|
"num_tokens": 75347419.0,
|
|
"step": 26960
|
|
},
|
|
{
|
|
"entropy": 5.141581726074219,
|
|
"epoch": 3.212030970815962,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003996824674384763,
|
|
"loss": 4.5121,
|
|
"mean_token_accuracy": 0.24364235401153564,
|
|
"num_tokens": 75361673.0,
|
|
"step": 26965
|
|
},
|
|
{
|
|
"entropy": 5.04302134513855,
|
|
"epoch": 3.2126265634306135,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039964699356852105,
|
|
"loss": 4.3939,
|
|
"mean_token_accuracy": 0.2518837109208107,
|
|
"num_tokens": 75376579.0,
|
|
"step": 26970
|
|
},
|
|
{
|
|
"entropy": 5.070455741882324,
|
|
"epoch": 3.213222156045265,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003996115152276809,
|
|
"loss": 4.4941,
|
|
"mean_token_accuracy": 0.23970090448856354,
|
|
"num_tokens": 75388421.0,
|
|
"step": 26975
|
|
},
|
|
{
|
|
"entropy": 5.049863481521607,
|
|
"epoch": 3.2138177486599164,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003995760324172283,
|
|
"loss": 4.4619,
|
|
"mean_token_accuracy": 0.24264966696500778,
|
|
"num_tokens": 75402185.0,
|
|
"step": 26980
|
|
},
|
|
{
|
|
"entropy": 5.052697801589966,
|
|
"epoch": 3.214413341274568,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039954054513843595,
|
|
"loss": 4.4185,
|
|
"mean_token_accuracy": 0.25987873524427413,
|
|
"num_tokens": 75415618.0,
|
|
"step": 26985
|
|
},
|
|
{
|
|
"entropy": 5.048001956939697,
|
|
"epoch": 3.21500893388922,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003995050533925767,
|
|
"loss": 4.5196,
|
|
"mean_token_accuracy": 0.23621477782726288,
|
|
"num_tokens": 75430679.0,
|
|
"step": 26990
|
|
},
|
|
{
|
|
"entropy": 5.080040216445923,
|
|
"epoch": 3.2156045265038715,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039946955718092364,
|
|
"loss": 4.478,
|
|
"mean_token_accuracy": 0.24309888780117034,
|
|
"num_tokens": 75443275.0,
|
|
"step": 26995
|
|
},
|
|
{
|
|
"entropy": 5.082398843765259,
|
|
"epoch": 3.2162001191185228,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039943405650474993,
|
|
"loss": 4.4658,
|
|
"mean_token_accuracy": 0.24479187726974488,
|
|
"num_tokens": 75456191.0,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"epoch": 3.2162001191185228,
|
|
"eval_entropy": 4.826097239670709,
|
|
"eval_loss": 4.553175926208496,
|
|
"eval_mean_token_accuracy": 0.2492517443683267,
|
|
"eval_num_tokens": 75456191.0,
|
|
"eval_runtime": 18.5298,
|
|
"eval_samples_per_second": 1376.864,
|
|
"eval_steps_per_second": 172.155,
|
|
"step": 27000
|
|
},
|
|
{
|
|
"entropy": 5.047699689865112,
|
|
"epoch": 3.2167957117331745,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003993985513653289,
|
|
"loss": 4.4429,
|
|
"mean_token_accuracy": 0.24540864676237106,
|
|
"num_tokens": 75469027.0,
|
|
"step": 27005
|
|
},
|
|
{
|
|
"entropy": 5.091913938522339,
|
|
"epoch": 3.217391304347826,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003993630417639341,
|
|
"loss": 4.4821,
|
|
"mean_token_accuracy": 0.24279489517211914,
|
|
"num_tokens": 75484307.0,
|
|
"step": 27010
|
|
},
|
|
{
|
|
"entropy": 5.118598365783692,
|
|
"epoch": 3.217986896962478,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039932752770183925,
|
|
"loss": 4.4346,
|
|
"mean_token_accuracy": 0.24059799313545227,
|
|
"num_tokens": 75496577.0,
|
|
"step": 27015
|
|
},
|
|
{
|
|
"entropy": 5.093510675430298,
|
|
"epoch": 3.218582489577129,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003992920091803181,
|
|
"loss": 4.4426,
|
|
"mean_token_accuracy": 0.2406431883573532,
|
|
"num_tokens": 75512308.0,
|
|
"step": 27020
|
|
},
|
|
{
|
|
"entropy": 5.0455938339233395,
|
|
"epoch": 3.219178082191781,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003992564862006447,
|
|
"loss": 4.4468,
|
|
"mean_token_accuracy": 0.24988682568073273,
|
|
"num_tokens": 75527194.0,
|
|
"step": 27025
|
|
},
|
|
{
|
|
"entropy": 5.087707233428955,
|
|
"epoch": 3.2197736748064325,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039922095876409306,
|
|
"loss": 4.5703,
|
|
"mean_token_accuracy": 0.2355560079216957,
|
|
"num_tokens": 75541736.0,
|
|
"step": 27030
|
|
},
|
|
{
|
|
"entropy": 5.136992788314819,
|
|
"epoch": 3.220369267421084,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003991854268719377,
|
|
"loss": 4.5172,
|
|
"mean_token_accuracy": 0.23962963968515397,
|
|
"num_tokens": 75554820.0,
|
|
"step": 27035
|
|
},
|
|
{
|
|
"entropy": 5.106638813018799,
|
|
"epoch": 3.2209648600357355,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000399149890525453,
|
|
"loss": 4.5211,
|
|
"mean_token_accuracy": 0.24146428555250168,
|
|
"num_tokens": 75569896.0,
|
|
"step": 27040
|
|
},
|
|
{
|
|
"entropy": 5.124935245513916,
|
|
"epoch": 3.221560452650387,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003991143497259135,
|
|
"loss": 4.5049,
|
|
"mean_token_accuracy": 0.23856306225061416,
|
|
"num_tokens": 75585766.0,
|
|
"step": 27045
|
|
},
|
|
{
|
|
"entropy": 5.109418821334839,
|
|
"epoch": 3.222156045265039,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003990788044745942,
|
|
"loss": 4.4788,
|
|
"mean_token_accuracy": 0.24201700091362,
|
|
"num_tokens": 75599910.0,
|
|
"step": 27050
|
|
},
|
|
{
|
|
"entropy": 5.028517532348633,
|
|
"epoch": 3.22275163787969,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039904325477276974,
|
|
"loss": 4.3891,
|
|
"mean_token_accuracy": 0.26035753786563876,
|
|
"num_tokens": 75613054.0,
|
|
"step": 27055
|
|
},
|
|
{
|
|
"entropy": 5.109559535980225,
|
|
"epoch": 3.223347230494342,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003990077006217155,
|
|
"loss": 4.5742,
|
|
"mean_token_accuracy": 0.24414268732070923,
|
|
"num_tokens": 75626528.0,
|
|
"step": 27060
|
|
},
|
|
{
|
|
"entropy": 5.122977590560913,
|
|
"epoch": 3.2239428231089935,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039897214202270673,
|
|
"loss": 4.571,
|
|
"mean_token_accuracy": 0.2451375901699066,
|
|
"num_tokens": 75643238.0,
|
|
"step": 27065
|
|
},
|
|
{
|
|
"entropy": 5.2388063907623295,
|
|
"epoch": 3.224538415723645,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039893657897701874,
|
|
"loss": 4.6125,
|
|
"mean_token_accuracy": 0.2286248028278351,
|
|
"num_tokens": 75657471.0,
|
|
"step": 27070
|
|
},
|
|
{
|
|
"entropy": 5.089288520812988,
|
|
"epoch": 3.2251340083382964,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003989010114859272,
|
|
"loss": 4.479,
|
|
"mean_token_accuracy": 0.24296826124191284,
|
|
"num_tokens": 75671836.0,
|
|
"step": 27075
|
|
},
|
|
{
|
|
"entropy": 5.092413425445557,
|
|
"epoch": 3.225729600952948,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039886543955070777,
|
|
"loss": 4.4533,
|
|
"mean_token_accuracy": 0.2411877319216728,
|
|
"num_tokens": 75685374.0,
|
|
"step": 27080
|
|
},
|
|
{
|
|
"entropy": 5.145541334152222,
|
|
"epoch": 3.2263251935676,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003988298631726364,
|
|
"loss": 4.586,
|
|
"mean_token_accuracy": 0.23432574570178985,
|
|
"num_tokens": 75697935.0,
|
|
"step": 27085
|
|
},
|
|
{
|
|
"entropy": 5.081054782867431,
|
|
"epoch": 3.2269207861822515,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039879428235298925,
|
|
"loss": 4.4769,
|
|
"mean_token_accuracy": 0.24375797808170319,
|
|
"num_tokens": 75713968.0,
|
|
"step": 27090
|
|
},
|
|
{
|
|
"entropy": 5.0901196002960205,
|
|
"epoch": 3.227516378796903,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003987586970930424,
|
|
"loss": 4.4358,
|
|
"mean_token_accuracy": 0.24662339091300964,
|
|
"num_tokens": 75726286.0,
|
|
"step": 27095
|
|
},
|
|
{
|
|
"entropy": 5.122731065750122,
|
|
"epoch": 3.2281119714115545,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003987231073940723,
|
|
"loss": 4.4993,
|
|
"mean_token_accuracy": 0.2460320308804512,
|
|
"num_tokens": 75739335.0,
|
|
"step": 27100
|
|
},
|
|
{
|
|
"entropy": 5.121315145492554,
|
|
"epoch": 3.228707564026206,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039868751325735556,
|
|
"loss": 4.514,
|
|
"mean_token_accuracy": 0.23917637765407562,
|
|
"num_tokens": 75755150.0,
|
|
"step": 27105
|
|
},
|
|
{
|
|
"entropy": 5.139104747772217,
|
|
"epoch": 3.2293031566408574,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003986519146841688,
|
|
"loss": 4.5282,
|
|
"mean_token_accuracy": 0.23182627111673354,
|
|
"num_tokens": 75768503.0,
|
|
"step": 27110
|
|
},
|
|
{
|
|
"entropy": 5.0975728034973145,
|
|
"epoch": 3.229898749255509,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000398616311675789,
|
|
"loss": 4.5493,
|
|
"mean_token_accuracy": 0.24001519083976747,
|
|
"num_tokens": 75783501.0,
|
|
"step": 27115
|
|
},
|
|
{
|
|
"entropy": 5.107522916793823,
|
|
"epoch": 3.230494341870161,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039858070423349297,
|
|
"loss": 4.5493,
|
|
"mean_token_accuracy": 0.23762090057134627,
|
|
"num_tokens": 75799630.0,
|
|
"step": 27120
|
|
},
|
|
{
|
|
"entropy": 5.1037498950958256,
|
|
"epoch": 3.2310899344848125,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039854509235855796,
|
|
"loss": 4.469,
|
|
"mean_token_accuracy": 0.25357985496520996,
|
|
"num_tokens": 75812781.0,
|
|
"step": 27125
|
|
},
|
|
{
|
|
"entropy": 5.11775312423706,
|
|
"epoch": 3.2316855270994638,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003985094760522615,
|
|
"loss": 4.4939,
|
|
"mean_token_accuracy": 0.2385570526123047,
|
|
"num_tokens": 75825469.0,
|
|
"step": 27130
|
|
},
|
|
{
|
|
"entropy": 5.12873911857605,
|
|
"epoch": 3.2322811197141155,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003984738553158809,
|
|
"loss": 4.5059,
|
|
"mean_token_accuracy": 0.24005612432956697,
|
|
"num_tokens": 75838632.0,
|
|
"step": 27135
|
|
},
|
|
{
|
|
"entropy": 5.066212701797485,
|
|
"epoch": 3.232876712328767,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003984382301506938,
|
|
"loss": 4.4438,
|
|
"mean_token_accuracy": 0.24313509464263916,
|
|
"num_tokens": 75853487.0,
|
|
"step": 27140
|
|
},
|
|
{
|
|
"entropy": 5.127564811706543,
|
|
"epoch": 3.233472304943419,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003984026005579781,
|
|
"loss": 4.579,
|
|
"mean_token_accuracy": 0.23998066335916518,
|
|
"num_tokens": 75868462.0,
|
|
"step": 27145
|
|
},
|
|
{
|
|
"entropy": 5.1402841091156,
|
|
"epoch": 3.23406789755807,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003983669665390119,
|
|
"loss": 4.5302,
|
|
"mean_token_accuracy": 0.23975293785333635,
|
|
"num_tokens": 75880573.0,
|
|
"step": 27150
|
|
},
|
|
{
|
|
"entropy": 5.1136024475097654,
|
|
"epoch": 3.234663490172722,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039833132809507306,
|
|
"loss": 4.555,
|
|
"mean_token_accuracy": 0.23973076045513153,
|
|
"num_tokens": 75895166.0,
|
|
"step": 27155
|
|
},
|
|
{
|
|
"entropy": 5.184154748916626,
|
|
"epoch": 3.2352590827873735,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039829568522743996,
|
|
"loss": 4.6129,
|
|
"mean_token_accuracy": 0.23200060278177262,
|
|
"num_tokens": 75909878.0,
|
|
"step": 27160
|
|
},
|
|
{
|
|
"entropy": 5.092649698257446,
|
|
"epoch": 3.235854675402025,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003982600379373912,
|
|
"loss": 4.5604,
|
|
"mean_token_accuracy": 0.24553428888320922,
|
|
"num_tokens": 75922822.0,
|
|
"step": 27165
|
|
},
|
|
{
|
|
"entropy": 5.169850587844849,
|
|
"epoch": 3.2364502680166765,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039822438622620523,
|
|
"loss": 4.5275,
|
|
"mean_token_accuracy": 0.24114565849304198,
|
|
"num_tokens": 75938021.0,
|
|
"step": 27170
|
|
},
|
|
{
|
|
"entropy": 5.068435955047607,
|
|
"epoch": 3.237045860631328,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003981887300951609,
|
|
"loss": 4.4085,
|
|
"mean_token_accuracy": 0.25240222811698915,
|
|
"num_tokens": 75951942.0,
|
|
"step": 27175
|
|
},
|
|
{
|
|
"entropy": 5.054079675674439,
|
|
"epoch": 3.23764145324598,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003981530695455371,
|
|
"loss": 4.4946,
|
|
"mean_token_accuracy": 0.24012813866138458,
|
|
"num_tokens": 75965949.0,
|
|
"step": 27180
|
|
},
|
|
{
|
|
"entropy": 5.101745891571045,
|
|
"epoch": 3.2382370458606315,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039811740457861293,
|
|
"loss": 4.505,
|
|
"mean_token_accuracy": 0.2420251652598381,
|
|
"num_tokens": 75980030.0,
|
|
"step": 27185
|
|
},
|
|
{
|
|
"entropy": 5.111840295791626,
|
|
"epoch": 3.238832638475283,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003980817351956677,
|
|
"loss": 4.5224,
|
|
"mean_token_accuracy": 0.23812973499298096,
|
|
"num_tokens": 75994875.0,
|
|
"step": 27190
|
|
},
|
|
{
|
|
"entropy": 5.079202556610108,
|
|
"epoch": 3.2394282310899345,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003980460613979807,
|
|
"loss": 4.4769,
|
|
"mean_token_accuracy": 0.23926340341567992,
|
|
"num_tokens": 76010122.0,
|
|
"step": 27195
|
|
},
|
|
{
|
|
"entropy": 5.131408166885376,
|
|
"epoch": 3.240023823704586,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039801038318683146,
|
|
"loss": 4.5142,
|
|
"mean_token_accuracy": 0.2448267310857773,
|
|
"num_tokens": 76023675.0,
|
|
"step": 27200
|
|
},
|
|
{
|
|
"entropy": 5.203343391418457,
|
|
"epoch": 3.2406194163192374,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003979747005634999,
|
|
"loss": 4.6777,
|
|
"mean_token_accuracy": 0.22771692425012588,
|
|
"num_tokens": 76037572.0,
|
|
"step": 27205
|
|
},
|
|
{
|
|
"entropy": 5.060094547271729,
|
|
"epoch": 3.241215008933889,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039793901352926575,
|
|
"loss": 4.399,
|
|
"mean_token_accuracy": 0.24703795313835145,
|
|
"num_tokens": 76050692.0,
|
|
"step": 27210
|
|
},
|
|
{
|
|
"entropy": 5.049340057373047,
|
|
"epoch": 3.241810601548541,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003979033220854091,
|
|
"loss": 4.3718,
|
|
"mean_token_accuracy": 0.24948471337556838,
|
|
"num_tokens": 76065131.0,
|
|
"step": 27215
|
|
},
|
|
{
|
|
"entropy": 5.116699934005737,
|
|
"epoch": 3.2424061941631925,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039786762623320997,
|
|
"loss": 4.5381,
|
|
"mean_token_accuracy": 0.23924171030521393,
|
|
"num_tokens": 76079894.0,
|
|
"step": 27220
|
|
},
|
|
{
|
|
"entropy": 5.057636547088623,
|
|
"epoch": 3.243001786777844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039783192597394896,
|
|
"loss": 4.4516,
|
|
"mean_token_accuracy": 0.24242798686027528,
|
|
"num_tokens": 76093209.0,
|
|
"step": 27225
|
|
},
|
|
{
|
|
"entropy": 5.075426721572876,
|
|
"epoch": 3.2435973793924955,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039779622130890654,
|
|
"loss": 4.4761,
|
|
"mean_token_accuracy": 0.2382188394665718,
|
|
"num_tokens": 76107147.0,
|
|
"step": 27230
|
|
},
|
|
{
|
|
"entropy": 5.1361335754394535,
|
|
"epoch": 3.244192972007147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003977605122393632,
|
|
"loss": 4.5665,
|
|
"mean_token_accuracy": 0.2342412531375885,
|
|
"num_tokens": 76121000.0,
|
|
"step": 27235
|
|
},
|
|
{
|
|
"entropy": 5.024349784851074,
|
|
"epoch": 3.244788564621799,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003977247987665999,
|
|
"loss": 4.4143,
|
|
"mean_token_accuracy": 0.24617361575365065,
|
|
"num_tokens": 76134273.0,
|
|
"step": 27240
|
|
},
|
|
{
|
|
"entropy": 5.104458236694336,
|
|
"epoch": 3.24538415723645,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003976890808918977,
|
|
"loss": 4.5603,
|
|
"mean_token_accuracy": 0.24325620532035827,
|
|
"num_tokens": 76146632.0,
|
|
"step": 27245
|
|
},
|
|
{
|
|
"entropy": 5.1587871551513675,
|
|
"epoch": 3.245979749851102,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039765335861653754,
|
|
"loss": 4.6351,
|
|
"mean_token_accuracy": 0.2280718669295311,
|
|
"num_tokens": 76158870.0,
|
|
"step": 27250
|
|
},
|
|
{
|
|
"entropy": 5.141941547393799,
|
|
"epoch": 3.2465753424657535,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003976176319418009,
|
|
"loss": 4.507,
|
|
"mean_token_accuracy": 0.23744359165430068,
|
|
"num_tokens": 76171106.0,
|
|
"step": 27255
|
|
},
|
|
{
|
|
"entropy": 5.211701583862305,
|
|
"epoch": 3.2471709350804048,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003975819008689691,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.2274825632572174,
|
|
"num_tokens": 76186542.0,
|
|
"step": 27260
|
|
},
|
|
{
|
|
"entropy": 5.070684814453125,
|
|
"epoch": 3.2477665276950565,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039754616539932393,
|
|
"loss": 4.442,
|
|
"mean_token_accuracy": 0.2476442724466324,
|
|
"num_tokens": 76199652.0,
|
|
"step": 27265
|
|
},
|
|
{
|
|
"entropy": 5.166136693954468,
|
|
"epoch": 3.248362120309708,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039751042553414694,
|
|
"loss": 4.6006,
|
|
"mean_token_accuracy": 0.22913097441196442,
|
|
"num_tokens": 76213990.0,
|
|
"step": 27270
|
|
},
|
|
{
|
|
"entropy": 5.027128982543945,
|
|
"epoch": 3.24895771292436,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039747468127472027,
|
|
"loss": 4.4176,
|
|
"mean_token_accuracy": 0.25280712097883223,
|
|
"num_tokens": 76228430.0,
|
|
"step": 27275
|
|
},
|
|
{
|
|
"entropy": 5.1272398948669435,
|
|
"epoch": 3.249553305539011,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039743893262232584,
|
|
"loss": 4.4858,
|
|
"mean_token_accuracy": 0.25112402737140654,
|
|
"num_tokens": 76242666.0,
|
|
"step": 27280
|
|
},
|
|
{
|
|
"entropy": 5.123517990112305,
|
|
"epoch": 3.250148898153663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039740317957824594,
|
|
"loss": 4.5434,
|
|
"mean_token_accuracy": 0.2465282380580902,
|
|
"num_tokens": 76258765.0,
|
|
"step": 27285
|
|
},
|
|
{
|
|
"entropy": 5.149652338027954,
|
|
"epoch": 3.2507444907683145,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039736742214376307,
|
|
"loss": 4.5546,
|
|
"mean_token_accuracy": 0.23909692466259003,
|
|
"num_tokens": 76271167.0,
|
|
"step": 27290
|
|
},
|
|
{
|
|
"entropy": 5.069303321838379,
|
|
"epoch": 3.251340083382966,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003973316603201597,
|
|
"loss": 4.4647,
|
|
"mean_token_accuracy": 0.24104640036821365,
|
|
"num_tokens": 76287157.0,
|
|
"step": 27295
|
|
},
|
|
{
|
|
"entropy": 5.125746440887451,
|
|
"epoch": 3.2519356759976175,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039729589410871863,
|
|
"loss": 4.5368,
|
|
"mean_token_accuracy": 0.24099928438663482,
|
|
"num_tokens": 76300300.0,
|
|
"step": 27300
|
|
},
|
|
{
|
|
"entropy": 5.0660913467407225,
|
|
"epoch": 3.252531268612269,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003972601235107227,
|
|
"loss": 4.447,
|
|
"mean_token_accuracy": 0.24672755599021912,
|
|
"num_tokens": 76312133.0,
|
|
"step": 27305
|
|
},
|
|
{
|
|
"entropy": 5.125822830200195,
|
|
"epoch": 3.253126861226921,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003972243485274548,
|
|
"loss": 4.5136,
|
|
"mean_token_accuracy": 0.23734577298164367,
|
|
"num_tokens": 76325546.0,
|
|
"step": 27310
|
|
},
|
|
{
|
|
"entropy": 5.149034023284912,
|
|
"epoch": 3.2537224538415725,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003971885691601983,
|
|
"loss": 4.5849,
|
|
"mean_token_accuracy": 0.2365715116262436,
|
|
"num_tokens": 76338514.0,
|
|
"step": 27315
|
|
},
|
|
{
|
|
"entropy": 5.134440803527832,
|
|
"epoch": 3.254318046456224,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003971527854102364,
|
|
"loss": 4.4967,
|
|
"mean_token_accuracy": 0.245215605199337,
|
|
"num_tokens": 76352975.0,
|
|
"step": 27320
|
|
},
|
|
{
|
|
"entropy": 5.173719644546509,
|
|
"epoch": 3.2549136390708755,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039711699727885285,
|
|
"loss": 4.5649,
|
|
"mean_token_accuracy": 0.2350692555308342,
|
|
"num_tokens": 76366224.0,
|
|
"step": 27325
|
|
},
|
|
{
|
|
"entropy": 5.022964906692505,
|
|
"epoch": 3.255509231685527,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003970812047673311,
|
|
"loss": 4.4125,
|
|
"mean_token_accuracy": 0.24865364134311677,
|
|
"num_tokens": 76380872.0,
|
|
"step": 27330
|
|
},
|
|
{
|
|
"entropy": 5.114365339279175,
|
|
"epoch": 3.256104824300179,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003970454078769551,
|
|
"loss": 4.5922,
|
|
"mean_token_accuracy": 0.23433122634887696,
|
|
"num_tokens": 76395414.0,
|
|
"step": 27335
|
|
},
|
|
{
|
|
"entropy": 5.097584772109985,
|
|
"epoch": 3.25670041691483,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039700960660900866,
|
|
"loss": 4.5066,
|
|
"mean_token_accuracy": 0.24045133590698242,
|
|
"num_tokens": 76407580.0,
|
|
"step": 27340
|
|
},
|
|
{
|
|
"entropy": 5.101235198974609,
|
|
"epoch": 3.257296009529482,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039697380096477596,
|
|
"loss": 4.5015,
|
|
"mean_token_accuracy": 0.24061799943447112,
|
|
"num_tokens": 76420848.0,
|
|
"step": 27345
|
|
},
|
|
{
|
|
"entropy": 5.031187582015991,
|
|
"epoch": 3.2578916021441335,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003969379909455414,
|
|
"loss": 4.433,
|
|
"mean_token_accuracy": 0.24432282149791718,
|
|
"num_tokens": 76434389.0,
|
|
"step": 27350
|
|
},
|
|
{
|
|
"entropy": 5.13803539276123,
|
|
"epoch": 3.258487194758785,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003969021765525894,
|
|
"loss": 4.5483,
|
|
"mean_token_accuracy": 0.23973507434129715,
|
|
"num_tokens": 76447763.0,
|
|
"step": 27355
|
|
},
|
|
{
|
|
"entropy": 5.166613912582397,
|
|
"epoch": 3.2590827873734365,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003968663577872045,
|
|
"loss": 4.5556,
|
|
"mean_token_accuracy": 0.23658806681632996,
|
|
"num_tokens": 76462628.0,
|
|
"step": 27360
|
|
},
|
|
{
|
|
"entropy": 5.129678058624267,
|
|
"epoch": 3.259678379988088,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003968305346506715,
|
|
"loss": 4.4519,
|
|
"mean_token_accuracy": 0.24578413516283035,
|
|
"num_tokens": 76475700.0,
|
|
"step": 27365
|
|
},
|
|
{
|
|
"entropy": 5.120663833618164,
|
|
"epoch": 3.26027397260274,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003967947071442753,
|
|
"loss": 4.5558,
|
|
"mean_token_accuracy": 0.23548314571380616,
|
|
"num_tokens": 76489457.0,
|
|
"step": 27370
|
|
},
|
|
{
|
|
"entropy": 5.0852783679962155,
|
|
"epoch": 3.260869565217391,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003967588752693009,
|
|
"loss": 4.511,
|
|
"mean_token_accuracy": 0.23807135373353958,
|
|
"num_tokens": 76504121.0,
|
|
"step": 27375
|
|
},
|
|
{
|
|
"entropy": 5.042781400680542,
|
|
"epoch": 3.261465157832043,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00039672303902703364,
|
|
"loss": 4.4442,
|
|
"mean_token_accuracy": 0.24827261120080948,
|
|
"num_tokens": 76517551.0,
|
|
"step": 27380
|
|
},
|
|
{
|
|
"entropy": 5.0323628902435305,
|
|
"epoch": 3.2620607504466945,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00039668719841875897,
|
|
"loss": 4.3974,
|
|
"mean_token_accuracy": 0.24623270183801652,
|
|
"num_tokens": 76531048.0,
|
|
"step": 27385
|
|
},
|
|
{
|
|
"entropy": 5.091189861297607,
|
|
"epoch": 3.262656343061346,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003966513534457623,
|
|
"loss": 4.4863,
|
|
"mean_token_accuracy": 0.23565113842487334,
|
|
"num_tokens": 76545491.0,
|
|
"step": 27390
|
|
},
|
|
{
|
|
"entropy": 5.052409648895264,
|
|
"epoch": 3.2632519356759975,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003966155041093293,
|
|
"loss": 4.465,
|
|
"mean_token_accuracy": 0.24309097230434418,
|
|
"num_tokens": 76558233.0,
|
|
"step": 27395
|
|
},
|
|
{
|
|
"entropy": 5.190199565887451,
|
|
"epoch": 3.263847528290649,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003965796504107461,
|
|
"loss": 4.592,
|
|
"mean_token_accuracy": 0.22892833948135377,
|
|
"num_tokens": 76572533.0,
|
|
"step": 27400
|
|
},
|
|
{
|
|
"entropy": 5.178822374343872,
|
|
"epoch": 3.264443120905301,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039654379235129836,
|
|
"loss": 4.6193,
|
|
"mean_token_accuracy": 0.23198460787534714,
|
|
"num_tokens": 76585229.0,
|
|
"step": 27405
|
|
},
|
|
{
|
|
"entropy": 5.15104455947876,
|
|
"epoch": 3.265038713519952,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039650792993227245,
|
|
"loss": 4.5716,
|
|
"mean_token_accuracy": 0.23479875922203064,
|
|
"num_tokens": 76598329.0,
|
|
"step": 27410
|
|
},
|
|
{
|
|
"entropy": 5.138138103485107,
|
|
"epoch": 3.265634306134604,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003964720631549546,
|
|
"loss": 4.5051,
|
|
"mean_token_accuracy": 0.24617604166269302,
|
|
"num_tokens": 76611197.0,
|
|
"step": 27415
|
|
},
|
|
{
|
|
"entropy": 5.054212522506714,
|
|
"epoch": 3.2662298987492555,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003964361920206314,
|
|
"loss": 4.4623,
|
|
"mean_token_accuracy": 0.24005146920681,
|
|
"num_tokens": 76624533.0,
|
|
"step": 27420
|
|
},
|
|
{
|
|
"entropy": 5.140074300765991,
|
|
"epoch": 3.266825491363907,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003964003165305894,
|
|
"loss": 4.6176,
|
|
"mean_token_accuracy": 0.23187369257211685,
|
|
"num_tokens": 76637716.0,
|
|
"step": 27425
|
|
},
|
|
{
|
|
"entropy": 5.164914083480835,
|
|
"epoch": 3.267421083978559,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003963644366861155,
|
|
"loss": 4.573,
|
|
"mean_token_accuracy": 0.23356015384197235,
|
|
"num_tokens": 76652150.0,
|
|
"step": 27430
|
|
},
|
|
{
|
|
"entropy": 5.117228412628174,
|
|
"epoch": 3.26801667659321,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003963285524884964,
|
|
"loss": 4.5013,
|
|
"mean_token_accuracy": 0.2445700317621231,
|
|
"num_tokens": 76664719.0,
|
|
"step": 27435
|
|
},
|
|
{
|
|
"entropy": 5.075574922561645,
|
|
"epoch": 3.268612269207862,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003962926639390196,
|
|
"loss": 4.5037,
|
|
"mean_token_accuracy": 0.2478550598025322,
|
|
"num_tokens": 76679080.0,
|
|
"step": 27440
|
|
},
|
|
{
|
|
"entropy": 5.059019470214844,
|
|
"epoch": 3.2692078618225136,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003962567710389721,
|
|
"loss": 4.4121,
|
|
"mean_token_accuracy": 0.24826320260763168,
|
|
"num_tokens": 76692507.0,
|
|
"step": 27445
|
|
},
|
|
{
|
|
"entropy": 5.058060598373413,
|
|
"epoch": 3.269803454437165,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003962208737896413,
|
|
"loss": 4.4516,
|
|
"mean_token_accuracy": 0.2462826743721962,
|
|
"num_tokens": 76705898.0,
|
|
"step": 27450
|
|
},
|
|
{
|
|
"entropy": 5.019668960571289,
|
|
"epoch": 3.2703990470518165,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039618497219231493,
|
|
"loss": 4.4102,
|
|
"mean_token_accuracy": 0.24669067263603212,
|
|
"num_tokens": 76719908.0,
|
|
"step": 27455
|
|
},
|
|
{
|
|
"entropy": 5.038879632949829,
|
|
"epoch": 3.270994639666468,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003961490662482806,
|
|
"loss": 4.4811,
|
|
"mean_token_accuracy": 0.24065375030040742,
|
|
"num_tokens": 76734839.0,
|
|
"step": 27460
|
|
},
|
|
{
|
|
"entropy": 5.068078327178955,
|
|
"epoch": 3.27159023228112,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003961131559588263,
|
|
"loss": 4.4812,
|
|
"mean_token_accuracy": 0.245675228536129,
|
|
"num_tokens": 76748189.0,
|
|
"step": 27465
|
|
},
|
|
{
|
|
"entropy": 5.067411231994629,
|
|
"epoch": 3.272185824895771,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003960772413252399,
|
|
"loss": 4.4487,
|
|
"mean_token_accuracy": 0.24803245961666107,
|
|
"num_tokens": 76762830.0,
|
|
"step": 27470
|
|
},
|
|
{
|
|
"entropy": 5.089552736282348,
|
|
"epoch": 3.272781417510423,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039604132234880983,
|
|
"loss": 4.4807,
|
|
"mean_token_accuracy": 0.2418666034936905,
|
|
"num_tokens": 76776506.0,
|
|
"step": 27475
|
|
},
|
|
{
|
|
"entropy": 5.10785551071167,
|
|
"epoch": 3.2733770101250745,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003960053990308243,
|
|
"loss": 4.4354,
|
|
"mean_token_accuracy": 0.245883746445179,
|
|
"num_tokens": 76790195.0,
|
|
"step": 27480
|
|
},
|
|
{
|
|
"entropy": 5.055846643447876,
|
|
"epoch": 3.2739726027397262,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039596947137257176,
|
|
"loss": 4.4125,
|
|
"mean_token_accuracy": 0.25129377841949463,
|
|
"num_tokens": 76805269.0,
|
|
"step": 27485
|
|
},
|
|
{
|
|
"entropy": 5.056072425842285,
|
|
"epoch": 3.2745681953543775,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003959335393753411,
|
|
"loss": 4.4296,
|
|
"mean_token_accuracy": 0.24504080414772034,
|
|
"num_tokens": 76819680.0,
|
|
"step": 27490
|
|
},
|
|
{
|
|
"entropy": 5.070244789123535,
|
|
"epoch": 3.275163787969029,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003958976030404209,
|
|
"loss": 4.4984,
|
|
"mean_token_accuracy": 0.2357587993144989,
|
|
"num_tokens": 76835983.0,
|
|
"step": 27495
|
|
},
|
|
{
|
|
"entropy": 5.129720306396484,
|
|
"epoch": 3.275759380583681,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039586166236910033,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.23663714677095413,
|
|
"num_tokens": 76849992.0,
|
|
"step": 27500
|
|
},
|
|
{
|
|
"entropy": 5.104657411575317,
|
|
"epoch": 3.276354973198332,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003958257173626684,
|
|
"loss": 4.5303,
|
|
"mean_token_accuracy": 0.24228756874799728,
|
|
"num_tokens": 76863990.0,
|
|
"step": 27505
|
|
},
|
|
{
|
|
"entropy": 5.1302837371826175,
|
|
"epoch": 3.276950565812984,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003957897680224144,
|
|
"loss": 4.5488,
|
|
"mean_token_accuracy": 0.23923708647489547,
|
|
"num_tokens": 76876383.0,
|
|
"step": 27510
|
|
},
|
|
{
|
|
"entropy": 5.074910306930542,
|
|
"epoch": 3.2775461584276355,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039575381434962787,
|
|
"loss": 4.431,
|
|
"mean_token_accuracy": 0.2495240479707718,
|
|
"num_tokens": 76890462.0,
|
|
"step": 27515
|
|
},
|
|
{
|
|
"entropy": 5.126620244979859,
|
|
"epoch": 3.278141751042287,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003957178563455983,
|
|
"loss": 4.5595,
|
|
"mean_token_accuracy": 0.241258342564106,
|
|
"num_tokens": 76903321.0,
|
|
"step": 27520
|
|
},
|
|
{
|
|
"entropy": 5.101594161987305,
|
|
"epoch": 3.2787373436569385,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003956818940116156,
|
|
"loss": 4.4746,
|
|
"mean_token_accuracy": 0.24885317385196687,
|
|
"num_tokens": 76915839.0,
|
|
"step": 27525
|
|
},
|
|
{
|
|
"entropy": 5.149973773956299,
|
|
"epoch": 3.27933293627159,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039564592734896945,
|
|
"loss": 4.5344,
|
|
"mean_token_accuracy": 0.24608805328607558,
|
|
"num_tokens": 76930302.0,
|
|
"step": 27530
|
|
},
|
|
{
|
|
"entropy": 5.037738847732544,
|
|
"epoch": 3.279928528886242,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003956099563589501,
|
|
"loss": 4.4732,
|
|
"mean_token_accuracy": 0.2506385952234268,
|
|
"num_tokens": 76944114.0,
|
|
"step": 27535
|
|
},
|
|
{
|
|
"entropy": 5.022286081314087,
|
|
"epoch": 3.2805241215008936,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003955739810428477,
|
|
"loss": 4.4299,
|
|
"mean_token_accuracy": 0.24394643902778626,
|
|
"num_tokens": 76958741.0,
|
|
"step": 27540
|
|
},
|
|
{
|
|
"entropy": 5.094385385513306,
|
|
"epoch": 3.281119714115545,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039553800140195274,
|
|
"loss": 4.5363,
|
|
"mean_token_accuracy": 0.23778407871723176,
|
|
"num_tokens": 76973259.0,
|
|
"step": 27545
|
|
},
|
|
{
|
|
"entropy": 5.1121245384216305,
|
|
"epoch": 3.2817153067301965,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039550201743755557,
|
|
"loss": 4.4686,
|
|
"mean_token_accuracy": 0.24732817858457565,
|
|
"num_tokens": 76985829.0,
|
|
"step": 27550
|
|
},
|
|
{
|
|
"entropy": 5.136034107208252,
|
|
"epoch": 3.282310899344848,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003954660291509469,
|
|
"loss": 4.5413,
|
|
"mean_token_accuracy": 0.24177091270685197,
|
|
"num_tokens": 77002044.0,
|
|
"step": 27555
|
|
},
|
|
{
|
|
"entropy": 5.031141376495361,
|
|
"epoch": 3.2829064919594995,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039543003654341776,
|
|
"loss": 4.4353,
|
|
"mean_token_accuracy": 0.24678076356649398,
|
|
"num_tokens": 77015468.0,
|
|
"step": 27560
|
|
},
|
|
{
|
|
"entropy": 5.0803954124450685,
|
|
"epoch": 3.283502084574151,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003953940396162589,
|
|
"loss": 4.4841,
|
|
"mean_token_accuracy": 0.24327076673507692,
|
|
"num_tokens": 77029876.0,
|
|
"step": 27565
|
|
},
|
|
{
|
|
"entropy": 5.117980480194092,
|
|
"epoch": 3.284097677188803,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039535803837076165,
|
|
"loss": 4.4796,
|
|
"mean_token_accuracy": 0.24247294217348098,
|
|
"num_tokens": 77045126.0,
|
|
"step": 27570
|
|
},
|
|
{
|
|
"entropy": 5.144092655181884,
|
|
"epoch": 3.2846932698034546,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003953220328082172,
|
|
"loss": 4.5563,
|
|
"mean_token_accuracy": 0.23807298094034196,
|
|
"num_tokens": 77059432.0,
|
|
"step": 27575
|
|
},
|
|
{
|
|
"entropy": 5.148646020889283,
|
|
"epoch": 3.2852888624181062,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039528602292991714,
|
|
"loss": 4.5031,
|
|
"mean_token_accuracy": 0.24089484065771102,
|
|
"num_tokens": 77072671.0,
|
|
"step": 27580
|
|
},
|
|
{
|
|
"entropy": 5.115417051315307,
|
|
"epoch": 3.2858844550327575,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000395250008737153,
|
|
"loss": 4.5426,
|
|
"mean_token_accuracy": 0.23754313141107558,
|
|
"num_tokens": 77086641.0,
|
|
"step": 27585
|
|
},
|
|
{
|
|
"entropy": 5.057784748077393,
|
|
"epoch": 3.286480047647409,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003952139902312165,
|
|
"loss": 4.4045,
|
|
"mean_token_accuracy": 0.25628594756126405,
|
|
"num_tokens": 77100933.0,
|
|
"step": 27590
|
|
},
|
|
{
|
|
"entropy": 5.03053913116455,
|
|
"epoch": 3.287075640262061,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003951779674133997,
|
|
"loss": 4.4141,
|
|
"mean_token_accuracy": 0.24806714057922363,
|
|
"num_tokens": 77116538.0,
|
|
"step": 27595
|
|
},
|
|
{
|
|
"entropy": 5.067913436889649,
|
|
"epoch": 3.287671232876712,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039514194028499456,
|
|
"loss": 4.4578,
|
|
"mean_token_accuracy": 0.24087181091308593,
|
|
"num_tokens": 77129831.0,
|
|
"step": 27600
|
|
},
|
|
{
|
|
"entropy": 5.129939556121826,
|
|
"epoch": 3.288266825491364,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003951059088472934,
|
|
"loss": 4.5721,
|
|
"mean_token_accuracy": 0.2386971339583397,
|
|
"num_tokens": 77144633.0,
|
|
"step": 27605
|
|
},
|
|
{
|
|
"entropy": 5.071404075622558,
|
|
"epoch": 3.2888624181060155,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039506987310158854,
|
|
"loss": 4.5192,
|
|
"mean_token_accuracy": 0.23866212815046312,
|
|
"num_tokens": 77159244.0,
|
|
"step": 27610
|
|
},
|
|
{
|
|
"entropy": 5.076464891433716,
|
|
"epoch": 3.2894580107206672,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039503383304917254,
|
|
"loss": 4.4333,
|
|
"mean_token_accuracy": 0.24582741856575013,
|
|
"num_tokens": 77173667.0,
|
|
"step": 27615
|
|
},
|
|
{
|
|
"entropy": 5.049593448638916,
|
|
"epoch": 3.2900536033353185,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003949977886913381,
|
|
"loss": 4.4796,
|
|
"mean_token_accuracy": 0.24581024199724197,
|
|
"num_tokens": 77187897.0,
|
|
"step": 27620
|
|
},
|
|
{
|
|
"entropy": 5.197428607940674,
|
|
"epoch": 3.29064919594997,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039496174002937815,
|
|
"loss": 4.5802,
|
|
"mean_token_accuracy": 0.24144141525030136,
|
|
"num_tokens": 77200786.0,
|
|
"step": 27625
|
|
},
|
|
{
|
|
"entropy": 5.077857780456543,
|
|
"epoch": 3.291244788564622,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003949256870645856,
|
|
"loss": 4.4875,
|
|
"mean_token_accuracy": 0.24342753738164902,
|
|
"num_tokens": 77215377.0,
|
|
"step": 27630
|
|
},
|
|
{
|
|
"entropy": 5.061850833892822,
|
|
"epoch": 3.2918403811792736,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003948896297982536,
|
|
"loss": 4.5052,
|
|
"mean_token_accuracy": 0.24431616365909575,
|
|
"num_tokens": 77229682.0,
|
|
"step": 27635
|
|
},
|
|
{
|
|
"entropy": 5.121480417251587,
|
|
"epoch": 3.292435973793925,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003948535682316755,
|
|
"loss": 4.5307,
|
|
"mean_token_accuracy": 0.2435721606016159,
|
|
"num_tokens": 77243929.0,
|
|
"step": 27640
|
|
},
|
|
{
|
|
"entropy": 5.176730918884277,
|
|
"epoch": 3.2930315664085765,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003948175023661449,
|
|
"loss": 4.5119,
|
|
"mean_token_accuracy": 0.24747075587511064,
|
|
"num_tokens": 77257642.0,
|
|
"step": 27645
|
|
},
|
|
{
|
|
"entropy": 5.071161079406738,
|
|
"epoch": 3.2936271590232282,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039478143220295526,
|
|
"loss": 4.4744,
|
|
"mean_token_accuracy": 0.24447097033262252,
|
|
"num_tokens": 77271755.0,
|
|
"step": 27650
|
|
},
|
|
{
|
|
"entropy": 5.116781949996948,
|
|
"epoch": 3.2942227516378795,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039474535774340034,
|
|
"loss": 4.5024,
|
|
"mean_token_accuracy": 0.24005704820156099,
|
|
"num_tokens": 77284756.0,
|
|
"step": 27655
|
|
},
|
|
{
|
|
"entropy": 5.121724271774292,
|
|
"epoch": 3.294818344252531,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003947092789887741,
|
|
"loss": 4.494,
|
|
"mean_token_accuracy": 0.24394149333238602,
|
|
"num_tokens": 77297713.0,
|
|
"step": 27660
|
|
},
|
|
{
|
|
"entropy": 5.15656886100769,
|
|
"epoch": 3.295413936867183,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039467319594037076,
|
|
"loss": 4.4832,
|
|
"mean_token_accuracy": 0.24785974621772766,
|
|
"num_tokens": 77311227.0,
|
|
"step": 27665
|
|
},
|
|
{
|
|
"entropy": 5.055635213851929,
|
|
"epoch": 3.2960095294818346,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039463710859948437,
|
|
"loss": 4.4471,
|
|
"mean_token_accuracy": 0.24843440651893617,
|
|
"num_tokens": 77323880.0,
|
|
"step": 27670
|
|
},
|
|
{
|
|
"entropy": 5.097371292114258,
|
|
"epoch": 3.296605122096486,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003946010169674095,
|
|
"loss": 4.5,
|
|
"mean_token_accuracy": 0.2457052618265152,
|
|
"num_tokens": 77337821.0,
|
|
"step": 27675
|
|
},
|
|
{
|
|
"entropy": 5.115740346908569,
|
|
"epoch": 3.2972007147111375,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039456492104544057,
|
|
"loss": 4.4873,
|
|
"mean_token_accuracy": 0.24333741515874863,
|
|
"num_tokens": 77352242.0,
|
|
"step": 27680
|
|
},
|
|
{
|
|
"entropy": 5.098741054534912,
|
|
"epoch": 3.297796307325789,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039452882083487224,
|
|
"loss": 4.5331,
|
|
"mean_token_accuracy": 0.24335598647594453,
|
|
"num_tokens": 77366235.0,
|
|
"step": 27685
|
|
},
|
|
{
|
|
"entropy": 5.092769956588745,
|
|
"epoch": 3.298391899940441,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039449271633699957,
|
|
"loss": 4.5008,
|
|
"mean_token_accuracy": 0.24581737518310548,
|
|
"num_tokens": 77380375.0,
|
|
"step": 27690
|
|
},
|
|
{
|
|
"entropy": 5.061756944656372,
|
|
"epoch": 3.298987492555092,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039445660755311736,
|
|
"loss": 4.4598,
|
|
"mean_token_accuracy": 0.2528499931097031,
|
|
"num_tokens": 77395273.0,
|
|
"step": 27695
|
|
},
|
|
{
|
|
"entropy": 5.0953339576721195,
|
|
"epoch": 3.299583085169744,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039442049448452096,
|
|
"loss": 4.4028,
|
|
"mean_token_accuracy": 0.2570137917995453,
|
|
"num_tokens": 77407593.0,
|
|
"step": 27700
|
|
},
|
|
{
|
|
"entropy": 5.02753791809082,
|
|
"epoch": 3.3001786777843956,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039438437713250547,
|
|
"loss": 4.4801,
|
|
"mean_token_accuracy": 0.2397022634744644,
|
|
"num_tokens": 77421792.0,
|
|
"step": 27705
|
|
},
|
|
{
|
|
"entropy": 5.11821436882019,
|
|
"epoch": 3.300774270399047,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039434825549836654,
|
|
"loss": 4.5083,
|
|
"mean_token_accuracy": 0.24787962585687637,
|
|
"num_tokens": 77434411.0,
|
|
"step": 27710
|
|
},
|
|
{
|
|
"entropy": 5.046762895584107,
|
|
"epoch": 3.3013698630136985,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003943121295833998,
|
|
"loss": 4.4301,
|
|
"mean_token_accuracy": 0.24806900918483735,
|
|
"num_tokens": 77447837.0,
|
|
"step": 27715
|
|
},
|
|
{
|
|
"entropy": 5.010302019119263,
|
|
"epoch": 3.30196545562835,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003942759993889009,
|
|
"loss": 4.4357,
|
|
"mean_token_accuracy": 0.2462290942668915,
|
|
"num_tokens": 77461150.0,
|
|
"step": 27720
|
|
},
|
|
{
|
|
"entropy": 4.989225292205811,
|
|
"epoch": 3.302561048243002,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039423986491616576,
|
|
"loss": 4.3931,
|
|
"mean_token_accuracy": 0.24525263756513596,
|
|
"num_tokens": 77476872.0,
|
|
"step": 27725
|
|
},
|
|
{
|
|
"entropy": 5.006634855270386,
|
|
"epoch": 3.3031566408576536,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003942037261664906,
|
|
"loss": 4.44,
|
|
"mean_token_accuracy": 0.2455247849225998,
|
|
"num_tokens": 77489742.0,
|
|
"step": 27730
|
|
},
|
|
{
|
|
"entropy": 5.125901365280152,
|
|
"epoch": 3.303752233472305,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003941675831411717,
|
|
"loss": 4.4985,
|
|
"mean_token_accuracy": 0.24604583233594896,
|
|
"num_tokens": 77503382.0,
|
|
"step": 27735
|
|
},
|
|
{
|
|
"entropy": 5.142478990554809,
|
|
"epoch": 3.3043478260869565,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039413143584150523,
|
|
"loss": 4.5373,
|
|
"mean_token_accuracy": 0.24421588331460953,
|
|
"num_tokens": 77516549.0,
|
|
"step": 27740
|
|
},
|
|
{
|
|
"entropy": 5.111745929718017,
|
|
"epoch": 3.3049434187016082,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003940952842687879,
|
|
"loss": 4.5246,
|
|
"mean_token_accuracy": 0.24245693385601044,
|
|
"num_tokens": 77530160.0,
|
|
"step": 27745
|
|
},
|
|
{
|
|
"entropy": 5.095084762573242,
|
|
"epoch": 3.3055390113162595,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003940591284243163,
|
|
"loss": 4.4459,
|
|
"mean_token_accuracy": 0.24712535738945007,
|
|
"num_tokens": 77544707.0,
|
|
"step": 27750
|
|
},
|
|
{
|
|
"entropy": 5.054268217086792,
|
|
"epoch": 3.306134603930911,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003940229683093874,
|
|
"loss": 4.4925,
|
|
"mean_token_accuracy": 0.24319506138563157,
|
|
"num_tokens": 77559222.0,
|
|
"step": 27755
|
|
},
|
|
{
|
|
"entropy": 5.0345237255096436,
|
|
"epoch": 3.306730196545563,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039398680392529805,
|
|
"loss": 4.4104,
|
|
"mean_token_accuracy": 0.2544391691684723,
|
|
"num_tokens": 77573563.0,
|
|
"step": 27760
|
|
},
|
|
{
|
|
"entropy": 5.144483375549316,
|
|
"epoch": 3.3073257891602146,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003939506352733456,
|
|
"loss": 4.567,
|
|
"mean_token_accuracy": 0.23876275569200517,
|
|
"num_tokens": 77589026.0,
|
|
"step": 27765
|
|
},
|
|
{
|
|
"entropy": 5.091957712173462,
|
|
"epoch": 3.307921381774866,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003939144623548273,
|
|
"loss": 4.4653,
|
|
"mean_token_accuracy": 0.24474598318338395,
|
|
"num_tokens": 77602471.0,
|
|
"step": 27770
|
|
},
|
|
{
|
|
"entropy": 5.113088321685791,
|
|
"epoch": 3.3085169743895175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039387828517104044,
|
|
"loss": 4.5417,
|
|
"mean_token_accuracy": 0.2401082694530487,
|
|
"num_tokens": 77615762.0,
|
|
"step": 27775
|
|
},
|
|
{
|
|
"entropy": 5.062425327301026,
|
|
"epoch": 3.3091125670041692,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003938421037232828,
|
|
"loss": 4.5143,
|
|
"mean_token_accuracy": 0.23869857043027878,
|
|
"num_tokens": 77629409.0,
|
|
"step": 27780
|
|
},
|
|
{
|
|
"entropy": 5.005145168304443,
|
|
"epoch": 3.309708159618821,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00039380591801285226,
|
|
"loss": 4.368,
|
|
"mean_token_accuracy": 0.25610421746969225,
|
|
"num_tokens": 77642576.0,
|
|
"step": 27785
|
|
},
|
|
{
|
|
"entropy": 5.089850950241089,
|
|
"epoch": 3.310303752233472,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039376972804104653,
|
|
"loss": 4.5059,
|
|
"mean_token_accuracy": 0.23680735677480697,
|
|
"num_tokens": 77656636.0,
|
|
"step": 27790
|
|
},
|
|
{
|
|
"entropy": 5.099330949783325,
|
|
"epoch": 3.310899344848124,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039373353380916376,
|
|
"loss": 4.5461,
|
|
"mean_token_accuracy": 0.23777266591787338,
|
|
"num_tokens": 77669879.0,
|
|
"step": 27795
|
|
},
|
|
{
|
|
"entropy": 5.073505592346192,
|
|
"epoch": 3.3114949374627756,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003936973353185022,
|
|
"loss": 4.537,
|
|
"mean_token_accuracy": 0.23779823035001754,
|
|
"num_tokens": 77682946.0,
|
|
"step": 27800
|
|
},
|
|
{
|
|
"entropy": 5.116344404220581,
|
|
"epoch": 3.312090530077427,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003936611325703602,
|
|
"loss": 4.4887,
|
|
"mean_token_accuracy": 0.24300253242254258,
|
|
"num_tokens": 77697315.0,
|
|
"step": 27805
|
|
},
|
|
{
|
|
"entropy": 5.21721830368042,
|
|
"epoch": 3.3126861226920785,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003936249255660363,
|
|
"loss": 4.6805,
|
|
"mean_token_accuracy": 0.23029879331588746,
|
|
"num_tokens": 77714083.0,
|
|
"step": 27810
|
|
},
|
|
{
|
|
"entropy": 5.053851652145386,
|
|
"epoch": 3.31328171530673,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003935887143068292,
|
|
"loss": 4.4303,
|
|
"mean_token_accuracy": 0.24702661037445067,
|
|
"num_tokens": 77726747.0,
|
|
"step": 27815
|
|
},
|
|
{
|
|
"entropy": 5.117301797866821,
|
|
"epoch": 3.313877307921382,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003935524987940376,
|
|
"loss": 4.5396,
|
|
"mean_token_accuracy": 0.24038249701261521,
|
|
"num_tokens": 77741913.0,
|
|
"step": 27820
|
|
},
|
|
{
|
|
"entropy": 5.052055835723877,
|
|
"epoch": 3.314472900536033,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003935162790289608,
|
|
"loss": 4.4617,
|
|
"mean_token_accuracy": 0.24982229471206666,
|
|
"num_tokens": 77755525.0,
|
|
"step": 27825
|
|
},
|
|
{
|
|
"entropy": 5.142538785934448,
|
|
"epoch": 3.315068493150685,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039348005501289775,
|
|
"loss": 4.5652,
|
|
"mean_token_accuracy": 0.23209089189767837,
|
|
"num_tokens": 77768428.0,
|
|
"step": 27830
|
|
},
|
|
{
|
|
"entropy": 5.109865760803222,
|
|
"epoch": 3.3156640857653366,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039344382674714773,
|
|
"loss": 4.5538,
|
|
"mean_token_accuracy": 0.24101058691740035,
|
|
"num_tokens": 77783573.0,
|
|
"step": 27835
|
|
},
|
|
{
|
|
"entropy": 5.145439720153808,
|
|
"epoch": 3.3162596783799883,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039340759423301026,
|
|
"loss": 4.4994,
|
|
"mean_token_accuracy": 0.23746402114629744,
|
|
"num_tokens": 77798421.0,
|
|
"step": 27840
|
|
},
|
|
{
|
|
"entropy": 5.172737979888916,
|
|
"epoch": 3.3168552709946395,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039337135747178476,
|
|
"loss": 4.5164,
|
|
"mean_token_accuracy": 0.23878449499607085,
|
|
"num_tokens": 77813326.0,
|
|
"step": 27845
|
|
},
|
|
{
|
|
"entropy": 5.1107930660247805,
|
|
"epoch": 3.317450863609291,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003933351164647713,
|
|
"loss": 4.5505,
|
|
"mean_token_accuracy": 0.24235944151878358,
|
|
"num_tokens": 77826978.0,
|
|
"step": 27850
|
|
},
|
|
{
|
|
"entropy": 5.142667055130005,
|
|
"epoch": 3.318046456223943,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003932988712132696,
|
|
"loss": 4.5295,
|
|
"mean_token_accuracy": 0.24388284981250763,
|
|
"num_tokens": 77839929.0,
|
|
"step": 27855
|
|
},
|
|
{
|
|
"entropy": 5.150486087799072,
|
|
"epoch": 3.3186420488385946,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039326262171857963,
|
|
"loss": 4.5263,
|
|
"mean_token_accuracy": 0.24718328565359116,
|
|
"num_tokens": 77853898.0,
|
|
"step": 27860
|
|
},
|
|
{
|
|
"entropy": 5.1173783302307125,
|
|
"epoch": 3.319237641453246,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00039322636798200174,
|
|
"loss": 4.5067,
|
|
"mean_token_accuracy": 0.24212231040000914,
|
|
"num_tokens": 77869290.0,
|
|
"step": 27865
|
|
},
|
|
{
|
|
"entropy": 5.156852197647095,
|
|
"epoch": 3.3198332340678975,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00039319011000483615,
|
|
"loss": 4.6188,
|
|
"mean_token_accuracy": 0.23791223913431167,
|
|
"num_tokens": 77885088.0,
|
|
"step": 27870
|
|
},
|
|
{
|
|
"entropy": 5.04326024055481,
|
|
"epoch": 3.3204288266825492,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039315384778838364,
|
|
"loss": 4.4367,
|
|
"mean_token_accuracy": 0.2432457372546196,
|
|
"num_tokens": 77898602.0,
|
|
"step": 27875
|
|
},
|
|
{
|
|
"entropy": 5.123322868347168,
|
|
"epoch": 3.321024419297201,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003931175813339447,
|
|
"loss": 4.4577,
|
|
"mean_token_accuracy": 0.2476427286863327,
|
|
"num_tokens": 77913149.0,
|
|
"step": 27880
|
|
},
|
|
{
|
|
"entropy": 5.091319513320923,
|
|
"epoch": 3.321620011911852,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039308131064282016,
|
|
"loss": 4.5503,
|
|
"mean_token_accuracy": 0.24033679068088531,
|
|
"num_tokens": 77927241.0,
|
|
"step": 27885
|
|
},
|
|
{
|
|
"entropy": 5.115565538406372,
|
|
"epoch": 3.322215604526504,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039304503571631095,
|
|
"loss": 4.5274,
|
|
"mean_token_accuracy": 0.24084036499261857,
|
|
"num_tokens": 77940035.0,
|
|
"step": 27890
|
|
},
|
|
{
|
|
"entropy": 5.009241819381714,
|
|
"epoch": 3.3228111971411556,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003930087565557183,
|
|
"loss": 4.3883,
|
|
"mean_token_accuracy": 0.24921703487634658,
|
|
"num_tokens": 77954960.0,
|
|
"step": 27895
|
|
},
|
|
{
|
|
"entropy": 5.158750009536743,
|
|
"epoch": 3.323406789755807,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039297247316234335,
|
|
"loss": 4.6258,
|
|
"mean_token_accuracy": 0.23538641929626464,
|
|
"num_tokens": 77968188.0,
|
|
"step": 27900
|
|
},
|
|
{
|
|
"entropy": 5.039299869537354,
|
|
"epoch": 3.3240023823704585,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003929361855374876,
|
|
"loss": 4.4538,
|
|
"mean_token_accuracy": 0.24853141158819197,
|
|
"num_tokens": 77983630.0,
|
|
"step": 27905
|
|
},
|
|
{
|
|
"entropy": 5.060484886169434,
|
|
"epoch": 3.3245979749851102,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039289989368245263,
|
|
"loss": 4.5262,
|
|
"mean_token_accuracy": 0.24088250547647477,
|
|
"num_tokens": 77998798.0,
|
|
"step": 27910
|
|
},
|
|
{
|
|
"entropy": 5.180576467514038,
|
|
"epoch": 3.325193567599762,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039286359759854023,
|
|
"loss": 4.5689,
|
|
"mean_token_accuracy": 0.23873756676912308,
|
|
"num_tokens": 78012600.0,
|
|
"step": 27915
|
|
},
|
|
{
|
|
"entropy": 5.191676092147827,
|
|
"epoch": 3.325789160214413,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003928272972870522,
|
|
"loss": 4.6123,
|
|
"mean_token_accuracy": 0.22950943410396576,
|
|
"num_tokens": 78028758.0,
|
|
"step": 27920
|
|
},
|
|
{
|
|
"entropy": 5.11490912437439,
|
|
"epoch": 3.326384752829065,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003927909927492906,
|
|
"loss": 4.5344,
|
|
"mean_token_accuracy": 0.23741752952337264,
|
|
"num_tokens": 78041100.0,
|
|
"step": 27925
|
|
},
|
|
{
|
|
"entropy": 5.189503383636475,
|
|
"epoch": 3.3269803454437166,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003927546839865576,
|
|
"loss": 4.6078,
|
|
"mean_token_accuracy": 0.23406755477190017,
|
|
"num_tokens": 78054016.0,
|
|
"step": 27930
|
|
},
|
|
{
|
|
"entropy": 5.0851071834564205,
|
|
"epoch": 3.3275759380583683,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003927183710001555,
|
|
"loss": 4.4504,
|
|
"mean_token_accuracy": 0.24430674612522124,
|
|
"num_tokens": 78067280.0,
|
|
"step": 27935
|
|
},
|
|
{
|
|
"entropy": 5.060009622573853,
|
|
"epoch": 3.3281715306730195,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003926820537913868,
|
|
"loss": 4.4932,
|
|
"mean_token_accuracy": 0.24523846060037613,
|
|
"num_tokens": 78080821.0,
|
|
"step": 27940
|
|
},
|
|
{
|
|
"entropy": 5.106815385818481,
|
|
"epoch": 3.328767123287671,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003926457323615543,
|
|
"loss": 4.4948,
|
|
"mean_token_accuracy": 0.24073273688554764,
|
|
"num_tokens": 78094020.0,
|
|
"step": 27945
|
|
},
|
|
{
|
|
"entropy": 5.106487894058228,
|
|
"epoch": 3.329362715902323,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003926094067119605,
|
|
"loss": 4.4787,
|
|
"mean_token_accuracy": 0.24655895084142684,
|
|
"num_tokens": 78107696.0,
|
|
"step": 27950
|
|
},
|
|
{
|
|
"entropy": 5.08908257484436,
|
|
"epoch": 3.329958308516974,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003925730768439086,
|
|
"loss": 4.4543,
|
|
"mean_token_accuracy": 0.2436939612030983,
|
|
"num_tokens": 78122295.0,
|
|
"step": 27955
|
|
},
|
|
{
|
|
"entropy": 5.094215345382691,
|
|
"epoch": 3.330553901131626,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003925367427587016,
|
|
"loss": 4.4415,
|
|
"mean_token_accuracy": 0.2458454579114914,
|
|
"num_tokens": 78135942.0,
|
|
"step": 27960
|
|
},
|
|
{
|
|
"entropy": 5.156821298599243,
|
|
"epoch": 3.3311494937462776,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003925004044576428,
|
|
"loss": 4.4919,
|
|
"mean_token_accuracy": 0.23885400891304015,
|
|
"num_tokens": 78150821.0,
|
|
"step": 27965
|
|
},
|
|
{
|
|
"entropy": 5.085904169082641,
|
|
"epoch": 3.3317450863609293,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039246406194203535,
|
|
"loss": 4.5492,
|
|
"mean_token_accuracy": 0.23502152413129807,
|
|
"num_tokens": 78167196.0,
|
|
"step": 27970
|
|
},
|
|
{
|
|
"entropy": 5.1339257717132565,
|
|
"epoch": 3.332340678975581,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039242771521318315,
|
|
"loss": 4.5122,
|
|
"mean_token_accuracy": 0.23873550146818162,
|
|
"num_tokens": 78181128.0,
|
|
"step": 27975
|
|
},
|
|
{
|
|
"entropy": 5.190422677993775,
|
|
"epoch": 3.332936271590232,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039239136427238967,
|
|
"loss": 4.5717,
|
|
"mean_token_accuracy": 0.23534732758998872,
|
|
"num_tokens": 78195097.0,
|
|
"step": 27980
|
|
},
|
|
{
|
|
"entropy": 5.136201190948486,
|
|
"epoch": 3.333531864204884,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039235500912095886,
|
|
"loss": 4.5298,
|
|
"mean_token_accuracy": 0.24136935025453568,
|
|
"num_tokens": 78208806.0,
|
|
"step": 27985
|
|
},
|
|
{
|
|
"entropy": 5.007053804397583,
|
|
"epoch": 3.3341274568195356,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039231864976019466,
|
|
"loss": 4.4091,
|
|
"mean_token_accuracy": 0.25212022960186004,
|
|
"num_tokens": 78223512.0,
|
|
"step": 27990
|
|
},
|
|
{
|
|
"entropy": 5.120873975753784,
|
|
"epoch": 3.334723049434187,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003922822861914012,
|
|
"loss": 4.5701,
|
|
"mean_token_accuracy": 0.24401963502168655,
|
|
"num_tokens": 78236031.0,
|
|
"step": 27995
|
|
},
|
|
{
|
|
"entropy": 5.056884765625,
|
|
"epoch": 3.3353186420488385,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003922459184158828,
|
|
"loss": 4.497,
|
|
"mean_token_accuracy": 0.24897898584604264,
|
|
"num_tokens": 78249756.0,
|
|
"step": 28000
|
|
},
|
|
{
|
|
"entropy": 5.141752767562866,
|
|
"epoch": 3.3359142346634902,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000392209546434944,
|
|
"loss": 4.5601,
|
|
"mean_token_accuracy": 0.23600289225578308,
|
|
"num_tokens": 78263211.0,
|
|
"step": 28005
|
|
},
|
|
{
|
|
"entropy": 5.109559392929077,
|
|
"epoch": 3.336509827278142,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003921731702498893,
|
|
"loss": 4.474,
|
|
"mean_token_accuracy": 0.24665291160345076,
|
|
"num_tokens": 78277084.0,
|
|
"step": 28010
|
|
},
|
|
{
|
|
"entropy": 5.128905630111694,
|
|
"epoch": 3.337105419892793,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039213678986202357,
|
|
"loss": 4.4975,
|
|
"mean_token_accuracy": 0.24110221415758132,
|
|
"num_tokens": 78290017.0,
|
|
"step": 28015
|
|
},
|
|
{
|
|
"entropy": 5.127799081802368,
|
|
"epoch": 3.337701012507445,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039210040527265164,
|
|
"loss": 4.5149,
|
|
"mean_token_accuracy": 0.2441351518034935,
|
|
"num_tokens": 78302512.0,
|
|
"step": 28020
|
|
},
|
|
{
|
|
"entropy": 5.122059774398804,
|
|
"epoch": 3.3382966051220966,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003920640164830785,
|
|
"loss": 4.5089,
|
|
"mean_token_accuracy": 0.24071864038705826,
|
|
"num_tokens": 78316243.0,
|
|
"step": 28025
|
|
},
|
|
{
|
|
"entropy": 5.076163101196289,
|
|
"epoch": 3.3388921977367483,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039202762349460933,
|
|
"loss": 4.5012,
|
|
"mean_token_accuracy": 0.24384398013353348,
|
|
"num_tokens": 78330077.0,
|
|
"step": 28030
|
|
},
|
|
{
|
|
"entropy": 5.111075830459595,
|
|
"epoch": 3.3394877903513995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039199122630854976,
|
|
"loss": 4.5519,
|
|
"mean_token_accuracy": 0.23910851776599884,
|
|
"num_tokens": 78346006.0,
|
|
"step": 28035
|
|
},
|
|
{
|
|
"entropy": 5.085481786727906,
|
|
"epoch": 3.3400833829660512,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039195482492620506,
|
|
"loss": 4.4793,
|
|
"mean_token_accuracy": 0.24062319844961166,
|
|
"num_tokens": 78360911.0,
|
|
"step": 28040
|
|
},
|
|
{
|
|
"entropy": 5.110004568099976,
|
|
"epoch": 3.340678975580703,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003919184193488809,
|
|
"loss": 4.4968,
|
|
"mean_token_accuracy": 0.24661415815353394,
|
|
"num_tokens": 78374339.0,
|
|
"step": 28045
|
|
},
|
|
{
|
|
"entropy": 5.109010553359985,
|
|
"epoch": 3.341274568195354,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003918820095778832,
|
|
"loss": 4.4371,
|
|
"mean_token_accuracy": 0.2445622965693474,
|
|
"num_tokens": 78388284.0,
|
|
"step": 28050
|
|
},
|
|
{
|
|
"entropy": 5.014727592468262,
|
|
"epoch": 3.341870160810006,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003918455956145178,
|
|
"loss": 4.479,
|
|
"mean_token_accuracy": 0.24622001349925995,
|
|
"num_tokens": 78401448.0,
|
|
"step": 28055
|
|
},
|
|
{
|
|
"entropy": 5.068795824050904,
|
|
"epoch": 3.3424657534246576,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039180917746009085,
|
|
"loss": 4.4706,
|
|
"mean_token_accuracy": 0.24411203265190123,
|
|
"num_tokens": 78415719.0,
|
|
"step": 28060
|
|
},
|
|
{
|
|
"entropy": 5.09240198135376,
|
|
"epoch": 3.3430613460393093,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0003917727551159087,
|
|
"loss": 4.4654,
|
|
"mean_token_accuracy": 0.2465624064207077,
|
|
"num_tokens": 78429671.0,
|
|
"step": 28065
|
|
},
|
|
{
|
|
"entropy": 5.029927062988281,
|
|
"epoch": 3.3436569386539605,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003917363285832777,
|
|
"loss": 4.4956,
|
|
"mean_token_accuracy": 0.25179257690906526,
|
|
"num_tokens": 78443113.0,
|
|
"step": 28070
|
|
},
|
|
{
|
|
"entropy": 5.119073057174683,
|
|
"epoch": 3.344252531268612,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003916998978635044,
|
|
"loss": 4.5237,
|
|
"mean_token_accuracy": 0.23608801364898682,
|
|
"num_tokens": 78456861.0,
|
|
"step": 28075
|
|
},
|
|
{
|
|
"entropy": 5.038431072235108,
|
|
"epoch": 3.344848123883264,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003916634629578953,
|
|
"loss": 4.4759,
|
|
"mean_token_accuracy": 0.2495397984981537,
|
|
"num_tokens": 78469273.0,
|
|
"step": 28080
|
|
},
|
|
{
|
|
"entropy": 5.116600704193115,
|
|
"epoch": 3.3454437164979156,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00039162702386775773,
|
|
"loss": 4.515,
|
|
"mean_token_accuracy": 0.23744362592697144,
|
|
"num_tokens": 78485518.0,
|
|
"step": 28085
|
|
},
|
|
{
|
|
"entropy": 5.140638732910157,
|
|
"epoch": 3.346039309112567,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003915905805943983,
|
|
"loss": 4.5612,
|
|
"mean_token_accuracy": 0.2379039153456688,
|
|
"num_tokens": 78499383.0,
|
|
"step": 28090
|
|
},
|
|
{
|
|
"entropy": 4.969188547134399,
|
|
"epoch": 3.3466349017272186,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003915541331391243,
|
|
"loss": 4.3838,
|
|
"mean_token_accuracy": 0.2592105150222778,
|
|
"num_tokens": 78513870.0,
|
|
"step": 28095
|
|
},
|
|
{
|
|
"entropy": 5.126983261108398,
|
|
"epoch": 3.3472304943418703,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003915176815032431,
|
|
"loss": 4.572,
|
|
"mean_token_accuracy": 0.23599813431501387,
|
|
"num_tokens": 78527836.0,
|
|
"step": 28100
|
|
},
|
|
{
|
|
"entropy": 5.098402643203736,
|
|
"epoch": 3.3478260869565215,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00039148122568806215,
|
|
"loss": 4.4558,
|
|
"mean_token_accuracy": 0.24089475125074386,
|
|
"num_tokens": 78543339.0,
|
|
"step": 28105
|
|
},
|
|
{
|
|
"entropy": 5.025260353088379,
|
|
"epoch": 3.348421679571173,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00039144476569488896,
|
|
"loss": 4.4351,
|
|
"mean_token_accuracy": 0.2464951232075691,
|
|
"num_tokens": 78559471.0,
|
|
"step": 28110
|
|
},
|
|
{
|
|
"entropy": 5.029403781890869,
|
|
"epoch": 3.349017272185825,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003914083015250314,
|
|
"loss": 4.4046,
|
|
"mean_token_accuracy": 0.2519806265830994,
|
|
"num_tokens": 78573480.0,
|
|
"step": 28115
|
|
},
|
|
{
|
|
"entropy": 5.08704195022583,
|
|
"epoch": 3.3496128648004766,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039137183317979724,
|
|
"loss": 4.5445,
|
|
"mean_token_accuracy": 0.24731834828853608,
|
|
"num_tokens": 78587734.0,
|
|
"step": 28120
|
|
},
|
|
{
|
|
"entropy": 5.114283609390259,
|
|
"epoch": 3.3502084574151283,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003913353606604947,
|
|
"loss": 4.5149,
|
|
"mean_token_accuracy": 0.24607163071632385,
|
|
"num_tokens": 78602430.0,
|
|
"step": 28125
|
|
},
|
|
{
|
|
"entropy": 5.102523851394653,
|
|
"epoch": 3.3508040500297795,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039129888396843187,
|
|
"loss": 4.5052,
|
|
"mean_token_accuracy": 0.24329029768705368,
|
|
"num_tokens": 78617897.0,
|
|
"step": 28130
|
|
},
|
|
{
|
|
"entropy": 5.057325553894043,
|
|
"epoch": 3.3513996426444312,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039126240310491725,
|
|
"loss": 4.4314,
|
|
"mean_token_accuracy": 0.24581076800823212,
|
|
"num_tokens": 78629920.0,
|
|
"step": 28135
|
|
},
|
|
{
|
|
"entropy": 5.110815191268921,
|
|
"epoch": 3.351995235259083,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00039122591807125924,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.23413971364498137,
|
|
"num_tokens": 78643984.0,
|
|
"step": 28140
|
|
},
|
|
{
|
|
"entropy": 5.132470369338989,
|
|
"epoch": 3.352590827873734,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039118942886876647,
|
|
"loss": 4.4944,
|
|
"mean_token_accuracy": 0.24282893985509874,
|
|
"num_tokens": 78656471.0,
|
|
"step": 28145
|
|
},
|
|
{
|
|
"entropy": 5.215203762054443,
|
|
"epoch": 3.353186420488386,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003911529354987478,
|
|
"loss": 4.6324,
|
|
"mean_token_accuracy": 0.23168717473745346,
|
|
"num_tokens": 78672160.0,
|
|
"step": 28150
|
|
},
|
|
{
|
|
"entropy": 5.117852973937988,
|
|
"epoch": 3.3537820131030376,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003911164379625122,
|
|
"loss": 4.5011,
|
|
"mean_token_accuracy": 0.23630928099155427,
|
|
"num_tokens": 78686931.0,
|
|
"step": 28155
|
|
},
|
|
{
|
|
"entropy": 5.110275554656982,
|
|
"epoch": 3.3543776057176893,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003910799362613688,
|
|
"loss": 4.5452,
|
|
"mean_token_accuracy": 0.24187777936458588,
|
|
"num_tokens": 78702857.0,
|
|
"step": 28160
|
|
},
|
|
{
|
|
"entropy": 5.1477439403533936,
|
|
"epoch": 3.3549731983323405,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039104343039662675,
|
|
"loss": 4.4862,
|
|
"mean_token_accuracy": 0.24366893619298935,
|
|
"num_tokens": 78716800.0,
|
|
"step": 28165
|
|
},
|
|
{
|
|
"entropy": 5.0842146396636965,
|
|
"epoch": 3.3555687909469922,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039100692036959564,
|
|
"loss": 4.4673,
|
|
"mean_token_accuracy": 0.24217925667762757,
|
|
"num_tokens": 78730961.0,
|
|
"step": 28170
|
|
},
|
|
{
|
|
"entropy": 5.052771806716919,
|
|
"epoch": 3.356164383561644,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003909704061815848,
|
|
"loss": 4.5137,
|
|
"mean_token_accuracy": 0.24172524213790894,
|
|
"num_tokens": 78744590.0,
|
|
"step": 28175
|
|
},
|
|
{
|
|
"entropy": 5.090318489074707,
|
|
"epoch": 3.3567599761762956,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003909338878339041,
|
|
"loss": 4.4443,
|
|
"mean_token_accuracy": 0.2457138866186142,
|
|
"num_tokens": 78759753.0,
|
|
"step": 28180
|
|
},
|
|
{
|
|
"entropy": 5.071387529373169,
|
|
"epoch": 3.357355568790947,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039089736532786336,
|
|
"loss": 4.4841,
|
|
"mean_token_accuracy": 0.2387129232287407,
|
|
"num_tokens": 78774021.0,
|
|
"step": 28185
|
|
},
|
|
{
|
|
"entropy": 5.127588319778442,
|
|
"epoch": 3.3579511614055986,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0003908608386647725,
|
|
"loss": 4.5045,
|
|
"mean_token_accuracy": 0.24385580122470857,
|
|
"num_tokens": 78787609.0,
|
|
"step": 28190
|
|
},
|
|
{
|
|
"entropy": 5.0342622756958,
|
|
"epoch": 3.3585467540202503,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00039082430784594173,
|
|
"loss": 4.4648,
|
|
"mean_token_accuracy": 0.24200697094202042,
|
|
"num_tokens": 78801139.0,
|
|
"step": 28195
|
|
},
|
|
{
|
|
"entropy": 5.1627357482910154,
|
|
"epoch": 3.3591423466349015,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003907877728726814,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.23898444771766664,
|
|
"num_tokens": 78816375.0,
|
|
"step": 28200
|
|
},
|
|
{
|
|
"entropy": 5.151660299301147,
|
|
"epoch": 3.359737939249553,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039075123374630194,
|
|
"loss": 4.4902,
|
|
"mean_token_accuracy": 0.24389976263046265,
|
|
"num_tokens": 78829265.0,
|
|
"step": 28205
|
|
},
|
|
{
|
|
"entropy": 5.0351770401000975,
|
|
"epoch": 3.360333531864205,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039071469046811396,
|
|
"loss": 4.4053,
|
|
"mean_token_accuracy": 0.2463058814406395,
|
|
"num_tokens": 78843132.0,
|
|
"step": 28210
|
|
},
|
|
{
|
|
"entropy": 5.0845691680908205,
|
|
"epoch": 3.3609291244788566,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039067814303942806,
|
|
"loss": 4.5273,
|
|
"mean_token_accuracy": 0.23587058633565902,
|
|
"num_tokens": 78857736.0,
|
|
"step": 28215
|
|
},
|
|
{
|
|
"entropy": 5.159053993225098,
|
|
"epoch": 3.361524717093508,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003906415914615553,
|
|
"loss": 4.5106,
|
|
"mean_token_accuracy": 0.23968305736780166,
|
|
"num_tokens": 78874190.0,
|
|
"step": 28220
|
|
},
|
|
{
|
|
"entropy": 5.081584548950195,
|
|
"epoch": 3.3621203097081596,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003906050357358067,
|
|
"loss": 4.4657,
|
|
"mean_token_accuracy": 0.24396395683288574,
|
|
"num_tokens": 78889983.0,
|
|
"step": 28225
|
|
},
|
|
{
|
|
"entropy": 5.068452930450439,
|
|
"epoch": 3.3627159023228113,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039056847586349335,
|
|
"loss": 4.4671,
|
|
"mean_token_accuracy": 0.2516028121113777,
|
|
"num_tokens": 78904832.0,
|
|
"step": 28230
|
|
},
|
|
{
|
|
"entropy": 5.115944337844849,
|
|
"epoch": 3.363311494937463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003905319118459268,
|
|
"loss": 4.5293,
|
|
"mean_token_accuracy": 0.2470058262348175,
|
|
"num_tokens": 78918324.0,
|
|
"step": 28235
|
|
},
|
|
{
|
|
"entropy": 5.069385194778443,
|
|
"epoch": 3.363907087552114,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003904953436844183,
|
|
"loss": 4.4139,
|
|
"mean_token_accuracy": 0.249299256503582,
|
|
"num_tokens": 78930601.0,
|
|
"step": 28240
|
|
},
|
|
{
|
|
"entropy": 5.077497100830078,
|
|
"epoch": 3.364502680166766,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00039045877138027963,
|
|
"loss": 4.5102,
|
|
"mean_token_accuracy": 0.23856150209903718,
|
|
"num_tokens": 78946298.0,
|
|
"step": 28245
|
|
},
|
|
{
|
|
"entropy": 5.072763156890869,
|
|
"epoch": 3.3650982727814176,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003904221949348226,
|
|
"loss": 4.4071,
|
|
"mean_token_accuracy": 0.25022963136434556,
|
|
"num_tokens": 78959839.0,
|
|
"step": 28250
|
|
},
|
|
{
|
|
"entropy": 5.083884429931641,
|
|
"epoch": 3.365693865396069,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003903856143493591,
|
|
"loss": 4.4584,
|
|
"mean_token_accuracy": 0.2438249558210373,
|
|
"num_tokens": 78974607.0,
|
|
"step": 28255
|
|
},
|
|
{
|
|
"entropy": 5.127647638320923,
|
|
"epoch": 3.3662894580107205,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039034902962520123,
|
|
"loss": 4.5438,
|
|
"mean_token_accuracy": 0.24092887192964554,
|
|
"num_tokens": 78988974.0,
|
|
"step": 28260
|
|
},
|
|
{
|
|
"entropy": 5.155484676361084,
|
|
"epoch": 3.3668850506253722,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039031244076366116,
|
|
"loss": 4.5431,
|
|
"mean_token_accuracy": 0.24088659286499023,
|
|
"num_tokens": 79004204.0,
|
|
"step": 28265
|
|
},
|
|
{
|
|
"entropy": 5.187546062469482,
|
|
"epoch": 3.367480643240024,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039027584776605136,
|
|
"loss": 4.5847,
|
|
"mean_token_accuracy": 0.23475676476955415,
|
|
"num_tokens": 79017572.0,
|
|
"step": 28270
|
|
},
|
|
{
|
|
"entropy": 5.026020669937134,
|
|
"epoch": 3.3680762358546756,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003902392506336843,
|
|
"loss": 4.4136,
|
|
"mean_token_accuracy": 0.2563850209116936,
|
|
"num_tokens": 79031764.0,
|
|
"step": 28275
|
|
},
|
|
{
|
|
"entropy": 5.087427043914795,
|
|
"epoch": 3.368671828469327,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00039020264936787276,
|
|
"loss": 4.501,
|
|
"mean_token_accuracy": 0.2446677267551422,
|
|
"num_tokens": 79046576.0,
|
|
"step": 28280
|
|
},
|
|
{
|
|
"entropy": 5.093807363510132,
|
|
"epoch": 3.3692674210839786,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003901660439699294,
|
|
"loss": 4.4871,
|
|
"mean_token_accuracy": 0.24119899272918702,
|
|
"num_tokens": 79061019.0,
|
|
"step": 28285
|
|
},
|
|
{
|
|
"entropy": 5.1608662605285645,
|
|
"epoch": 3.3698630136986303,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039012943444116725,
|
|
"loss": 4.5359,
|
|
"mean_token_accuracy": 0.23760628551244736,
|
|
"num_tokens": 79076062.0,
|
|
"step": 28290
|
|
},
|
|
{
|
|
"entropy": 5.091895675659179,
|
|
"epoch": 3.3704586063132815,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039009282078289963,
|
|
"loss": 4.4829,
|
|
"mean_token_accuracy": 0.24531058371067047,
|
|
"num_tokens": 79089594.0,
|
|
"step": 28295
|
|
},
|
|
{
|
|
"entropy": 5.122894048690796,
|
|
"epoch": 3.3710541989279332,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003900562029964396,
|
|
"loss": 4.562,
|
|
"mean_token_accuracy": 0.24068223237991332,
|
|
"num_tokens": 79103969.0,
|
|
"step": 28300
|
|
},
|
|
{
|
|
"entropy": 5.095895910263062,
|
|
"epoch": 3.371649791542585,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039001958108310066,
|
|
"loss": 4.4814,
|
|
"mean_token_accuracy": 0.2414073407649994,
|
|
"num_tokens": 79118763.0,
|
|
"step": 28305
|
|
},
|
|
{
|
|
"entropy": 5.057187557220459,
|
|
"epoch": 3.3722453841572366,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038998295504419627,
|
|
"loss": 4.4307,
|
|
"mean_token_accuracy": 0.2499202623963356,
|
|
"num_tokens": 79132398.0,
|
|
"step": 28310
|
|
},
|
|
{
|
|
"entropy": 5.073830556869507,
|
|
"epoch": 3.372840976771888,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003899463248810403,
|
|
"loss": 4.5238,
|
|
"mean_token_accuracy": 0.23956352472305298,
|
|
"num_tokens": 79148737.0,
|
|
"step": 28315
|
|
},
|
|
{
|
|
"entropy": 5.122357749938965,
|
|
"epoch": 3.3734365693865396,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038990969059494654,
|
|
"loss": 4.4702,
|
|
"mean_token_accuracy": 0.24253679513931276,
|
|
"num_tokens": 79162176.0,
|
|
"step": 28320
|
|
},
|
|
{
|
|
"entropy": 5.068714380264282,
|
|
"epoch": 3.3740321620011913,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038987305218722904,
|
|
"loss": 4.4697,
|
|
"mean_token_accuracy": 0.2424490675330162,
|
|
"num_tokens": 79174963.0,
|
|
"step": 28325
|
|
},
|
|
{
|
|
"entropy": 5.049692392349243,
|
|
"epoch": 3.374627754615843,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003898364096592018,
|
|
"loss": 4.4224,
|
|
"mean_token_accuracy": 0.24585129618644713,
|
|
"num_tokens": 79190254.0,
|
|
"step": 28330
|
|
},
|
|
{
|
|
"entropy": 5.122822380065918,
|
|
"epoch": 3.375223347230494,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038979976301217934,
|
|
"loss": 4.428,
|
|
"mean_token_accuracy": 0.24582521468400956,
|
|
"num_tokens": 79201989.0,
|
|
"step": 28335
|
|
},
|
|
{
|
|
"entropy": 5.05810661315918,
|
|
"epoch": 3.375818939845146,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003897631122474761,
|
|
"loss": 4.4866,
|
|
"mean_token_accuracy": 0.24950200617313384,
|
|
"num_tokens": 79215033.0,
|
|
"step": 28340
|
|
},
|
|
{
|
|
"entropy": 5.086520767211914,
|
|
"epoch": 3.3764145324597976,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038972645736640654,
|
|
"loss": 4.4571,
|
|
"mean_token_accuracy": 0.24831454902887345,
|
|
"num_tokens": 79227236.0,
|
|
"step": 28345
|
|
},
|
|
{
|
|
"entropy": 5.082135343551636,
|
|
"epoch": 3.377010125074449,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038968979837028555,
|
|
"loss": 4.4084,
|
|
"mean_token_accuracy": 0.24928031265735626,
|
|
"num_tokens": 79239827.0,
|
|
"step": 28350
|
|
},
|
|
{
|
|
"entropy": 5.056655740737915,
|
|
"epoch": 3.3776057176891006,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038965313526042797,
|
|
"loss": 4.3951,
|
|
"mean_token_accuracy": 0.24540068507194518,
|
|
"num_tokens": 79254919.0,
|
|
"step": 28355
|
|
},
|
|
{
|
|
"entropy": 5.010281705856324,
|
|
"epoch": 3.3782013103037523,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038961646803814873,
|
|
"loss": 4.4432,
|
|
"mean_token_accuracy": 0.24048807173967363,
|
|
"num_tokens": 79268882.0,
|
|
"step": 28360
|
|
},
|
|
{
|
|
"entropy": 5.126976251602173,
|
|
"epoch": 3.378796902918404,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003895797967047632,
|
|
"loss": 4.5267,
|
|
"mean_token_accuracy": 0.23728861510753632,
|
|
"num_tokens": 79282838.0,
|
|
"step": 28365
|
|
},
|
|
{
|
|
"entropy": 5.11497859954834,
|
|
"epoch": 3.379392495533055,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003895431212615867,
|
|
"loss": 4.5453,
|
|
"mean_token_accuracy": 0.23848717510700226,
|
|
"num_tokens": 79296518.0,
|
|
"step": 28370
|
|
},
|
|
{
|
|
"entropy": 5.154944515228271,
|
|
"epoch": 3.379988088147707,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003895064417099346,
|
|
"loss": 4.5277,
|
|
"mean_token_accuracy": 0.24375176876783372,
|
|
"num_tokens": 79311099.0,
|
|
"step": 28375
|
|
},
|
|
{
|
|
"entropy": 5.094334602355957,
|
|
"epoch": 3.3805836807623586,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003894697580511226,
|
|
"loss": 4.5295,
|
|
"mean_token_accuracy": 0.23970879912376403,
|
|
"num_tokens": 79323385.0,
|
|
"step": 28380
|
|
},
|
|
{
|
|
"entropy": 5.0676774978637695,
|
|
"epoch": 3.3811792733770103,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038943307028646665,
|
|
"loss": 4.5002,
|
|
"mean_token_accuracy": 0.24443146586418152,
|
|
"num_tokens": 79338240.0,
|
|
"step": 28385
|
|
},
|
|
{
|
|
"entropy": 5.164920520782471,
|
|
"epoch": 3.3817748659916615,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003893963784172824,
|
|
"loss": 4.552,
|
|
"mean_token_accuracy": 0.23458191454410554,
|
|
"num_tokens": 79350052.0,
|
|
"step": 28390
|
|
},
|
|
{
|
|
"entropy": 5.090990114212036,
|
|
"epoch": 3.3823704586063132,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003893596824448861,
|
|
"loss": 4.4725,
|
|
"mean_token_accuracy": 0.25676506012678146,
|
|
"num_tokens": 79364657.0,
|
|
"step": 28395
|
|
},
|
|
{
|
|
"entropy": 5.075233030319214,
|
|
"epoch": 3.382966051220965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038932298237059394,
|
|
"loss": 4.5254,
|
|
"mean_token_accuracy": 0.24192455112934114,
|
|
"num_tokens": 79379131.0,
|
|
"step": 28400
|
|
},
|
|
{
|
|
"entropy": 5.053643608093262,
|
|
"epoch": 3.383561643835616,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038928627819572213,
|
|
"loss": 4.4031,
|
|
"mean_token_accuracy": 0.2489691585302353,
|
|
"num_tokens": 79392358.0,
|
|
"step": 28405
|
|
},
|
|
{
|
|
"entropy": 5.102148914337159,
|
|
"epoch": 3.384157236450268,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003892495699215875,
|
|
"loss": 4.4619,
|
|
"mean_token_accuracy": 0.2430756837129593,
|
|
"num_tokens": 79407027.0,
|
|
"step": 28410
|
|
},
|
|
{
|
|
"entropy": 5.101733636856079,
|
|
"epoch": 3.3847528290649196,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038921285754950645,
|
|
"loss": 4.5003,
|
|
"mean_token_accuracy": 0.24150698482990265,
|
|
"num_tokens": 79421949.0,
|
|
"step": 28415
|
|
},
|
|
{
|
|
"entropy": 5.100817012786865,
|
|
"epoch": 3.3853484216795713,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000389176141080796,
|
|
"loss": 4.4934,
|
|
"mean_token_accuracy": 0.24108649641275406,
|
|
"num_tokens": 79435628.0,
|
|
"step": 28420
|
|
},
|
|
{
|
|
"entropy": 5.113077592849732,
|
|
"epoch": 3.385944014294223,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000389139420516773,
|
|
"loss": 4.5565,
|
|
"mean_token_accuracy": 0.23867682814598085,
|
|
"num_tokens": 79448618.0,
|
|
"step": 28425
|
|
},
|
|
{
|
|
"entropy": 5.0562643051147464,
|
|
"epoch": 3.3865396069088742,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038910269585875446,
|
|
"loss": 4.458,
|
|
"mean_token_accuracy": 0.24827804863452912,
|
|
"num_tokens": 79462293.0,
|
|
"step": 28430
|
|
},
|
|
{
|
|
"entropy": 5.072932147979737,
|
|
"epoch": 3.387135199523526,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003890659671080579,
|
|
"loss": 4.448,
|
|
"mean_token_accuracy": 0.2491334557533264,
|
|
"num_tokens": 79475478.0,
|
|
"step": 28435
|
|
},
|
|
{
|
|
"entropy": 5.146910715103149,
|
|
"epoch": 3.3877307921381776,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038902923426600047,
|
|
"loss": 4.5783,
|
|
"mean_token_accuracy": 0.2371552348136902,
|
|
"num_tokens": 79488884.0,
|
|
"step": 28440
|
|
},
|
|
{
|
|
"entropy": 5.128928089141846,
|
|
"epoch": 3.388326384752829,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003889924973338998,
|
|
"loss": 4.452,
|
|
"mean_token_accuracy": 0.24540581107139586,
|
|
"num_tokens": 79504130.0,
|
|
"step": 28445
|
|
},
|
|
{
|
|
"entropy": 5.127173805236817,
|
|
"epoch": 3.3889219773674806,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038895575631307355,
|
|
"loss": 4.4847,
|
|
"mean_token_accuracy": 0.24415805488824843,
|
|
"num_tokens": 79517351.0,
|
|
"step": 28450
|
|
},
|
|
{
|
|
"entropy": 5.0889020442962645,
|
|
"epoch": 3.3895175699821323,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003889190112048397,
|
|
"loss": 4.4815,
|
|
"mean_token_accuracy": 0.2457532450556755,
|
|
"num_tokens": 79530022.0,
|
|
"step": 28455
|
|
},
|
|
{
|
|
"entropy": 5.1023438453674315,
|
|
"epoch": 3.390113162596784,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003888822620105161,
|
|
"loss": 4.5228,
|
|
"mean_token_accuracy": 0.24268061369657518,
|
|
"num_tokens": 79545208.0,
|
|
"step": 28460
|
|
},
|
|
{
|
|
"entropy": 5.089751720428467,
|
|
"epoch": 3.390708755211435,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00038884550873142084,
|
|
"loss": 4.4928,
|
|
"mean_token_accuracy": 0.24334687739610672,
|
|
"num_tokens": 79562702.0,
|
|
"step": 28465
|
|
},
|
|
{
|
|
"entropy": 5.048867130279541,
|
|
"epoch": 3.391304347826087,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003888087513688724,
|
|
"loss": 4.4692,
|
|
"mean_token_accuracy": 0.24778002351522446,
|
|
"num_tokens": 79577171.0,
|
|
"step": 28470
|
|
},
|
|
{
|
|
"entropy": 5.108207845687867,
|
|
"epoch": 3.3918999404407386,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000388771989924189,
|
|
"loss": 4.5352,
|
|
"mean_token_accuracy": 0.24281918108463288,
|
|
"num_tokens": 79591597.0,
|
|
"step": 28475
|
|
},
|
|
{
|
|
"entropy": 5.108981513977051,
|
|
"epoch": 3.3924955330553903,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003887352243986894,
|
|
"loss": 4.5003,
|
|
"mean_token_accuracy": 0.2463040754199028,
|
|
"num_tokens": 79604929.0,
|
|
"step": 28480
|
|
},
|
|
{
|
|
"entropy": 5.108423948287964,
|
|
"epoch": 3.3930911256700416,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003886984547936921,
|
|
"loss": 4.5199,
|
|
"mean_token_accuracy": 0.2425185650587082,
|
|
"num_tokens": 79618802.0,
|
|
"step": 28485
|
|
},
|
|
{
|
|
"entropy": 5.110343313217163,
|
|
"epoch": 3.3936867182846933,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003886616811105162,
|
|
"loss": 4.49,
|
|
"mean_token_accuracy": 0.24483792632818221,
|
|
"num_tokens": 79632792.0,
|
|
"step": 28490
|
|
},
|
|
{
|
|
"entropy": 5.139875745773315,
|
|
"epoch": 3.394282310899345,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038862490335048064,
|
|
"loss": 4.5336,
|
|
"mean_token_accuracy": 0.23839763700962066,
|
|
"num_tokens": 79647459.0,
|
|
"step": 28495
|
|
},
|
|
{
|
|
"entropy": 5.104537391662598,
|
|
"epoch": 3.394877903513996,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038858812151490435,
|
|
"loss": 4.4772,
|
|
"mean_token_accuracy": 0.24218343645334245,
|
|
"num_tokens": 79660510.0,
|
|
"step": 28500
|
|
},
|
|
{
|
|
"entropy": 5.105217218399048,
|
|
"epoch": 3.395473496128648,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000388551335605107,
|
|
"loss": 4.4332,
|
|
"mean_token_accuracy": 0.24412697404623032,
|
|
"num_tokens": 79674487.0,
|
|
"step": 28505
|
|
},
|
|
{
|
|
"entropy": 5.154681968688965,
|
|
"epoch": 3.3960690887432996,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038851454562240773,
|
|
"loss": 4.6042,
|
|
"mean_token_accuracy": 0.23458333164453507,
|
|
"num_tokens": 79688714.0,
|
|
"step": 28510
|
|
},
|
|
{
|
|
"entropy": 5.121862459182739,
|
|
"epoch": 3.3966646813579513,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003884777515681264,
|
|
"loss": 4.4821,
|
|
"mean_token_accuracy": 0.24264988899230958,
|
|
"num_tokens": 79702932.0,
|
|
"step": 28515
|
|
},
|
|
{
|
|
"entropy": 5.101507472991943,
|
|
"epoch": 3.3972602739726026,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00038844095344358254,
|
|
"loss": 4.5056,
|
|
"mean_token_accuracy": 0.23754822462797165,
|
|
"num_tokens": 79717049.0,
|
|
"step": 28520
|
|
},
|
|
{
|
|
"entropy": 5.130908060073852,
|
|
"epoch": 3.3978558665872542,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038840415125009623,
|
|
"loss": 4.4928,
|
|
"mean_token_accuracy": 0.24756631404161453,
|
|
"num_tokens": 79731443.0,
|
|
"step": 28525
|
|
},
|
|
{
|
|
"entropy": 5.07260274887085,
|
|
"epoch": 3.398451459201906,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003883673449889873,
|
|
"loss": 4.4825,
|
|
"mean_token_accuracy": 0.2502134248614311,
|
|
"num_tokens": 79745258.0,
|
|
"step": 28530
|
|
},
|
|
{
|
|
"entropy": 5.035758018493652,
|
|
"epoch": 3.3990470518165576,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000388330534661576,
|
|
"loss": 4.4609,
|
|
"mean_token_accuracy": 0.24274262338876723,
|
|
"num_tokens": 79759238.0,
|
|
"step": 28535
|
|
},
|
|
{
|
|
"entropy": 5.104531097412109,
|
|
"epoch": 3.399642644431209,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003882937202691828,
|
|
"loss": 4.4997,
|
|
"mean_token_accuracy": 0.24348720908164978,
|
|
"num_tokens": 79774181.0,
|
|
"step": 28540
|
|
},
|
|
{
|
|
"entropy": 5.124731111526489,
|
|
"epoch": 3.4002382370458606,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038825690181312793,
|
|
"loss": 4.4848,
|
|
"mean_token_accuracy": 0.24623481631278993,
|
|
"num_tokens": 79787637.0,
|
|
"step": 28545
|
|
},
|
|
{
|
|
"entropy": 5.119988059997558,
|
|
"epoch": 3.4008338296605123,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003882200792947322,
|
|
"loss": 4.5467,
|
|
"mean_token_accuracy": 0.23320578187704086,
|
|
"num_tokens": 79800196.0,
|
|
"step": 28550
|
|
},
|
|
{
|
|
"entropy": 5.183726358413696,
|
|
"epoch": 3.4014294222751635,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003881832527153163,
|
|
"loss": 4.6095,
|
|
"mean_token_accuracy": 0.23364076912403106,
|
|
"num_tokens": 79813836.0,
|
|
"step": 28555
|
|
},
|
|
{
|
|
"entropy": 5.060168838500976,
|
|
"epoch": 3.4020250148898152,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003881464220762012,
|
|
"loss": 4.3834,
|
|
"mean_token_accuracy": 0.2460038721561432,
|
|
"num_tokens": 79826523.0,
|
|
"step": 28560
|
|
},
|
|
{
|
|
"entropy": 5.045231437683105,
|
|
"epoch": 3.402620607504467,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003881095873787079,
|
|
"loss": 4.4439,
|
|
"mean_token_accuracy": 0.2457137808203697,
|
|
"num_tokens": 79838728.0,
|
|
"step": 28565
|
|
},
|
|
{
|
|
"entropy": 5.116184425354004,
|
|
"epoch": 3.4032162001191186,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038807274862415756,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.23730752915143966,
|
|
"num_tokens": 79852813.0,
|
|
"step": 28570
|
|
},
|
|
{
|
|
"entropy": 5.0598204135894775,
|
|
"epoch": 3.4038117927337703,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038803590581387156,
|
|
"loss": 4.4139,
|
|
"mean_token_accuracy": 0.2553176984190941,
|
|
"num_tokens": 79865617.0,
|
|
"step": 28575
|
|
},
|
|
{
|
|
"entropy": 5.116203355789184,
|
|
"epoch": 3.4044073853484216,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038799905894917143,
|
|
"loss": 4.4682,
|
|
"mean_token_accuracy": 0.24455018490552902,
|
|
"num_tokens": 79880738.0,
|
|
"step": 28580
|
|
},
|
|
{
|
|
"entropy": 5.128240299224854,
|
|
"epoch": 3.4050029779630733,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003879622080313788,
|
|
"loss": 4.4768,
|
|
"mean_token_accuracy": 0.2407515287399292,
|
|
"num_tokens": 79892633.0,
|
|
"step": 28585
|
|
},
|
|
{
|
|
"entropy": 5.093492460250855,
|
|
"epoch": 3.405598570577725,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038792535306181536,
|
|
"loss": 4.4246,
|
|
"mean_token_accuracy": 0.24998053014278412,
|
|
"num_tokens": 79906201.0,
|
|
"step": 28590
|
|
},
|
|
{
|
|
"entropy": 5.0353350162506105,
|
|
"epoch": 3.4061941631923762,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003878884940418032,
|
|
"loss": 4.4346,
|
|
"mean_token_accuracy": 0.2416188821196556,
|
|
"num_tokens": 79918951.0,
|
|
"step": 28595
|
|
},
|
|
{
|
|
"entropy": 5.074929285049438,
|
|
"epoch": 3.406789755807028,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038785163097266424,
|
|
"loss": 4.3968,
|
|
"mean_token_accuracy": 0.2492722451686859,
|
|
"num_tokens": 79932245.0,
|
|
"step": 28600
|
|
},
|
|
{
|
|
"entropy": 5.105030155181884,
|
|
"epoch": 3.4073853484216796,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00038781476385572075,
|
|
"loss": 4.4849,
|
|
"mean_token_accuracy": 0.24380604028701783,
|
|
"num_tokens": 79944732.0,
|
|
"step": 28605
|
|
},
|
|
{
|
|
"entropy": 5.096111536026001,
|
|
"epoch": 3.4079809410363313,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003877778926922952,
|
|
"loss": 4.5356,
|
|
"mean_token_accuracy": 0.23697822242975236,
|
|
"num_tokens": 79958692.0,
|
|
"step": 28610
|
|
},
|
|
{
|
|
"entropy": 5.125850343704224,
|
|
"epoch": 3.4085765336509826,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003877410174837099,
|
|
"loss": 4.4969,
|
|
"mean_token_accuracy": 0.23769251853227616,
|
|
"num_tokens": 79973042.0,
|
|
"step": 28615
|
|
},
|
|
{
|
|
"entropy": 5.050249481201172,
|
|
"epoch": 3.4091721262656343,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038770413823128764,
|
|
"loss": 4.4318,
|
|
"mean_token_accuracy": 0.24695201814174653,
|
|
"num_tokens": 79988296.0,
|
|
"step": 28620
|
|
},
|
|
{
|
|
"entropy": 5.028029918670654,
|
|
"epoch": 3.409767718880286,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038766725493635123,
|
|
"loss": 4.4096,
|
|
"mean_token_accuracy": 0.2546508938074112,
|
|
"num_tokens": 80004073.0,
|
|
"step": 28625
|
|
},
|
|
{
|
|
"entropy": 5.121901941299439,
|
|
"epoch": 3.4103633114949377,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038763036760022356,
|
|
"loss": 4.5132,
|
|
"mean_token_accuracy": 0.24476812779903412,
|
|
"num_tokens": 80019210.0,
|
|
"step": 28630
|
|
},
|
|
{
|
|
"entropy": 5.055610084533692,
|
|
"epoch": 3.410958904109589,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038759347622422774,
|
|
"loss": 4.4399,
|
|
"mean_token_accuracy": 0.24542711824178695,
|
|
"num_tokens": 80033107.0,
|
|
"step": 28635
|
|
},
|
|
{
|
|
"entropy": 5.101281356811524,
|
|
"epoch": 3.4115544967242406,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003875565808096869,
|
|
"loss": 4.5436,
|
|
"mean_token_accuracy": 0.23485468924045563,
|
|
"num_tokens": 80048131.0,
|
|
"step": 28640
|
|
},
|
|
{
|
|
"entropy": 5.110822677612305,
|
|
"epoch": 3.4121500893388923,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003875196813579246,
|
|
"loss": 4.509,
|
|
"mean_token_accuracy": 0.23773505091667174,
|
|
"num_tokens": 80062896.0,
|
|
"step": 28645
|
|
},
|
|
{
|
|
"entropy": 5.110004234313965,
|
|
"epoch": 3.4127456819535436,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003874827778702643,
|
|
"loss": 4.5171,
|
|
"mean_token_accuracy": 0.24166055917739868,
|
|
"num_tokens": 80078047.0,
|
|
"step": 28650
|
|
},
|
|
{
|
|
"entropy": 5.156058692932129,
|
|
"epoch": 3.4133412745681952,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003874458703480296,
|
|
"loss": 4.5449,
|
|
"mean_token_accuracy": 0.24117932170629502,
|
|
"num_tokens": 80092201.0,
|
|
"step": 28655
|
|
},
|
|
{
|
|
"entropy": 5.10605525970459,
|
|
"epoch": 3.413936867182847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038740895879254433,
|
|
"loss": 4.5109,
|
|
"mean_token_accuracy": 0.23919681310653687,
|
|
"num_tokens": 80107963.0,
|
|
"step": 28660
|
|
},
|
|
{
|
|
"entropy": 5.117032718658447,
|
|
"epoch": 3.4145324597974986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038737204320513254,
|
|
"loss": 4.4971,
|
|
"mean_token_accuracy": 0.2450534760951996,
|
|
"num_tokens": 80121418.0,
|
|
"step": 28665
|
|
},
|
|
{
|
|
"entropy": 5.003394031524659,
|
|
"epoch": 3.4151280524121503,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003873351235871181,
|
|
"loss": 4.3844,
|
|
"mean_token_accuracy": 0.25668188333511355,
|
|
"num_tokens": 80135340.0,
|
|
"step": 28670
|
|
},
|
|
{
|
|
"entropy": 5.020518589019775,
|
|
"epoch": 3.4157236450268016,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038729819993982566,
|
|
"loss": 4.4075,
|
|
"mean_token_accuracy": 0.25255009680986407,
|
|
"num_tokens": 80148783.0,
|
|
"step": 28675
|
|
},
|
|
{
|
|
"entropy": 5.1594892024993895,
|
|
"epoch": 3.4163192376414533,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003872612722645792,
|
|
"loss": 4.5874,
|
|
"mean_token_accuracy": 0.2386369898915291,
|
|
"num_tokens": 80163418.0,
|
|
"step": 28680
|
|
},
|
|
{
|
|
"entropy": 5.165652179718018,
|
|
"epoch": 3.416914830256105,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038722434056270356,
|
|
"loss": 4.5471,
|
|
"mean_token_accuracy": 0.23860058784484864,
|
|
"num_tokens": 80178685.0,
|
|
"step": 28685
|
|
},
|
|
{
|
|
"entropy": 5.108291339874268,
|
|
"epoch": 3.4175104228707562,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003871874048355233,
|
|
"loss": 4.5009,
|
|
"mean_token_accuracy": 0.24842602163553237,
|
|
"num_tokens": 80190465.0,
|
|
"step": 28690
|
|
},
|
|
{
|
|
"entropy": 5.0126978874206545,
|
|
"epoch": 3.418106015485408,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038715046508436306,
|
|
"loss": 4.4122,
|
|
"mean_token_accuracy": 0.25225404649972916,
|
|
"num_tokens": 80204660.0,
|
|
"step": 28695
|
|
},
|
|
{
|
|
"entropy": 5.071780252456665,
|
|
"epoch": 3.4187016081000596,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038711352131054813,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.24921009689569473,
|
|
"num_tokens": 80218543.0,
|
|
"step": 28700
|
|
},
|
|
{
|
|
"entropy": 5.179675769805908,
|
|
"epoch": 3.4192972007147113,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003870765735154034,
|
|
"loss": 4.5667,
|
|
"mean_token_accuracy": 0.24048624336719512,
|
|
"num_tokens": 80232409.0,
|
|
"step": 28705
|
|
},
|
|
{
|
|
"entropy": 5.146733283996582,
|
|
"epoch": 3.4198927933293626,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003870396217002542,
|
|
"loss": 4.5216,
|
|
"mean_token_accuracy": 0.23743304163217543,
|
|
"num_tokens": 80245959.0,
|
|
"step": 28710
|
|
},
|
|
{
|
|
"entropy": 5.032766437530517,
|
|
"epoch": 3.4204883859440143,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038700266586642597,
|
|
"loss": 4.3818,
|
|
"mean_token_accuracy": 0.2573681309819221,
|
|
"num_tokens": 80259588.0,
|
|
"step": 28715
|
|
},
|
|
{
|
|
"entropy": 5.096659135818482,
|
|
"epoch": 3.421083978558666,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003869657060152443,
|
|
"loss": 4.5425,
|
|
"mean_token_accuracy": 0.24364933520555496,
|
|
"num_tokens": 80274728.0,
|
|
"step": 28720
|
|
},
|
|
{
|
|
"entropy": 5.150798225402832,
|
|
"epoch": 3.4216795711733177,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003869287421480347,
|
|
"loss": 4.5472,
|
|
"mean_token_accuracy": 0.23764430582523347,
|
|
"num_tokens": 80289376.0,
|
|
"step": 28725
|
|
},
|
|
{
|
|
"entropy": 5.143869304656983,
|
|
"epoch": 3.422275163787969,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003868917742661231,
|
|
"loss": 4.5397,
|
|
"mean_token_accuracy": 0.2389003038406372,
|
|
"num_tokens": 80302018.0,
|
|
"step": 28730
|
|
},
|
|
{
|
|
"entropy": 5.072984600067139,
|
|
"epoch": 3.4228707564026206,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038685480237083547,
|
|
"loss": 4.4767,
|
|
"mean_token_accuracy": 0.2412241965532303,
|
|
"num_tokens": 80315151.0,
|
|
"step": 28735
|
|
},
|
|
{
|
|
"entropy": 5.135135364532471,
|
|
"epoch": 3.4234663490172723,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000386817826463498,
|
|
"loss": 4.5151,
|
|
"mean_token_accuracy": 0.24165502339601516,
|
|
"num_tokens": 80328883.0,
|
|
"step": 28740
|
|
},
|
|
{
|
|
"entropy": 5.125929737091065,
|
|
"epoch": 3.4240619416319236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003867808465454368,
|
|
"loss": 4.498,
|
|
"mean_token_accuracy": 0.24063563346862793,
|
|
"num_tokens": 80342537.0,
|
|
"step": 28745
|
|
},
|
|
{
|
|
"entropy": 5.0681530952453615,
|
|
"epoch": 3.4246575342465753,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003867438626179785,
|
|
"loss": 4.454,
|
|
"mean_token_accuracy": 0.24245655834674834,
|
|
"num_tokens": 80355713.0,
|
|
"step": 28750
|
|
},
|
|
{
|
|
"entropy": 5.16880521774292,
|
|
"epoch": 3.425253126861227,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038670687468244947,
|
|
"loss": 4.6295,
|
|
"mean_token_accuracy": 0.23075623363256453,
|
|
"num_tokens": 80370518.0,
|
|
"step": 28755
|
|
},
|
|
{
|
|
"entropy": 5.051210165023804,
|
|
"epoch": 3.4258487194758787,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003866698827401765,
|
|
"loss": 4.4401,
|
|
"mean_token_accuracy": 0.248310948908329,
|
|
"num_tokens": 80382492.0,
|
|
"step": 28760
|
|
},
|
|
{
|
|
"entropy": 5.133848428726196,
|
|
"epoch": 3.42644431209053,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003866328867924864,
|
|
"loss": 4.5666,
|
|
"mean_token_accuracy": 0.23153989315032958,
|
|
"num_tokens": 80396344.0,
|
|
"step": 28765
|
|
},
|
|
{
|
|
"entropy": 5.174276113510132,
|
|
"epoch": 3.4270399047051816,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003865958868407061,
|
|
"loss": 4.5519,
|
|
"mean_token_accuracy": 0.24354556649923326,
|
|
"num_tokens": 80408823.0,
|
|
"step": 28770
|
|
},
|
|
{
|
|
"entropy": 5.115629529953003,
|
|
"epoch": 3.4276354973198333,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003865588828861629,
|
|
"loss": 4.5728,
|
|
"mean_token_accuracy": 0.23955194503068925,
|
|
"num_tokens": 80423030.0,
|
|
"step": 28775
|
|
},
|
|
{
|
|
"entropy": 5.1317507266998295,
|
|
"epoch": 3.428231089934485,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003865218749301838,
|
|
"loss": 4.5359,
|
|
"mean_token_accuracy": 0.24184137731790542,
|
|
"num_tokens": 80438262.0,
|
|
"step": 28780
|
|
},
|
|
{
|
|
"entropy": 5.079057884216309,
|
|
"epoch": 3.4288266825491363,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003864848629740965,
|
|
"loss": 4.4474,
|
|
"mean_token_accuracy": 0.24737464636564255,
|
|
"num_tokens": 80453228.0,
|
|
"step": 28785
|
|
},
|
|
{
|
|
"entropy": 5.179785966873169,
|
|
"epoch": 3.429422275163788,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038644784701922835,
|
|
"loss": 4.5426,
|
|
"mean_token_accuracy": 0.24099863320589066,
|
|
"num_tokens": 80466274.0,
|
|
"step": 28790
|
|
},
|
|
{
|
|
"entropy": 5.085902738571167,
|
|
"epoch": 3.4300178677784396,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038641082706690716,
|
|
"loss": 4.5257,
|
|
"mean_token_accuracy": 0.24981726706027985,
|
|
"num_tokens": 80481788.0,
|
|
"step": 28795
|
|
},
|
|
{
|
|
"entropy": 5.0576389789581295,
|
|
"epoch": 3.430613460393091,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038637380311846075,
|
|
"loss": 4.4533,
|
|
"mean_token_accuracy": 0.24765873849391937,
|
|
"num_tokens": 80495949.0,
|
|
"step": 28800
|
|
},
|
|
{
|
|
"entropy": 5.083550930023193,
|
|
"epoch": 3.4312090530077426,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003863367751752171,
|
|
"loss": 4.5076,
|
|
"mean_token_accuracy": 0.24402122795581818,
|
|
"num_tokens": 80510071.0,
|
|
"step": 28805
|
|
},
|
|
{
|
|
"entropy": 4.992257404327392,
|
|
"epoch": 3.4318046456223943,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003862997432385043,
|
|
"loss": 4.3747,
|
|
"mean_token_accuracy": 0.25576313138008117,
|
|
"num_tokens": 80525344.0,
|
|
"step": 28810
|
|
},
|
|
{
|
|
"entropy": 5.125074338912964,
|
|
"epoch": 3.432400238237046,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003862627073096508,
|
|
"loss": 4.4683,
|
|
"mean_token_accuracy": 0.24622675627470017,
|
|
"num_tokens": 80540673.0,
|
|
"step": 28815
|
|
},
|
|
{
|
|
"entropy": 5.02250189781189,
|
|
"epoch": 3.4329958308516977,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003862256673899848,
|
|
"loss": 4.4232,
|
|
"mean_token_accuracy": 0.2417873427271843,
|
|
"num_tokens": 80553334.0,
|
|
"step": 28820
|
|
},
|
|
{
|
|
"entropy": 5.07590765953064,
|
|
"epoch": 3.433591423466349,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003861886234808349,
|
|
"loss": 4.4785,
|
|
"mean_token_accuracy": 0.2421746075153351,
|
|
"num_tokens": 80567414.0,
|
|
"step": 28825
|
|
},
|
|
{
|
|
"entropy": 5.09613561630249,
|
|
"epoch": 3.4341870160810006,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038615157558353,
|
|
"loss": 4.4603,
|
|
"mean_token_accuracy": 0.24221351444721223,
|
|
"num_tokens": 80580355.0,
|
|
"step": 28830
|
|
},
|
|
{
|
|
"entropy": 5.0975250720977785,
|
|
"epoch": 3.4347826086956523,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00038611452369939864,
|
|
"loss": 4.4454,
|
|
"mean_token_accuracy": 0.2469448998570442,
|
|
"num_tokens": 80593514.0,
|
|
"step": 28835
|
|
},
|
|
{
|
|
"entropy": 5.128427886962891,
|
|
"epoch": 3.4353782013103036,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003860774678297701,
|
|
"loss": 4.4995,
|
|
"mean_token_accuracy": 0.2512791872024536,
|
|
"num_tokens": 80607719.0,
|
|
"step": 28840
|
|
},
|
|
{
|
|
"entropy": 5.051541757583618,
|
|
"epoch": 3.4359737939249553,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038604040797597335,
|
|
"loss": 4.4437,
|
|
"mean_token_accuracy": 0.24907479733228682,
|
|
"num_tokens": 80621401.0,
|
|
"step": 28845
|
|
},
|
|
{
|
|
"entropy": 5.1494285583496096,
|
|
"epoch": 3.436569386539607,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003860033441393377,
|
|
"loss": 4.5756,
|
|
"mean_token_accuracy": 0.2322293385863304,
|
|
"num_tokens": 80636872.0,
|
|
"step": 28850
|
|
},
|
|
{
|
|
"entropy": 5.062596273422241,
|
|
"epoch": 3.4371649791542587,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038596627632119255,
|
|
"loss": 4.4475,
|
|
"mean_token_accuracy": 0.24488244950771332,
|
|
"num_tokens": 80649959.0,
|
|
"step": 28855
|
|
},
|
|
{
|
|
"entropy": 5.124767208099366,
|
|
"epoch": 3.43776057176891,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003859292045228676,
|
|
"loss": 4.4839,
|
|
"mean_token_accuracy": 0.23926243633031846,
|
|
"num_tokens": 80663283.0,
|
|
"step": 28860
|
|
},
|
|
{
|
|
"entropy": 5.138283967971802,
|
|
"epoch": 3.4383561643835616,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038589212874569237,
|
|
"loss": 4.4362,
|
|
"mean_token_accuracy": 0.25210483074188234,
|
|
"num_tokens": 80676899.0,
|
|
"step": 28865
|
|
},
|
|
{
|
|
"entropy": 5.080347919464112,
|
|
"epoch": 3.4389517569982133,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003858550489909967,
|
|
"loss": 4.4795,
|
|
"mean_token_accuracy": 0.2433566391468048,
|
|
"num_tokens": 80690915.0,
|
|
"step": 28870
|
|
},
|
|
{
|
|
"entropy": 5.063012266159058,
|
|
"epoch": 3.439547349612865,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003858179652601108,
|
|
"loss": 4.4778,
|
|
"mean_token_accuracy": 0.24475434124469758,
|
|
"num_tokens": 80704845.0,
|
|
"step": 28875
|
|
},
|
|
{
|
|
"entropy": 5.075566291809082,
|
|
"epoch": 3.4401429422275163,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0003857808775543646,
|
|
"loss": 4.4855,
|
|
"mean_token_accuracy": 0.24418709725141524,
|
|
"num_tokens": 80720722.0,
|
|
"step": 28880
|
|
},
|
|
{
|
|
"entropy": 5.0909606456756595,
|
|
"epoch": 3.440738534842168,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003857437858750884,
|
|
"loss": 4.4732,
|
|
"mean_token_accuracy": 0.2440725088119507,
|
|
"num_tokens": 80735678.0,
|
|
"step": 28885
|
|
},
|
|
{
|
|
"entropy": 5.1684197902679445,
|
|
"epoch": 3.4413341274568197,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038570669022361273,
|
|
"loss": 4.6034,
|
|
"mean_token_accuracy": 0.23342466950416565,
|
|
"num_tokens": 80749040.0,
|
|
"step": 28890
|
|
},
|
|
{
|
|
"entropy": 5.126892709732056,
|
|
"epoch": 3.441929720071471,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000385669590601268,
|
|
"loss": 4.5481,
|
|
"mean_token_accuracy": 0.23531951904296874,
|
|
"num_tokens": 80763681.0,
|
|
"step": 28895
|
|
},
|
|
{
|
|
"entropy": 5.063118886947632,
|
|
"epoch": 3.4425253126861226,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003856324870093851,
|
|
"loss": 4.4711,
|
|
"mean_token_accuracy": 0.23999127745628357,
|
|
"num_tokens": 80776997.0,
|
|
"step": 28900
|
|
},
|
|
{
|
|
"entropy": 5.119322013854981,
|
|
"epoch": 3.4431209053007743,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00038559537944929465,
|
|
"loss": 4.5445,
|
|
"mean_token_accuracy": 0.24500077217817307,
|
|
"num_tokens": 80792398.0,
|
|
"step": 28905
|
|
},
|
|
{
|
|
"entropy": 5.057018089294433,
|
|
"epoch": 3.443716497915426,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003855582679223279,
|
|
"loss": 4.3764,
|
|
"mean_token_accuracy": 0.2557200059294701,
|
|
"num_tokens": 80804383.0,
|
|
"step": 28910
|
|
},
|
|
{
|
|
"entropy": 5.102058601379395,
|
|
"epoch": 3.4443120905300773,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038552115242981573,
|
|
"loss": 4.5352,
|
|
"mean_token_accuracy": 0.23605532795190812,
|
|
"num_tokens": 80817215.0,
|
|
"step": 28915
|
|
},
|
|
{
|
|
"entropy": 5.217960691452026,
|
|
"epoch": 3.444907683144729,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038548403297308955,
|
|
"loss": 4.6641,
|
|
"mean_token_accuracy": 0.23072075098752975,
|
|
"num_tokens": 80830153.0,
|
|
"step": 28920
|
|
},
|
|
{
|
|
"entropy": 5.165557527542115,
|
|
"epoch": 3.4455032757593806,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038544690955348077,
|
|
"loss": 4.5215,
|
|
"mean_token_accuracy": 0.23724731653928757,
|
|
"num_tokens": 80844748.0,
|
|
"step": 28925
|
|
},
|
|
{
|
|
"entropy": 5.102518367767334,
|
|
"epoch": 3.4460988683740323,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038540978217232086,
|
|
"loss": 4.5376,
|
|
"mean_token_accuracy": 0.23954834491014482,
|
|
"num_tokens": 80860478.0,
|
|
"step": 28930
|
|
},
|
|
{
|
|
"entropy": 5.120970392227173,
|
|
"epoch": 3.4466944609886836,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003853726508309416,
|
|
"loss": 4.5263,
|
|
"mean_token_accuracy": 0.24292160272598268,
|
|
"num_tokens": 80873020.0,
|
|
"step": 28935
|
|
},
|
|
{
|
|
"entropy": 5.1453714847564695,
|
|
"epoch": 3.4472900536033353,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003853355155306748,
|
|
"loss": 4.547,
|
|
"mean_token_accuracy": 0.2374743714928627,
|
|
"num_tokens": 80886735.0,
|
|
"step": 28940
|
|
},
|
|
{
|
|
"entropy": 5.075749158859253,
|
|
"epoch": 3.447885646217987,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038529837627285246,
|
|
"loss": 4.4936,
|
|
"mean_token_accuracy": 0.2410569131374359,
|
|
"num_tokens": 80898646.0,
|
|
"step": 28945
|
|
},
|
|
{
|
|
"entropy": 5.217856550216675,
|
|
"epoch": 3.4484812388326382,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003852612330588067,
|
|
"loss": 4.5946,
|
|
"mean_token_accuracy": 0.2297694131731987,
|
|
"num_tokens": 80911959.0,
|
|
"step": 28950
|
|
},
|
|
{
|
|
"entropy": 5.111594486236572,
|
|
"epoch": 3.44907683144729,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038522408588986985,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.24005864560604095,
|
|
"num_tokens": 80925168.0,
|
|
"step": 28955
|
|
},
|
|
{
|
|
"entropy": 5.1082244396209715,
|
|
"epoch": 3.4496724240619416,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003851869347673742,
|
|
"loss": 4.5604,
|
|
"mean_token_accuracy": 0.23826182037591934,
|
|
"num_tokens": 80940475.0,
|
|
"step": 28960
|
|
},
|
|
{
|
|
"entropy": 5.170357322692871,
|
|
"epoch": 3.4502680166765933,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038514977969265234,
|
|
"loss": 4.4915,
|
|
"mean_token_accuracy": 0.24229870736598969,
|
|
"num_tokens": 80953110.0,
|
|
"step": 28965
|
|
},
|
|
{
|
|
"entropy": 5.07225399017334,
|
|
"epoch": 3.450863609291245,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003851126206670369,
|
|
"loss": 4.4882,
|
|
"mean_token_accuracy": 0.24673662781715394,
|
|
"num_tokens": 80966206.0,
|
|
"step": 28970
|
|
},
|
|
{
|
|
"entropy": 5.017441082000732,
|
|
"epoch": 3.4514592019058963,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038507545769186094,
|
|
"loss": 4.3999,
|
|
"mean_token_accuracy": 0.24860494583845139,
|
|
"num_tokens": 80978894.0,
|
|
"step": 28975
|
|
},
|
|
{
|
|
"entropy": 5.106687116622925,
|
|
"epoch": 3.452054794520548,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003850382907684572,
|
|
"loss": 4.4605,
|
|
"mean_token_accuracy": 0.2439810648560524,
|
|
"num_tokens": 80991604.0,
|
|
"step": 28980
|
|
},
|
|
{
|
|
"entropy": 5.177097749710083,
|
|
"epoch": 3.4526503871351997,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00038500111989815894,
|
|
"loss": 4.4755,
|
|
"mean_token_accuracy": 0.24353839606046676,
|
|
"num_tokens": 81004531.0,
|
|
"step": 28985
|
|
},
|
|
{
|
|
"entropy": 5.0843945980072025,
|
|
"epoch": 3.453245979749851,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038496394508229925,
|
|
"loss": 4.4478,
|
|
"mean_token_accuracy": 0.24475215673446654,
|
|
"num_tokens": 81017152.0,
|
|
"step": 28990
|
|
},
|
|
{
|
|
"entropy": 5.188340282440185,
|
|
"epoch": 3.4538415723645026,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038492676632221175,
|
|
"loss": 4.6392,
|
|
"mean_token_accuracy": 0.23016320765018464,
|
|
"num_tokens": 81031234.0,
|
|
"step": 28995
|
|
},
|
|
{
|
|
"entropy": 5.1129951000213625,
|
|
"epoch": 3.4544371649791543,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038488958361922984,
|
|
"loss": 4.469,
|
|
"mean_token_accuracy": 0.2358671799302101,
|
|
"num_tokens": 81045031.0,
|
|
"step": 29000
|
|
},
|
|
{
|
|
"entropy": 5.063570833206176,
|
|
"epoch": 3.455032757593806,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038485239697468715,
|
|
"loss": 4.4771,
|
|
"mean_token_accuracy": 0.2437605455517769,
|
|
"num_tokens": 81060125.0,
|
|
"step": 29005
|
|
},
|
|
{
|
|
"entropy": 5.070191669464111,
|
|
"epoch": 3.4556283502084573,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003848152063899177,
|
|
"loss": 4.4522,
|
|
"mean_token_accuracy": 0.2495649978518486,
|
|
"num_tokens": 81074890.0,
|
|
"step": 29010
|
|
},
|
|
{
|
|
"entropy": 5.098266983032227,
|
|
"epoch": 3.456223942823109,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038477801186625533,
|
|
"loss": 4.4673,
|
|
"mean_token_accuracy": 0.24679163545370103,
|
|
"num_tokens": 81090062.0,
|
|
"step": 29015
|
|
},
|
|
{
|
|
"entropy": 5.113992738723755,
|
|
"epoch": 3.4568195354377607,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038474081340503414,
|
|
"loss": 4.4988,
|
|
"mean_token_accuracy": 0.24785659462213516,
|
|
"num_tokens": 81103063.0,
|
|
"step": 29020
|
|
},
|
|
{
|
|
"entropy": 5.076468753814697,
|
|
"epoch": 3.4574151280524124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003847036110075884,
|
|
"loss": 4.4971,
|
|
"mean_token_accuracy": 0.24092524200677873,
|
|
"num_tokens": 81115962.0,
|
|
"step": 29025
|
|
},
|
|
{
|
|
"entropy": 5.181508541107178,
|
|
"epoch": 3.4580107206670636,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038466640467525254,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.23700104057788848,
|
|
"num_tokens": 81130443.0,
|
|
"step": 29030
|
|
},
|
|
{
|
|
"entropy": 5.116259765625,
|
|
"epoch": 3.4586063132817153,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00038462919440936094,
|
|
"loss": 4.5159,
|
|
"mean_token_accuracy": 0.2439677432179451,
|
|
"num_tokens": 81145771.0,
|
|
"step": 29035
|
|
},
|
|
{
|
|
"entropy": 5.111439514160156,
|
|
"epoch": 3.459201905896367,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038459198021124853,
|
|
"loss": 4.5292,
|
|
"mean_token_accuracy": 0.24435874521732331,
|
|
"num_tokens": 81159796.0,
|
|
"step": 29040
|
|
},
|
|
{
|
|
"entropy": 5.1086005687713625,
|
|
"epoch": 3.4597974985110183,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003845547620822498,
|
|
"loss": 4.5721,
|
|
"mean_token_accuracy": 0.2346886247396469,
|
|
"num_tokens": 81172357.0,
|
|
"step": 29045
|
|
},
|
|
{
|
|
"entropy": 5.101069688796997,
|
|
"epoch": 3.46039309112567,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038451754002370004,
|
|
"loss": 4.4362,
|
|
"mean_token_accuracy": 0.24229610413312913,
|
|
"num_tokens": 81186127.0,
|
|
"step": 29050
|
|
},
|
|
{
|
|
"entropy": 5.098480558395385,
|
|
"epoch": 3.4609886837403216,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0003844803140369342,
|
|
"loss": 4.4971,
|
|
"mean_token_accuracy": 0.2396631807088852,
|
|
"num_tokens": 81202619.0,
|
|
"step": 29055
|
|
},
|
|
{
|
|
"entropy": 5.070401191711426,
|
|
"epoch": 3.4615842763549733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003844430841232873,
|
|
"loss": 4.4548,
|
|
"mean_token_accuracy": 0.24881606847047805,
|
|
"num_tokens": 81216748.0,
|
|
"step": 29060
|
|
},
|
|
{
|
|
"entropy": 5.10388593673706,
|
|
"epoch": 3.4621798689696246,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003844058502840951,
|
|
"loss": 4.5292,
|
|
"mean_token_accuracy": 0.2434949278831482,
|
|
"num_tokens": 81232360.0,
|
|
"step": 29065
|
|
},
|
|
{
|
|
"entropy": 5.138611841201782,
|
|
"epoch": 3.4627754615842763,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003843686125206928,
|
|
"loss": 4.5072,
|
|
"mean_token_accuracy": 0.23812337219715118,
|
|
"num_tokens": 81245461.0,
|
|
"step": 29070
|
|
},
|
|
{
|
|
"entropy": 5.182061862945557,
|
|
"epoch": 3.463371054198928,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003843313708344163,
|
|
"loss": 4.6052,
|
|
"mean_token_accuracy": 0.23183583319187165,
|
|
"num_tokens": 81259546.0,
|
|
"step": 29075
|
|
},
|
|
{
|
|
"entropy": 5.040978717803955,
|
|
"epoch": 3.4639666468135797,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003842941252266013,
|
|
"loss": 4.3655,
|
|
"mean_token_accuracy": 0.2585952430963516,
|
|
"num_tokens": 81271939.0,
|
|
"step": 29080
|
|
},
|
|
{
|
|
"entropy": 5.0344713687896725,
|
|
"epoch": 3.464562239428231,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003842568756985837,
|
|
"loss": 4.397,
|
|
"mean_token_accuracy": 0.25454906821250917,
|
|
"num_tokens": 81285214.0,
|
|
"step": 29085
|
|
},
|
|
{
|
|
"entropy": 5.133789777755737,
|
|
"epoch": 3.4651578320428826,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038421962225169954,
|
|
"loss": 4.5611,
|
|
"mean_token_accuracy": 0.23562396615743636,
|
|
"num_tokens": 81299153.0,
|
|
"step": 29090
|
|
},
|
|
{
|
|
"entropy": 5.142088317871094,
|
|
"epoch": 3.4657534246575343,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003841823648872852,
|
|
"loss": 4.5012,
|
|
"mean_token_accuracy": 0.24274544268846512,
|
|
"num_tokens": 81313442.0,
|
|
"step": 29095
|
|
},
|
|
{
|
|
"entropy": 5.1055573463439945,
|
|
"epoch": 3.4663490172721856,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003841451036066769,
|
|
"loss": 4.4571,
|
|
"mean_token_accuracy": 0.24531496018171312,
|
|
"num_tokens": 81326957.0,
|
|
"step": 29100
|
|
},
|
|
{
|
|
"entropy": 5.093291521072388,
|
|
"epoch": 3.4669446098868373,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038410783841121124,
|
|
"loss": 4.5041,
|
|
"mean_token_accuracy": 0.24359657615423203,
|
|
"num_tokens": 81340822.0,
|
|
"step": 29105
|
|
},
|
|
{
|
|
"entropy": 5.1355701923370365,
|
|
"epoch": 3.467540202501489,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003840705693022248,
|
|
"loss": 4.5359,
|
|
"mean_token_accuracy": 0.24365808069705963,
|
|
"num_tokens": 81354892.0,
|
|
"step": 29110
|
|
},
|
|
{
|
|
"entropy": 5.113315439224243,
|
|
"epoch": 3.4681357951161407,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003840332962810543,
|
|
"loss": 4.4816,
|
|
"mean_token_accuracy": 0.24547092616558075,
|
|
"num_tokens": 81368508.0,
|
|
"step": 29115
|
|
},
|
|
{
|
|
"entropy": 5.1465491771698,
|
|
"epoch": 3.4687313877307924,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003839960193490368,
|
|
"loss": 4.508,
|
|
"mean_token_accuracy": 0.23587109744548798,
|
|
"num_tokens": 81381929.0,
|
|
"step": 29120
|
|
},
|
|
{
|
|
"entropy": 5.25040111541748,
|
|
"epoch": 3.4693269803454436,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003839587385075093,
|
|
"loss": 4.6964,
|
|
"mean_token_accuracy": 0.22479551285505295,
|
|
"num_tokens": 81396192.0,
|
|
"step": 29125
|
|
},
|
|
{
|
|
"entropy": 5.135446166992187,
|
|
"epoch": 3.4699225729600953,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000383921453757809,
|
|
"loss": 4.5278,
|
|
"mean_token_accuracy": 0.24459851682186126,
|
|
"num_tokens": 81411108.0,
|
|
"step": 29130
|
|
},
|
|
{
|
|
"entropy": 5.111453199386597,
|
|
"epoch": 3.470518165574747,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003838841651012733,
|
|
"loss": 4.4809,
|
|
"mean_token_accuracy": 0.24473359435796738,
|
|
"num_tokens": 81424083.0,
|
|
"step": 29135
|
|
},
|
|
{
|
|
"entropy": 5.1466752052307125,
|
|
"epoch": 3.4711137581893983,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038384687253923956,
|
|
"loss": 4.6027,
|
|
"mean_token_accuracy": 0.2289619192481041,
|
|
"num_tokens": 81438676.0,
|
|
"step": 29140
|
|
},
|
|
{
|
|
"entropy": 5.09907636642456,
|
|
"epoch": 3.47170935080405,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038380957607304553,
|
|
"loss": 4.4623,
|
|
"mean_token_accuracy": 0.23972986936569213,
|
|
"num_tokens": 81453000.0,
|
|
"step": 29145
|
|
},
|
|
{
|
|
"entropy": 5.143868398666382,
|
|
"epoch": 3.4723049434187017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003837722757040289,
|
|
"loss": 4.56,
|
|
"mean_token_accuracy": 0.23723453730344773,
|
|
"num_tokens": 81467360.0,
|
|
"step": 29150
|
|
},
|
|
{
|
|
"entropy": 5.1101446628570555,
|
|
"epoch": 3.4729005360333534,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00038373497143352764,
|
|
"loss": 4.499,
|
|
"mean_token_accuracy": 0.242287977039814,
|
|
"num_tokens": 81478850.0,
|
|
"step": 29155
|
|
},
|
|
{
|
|
"entropy": 5.163586378097534,
|
|
"epoch": 3.4734961286480046,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003836976632628797,
|
|
"loss": 4.535,
|
|
"mean_token_accuracy": 0.2486698344349861,
|
|
"num_tokens": 81492450.0,
|
|
"step": 29160
|
|
},
|
|
{
|
|
"entropy": 5.11388258934021,
|
|
"epoch": 3.4740917212626563,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00038366035119342327,
|
|
"loss": 4.5263,
|
|
"mean_token_accuracy": 0.24273287653923034,
|
|
"num_tokens": 81506614.0,
|
|
"step": 29165
|
|
},
|
|
{
|
|
"entropy": 5.121220350265503,
|
|
"epoch": 3.474687313877308,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003836230352264968,
|
|
"loss": 4.559,
|
|
"mean_token_accuracy": 0.24179341197013854,
|
|
"num_tokens": 81520618.0,
|
|
"step": 29170
|
|
},
|
|
{
|
|
"entropy": 5.114096784591675,
|
|
"epoch": 3.4752829064919597,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003835857153634385,
|
|
"loss": 4.4541,
|
|
"mean_token_accuracy": 0.24603590220212937,
|
|
"num_tokens": 81534466.0,
|
|
"step": 29175
|
|
},
|
|
{
|
|
"entropy": 5.021842384338379,
|
|
"epoch": 3.475878499106611,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038354839160558736,
|
|
"loss": 4.4709,
|
|
"mean_token_accuracy": 0.2477358564734459,
|
|
"num_tokens": 81547744.0,
|
|
"step": 29180
|
|
},
|
|
{
|
|
"entropy": 5.120368623733521,
|
|
"epoch": 3.4764740917212626,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003835110639542817,
|
|
"loss": 4.4961,
|
|
"mean_token_accuracy": 0.24741654843091965,
|
|
"num_tokens": 81562152.0,
|
|
"step": 29185
|
|
},
|
|
{
|
|
"entropy": 5.142348003387451,
|
|
"epoch": 3.4770696843359143,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038347373241086075,
|
|
"loss": 4.477,
|
|
"mean_token_accuracy": 0.24092300236225128,
|
|
"num_tokens": 81575999.0,
|
|
"step": 29190
|
|
},
|
|
{
|
|
"entropy": 5.131335830688476,
|
|
"epoch": 3.4776652769505656,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038343639697666337,
|
|
"loss": 4.5038,
|
|
"mean_token_accuracy": 0.2394130691885948,
|
|
"num_tokens": 81589384.0,
|
|
"step": 29195
|
|
},
|
|
{
|
|
"entropy": 5.097676181793213,
|
|
"epoch": 3.4782608695652173,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003833990576530287,
|
|
"loss": 4.4768,
|
|
"mean_token_accuracy": 0.24578756093978882,
|
|
"num_tokens": 81604734.0,
|
|
"step": 29200
|
|
},
|
|
{
|
|
"entropy": 5.1306946754455565,
|
|
"epoch": 3.478856462179869,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003833617144412961,
|
|
"loss": 4.513,
|
|
"mean_token_accuracy": 0.2423120006918907,
|
|
"num_tokens": 81619194.0,
|
|
"step": 29205
|
|
},
|
|
{
|
|
"entropy": 5.163158273696899,
|
|
"epoch": 3.4794520547945207,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000383324367342805,
|
|
"loss": 4.5123,
|
|
"mean_token_accuracy": 0.24180760681629182,
|
|
"num_tokens": 81631739.0,
|
|
"step": 29210
|
|
},
|
|
{
|
|
"entropy": 5.064615297317505,
|
|
"epoch": 3.480047647409172,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0003832870163588949,
|
|
"loss": 4.4545,
|
|
"mean_token_accuracy": 0.24572256505489348,
|
|
"num_tokens": 81647838.0,
|
|
"step": 29215
|
|
},
|
|
{
|
|
"entropy": 5.1196911334991455,
|
|
"epoch": 3.4806432400238236,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038324966149090557,
|
|
"loss": 4.5191,
|
|
"mean_token_accuracy": 0.23707004338502885,
|
|
"num_tokens": 81661193.0,
|
|
"step": 29220
|
|
},
|
|
{
|
|
"entropy": 5.084264183044434,
|
|
"epoch": 3.4812388326384753,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000383212302740177,
|
|
"loss": 4.4624,
|
|
"mean_token_accuracy": 0.24197737574577333,
|
|
"num_tokens": 81676483.0,
|
|
"step": 29225
|
|
},
|
|
{
|
|
"entropy": 5.116731262207031,
|
|
"epoch": 3.481834425253127,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000383174940108049,
|
|
"loss": 4.4515,
|
|
"mean_token_accuracy": 0.2461121305823326,
|
|
"num_tokens": 81689581.0,
|
|
"step": 29230
|
|
},
|
|
{
|
|
"entropy": 5.067478179931641,
|
|
"epoch": 3.4824300178677783,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003831375735958618,
|
|
"loss": 4.5035,
|
|
"mean_token_accuracy": 0.2461158365011215,
|
|
"num_tokens": 81703730.0,
|
|
"step": 29235
|
|
},
|
|
{
|
|
"entropy": 5.0708681583404545,
|
|
"epoch": 3.48302561048243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003831002032049557,
|
|
"loss": 4.4643,
|
|
"mean_token_accuracy": 0.24195368736982345,
|
|
"num_tokens": 81716427.0,
|
|
"step": 29240
|
|
},
|
|
{
|
|
"entropy": 5.127667760848999,
|
|
"epoch": 3.4836212030970817,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038306282893667097,
|
|
"loss": 4.5574,
|
|
"mean_token_accuracy": 0.24135467261075974,
|
|
"num_tokens": 81729090.0,
|
|
"step": 29245
|
|
},
|
|
{
|
|
"entropy": 5.132026958465576,
|
|
"epoch": 3.484216795711733,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038302545079234833,
|
|
"loss": 4.5189,
|
|
"mean_token_accuracy": 0.24221067875623703,
|
|
"num_tokens": 81743531.0,
|
|
"step": 29250
|
|
},
|
|
{
|
|
"entropy": 5.106656789779663,
|
|
"epoch": 3.4848123883263846,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003829880687733284,
|
|
"loss": 4.459,
|
|
"mean_token_accuracy": 0.24291899651288987,
|
|
"num_tokens": 81757494.0,
|
|
"step": 29255
|
|
},
|
|
{
|
|
"entropy": 5.072665405273438,
|
|
"epoch": 3.4854079809410363,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003829506828809521,
|
|
"loss": 4.4571,
|
|
"mean_token_accuracy": 0.2505926162004471,
|
|
"num_tokens": 81769929.0,
|
|
"step": 29260
|
|
},
|
|
{
|
|
"entropy": 5.071054315567016,
|
|
"epoch": 3.486003573555688,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038291329311656013,
|
|
"loss": 4.4415,
|
|
"mean_token_accuracy": 0.2502641022205353,
|
|
"num_tokens": 81784036.0,
|
|
"step": 29265
|
|
},
|
|
{
|
|
"entropy": 5.118906307220459,
|
|
"epoch": 3.4865991661703397,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003828758994814939,
|
|
"loss": 4.5605,
|
|
"mean_token_accuracy": 0.22929191291332246,
|
|
"num_tokens": 81798362.0,
|
|
"step": 29270
|
|
},
|
|
{
|
|
"entropy": 5.12980580329895,
|
|
"epoch": 3.487194758784991,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003828385019770946,
|
|
"loss": 4.5389,
|
|
"mean_token_accuracy": 0.2392653465270996,
|
|
"num_tokens": 81813962.0,
|
|
"step": 29275
|
|
},
|
|
{
|
|
"entropy": 5.206965732574463,
|
|
"epoch": 3.4877903513996427,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038280110060470355,
|
|
"loss": 4.5657,
|
|
"mean_token_accuracy": 0.23775510638952255,
|
|
"num_tokens": 81826957.0,
|
|
"step": 29280
|
|
},
|
|
{
|
|
"entropy": 5.134732866287232,
|
|
"epoch": 3.4883859440142944,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038276369536566224,
|
|
"loss": 4.573,
|
|
"mean_token_accuracy": 0.2317735254764557,
|
|
"num_tokens": 81841319.0,
|
|
"step": 29285
|
|
},
|
|
{
|
|
"entropy": 5.138465166091919,
|
|
"epoch": 3.4889815366289456,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038272628626131246,
|
|
"loss": 4.5385,
|
|
"mean_token_accuracy": 0.243063822388649,
|
|
"num_tokens": 81856515.0,
|
|
"step": 29290
|
|
},
|
|
{
|
|
"entropy": 5.0947675704956055,
|
|
"epoch": 3.4895771292435973,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003826888732929959,
|
|
"loss": 4.4708,
|
|
"mean_token_accuracy": 0.23956049084663392,
|
|
"num_tokens": 81870698.0,
|
|
"step": 29295
|
|
},
|
|
{
|
|
"entropy": 5.056334733963013,
|
|
"epoch": 3.490172721858249,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038265145646205453,
|
|
"loss": 4.3779,
|
|
"mean_token_accuracy": 0.25319150686264036,
|
|
"num_tokens": 81884180.0,
|
|
"step": 29300
|
|
},
|
|
{
|
|
"entropy": 5.110016012191773,
|
|
"epoch": 3.4907683144729007,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00038261403576983044,
|
|
"loss": 4.4226,
|
|
"mean_token_accuracy": 0.24797395169734954,
|
|
"num_tokens": 81897827.0,
|
|
"step": 29305
|
|
},
|
|
{
|
|
"entropy": 5.048312759399414,
|
|
"epoch": 3.491363907087552,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003825766112176659,
|
|
"loss": 4.4043,
|
|
"mean_token_accuracy": 0.24654753655195236,
|
|
"num_tokens": 81911364.0,
|
|
"step": 29310
|
|
},
|
|
{
|
|
"entropy": 5.030928039550782,
|
|
"epoch": 3.4919594997022037,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003825391828069032,
|
|
"loss": 4.4117,
|
|
"mean_token_accuracy": 0.24576332718133925,
|
|
"num_tokens": 81926822.0,
|
|
"step": 29315
|
|
},
|
|
{
|
|
"entropy": 5.143932294845581,
|
|
"epoch": 3.4925550923168553,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003825017505388849,
|
|
"loss": 4.5677,
|
|
"mean_token_accuracy": 0.23582835048437117,
|
|
"num_tokens": 81941517.0,
|
|
"step": 29320
|
|
},
|
|
{
|
|
"entropy": 5.075616502761841,
|
|
"epoch": 3.493150684931507,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003824643144149535,
|
|
"loss": 4.4368,
|
|
"mean_token_accuracy": 0.2516453698277473,
|
|
"num_tokens": 81954941.0,
|
|
"step": 29325
|
|
},
|
|
{
|
|
"entropy": 5.064763021469116,
|
|
"epoch": 3.4937462775461583,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038242687443645196,
|
|
"loss": 4.4249,
|
|
"mean_token_accuracy": 0.24886052310466766,
|
|
"num_tokens": 81967901.0,
|
|
"step": 29330
|
|
},
|
|
{
|
|
"entropy": 5.123205184936523,
|
|
"epoch": 3.49434187016081,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003823894306047231,
|
|
"loss": 4.4646,
|
|
"mean_token_accuracy": 0.2436779782176018,
|
|
"num_tokens": 81981677.0,
|
|
"step": 29335
|
|
},
|
|
{
|
|
"entropy": 5.118592739105225,
|
|
"epoch": 3.4949374627754617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038235198292110997,
|
|
"loss": 4.534,
|
|
"mean_token_accuracy": 0.2389678180217743,
|
|
"num_tokens": 81994534.0,
|
|
"step": 29340
|
|
},
|
|
{
|
|
"entropy": 5.108546257019043,
|
|
"epoch": 3.495533055390113,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038231453138695573,
|
|
"loss": 4.4453,
|
|
"mean_token_accuracy": 0.2564485639333725,
|
|
"num_tokens": 82007427.0,
|
|
"step": 29345
|
|
},
|
|
{
|
|
"entropy": 5.044552326202393,
|
|
"epoch": 3.4961286480047646,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003822770760036037,
|
|
"loss": 4.4341,
|
|
"mean_token_accuracy": 0.24813326001167296,
|
|
"num_tokens": 82019964.0,
|
|
"step": 29350
|
|
},
|
|
{
|
|
"entropy": 5.13080792427063,
|
|
"epoch": 3.4967242406194163,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038223961677239746,
|
|
"loss": 4.535,
|
|
"mean_token_accuracy": 0.23528113961219788,
|
|
"num_tokens": 82033560.0,
|
|
"step": 29355
|
|
},
|
|
{
|
|
"entropy": 5.103008699417114,
|
|
"epoch": 3.497319833234068,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003822021536946804,
|
|
"loss": 4.4032,
|
|
"mean_token_accuracy": 0.25172124356031417,
|
|
"num_tokens": 82047466.0,
|
|
"step": 29360
|
|
},
|
|
{
|
|
"entropy": 5.055095481872558,
|
|
"epoch": 3.4979154258487193,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038216468677179644,
|
|
"loss": 4.4806,
|
|
"mean_token_accuracy": 0.2456493467092514,
|
|
"num_tokens": 82060273.0,
|
|
"step": 29365
|
|
},
|
|
{
|
|
"entropy": 5.12912883758545,
|
|
"epoch": 3.498511018463371,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003821272160050894,
|
|
"loss": 4.5014,
|
|
"mean_token_accuracy": 0.24001599550247193,
|
|
"num_tokens": 82077554.0,
|
|
"step": 29370
|
|
},
|
|
{
|
|
"entropy": 5.194777250289917,
|
|
"epoch": 3.4991066110780227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003820897413959034,
|
|
"loss": 4.6223,
|
|
"mean_token_accuracy": 0.23768283128738404,
|
|
"num_tokens": 82091301.0,
|
|
"step": 29375
|
|
},
|
|
{
|
|
"entropy": 5.213527250289917,
|
|
"epoch": 3.4997022036926744,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003820522629455824,
|
|
"loss": 4.5849,
|
|
"mean_token_accuracy": 0.24345141947269439,
|
|
"num_tokens": 82106669.0,
|
|
"step": 29380
|
|
},
|
|
{
|
|
"entropy": 5.10937533378601,
|
|
"epoch": 3.5002977963073256,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003820147806554708,
|
|
"loss": 4.4652,
|
|
"mean_token_accuracy": 0.24540454745292664,
|
|
"num_tokens": 82121721.0,
|
|
"step": 29385
|
|
},
|
|
{
|
|
"entropy": 5.156639337539673,
|
|
"epoch": 3.5008933889219773,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00038197729452691304,
|
|
"loss": 4.5925,
|
|
"mean_token_accuracy": 0.23804470002651215,
|
|
"num_tokens": 82134857.0,
|
|
"step": 29390
|
|
},
|
|
{
|
|
"entropy": 5.141063547134399,
|
|
"epoch": 3.501488981536629,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003819398045612536,
|
|
"loss": 4.5605,
|
|
"mean_token_accuracy": 0.2315441444516182,
|
|
"num_tokens": 82148007.0,
|
|
"step": 29395
|
|
},
|
|
{
|
|
"entropy": 5.061050319671631,
|
|
"epoch": 3.5020845741512803,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038190231075983734,
|
|
"loss": 4.471,
|
|
"mean_token_accuracy": 0.24476219117641448,
|
|
"num_tokens": 82162758.0,
|
|
"step": 29400
|
|
},
|
|
{
|
|
"entropy": 5.0831211566925045,
|
|
"epoch": 3.502680166765932,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038186481312400887,
|
|
"loss": 4.5101,
|
|
"mean_token_accuracy": 0.24335111528635026,
|
|
"num_tokens": 82177881.0,
|
|
"step": 29405
|
|
},
|
|
{
|
|
"entropy": 5.126891994476319,
|
|
"epoch": 3.5032757593805837,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038182731165511334,
|
|
"loss": 4.5148,
|
|
"mean_token_accuracy": 0.2417263239622116,
|
|
"num_tokens": 82193685.0,
|
|
"step": 29410
|
|
},
|
|
{
|
|
"entropy": 5.138103914260864,
|
|
"epoch": 3.5038713519952354,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003817898063544959,
|
|
"loss": 4.513,
|
|
"mean_token_accuracy": 0.24035827219486236,
|
|
"num_tokens": 82207938.0,
|
|
"step": 29415
|
|
},
|
|
{
|
|
"entropy": 5.156846714019776,
|
|
"epoch": 3.504466944609887,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038175229722350174,
|
|
"loss": 4.6149,
|
|
"mean_token_accuracy": 0.23643269538879394,
|
|
"num_tokens": 82221953.0,
|
|
"step": 29420
|
|
},
|
|
{
|
|
"entropy": 5.091891145706176,
|
|
"epoch": 3.5050625372245383,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003817147842634762,
|
|
"loss": 4.5163,
|
|
"mean_token_accuracy": 0.23834772706031798,
|
|
"num_tokens": 82237231.0,
|
|
"step": 29425
|
|
},
|
|
{
|
|
"entropy": 5.054409027099609,
|
|
"epoch": 3.50565812983919,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003816772674757649,
|
|
"loss": 4.4027,
|
|
"mean_token_accuracy": 0.2485136717557907,
|
|
"num_tokens": 82250584.0,
|
|
"step": 29430
|
|
},
|
|
{
|
|
"entropy": 5.148538446426391,
|
|
"epoch": 3.5062537224538417,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038163974686171345,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.23659974634647368,
|
|
"num_tokens": 82264539.0,
|
|
"step": 29435
|
|
},
|
|
{
|
|
"entropy": 5.120200490951538,
|
|
"epoch": 3.506849315068493,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003816022224226676,
|
|
"loss": 4.5144,
|
|
"mean_token_accuracy": 0.24496261328458785,
|
|
"num_tokens": 82280426.0,
|
|
"step": 29440
|
|
},
|
|
{
|
|
"entropy": 5.128129625320435,
|
|
"epoch": 3.5074449076831447,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003815646941599734,
|
|
"loss": 4.5065,
|
|
"mean_token_accuracy": 0.2500070184469223,
|
|
"num_tokens": 82293767.0,
|
|
"step": 29445
|
|
},
|
|
{
|
|
"entropy": 5.096526145935059,
|
|
"epoch": 3.5080405002977963,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038152716207497697,
|
|
"loss": 4.3985,
|
|
"mean_token_accuracy": 0.2531888872385025,
|
|
"num_tokens": 82306470.0,
|
|
"step": 29450
|
|
},
|
|
{
|
|
"entropy": 5.11039366722107,
|
|
"epoch": 3.508636092912448,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003814896261690243,
|
|
"loss": 4.535,
|
|
"mean_token_accuracy": 0.2408464953303337,
|
|
"num_tokens": 82319769.0,
|
|
"step": 29455
|
|
},
|
|
{
|
|
"entropy": 4.998794937133789,
|
|
"epoch": 3.5092316855270993,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000381452086443462,
|
|
"loss": 4.4029,
|
|
"mean_token_accuracy": 0.25084176659584045,
|
|
"num_tokens": 82332783.0,
|
|
"step": 29460
|
|
},
|
|
{
|
|
"entropy": 5.211868333816528,
|
|
"epoch": 3.509827278141751,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003814145428996363,
|
|
"loss": 4.608,
|
|
"mean_token_accuracy": 0.23461947292089463,
|
|
"num_tokens": 82347702.0,
|
|
"step": 29465
|
|
},
|
|
{
|
|
"entropy": 5.135992574691772,
|
|
"epoch": 3.5104228707564027,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003813769955388941,
|
|
"loss": 4.5135,
|
|
"mean_token_accuracy": 0.24249772727489471,
|
|
"num_tokens": 82361495.0,
|
|
"step": 29470
|
|
},
|
|
{
|
|
"entropy": 5.058071756362915,
|
|
"epoch": 3.5110184633710544,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038133944436258196,
|
|
"loss": 4.464,
|
|
"mean_token_accuracy": 0.24558622539043426,
|
|
"num_tokens": 82375729.0,
|
|
"step": 29475
|
|
},
|
|
{
|
|
"entropy": 5.066173791885376,
|
|
"epoch": 3.5116140559857056,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003813018893720468,
|
|
"loss": 4.4889,
|
|
"mean_token_accuracy": 0.23422738015651703,
|
|
"num_tokens": 82390766.0,
|
|
"step": 29480
|
|
},
|
|
{
|
|
"entropy": 5.122262382507325,
|
|
"epoch": 3.5122096486003573,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003812643305686358,
|
|
"loss": 4.5503,
|
|
"mean_token_accuracy": 0.2420456141233444,
|
|
"num_tokens": 82405240.0,
|
|
"step": 29485
|
|
},
|
|
{
|
|
"entropy": 5.132363605499267,
|
|
"epoch": 3.512805241215009,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000381226767953696,
|
|
"loss": 4.4633,
|
|
"mean_token_accuracy": 0.23915163278579712,
|
|
"num_tokens": 82420654.0,
|
|
"step": 29490
|
|
},
|
|
{
|
|
"entropy": 5.096292448043823,
|
|
"epoch": 3.5134008338296603,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003811892015285748,
|
|
"loss": 4.4754,
|
|
"mean_token_accuracy": 0.24377948194742202,
|
|
"num_tokens": 82435651.0,
|
|
"step": 29495
|
|
},
|
|
{
|
|
"entropy": 5.15273756980896,
|
|
"epoch": 3.513996426444312,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00038115163129461943,
|
|
"loss": 4.5797,
|
|
"mean_token_accuracy": 0.2387613296508789,
|
|
"num_tokens": 82451614.0,
|
|
"step": 29500
|
|
},
|
|
{
|
|
"entropy": 5.170421075820923,
|
|
"epoch": 3.5145920190589637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038111405725317784,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.2378142297267914,
|
|
"num_tokens": 82466987.0,
|
|
"step": 29505
|
|
},
|
|
{
|
|
"entropy": 5.0387226104736325,
|
|
"epoch": 3.5151876116736154,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0003810764794055974,
|
|
"loss": 4.4205,
|
|
"mean_token_accuracy": 0.24908000528812407,
|
|
"num_tokens": 82482139.0,
|
|
"step": 29510
|
|
},
|
|
{
|
|
"entropy": 5.053325033187866,
|
|
"epoch": 3.515783204288267,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003810388977532262,
|
|
"loss": 4.465,
|
|
"mean_token_accuracy": 0.24014006853103637,
|
|
"num_tokens": 82495045.0,
|
|
"step": 29515
|
|
},
|
|
{
|
|
"entropy": 5.08507513999939,
|
|
"epoch": 3.5163787969029183,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003810013122974122,
|
|
"loss": 4.5281,
|
|
"mean_token_accuracy": 0.2419249877333641,
|
|
"num_tokens": 82508675.0,
|
|
"step": 29520
|
|
},
|
|
{
|
|
"entropy": 5.110270547866821,
|
|
"epoch": 3.51697438951757,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038096372303950333,
|
|
"loss": 4.4808,
|
|
"mean_token_accuracy": 0.2548149973154068,
|
|
"num_tokens": 82521552.0,
|
|
"step": 29525
|
|
},
|
|
{
|
|
"entropy": 5.197235441207885,
|
|
"epoch": 3.5175699821322217,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003809261299808481,
|
|
"loss": 4.6364,
|
|
"mean_token_accuracy": 0.2269456461071968,
|
|
"num_tokens": 82535746.0,
|
|
"step": 29530
|
|
},
|
|
{
|
|
"entropy": 5.178350257873535,
|
|
"epoch": 3.518165574746873,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038088853312279473,
|
|
"loss": 4.5588,
|
|
"mean_token_accuracy": 0.237230384349823,
|
|
"num_tokens": 82550996.0,
|
|
"step": 29535
|
|
},
|
|
{
|
|
"entropy": 5.103149461746216,
|
|
"epoch": 3.5187611673615247,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003808509324666919,
|
|
"loss": 4.4896,
|
|
"mean_token_accuracy": 0.2487146645784378,
|
|
"num_tokens": 82564592.0,
|
|
"step": 29540
|
|
},
|
|
{
|
|
"entropy": 5.11358675956726,
|
|
"epoch": 3.5193567599761764,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003808133280138882,
|
|
"loss": 4.515,
|
|
"mean_token_accuracy": 0.24334771037101746,
|
|
"num_tokens": 82577623.0,
|
|
"step": 29545
|
|
},
|
|
{
|
|
"entropy": 5.049162340164185,
|
|
"epoch": 3.5199523525908276,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003807757197657325,
|
|
"loss": 4.3955,
|
|
"mean_token_accuracy": 0.24688447266817093,
|
|
"num_tokens": 82591171.0,
|
|
"step": 29550
|
|
},
|
|
{
|
|
"entropy": 5.089665222167969,
|
|
"epoch": 3.5205479452054793,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003807381077235737,
|
|
"loss": 4.5504,
|
|
"mean_token_accuracy": 0.2398604542016983,
|
|
"num_tokens": 82604768.0,
|
|
"step": 29555
|
|
},
|
|
{
|
|
"entropy": 5.064856481552124,
|
|
"epoch": 3.521143537820131,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003807004918887608,
|
|
"loss": 4.4433,
|
|
"mean_token_accuracy": 0.24974773377180098,
|
|
"num_tokens": 82618463.0,
|
|
"step": 29560
|
|
},
|
|
{
|
|
"entropy": 5.16410984992981,
|
|
"epoch": 3.5217391304347827,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003806628722626433,
|
|
"loss": 4.6692,
|
|
"mean_token_accuracy": 0.23477694094181062,
|
|
"num_tokens": 82631786.0,
|
|
"step": 29565
|
|
},
|
|
{
|
|
"entropy": 5.099377632141113,
|
|
"epoch": 3.5223347230494344,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003806252488465703,
|
|
"loss": 4.4242,
|
|
"mean_token_accuracy": 0.2556456714868546,
|
|
"num_tokens": 82645042.0,
|
|
"step": 29570
|
|
},
|
|
{
|
|
"entropy": 5.081893587112427,
|
|
"epoch": 3.5229303156640857,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003805876216418914,
|
|
"loss": 4.4884,
|
|
"mean_token_accuracy": 0.24062208831310272,
|
|
"num_tokens": 82659281.0,
|
|
"step": 29575
|
|
},
|
|
{
|
|
"entropy": 5.0552277088165285,
|
|
"epoch": 3.5235259082787374,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000380549990649956,
|
|
"loss": 4.4382,
|
|
"mean_token_accuracy": 0.24980514794588088,
|
|
"num_tokens": 82675978.0,
|
|
"step": 29580
|
|
},
|
|
{
|
|
"entropy": 5.196321439743042,
|
|
"epoch": 3.524121500893389,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00038051235587211417,
|
|
"loss": 4.5234,
|
|
"mean_token_accuracy": 0.24229825884103776,
|
|
"num_tokens": 82689636.0,
|
|
"step": 29585
|
|
},
|
|
{
|
|
"entropy": 5.168427181243897,
|
|
"epoch": 3.5247170935080403,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003804747173097157,
|
|
"loss": 4.5523,
|
|
"mean_token_accuracy": 0.23731330186128616,
|
|
"num_tokens": 82701940.0,
|
|
"step": 29590
|
|
},
|
|
{
|
|
"entropy": 5.057218265533447,
|
|
"epoch": 3.525312686122692,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003804370749641106,
|
|
"loss": 4.3915,
|
|
"mean_token_accuracy": 0.24952039420604705,
|
|
"num_tokens": 82715052.0,
|
|
"step": 29595
|
|
},
|
|
{
|
|
"entropy": 5.094235229492187,
|
|
"epoch": 3.5259082787373437,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00038039942883664904,
|
|
"loss": 4.5321,
|
|
"mean_token_accuracy": 0.23899976313114166,
|
|
"num_tokens": 82730332.0,
|
|
"step": 29600
|
|
},
|
|
{
|
|
"entropy": 5.065233564376831,
|
|
"epoch": 3.5265038713519954,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00038036177892868133,
|
|
"loss": 4.4057,
|
|
"mean_token_accuracy": 0.24614049941301347,
|
|
"num_tokens": 82747001.0,
|
|
"step": 29605
|
|
},
|
|
{
|
|
"entropy": 5.114808034896851,
|
|
"epoch": 3.527099463966647,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000380324125241558,
|
|
"loss": 4.4793,
|
|
"mean_token_accuracy": 0.23839416056871415,
|
|
"num_tokens": 82761525.0,
|
|
"step": 29610
|
|
},
|
|
{
|
|
"entropy": 5.103721189498901,
|
|
"epoch": 3.5276950565812983,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00038028646777662947,
|
|
"loss": 4.4781,
|
|
"mean_token_accuracy": 0.24605531096458436,
|
|
"num_tokens": 82775278.0,
|
|
"step": 29615
|
|
},
|
|
{
|
|
"entropy": 5.064964008331299,
|
|
"epoch": 3.52829064919595,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003802488065352465,
|
|
"loss": 4.4728,
|
|
"mean_token_accuracy": 0.23919305056333542,
|
|
"num_tokens": 82790729.0,
|
|
"step": 29620
|
|
},
|
|
{
|
|
"entropy": 5.112843179702759,
|
|
"epoch": 3.5288862418106017,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00038021114151876,
|
|
"loss": 4.5326,
|
|
"mean_token_accuracy": 0.24004292935132981,
|
|
"num_tokens": 82803812.0,
|
|
"step": 29625
|
|
},
|
|
{
|
|
"entropy": 5.131251525878906,
|
|
"epoch": 3.529481834425253,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038017347272852086,
|
|
"loss": 4.5444,
|
|
"mean_token_accuracy": 0.24003096371889115,
|
|
"num_tokens": 82820011.0,
|
|
"step": 29630
|
|
},
|
|
{
|
|
"entropy": 5.175977516174316,
|
|
"epoch": 3.5300774270399047,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003801358001658804,
|
|
"loss": 4.6104,
|
|
"mean_token_accuracy": 0.23378413468599318,
|
|
"num_tokens": 82834641.0,
|
|
"step": 29635
|
|
},
|
|
{
|
|
"entropy": 5.154147005081176,
|
|
"epoch": 3.5306730196545564,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038009812383218956,
|
|
"loss": 4.5268,
|
|
"mean_token_accuracy": 0.2458646073937416,
|
|
"num_tokens": 82849409.0,
|
|
"step": 29640
|
|
},
|
|
{
|
|
"entropy": 5.126295042037964,
|
|
"epoch": 3.5312686122692076,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038006044372880006,
|
|
"loss": 4.4961,
|
|
"mean_token_accuracy": 0.24684688746929168,
|
|
"num_tokens": 82861557.0,
|
|
"step": 29645
|
|
},
|
|
{
|
|
"entropy": 5.103320503234864,
|
|
"epoch": 3.5318642048838593,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038002275985706316,
|
|
"loss": 4.4651,
|
|
"mean_token_accuracy": 0.24569444209337235,
|
|
"num_tokens": 82875716.0,
|
|
"step": 29650
|
|
},
|
|
{
|
|
"entropy": 5.118329191207886,
|
|
"epoch": 3.532459797498511,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037998507221833066,
|
|
"loss": 4.4751,
|
|
"mean_token_accuracy": 0.24219005554914474,
|
|
"num_tokens": 82888468.0,
|
|
"step": 29655
|
|
},
|
|
{
|
|
"entropy": 5.140690422058105,
|
|
"epoch": 3.5330553901131627,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037994738081395426,
|
|
"loss": 4.5054,
|
|
"mean_token_accuracy": 0.24395187199115753,
|
|
"num_tokens": 82901715.0,
|
|
"step": 29660
|
|
},
|
|
{
|
|
"entropy": 5.106176424026489,
|
|
"epoch": 3.5336509827278144,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000379909685645286,
|
|
"loss": 4.4491,
|
|
"mean_token_accuracy": 0.2480965182185173,
|
|
"num_tokens": 82915827.0,
|
|
"step": 29665
|
|
},
|
|
{
|
|
"entropy": 5.099270534515381,
|
|
"epoch": 3.5342465753424657,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037987198671367783,
|
|
"loss": 4.457,
|
|
"mean_token_accuracy": 0.24107633531093597,
|
|
"num_tokens": 82929147.0,
|
|
"step": 29670
|
|
},
|
|
{
|
|
"entropy": 5.075956678390503,
|
|
"epoch": 3.5348421679571174,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003798342840204821,
|
|
"loss": 4.5082,
|
|
"mean_token_accuracy": 0.23962303698062898,
|
|
"num_tokens": 82943151.0,
|
|
"step": 29675
|
|
},
|
|
{
|
|
"entropy": 5.08062891960144,
|
|
"epoch": 3.535437760571769,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000379796577567051,
|
|
"loss": 4.5148,
|
|
"mean_token_accuracy": 0.23994263112545014,
|
|
"num_tokens": 82958518.0,
|
|
"step": 29680
|
|
},
|
|
{
|
|
"entropy": 5.146578645706176,
|
|
"epoch": 3.5360333531864203,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000379758867354737,
|
|
"loss": 4.5139,
|
|
"mean_token_accuracy": 0.23609918504953384,
|
|
"num_tokens": 82973771.0,
|
|
"step": 29685
|
|
},
|
|
{
|
|
"entropy": 5.185872507095337,
|
|
"epoch": 3.536628945801072,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00037972115338489275,
|
|
"loss": 4.5867,
|
|
"mean_token_accuracy": 0.23114873468875885,
|
|
"num_tokens": 82988721.0,
|
|
"step": 29690
|
|
},
|
|
{
|
|
"entropy": 5.126970195770264,
|
|
"epoch": 3.5372245384157237,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003796834356588711,
|
|
"loss": 4.4701,
|
|
"mean_token_accuracy": 0.24162937551736832,
|
|
"num_tokens": 83002392.0,
|
|
"step": 29695
|
|
},
|
|
{
|
|
"entropy": 5.042786693572998,
|
|
"epoch": 3.537820131030375,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00037964571417802473,
|
|
"loss": 4.4366,
|
|
"mean_token_accuracy": 0.24830861687660216,
|
|
"num_tokens": 83017813.0,
|
|
"step": 29700
|
|
},
|
|
{
|
|
"entropy": 5.028917360305786,
|
|
"epoch": 3.5384157236450267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003796079889437068,
|
|
"loss": 4.4151,
|
|
"mean_token_accuracy": 0.2544854372739792,
|
|
"num_tokens": 83033164.0,
|
|
"step": 29705
|
|
},
|
|
{
|
|
"entropy": 5.0550415992736815,
|
|
"epoch": 3.5390113162596784,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037957025995727036,
|
|
"loss": 4.4189,
|
|
"mean_token_accuracy": 0.2514521047472954,
|
|
"num_tokens": 83046635.0,
|
|
"step": 29710
|
|
},
|
|
{
|
|
"entropy": 5.040569877624511,
|
|
"epoch": 3.53960690887433,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00037953252722006873,
|
|
"loss": 4.4603,
|
|
"mean_token_accuracy": 0.24424469321966172,
|
|
"num_tokens": 83061606.0,
|
|
"step": 29715
|
|
},
|
|
{
|
|
"entropy": 5.060636520385742,
|
|
"epoch": 3.5402025014889817,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003794947907334553,
|
|
"loss": 4.4149,
|
|
"mean_token_accuracy": 0.253630793094635,
|
|
"num_tokens": 83074907.0,
|
|
"step": 29720
|
|
},
|
|
{
|
|
"entropy": 5.09439435005188,
|
|
"epoch": 3.540798094103633,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003794570504987836,
|
|
"loss": 4.5104,
|
|
"mean_token_accuracy": 0.24456507116556167,
|
|
"num_tokens": 83089332.0,
|
|
"step": 29725
|
|
},
|
|
{
|
|
"entropy": 5.145777606964112,
|
|
"epoch": 3.5413936867182847,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00037941930651740736,
|
|
"loss": 4.542,
|
|
"mean_token_accuracy": 0.23892636895179747,
|
|
"num_tokens": 83102854.0,
|
|
"step": 29730
|
|
},
|
|
{
|
|
"entropy": 5.162043190002441,
|
|
"epoch": 3.5419892793329364,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037938155879068037,
|
|
"loss": 4.531,
|
|
"mean_token_accuracy": 0.23907847106456756,
|
|
"num_tokens": 83116819.0,
|
|
"step": 29735
|
|
},
|
|
{
|
|
"entropy": 5.173544836044312,
|
|
"epoch": 3.5425848719475876,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003793438073199565,
|
|
"loss": 4.6033,
|
|
"mean_token_accuracy": 0.23527873903512955,
|
|
"num_tokens": 83132209.0,
|
|
"step": 29740
|
|
},
|
|
{
|
|
"entropy": 5.073328161239624,
|
|
"epoch": 3.5431804645622393,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037930605210659003,
|
|
"loss": 4.3899,
|
|
"mean_token_accuracy": 0.2503674626350403,
|
|
"num_tokens": 83145868.0,
|
|
"step": 29745
|
|
},
|
|
{
|
|
"entropy": 5.21679720878601,
|
|
"epoch": 3.543776057176891,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00037926829315193506,
|
|
"loss": 4.6549,
|
|
"mean_token_accuracy": 0.22721559405326844,
|
|
"num_tokens": 83160991.0,
|
|
"step": 29750
|
|
},
|
|
{
|
|
"entropy": 5.144850492477417,
|
|
"epoch": 3.5443716497915427,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037923053045734595,
|
|
"loss": 4.6006,
|
|
"mean_token_accuracy": 0.2375075027346611,
|
|
"num_tokens": 83173027.0,
|
|
"step": 29755
|
|
},
|
|
{
|
|
"entropy": 5.030132532119751,
|
|
"epoch": 3.5449672424061944,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003791927640241771,
|
|
"loss": 4.4051,
|
|
"mean_token_accuracy": 0.2548538029193878,
|
|
"num_tokens": 83185681.0,
|
|
"step": 29760
|
|
},
|
|
{
|
|
"entropy": 5.172167825698852,
|
|
"epoch": 3.5455628350208457,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037915499385378327,
|
|
"loss": 4.5926,
|
|
"mean_token_accuracy": 0.2349323198199272,
|
|
"num_tokens": 83198781.0,
|
|
"step": 29765
|
|
},
|
|
{
|
|
"entropy": 5.116758728027344,
|
|
"epoch": 3.5461584276354974,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037911721994751907,
|
|
"loss": 4.4804,
|
|
"mean_token_accuracy": 0.24569777995347977,
|
|
"num_tokens": 83211928.0,
|
|
"step": 29770
|
|
},
|
|
{
|
|
"entropy": 5.07128758430481,
|
|
"epoch": 3.546754020250149,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00037907944230673957,
|
|
"loss": 4.4998,
|
|
"mean_token_accuracy": 0.23679215610027313,
|
|
"num_tokens": 83224457.0,
|
|
"step": 29775
|
|
},
|
|
{
|
|
"entropy": 5.063657951354981,
|
|
"epoch": 3.5473496128648003,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037904166093279964,
|
|
"loss": 4.4706,
|
|
"mean_token_accuracy": 0.24621828347444535,
|
|
"num_tokens": 83238576.0,
|
|
"step": 29780
|
|
},
|
|
{
|
|
"entropy": 5.142461109161377,
|
|
"epoch": 3.547945205479452,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037900387582705453,
|
|
"loss": 4.5242,
|
|
"mean_token_accuracy": 0.2345454588532448,
|
|
"num_tokens": 83252387.0,
|
|
"step": 29785
|
|
},
|
|
{
|
|
"entropy": 5.051406812667847,
|
|
"epoch": 3.5485407980941037,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003789660869908595,
|
|
"loss": 4.482,
|
|
"mean_token_accuracy": 0.24488673657178878,
|
|
"num_tokens": 83265317.0,
|
|
"step": 29790
|
|
},
|
|
{
|
|
"entropy": 5.089718580245972,
|
|
"epoch": 3.549136390708755,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037892829442556986,
|
|
"loss": 4.4699,
|
|
"mean_token_accuracy": 0.25474153757095336,
|
|
"num_tokens": 83280657.0,
|
|
"step": 29795
|
|
},
|
|
{
|
|
"entropy": 5.157651281356811,
|
|
"epoch": 3.5497319833234067,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003788904981325414,
|
|
"loss": 4.4741,
|
|
"mean_token_accuracy": 0.2470400497317314,
|
|
"num_tokens": 83293398.0,
|
|
"step": 29800
|
|
},
|
|
{
|
|
"entropy": 5.103576135635376,
|
|
"epoch": 3.5503275759380584,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00037885269811312975,
|
|
"loss": 4.4954,
|
|
"mean_token_accuracy": 0.24703205078840257,
|
|
"num_tokens": 83305858.0,
|
|
"step": 29805
|
|
},
|
|
{
|
|
"entropy": 5.053570222854614,
|
|
"epoch": 3.55092316855271,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037881489436869054,
|
|
"loss": 4.5018,
|
|
"mean_token_accuracy": 0.25212316066026685,
|
|
"num_tokens": 83318524.0,
|
|
"step": 29810
|
|
},
|
|
{
|
|
"entropy": 5.139769172668457,
|
|
"epoch": 3.5515187611673618,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003787770869005799,
|
|
"loss": 4.5648,
|
|
"mean_token_accuracy": 0.23255048096179962,
|
|
"num_tokens": 83331304.0,
|
|
"step": 29815
|
|
},
|
|
{
|
|
"entropy": 5.124501943588257,
|
|
"epoch": 3.552114353782013,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003787392757101539,
|
|
"loss": 4.4794,
|
|
"mean_token_accuracy": 0.24408266991376876,
|
|
"num_tokens": 83342857.0,
|
|
"step": 29820
|
|
},
|
|
{
|
|
"entropy": 5.070353746414185,
|
|
"epoch": 3.5527099463966647,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003787014607987687,
|
|
"loss": 4.4637,
|
|
"mean_token_accuracy": 0.24325990527868271,
|
|
"num_tokens": 83359294.0,
|
|
"step": 29825
|
|
},
|
|
{
|
|
"entropy": 5.139788246154785,
|
|
"epoch": 3.5533055390113164,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003786636421677807,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.24244061559438707,
|
|
"num_tokens": 83372596.0,
|
|
"step": 29830
|
|
},
|
|
{
|
|
"entropy": 5.117879390716553,
|
|
"epoch": 3.5539011316259677,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003786258198185465,
|
|
"loss": 4.5559,
|
|
"mean_token_accuracy": 0.24420059323310853,
|
|
"num_tokens": 83385799.0,
|
|
"step": 29835
|
|
},
|
|
{
|
|
"entropy": 5.028677988052368,
|
|
"epoch": 3.5544967242406194,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003785879937524225,
|
|
"loss": 4.4107,
|
|
"mean_token_accuracy": 0.25201784521341325,
|
|
"num_tokens": 83399616.0,
|
|
"step": 29840
|
|
},
|
|
{
|
|
"entropy": 5.080384969711304,
|
|
"epoch": 3.555092316855271,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037855016397076574,
|
|
"loss": 4.4797,
|
|
"mean_token_accuracy": 0.24385724663734437,
|
|
"num_tokens": 83413046.0,
|
|
"step": 29845
|
|
},
|
|
{
|
|
"entropy": 5.042868757247925,
|
|
"epoch": 3.5556879094699223,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003785123304749329,
|
|
"loss": 4.4051,
|
|
"mean_token_accuracy": 0.2561567217111588,
|
|
"num_tokens": 83426322.0,
|
|
"step": 29850
|
|
},
|
|
{
|
|
"entropy": 5.139514446258545,
|
|
"epoch": 3.556283502084574,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000378474493266281,
|
|
"loss": 4.5034,
|
|
"mean_token_accuracy": 0.24532950669527054,
|
|
"num_tokens": 83438993.0,
|
|
"step": 29855
|
|
},
|
|
{
|
|
"entropy": 5.128561925888062,
|
|
"epoch": 3.5568790946992257,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003784366523461674,
|
|
"loss": 4.509,
|
|
"mean_token_accuracy": 0.2483025535941124,
|
|
"num_tokens": 83453199.0,
|
|
"step": 29860
|
|
},
|
|
{
|
|
"entropy": 5.147268962860108,
|
|
"epoch": 3.5574746873138774,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003783988077159491,
|
|
"loss": 4.5337,
|
|
"mean_token_accuracy": 0.24802985340356826,
|
|
"num_tokens": 83467508.0,
|
|
"step": 29865
|
|
},
|
|
{
|
|
"entropy": 5.095188188552856,
|
|
"epoch": 3.558070279928529,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003783609593769838,
|
|
"loss": 4.4872,
|
|
"mean_token_accuracy": 0.2447495400905609,
|
|
"num_tokens": 83481089.0,
|
|
"step": 29870
|
|
},
|
|
{
|
|
"entropy": 5.067273902893066,
|
|
"epoch": 3.5586658725431803,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037832310733062883,
|
|
"loss": 4.4678,
|
|
"mean_token_accuracy": 0.23844107687473298,
|
|
"num_tokens": 83497286.0,
|
|
"step": 29875
|
|
},
|
|
{
|
|
"entropy": 5.2055583000183105,
|
|
"epoch": 3.559261465157832,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00037828525157824214,
|
|
"loss": 4.5682,
|
|
"mean_token_accuracy": 0.23968013226985932,
|
|
"num_tokens": 83512998.0,
|
|
"step": 29880
|
|
},
|
|
{
|
|
"entropy": 5.108141613006592,
|
|
"epoch": 3.5598570577724837,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00037824739212118124,
|
|
"loss": 4.4596,
|
|
"mean_token_accuracy": 0.24237576276063919,
|
|
"num_tokens": 83527037.0,
|
|
"step": 29885
|
|
},
|
|
{
|
|
"entropy": 5.093314599990845,
|
|
"epoch": 3.560452650387135,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003782095289608044,
|
|
"loss": 4.5379,
|
|
"mean_token_accuracy": 0.2411542758345604,
|
|
"num_tokens": 83541734.0,
|
|
"step": 29890
|
|
},
|
|
{
|
|
"entropy": 5.103479862213135,
|
|
"epoch": 3.5610482430017867,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00037817166209846954,
|
|
"loss": 4.5005,
|
|
"mean_token_accuracy": 0.24055024832487107,
|
|
"num_tokens": 83555273.0,
|
|
"step": 29895
|
|
},
|
|
{
|
|
"entropy": 5.120006847381592,
|
|
"epoch": 3.5616438356164384,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003781337915355348,
|
|
"loss": 4.4999,
|
|
"mean_token_accuracy": 0.24360002875328063,
|
|
"num_tokens": 83568520.0,
|
|
"step": 29900
|
|
},
|
|
{
|
|
"entropy": 5.161382102966309,
|
|
"epoch": 3.56223942823109,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003780959172733588,
|
|
"loss": 4.6098,
|
|
"mean_token_accuracy": 0.23277296572923661,
|
|
"num_tokens": 83583926.0,
|
|
"step": 29905
|
|
},
|
|
{
|
|
"entropy": 5.123368883132935,
|
|
"epoch": 3.5628350208457418,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00037805803931329976,
|
|
"loss": 4.5047,
|
|
"mean_token_accuracy": 0.24267435520887376,
|
|
"num_tokens": 83597876.0,
|
|
"step": 29910
|
|
},
|
|
{
|
|
"entropy": 5.101925468444824,
|
|
"epoch": 3.563430613460393,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003780201576567164,
|
|
"loss": 4.4783,
|
|
"mean_token_accuracy": 0.24835588037967682,
|
|
"num_tokens": 83612579.0,
|
|
"step": 29915
|
|
},
|
|
{
|
|
"entropy": 5.117383337020874,
|
|
"epoch": 3.5640262060750447,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037798227230496754,
|
|
"loss": 4.5037,
|
|
"mean_token_accuracy": 0.24369210004806519,
|
|
"num_tokens": 83624288.0,
|
|
"step": 29920
|
|
},
|
|
{
|
|
"entropy": 5.043417978286743,
|
|
"epoch": 3.5646217986896964,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00037794438325941207,
|
|
"loss": 4.4181,
|
|
"mean_token_accuracy": 0.24707353115081787,
|
|
"num_tokens": 83640731.0,
|
|
"step": 29925
|
|
},
|
|
{
|
|
"entropy": 5.135455513000489,
|
|
"epoch": 3.5652173913043477,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003779064905214088,
|
|
"loss": 4.4919,
|
|
"mean_token_accuracy": 0.24273594319820405,
|
|
"num_tokens": 83652950.0,
|
|
"step": 29930
|
|
},
|
|
{
|
|
"entropy": 5.159612083435059,
|
|
"epoch": 3.5658129839189994,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003778685940923171,
|
|
"loss": 4.5591,
|
|
"mean_token_accuracy": 0.23357920795679094,
|
|
"num_tokens": 83665494.0,
|
|
"step": 29935
|
|
},
|
|
{
|
|
"entropy": 5.138350772857666,
|
|
"epoch": 3.566408576533651,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00037783069397349624,
|
|
"loss": 4.5033,
|
|
"mean_token_accuracy": 0.2366756960749626,
|
|
"num_tokens": 83680525.0,
|
|
"step": 29940
|
|
},
|
|
{
|
|
"entropy": 5.122481870651245,
|
|
"epoch": 3.5670041691483023,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00037779279016630555,
|
|
"loss": 4.5165,
|
|
"mean_token_accuracy": 0.24166320413351058,
|
|
"num_tokens": 83695907.0,
|
|
"step": 29945
|
|
},
|
|
{
|
|
"entropy": 5.0981041431427006,
|
|
"epoch": 3.567599761762954,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003777548826721046,
|
|
"loss": 4.557,
|
|
"mean_token_accuracy": 0.24262532442808152,
|
|
"num_tokens": 83710548.0,
|
|
"step": 29950
|
|
},
|
|
{
|
|
"entropy": 5.096738719940186,
|
|
"epoch": 3.5681953543776057,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000377716971492253,
|
|
"loss": 4.4714,
|
|
"mean_token_accuracy": 0.23984990119934083,
|
|
"num_tokens": 83723557.0,
|
|
"step": 29955
|
|
},
|
|
{
|
|
"entropy": 5.195137929916382,
|
|
"epoch": 3.5687909469922574,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00037767905662811074,
|
|
"loss": 4.5201,
|
|
"mean_token_accuracy": 0.24573925584554673,
|
|
"num_tokens": 83735586.0,
|
|
"step": 29960
|
|
},
|
|
{
|
|
"entropy": 5.176673746109008,
|
|
"epoch": 3.569386539606909,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037764113808103766,
|
|
"loss": 4.5762,
|
|
"mean_token_accuracy": 0.2351652428507805,
|
|
"num_tokens": 83749577.0,
|
|
"step": 29965
|
|
},
|
|
{
|
|
"entropy": 5.103313446044922,
|
|
"epoch": 3.5699821322215604,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00037760321585239375,
|
|
"loss": 4.5269,
|
|
"mean_token_accuracy": 0.23787364661693572,
|
|
"num_tokens": 83763069.0,
|
|
"step": 29970
|
|
},
|
|
{
|
|
"entropy": 5.120736217498779,
|
|
"epoch": 3.570577724836212,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00037756528994353945,
|
|
"loss": 4.4602,
|
|
"mean_token_accuracy": 0.2479439079761505,
|
|
"num_tokens": 83777581.0,
|
|
"step": 29975
|
|
},
|
|
{
|
|
"entropy": 5.182498216629028,
|
|
"epoch": 3.5711733174508637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037752736035583486,
|
|
"loss": 4.5338,
|
|
"mean_token_accuracy": 0.24497439861297607,
|
|
"num_tokens": 83791340.0,
|
|
"step": 29980
|
|
},
|
|
{
|
|
"entropy": 5.167539644241333,
|
|
"epoch": 3.571768910065515,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003774894270906405,
|
|
"loss": 4.5898,
|
|
"mean_token_accuracy": 0.23818404227495193,
|
|
"num_tokens": 83804172.0,
|
|
"step": 29985
|
|
},
|
|
{
|
|
"entropy": 5.087384557723999,
|
|
"epoch": 3.5723645026801667,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003774514901493172,
|
|
"loss": 4.4794,
|
|
"mean_token_accuracy": 0.24083046466112137,
|
|
"num_tokens": 83817583.0,
|
|
"step": 29990
|
|
},
|
|
{
|
|
"entropy": 5.184930753707886,
|
|
"epoch": 3.5729600952948184,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037741354953322546,
|
|
"loss": 4.5712,
|
|
"mean_token_accuracy": 0.24100476503372192,
|
|
"num_tokens": 83832685.0,
|
|
"step": 29995
|
|
},
|
|
{
|
|
"entropy": 5.14068455696106,
|
|
"epoch": 3.5735556879094696,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003773756052437262,
|
|
"loss": 4.4956,
|
|
"mean_token_accuracy": 0.2464294508099556,
|
|
"num_tokens": 83846633.0,
|
|
"step": 30000
|
|
},
|
|
{
|
|
"epoch": 3.5735556879094696,
|
|
"eval_entropy": 4.842955750507247,
|
|
"eval_loss": 4.536663055419922,
|
|
"eval_mean_token_accuracy": 0.25163681764260726,
|
|
"eval_num_tokens": 83846633.0,
|
|
"eval_runtime": 18.4747,
|
|
"eval_samples_per_second": 1380.967,
|
|
"eval_steps_per_second": 172.668,
|
|
"step": 30000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 83940,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 2.21355974356992e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|