2c7a0efbfc
Model: fpadovani/urd-arab-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.357355568790947,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.926274108886719,
|
|
"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
|
|
}
|
|
],
|
|
"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": 2229153962065920.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|