2c7a0efbfc
Model: fpadovani/urd-arab-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
18068 lines
496 KiB
JSON
18068 lines
496 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.072066706372841,
|
|
"eval_steps": 3000,
|
|
"global_step": 9000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.926274108886719,
|
|
"epoch": 0.0005955926146515784,
|
|
"grad_norm": 15.8125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.4668,
|
|
"mean_token_accuracy": 0.00011862700339406728,
|
|
"num_tokens": 13933.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.932535886764526,
|
|
"epoch": 0.0011911852293031567,
|
|
"grad_norm": 16.0,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.4393,
|
|
"mean_token_accuracy": 0.00014443041873164476,
|
|
"num_tokens": 28184.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.941028690338134,
|
|
"epoch": 0.001786777843954735,
|
|
"grad_norm": 16.375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.366,
|
|
"mean_token_accuracy": 5.685048527084291e-05,
|
|
"num_tokens": 42481.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 4.974720859527588,
|
|
"epoch": 0.0023823704586063135,
|
|
"grad_norm": 18.25,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 14.2566,
|
|
"mean_token_accuracy": 9.621907083783299e-05,
|
|
"num_tokens": 58257.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 5.058082151412964,
|
|
"epoch": 0.0029779630732578916,
|
|
"grad_norm": 21.625,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 13.8803,
|
|
"mean_token_accuracy": 0.00022898090537637472,
|
|
"num_tokens": 73037.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 5.31669545173645,
|
|
"epoch": 0.00357355568790947,
|
|
"grad_norm": 24.875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 13.2981,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 87144.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 6.431478261947632,
|
|
"epoch": 0.004169148302561048,
|
|
"grad_norm": 26.125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 12.2997,
|
|
"mean_token_accuracy": 0.00021689585410058498,
|
|
"num_tokens": 100908.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 9.774415397644043,
|
|
"epoch": 0.004764740917212627,
|
|
"grad_norm": 3.5625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 11.0372,
|
|
"mean_token_accuracy": 0.00017865551344584674,
|
|
"num_tokens": 116164.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.664159393310547,
|
|
"epoch": 0.005360333531864205,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.734,
|
|
"mean_token_accuracy": 0.008229692280292512,
|
|
"num_tokens": 129754.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.731787872314452,
|
|
"epoch": 0.005955926146515783,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.595,
|
|
"mean_token_accuracy": 0.012316014664247633,
|
|
"num_tokens": 143356.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.736772346496583,
|
|
"epoch": 0.006551518761167362,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 10.4613,
|
|
"mean_token_accuracy": 0.010549227753654123,
|
|
"num_tokens": 159656.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.722232151031495,
|
|
"epoch": 0.00714711137581894,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.2733,
|
|
"mean_token_accuracy": 0.010485857352614402,
|
|
"num_tokens": 176053.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.731705951690675,
|
|
"epoch": 0.007742703990470518,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 10.1271,
|
|
"mean_token_accuracy": 0.011739565338939429,
|
|
"num_tokens": 191011.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.737554550170898,
|
|
"epoch": 0.008338296605122097,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.9987,
|
|
"mean_token_accuracy": 0.020756381284445524,
|
|
"num_tokens": 203975.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.73554105758667,
|
|
"epoch": 0.008933889219773675,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.9208,
|
|
"mean_token_accuracy": 0.02677243258804083,
|
|
"num_tokens": 216231.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.731139755249023,
|
|
"epoch": 0.009529481834425254,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.8468,
|
|
"mean_token_accuracy": 0.019028229545801877,
|
|
"num_tokens": 230525.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.729487705230714,
|
|
"epoch": 0.01012507444907683,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.7316,
|
|
"mean_token_accuracy": 0.01892870357260108,
|
|
"num_tokens": 243197.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.723625087738037,
|
|
"epoch": 0.01072066706372841,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.5835,
|
|
"mean_token_accuracy": 0.024439648631960152,
|
|
"num_tokens": 257358.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.716553783416748,
|
|
"epoch": 0.011316259678379988,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.5493,
|
|
"mean_token_accuracy": 0.030682512372732163,
|
|
"num_tokens": 271978.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.702925300598144,
|
|
"epoch": 0.011911852293031567,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.4086,
|
|
"mean_token_accuracy": 0.03231615498661995,
|
|
"num_tokens": 286644.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.68063383102417,
|
|
"epoch": 0.012507444907683145,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.2776,
|
|
"mean_token_accuracy": 0.03108740095049143,
|
|
"num_tokens": 299888.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.65084342956543,
|
|
"epoch": 0.013103037522334724,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.1219,
|
|
"mean_token_accuracy": 0.03252283651381731,
|
|
"num_tokens": 314062.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.616011810302734,
|
|
"epoch": 0.0136986301369863,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9673,
|
|
"mean_token_accuracy": 0.0338243318721652,
|
|
"num_tokens": 326877.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.572829627990723,
|
|
"epoch": 0.01429422275163788,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8608,
|
|
"mean_token_accuracy": 0.037117029167711736,
|
|
"num_tokens": 339831.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.519098854064941,
|
|
"epoch": 0.014889815366289458,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7606,
|
|
"mean_token_accuracy": 0.034193937107920645,
|
|
"num_tokens": 353316.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.45387372970581,
|
|
"epoch": 0.015485407980941036,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.6455,
|
|
"mean_token_accuracy": 0.034920128993690014,
|
|
"num_tokens": 368263.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.377443218231202,
|
|
"epoch": 0.016081000595592615,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5523,
|
|
"mean_token_accuracy": 0.03318903725594282,
|
|
"num_tokens": 381899.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.28380470275879,
|
|
"epoch": 0.016676593210244194,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3856,
|
|
"mean_token_accuracy": 0.03339306432753801,
|
|
"num_tokens": 393924.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.16828088760376,
|
|
"epoch": 0.017272185824895772,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2307,
|
|
"mean_token_accuracy": 0.03646030705422163,
|
|
"num_tokens": 404670.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.028338718414307,
|
|
"epoch": 0.01786777843954735,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1711,
|
|
"mean_token_accuracy": 0.032446819357573986,
|
|
"num_tokens": 418805.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.875869274139404,
|
|
"epoch": 0.01846337105419893,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.1096,
|
|
"mean_token_accuracy": 0.0350328603759408,
|
|
"num_tokens": 434053.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.687991714477539,
|
|
"epoch": 0.019058963668850508,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9651,
|
|
"mean_token_accuracy": 0.03275042381137609,
|
|
"num_tokens": 447771.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.478072261810302,
|
|
"epoch": 0.019654556283502083,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.8309,
|
|
"mean_token_accuracy": 0.035520490072667596,
|
|
"num_tokens": 462055.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.239253616333007,
|
|
"epoch": 0.02025014889815366,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7862,
|
|
"mean_token_accuracy": 0.034369570948183534,
|
|
"num_tokens": 475573.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.978817081451416,
|
|
"epoch": 0.02084574151280524,
|
|
"grad_norm": 0.7421875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.716,
|
|
"mean_token_accuracy": 0.030998582765460015,
|
|
"num_tokens": 490172.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.754789733886719,
|
|
"epoch": 0.02144133412745682,
|
|
"grad_norm": 0.6640625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.6854,
|
|
"mean_token_accuracy": 0.03425474334508181,
|
|
"num_tokens": 503073.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.57414264678955,
|
|
"epoch": 0.022036926742108397,
|
|
"grad_norm": 0.66015625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5492,
|
|
"mean_token_accuracy": 0.03272276725620031,
|
|
"num_tokens": 518422.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.40087013244629,
|
|
"epoch": 0.022632519356759976,
|
|
"grad_norm": 0.63671875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.6062,
|
|
"mean_token_accuracy": 0.03543335385620594,
|
|
"num_tokens": 531422.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.252633190155029,
|
|
"epoch": 0.023228111971411555,
|
|
"grad_norm": 0.6171875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.6646,
|
|
"mean_token_accuracy": 0.03285746406763792,
|
|
"num_tokens": 547556.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.170538139343261,
|
|
"epoch": 0.023823704586063133,
|
|
"grad_norm": 0.6796875,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.5794,
|
|
"mean_token_accuracy": 0.033370182104408744,
|
|
"num_tokens": 559950.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.103077602386474,
|
|
"epoch": 0.024419297200714712,
|
|
"grad_norm": 0.51171875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.5337,
|
|
"mean_token_accuracy": 0.031332789547741415,
|
|
"num_tokens": 573158.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.034292221069336,
|
|
"epoch": 0.02501488981536629,
|
|
"grad_norm": 0.69140625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.5766,
|
|
"mean_token_accuracy": 0.031351211667060855,
|
|
"num_tokens": 587653.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.992253684997559,
|
|
"epoch": 0.02561048243001787,
|
|
"grad_norm": 0.5625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.5704,
|
|
"mean_token_accuracy": 0.03251508735120297,
|
|
"num_tokens": 599566.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.959266328811646,
|
|
"epoch": 0.026206075044669448,
|
|
"grad_norm": 0.578125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.4667,
|
|
"mean_token_accuracy": 0.03331163264811039,
|
|
"num_tokens": 613870.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.948250102996826,
|
|
"epoch": 0.026801667659321026,
|
|
"grad_norm": 0.57421875,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.4818,
|
|
"mean_token_accuracy": 0.0346223758533597,
|
|
"num_tokens": 625417.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.9228109359741214,
|
|
"epoch": 0.0273972602739726,
|
|
"grad_norm": 0.58203125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.5592,
|
|
"mean_token_accuracy": 0.031082126125693322,
|
|
"num_tokens": 638091.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.910252237319947,
|
|
"epoch": 0.02799285288862418,
|
|
"grad_norm": 0.6328125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.4702,
|
|
"mean_token_accuracy": 0.03281628340482712,
|
|
"num_tokens": 653733.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.909072208404541,
|
|
"epoch": 0.02858844550327576,
|
|
"grad_norm": 0.59375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.5194,
|
|
"mean_token_accuracy": 0.03327430803328753,
|
|
"num_tokens": 667197.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.887023973464966,
|
|
"epoch": 0.029184038117927337,
|
|
"grad_norm": 0.734375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.5134,
|
|
"mean_token_accuracy": 0.037746869027614594,
|
|
"num_tokens": 682333.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.89075927734375,
|
|
"epoch": 0.029779630732578916,
|
|
"grad_norm": 0.71875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.5539,
|
|
"mean_token_accuracy": 0.032532981038093566,
|
|
"num_tokens": 698745.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.955071830749512,
|
|
"epoch": 0.030375223347230494,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.4173,
|
|
"mean_token_accuracy": 0.043024342879652976,
|
|
"num_tokens": 713585.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.944690847396851,
|
|
"epoch": 0.030970815961882073,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.4623,
|
|
"mean_token_accuracy": 0.042671557515859604,
|
|
"num_tokens": 728735.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.956158876419067,
|
|
"epoch": 0.03156640857653365,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.4475,
|
|
"mean_token_accuracy": 0.04548847936093807,
|
|
"num_tokens": 742292.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.925923490524292,
|
|
"epoch": 0.03216200119118523,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.3578,
|
|
"mean_token_accuracy": 0.047962702065706256,
|
|
"num_tokens": 755915.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.94246187210083,
|
|
"epoch": 0.03275759380583681,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.4207,
|
|
"mean_token_accuracy": 0.04774568788707256,
|
|
"num_tokens": 769669.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.911481952667236,
|
|
"epoch": 0.03335318642048839,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.4256,
|
|
"mean_token_accuracy": 0.04661661200225353,
|
|
"num_tokens": 782871.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.880767726898194,
|
|
"epoch": 0.033948779035139966,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.2966,
|
|
"mean_token_accuracy": 0.0506436686962843,
|
|
"num_tokens": 796354.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.867405939102173,
|
|
"epoch": 0.034544371649791544,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.4574,
|
|
"mean_token_accuracy": 0.05282125771045685,
|
|
"num_tokens": 810833.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.86374797821045,
|
|
"epoch": 0.03513996426444312,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.3082,
|
|
"mean_token_accuracy": 0.05726734437048435,
|
|
"num_tokens": 824970.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.800059223175049,
|
|
"epoch": 0.0357355568790947,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.2385,
|
|
"mean_token_accuracy": 0.05636283792555332,
|
|
"num_tokens": 838403.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.823443984985351,
|
|
"epoch": 0.03633114949374628,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.3552,
|
|
"mean_token_accuracy": 0.05279202722012997,
|
|
"num_tokens": 850970.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.811036491394043,
|
|
"epoch": 0.03692674210839786,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.3013,
|
|
"mean_token_accuracy": 0.05962081924080849,
|
|
"num_tokens": 864950.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.821821880340576,
|
|
"epoch": 0.03752233472304944,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.358,
|
|
"mean_token_accuracy": 0.06332920268177986,
|
|
"num_tokens": 876860.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.865830898284912,
|
|
"epoch": 0.038117927337701016,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.2622,
|
|
"mean_token_accuracy": 0.05612402558326721,
|
|
"num_tokens": 890278.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.752763891220093,
|
|
"epoch": 0.03871351995235259,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.267,
|
|
"mean_token_accuracy": 0.06026482917368412,
|
|
"num_tokens": 903716.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.753884935379029,
|
|
"epoch": 0.039309112567004166,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.2011,
|
|
"mean_token_accuracy": 0.06185343787074089,
|
|
"num_tokens": 919346.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.750566244125366,
|
|
"epoch": 0.039904705181655745,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.2541,
|
|
"mean_token_accuracy": 0.06152658350765705,
|
|
"num_tokens": 931959.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.695417499542236,
|
|
"epoch": 0.04050029779630732,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.16,
|
|
"mean_token_accuracy": 0.062984299659729,
|
|
"num_tokens": 947237.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.685136985778809,
|
|
"epoch": 0.0410958904109589,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.1835,
|
|
"mean_token_accuracy": 0.06309934109449386,
|
|
"num_tokens": 961650.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.685891962051391,
|
|
"epoch": 0.04169148302561048,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.1755,
|
|
"mean_token_accuracy": 0.06446794606745243,
|
|
"num_tokens": 976138.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.718321514129639,
|
|
"epoch": 0.04228707564026206,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.1981,
|
|
"mean_token_accuracy": 0.06850187592208386,
|
|
"num_tokens": 991306.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.708969354629517,
|
|
"epoch": 0.04288266825491364,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.1376,
|
|
"mean_token_accuracy": 0.06881025917828083,
|
|
"num_tokens": 1006494.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.608221101760864,
|
|
"epoch": 0.043478260869565216,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.0733,
|
|
"mean_token_accuracy": 0.07095063887536526,
|
|
"num_tokens": 1020458.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.748707485198975,
|
|
"epoch": 0.044073853484216795,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.2174,
|
|
"mean_token_accuracy": 0.06676653660833835,
|
|
"num_tokens": 1035801.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.570728588104248,
|
|
"epoch": 0.04466944609886837,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.0279,
|
|
"mean_token_accuracy": 0.07174774669110776,
|
|
"num_tokens": 1051671.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.636310958862305,
|
|
"epoch": 0.04526503871351995,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.0157,
|
|
"mean_token_accuracy": 0.07355342879891395,
|
|
"num_tokens": 1065580.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.610966634750366,
|
|
"epoch": 0.04586063132817153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.0201,
|
|
"mean_token_accuracy": 0.07639546617865563,
|
|
"num_tokens": 1078646.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.600120115280151,
|
|
"epoch": 0.04645622394282311,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.0033,
|
|
"mean_token_accuracy": 0.07510423436760902,
|
|
"num_tokens": 1090921.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.629261922836304,
|
|
"epoch": 0.04705181655747469,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.0276,
|
|
"mean_token_accuracy": 0.07344624996185303,
|
|
"num_tokens": 1103223.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.4967241287231445,
|
|
"epoch": 0.047647409172126266,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.938,
|
|
"mean_token_accuracy": 0.08089623451232911,
|
|
"num_tokens": 1117103.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.512509059906006,
|
|
"epoch": 0.048243001786777845,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.0582,
|
|
"mean_token_accuracy": 0.07738725878298283,
|
|
"num_tokens": 1131452.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.531740188598633,
|
|
"epoch": 0.048838594401429423,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9661,
|
|
"mean_token_accuracy": 0.08345204256474972,
|
|
"num_tokens": 1144755.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.527704954147339,
|
|
"epoch": 0.049434187016081,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.9606,
|
|
"mean_token_accuracy": 0.07925527319312095,
|
|
"num_tokens": 1157544.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.476634216308594,
|
|
"epoch": 0.05002977963073258,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.929,
|
|
"mean_token_accuracy": 0.08062414154410362,
|
|
"num_tokens": 1171753.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.422762823104859,
|
|
"epoch": 0.05062537224538416,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8737,
|
|
"mean_token_accuracy": 0.07864995375275612,
|
|
"num_tokens": 1186570.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.452899742126465,
|
|
"epoch": 0.05122096486003574,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.9745,
|
|
"mean_token_accuracy": 0.08109329342842102,
|
|
"num_tokens": 1201674.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.437095403671265,
|
|
"epoch": 0.051816557474687316,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.8102,
|
|
"mean_token_accuracy": 0.08515282273292542,
|
|
"num_tokens": 1216060.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.481182050704956,
|
|
"epoch": 0.052412150089338895,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.8696,
|
|
"mean_token_accuracy": 0.08633813112974167,
|
|
"num_tokens": 1229736.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.398722457885742,
|
|
"epoch": 0.053007742703990474,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.8579,
|
|
"mean_token_accuracy": 0.08321957737207412,
|
|
"num_tokens": 1243253.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.358558320999146,
|
|
"epoch": 0.05360333531864205,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8454,
|
|
"mean_token_accuracy": 0.08370575830340385,
|
|
"num_tokens": 1256399.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.358534049987793,
|
|
"epoch": 0.054198927933293624,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8999,
|
|
"mean_token_accuracy": 0.08046779558062553,
|
|
"num_tokens": 1270676.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.415665769577027,
|
|
"epoch": 0.0547945205479452,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8241,
|
|
"mean_token_accuracy": 0.09082722887396813,
|
|
"num_tokens": 1283059.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.483054494857788,
|
|
"epoch": 0.05539011316259678,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.8842,
|
|
"mean_token_accuracy": 0.0829451285302639,
|
|
"num_tokens": 1297312.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.381071615219116,
|
|
"epoch": 0.05598570577724836,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.8459,
|
|
"mean_token_accuracy": 0.08478990085422992,
|
|
"num_tokens": 1309608.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.31707239151001,
|
|
"epoch": 0.05658129839189994,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.829,
|
|
"mean_token_accuracy": 0.08446860313415527,
|
|
"num_tokens": 1323605.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.327056503295898,
|
|
"epoch": 0.05717689100655152,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.8202,
|
|
"mean_token_accuracy": 0.0890904888510704,
|
|
"num_tokens": 1335742.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.3317619323730465,
|
|
"epoch": 0.057772483621203095,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.8002,
|
|
"mean_token_accuracy": 0.08907385244965553,
|
|
"num_tokens": 1349190.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.346725845336914,
|
|
"epoch": 0.058368076235854674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.881,
|
|
"mean_token_accuracy": 0.0836374070495367,
|
|
"num_tokens": 1365737.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.2879852771759035,
|
|
"epoch": 0.05896366885050625,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.8055,
|
|
"mean_token_accuracy": 0.0872837707400322,
|
|
"num_tokens": 1380591.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.267280864715576,
|
|
"epoch": 0.05955926146515783,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7571,
|
|
"mean_token_accuracy": 0.09086202606558799,
|
|
"num_tokens": 1394303.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.285760402679443,
|
|
"epoch": 0.06015485407980941,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7195,
|
|
"mean_token_accuracy": 0.09099448174238205,
|
|
"num_tokens": 1407232.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.2401186466217045,
|
|
"epoch": 0.06075044669446099,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.7664,
|
|
"mean_token_accuracy": 0.08979170322418213,
|
|
"num_tokens": 1421822.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.341850996017456,
|
|
"epoch": 0.06134603930911257,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7861,
|
|
"mean_token_accuracy": 0.09510571733117104,
|
|
"num_tokens": 1434555.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.195777559280396,
|
|
"epoch": 0.061941631923764146,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.7399,
|
|
"mean_token_accuracy": 0.09447200521826744,
|
|
"num_tokens": 1446221.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.192428064346314,
|
|
"epoch": 0.06253722453841572,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6389,
|
|
"mean_token_accuracy": 0.09402211159467697,
|
|
"num_tokens": 1459623.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.193966436386108,
|
|
"epoch": 0.0631328171530673,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6863,
|
|
"mean_token_accuracy": 0.09898325428366661,
|
|
"num_tokens": 1474618.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.175309848785401,
|
|
"epoch": 0.06372840976771887,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.5813,
|
|
"mean_token_accuracy": 0.10318320542573929,
|
|
"num_tokens": 1486820.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.207240247726441,
|
|
"epoch": 0.06432400238237046,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7186,
|
|
"mean_token_accuracy": 0.091385018825531,
|
|
"num_tokens": 1500696.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.12197847366333,
|
|
"epoch": 0.06491959499702203,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.09674113467335702,
|
|
"num_tokens": 1513926.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.137995910644531,
|
|
"epoch": 0.06551518761167362,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7211,
|
|
"mean_token_accuracy": 0.09307532459497452,
|
|
"num_tokens": 1527390.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.130176258087158,
|
|
"epoch": 0.06611078022632519,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5932,
|
|
"mean_token_accuracy": 0.09782459288835525,
|
|
"num_tokens": 1540631.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.2148011207580565,
|
|
"epoch": 0.06670637284097677,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6975,
|
|
"mean_token_accuracy": 0.09347774386405945,
|
|
"num_tokens": 1554822.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.03975887298584,
|
|
"epoch": 0.06730196545562835,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5584,
|
|
"mean_token_accuracy": 0.09844642356038094,
|
|
"num_tokens": 1569702.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.067330551147461,
|
|
"epoch": 0.06789755807027993,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.6223,
|
|
"mean_token_accuracy": 0.09400645792484283,
|
|
"num_tokens": 1583023.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.115908527374268,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6192,
|
|
"mean_token_accuracy": 0.09033841267228127,
|
|
"num_tokens": 1597012.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.209295701980591,
|
|
"epoch": 0.06908874329958309,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.7117,
|
|
"mean_token_accuracy": 0.09010799154639244,
|
|
"num_tokens": 1610668.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.150216722488404,
|
|
"epoch": 0.06968433591423466,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7749,
|
|
"mean_token_accuracy": 0.08841467723250389,
|
|
"num_tokens": 1628312.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.064253616333008,
|
|
"epoch": 0.07027992852888625,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.561,
|
|
"mean_token_accuracy": 0.09543564394116402,
|
|
"num_tokens": 1642933.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.070201730728149,
|
|
"epoch": 0.07087552114353782,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6413,
|
|
"mean_token_accuracy": 0.09548119828104973,
|
|
"num_tokens": 1659141.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.122019195556641,
|
|
"epoch": 0.0714711137581894,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.6093,
|
|
"mean_token_accuracy": 0.09905487075448036,
|
|
"num_tokens": 1673555.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.053143501281738,
|
|
"epoch": 0.07206670637284097,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6697,
|
|
"mean_token_accuracy": 0.10019941478967667,
|
|
"num_tokens": 1688619.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.0462723731994625,
|
|
"epoch": 0.07266229898749256,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5425,
|
|
"mean_token_accuracy": 0.10600225329399109,
|
|
"num_tokens": 1702096.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.132640171051025,
|
|
"epoch": 0.07325789160214413,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6215,
|
|
"mean_token_accuracy": 0.10150862634181976,
|
|
"num_tokens": 1716915.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.936264419555664,
|
|
"epoch": 0.07385348421679572,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4838,
|
|
"mean_token_accuracy": 0.10570442453026771,
|
|
"num_tokens": 1730743.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.994334936141968,
|
|
"epoch": 0.07444907683144729,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5033,
|
|
"mean_token_accuracy": 0.10180857703089714,
|
|
"num_tokens": 1744537.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.99732551574707,
|
|
"epoch": 0.07504466944609887,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5182,
|
|
"mean_token_accuracy": 0.10188300311565399,
|
|
"num_tokens": 1757394.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.927392387390137,
|
|
"epoch": 0.07564026206075045,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.4358,
|
|
"mean_token_accuracy": 0.10770431458950043,
|
|
"num_tokens": 1772966.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.026741075515747,
|
|
"epoch": 0.07623585467540203,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5425,
|
|
"mean_token_accuracy": 0.10556690841913223,
|
|
"num_tokens": 1786753.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.861152505874633,
|
|
"epoch": 0.0768314472900536,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.3763,
|
|
"mean_token_accuracy": 0.11122649013996125,
|
|
"num_tokens": 1799665.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.868685913085938,
|
|
"epoch": 0.07742703990470517,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4846,
|
|
"mean_token_accuracy": 0.10084349736571312,
|
|
"num_tokens": 1813363.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.994466543197632,
|
|
"epoch": 0.07802263251935676,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5685,
|
|
"mean_token_accuracy": 0.10275080278515816,
|
|
"num_tokens": 1827715.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.026219892501831,
|
|
"epoch": 0.07861822513400833,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.6268,
|
|
"mean_token_accuracy": 0.10650768801569939,
|
|
"num_tokens": 1842248.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.900357961654663,
|
|
"epoch": 0.07921381774865992,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5266,
|
|
"mean_token_accuracy": 0.10092263966798783,
|
|
"num_tokens": 1855993.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.938298559188842,
|
|
"epoch": 0.07980941036331149,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4194,
|
|
"mean_token_accuracy": 0.10466923043131829,
|
|
"num_tokens": 1869053.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.966603469848633,
|
|
"epoch": 0.08040500297796307,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5734,
|
|
"mean_token_accuracy": 0.09326259717345238,
|
|
"num_tokens": 1883371.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.978801679611206,
|
|
"epoch": 0.08100059559261465,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5161,
|
|
"mean_token_accuracy": 0.09706588312983513,
|
|
"num_tokens": 1899299.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.844657135009766,
|
|
"epoch": 0.08159618820726623,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.3054,
|
|
"mean_token_accuracy": 0.11091078594326972,
|
|
"num_tokens": 1913908.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.786835432052612,
|
|
"epoch": 0.0821917808219178,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4239,
|
|
"mean_token_accuracy": 0.10840331017971039,
|
|
"num_tokens": 1928379.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.835281419754028,
|
|
"epoch": 0.08278737343656939,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4283,
|
|
"mean_token_accuracy": 0.10425578132271766,
|
|
"num_tokens": 1942308.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.762073135375976,
|
|
"epoch": 0.08338296605122096,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.2387,
|
|
"mean_token_accuracy": 0.1136186271905899,
|
|
"num_tokens": 1954659.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.8574135303497314,
|
|
"epoch": 0.08397855866587255,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4196,
|
|
"mean_token_accuracy": 0.10803430527448654,
|
|
"num_tokens": 1969847.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.853384637832642,
|
|
"epoch": 0.08457415128052412,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.429,
|
|
"mean_token_accuracy": 0.105791487544775,
|
|
"num_tokens": 1983973.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.732511758804321,
|
|
"epoch": 0.0851697438951757,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.3518,
|
|
"mean_token_accuracy": 0.11114974096417427,
|
|
"num_tokens": 1997786.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.8639874935150145,
|
|
"epoch": 0.08576533650982728,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5061,
|
|
"mean_token_accuracy": 0.10455258190631866,
|
|
"num_tokens": 2012849.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.807453870773315,
|
|
"epoch": 0.08636092912447886,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4032,
|
|
"mean_token_accuracy": 0.10928454548120499,
|
|
"num_tokens": 2026935.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.772582387924194,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3773,
|
|
"mean_token_accuracy": 0.1119888186454773,
|
|
"num_tokens": 2039722.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.834014654159546,
|
|
"epoch": 0.08755211435378202,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.3715,
|
|
"mean_token_accuracy": 0.11609113588929176,
|
|
"num_tokens": 2053064.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.904176330566406,
|
|
"epoch": 0.08814770696843359,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5257,
|
|
"mean_token_accuracy": 0.10476789623498917,
|
|
"num_tokens": 2065401.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.737480878829956,
|
|
"epoch": 0.08874329958308518,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3052,
|
|
"mean_token_accuracy": 0.11336522176861763,
|
|
"num_tokens": 2078975.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.735174989700317,
|
|
"epoch": 0.08933889219773675,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3974,
|
|
"mean_token_accuracy": 0.10913275107741356,
|
|
"num_tokens": 2094427.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.722973251342774,
|
|
"epoch": 0.08993448481238833,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.3871,
|
|
"mean_token_accuracy": 0.11023307666182518,
|
|
"num_tokens": 2108993.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.706762838363647,
|
|
"epoch": 0.0905300774270399,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.2408,
|
|
"mean_token_accuracy": 0.11945048868656158,
|
|
"num_tokens": 2121913.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.8349220752716064,
|
|
"epoch": 0.09112567004169149,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3578,
|
|
"mean_token_accuracy": 0.11043609380722046,
|
|
"num_tokens": 2135224.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.7104603290557865,
|
|
"epoch": 0.09172126265634306,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.3964,
|
|
"mean_token_accuracy": 0.10966008827090264,
|
|
"num_tokens": 2150603.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.725274705886841,
|
|
"epoch": 0.09231685527099463,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3326,
|
|
"mean_token_accuracy": 0.11593154519796371,
|
|
"num_tokens": 2165710.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.652264928817749,
|
|
"epoch": 0.09291244788564622,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.3027,
|
|
"mean_token_accuracy": 0.11332699209451676,
|
|
"num_tokens": 2180477.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.686633014678955,
|
|
"epoch": 0.09350804050029779,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2586,
|
|
"mean_token_accuracy": 0.11259361952543259,
|
|
"num_tokens": 2193654.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.678912401199341,
|
|
"epoch": 0.09410363311494938,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.264,
|
|
"mean_token_accuracy": 0.12137154266238212,
|
|
"num_tokens": 2208161.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.70740065574646,
|
|
"epoch": 0.09469922572960095,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.3116,
|
|
"mean_token_accuracy": 0.11378278210759163,
|
|
"num_tokens": 2222306.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.733925533294678,
|
|
"epoch": 0.09529481834425253,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.4299,
|
|
"mean_token_accuracy": 0.11220810115337372,
|
|
"num_tokens": 2237919.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.621367502212524,
|
|
"epoch": 0.0958904109589041,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.2794,
|
|
"mean_token_accuracy": 0.11783934608101845,
|
|
"num_tokens": 2253244.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.794623804092407,
|
|
"epoch": 0.09648600357355569,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3637,
|
|
"mean_token_accuracy": 0.10893271565437317,
|
|
"num_tokens": 2267429.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.614417934417725,
|
|
"epoch": 0.09708159618820726,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2265,
|
|
"mean_token_accuracy": 0.11502965763211251,
|
|
"num_tokens": 2281830.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.656324005126953,
|
|
"epoch": 0.09767718880285885,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.2975,
|
|
"mean_token_accuracy": 0.11383071094751358,
|
|
"num_tokens": 2297243.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.720933055877685,
|
|
"epoch": 0.09827278141751042,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3115,
|
|
"mean_token_accuracy": 0.11662096157670021,
|
|
"num_tokens": 2308952.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.655382871627808,
|
|
"epoch": 0.098868374032162,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.2587,
|
|
"mean_token_accuracy": 0.11734143644571304,
|
|
"num_tokens": 2321645.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.577720689773559,
|
|
"epoch": 0.09946396664681358,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.2649,
|
|
"mean_token_accuracy": 0.11464339271187782,
|
|
"num_tokens": 2333309.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.664750051498413,
|
|
"epoch": 0.10005955926146516,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.2765,
|
|
"mean_token_accuracy": 0.1120231382548809,
|
|
"num_tokens": 2347843.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.639902114868164,
|
|
"epoch": 0.10065515187611673,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.3307,
|
|
"mean_token_accuracy": 0.11536335200071335,
|
|
"num_tokens": 2361024.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.580413913726806,
|
|
"epoch": 0.10125074449076832,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2427,
|
|
"mean_token_accuracy": 0.11439065337181091,
|
|
"num_tokens": 2375498.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.6116190433502195,
|
|
"epoch": 0.10184633710541989,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.1921,
|
|
"mean_token_accuracy": 0.11994925290346145,
|
|
"num_tokens": 2392063.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.6043500900268555,
|
|
"epoch": 0.10244192972007148,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.1885,
|
|
"mean_token_accuracy": 0.12353525608778,
|
|
"num_tokens": 2407267.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.604389762878418,
|
|
"epoch": 0.10303752233472305,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.1569,
|
|
"mean_token_accuracy": 0.11905085891485215,
|
|
"num_tokens": 2421814.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.589984607696533,
|
|
"epoch": 0.10363311494937463,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2479,
|
|
"mean_token_accuracy": 0.11835012435913086,
|
|
"num_tokens": 2438931.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.581540298461914,
|
|
"epoch": 0.1042287075640262,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.1806,
|
|
"mean_token_accuracy": 0.12253711521625518,
|
|
"num_tokens": 2451210.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.536899662017822,
|
|
"epoch": 0.10482430017867779,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.2706,
|
|
"mean_token_accuracy": 0.1189447209239006,
|
|
"num_tokens": 2465343.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.474660968780517,
|
|
"epoch": 0.10541989279332936,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.11866791471838951,
|
|
"num_tokens": 2478732.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.55727915763855,
|
|
"epoch": 0.10601548540798095,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.1909,
|
|
"mean_token_accuracy": 0.1250196047127247,
|
|
"num_tokens": 2493362.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.629166555404663,
|
|
"epoch": 0.10661107802263252,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.2534,
|
|
"mean_token_accuracy": 0.12227484285831451,
|
|
"num_tokens": 2506154.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.558849668502807,
|
|
"epoch": 0.1072066706372841,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.1186575561761856,
|
|
"num_tokens": 2519189.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.536633110046386,
|
|
"epoch": 0.10780226325193568,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2076,
|
|
"mean_token_accuracy": 0.11862791329622269,
|
|
"num_tokens": 2532486.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.55183367729187,
|
|
"epoch": 0.10839785586658725,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.1728,
|
|
"mean_token_accuracy": 0.12181233391165733,
|
|
"num_tokens": 2546239.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.576446437835694,
|
|
"epoch": 0.10899344848123883,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.11069378778338432,
|
|
"num_tokens": 2563054.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.497651290893555,
|
|
"epoch": 0.1095890410958904,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.11671268492937088,
|
|
"num_tokens": 2577503.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.728296566009521,
|
|
"epoch": 0.11018463371054199,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.11801609098911285,
|
|
"num_tokens": 2591506.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.558925008773803,
|
|
"epoch": 0.11078022632519356,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2352,
|
|
"mean_token_accuracy": 0.11240646243095398,
|
|
"num_tokens": 2607777.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.600870990753174,
|
|
"epoch": 0.11137581893984515,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2738,
|
|
"mean_token_accuracy": 0.11794044449925423,
|
|
"num_tokens": 2619506.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.54284782409668,
|
|
"epoch": 0.11197141155449672,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.2497,
|
|
"mean_token_accuracy": 0.11557438299059868,
|
|
"num_tokens": 2634182.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.573303747177124,
|
|
"epoch": 0.1125670041691483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.1622,
|
|
"mean_token_accuracy": 0.12252075374126434,
|
|
"num_tokens": 2649266.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.426169967651367,
|
|
"epoch": 0.11316259678379988,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.12529388517141343,
|
|
"num_tokens": 2662745.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.451272201538086,
|
|
"epoch": 0.11375818939845146,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.0846,
|
|
"mean_token_accuracy": 0.12483394667506217,
|
|
"num_tokens": 2676071.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.480741739273071,
|
|
"epoch": 0.11435378201310303,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.1708,
|
|
"mean_token_accuracy": 0.11926832273602486,
|
|
"num_tokens": 2690511.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.507002210617065,
|
|
"epoch": 0.11494937462775462,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.1042,
|
|
"mean_token_accuracy": 0.1290435165166855,
|
|
"num_tokens": 2704891.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.419072484970092,
|
|
"epoch": 0.11554496724240619,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.1458,
|
|
"mean_token_accuracy": 0.1196157082915306,
|
|
"num_tokens": 2718288.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.415342903137207,
|
|
"epoch": 0.11614055985705778,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.12383151575922965,
|
|
"num_tokens": 2732853.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.471505546569825,
|
|
"epoch": 0.11673615247170935,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2046,
|
|
"mean_token_accuracy": 0.11899536103010178,
|
|
"num_tokens": 2746801.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.459245824813843,
|
|
"epoch": 0.11733174508636093,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.112,
|
|
"mean_token_accuracy": 0.11679932549595833,
|
|
"num_tokens": 2760896.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.412615394592285,
|
|
"epoch": 0.1179273377010125,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.0678,
|
|
"mean_token_accuracy": 0.12289713546633721,
|
|
"num_tokens": 2774464.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.399781894683838,
|
|
"epoch": 0.11852293031566409,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.1118,
|
|
"mean_token_accuracy": 0.11976283565163612,
|
|
"num_tokens": 2789696.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.381843900680542,
|
|
"epoch": 0.11911852293031566,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.0924,
|
|
"mean_token_accuracy": 0.12352070063352585,
|
|
"num_tokens": 2802830.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.375089693069458,
|
|
"epoch": 0.11971411554496725,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004999999974174771,
|
|
"loss": 6.0436,
|
|
"mean_token_accuracy": 0.1244612418115139,
|
|
"num_tokens": 2816983.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.407578754425049,
|
|
"epoch": 0.12030970815961882,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999869259778,
|
|
"loss": 6.1444,
|
|
"mean_token_accuracy": 0.12450993210077285,
|
|
"num_tokens": 2831192.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.504035902023316,
|
|
"epoch": 0.1209053007742704,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999999683640947,
|
|
"loss": 6.1288,
|
|
"mean_token_accuracy": 0.12754198983311654,
|
|
"num_tokens": 2844621.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.333795022964478,
|
|
"epoch": 0.12150089338892198,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004999999417318286,
|
|
"loss": 6.0542,
|
|
"mean_token_accuracy": 0.12644676640629768,
|
|
"num_tokens": 2857056.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.424797821044922,
|
|
"epoch": 0.12209648600357356,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004999999070291805,
|
|
"loss": 6.2119,
|
|
"mean_token_accuracy": 0.1165068842470646,
|
|
"num_tokens": 2870129.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.512726831436157,
|
|
"epoch": 0.12269207861822513,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004999998642561514,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.11828980967402458,
|
|
"num_tokens": 2883395.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.3232306957244875,
|
|
"epoch": 0.1232876712328767,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999998134127432,
|
|
"loss": 5.9703,
|
|
"mean_token_accuracy": 0.1303369678556919,
|
|
"num_tokens": 2897295.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.368861484527588,
|
|
"epoch": 0.12388326384752829,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999997544989574,
|
|
"loss": 6.0905,
|
|
"mean_token_accuracy": 0.12177211344242096,
|
|
"num_tokens": 2910532.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.435405492782593,
|
|
"epoch": 0.12447885646217986,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999996875147963,
|
|
"loss": 6.1027,
|
|
"mean_token_accuracy": 0.12170586735010147,
|
|
"num_tokens": 2924713.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.515688467025757,
|
|
"epoch": 0.12507444907683143,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999996124602621,
|
|
"loss": 6.2032,
|
|
"mean_token_accuracy": 0.11491205915808678,
|
|
"num_tokens": 2941652.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.393681001663208,
|
|
"epoch": 0.12567004169148302,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999995293353578,
|
|
"loss": 6.1002,
|
|
"mean_token_accuracy": 0.12318666279315948,
|
|
"num_tokens": 2953863.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.332122325897217,
|
|
"epoch": 0.1262656343061346,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999994381400862,
|
|
"loss": 6.0083,
|
|
"mean_token_accuracy": 0.1310349240899086,
|
|
"num_tokens": 2965301.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.278225326538086,
|
|
"epoch": 0.1268612269207862,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999993388744504,
|
|
"loss": 6.0302,
|
|
"mean_token_accuracy": 0.12268994748592377,
|
|
"num_tokens": 2979693.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.272536945343018,
|
|
"epoch": 0.12745681953543775,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999992315384543,
|
|
"loss": 5.9527,
|
|
"mean_token_accuracy": 0.13503969833254814,
|
|
"num_tokens": 2993089.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.530353593826294,
|
|
"epoch": 0.12805241215008933,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999991161321014,
|
|
"loss": 6.167,
|
|
"mean_token_accuracy": 0.12093808650970458,
|
|
"num_tokens": 3006201.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.327599763870239,
|
|
"epoch": 0.12864800476474092,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999989926553962,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.12528552636504173,
|
|
"num_tokens": 3021067.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.2632410526275635,
|
|
"epoch": 0.1292435973793925,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000499998861108343,
|
|
"loss": 6.1262,
|
|
"mean_token_accuracy": 0.12118237018585205,
|
|
"num_tokens": 3035126.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.388171243667602,
|
|
"epoch": 0.12983918999404406,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999987214909464,
|
|
"loss": 6.0118,
|
|
"mean_token_accuracy": 0.12827680110931397,
|
|
"num_tokens": 3048811.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.295111227035522,
|
|
"epoch": 0.13043478260869565,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999985738032115,
|
|
"loss": 6.0147,
|
|
"mean_token_accuracy": 0.12736694738268853,
|
|
"num_tokens": 3061651.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.3264165878295895,
|
|
"epoch": 0.13103037522334723,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999984180451436,
|
|
"loss": 6.0131,
|
|
"mean_token_accuracy": 0.12697443291544913,
|
|
"num_tokens": 3074075.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.3050531387329105,
|
|
"epoch": 0.13162596783799882,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004999982542167483,
|
|
"loss": 5.9899,
|
|
"mean_token_accuracy": 0.1274932511150837,
|
|
"num_tokens": 3086217.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.262260293960571,
|
|
"epoch": 0.13222156045265038,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999980823180314,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.12617919519543647,
|
|
"num_tokens": 3101375.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.304317045211792,
|
|
"epoch": 0.13281715306730196,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499997902348999,
|
|
"loss": 6.02,
|
|
"mean_token_accuracy": 0.12563774064183236,
|
|
"num_tokens": 3116799.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.35048394203186,
|
|
"epoch": 0.13341274568195355,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004999977143096578,
|
|
"loss": 6.0808,
|
|
"mean_token_accuracy": 0.1243694968521595,
|
|
"num_tokens": 3130224.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.344778823852539,
|
|
"epoch": 0.13400833829660513,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999975182000143,
|
|
"loss": 6.1021,
|
|
"mean_token_accuracy": 0.12919701635837555,
|
|
"num_tokens": 3145627.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.211950254440308,
|
|
"epoch": 0.1346039309112567,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999973140200759,
|
|
"loss": 5.8887,
|
|
"mean_token_accuracy": 0.1368369199335575,
|
|
"num_tokens": 3159927.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.157776784896851,
|
|
"epoch": 0.13519952352590828,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999971017698495,
|
|
"loss": 5.8927,
|
|
"mean_token_accuracy": 0.13457455784082412,
|
|
"num_tokens": 3174135.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.223761987686157,
|
|
"epoch": 0.13579511614055986,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999968814493428,
|
|
"loss": 5.9441,
|
|
"mean_token_accuracy": 0.1311629109084606,
|
|
"num_tokens": 3186673.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.327444362640381,
|
|
"epoch": 0.13639070875521145,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999966530585639,
|
|
"loss": 6.1353,
|
|
"mean_token_accuracy": 0.11745902895927429,
|
|
"num_tokens": 3201645.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.238715696334839,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999964165975209,
|
|
"loss": 5.9617,
|
|
"mean_token_accuracy": 0.13160938993096352,
|
|
"num_tokens": 3215255.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.319231986999512,
|
|
"epoch": 0.1375818939845146,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999961720662221,
|
|
"loss": 5.9325,
|
|
"mean_token_accuracy": 0.13657833486795426,
|
|
"num_tokens": 3228207.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.222438335418701,
|
|
"epoch": 0.13817748659916618,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999959194646766,
|
|
"loss": 6.0412,
|
|
"mean_token_accuracy": 0.13396313041448593,
|
|
"num_tokens": 3242242.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.300257539749145,
|
|
"epoch": 0.13877307921381773,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999956587928932,
|
|
"loss": 6.0321,
|
|
"mean_token_accuracy": 0.13306989818811416,
|
|
"num_tokens": 3257408.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.260866117477417,
|
|
"epoch": 0.13936867182846932,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999953900508814,
|
|
"loss": 5.9639,
|
|
"mean_token_accuracy": 0.129524414986372,
|
|
"num_tokens": 3269991.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.170885848999023,
|
|
"epoch": 0.1399642644431209,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999951132386507,
|
|
"loss": 5.9501,
|
|
"mean_token_accuracy": 0.1295623980462551,
|
|
"num_tokens": 3285119.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.208763122558594,
|
|
"epoch": 0.1405598570577725,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999948283562111,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.12472678646445275,
|
|
"num_tokens": 3299102.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.304540395736694,
|
|
"epoch": 0.14115544967242405,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499994535403573,
|
|
"loss": 6.0519,
|
|
"mean_token_accuracy": 0.13086569234728812,
|
|
"num_tokens": 3313907.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.254537677764892,
|
|
"epoch": 0.14175104228707563,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999942343807465,
|
|
"loss": 5.9941,
|
|
"mean_token_accuracy": 0.12761559188365937,
|
|
"num_tokens": 3326128.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.257322597503662,
|
|
"epoch": 0.14234663490172722,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999939252877428,
|
|
"loss": 6.0296,
|
|
"mean_token_accuracy": 0.12958202362060547,
|
|
"num_tokens": 3339257.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.337223196029663,
|
|
"epoch": 0.1429422275163788,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999936081245727,
|
|
"loss": 6.0419,
|
|
"mean_token_accuracy": 0.12149293422698974,
|
|
"num_tokens": 3353893.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.252517747879028,
|
|
"epoch": 0.14353782013103036,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999932828912478,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.13144316002726555,
|
|
"num_tokens": 3370872.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.252450323104858,
|
|
"epoch": 0.14413341274568195,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999929495877796,
|
|
"loss": 6.0004,
|
|
"mean_token_accuracy": 0.13029421120882034,
|
|
"num_tokens": 3384741.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.208795642852783,
|
|
"epoch": 0.14472900536033353,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999926082141801,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.13095673248171807,
|
|
"num_tokens": 3399813.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.242795705795288,
|
|
"epoch": 0.14532459797498512,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999922587704616,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.13632318675518035,
|
|
"num_tokens": 3413314.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.179244565963745,
|
|
"epoch": 0.14592019058963668,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999919012566366,
|
|
"loss": 5.8706,
|
|
"mean_token_accuracy": 0.13855719268321992,
|
|
"num_tokens": 3427973.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.1802732944488525,
|
|
"epoch": 0.14651578320428826,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999915356727179,
|
|
"loss": 5.9579,
|
|
"mean_token_accuracy": 0.13377300053834915,
|
|
"num_tokens": 3443097.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.246569728851318,
|
|
"epoch": 0.14711137581893985,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999911620187186,
|
|
"loss": 6.021,
|
|
"mean_token_accuracy": 0.12546632513403894,
|
|
"num_tokens": 3456922.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.243866634368897,
|
|
"epoch": 0.14770696843359143,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999907802946521,
|
|
"loss": 5.9183,
|
|
"mean_token_accuracy": 0.1375621698796749,
|
|
"num_tokens": 3471247.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.177654361724853,
|
|
"epoch": 0.148302561048243,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999903905005323,
|
|
"loss": 5.8653,
|
|
"mean_token_accuracy": 0.13714087158441543,
|
|
"num_tokens": 3485026.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.271946573257447,
|
|
"epoch": 0.14889815366289458,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999899926363729,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.13483964279294014,
|
|
"num_tokens": 3498012.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.2273016452789305,
|
|
"epoch": 0.14949374627754616,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999895867021882,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.1265692263841629,
|
|
"num_tokens": 3511732.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.1190019130706785,
|
|
"epoch": 0.15008933889219775,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999891726979928,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.1352582648396492,
|
|
"num_tokens": 3527204.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.21186671257019,
|
|
"epoch": 0.1506849315068493,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999887506238018,
|
|
"loss": 5.9262,
|
|
"mean_token_accuracy": 0.12997026965022088,
|
|
"num_tokens": 3540571.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.112713384628296,
|
|
"epoch": 0.1512805241215009,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049998832047963,
|
|
"loss": 5.8515,
|
|
"mean_token_accuracy": 0.13946565240621567,
|
|
"num_tokens": 3553888.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.157454872131348,
|
|
"epoch": 0.15187611673615248,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004999878822654929,
|
|
"loss": 5.9081,
|
|
"mean_token_accuracy": 0.13053104430437087,
|
|
"num_tokens": 3565304.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.218049049377441,
|
|
"epoch": 0.15247170935080406,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999874359814064,
|
|
"loss": 5.9294,
|
|
"mean_token_accuracy": 0.13851200342178344,
|
|
"num_tokens": 3580109.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.0666327476501465,
|
|
"epoch": 0.15306730196545562,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999869816273863,
|
|
"loss": 5.8879,
|
|
"mean_token_accuracy": 0.13641879782080651,
|
|
"num_tokens": 3594204.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.171440553665161,
|
|
"epoch": 0.1536628945801072,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999865192034489,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.1309145838022232,
|
|
"num_tokens": 3608722.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.045901823043823,
|
|
"epoch": 0.1542584871947588,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499986048709611,
|
|
"loss": 5.7894,
|
|
"mean_token_accuracy": 0.13367475122213363,
|
|
"num_tokens": 3624597.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.179301786422729,
|
|
"epoch": 0.15485407980941035,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999855701458893,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.1315551571547985,
|
|
"num_tokens": 3641733.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.143159103393555,
|
|
"epoch": 0.15544967242406194,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999850835123009,
|
|
"loss": 5.8434,
|
|
"mean_token_accuracy": 0.1379377357661724,
|
|
"num_tokens": 3654188.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.202222394943237,
|
|
"epoch": 0.15604526503871352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999845888088635,
|
|
"loss": 5.9983,
|
|
"mean_token_accuracy": 0.1310037076473236,
|
|
"num_tokens": 3667738.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.162489032745361,
|
|
"epoch": 0.1566408576533651,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999840860355946,
|
|
"loss": 5.8906,
|
|
"mean_token_accuracy": 0.13672316521406175,
|
|
"num_tokens": 3682616.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.092942190170288,
|
|
"epoch": 0.15723645026801666,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999835751925124,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.13373669609427452,
|
|
"num_tokens": 3695873.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.259343481063842,
|
|
"epoch": 0.15783204288266825,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999830562796351,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.1330730862915516,
|
|
"num_tokens": 3710117.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.187768888473511,
|
|
"epoch": 0.15842763549731984,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999825292969814,
|
|
"loss": 5.9429,
|
|
"mean_token_accuracy": 0.13421416878700257,
|
|
"num_tokens": 3723153.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.122033786773682,
|
|
"epoch": 0.15902322811197142,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999819942445703,
|
|
"loss": 5.9251,
|
|
"mean_token_accuracy": 0.12868732511997222,
|
|
"num_tokens": 3736970.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.176203823089599,
|
|
"epoch": 0.15961882072662298,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999814511224207,
|
|
"loss": 5.9061,
|
|
"mean_token_accuracy": 0.13429975584149362,
|
|
"num_tokens": 3750737.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.204562568664551,
|
|
"epoch": 0.16021441334127456,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999808999305523,
|
|
"loss": 5.9856,
|
|
"mean_token_accuracy": 0.13239325806498528,
|
|
"num_tokens": 3764955.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.120605897903443,
|
|
"epoch": 0.16081000595592615,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999803406689848,
|
|
"loss": 5.7805,
|
|
"mean_token_accuracy": 0.13752676397562028,
|
|
"num_tokens": 3780107.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.095135593414307,
|
|
"epoch": 0.16140559857057774,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999797733377384,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.13585890531539918,
|
|
"num_tokens": 3794609.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.1934168338775635,
|
|
"epoch": 0.1620011911852293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999791979368332,
|
|
"loss": 5.9342,
|
|
"mean_token_accuracy": 0.13824013844132424,
|
|
"num_tokens": 3808870.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.155633926391602,
|
|
"epoch": 0.16259678379988088,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999786144662899,
|
|
"loss": 5.9078,
|
|
"mean_token_accuracy": 0.13579775020480156,
|
|
"num_tokens": 3822608.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.087682104110717,
|
|
"epoch": 0.16319237641453246,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999780229261295,
|
|
"loss": 5.8327,
|
|
"mean_token_accuracy": 0.1425986669957638,
|
|
"num_tokens": 3837175.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.055517578125,
|
|
"epoch": 0.16378796902918405,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999774233163734,
|
|
"loss": 5.7423,
|
|
"mean_token_accuracy": 0.14461472779512405,
|
|
"num_tokens": 3851298.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 5.9919859886169435,
|
|
"epoch": 0.1643835616438356,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999768156370428,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.13986781537532805,
|
|
"num_tokens": 3865396.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.064241790771485,
|
|
"epoch": 0.1649791542584872,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999761998881596,
|
|
"loss": 5.7428,
|
|
"mean_token_accuracy": 0.14307337179780005,
|
|
"num_tokens": 3876827.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.164361906051636,
|
|
"epoch": 0.16557474687313878,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999755760697459,
|
|
"loss": 5.9011,
|
|
"mean_token_accuracy": 0.1336224891245365,
|
|
"num_tokens": 3892707.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.203294897079468,
|
|
"epoch": 0.16617033948779036,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499974944181824,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.1365553431212902,
|
|
"num_tokens": 3906193.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.9282581329345705,
|
|
"epoch": 0.16676593210244192,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999743042244167,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.14891034066677095,
|
|
"num_tokens": 3919175.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.144384336471558,
|
|
"epoch": 0.1673615247170935,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499973656197547,
|
|
"loss": 5.9674,
|
|
"mean_token_accuracy": 0.1305065281689167,
|
|
"num_tokens": 3933207.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.057987260818481,
|
|
"epoch": 0.1679571173317451,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999730001012379,
|
|
"loss": 5.7858,
|
|
"mean_token_accuracy": 0.14294685795903206,
|
|
"num_tokens": 3945962.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.053352546691895,
|
|
"epoch": 0.16855270994639668,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999723359355131,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.1461661621928215,
|
|
"num_tokens": 3959645.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.040371036529541,
|
|
"epoch": 0.16914830256104824,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999716637003965,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.13801866844296456,
|
|
"num_tokens": 3975142.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.112378263473511,
|
|
"epoch": 0.16974389517569982,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499970983395912,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.13851202577352523,
|
|
"num_tokens": 3989214.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.057251453399658,
|
|
"epoch": 0.1703394877903514,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999702950220841,
|
|
"loss": 5.8493,
|
|
"mean_token_accuracy": 0.1395124040544033,
|
|
"num_tokens": 4003753.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.071414852142334,
|
|
"epoch": 0.17093508040500296,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999695985789376,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.1433809742331505,
|
|
"num_tokens": 4018739.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.13561372756958,
|
|
"epoch": 0.17153067301965455,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999688940664972,
|
|
"loss": 5.882,
|
|
"mean_token_accuracy": 0.13892385587096215,
|
|
"num_tokens": 4031822.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.02050461769104,
|
|
"epoch": 0.17212626563430614,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999681814847884,
|
|
"loss": 5.8568,
|
|
"mean_token_accuracy": 0.137375108897686,
|
|
"num_tokens": 4044757.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.991058826446533,
|
|
"epoch": 0.17272185824895772,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999674608338367,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.14199545755982398,
|
|
"num_tokens": 4059795.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.073600339889526,
|
|
"epoch": 0.17331745086360928,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999667321136681,
|
|
"loss": 5.8503,
|
|
"mean_token_accuracy": 0.13699849992990493,
|
|
"num_tokens": 4074772.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.116254615783691,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999659953243085,
|
|
"loss": 5.8433,
|
|
"mean_token_accuracy": 0.13740890696644784,
|
|
"num_tokens": 4088534.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.042709302902222,
|
|
"epoch": 0.17450863609291245,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999652504657844,
|
|
"loss": 5.7693,
|
|
"mean_token_accuracy": 0.1436406798660755,
|
|
"num_tokens": 4101729.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.04177188873291,
|
|
"epoch": 0.17510422870756404,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999644975381226,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.14489644914865493,
|
|
"num_tokens": 4114463.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.989459562301636,
|
|
"epoch": 0.1756998213222156,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00049996373654135,
|
|
"loss": 5.7785,
|
|
"mean_token_accuracy": 0.146892012655735,
|
|
"num_tokens": 4125822.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.07545657157898,
|
|
"epoch": 0.17629541393686718,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999629674754939,
|
|
"loss": 5.7073,
|
|
"mean_token_accuracy": 0.14525049775838852,
|
|
"num_tokens": 4139385.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.043941879272461,
|
|
"epoch": 0.17689100655151876,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999621903405819,
|
|
"loss": 5.8951,
|
|
"mean_token_accuracy": 0.1356865182518959,
|
|
"num_tokens": 4153713.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.044046068191529,
|
|
"epoch": 0.17748659916617035,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999614051366421,
|
|
"loss": 5.8335,
|
|
"mean_token_accuracy": 0.14461283832788469,
|
|
"num_tokens": 4167030.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.990119695663452,
|
|
"epoch": 0.1780821917808219,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999606118637022,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.14729824513196946,
|
|
"num_tokens": 4179525.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.981477880477906,
|
|
"epoch": 0.1786777843954735,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999598105217911,
|
|
"loss": 5.7497,
|
|
"mean_token_accuracy": 0.14276750460267068,
|
|
"num_tokens": 4193234.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.173784637451172,
|
|
"epoch": 0.17927337701012508,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999590011109373,
|
|
"loss": 5.9799,
|
|
"mean_token_accuracy": 0.128591887652874,
|
|
"num_tokens": 4207822.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.923196935653687,
|
|
"epoch": 0.17986896962477666,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049995818363117,
|
|
"loss": 5.6535,
|
|
"mean_token_accuracy": 0.14714332669973373,
|
|
"num_tokens": 4219990.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.953115797042846,
|
|
"epoch": 0.18046456223942822,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999573580825182,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.15343131870031357,
|
|
"num_tokens": 4232842.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.9914970874786375,
|
|
"epoch": 0.1810601548540798,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999565244650119,
|
|
"loss": 5.7544,
|
|
"mean_token_accuracy": 0.13864349573850632,
|
|
"num_tokens": 4247750.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.050769424438476,
|
|
"epoch": 0.1816557474687314,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999556827786807,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.1400708667933941,
|
|
"num_tokens": 4260757.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.06231541633606,
|
|
"epoch": 0.18225134008338298,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999548330235549,
|
|
"loss": 5.829,
|
|
"mean_token_accuracy": 0.14363204836845397,
|
|
"num_tokens": 4274430.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.96493010520935,
|
|
"epoch": 0.18284693269803454,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999539751996651,
|
|
"loss": 5.6967,
|
|
"mean_token_accuracy": 0.14499881193041803,
|
|
"num_tokens": 4288289.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.992290449142456,
|
|
"epoch": 0.18344252531268612,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499953109307042,
|
|
"loss": 5.8219,
|
|
"mean_token_accuracy": 0.1416143000125885,
|
|
"num_tokens": 4303460.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.035411548614502,
|
|
"epoch": 0.1840381179273377,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999522353457165,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.13796049132943153,
|
|
"num_tokens": 4317812.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.015031242370606,
|
|
"epoch": 0.18463371054198927,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999513533157201,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.14893085807561873,
|
|
"num_tokens": 4331298.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.161585998535156,
|
|
"epoch": 0.18522930315664085,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999504632170844,
|
|
"loss": 5.8794,
|
|
"mean_token_accuracy": 0.1360538810491562,
|
|
"num_tokens": 4347241.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.964785718917847,
|
|
"epoch": 0.18582489577129244,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999495650498413,
|
|
"loss": 5.7602,
|
|
"mean_token_accuracy": 0.14079782590270043,
|
|
"num_tokens": 4363523.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.911650562286377,
|
|
"epoch": 0.18642048838594402,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999486588140231,
|
|
"loss": 5.6576,
|
|
"mean_token_accuracy": 0.15331710651516914,
|
|
"num_tokens": 4375701.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.014779376983642,
|
|
"epoch": 0.18701608100059558,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999477445096623,
|
|
"loss": 5.8527,
|
|
"mean_token_accuracy": 0.14194864854216577,
|
|
"num_tokens": 4388482.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.080461072921753,
|
|
"epoch": 0.18761167361524717,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999468221367916,
|
|
"loss": 5.8348,
|
|
"mean_token_accuracy": 0.13843949511647224,
|
|
"num_tokens": 4404275.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.975428628921509,
|
|
"epoch": 0.18820726622989875,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999458916954442,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.14692061692476271,
|
|
"num_tokens": 4418076.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.872400999069214,
|
|
"epoch": 0.18880285884455034,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999449531856532,
|
|
"loss": 5.6354,
|
|
"mean_token_accuracy": 0.15272490680217743,
|
|
"num_tokens": 4431241.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.013757419586182,
|
|
"epoch": 0.1893984514592019,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999440066074526,
|
|
"loss": 5.7146,
|
|
"mean_token_accuracy": 0.14599696099758147,
|
|
"num_tokens": 4443915.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.0449987888336185,
|
|
"epoch": 0.18999404407385348,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999430519608762,
|
|
"loss": 5.8983,
|
|
"mean_token_accuracy": 0.13701653406023978,
|
|
"num_tokens": 4459976.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.991712522506714,
|
|
"epoch": 0.19058963668850507,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999420892459584,
|
|
"loss": 5.8444,
|
|
"mean_token_accuracy": 0.13542850986123084,
|
|
"num_tokens": 4473955.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.052430200576782,
|
|
"epoch": 0.19118522930315665,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999411184627334,
|
|
"loss": 5.7773,
|
|
"mean_token_accuracy": 0.13845517933368684,
|
|
"num_tokens": 4489008.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.891053676605225,
|
|
"epoch": 0.1917808219178082,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999401396112364,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.155222550034523,
|
|
"num_tokens": 4502755.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.040102434158325,
|
|
"epoch": 0.1923764145324598,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000499939152691502,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.1377498872578144,
|
|
"num_tokens": 4518225.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.924446630477905,
|
|
"epoch": 0.19297200714711138,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999381577035663,
|
|
"loss": 5.6818,
|
|
"mean_token_accuracy": 0.14550431594252586,
|
|
"num_tokens": 4533246.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.977464389801026,
|
|
"epoch": 0.19356759976176297,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999371546474643,
|
|
"loss": 5.8221,
|
|
"mean_token_accuracy": 0.1356734313070774,
|
|
"num_tokens": 4547726.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.014477348327636,
|
|
"epoch": 0.19416319237641452,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999361435232324,
|
|
"loss": 5.8476,
|
|
"mean_token_accuracy": 0.13353351354599,
|
|
"num_tokens": 4564462.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.023280191421509,
|
|
"epoch": 0.1947587849910661,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999351243309069,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.13879656195640563,
|
|
"num_tokens": 4578846.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.872073411941528,
|
|
"epoch": 0.1953543776057177,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999340970705241,
|
|
"loss": 5.6539,
|
|
"mean_token_accuracy": 0.1500879056751728,
|
|
"num_tokens": 4593547.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.015725040435791,
|
|
"epoch": 0.19594997022036928,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999330617421209,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.14505322128534318,
|
|
"num_tokens": 4607466.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.9246180057525635,
|
|
"epoch": 0.19654556283502084,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999320183457346,
|
|
"loss": 5.6392,
|
|
"mean_token_accuracy": 0.148372121155262,
|
|
"num_tokens": 4621624.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.9067527770996096,
|
|
"epoch": 0.19714115544967242,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999309668814024,
|
|
"loss": 5.617,
|
|
"mean_token_accuracy": 0.14399564936757087,
|
|
"num_tokens": 4635720.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.892867851257324,
|
|
"epoch": 0.197736748064324,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999299073491623,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.1508186750113964,
|
|
"num_tokens": 4649614.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.997893524169922,
|
|
"epoch": 0.1983323406789756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999288397490519,
|
|
"loss": 5.7732,
|
|
"mean_token_accuracy": 0.1456414595246315,
|
|
"num_tokens": 4661930.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.971903896331787,
|
|
"epoch": 0.19892793329362715,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999277640811099,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.14272156581282616,
|
|
"num_tokens": 4677016.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.008993244171142,
|
|
"epoch": 0.19952352590827874,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999266803453747,
|
|
"loss": 5.7464,
|
|
"mean_token_accuracy": 0.1429272286593914,
|
|
"num_tokens": 4692780.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.033808994293213,
|
|
"epoch": 0.20011911852293032,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999255885418852,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.1426839977502823,
|
|
"num_tokens": 4707069.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.893804407119751,
|
|
"epoch": 0.20071471113758188,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999244886706804,
|
|
"loss": 5.7063,
|
|
"mean_token_accuracy": 0.1458833895623684,
|
|
"num_tokens": 4720658.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.945674657821655,
|
|
"epoch": 0.20131030375223347,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999233807318001,
|
|
"loss": 5.682,
|
|
"mean_token_accuracy": 0.13697761818766593,
|
|
"num_tokens": 4735901.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.00821590423584,
|
|
"epoch": 0.20190589636688505,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999222647252837,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.13373836725950242,
|
|
"num_tokens": 4748725.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.044517755508423,
|
|
"epoch": 0.20250148898153664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999211406511714,
|
|
"loss": 5.767,
|
|
"mean_token_accuracy": 0.14149385541677476,
|
|
"num_tokens": 4761593.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.001615190505982,
|
|
"epoch": 0.2030970815961882,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999200085095035,
|
|
"loss": 5.7362,
|
|
"mean_token_accuracy": 0.14610189199447632,
|
|
"num_tokens": 4774304.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.923042249679566,
|
|
"epoch": 0.20369267421083978,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999188683003207,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.14059431999921798,
|
|
"num_tokens": 4787350.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.941183710098267,
|
|
"epoch": 0.20428826682549137,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999177200236635,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.1450108490884304,
|
|
"num_tokens": 4801465.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.852363920211792,
|
|
"epoch": 0.20488385944014295,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999165636795736,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.1463468052446842,
|
|
"num_tokens": 4815757.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.936472415924072,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999153992680923,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.14150822386145592,
|
|
"num_tokens": 4830164.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.937071943283081,
|
|
"epoch": 0.2060750446694461,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999142267892612,
|
|
"loss": 5.6803,
|
|
"mean_token_accuracy": 0.14392196759581566,
|
|
"num_tokens": 4844459.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.925596857070923,
|
|
"epoch": 0.20667063728409768,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999130462431224,
|
|
"loss": 5.752,
|
|
"mean_token_accuracy": 0.14532395526766778,
|
|
"num_tokens": 4859189.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.925850582122803,
|
|
"epoch": 0.20726622989874927,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999118576297185,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.14198393672704696,
|
|
"num_tokens": 4872911.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.92238974571228,
|
|
"epoch": 0.20786182251340082,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999106609490918,
|
|
"loss": 5.6761,
|
|
"mean_token_accuracy": 0.14941318109631538,
|
|
"num_tokens": 4886260.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.746127891540527,
|
|
"epoch": 0.2084574151280524,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999094562012855,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.15673593282699586,
|
|
"num_tokens": 4899177.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.8976975440979,
|
|
"epoch": 0.209053007742704,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999082433863426,
|
|
"loss": 5.7069,
|
|
"mean_token_accuracy": 0.1483059123158455,
|
|
"num_tokens": 4912071.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.992261219024658,
|
|
"epoch": 0.20964860035735558,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999070225043068,
|
|
"loss": 5.6592,
|
|
"mean_token_accuracy": 0.15259260535240174,
|
|
"num_tokens": 4925247.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.855973911285401,
|
|
"epoch": 0.21024419297200714,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999057935552217,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.1384056493639946,
|
|
"num_tokens": 4940380.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.892102193832398,
|
|
"epoch": 0.21083978558665872,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999045565391313,
|
|
"loss": 5.595,
|
|
"mean_token_accuracy": 0.14626146107912064,
|
|
"num_tokens": 4955868.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.883128595352173,
|
|
"epoch": 0.2114353782013103,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999033114560803,
|
|
"loss": 5.6745,
|
|
"mean_token_accuracy": 0.1434931829571724,
|
|
"num_tokens": 4969986.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.85156774520874,
|
|
"epoch": 0.2120309708159619,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999020583061132,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.14893678277730943,
|
|
"num_tokens": 4985980.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.833650159835815,
|
|
"epoch": 0.21262656343061345,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999007970892749,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.14920421838760375,
|
|
"num_tokens": 5001932.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.931062793731689,
|
|
"epoch": 0.21322215604526504,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998995278056107,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.15090135633945465,
|
|
"num_tokens": 5015375.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.942039728164673,
|
|
"epoch": 0.21381774865991662,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998982504551661,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.14353301078081132,
|
|
"num_tokens": 5030520.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.952792167663574,
|
|
"epoch": 0.2144133412745682,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998969650379869,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.14696830362081528,
|
|
"num_tokens": 5045020.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.917175245285034,
|
|
"epoch": 0.21500893388921977,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998956715541192,
|
|
"loss": 5.6059,
|
|
"mean_token_accuracy": 0.15293274223804473,
|
|
"num_tokens": 5058195.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.824610185623169,
|
|
"epoch": 0.21560452650387135,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998943700036095,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.15144876390695572,
|
|
"num_tokens": 5071687.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.900070285797119,
|
|
"epoch": 0.21620011911852294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998930603865042,
|
|
"loss": 5.6928,
|
|
"mean_token_accuracy": 0.14285470619797708,
|
|
"num_tokens": 5083817.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.899575519561767,
|
|
"epoch": 0.2167957117331745,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998917427028507,
|
|
"loss": 5.666,
|
|
"mean_token_accuracy": 0.14626671373844147,
|
|
"num_tokens": 5097957.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.856019687652588,
|
|
"epoch": 0.21739130434782608,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998904169526959,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.1456719234585762,
|
|
"num_tokens": 5112681.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.894531869888306,
|
|
"epoch": 0.21798689696247767,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998890831360876,
|
|
"loss": 5.6605,
|
|
"mean_token_accuracy": 0.1507721021771431,
|
|
"num_tokens": 5126152.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.829772663116455,
|
|
"epoch": 0.21858248957712925,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998877412530735,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.15387759804725648,
|
|
"num_tokens": 5140452.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.849728775024414,
|
|
"epoch": 0.2191780821917808,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998863913037017,
|
|
"loss": 5.7084,
|
|
"mean_token_accuracy": 0.142798063904047,
|
|
"num_tokens": 5155020.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.9373781204223635,
|
|
"epoch": 0.2197736748064324,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998850332880208,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.1517767332494259,
|
|
"num_tokens": 5169321.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.874116325378418,
|
|
"epoch": 0.22036926742108398,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998836672060795,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.15280101597309112,
|
|
"num_tokens": 5182156.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.7975139141082765,
|
|
"epoch": 0.22096486003573557,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998822930579264,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.1467317521572113,
|
|
"num_tokens": 5196543.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.843800210952759,
|
|
"epoch": 0.22156045265038712,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998809108436112,
|
|
"loss": 5.6274,
|
|
"mean_token_accuracy": 0.15367698073387145,
|
|
"num_tokens": 5210454.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.956942701339722,
|
|
"epoch": 0.2221560452650387,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998795205631834,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.14255602583289145,
|
|
"num_tokens": 5226371.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.8665846824646,
|
|
"epoch": 0.2227516378796903,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998781222166929,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.15659446865320206,
|
|
"num_tokens": 5239182.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.79332127571106,
|
|
"epoch": 0.22334723049434188,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998767158041897,
|
|
"loss": 5.5635,
|
|
"mean_token_accuracy": 0.15482927113771439,
|
|
"num_tokens": 5254704.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.805406188964843,
|
|
"epoch": 0.22394282310899344,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998753013257242,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.15331717804074288,
|
|
"num_tokens": 5267218.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.863832473754883,
|
|
"epoch": 0.22453841572364502,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998738787813475,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.147457355260849,
|
|
"num_tokens": 5282376.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.861818122863769,
|
|
"epoch": 0.2251340083382966,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998724481711103,
|
|
"loss": 5.644,
|
|
"mean_token_accuracy": 0.14824887365102768,
|
|
"num_tokens": 5296135.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.85996036529541,
|
|
"epoch": 0.2257296009529482,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499871009495064,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.15290106683969498,
|
|
"num_tokens": 5310347.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.905732774734497,
|
|
"epoch": 0.22632519356759975,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998695627532601,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.1427819922566414,
|
|
"num_tokens": 5324958.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.7436851978302,
|
|
"epoch": 0.22692078618225134,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998681079457507,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.15394582152366637,
|
|
"num_tokens": 5338913.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.749853086471558,
|
|
"epoch": 0.22751637879690292,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499866645072588,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.15937881916761398,
|
|
"num_tokens": 5351151.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.723223495483398,
|
|
"epoch": 0.2281119714115545,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998651741338242,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.1528441146016121,
|
|
"num_tokens": 5365139.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.908973503112793,
|
|
"epoch": 0.22870756402620607,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998636951295122,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.1462341070175171,
|
|
"num_tokens": 5378821.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.833300638198852,
|
|
"epoch": 0.22930315664085765,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998622080597052,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.14569789469242095,
|
|
"num_tokens": 5393912.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.967876863479614,
|
|
"epoch": 0.22989874925550924,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998607129244563,
|
|
"loss": 5.6855,
|
|
"mean_token_accuracy": 0.15573813542723655,
|
|
"num_tokens": 5406373.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.776638650894165,
|
|
"epoch": 0.23049434187016082,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998592097238192,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.15726928114891053,
|
|
"num_tokens": 5421701.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.802846050262451,
|
|
"epoch": 0.23108993448481238,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998576984578479,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.15237817242741586,
|
|
"num_tokens": 5435584.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.832087850570678,
|
|
"epoch": 0.23168552709946397,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998561791265966,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.1429808333516121,
|
|
"num_tokens": 5451241.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.9865015029907225,
|
|
"epoch": 0.23228111971411555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998546517301196,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.14687193483114241,
|
|
"num_tokens": 5465740.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.813498163223267,
|
|
"epoch": 0.2328767123287671,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499853116268472,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.16084107905626296,
|
|
"num_tokens": 5479142.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.917529582977295,
|
|
"epoch": 0.2334723049434187,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998515727417086,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.15238895416259765,
|
|
"num_tokens": 5491503.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.757050943374634,
|
|
"epoch": 0.23406789755807028,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998500211498848,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.1481686107814312,
|
|
"num_tokens": 5506817.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.877749013900757,
|
|
"epoch": 0.23466349017272187,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998484614930566,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.15181323289871215,
|
|
"num_tokens": 5519223.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.817584753036499,
|
|
"epoch": 0.23525908278737342,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998468937712794,
|
|
"loss": 5.6774,
|
|
"mean_token_accuracy": 0.1495397612452507,
|
|
"num_tokens": 5534904.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.852335691452026,
|
|
"epoch": 0.235854675402025,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998453179846098,
|
|
"loss": 5.6096,
|
|
"mean_token_accuracy": 0.15499591827392578,
|
|
"num_tokens": 5548815.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.812982559204102,
|
|
"epoch": 0.2364502680166766,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998437341331043,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.1524474650621414,
|
|
"num_tokens": 5563277.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.866748237609864,
|
|
"epoch": 0.23704586063132818,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998421422168195,
|
|
"loss": 5.6701,
|
|
"mean_token_accuracy": 0.15211372300982476,
|
|
"num_tokens": 5576083.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.858061838150024,
|
|
"epoch": 0.23764145324597974,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998405422358126,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.1504637897014618,
|
|
"num_tokens": 5592293.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.70010781288147,
|
|
"epoch": 0.23823704586063132,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998389341901411,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.16007496565580367,
|
|
"num_tokens": 5606088.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.788255786895752,
|
|
"epoch": 0.2388326384752829,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998373180798626,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.15649832785129547,
|
|
"num_tokens": 5620039.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.769215250015259,
|
|
"epoch": 0.2394282310899345,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998356939050351,
|
|
"loss": 5.6145,
|
|
"mean_token_accuracy": 0.15451158285140992,
|
|
"num_tokens": 5634738.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.819713115692139,
|
|
"epoch": 0.24002382370458605,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998340616657168,
|
|
"loss": 5.4799,
|
|
"mean_token_accuracy": 0.15834107398986816,
|
|
"num_tokens": 5649410.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.685422706604004,
|
|
"epoch": 0.24061941631923764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998324213619661,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.15346736013889312,
|
|
"num_tokens": 5662641.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.892227458953857,
|
|
"epoch": 0.24121500893388922,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998307729938423,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.15353201925754548,
|
|
"num_tokens": 5675558.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.6808325290679935,
|
|
"epoch": 0.2418106015485408,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499829116561404,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.1574713483452797,
|
|
"num_tokens": 5690152.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.824256658554077,
|
|
"epoch": 0.24240619416319237,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998274520647109,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.15091209411621093,
|
|
"num_tokens": 5705378.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.792923498153686,
|
|
"epoch": 0.24300178677784395,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998257795038227,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.1475793808698654,
|
|
"num_tokens": 5718470.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.796890020370483,
|
|
"epoch": 0.24359737939249554,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998240988787992,
|
|
"loss": 5.5579,
|
|
"mean_token_accuracy": 0.1571284055709839,
|
|
"num_tokens": 5731073.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.7663506984710695,
|
|
"epoch": 0.24419297200714712,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998224101897009,
|
|
"loss": 5.5347,
|
|
"mean_token_accuracy": 0.15575063228607178,
|
|
"num_tokens": 5744978.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.83977370262146,
|
|
"epoch": 0.24478856462179868,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998207134365883,
|
|
"loss": 5.6617,
|
|
"mean_token_accuracy": 0.1565300188958645,
|
|
"num_tokens": 5758723.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.721971750259399,
|
|
"epoch": 0.24538415723645027,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998190086195223,
|
|
"loss": 5.508,
|
|
"mean_token_accuracy": 0.15415533781051635,
|
|
"num_tokens": 5773646.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.807780694961548,
|
|
"epoch": 0.24597974985110185,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998172957385638,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.1513384312391281,
|
|
"num_tokens": 5787226.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.807900142669678,
|
|
"epoch": 0.2465753424657534,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998155747937746,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.15615093782544137,
|
|
"num_tokens": 5801378.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.811914014816284,
|
|
"epoch": 0.247170935080405,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998138457852162,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.15894006341695785,
|
|
"num_tokens": 5815136.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.7826625347137455,
|
|
"epoch": 0.24776652769505658,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998121087129507,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.1564724251627922,
|
|
"num_tokens": 5830222.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.774316072463989,
|
|
"epoch": 0.24836212030970817,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998103635770404,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.14870412200689315,
|
|
"num_tokens": 5844289.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.8135326385498045,
|
|
"epoch": 0.24895771292435973,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998086103775478,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.1576744720339775,
|
|
"num_tokens": 5857876.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.755991125106812,
|
|
"epoch": 0.2495533055390113,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998068491145359,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.14946600943803787,
|
|
"num_tokens": 5872032.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.7675745487213135,
|
|
"epoch": 0.25014889815366287,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998050797880678,
|
|
"loss": 5.5291,
|
|
"mean_token_accuracy": 0.15345812737941741,
|
|
"num_tokens": 5885478.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.835575771331787,
|
|
"epoch": 0.25074449076831445,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998033023982071,
|
|
"loss": 5.6486,
|
|
"mean_token_accuracy": 0.14204476475715638,
|
|
"num_tokens": 5900888.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.732381963729859,
|
|
"epoch": 0.25134008338296604,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998015169450174,
|
|
"loss": 5.4721,
|
|
"mean_token_accuracy": 0.15993799418210983,
|
|
"num_tokens": 5917158.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.7967307567596436,
|
|
"epoch": 0.2519356759976176,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997997234285627,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.1500745326280594,
|
|
"num_tokens": 5931879.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.675069808959961,
|
|
"epoch": 0.2525312686122692,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997979218489076,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.15455867499113082,
|
|
"num_tokens": 5947015.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.684785461425781,
|
|
"epoch": 0.2531268612269208,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997961122061164,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.15598441213369368,
|
|
"num_tokens": 5962063.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.699853420257568,
|
|
"epoch": 0.2537224538415724,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997942945002543,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.16179423332214354,
|
|
"num_tokens": 5977697.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.768417644500732,
|
|
"epoch": 0.25431804645622397,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997924687313862,
|
|
"loss": 5.5382,
|
|
"mean_token_accuracy": 0.1563252717256546,
|
|
"num_tokens": 5994117.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.733187580108643,
|
|
"epoch": 0.2549136390708755,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997906348995777,
|
|
"loss": 5.525,
|
|
"mean_token_accuracy": 0.15403501689434052,
|
|
"num_tokens": 6009878.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.760872936248779,
|
|
"epoch": 0.2555092316855271,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997887930048947,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.15625921934843062,
|
|
"num_tokens": 6021152.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.78124737739563,
|
|
"epoch": 0.25610482430017867,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997869430474033,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.15420911312103272,
|
|
"num_tokens": 6035975.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.628174638748169,
|
|
"epoch": 0.25670041691483025,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997850850271696,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.15644560009241104,
|
|
"num_tokens": 6048326.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.875419235229492,
|
|
"epoch": 0.25729600952948184,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997832189442604,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.15095992684364318,
|
|
"num_tokens": 6063327.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.737497997283936,
|
|
"epoch": 0.2578916021441334,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997813447987426,
|
|
"loss": 5.5316,
|
|
"mean_token_accuracy": 0.15511489361524583,
|
|
"num_tokens": 6077207.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.731353807449341,
|
|
"epoch": 0.258487194758785,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997794625906834,
|
|
"loss": 5.5123,
|
|
"mean_token_accuracy": 0.15723375827074051,
|
|
"num_tokens": 6094691.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.758441305160522,
|
|
"epoch": 0.2590827873734366,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997775723201504,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.15815255790948868,
|
|
"num_tokens": 6108539.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.736060714721679,
|
|
"epoch": 0.2596783799880881,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997756739872112,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.1544911876320839,
|
|
"num_tokens": 6122799.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.797795200347901,
|
|
"epoch": 0.2602739726027397,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997737675919344,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.16468376070261,
|
|
"num_tokens": 6137525.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.8151754379272464,
|
|
"epoch": 0.2608695652173913,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997718531343877,
|
|
"loss": 5.6622,
|
|
"mean_token_accuracy": 0.15274518579244614,
|
|
"num_tokens": 6151418.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.805972099304199,
|
|
"epoch": 0.2614651578320429,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997699306146402,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.15299971848726274,
|
|
"num_tokens": 6164839.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.637115383148194,
|
|
"epoch": 0.26206075044669447,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997680000327607,
|
|
"loss": 5.4347,
|
|
"mean_token_accuracy": 0.16252323240041733,
|
|
"num_tokens": 6179641.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.771062994003296,
|
|
"epoch": 0.26265634306134605,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004997660613888185,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.1493033602833748,
|
|
"num_tokens": 6196204.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.878154134750366,
|
|
"epoch": 0.26325193567599764,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997641146828831,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.1535416066646576,
|
|
"num_tokens": 6210704.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.677254629135132,
|
|
"epoch": 0.26384752829064917,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997621599150244,
|
|
"loss": 5.4659,
|
|
"mean_token_accuracy": 0.16301869750022888,
|
|
"num_tokens": 6226028.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.774082469940185,
|
|
"epoch": 0.26444312090530075,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997601970853124,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.15197534412145614,
|
|
"num_tokens": 6242376.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.740234518051148,
|
|
"epoch": 0.26503871351995234,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997582261938177,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.1531852275133133,
|
|
"num_tokens": 6255471.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.733001852035523,
|
|
"epoch": 0.2656343061346039,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997562472406107,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.16006610095500945,
|
|
"num_tokens": 6268081.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.684260606765747,
|
|
"epoch": 0.2662298987492555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997542602257626,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.1666449248790741,
|
|
"num_tokens": 6281765.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.790953207015991,
|
|
"epoch": 0.2668254913639071,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997522651493447,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.1565714307129383,
|
|
"num_tokens": 6297392.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.612934255599976,
|
|
"epoch": 0.2674210839785587,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997502620114284,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.1620727762579918,
|
|
"num_tokens": 6310726.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.775699138641357,
|
|
"epoch": 0.26801667659321027,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997482508120856,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.16205329895019532,
|
|
"num_tokens": 6325290.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.702234697341919,
|
|
"epoch": 0.2686122692078618,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997462315513884,
|
|
"loss": 5.5529,
|
|
"mean_token_accuracy": 0.15332119464874266,
|
|
"num_tokens": 6340056.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.680809068679809,
|
|
"epoch": 0.2692078618225134,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997442042294095,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.1613737717270851,
|
|
"num_tokens": 6353378.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.730574035644532,
|
|
"epoch": 0.26980345443716497,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997421688462213,
|
|
"loss": 5.5202,
|
|
"mean_token_accuracy": 0.15490979701280594,
|
|
"num_tokens": 6365916.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.720281267166138,
|
|
"epoch": 0.27039904705181655,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997401254018969,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.16011253744363785,
|
|
"num_tokens": 6380274.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.747355031967163,
|
|
"epoch": 0.27099463966646814,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997380738965096,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.15410203337669373,
|
|
"num_tokens": 6394769.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.685437393188477,
|
|
"epoch": 0.2715902322811197,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499736014330133,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.1563577249646187,
|
|
"num_tokens": 6408980.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.707857322692871,
|
|
"epoch": 0.2721858248957713,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997339467028409,
|
|
"loss": 5.4466,
|
|
"mean_token_accuracy": 0.1624538853764534,
|
|
"num_tokens": 6424267.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.687609052658081,
|
|
"epoch": 0.2727814175104229,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004997318710147076,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.16648496836423873,
|
|
"num_tokens": 6438827.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.690534782409668,
|
|
"epoch": 0.2733770101250744,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997297872658075,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.15981334447860718,
|
|
"num_tokens": 6453040.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.738874864578247,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997276954562152,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.15814361572265626,
|
|
"num_tokens": 6469960.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.6687750816345215,
|
|
"epoch": 0.2745681953543776,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499725595586006,
|
|
"loss": 5.5159,
|
|
"mean_token_accuracy": 0.1565321996808052,
|
|
"num_tokens": 6483914.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.600572776794434,
|
|
"epoch": 0.2751637879690292,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499723487655255,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.165006785094738,
|
|
"num_tokens": 6497290.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.638116407394409,
|
|
"epoch": 0.27575938058368077,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997213716640378,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.1609934851527214,
|
|
"num_tokens": 6512558.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.681073951721191,
|
|
"epoch": 0.27635497319833235,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997192476124306,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.1543683797121048,
|
|
"num_tokens": 6527786.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.664290475845337,
|
|
"epoch": 0.27695056581298394,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997171155005091,
|
|
"loss": 5.4506,
|
|
"mean_token_accuracy": 0.1584233894944191,
|
|
"num_tokens": 6540925.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.691961193084717,
|
|
"epoch": 0.27754615842763547,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997149753283502,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.15958700627088546,
|
|
"num_tokens": 6553945.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.706377840042114,
|
|
"epoch": 0.27814175104228706,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997128270960304,
|
|
"loss": 5.5163,
|
|
"mean_token_accuracy": 0.16332324147224425,
|
|
"num_tokens": 6568986.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.6778669357299805,
|
|
"epoch": 0.27873734365693864,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997106708036268,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.1605681896209717,
|
|
"num_tokens": 6582219.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.675868034362793,
|
|
"epoch": 0.2793329362715902,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499708506451217,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.15856398940086364,
|
|
"num_tokens": 6597670.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.651786422729492,
|
|
"epoch": 0.2799285288862418,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997063340388783,
|
|
"loss": 5.5429,
|
|
"mean_token_accuracy": 0.1593650110065937,
|
|
"num_tokens": 6612923.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.812162923812866,
|
|
"epoch": 0.2805241215008934,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997041535666888,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.16022965535521508,
|
|
"num_tokens": 6624762.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.630000257492066,
|
|
"epoch": 0.281119714115545,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997019650347266,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.1686081826686859,
|
|
"num_tokens": 6637910.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.7279884815216064,
|
|
"epoch": 0.28171530673019657,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996997684430703,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.158505779504776,
|
|
"num_tokens": 6652212.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.750305461883545,
|
|
"epoch": 0.2823108993448481,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996975637917986,
|
|
"loss": 5.5519,
|
|
"mean_token_accuracy": 0.15858569145202636,
|
|
"num_tokens": 6665535.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.708090734481812,
|
|
"epoch": 0.2829064919594997,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004996953510809906,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.16342256516218184,
|
|
"num_tokens": 6680013.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.6703039646148685,
|
|
"epoch": 0.28350208457415127,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996931303107258,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.16596188247203827,
|
|
"num_tokens": 6692384.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.69407286643982,
|
|
"epoch": 0.28409767718880286,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996909014810837,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.1595408760011196,
|
|
"num_tokens": 6707127.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.690748167037964,
|
|
"epoch": 0.28469326980345444,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004996886645921442,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.16248813569545745,
|
|
"num_tokens": 6720434.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.661434459686279,
|
|
"epoch": 0.285288862418106,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996864196439877,
|
|
"loss": 5.5837,
|
|
"mean_token_accuracy": 0.1565555177628994,
|
|
"num_tokens": 6734457.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.750744819641113,
|
|
"epoch": 0.2858844550327576,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996841666366947,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.15229643881320953,
|
|
"num_tokens": 6750351.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.658818674087525,
|
|
"epoch": 0.2864800476474092,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996819055703458,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.16347557157278061,
|
|
"num_tokens": 6765252.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.655593967437744,
|
|
"epoch": 0.2870756402620607,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996796364450224,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.1633814185857773,
|
|
"num_tokens": 6778020.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.649205923080444,
|
|
"epoch": 0.2876712328767123,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996773592608057,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.16340244710445403,
|
|
"num_tokens": 6792233.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.806488037109375,
|
|
"epoch": 0.2882668254913639,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996750740177775,
|
|
"loss": 5.593,
|
|
"mean_token_accuracy": 0.15179218500852584,
|
|
"num_tokens": 6807781.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.601470994949341,
|
|
"epoch": 0.2888624181060155,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996727807160196,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.1655975565314293,
|
|
"num_tokens": 6822406.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.62792272567749,
|
|
"epoch": 0.28945801072066707,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996704793556144,
|
|
"loss": 5.4443,
|
|
"mean_token_accuracy": 0.15741414576768875,
|
|
"num_tokens": 6835192.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.686983442306518,
|
|
"epoch": 0.29005360333531865,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996681699366443,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.1636321559548378,
|
|
"num_tokens": 6846921.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.634683132171631,
|
|
"epoch": 0.29064919594997024,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996658524591924,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.1642177626490593,
|
|
"num_tokens": 6864195.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.62883620262146,
|
|
"epoch": 0.2912447885646218,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996635269233415,
|
|
"loss": 5.4018,
|
|
"mean_token_accuracy": 0.15959485471248627,
|
|
"num_tokens": 6879095.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.645639038085937,
|
|
"epoch": 0.29184038117927336,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996611933291752,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.16254814714193344,
|
|
"num_tokens": 6891853.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.682731676101684,
|
|
"epoch": 0.29243597379392494,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996588516767772,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.15918793380260468,
|
|
"num_tokens": 6905235.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.622744417190551,
|
|
"epoch": 0.2930315664085765,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996565019662315,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.1667335644364357,
|
|
"num_tokens": 6918438.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.684930801391602,
|
|
"epoch": 0.2936271590232281,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004996541441976223,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.16349320709705353,
|
|
"num_tokens": 6931749.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.6001488208770756,
|
|
"epoch": 0.2942227516378797,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996517783710342,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.17157334089279175,
|
|
"num_tokens": 6946114.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.642820072174072,
|
|
"epoch": 0.2948183442525313,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996494044865521,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.16377470642328262,
|
|
"num_tokens": 6959002.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.623351621627807,
|
|
"epoch": 0.29541393686718287,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996470225442611,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.16650692522525787,
|
|
"num_tokens": 6973248.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.604974031448364,
|
|
"epoch": 0.2960095294818344,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996446325442466,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.16485302448272704,
|
|
"num_tokens": 6985223.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.659956407546997,
|
|
"epoch": 0.296605122096486,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996422344865945,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.16301326006650924,
|
|
"num_tokens": 6998948.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.703521823883056,
|
|
"epoch": 0.29720071471113757,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996398283713907,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.16087786257266998,
|
|
"num_tokens": 7011594.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.517322826385498,
|
|
"epoch": 0.29779630732578916,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996374141987215,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.16284587234258652,
|
|
"num_tokens": 7025451.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.603648471832275,
|
|
"epoch": 0.29839189994044074,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996349919686733,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.16220980733633042,
|
|
"num_tokens": 7038301.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.7301164150238035,
|
|
"epoch": 0.2989874925550923,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996325616813334,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.1573624238371849,
|
|
"num_tokens": 7053777.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.654399871826172,
|
|
"epoch": 0.2995830851697439,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996301233367886,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.16134716123342513,
|
|
"num_tokens": 7069516.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.63122296333313,
|
|
"epoch": 0.3001786777843955,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996276769351265,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.15889426767826081,
|
|
"num_tokens": 7083514.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.625289440155029,
|
|
"epoch": 0.30077427039904703,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996252224764349,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.16070133969187736,
|
|
"num_tokens": 7096637.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.757515525817871,
|
|
"epoch": 0.3013698630136986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996227599608018,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.17124143242835999,
|
|
"num_tokens": 7111994.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.60223240852356,
|
|
"epoch": 0.3019654556283502,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996202893883156,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.16722567081451417,
|
|
"num_tokens": 7125148.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.6869062900543215,
|
|
"epoch": 0.3025610482430018,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996178107590648,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.1579883798956871,
|
|
"num_tokens": 7140015.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.694077968597412,
|
|
"epoch": 0.30315664085765337,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996153240731381,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.16261224448680878,
|
|
"num_tokens": 7152939.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.656959056854248,
|
|
"epoch": 0.30375223347230496,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996128293306251,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.15252157896757126,
|
|
"num_tokens": 7167115.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.650059747695923,
|
|
"epoch": 0.30434782608695654,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996103265316152,
|
|
"loss": 5.405,
|
|
"mean_token_accuracy": 0.1619548663496971,
|
|
"num_tokens": 7180455.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.621711111068725,
|
|
"epoch": 0.3049434187016081,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996078156761979,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.16667965352535247,
|
|
"num_tokens": 7193777.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.720235681533813,
|
|
"epoch": 0.30553901131625966,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996052967644636,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.16859492510557175,
|
|
"num_tokens": 7205851.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.658883047103882,
|
|
"epoch": 0.30613460393091124,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996027697965024,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.15974574387073517,
|
|
"num_tokens": 7221359.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.722562074661255,
|
|
"epoch": 0.3067301965455628,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499600234772405,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.15828749239444734,
|
|
"num_tokens": 7235583.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.659008884429932,
|
|
"epoch": 0.3073257891602144,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995976916922624,
|
|
"loss": 5.4571,
|
|
"mean_token_accuracy": 0.16872933506965637,
|
|
"num_tokens": 7250477.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.575438928604126,
|
|
"epoch": 0.307921381774866,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995951405561658,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.16320499032735825,
|
|
"num_tokens": 7264197.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.7057945728302,
|
|
"epoch": 0.3085169743895176,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004995925813642068,
|
|
"loss": 5.4301,
|
|
"mean_token_accuracy": 0.1670471578836441,
|
|
"num_tokens": 7278989.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.596223020553589,
|
|
"epoch": 0.30911256700416917,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995900141164768,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.16520352214574813,
|
|
"num_tokens": 7293213.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.642040157318116,
|
|
"epoch": 0.3097081596188207,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995874388130683,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.1643291413784027,
|
|
"num_tokens": 7306774.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.541489362716675,
|
|
"epoch": 0.3103037522334723,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995848554540734,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.16852965205907822,
|
|
"num_tokens": 7321239.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.608112096786499,
|
|
"epoch": 0.31089934484812387,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000499582264039585,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.16969144344329834,
|
|
"num_tokens": 7335872.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.587273740768433,
|
|
"epoch": 0.31149493746277546,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499579664569696,
|
|
"loss": 5.3986,
|
|
"mean_token_accuracy": 0.16438512206077577,
|
|
"num_tokens": 7350523.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.714767551422119,
|
|
"epoch": 0.31209053007742704,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995770570444996,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.16590621918439866,
|
|
"num_tokens": 7363201.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.672125720977784,
|
|
"epoch": 0.3126861226920786,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995744414640892,
|
|
"loss": 5.4776,
|
|
"mean_token_accuracy": 0.16536226719617844,
|
|
"num_tokens": 7375377.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.598500680923462,
|
|
"epoch": 0.3132817153067302,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995718178285587,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.1610244855284691,
|
|
"num_tokens": 7388871.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.603353834152221,
|
|
"epoch": 0.3138773079213818,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995691861380022,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.1694616049528122,
|
|
"num_tokens": 7402235.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.588888549804688,
|
|
"epoch": 0.31447290053603333,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995665463925142,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.1702384278178215,
|
|
"num_tokens": 7414673.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.603456687927246,
|
|
"epoch": 0.3150684931506849,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995638985921893,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.1671357810497284,
|
|
"num_tokens": 7429039.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.653233814239502,
|
|
"epoch": 0.3156640857653365,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995612427371224,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.1631896674633026,
|
|
"num_tokens": 7443060.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.561821508407593,
|
|
"epoch": 0.3162596783799881,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499558578827409,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.1673417568206787,
|
|
"num_tokens": 7456717.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.510098791122436,
|
|
"epoch": 0.31685527099463967,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995559068631444,
|
|
"loss": 5.3902,
|
|
"mean_token_accuracy": 0.16376861929893494,
|
|
"num_tokens": 7470878.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.585044717788696,
|
|
"epoch": 0.31745086360929126,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995532268444244,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.1690148487687111,
|
|
"num_tokens": 7486427.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.680125522613525,
|
|
"epoch": 0.31804645622394284,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995505387713453,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.15970658510923386,
|
|
"num_tokens": 7500759.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.595620584487915,
|
|
"epoch": 0.3186420488385944,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995478426440037,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.16363002210855485,
|
|
"num_tokens": 7513224.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.56921157836914,
|
|
"epoch": 0.31923764145324596,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995451384624959,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.16787581592798234,
|
|
"num_tokens": 7528128.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.619098758697509,
|
|
"epoch": 0.31983323406789754,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995424262269191,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.17019287794828414,
|
|
"num_tokens": 7541731.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.637658786773682,
|
|
"epoch": 0.32042882668254913,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995397059373704,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.16239553838968276,
|
|
"num_tokens": 7555938.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.5821184635162355,
|
|
"epoch": 0.3210244192972007,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995369775939478,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.16661161184310913,
|
|
"num_tokens": 7570033.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.588184785842896,
|
|
"epoch": 0.3216200119118523,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995342411967487,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.16195307672023773,
|
|
"num_tokens": 7585131.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.5823287010192875,
|
|
"epoch": 0.3222156045265039,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995314967458715,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.16910858303308487,
|
|
"num_tokens": 7600167.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.595126008987426,
|
|
"epoch": 0.32281119714115547,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995287442414145,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.16785854250192642,
|
|
"num_tokens": 7612301.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.670919895172119,
|
|
"epoch": 0.323406789755807,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995259836834767,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.16672904193401336,
|
|
"num_tokens": 7625837.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.593075847625732,
|
|
"epoch": 0.3240023823704586,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995232150721568,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.1659615993499756,
|
|
"num_tokens": 7640555.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.521756744384765,
|
|
"epoch": 0.32459797498511017,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995204384075542,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.16779649555683135,
|
|
"num_tokens": 7655395.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.592764663696289,
|
|
"epoch": 0.32519356759976176,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995176536897685,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.15718302726745606,
|
|
"num_tokens": 7670429.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.564849042892456,
|
|
"epoch": 0.32578916021441334,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995148609188997,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.1616342008113861,
|
|
"num_tokens": 7684240.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.677158641815185,
|
|
"epoch": 0.32638475282906493,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995120600950479,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.16039044857025148,
|
|
"num_tokens": 7698412.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.597699451446533,
|
|
"epoch": 0.3269803454437165,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995092512183134,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.1639407083392143,
|
|
"num_tokens": 7712814.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.653441715240478,
|
|
"epoch": 0.3275759380583681,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995064342887972,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.1640625,
|
|
"num_tokens": 7726740.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.585921716690064,
|
|
"epoch": 0.32817153067301963,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995036093066001,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.1629028469324112,
|
|
"num_tokens": 7741411.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.535441064834595,
|
|
"epoch": 0.3287671232876712,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995007762718237,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.1750536099076271,
|
|
"num_tokens": 7753530.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.548461389541626,
|
|
"epoch": 0.3293627159023228,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994979351845693,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.1694473460316658,
|
|
"num_tokens": 7766924.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.568308877944946,
|
|
"epoch": 0.3299583085169744,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004994950860449392,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.16138947308063506,
|
|
"num_tokens": 7781561.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.650861835479736,
|
|
"epoch": 0.33055390113162597,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994922288530353,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.1612231746315956,
|
|
"num_tokens": 7796254.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.5372191905975345,
|
|
"epoch": 0.33114949374627756,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994893636089601,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.1660068452358246,
|
|
"num_tokens": 7808683.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.674601745605469,
|
|
"epoch": 0.33174508636092914,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994864903128164,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.160142220556736,
|
|
"num_tokens": 7822688.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.652541589736939,
|
|
"epoch": 0.33234067897558073,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994836089647073,
|
|
"loss": 5.3996,
|
|
"mean_token_accuracy": 0.1659604012966156,
|
|
"num_tokens": 7838425.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.51391978263855,
|
|
"epoch": 0.33293627159023226,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994807195647362,
|
|
"loss": 5.3511,
|
|
"mean_token_accuracy": 0.17419065684080123,
|
|
"num_tokens": 7851685.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.596407079696656,
|
|
"epoch": 0.33353186420488384,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994778221130066,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.16951974332332612,
|
|
"num_tokens": 7864735.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.506788825988769,
|
|
"epoch": 0.33412745681953543,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004994749166096226,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.16573702692985534,
|
|
"num_tokens": 7880240.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.481150054931641,
|
|
"epoch": 0.334723049434187,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004994720030546882,
|
|
"loss": 5.3548,
|
|
"mean_token_accuracy": 0.16667070090770722,
|
|
"num_tokens": 7893749.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.611258029937744,
|
|
"epoch": 0.3353186420488386,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994690814483081,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.17003161758184432,
|
|
"num_tokens": 7906132.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.484817552566528,
|
|
"epoch": 0.3359142346634902,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994661517905869,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.1729711577296257,
|
|
"num_tokens": 7919621.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.451206493377685,
|
|
"epoch": 0.33650982727814177,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004994632140816299,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.17531078755855561,
|
|
"num_tokens": 7932882.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.579314470291138,
|
|
"epoch": 0.33710541989279336,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994602683215424,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.16776238679885863,
|
|
"num_tokens": 7946374.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.608100175857544,
|
|
"epoch": 0.3377010125074449,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049945731451043,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.16137655675411225,
|
|
"num_tokens": 7959766.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.522439289093017,
|
|
"epoch": 0.33829660512209647,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004994543526483985,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.16792797297239304,
|
|
"num_tokens": 7974976.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.633068704605103,
|
|
"epoch": 0.33889219773674806,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994513827355546,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.15954930037260057,
|
|
"num_tokens": 7990605.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.561303997039795,
|
|
"epoch": 0.33948779035139964,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994484047720043,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.17052376717329026,
|
|
"num_tokens": 8004346.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.62995285987854,
|
|
"epoch": 0.34008338296605123,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994454187578547,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.1709371492266655,
|
|
"num_tokens": 8020219.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.68173189163208,
|
|
"epoch": 0.3406789755807028,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994424246932129,
|
|
"loss": 5.5041,
|
|
"mean_token_accuracy": 0.16103566735982894,
|
|
"num_tokens": 8034486.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.546448850631714,
|
|
"epoch": 0.3412745681953544,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994394225781863,
|
|
"loss": 5.3829,
|
|
"mean_token_accuracy": 0.16636965572834014,
|
|
"num_tokens": 8047661.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.5298261642456055,
|
|
"epoch": 0.34187016081000593,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994364124128825,
|
|
"loss": 5.3442,
|
|
"mean_token_accuracy": 0.1692613497376442,
|
|
"num_tokens": 8063638.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.557293844223023,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994333941974094,
|
|
"loss": 5.3739,
|
|
"mean_token_accuracy": 0.16984928846359254,
|
|
"num_tokens": 8075743.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.562584686279297,
|
|
"epoch": 0.3430613460393091,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994303679318754,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.17036716639995575,
|
|
"num_tokens": 8090169.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.520627689361572,
|
|
"epoch": 0.3436569386539607,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994273336163891,
|
|
"loss": 5.3606,
|
|
"mean_token_accuracy": 0.16793280690908433,
|
|
"num_tokens": 8104919.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.607230520248413,
|
|
"epoch": 0.34425253126861227,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994242912510591,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.17202310562133788,
|
|
"num_tokens": 8117893.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.5752369403839115,
|
|
"epoch": 0.34484812388326386,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994212408359948,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.15659124553203582,
|
|
"num_tokens": 8133325.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.555515193939209,
|
|
"epoch": 0.34544371649791544,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994181823713054,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.17399801909923554,
|
|
"num_tokens": 8147728.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.53694109916687,
|
|
"epoch": 0.34603930911256703,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994151158571006,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.1690783217549324,
|
|
"num_tokens": 8163045.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.579945468902588,
|
|
"epoch": 0.34663490172721856,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994120412934906,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.16330579668283463,
|
|
"num_tokens": 8176946.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.55695333480835,
|
|
"epoch": 0.34723049434187014,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.17500018179416657,
|
|
"num_tokens": 8189507.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.5458403587341305,
|
|
"epoch": 0.34782608695652173,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994058680184959,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.16473894268274308,
|
|
"num_tokens": 8203920.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.583098363876343,
|
|
"epoch": 0.3484216795711733,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994027693073327,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.16916266828775406,
|
|
"num_tokens": 8217719.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.498113679885864,
|
|
"epoch": 0.3490172721858249,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004993996625472071,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.1656230941414833,
|
|
"num_tokens": 8232796.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.611781883239746,
|
|
"epoch": 0.3496128648004765,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993965477382304,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.16605483144521713,
|
|
"num_tokens": 8244150.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.51896595954895,
|
|
"epoch": 0.35020845741512807,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993934248805143,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.1716987296938896,
|
|
"num_tokens": 8259070.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.557607984542846,
|
|
"epoch": 0.35080405002977966,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004993902939741709,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.17213038504123687,
|
|
"num_tokens": 8273558.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.558725500106812,
|
|
"epoch": 0.3513996426444312,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004993871550193126,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.16512211114168168,
|
|
"num_tokens": 8287816.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.551508140563965,
|
|
"epoch": 0.3519952352590828,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993840080160519,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.16179206371307372,
|
|
"num_tokens": 8303047.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.5350017070770265,
|
|
"epoch": 0.35259082787373436,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993808529645016,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.17535457462072374,
|
|
"num_tokens": 8315907.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.526376485824585,
|
|
"epoch": 0.35318642048838594,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993776898647749,
|
|
"loss": 5.2635,
|
|
"mean_token_accuracy": 0.18118688762187957,
|
|
"num_tokens": 8329343.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.607866668701172,
|
|
"epoch": 0.35378201310303753,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993745187169852,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.16549852937459947,
|
|
"num_tokens": 8343698.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.615293073654175,
|
|
"epoch": 0.3543776057176891,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993713395212464,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.1712152659893036,
|
|
"num_tokens": 8357697.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.4842555046081545,
|
|
"epoch": 0.3549731983323407,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004993681522776725,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.16991902887821198,
|
|
"num_tokens": 8370743.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.450813293457031,
|
|
"epoch": 0.35556879094699223,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993649569863778,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.1822266697883606,
|
|
"num_tokens": 8383328.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.515005159378052,
|
|
"epoch": 0.3561643835616438,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004993617536474768,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.17316077202558516,
|
|
"num_tokens": 8398539.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.561909484863281,
|
|
"epoch": 0.3567599761762954,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993585422610845,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.1747918203473091,
|
|
"num_tokens": 8411238.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.403289079666138,
|
|
"epoch": 0.357355568790947,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993553228273161,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.1780083805322647,
|
|
"num_tokens": 8424818.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.357355568790947,
|
|
"eval_entropy": 5.37680235925513,
|
|
"eval_loss": 5.318552017211914,
|
|
"eval_mean_token_accuracy": 0.17886876086923395,
|
|
"eval_num_tokens": 8424818.0,
|
|
"eval_runtime": 18.7597,
|
|
"eval_samples_per_second": 1359.988,
|
|
"eval_steps_per_second": 170.045,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.680321264266968,
|
|
"epoch": 0.3579511614055986,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499352095346287,
|
|
"loss": 5.399,
|
|
"mean_token_accuracy": 0.1633133828639984,
|
|
"num_tokens": 8438974.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.512087774276734,
|
|
"epoch": 0.35854675402025016,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993488598181131,
|
|
"loss": 5.3446,
|
|
"mean_token_accuracy": 0.17261969894170762,
|
|
"num_tokens": 8453583.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.586219453811646,
|
|
"epoch": 0.35914234663490174,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004993456162429103,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.1768076851963997,
|
|
"num_tokens": 8467621.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.497888278961182,
|
|
"epoch": 0.35973793924955333,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993423646207951,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.16826776117086412,
|
|
"num_tokens": 8482697.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.587547063827515,
|
|
"epoch": 0.36033353186420486,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499339104951884,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.1691280946135521,
|
|
"num_tokens": 8495347.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.386959505081177,
|
|
"epoch": 0.36092912447885644,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993358372362939,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.17298889458179473,
|
|
"num_tokens": 8509132.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.58005108833313,
|
|
"epoch": 0.36152471709350803,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993325614741421,
|
|
"loss": 5.3427,
|
|
"mean_token_accuracy": 0.1748684138059616,
|
|
"num_tokens": 8523563.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.462400150299072,
|
|
"epoch": 0.3621203097081596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993292776655461,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.17874590456485748,
|
|
"num_tokens": 8536399.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.38701868057251,
|
|
"epoch": 0.3627159023228112,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004993259858106236,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.1766919583082199,
|
|
"num_tokens": 8550969.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.559665727615356,
|
|
"epoch": 0.3633114949374628,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004993226859094927,
|
|
"loss": 5.394,
|
|
"mean_token_accuracy": 0.16338545382022857,
|
|
"num_tokens": 8567051.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.580748558044434,
|
|
"epoch": 0.36390708755211437,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993193779622719,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.16738884449005126,
|
|
"num_tokens": 8581255.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.528922605514526,
|
|
"epoch": 0.36450268016676596,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993160619690796,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.16771526932716369,
|
|
"num_tokens": 8595640.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.544296360015869,
|
|
"epoch": 0.3650982727814175,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993127379300349,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.17728762030601503,
|
|
"num_tokens": 8609506.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.492613697052002,
|
|
"epoch": 0.3656938653960691,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000499309405845257,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.1677103117108345,
|
|
"num_tokens": 8624691.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.452147674560547,
|
|
"epoch": 0.36628945801072066,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993060657148654,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.1761177286505699,
|
|
"num_tokens": 8637218.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.438749027252197,
|
|
"epoch": 0.36688505062537224,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.00049930271753898,
|
|
"loss": 5.3447,
|
|
"mean_token_accuracy": 0.16596392095088958,
|
|
"num_tokens": 8650153.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.507561540603637,
|
|
"epoch": 0.36748064324002383,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004992993613177208,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.17530115246772765,
|
|
"num_tokens": 8663280.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.494558048248291,
|
|
"epoch": 0.3680762358546754,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992959970512082,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.17123837321996688,
|
|
"num_tokens": 8677266.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.454576587677002,
|
|
"epoch": 0.368671828469327,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992926247395627,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.16978070735931397,
|
|
"num_tokens": 8692660.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.541762828826904,
|
|
"epoch": 0.36926742108397853,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992892443829057,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.16679900139570236,
|
|
"num_tokens": 8706200.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.477366161346436,
|
|
"epoch": 0.3698630136986301,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499285855981358,
|
|
"loss": 5.2383,
|
|
"mean_token_accuracy": 0.18339828699827193,
|
|
"num_tokens": 8720421.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.4448723793029785,
|
|
"epoch": 0.3704586063132817,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992824595350414,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.17096095830202102,
|
|
"num_tokens": 8732343.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.54713077545166,
|
|
"epoch": 0.3710541989279333,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004992790550440775,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.169817216694355,
|
|
"num_tokens": 8746247.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.476923227310181,
|
|
"epoch": 0.3716497915425849,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992756425085887,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.17333812415599822,
|
|
"num_tokens": 8760964.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.406105470657349,
|
|
"epoch": 0.37224538415723646,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992722219286972,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.17805521190166473,
|
|
"num_tokens": 8774889.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.49105749130249,
|
|
"epoch": 0.37284097677188804,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004992687933045258,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.17202328592538835,
|
|
"num_tokens": 8790479.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.518159627914429,
|
|
"epoch": 0.37343656938653963,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992653566361974,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.17018354088068008,
|
|
"num_tokens": 8805129.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.51479058265686,
|
|
"epoch": 0.37403216200119116,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992619119238351,
|
|
"loss": 5.2554,
|
|
"mean_token_accuracy": 0.17537494003772736,
|
|
"num_tokens": 8818046.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.474508285522461,
|
|
"epoch": 0.37462775461584275,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499258459167563,
|
|
"loss": 5.2925,
|
|
"mean_token_accuracy": 0.17804195433855058,
|
|
"num_tokens": 8830715.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.538359642028809,
|
|
"epoch": 0.37522334723049433,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004992549983675043,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.1781470611691475,
|
|
"num_tokens": 8846349.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.456615257263183,
|
|
"epoch": 0.3758189398451459,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004992515295237835,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.17611448764801024,
|
|
"num_tokens": 8861316.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.466844654083252,
|
|
"epoch": 0.3764145324597975,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499248052636525,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.168072509765625,
|
|
"num_tokens": 8874349.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.5694833278656,
|
|
"epoch": 0.3770101250744491,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004992445677058534,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.16894514560699464,
|
|
"num_tokens": 8887836.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.4926026344299315,
|
|
"epoch": 0.3776057176891007,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004992410747318938,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.17341060191392899,
|
|
"num_tokens": 8902009.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.46876220703125,
|
|
"epoch": 0.37820131030375226,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004992375737147715,
|
|
"loss": 5.2453,
|
|
"mean_token_accuracy": 0.1756640538573265,
|
|
"num_tokens": 8915960.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.444065523147583,
|
|
"epoch": 0.3787969029184038,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992340646546118,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.17703939378261566,
|
|
"num_tokens": 8930742.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.522914028167724,
|
|
"epoch": 0.3793924955330554,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.000499230547551541,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.16881698220968247,
|
|
"num_tokens": 8943535.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.406088829040527,
|
|
"epoch": 0.37998808814770696,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992270224056849,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.17789653837680816,
|
|
"num_tokens": 8958187.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.460651969909668,
|
|
"epoch": 0.38058368076235854,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992234892171702,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.17661686539649962,
|
|
"num_tokens": 8970409.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.5636115074157715,
|
|
"epoch": 0.38117927337701013,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992199479861235,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.1653168261051178,
|
|
"num_tokens": 8982302.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.482617282867432,
|
|
"epoch": 0.3817748659916617,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992163987126717,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.17122839987277985,
|
|
"num_tokens": 8996215.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.508302402496338,
|
|
"epoch": 0.3823704586063133,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004992128413969423,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.17007533311843873,
|
|
"num_tokens": 9011423.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.532516860961914,
|
|
"epoch": 0.3829660512209649,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992092760390628,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.1655038118362427,
|
|
"num_tokens": 9025322.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.524756622314453,
|
|
"epoch": 0.3835616438356164,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004992057026391612,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.17595667839050294,
|
|
"num_tokens": 9039199.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.467118883132935,
|
|
"epoch": 0.384157236450268,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992021211973655,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.18080250918865204,
|
|
"num_tokens": 9051808.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.549422788619995,
|
|
"epoch": 0.3847528290649196,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991985317138043,
|
|
"loss": 5.3876,
|
|
"mean_token_accuracy": 0.16935683488845826,
|
|
"num_tokens": 9066068.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.519559907913208,
|
|
"epoch": 0.3853484216795712,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991949341886063,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.17499166280031203,
|
|
"num_tokens": 9079209.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.506857776641846,
|
|
"epoch": 0.38594401429422276,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991913286219004,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.1776731863617897,
|
|
"num_tokens": 9092270.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.487370443344116,
|
|
"epoch": 0.38653960690887434,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991877150138162,
|
|
"loss": 5.2994,
|
|
"mean_token_accuracy": 0.1630220353603363,
|
|
"num_tokens": 9106231.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.474565696716309,
|
|
"epoch": 0.38713519952352593,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004991840933644831,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.16995661556720734,
|
|
"num_tokens": 9119325.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.470413160324097,
|
|
"epoch": 0.38773079213817746,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499180463674031,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.16592499911785125,
|
|
"num_tokens": 9132792.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.473909616470337,
|
|
"epoch": 0.38832638475282905,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004991768259425903,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.18330173641443254,
|
|
"num_tokens": 9146659.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.479486703872681,
|
|
"epoch": 0.38892197736748063,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004991731801702914,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.17022957354784013,
|
|
"num_tokens": 9161035.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.531767892837524,
|
|
"epoch": 0.3895175699821322,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991695263572648,
|
|
"loss": 5.3527,
|
|
"mean_token_accuracy": 0.17080482095479965,
|
|
"num_tokens": 9176057.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.455781269073486,
|
|
"epoch": 0.3901131625967838,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991658645036419,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.1727764666080475,
|
|
"num_tokens": 9191021.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.406662321090698,
|
|
"epoch": 0.3907087552114354,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004991621946095539,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.18158661425113679,
|
|
"num_tokens": 9204717.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.5115703582763675,
|
|
"epoch": 0.391304347826087,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991585166751325,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.17364758551120757,
|
|
"num_tokens": 9218395.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.437616539001465,
|
|
"epoch": 0.39189994044073856,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991548307005094,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.17418505400419235,
|
|
"num_tokens": 9231419.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.457427072525024,
|
|
"epoch": 0.3924955330553901,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991511366858172,
|
|
"loss": 5.3173,
|
|
"mean_token_accuracy": 0.17052946090698243,
|
|
"num_tokens": 9246557.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.466603088378906,
|
|
"epoch": 0.3930911256700417,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004991474346311879,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.17370083630084993,
|
|
"num_tokens": 9261173.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.501963996887207,
|
|
"epoch": 0.39368671828469326,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991437245367547,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.17294615060091018,
|
|
"num_tokens": 9274819.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.363840007781983,
|
|
"epoch": 0.39428231089934485,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004991400064026506,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.18551855087280272,
|
|
"num_tokens": 9287219.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.423783922195435,
|
|
"epoch": 0.39487790351399643,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004991362802290089,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.16937638223171234,
|
|
"num_tokens": 9301069.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.46996488571167,
|
|
"epoch": 0.395473496128648,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991325460159631,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.16755855083465576,
|
|
"num_tokens": 9314807.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.426510858535766,
|
|
"epoch": 0.3960690887432996,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991288037636474,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.17628339678049088,
|
|
"num_tokens": 9328702.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.4537323951721195,
|
|
"epoch": 0.3966646813579512,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004991250534721959,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.17392530888319016,
|
|
"num_tokens": 9342949.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.451861000061035,
|
|
"epoch": 0.3972602739726027,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991212951417431,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.1817117303609848,
|
|
"num_tokens": 9357382.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.535891103744507,
|
|
"epoch": 0.3978558665872543,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004991175287724239,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.16250568628311157,
|
|
"num_tokens": 9371297.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.55002384185791,
|
|
"epoch": 0.3984514592019059,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991137543643733,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.16425398588180543,
|
|
"num_tokens": 9386213.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.467666053771973,
|
|
"epoch": 0.3990470518165575,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991099719177268,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.17735555768013,
|
|
"num_tokens": 9398166.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.394056797027588,
|
|
"epoch": 0.39964264443120906,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004991061814326198,
|
|
"loss": 5.2227,
|
|
"mean_token_accuracy": 0.17660689502954482,
|
|
"num_tokens": 9411611.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.422789573669434,
|
|
"epoch": 0.40023823704586065,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004991023829091887,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.1764301061630249,
|
|
"num_tokens": 9426461.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.447587490081787,
|
|
"epoch": 0.40083382966051223,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990985763475694,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.1825166314840317,
|
|
"num_tokens": 9437337.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.3998894691467285,
|
|
"epoch": 0.40142942227516376,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990947617478984,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.17848754674196243,
|
|
"num_tokens": 9450361.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.436241626739502,
|
|
"epoch": 0.40202501488981535,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004990909391103127,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.17749863415956496,
|
|
"num_tokens": 9463336.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.586833906173706,
|
|
"epoch": 0.40262060750446693,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990871084349494,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.17890213876962663,
|
|
"num_tokens": 9476602.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.424135065078735,
|
|
"epoch": 0.4032162001191185,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990832697219459,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.1717560201883316,
|
|
"num_tokens": 9490355.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.488651895523072,
|
|
"epoch": 0.4038117927337701,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990794229714398,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.17166533917188645,
|
|
"num_tokens": 9502191.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.564592266082764,
|
|
"epoch": 0.4044073853484217,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004990755681835693,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.1683407500386238,
|
|
"num_tokens": 9515694.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.45644359588623,
|
|
"epoch": 0.4050029779630733,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004990717053584723,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.1660124346613884,
|
|
"num_tokens": 9530146.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.529081010818482,
|
|
"epoch": 0.40559857057772486,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990678344962876,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.17050016224384307,
|
|
"num_tokens": 9541969.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.462375020980835,
|
|
"epoch": 0.4061941631923764,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990639555971539,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.16662318557500838,
|
|
"num_tokens": 9555837.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.532939672470093,
|
|
"epoch": 0.406789755807028,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990600686612106,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.1663308322429657,
|
|
"num_tokens": 9570841.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.449370431900024,
|
|
"epoch": 0.40738534842167956,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990561736885968,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.1833135575056076,
|
|
"num_tokens": 9583342.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.474269104003906,
|
|
"epoch": 0.40798094103633115,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004990522706794523,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.175234092772007,
|
|
"num_tokens": 9597217.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.464181041717529,
|
|
"epoch": 0.40857653365098273,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004990483596339174,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.17360809892416001,
|
|
"num_tokens": 9612251.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.450800228118896,
|
|
"epoch": 0.4091721262656343,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004990444405521318,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.17209622710943223,
|
|
"num_tokens": 9625693.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.442666816711426,
|
|
"epoch": 0.4097677188802859,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004990405134342366,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.17929224520921708,
|
|
"num_tokens": 9639687.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.452113676071167,
|
|
"epoch": 0.4103633114949375,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990365782803724,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.17022576034069062,
|
|
"num_tokens": 9652258.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.467024660110473,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004990326350906803,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.18065717816352844,
|
|
"num_tokens": 9665946.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.425072288513183,
|
|
"epoch": 0.4115544967242406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990286838653019,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.17535804063081742,
|
|
"num_tokens": 9680474.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.42586760520935,
|
|
"epoch": 0.4121500893388922,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004990247246043789,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.1768714651465416,
|
|
"num_tokens": 9693797.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.498319005966186,
|
|
"epoch": 0.4127456819535438,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990207573080533,
|
|
"loss": 5.2883,
|
|
"mean_token_accuracy": 0.17165374159812927,
|
|
"num_tokens": 9705875.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.544101190567017,
|
|
"epoch": 0.41334127456819536,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004990167819764672,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.16366368532180786,
|
|
"num_tokens": 9720968.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.46802339553833,
|
|
"epoch": 0.41393686718284695,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004990127986097636,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.17400429993867875,
|
|
"num_tokens": 9735586.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.406962060928345,
|
|
"epoch": 0.41453245979749853,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499008807208085,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.17054087668657303,
|
|
"num_tokens": 9750253.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.470438528060913,
|
|
"epoch": 0.4151280524121501,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990048077715746,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.17191239446401596,
|
|
"num_tokens": 9762814.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.51074800491333,
|
|
"epoch": 0.41572364502680165,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990008003003762,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.16247006505727768,
|
|
"num_tokens": 9777144.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.449260807037353,
|
|
"epoch": 0.41631923764145323,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989967847946331,
|
|
"loss": 5.2278,
|
|
"mean_token_accuracy": 0.17618376314640044,
|
|
"num_tokens": 9791746.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.452185726165771,
|
|
"epoch": 0.4169148302561048,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989927612544895,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.18122688978910445,
|
|
"num_tokens": 9804599.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.381531381607056,
|
|
"epoch": 0.4175104228707564,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004989887296800899,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.1840138852596283,
|
|
"num_tokens": 9817030.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.5035069465637205,
|
|
"epoch": 0.418106015485408,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004989846900715786,
|
|
"loss": 5.3751,
|
|
"mean_token_accuracy": 0.16727980375289916,
|
|
"num_tokens": 9832478.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.484005308151245,
|
|
"epoch": 0.4187016081000596,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989806424291008,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.17928555905818938,
|
|
"num_tokens": 9844534.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.313459587097168,
|
|
"epoch": 0.41929720071471116,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989765867528014,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.17965180724859237,
|
|
"num_tokens": 9856610.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.420787525177002,
|
|
"epoch": 0.4198927933293627,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989725230428262,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.17461090832948684,
|
|
"num_tokens": 9870527.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.393940591812134,
|
|
"epoch": 0.4204883859440143,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004989684512993205,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.1825983390212059,
|
|
"num_tokens": 9883616.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.339281606674194,
|
|
"epoch": 0.42108397855866586,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989643715224307,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.1792970046401024,
|
|
"num_tokens": 9896261.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.488557291030884,
|
|
"epoch": 0.42167957117331745,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989602837123031,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.17837779670953752,
|
|
"num_tokens": 9910405.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.512346267700195,
|
|
"epoch": 0.42227516378796903,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989561878690842,
|
|
"loss": 5.3244,
|
|
"mean_token_accuracy": 0.18207647353410722,
|
|
"num_tokens": 9923932.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.411928462982178,
|
|
"epoch": 0.4228707564026206,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000498952083992921,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.178289432823658,
|
|
"num_tokens": 9938132.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.391793441772461,
|
|
"epoch": 0.4234663490172722,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004989479720839605,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.18577739149332045,
|
|
"num_tokens": 9952468.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.468659734725952,
|
|
"epoch": 0.4240619416319238,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004989438521423506,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.1724991723895073,
|
|
"num_tokens": 9967269.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.389604949951172,
|
|
"epoch": 0.4246575342465753,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989397241682387,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.17644831985235215,
|
|
"num_tokens": 9979776.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.555214786529541,
|
|
"epoch": 0.4252531268612269,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000498935588161773,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.16603707075119017,
|
|
"num_tokens": 9993276.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.3539684295654295,
|
|
"epoch": 0.4258487194758785,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989314441231019,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.1891721025109291,
|
|
"num_tokens": 10005683.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.405005931854248,
|
|
"epoch": 0.4264443120905301,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004989272920523741,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.17995380461215973,
|
|
"num_tokens": 10018526.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.44573974609375,
|
|
"epoch": 0.42703990470518166,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004989231319497382,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.1663253426551819,
|
|
"num_tokens": 10034505.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.50796422958374,
|
|
"epoch": 0.42763549731983325,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989189638153437,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.17348333597183227,
|
|
"num_tokens": 10047465.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.407271909713745,
|
|
"epoch": 0.42823108993448483,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004989147876493401,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.17431857883930207,
|
|
"num_tokens": 10061644.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.4884562492370605,
|
|
"epoch": 0.4288266825491364,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004989106034518771,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.16636295318603517,
|
|
"num_tokens": 10076672.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.47823576927185,
|
|
"epoch": 0.42942227516378795,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004989064112231049,
|
|
"loss": 5.3624,
|
|
"mean_token_accuracy": 0.16651387363672257,
|
|
"num_tokens": 10091784.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.440695524215698,
|
|
"epoch": 0.43001786777843953,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004989022109631736,
|
|
"loss": 5.2044,
|
|
"mean_token_accuracy": 0.17865151762962342,
|
|
"num_tokens": 10104848.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.313720750808716,
|
|
"epoch": 0.4306134603930911,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988980026722341,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.17476957142353058,
|
|
"num_tokens": 10120561.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.463210964202881,
|
|
"epoch": 0.4312090530077427,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004988937863504373,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.17324580252170563,
|
|
"num_tokens": 10135692.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.414644336700439,
|
|
"epoch": 0.4318046456223943,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004988895619979344,
|
|
"loss": 5.176,
|
|
"mean_token_accuracy": 0.18038345873355865,
|
|
"num_tokens": 10148768.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.408927726745605,
|
|
"epoch": 0.4324002382370459,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498885329614877,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.17999188899993895,
|
|
"num_tokens": 10162234.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.443536901473999,
|
|
"epoch": 0.43299583085169746,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988810892014168,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.17555629163980485,
|
|
"num_tokens": 10177588.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.392063570022583,
|
|
"epoch": 0.433591423466349,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004988768407577058,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.18176117688417434,
|
|
"num_tokens": 10190324.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.280470323562622,
|
|
"epoch": 0.4341870160810006,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988725842838968,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.18004910945892333,
|
|
"num_tokens": 10204790.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.429841375350952,
|
|
"epoch": 0.43478260869565216,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000498868319780142,
|
|
"loss": 5.1764,
|
|
"mean_token_accuracy": 0.17985706627368928,
|
|
"num_tokens": 10219777.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.392672491073609,
|
|
"epoch": 0.43537820131030375,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988640472465947,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.174774831533432,
|
|
"num_tokens": 10234477.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.326955938339234,
|
|
"epoch": 0.43597379392495533,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004988597666834078,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.18471942394971846,
|
|
"num_tokens": 10247196.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.453542613983155,
|
|
"epoch": 0.4365693865396069,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988554780907353,
|
|
"loss": 5.2451,
|
|
"mean_token_accuracy": 0.1743731051683426,
|
|
"num_tokens": 10260752.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.379400730133057,
|
|
"epoch": 0.4371649791542585,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988511814687306,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.17780135124921798,
|
|
"num_tokens": 10274500.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.440290880203247,
|
|
"epoch": 0.4377605717689101,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004988468768175479,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.17906238734722138,
|
|
"num_tokens": 10290271.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.457077503204346,
|
|
"epoch": 0.4383561643835616,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004988425641373418,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.1688911572098732,
|
|
"num_tokens": 10305645.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.367054414749146,
|
|
"epoch": 0.4389517569982132,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004988382434282668,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.18412871211767196,
|
|
"num_tokens": 10321267.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.478347396850586,
|
|
"epoch": 0.4395473496128648,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000498833914690478,
|
|
"loss": 5.2146,
|
|
"mean_token_accuracy": 0.17777034193277358,
|
|
"num_tokens": 10336597.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.423448801040649,
|
|
"epoch": 0.4401429422275164,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004988295779241306,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.17510208189487458,
|
|
"num_tokens": 10351887.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.320586347579956,
|
|
"epoch": 0.44073853484216796,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004988252331293802,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.17715793550014497,
|
|
"num_tokens": 10366078.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.372301197052002,
|
|
"epoch": 0.44133412745681955,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004988208803063827,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.18149596601724624,
|
|
"num_tokens": 10380382.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.412890100479126,
|
|
"epoch": 0.44192972007147113,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004988165194552939,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.18643212467432022,
|
|
"num_tokens": 10394554.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.385644626617432,
|
|
"epoch": 0.4425253126861227,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988121505762706,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.1813192620873451,
|
|
"num_tokens": 10408803.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.433049821853638,
|
|
"epoch": 0.44312090530077425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988077736694693,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.17627055197954178,
|
|
"num_tokens": 10421577.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.406940555572509,
|
|
"epoch": 0.44371649791542583,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988033887350471,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.17448823451995848,
|
|
"num_tokens": 10435117.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.4828883647918705,
|
|
"epoch": 0.4443120905300774,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987989957731611,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.1733681872487068,
|
|
"num_tokens": 10448762.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.406545734405517,
|
|
"epoch": 0.444907683144729,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987945947839691,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.17133970111608504,
|
|
"num_tokens": 10462722.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.471333360671997,
|
|
"epoch": 0.4455032757593806,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498790185767629,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.1732810392975807,
|
|
"num_tokens": 10477834.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.389318656921387,
|
|
"epoch": 0.4460988683740322,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987857687242986,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.1818789780139923,
|
|
"num_tokens": 10490807.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.3262608528137205,
|
|
"epoch": 0.44669446098868376,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987813436541366,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.18469011336565017,
|
|
"num_tokens": 10505064.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.360294532775879,
|
|
"epoch": 0.4472900536033353,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004987769105573016,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.183121694624424,
|
|
"num_tokens": 10517567.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.517618465423584,
|
|
"epoch": 0.4478856462179869,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004987724694339526,
|
|
"loss": 5.3172,
|
|
"mean_token_accuracy": 0.1762111082673073,
|
|
"num_tokens": 10533697.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.3861993789672855,
|
|
"epoch": 0.44848123883263846,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987680202842491,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.1786264106631279,
|
|
"num_tokens": 10547533.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.376552867889404,
|
|
"epoch": 0.44907683144729005,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004987635631083505,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.1777271956205368,
|
|
"num_tokens": 10562193.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.372302389144897,
|
|
"epoch": 0.44967242406194163,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987590979064167,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.18318057358264922,
|
|
"num_tokens": 10575202.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.469649791717529,
|
|
"epoch": 0.4502680166765932,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004987546246786078,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.17711444050073624,
|
|
"num_tokens": 10589064.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.476633310317993,
|
|
"epoch": 0.4508636092912448,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987501434250844,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.16773197799921036,
|
|
"num_tokens": 10602837.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.409980726242066,
|
|
"epoch": 0.4514592019058964,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498745654146007,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.17838809937238692,
|
|
"num_tokens": 10618200.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.402648162841797,
|
|
"epoch": 0.4520547945205479,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000498741156841537,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.1775661364197731,
|
|
"num_tokens": 10631804.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.450578212738037,
|
|
"epoch": 0.4526503871351995,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004987366515118353,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.1735926926136017,
|
|
"num_tokens": 10647066.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.3924126625061035,
|
|
"epoch": 0.4532459797498511,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004987321381570638,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.17805004715919495,
|
|
"num_tokens": 10661436.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.439834356307983,
|
|
"epoch": 0.4538415723645027,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987276167773842,
|
|
"loss": 5.2934,
|
|
"mean_token_accuracy": 0.17254049926996232,
|
|
"num_tokens": 10675299.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.331587505340576,
|
|
"epoch": 0.45443716497915426,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004987230873729588,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.18543247133493423,
|
|
"num_tokens": 10689073.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.310808563232422,
|
|
"epoch": 0.45503275759380585,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049871854994395,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.18927500993013383,
|
|
"num_tokens": 10703017.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.510147285461426,
|
|
"epoch": 0.45562835020845743,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004987140044905205,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.17074571251869203,
|
|
"num_tokens": 10718151.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.4032470226287845,
|
|
"epoch": 0.456223942823109,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987094510128335,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.18504303991794585,
|
|
"num_tokens": 10731299.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.340116786956787,
|
|
"epoch": 0.45681953543776055,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987048895110522,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.17852347046136857,
|
|
"num_tokens": 10745152.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.321061706542968,
|
|
"epoch": 0.45741512805241213,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004987003199853401,
|
|
"loss": 5.1711,
|
|
"mean_token_accuracy": 0.1791461393237114,
|
|
"num_tokens": 10758557.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.434852409362793,
|
|
"epoch": 0.4580107206670637,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004986957424358613,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.17962770760059357,
|
|
"num_tokens": 10773647.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.408813190460205,
|
|
"epoch": 0.4586063132817153,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049869115686278,
|
|
"loss": 5.2314,
|
|
"mean_token_accuracy": 0.18089141547679902,
|
|
"num_tokens": 10786973.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.457066488265991,
|
|
"epoch": 0.4592019058963669,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004986865632662606,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.17332253456115723,
|
|
"num_tokens": 10800521.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.422528409957886,
|
|
"epoch": 0.4597974985110185,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986819616464678,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.181814606487751,
|
|
"num_tokens": 10814934.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.399583959579468,
|
|
"epoch": 0.46039309112567006,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004986773520035667,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.18810149431228637,
|
|
"num_tokens": 10830156.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.361807823181152,
|
|
"epoch": 0.46098868374032165,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004986727343377227,
|
|
"loss": 5.1607,
|
|
"mean_token_accuracy": 0.18367910534143447,
|
|
"num_tokens": 10844354.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.3933305740356445,
|
|
"epoch": 0.4615842763549732,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986681086491014,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.18292448669672012,
|
|
"num_tokens": 10855978.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.37632040977478,
|
|
"epoch": 0.46217986896962476,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986634749378686,
|
|
"loss": 5.0983,
|
|
"mean_token_accuracy": 0.1917484551668167,
|
|
"num_tokens": 10869395.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.326293659210205,
|
|
"epoch": 0.46277546158427635,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004986588332041908,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.18216816186904908,
|
|
"num_tokens": 10884817.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.371928930282593,
|
|
"epoch": 0.46337105419892793,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004986541834482342,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.18720285147428511,
|
|
"num_tokens": 10898435.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.342796754837036,
|
|
"epoch": 0.4639666468135795,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004986495256701657,
|
|
"loss": 5.2196,
|
|
"mean_token_accuracy": 0.17733437120914458,
|
|
"num_tokens": 10911777.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.416338014602661,
|
|
"epoch": 0.4645622394282311,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004986448598701523,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.18013208210468293,
|
|
"num_tokens": 10925025.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.366250228881836,
|
|
"epoch": 0.4651578320428827,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004986401860483615,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.18250798135995866,
|
|
"num_tokens": 10940019.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.43860969543457,
|
|
"epoch": 0.4657534246575342,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004986355042049608,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.17277711629867554,
|
|
"num_tokens": 10954702.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.377546691894532,
|
|
"epoch": 0.4663490172721858,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004986308143401181,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.1878010779619217,
|
|
"num_tokens": 10970231.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.394086408615112,
|
|
"epoch": 0.4669446098868374,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004986261164540018,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.17613804936408997,
|
|
"num_tokens": 10986561.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.428871011734008,
|
|
"epoch": 0.467540202501489,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004986214105467801,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.18019791692495346,
|
|
"num_tokens": 11000246.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.331533193588257,
|
|
"epoch": 0.46813579511614056,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004986166966186223,
|
|
"loss": 5.0457,
|
|
"mean_token_accuracy": 0.1948564752936363,
|
|
"num_tokens": 11012590.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.266906261444092,
|
|
"epoch": 0.46873138773079215,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004986119746696969,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.18875349164009095,
|
|
"num_tokens": 11025620.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.310734844207763,
|
|
"epoch": 0.46932698034544373,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004986072447001736,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.1885087177157402,
|
|
"num_tokens": 11038352.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.331786203384399,
|
|
"epoch": 0.4699225729600953,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986025067102221,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.19463525116443633,
|
|
"num_tokens": 11051226.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.4130147933959964,
|
|
"epoch": 0.47051816557474685,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004985977607000121,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.18284327983856202,
|
|
"num_tokens": 11065910.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.420770120620728,
|
|
"epoch": 0.47111375818939843,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985930066697141,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.18784887790679933,
|
|
"num_tokens": 11078804.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.364886808395386,
|
|
"epoch": 0.47170935080405,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004985882446194984,
|
|
"loss": 5.1458,
|
|
"mean_token_accuracy": 0.19021952003240586,
|
|
"num_tokens": 11090903.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.432231760025024,
|
|
"epoch": 0.4723049434187016,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000498583474549536,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.17478130906820297,
|
|
"num_tokens": 11106914.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.420093584060669,
|
|
"epoch": 0.4729005360333532,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985786964599978,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.18365588784217834,
|
|
"num_tokens": 11121471.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.304426050186157,
|
|
"epoch": 0.4734961286480048,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985739103510553,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.18712460696697236,
|
|
"num_tokens": 11135553.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.394079256057739,
|
|
"epoch": 0.47409172126265636,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985691162228802,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.18243786990642546,
|
|
"num_tokens": 11149335.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.423213386535645,
|
|
"epoch": 0.47468731387730795,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985643140756442,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.17831269204616546,
|
|
"num_tokens": 11161589.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.368987321853638,
|
|
"epoch": 0.4752829064919595,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.00049855950390952,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.1739825874567032,
|
|
"num_tokens": 11175094.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.3500786304473875,
|
|
"epoch": 0.47587849910661106,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004985546857246797,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.18300384730100633,
|
|
"num_tokens": 11191452.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.331335973739624,
|
|
"epoch": 0.47647409172126265,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985498595212964,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.18484076261520385,
|
|
"num_tokens": 11203831.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.402827215194702,
|
|
"epoch": 0.47706968433591423,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004985450252995431,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.17342661917209626,
|
|
"num_tokens": 11218022.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.377013206481934,
|
|
"epoch": 0.4776652769505658,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004985401830595932,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.17944857925176622,
|
|
"num_tokens": 11229993.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.443713617324829,
|
|
"epoch": 0.4782608695652174,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985353328016204,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.1754394769668579,
|
|
"num_tokens": 11243089.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.444408416748047,
|
|
"epoch": 0.478856462179869,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004985304745257986,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.17147151678800582,
|
|
"num_tokens": 11260349.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.401764726638794,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004985256082323022,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.18407257348299028,
|
|
"num_tokens": 11275875.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.424989700317383,
|
|
"epoch": 0.4800476474091721,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985207339213057,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.18253789991140365,
|
|
"num_tokens": 11289611.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.379727458953857,
|
|
"epoch": 0.4806432400238237,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004985158515929837,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.177983558177948,
|
|
"num_tokens": 11303917.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.368940591812134,
|
|
"epoch": 0.4812388326384753,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004985109612475116,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.18253531455993652,
|
|
"num_tokens": 11317400.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.367254209518433,
|
|
"epoch": 0.48183442525312686,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985060628850648,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.1823686182498932,
|
|
"num_tokens": 11330771.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.408759593963623,
|
|
"epoch": 0.48243001786777845,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004985011565058189,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.18497083336114883,
|
|
"num_tokens": 11344430.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.483620691299438,
|
|
"epoch": 0.48302561048243003,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004984962421099498,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.1729663148522377,
|
|
"num_tokens": 11358940.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.334818410873413,
|
|
"epoch": 0.4836212030970816,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000498491319697634,
|
|
"loss": 5.1855,
|
|
"mean_token_accuracy": 0.18312254995107652,
|
|
"num_tokens": 11371772.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.387055587768555,
|
|
"epoch": 0.48421679571173315,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498486389269048,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.17532442808151244,
|
|
"num_tokens": 11383976.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.414940881729126,
|
|
"epoch": 0.48481238832638474,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984814508243685,
|
|
"loss": 5.2065,
|
|
"mean_token_accuracy": 0.17781192064285278,
|
|
"num_tokens": 11398659.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.515937662124633,
|
|
"epoch": 0.4854079809410363,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004984765043637727,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.17402607202529907,
|
|
"num_tokens": 11413083.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.359595489501953,
|
|
"epoch": 0.4860035735556879,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000498471549887438,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.18464861810207367,
|
|
"num_tokens": 11426408.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.402296161651611,
|
|
"epoch": 0.4865991661703395,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004984665873955422,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.1712955966591835,
|
|
"num_tokens": 11440609.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.3476975440979,
|
|
"epoch": 0.4871947587849911,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004984616168882632,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.18086556494235992,
|
|
"num_tokens": 11454795.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.393082523345948,
|
|
"epoch": 0.48779035139964266,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984566383657794,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.1818688228726387,
|
|
"num_tokens": 11468695.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.334658479690551,
|
|
"epoch": 0.48838594401429425,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004984516518282692,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.18530638217926027,
|
|
"num_tokens": 11483601.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.491518497467041,
|
|
"epoch": 0.4889815366289458,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004984466572759117,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.17401891052722931,
|
|
"num_tokens": 11497860.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.3319940090179445,
|
|
"epoch": 0.48957712924359736,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004984416547088858,
|
|
"loss": 5.0456,
|
|
"mean_token_accuracy": 0.18910971134901047,
|
|
"num_tokens": 11512582.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.273644924163818,
|
|
"epoch": 0.49017272185824895,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004984366441273711,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.1824891299009323,
|
|
"num_tokens": 11525480.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.331992197036743,
|
|
"epoch": 0.49076831447290054,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004984316255315472,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.1852354273200035,
|
|
"num_tokens": 11540465.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.343194818496704,
|
|
"epoch": 0.4913639070875521,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004984265989215942,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.1740109443664551,
|
|
"num_tokens": 11555622.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.365783548355102,
|
|
"epoch": 0.4919594997022037,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004984215642976923,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.18323372453451156,
|
|
"num_tokens": 11569547.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.354334735870362,
|
|
"epoch": 0.4925550923168553,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984165216600224,
|
|
"loss": 5.1192,
|
|
"mean_token_accuracy": 0.18380082100629808,
|
|
"num_tokens": 11583464.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.326048707962036,
|
|
"epoch": 0.4931506849315068,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004984114710087648,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.1819705381989479,
|
|
"num_tokens": 11597639.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.384754037857055,
|
|
"epoch": 0.4937462775461584,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984064123441011,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.17815957367420196,
|
|
"num_tokens": 11610645.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.401113748550415,
|
|
"epoch": 0.49434187016081,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984013456662127,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.17818289399147033,
|
|
"num_tokens": 11624802.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.427695322036743,
|
|
"epoch": 0.4949374627754616,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004983962709752812,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.18149085938930512,
|
|
"num_tokens": 11638538.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.411260271072388,
|
|
"epoch": 0.49553305539011316,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983911882714886,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.1772036150097847,
|
|
"num_tokens": 11651639.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.382980918884277,
|
|
"epoch": 0.49612864800476475,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983860975550174,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.17371416836977005,
|
|
"num_tokens": 11668784.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.41145601272583,
|
|
"epoch": 0.49672424061941634,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004983809988260501,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.18291076570749282,
|
|
"num_tokens": 11682737.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.279611301422119,
|
|
"epoch": 0.4973198332340679,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983758920847696,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.18731954097747802,
|
|
"num_tokens": 11697666.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.40027174949646,
|
|
"epoch": 0.49791542584871945,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004983707773313589,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.17676257342100143,
|
|
"num_tokens": 11712747.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.382396697998047,
|
|
"epoch": 0.49851101846337104,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004983656545660016,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.17878617644309996,
|
|
"num_tokens": 11727233.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.371932077407837,
|
|
"epoch": 0.4991066110780226,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004983605237888815,
|
|
"loss": 5.265,
|
|
"mean_token_accuracy": 0.17287526577711104,
|
|
"num_tokens": 11743677.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.4083061695098875,
|
|
"epoch": 0.4997022036926742,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983553850001826,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.18976587653160096,
|
|
"num_tokens": 11756362.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.228198432922364,
|
|
"epoch": 0.5002977963073257,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983502382000892,
|
|
"loss": 5.1063,
|
|
"mean_token_accuracy": 0.18061042875051497,
|
|
"num_tokens": 11769955.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.255529689788818,
|
|
"epoch": 0.5008933889219773,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004983450833887859,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.19134392440319062,
|
|
"num_tokens": 11783617.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.417185735702515,
|
|
"epoch": 0.5014889815366289,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004983399205664575,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.17644449174404145,
|
|
"num_tokens": 11797408.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.450252199172974,
|
|
"epoch": 0.5020845741512805,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004983347497332894,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.16968824416399003,
|
|
"num_tokens": 11810058.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.324225902557373,
|
|
"epoch": 0.5026801667659321,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983295708894668,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.1793075233697891,
|
|
"num_tokens": 11822921.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.356392240524292,
|
|
"epoch": 0.5032757593805837,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004983243840351757,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.18140227496623992,
|
|
"num_tokens": 11837189.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.407381677627564,
|
|
"epoch": 0.5038713519952353,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983191891706021,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.18710006326436995,
|
|
"num_tokens": 11851579.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.273737382888794,
|
|
"epoch": 0.5044669446098868,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004983139862959322,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.1863243132829666,
|
|
"num_tokens": 11867013.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.247968244552612,
|
|
"epoch": 0.5050625372245384,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983087754113527,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.19239823520183563,
|
|
"num_tokens": 11879566.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.36608738899231,
|
|
"epoch": 0.50565812983919,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004983035565170505,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.18535499274730682,
|
|
"num_tokens": 11893103.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.336899375915527,
|
|
"epoch": 0.5062537224538416,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982983296132128,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.1883890300989151,
|
|
"num_tokens": 11907396.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.317756032943725,
|
|
"epoch": 0.5068493150684932,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004982930947000271,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.18940700888633727,
|
|
"num_tokens": 11921674.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.38133659362793,
|
|
"epoch": 0.5074449076831448,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004982878517776812,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.18168587237596512,
|
|
"num_tokens": 11933739.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.218308448791504,
|
|
"epoch": 0.5080405002977963,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000498282600846363,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.19236501008272172,
|
|
"num_tokens": 11946686.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.3818175315856935,
|
|
"epoch": 0.5086360929124479,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000498277341906261,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.18358779102563857,
|
|
"num_tokens": 11962112.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.321989727020264,
|
|
"epoch": 0.5092316855270994,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004982720749575637,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.186101932823658,
|
|
"num_tokens": 11976094.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.334202766418457,
|
|
"epoch": 0.509827278141751,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982668000004602,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.17744266092777253,
|
|
"num_tokens": 11991969.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.421050214767456,
|
|
"epoch": 0.5104228707564026,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004982615170351395,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.1779862806200981,
|
|
"num_tokens": 12007588.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.292688941955566,
|
|
"epoch": 0.5110184633710542,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982562260617912,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.18632632941007615,
|
|
"num_tokens": 12021658.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.3696043491363525,
|
|
"epoch": 0.5116140559857058,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004982509270806052,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.17920160740613938,
|
|
"num_tokens": 12035216.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.366880273818969,
|
|
"epoch": 0.5122096486003573,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982456200917712,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.18781054466962815,
|
|
"num_tokens": 12047435.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.43516058921814,
|
|
"epoch": 0.5128052412150089,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00049824030509548,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.17456135600805284,
|
|
"num_tokens": 12060314.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.4427807331085205,
|
|
"epoch": 0.5134008338296605,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000498234982091922,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.17351605147123336,
|
|
"num_tokens": 12076829.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.342952823638916,
|
|
"epoch": 0.5139964264443121,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004982296510812879,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.18961286991834642,
|
|
"num_tokens": 12090008.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.334354257583618,
|
|
"epoch": 0.5145920190589637,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004982243120637694,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.1797313079237938,
|
|
"num_tokens": 12103163.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.441323900222779,
|
|
"epoch": 0.5151876116736153,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004982189650395577,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.1782443955540657,
|
|
"num_tokens": 12117398.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.315100240707397,
|
|
"epoch": 0.5157832042882668,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004982136100088447,
|
|
"loss": 5.1389,
|
|
"mean_token_accuracy": 0.1855406641960144,
|
|
"num_tokens": 12132649.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.306979608535767,
|
|
"epoch": 0.5163787969029184,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004982082469718224,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.1825730711221695,
|
|
"num_tokens": 12146385.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.274682950973511,
|
|
"epoch": 0.51697438951757,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982028759286831,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.19284637421369552,
|
|
"num_tokens": 12159928.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.261528635025025,
|
|
"epoch": 0.5175699821322216,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981974968796197,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.18565332591533662,
|
|
"num_tokens": 12174624.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.308650350570678,
|
|
"epoch": 0.5181655747468732,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004981921098248249,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.19029283076524733,
|
|
"num_tokens": 12187383.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.368241548538208,
|
|
"epoch": 0.5187611673615247,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498186714764492,
|
|
"loss": 5.1671,
|
|
"mean_token_accuracy": 0.17929755598306657,
|
|
"num_tokens": 12200381.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.406327629089356,
|
|
"epoch": 0.5193567599761763,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004981813116988145,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.1789672315120697,
|
|
"num_tokens": 12216497.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.309513139724731,
|
|
"epoch": 0.5199523525908278,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981759006279864,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.1865038126707077,
|
|
"num_tokens": 12230368.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.3643265724182125,
|
|
"epoch": 0.5205479452054794,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981704815522014,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.17929701060056685,
|
|
"num_tokens": 12246492.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.363251352310181,
|
|
"epoch": 0.521143537820131,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004981650544716542,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.18221537619829178,
|
|
"num_tokens": 12260486.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.290689611434937,
|
|
"epoch": 0.5217391304347826,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981596193865393,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.1854724481701851,
|
|
"num_tokens": 12275001.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.286444282531738,
|
|
"epoch": 0.5223347230494342,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004981541762970517,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.18841983526945114,
|
|
"num_tokens": 12289690.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.306200170516968,
|
|
"epoch": 0.5229303156640858,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981487252033866,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.18047735393047332,
|
|
"num_tokens": 12304098.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.335263347625732,
|
|
"epoch": 0.5235259082787374,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004981432661057396,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.18927100896835328,
|
|
"num_tokens": 12318583.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.377587938308716,
|
|
"epoch": 0.5241215008933889,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004981377990043064,
|
|
"loss": 5.1386,
|
|
"mean_token_accuracy": 0.1801874965429306,
|
|
"num_tokens": 12332239.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.279301881790161,
|
|
"epoch": 0.5247170935080405,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004981323238992831,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.18113580644130706,
|
|
"num_tokens": 12344730.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.363180828094483,
|
|
"epoch": 0.5253126861226921,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004981268407908662,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.18083513528108597,
|
|
"num_tokens": 12358661.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.350935792922973,
|
|
"epoch": 0.5259082787373437,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981213496792523,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.18657889664173127,
|
|
"num_tokens": 12372876.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.409125471115113,
|
|
"epoch": 0.5265038713519953,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004981158505646383,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.17748216688632965,
|
|
"num_tokens": 12386960.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.2739006042480465,
|
|
"epoch": 0.5270994639666469,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004981103434472216,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.19526512920856476,
|
|
"num_tokens": 12400497.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.407064628601074,
|
|
"epoch": 0.5276950565812983,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981048283271997,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.1837845429778099,
|
|
"num_tokens": 12415013.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.376692056655884,
|
|
"epoch": 0.5282906491959499,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004980993052047701,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.1846063882112503,
|
|
"num_tokens": 12427915.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.3180173397064205,
|
|
"epoch": 0.5288862418106015,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980937740801313,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.183672171831131,
|
|
"num_tokens": 12440136.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.306796073913574,
|
|
"epoch": 0.5294818344252531,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004980882349534816,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.18244660794734954,
|
|
"num_tokens": 12454190.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.463627767562866,
|
|
"epoch": 0.5300774270399047,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004980826878250195,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.17683406919240952,
|
|
"num_tokens": 12470069.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.3316303253173825,
|
|
"epoch": 0.5306730196545563,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004980771326949442,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.17865769416093827,
|
|
"num_tokens": 12485349.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.359301424026489,
|
|
"epoch": 0.5312686122692079,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004980715695634549,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.1834998235106468,
|
|
"num_tokens": 12500690.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.3912193775177,
|
|
"epoch": 0.5318642048838594,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004980659984307511,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.18115987703204156,
|
|
"num_tokens": 12512619.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.43045334815979,
|
|
"epoch": 0.532459797498511,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004980604192970325,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.17694442868232726,
|
|
"num_tokens": 12527193.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.325862789154053,
|
|
"epoch": 0.5330553901131626,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004980548321624993,
|
|
"loss": 5.1922,
|
|
"mean_token_accuracy": 0.1832765594124794,
|
|
"num_tokens": 12540127.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.325676584243775,
|
|
"epoch": 0.5336509827278142,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000498049237027352,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.18478801995515823,
|
|
"num_tokens": 12555818.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.341642713546753,
|
|
"epoch": 0.5342465753424658,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980436338917914,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.18077556937932968,
|
|
"num_tokens": 12568337.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.315216779708862,
|
|
"epoch": 0.5348421679571174,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498038022756018,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.18242402970790864,
|
|
"num_tokens": 12581368.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.3535552501678465,
|
|
"epoch": 0.535437760571769,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004980324036202335,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.18351043313741683,
|
|
"num_tokens": 12595738.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.283936214447022,
|
|
"epoch": 0.5360333531864205,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980267764846393,
|
|
"loss": 5.0846,
|
|
"mean_token_accuracy": 0.1905273526906967,
|
|
"num_tokens": 12609736.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.267637300491333,
|
|
"epoch": 0.5366289458010721,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004980211413494373,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.183333058655262,
|
|
"num_tokens": 12624101.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.236968851089477,
|
|
"epoch": 0.5372245384157236,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004980154982148296,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.19253573715686798,
|
|
"num_tokens": 12639126.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.323569059371948,
|
|
"epoch": 0.5378201310303752,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004980098470810185,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.18165246695280074,
|
|
"num_tokens": 12652532.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.349842882156372,
|
|
"epoch": 0.5384157236450268,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980041879482068,
|
|
"loss": 5.1726,
|
|
"mean_token_accuracy": 0.1902925729751587,
|
|
"num_tokens": 12666270.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.295321464538574,
|
|
"epoch": 0.5390113162596784,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004979985208165975,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.1878521516919136,
|
|
"num_tokens": 12682393.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.372230148315429,
|
|
"epoch": 0.5396069088743299,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004979928456863937,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.18520011156797409,
|
|
"num_tokens": 12696685.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.217958593368531,
|
|
"epoch": 0.5402025014889815,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004979871625577991,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.19265486299991608,
|
|
"num_tokens": 12711091.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.317847633361817,
|
|
"epoch": 0.5407980941036331,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979814714310177,
|
|
"loss": 5.1207,
|
|
"mean_token_accuracy": 0.1897505909204483,
|
|
"num_tokens": 12725041.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.351825428009033,
|
|
"epoch": 0.5413936867182847,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979757723062533,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.18284923881292342,
|
|
"num_tokens": 12738318.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.288203430175781,
|
|
"epoch": 0.5419892793329363,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979700651837107,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.1857344388961792,
|
|
"num_tokens": 12750695.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.274901437759399,
|
|
"epoch": 0.5425848719475879,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004979643500635942,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.18815772086381913,
|
|
"num_tokens": 12764779.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.340201425552368,
|
|
"epoch": 0.5431804645622395,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979586269461089,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.17946089059114456,
|
|
"num_tokens": 12779197.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.322599029541015,
|
|
"epoch": 0.543776057176891,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979528958314604,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.18912597000598907,
|
|
"num_tokens": 12791140.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.254619216918945,
|
|
"epoch": 0.5443716497915426,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004979471567198539,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.19738948941230774,
|
|
"num_tokens": 12806382.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.309173154830932,
|
|
"epoch": 0.5449672424061942,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004979414096114953,
|
|
"loss": 5.0657,
|
|
"mean_token_accuracy": 0.19092788249254228,
|
|
"num_tokens": 12819095.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.191449928283691,
|
|
"epoch": 0.5455628350208458,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497935654506591,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.1970282480120659,
|
|
"num_tokens": 12831562.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.396162366867065,
|
|
"epoch": 0.5461584276354973,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000497929891405347,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.17817889600992204,
|
|
"num_tokens": 12845535.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.240388965606689,
|
|
"epoch": 0.5467540202501489,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979241203079705,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.19041113704442977,
|
|
"num_tokens": 12859067.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.341919183731079,
|
|
"epoch": 0.5473496128648004,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979183412146681,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.19000178277492524,
|
|
"num_tokens": 12872712.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.3105340003967285,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004979125541256474,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.18238989412784576,
|
|
"num_tokens": 12886701.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.300245380401611,
|
|
"epoch": 0.5485407980941036,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979067590411157,
|
|
"loss": 5.1038,
|
|
"mean_token_accuracy": 0.1909145936369896,
|
|
"num_tokens": 12900041.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.292470169067383,
|
|
"epoch": 0.5491363907087552,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000497900955961281,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.19345691055059433,
|
|
"num_tokens": 12912454.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.398757410049439,
|
|
"epoch": 0.5497319833234068,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004978951448863514,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.18304414600133895,
|
|
"num_tokens": 12926373.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.363936805725098,
|
|
"epoch": 0.5503275759380584,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004978893258165354,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.1858728438615799,
|
|
"num_tokens": 12939837.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.343402624130249,
|
|
"epoch": 0.55092316855271,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004978834987520417,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.18721891194581985,
|
|
"num_tokens": 12952904.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.362418746948242,
|
|
"epoch": 0.5515187611673615,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004978776636930792,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.17951781302690506,
|
|
"num_tokens": 12966896.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.3260987281799315,
|
|
"epoch": 0.5521143537820131,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004978718206398574,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.18791312277317046,
|
|
"num_tokens": 12980841.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.257918167114258,
|
|
"epoch": 0.5527099463966647,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978659695925856,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.1898777574300766,
|
|
"num_tokens": 12994506.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.3139807224273685,
|
|
"epoch": 0.5533055390113163,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004978601105514739,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.18538330644369125,
|
|
"num_tokens": 13008817.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.323249340057373,
|
|
"epoch": 0.5539011316259679,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004978542435167324,
|
|
"loss": 5.1335,
|
|
"mean_token_accuracy": 0.18302487283945085,
|
|
"num_tokens": 13024227.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.274266052246094,
|
|
"epoch": 0.5544967242406195,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004978483684885716,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.19358408749103545,
|
|
"num_tokens": 13037448.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.213516473770142,
|
|
"epoch": 0.5550923168552709,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004978424854672021,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.19025247246026994,
|
|
"num_tokens": 13050582.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.352503919601441,
|
|
"epoch": 0.5556879094699225,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004978365944528349,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.18656214624643325,
|
|
"num_tokens": 13063059.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.40325140953064,
|
|
"epoch": 0.5562835020845741,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978306954456814,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.17506725639104842,
|
|
"num_tokens": 13077193.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.320083713531494,
|
|
"epoch": 0.5568790946992257,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004978247884459532,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.17727275043725968,
|
|
"num_tokens": 13091462.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.274306726455689,
|
|
"epoch": 0.5574746873138773,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004978188734538621,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.18309739977121353,
|
|
"num_tokens": 13107406.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.328941059112549,
|
|
"epoch": 0.5580702799285289,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004978129504696203,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.18748715072870253,
|
|
"num_tokens": 13123623.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.251247930526733,
|
|
"epoch": 0.5586658725431805,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004978070194934402,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.18562707751989366,
|
|
"num_tokens": 13138644.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.318075704574585,
|
|
"epoch": 0.559261465157832,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004978010805255347,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.17561105340719224,
|
|
"num_tokens": 13152485.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.349049663543701,
|
|
"epoch": 0.5598570577724836,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004977951335661165,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.19345757663249968,
|
|
"num_tokens": 13165766.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.2103844165802,
|
|
"epoch": 0.5604526503871352,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977891786153992,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.17944135665893554,
|
|
"num_tokens": 13180298.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.368817710876465,
|
|
"epoch": 0.5610482430017868,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004977832156735963,
|
|
"loss": 5.2114,
|
|
"mean_token_accuracy": 0.1776925280690193,
|
|
"num_tokens": 13194925.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.355443143844605,
|
|
"epoch": 0.5616438356164384,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004977772447409217,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.18947134017944336,
|
|
"num_tokens": 13208486.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.282683181762695,
|
|
"epoch": 0.56223942823109,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004977712658175894,
|
|
"loss": 5.1205,
|
|
"mean_token_accuracy": 0.1868671163916588,
|
|
"num_tokens": 13222428.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.324584197998047,
|
|
"epoch": 0.5628350208457416,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004977652789038142,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.18026006817817689,
|
|
"num_tokens": 13237341.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.3339954853057865,
|
|
"epoch": 0.5634306134603931,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004977592839998105,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.18767637610435486,
|
|
"num_tokens": 13251085.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.354875707626343,
|
|
"epoch": 0.5640262060750447,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004977532811057936,
|
|
"loss": 5.1949,
|
|
"mean_token_accuracy": 0.18514059633016586,
|
|
"num_tokens": 13266660.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.2686361312866214,
|
|
"epoch": 0.5646217986896962,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004977472702219786,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.18778657615184785,
|
|
"num_tokens": 13280550.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.300787258148193,
|
|
"epoch": 0.5652173913043478,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004977412513485812,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.18928858041763305,
|
|
"num_tokens": 13292905.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.266883802413941,
|
|
"epoch": 0.5658129839189994,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977352244858172,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.19949344992637635,
|
|
"num_tokens": 13305271.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.359965848922729,
|
|
"epoch": 0.566408576533651,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004977291896339029,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.18041886985301972,
|
|
"num_tokens": 13319904.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.309332466125488,
|
|
"epoch": 0.5670041691483025,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004977231467930546,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.19170868694782256,
|
|
"num_tokens": 13331799.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.349821329116821,
|
|
"epoch": 0.5675997617629541,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004977170959634893,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.19196423143148422,
|
|
"num_tokens": 13345269.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.247021245956421,
|
|
"epoch": 0.5681953543776057,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004977110371454239,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.18546835482120513,
|
|
"num_tokens": 13358555.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.3337883949279785,
|
|
"epoch": 0.5687909469922573,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977049703390755,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.18396190404891968,
|
|
"num_tokens": 13373444.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.358067464828491,
|
|
"epoch": 0.5693865396069089,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004976988955446622,
|
|
"loss": 5.1258,
|
|
"mean_token_accuracy": 0.18579309284687043,
|
|
"num_tokens": 13387530.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.301473951339721,
|
|
"epoch": 0.5699821322215605,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004976928127624013,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.1862201377749443,
|
|
"num_tokens": 13402718.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.3818285942077635,
|
|
"epoch": 0.570577724836212,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004976867219925116,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.18179702758789062,
|
|
"num_tokens": 13416076.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.250191974639892,
|
|
"epoch": 0.5711733174508636,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000497680623235211,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.19693999290466307,
|
|
"num_tokens": 13428286.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.27693543434143,
|
|
"epoch": 0.5717689100655152,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004976745164907185,
|
|
"loss": 5.1139,
|
|
"mean_token_accuracy": 0.18380515724420549,
|
|
"num_tokens": 13442801.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.391993284225464,
|
|
"epoch": 0.5723645026801668,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976684017592533,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.18104581236839296,
|
|
"num_tokens": 13457796.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.323946619033814,
|
|
"epoch": 0.5729600952948184,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976622790410345,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.18597734570503235,
|
|
"num_tokens": 13473291.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.204704236984253,
|
|
"epoch": 0.5735556879094699,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004976561483362818,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.18793633133172988,
|
|
"num_tokens": 13487275.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.2825428485870365,
|
|
"epoch": 0.5741512805241215,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000497650009645215,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.19531758427619933,
|
|
"num_tokens": 13500148.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.308289289474487,
|
|
"epoch": 0.574746873138773,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976438629680543,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.19100415259599685,
|
|
"num_tokens": 13514231.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.318165969848633,
|
|
"epoch": 0.5753424657534246,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004976377083050204,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.18271679878234864,
|
|
"num_tokens": 13528691.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.306242322921753,
|
|
"epoch": 0.5759380583680762,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004976315456563339,
|
|
"loss": 5.1347,
|
|
"mean_token_accuracy": 0.18551575839519502,
|
|
"num_tokens": 13542115.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.301770448684692,
|
|
"epoch": 0.5765336509827278,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976253750222157,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.1829224482178688,
|
|
"num_tokens": 13556269.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.343232870101929,
|
|
"epoch": 0.5771292435973794,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004976191964028874,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.1852123335003853,
|
|
"num_tokens": 13571853.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.3390281200408936,
|
|
"epoch": 0.577724836212031,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004976130097985703,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.18490727990865707,
|
|
"num_tokens": 13587631.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.318580245971679,
|
|
"epoch": 0.5783204288266826,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004976068152094867,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.19177399575710297,
|
|
"num_tokens": 13603140.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.204405355453491,
|
|
"epoch": 0.5789160214413341,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004976006126358584,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.19838816821575164,
|
|
"num_tokens": 13617606.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.357296276092529,
|
|
"epoch": 0.5795116140559857,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004975944020779082,
|
|
"loss": 5.1331,
|
|
"mean_token_accuracy": 0.18520898520946502,
|
|
"num_tokens": 13632244.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.309529113769531,
|
|
"epoch": 0.5801072066706373,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975881835358586,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.18462262749671937,
|
|
"num_tokens": 13646166.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.294286060333252,
|
|
"epoch": 0.5807027992852889,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004975819570099328,
|
|
"loss": 5.0987,
|
|
"mean_token_accuracy": 0.18599398732185363,
|
|
"num_tokens": 13661141.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.3408928394317625,
|
|
"epoch": 0.5812983918999405,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000497575722500354,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.18936541229486464,
|
|
"num_tokens": 13675007.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.3129129886627195,
|
|
"epoch": 0.5818939845145921,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000497569480007346,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.1885376289486885,
|
|
"num_tokens": 13690679.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.242873954772949,
|
|
"epoch": 0.5824895771292437,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004975632295311327,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.1896588459610939,
|
|
"num_tokens": 13705068.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.269522476196289,
|
|
"epoch": 0.5830851697438951,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004975569710719382,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.19121027886867523,
|
|
"num_tokens": 13719550.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.333636665344239,
|
|
"epoch": 0.5836807623585467,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975507046299869,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.1869287446141243,
|
|
"num_tokens": 13733516.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.417228651046753,
|
|
"epoch": 0.5842763549731983,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004975444302055038,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.18411969393491745,
|
|
"num_tokens": 13747242.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.219224071502685,
|
|
"epoch": 0.5848719475878499,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004975381477987136,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.18591572791337968,
|
|
"num_tokens": 13761434.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.3894013404846195,
|
|
"epoch": 0.5854675402025015,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004975318574098422,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.18624072819948195,
|
|
"num_tokens": 13773942.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.327998971939087,
|
|
"epoch": 0.586063132817153,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004975255590391147,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.19349586665630342,
|
|
"num_tokens": 13787217.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.302249526977539,
|
|
"epoch": 0.5866587254318046,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004975192526867572,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.19150582551956177,
|
|
"num_tokens": 13801444.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.344896459579468,
|
|
"epoch": 0.5872543180464562,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975129383529959,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.18853237181901933,
|
|
"num_tokens": 13814453.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.3083351135253904,
|
|
"epoch": 0.5878499106611078,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004975066160380573,
|
|
"loss": 5.0661,
|
|
"mean_token_accuracy": 0.18458928018808365,
|
|
"num_tokens": 13829620.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.220902061462402,
|
|
"epoch": 0.5884455032757594,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975002857421681,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.18334962278604508,
|
|
"num_tokens": 13842005.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.185434198379516,
|
|
"epoch": 0.589041095890411,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004974939474655554,
|
|
"loss": 4.9659,
|
|
"mean_token_accuracy": 0.19217298179864883,
|
|
"num_tokens": 13854299.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.237213563919068,
|
|
"epoch": 0.5896366885050626,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004974876012084468,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.19455666095018387,
|
|
"num_tokens": 13866294.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.286949968338012,
|
|
"epoch": 0.5902322811197142,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004974812469710694,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.18583744168281555,
|
|
"num_tokens": 13879820.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.244901895523071,
|
|
"epoch": 0.5908278737343657,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004974748847536516,
|
|
"loss": 5.0855,
|
|
"mean_token_accuracy": 0.17792990505695344,
|
|
"num_tokens": 13894664.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.331088590621948,
|
|
"epoch": 0.5914234663490173,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004974685145564213,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.18015981912612916,
|
|
"num_tokens": 13908706.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.280873966217041,
|
|
"epoch": 0.5920190589636688,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004974621363796071,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.19480266869068147,
|
|
"num_tokens": 13921402.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.244831800460815,
|
|
"epoch": 0.5926146515783204,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004974557502234378,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.1833819180727005,
|
|
"num_tokens": 13934731.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.280506706237793,
|
|
"epoch": 0.593210244192972,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004974493560881423,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.18667688667774202,
|
|
"num_tokens": 13947990.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.322307014465332,
|
|
"epoch": 0.5938058368076236,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004974429539739502,
|
|
"loss": 4.9994,
|
|
"mean_token_accuracy": 0.19545883387327195,
|
|
"num_tokens": 13961167.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.248807811737061,
|
|
"epoch": 0.5944014294222751,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004974365438810911,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.195140278339386,
|
|
"num_tokens": 13974136.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.217555189132691,
|
|
"epoch": 0.5949970220369267,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004974301258097948,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.18835571855306626,
|
|
"num_tokens": 13989229.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.366804361343384,
|
|
"epoch": 0.5955926146515783,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004974236997602915,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.17720674574375153,
|
|
"num_tokens": 14003136.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.3019743919372555,
|
|
"epoch": 0.5961882072662299,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004974172657328116,
|
|
"loss": 5.0866,
|
|
"mean_token_accuracy": 0.18821991980075836,
|
|
"num_tokens": 14017712.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.364273643493652,
|
|
"epoch": 0.5967837998808815,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000497410823727586,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.18556804805994034,
|
|
"num_tokens": 14032740.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.28114881515503,
|
|
"epoch": 0.5973793924955331,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000497404373744846,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.18723592758178711,
|
|
"num_tokens": 14048059.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.284004831314087,
|
|
"epoch": 0.5979749851101847,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004973979157848227,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.1942220449447632,
|
|
"num_tokens": 14062318.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.325515365600586,
|
|
"epoch": 0.5985705777248362,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004973914498477475,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.18517005294561387,
|
|
"num_tokens": 14076617.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.317840814590454,
|
|
"epoch": 0.5991661703394878,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004973849759338527,
|
|
"loss": 5.1475,
|
|
"mean_token_accuracy": 0.18557091653347016,
|
|
"num_tokens": 14092067.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.326718473434449,
|
|
"epoch": 0.5997617629541394,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004973784940433706,
|
|
"loss": 5.1056,
|
|
"mean_token_accuracy": 0.18405185490846634,
|
|
"num_tokens": 14106969.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.25502347946167,
|
|
"epoch": 0.600357355568791,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973720041765332,
|
|
"loss": 5.059,
|
|
"mean_token_accuracy": 0.18913086056709288,
|
|
"num_tokens": 14119877.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.29155535697937,
|
|
"epoch": 0.6009529481834425,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004973655063335736,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.18656927794218064,
|
|
"num_tokens": 14133831.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.266172075271607,
|
|
"epoch": 0.6015485407980941,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000497359000514725,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.1908604919910431,
|
|
"num_tokens": 14147482.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.202458667755127,
|
|
"epoch": 0.6021441334127456,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004973524867202205,
|
|
"loss": 5.0293,
|
|
"mean_token_accuracy": 0.18654340356588364,
|
|
"num_tokens": 14162276.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.254043626785278,
|
|
"epoch": 0.6027397260273972,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004973459649502939,
|
|
"loss": 5.0707,
|
|
"mean_token_accuracy": 0.18662265837192535,
|
|
"num_tokens": 14177129.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.302168226242065,
|
|
"epoch": 0.6033353186420488,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004973394352051789,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.1908659130334854,
|
|
"num_tokens": 14191104.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.2784045219421385,
|
|
"epoch": 0.6039309112567004,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049733289748511,
|
|
"loss": 5.0996,
|
|
"mean_token_accuracy": 0.18507454544305801,
|
|
"num_tokens": 14205703.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.178795957565308,
|
|
"epoch": 0.604526503871352,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004973263517903213,
|
|
"loss": 4.9013,
|
|
"mean_token_accuracy": 0.20626239776611327,
|
|
"num_tokens": 14219108.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.303779602050781,
|
|
"epoch": 0.6051220964860036,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973197981210481,
|
|
"loss": 5.1317,
|
|
"mean_token_accuracy": 0.1848259225487709,
|
|
"num_tokens": 14231677.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.20259838104248,
|
|
"epoch": 0.6057176891006552,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004973132364775252,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.1981998175382614,
|
|
"num_tokens": 14246844.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.3327240467071535,
|
|
"epoch": 0.6063132817153067,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973066668599879,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.18779212683439256,
|
|
"num_tokens": 14261879.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.359662628173828,
|
|
"epoch": 0.6069088743299583,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004973000892686719,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.18234526216983796,
|
|
"num_tokens": 14276884.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.198430299758911,
|
|
"epoch": 0.6075044669446099,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004972935037038131,
|
|
"loss": 5.0431,
|
|
"mean_token_accuracy": 0.19098564088344575,
|
|
"num_tokens": 14291997.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.271669673919678,
|
|
"epoch": 0.6081000595592615,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004972869101656478,
|
|
"loss": 4.9896,
|
|
"mean_token_accuracy": 0.196336230635643,
|
|
"num_tokens": 14304407.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.282280206680298,
|
|
"epoch": 0.6086956521739131,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004972803086544125,
|
|
"loss": 5.0766,
|
|
"mean_token_accuracy": 0.18773432523012162,
|
|
"num_tokens": 14317948.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.276966619491577,
|
|
"epoch": 0.6092912447885647,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004972736991703439,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.19231303483247758,
|
|
"num_tokens": 14330100.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.209065723419189,
|
|
"epoch": 0.6098868374032163,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004972670817136791,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.18684857785701753,
|
|
"num_tokens": 14343655.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.263560581207275,
|
|
"epoch": 0.6104824300178677,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004972604562846554,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.19189692735671998,
|
|
"num_tokens": 14357049.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.28076548576355,
|
|
"epoch": 0.6110780226325193,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004972538228835106,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.18721731901168823,
|
|
"num_tokens": 14371184.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.362889242172241,
|
|
"epoch": 0.6116736152471709,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004972471815104825,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.18689340800046922,
|
|
"num_tokens": 14385076.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.282217979431152,
|
|
"epoch": 0.6122692078618225,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004972405321658094,
|
|
"loss": 5.0626,
|
|
"mean_token_accuracy": 0.18430265486240388,
|
|
"num_tokens": 14400071.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.31106653213501,
|
|
"epoch": 0.6128648004764741,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004972338748497297,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.18941776901483537,
|
|
"num_tokens": 14414203.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.3473796367645265,
|
|
"epoch": 0.6134603930911257,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004972272095624822,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.1794777810573578,
|
|
"num_tokens": 14429325.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.255878448486328,
|
|
"epoch": 0.6140559857057772,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000497220536304306,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.1894165277481079,
|
|
"num_tokens": 14443432.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.315220737457276,
|
|
"epoch": 0.6146515783204288,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004972138550754405,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.1881655976176262,
|
|
"num_tokens": 14457251.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.270356750488281,
|
|
"epoch": 0.6152471709350804,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004972071658761254,
|
|
"loss": 5.05,
|
|
"mean_token_accuracy": 0.19277913123369217,
|
|
"num_tokens": 14472931.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.328121185302734,
|
|
"epoch": 0.615842763549732,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972004687066005,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.19259994029998778,
|
|
"num_tokens": 14484689.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.2825531482696535,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004971937635671061,
|
|
"loss": 5.0429,
|
|
"mean_token_accuracy": 0.18971439301967621,
|
|
"num_tokens": 14499522.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.271452188491821,
|
|
"epoch": 0.6170339487790352,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971870504578825,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.1883655458688736,
|
|
"num_tokens": 14513347.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.217121171951294,
|
|
"epoch": 0.6176295413936868,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004971803293791708,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.18621584326028823,
|
|
"num_tokens": 14526741.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.162420463562012,
|
|
"epoch": 0.6182251340083383,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004971736003312119,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.19757253378629686,
|
|
"num_tokens": 14540317.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.235009241104126,
|
|
"epoch": 0.6188207266229899,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004971668633142472,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.19080387204885482,
|
|
"num_tokens": 14553468.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.304305648803711,
|
|
"epoch": 0.6194163192376414,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004971601183285183,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.18930230438709258,
|
|
"num_tokens": 14566294.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.268048572540283,
|
|
"epoch": 0.620011911852293,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004971533653742672,
|
|
"loss": 5.0412,
|
|
"mean_token_accuracy": 0.19278932809829713,
|
|
"num_tokens": 14581603.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.226327657699585,
|
|
"epoch": 0.6206075044669446,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000497146604451736,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.19570356160402297,
|
|
"num_tokens": 14596957.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.209311532974243,
|
|
"epoch": 0.6212030970815962,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004971398355611674,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.19735753238201142,
|
|
"num_tokens": 14609228.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.258736610412598,
|
|
"epoch": 0.6217986896962477,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497133058702804,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.18860846906900405,
|
|
"num_tokens": 14621928.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.260164213180542,
|
|
"epoch": 0.6223942823108993,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000497126273876889,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.19348251074552536,
|
|
"num_tokens": 14634896.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.267403078079224,
|
|
"epoch": 0.6229898749255509,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004971194810836657,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.18580241054296492,
|
|
"num_tokens": 14648867.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.320101690292359,
|
|
"epoch": 0.6235854675402025,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004971126803233778,
|
|
"loss": 5.1236,
|
|
"mean_token_accuracy": 0.17945374846458434,
|
|
"num_tokens": 14664360.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.247040796279907,
|
|
"epoch": 0.6241810601548541,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004971058715962691,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.18712168633937837,
|
|
"num_tokens": 14678173.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.295566701889038,
|
|
"epoch": 0.6247766527695057,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000497099054902584,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.1858678475022316,
|
|
"num_tokens": 14690710.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.242764663696289,
|
|
"epoch": 0.6253722453841573,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004970922302425669,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.1859528675675392,
|
|
"num_tokens": 14705678.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.2264985084533695,
|
|
"epoch": 0.6259678379988088,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004970853976164624,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.19399054795503617,
|
|
"num_tokens": 14719357.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.255155181884765,
|
|
"epoch": 0.6265634306134604,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000497078557024516,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.1903844103217125,
|
|
"num_tokens": 14732176.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.264030456542969,
|
|
"epoch": 0.627159023228112,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970717084669728,
|
|
"loss": 4.9629,
|
|
"mean_token_accuracy": 0.19436786621809005,
|
|
"num_tokens": 14746789.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.230049324035645,
|
|
"epoch": 0.6277546158427636,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004970648519440785,
|
|
"loss": 5.0538,
|
|
"mean_token_accuracy": 0.18883288502693177,
|
|
"num_tokens": 14759233.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.287742280960083,
|
|
"epoch": 0.6283502084574152,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004970579874560789,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.18382622599601744,
|
|
"num_tokens": 14773187.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.381859397888183,
|
|
"epoch": 0.6289458010720667,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004970511150032205,
|
|
"loss": 5.1357,
|
|
"mean_token_accuracy": 0.1838845729827881,
|
|
"num_tokens": 14788501.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.209787178039551,
|
|
"epoch": 0.6295413936867182,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004970442345857495,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.18424489200115204,
|
|
"num_tokens": 14802945.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.359104967117309,
|
|
"epoch": 0.6301369863013698,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004970373462039128,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.1816278278827667,
|
|
"num_tokens": 14818572.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.356029891967774,
|
|
"epoch": 0.6307325789160214,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004970304498579576,
|
|
"loss": 5.0532,
|
|
"mean_token_accuracy": 0.1861602783203125,
|
|
"num_tokens": 14832962.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.2350891590118405,
|
|
"epoch": 0.631328171530673,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004970235455481312,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.19681889265775682,
|
|
"num_tokens": 14846181.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.208218765258789,
|
|
"epoch": 0.6319237641453246,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004970166332746811,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.19732060432434081,
|
|
"num_tokens": 14858859.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.226653528213501,
|
|
"epoch": 0.6325193567599762,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004970097130378554,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.19484451711177825,
|
|
"num_tokens": 14873858.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.239650583267212,
|
|
"epoch": 0.6331149493746278,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004970027848379023,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.1990181490778923,
|
|
"num_tokens": 14888287.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.221383476257325,
|
|
"epoch": 0.6337105419892793,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004969958486750702,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.1946862056851387,
|
|
"num_tokens": 14903261.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.241174030303955,
|
|
"epoch": 0.6343061346039309,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000496988904549608,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.19759255945682525,
|
|
"num_tokens": 14917788.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.301777267456055,
|
|
"epoch": 0.6349017272185825,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969819524617647,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.18964486867189406,
|
|
"num_tokens": 14930975.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.319721746444702,
|
|
"epoch": 0.6354973198332341,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004969749924117896,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.187764573097229,
|
|
"num_tokens": 14945904.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.223715496063233,
|
|
"epoch": 0.6360929124478857,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004969680243999325,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.19319533705711364,
|
|
"num_tokens": 14960885.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.194136905670166,
|
|
"epoch": 0.6366885050625373,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004969610484264433,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.19384798556566238,
|
|
"num_tokens": 14973061.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.282986307144165,
|
|
"epoch": 0.6372840976771889,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969540644915721,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.19514816850423813,
|
|
"num_tokens": 14985921.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.329117298126221,
|
|
"epoch": 0.6378796902918403,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969470725955695,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.1879531517624855,
|
|
"num_tokens": 15000008.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.255239820480346,
|
|
"epoch": 0.6384752829064919,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004969400727386864,
|
|
"loss": 5.1218,
|
|
"mean_token_accuracy": 0.18171454668045045,
|
|
"num_tokens": 15014175.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.254637622833252,
|
|
"epoch": 0.6390708755211435,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004969330649211737,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.18522126078605652,
|
|
"num_tokens": 15027872.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.387550020217896,
|
|
"epoch": 0.6396664681357951,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004969260491432826,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.18494511097669603,
|
|
"num_tokens": 15041295.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.241433763504029,
|
|
"epoch": 0.6402620607504467,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004969190254052651,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.19218669533729554,
|
|
"num_tokens": 15055756.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.262500762939453,
|
|
"epoch": 0.6408576533650983,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004969119937073731,
|
|
"loss": 5.0546,
|
|
"mean_token_accuracy": 0.1927003115415573,
|
|
"num_tokens": 15070375.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.198754072189331,
|
|
"epoch": 0.6414532459797498,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004969049540498585,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.1988879844546318,
|
|
"num_tokens": 15084580.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.1839128017425535,
|
|
"epoch": 0.6420488385944014,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004968979064329741,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.18755934834480287,
|
|
"num_tokens": 15097137.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.241489410400391,
|
|
"epoch": 0.642644431209053,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004968908508569725,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.19350459575653076,
|
|
"num_tokens": 15112375.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.301629686355591,
|
|
"epoch": 0.6432400238237046,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968837873221069,
|
|
"loss": 5.1714,
|
|
"mean_token_accuracy": 0.1879799708724022,
|
|
"num_tokens": 15126356.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.301209449768066,
|
|
"epoch": 0.6438356164383562,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004968767158286306,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.18719206899404525,
|
|
"num_tokens": 15140626.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.290619802474976,
|
|
"epoch": 0.6444312090530078,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968696363767972,
|
|
"loss": 5.1427,
|
|
"mean_token_accuracy": 0.1827332302927971,
|
|
"num_tokens": 15155131.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.278539085388184,
|
|
"epoch": 0.6450268016676594,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004968625489668607,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.18880775570869446,
|
|
"num_tokens": 15170488.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.278753137588501,
|
|
"epoch": 0.6456223942823109,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004968554535990754,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.1999405801296234,
|
|
"num_tokens": 15182905.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.286464738845825,
|
|
"epoch": 0.6462179868969625,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004968483502736956,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.1871281534433365,
|
|
"num_tokens": 15196341.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.256410455703735,
|
|
"epoch": 0.646813579511614,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004968412389909762,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.1897108554840088,
|
|
"num_tokens": 15208973.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.273350620269776,
|
|
"epoch": 0.6474091721262656,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004968341197511722,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.18364183604717255,
|
|
"num_tokens": 15225122.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.305637407302856,
|
|
"epoch": 0.6480047647409172,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004968269925545391,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.18446778506040573,
|
|
"num_tokens": 15236932.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.243228816986084,
|
|
"epoch": 0.6486003573555688,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004968198574013323,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.19088656306266785,
|
|
"num_tokens": 15249060.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.220152759552002,
|
|
"epoch": 0.6491959499702203,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004968127142918081,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.19013717621564866,
|
|
"num_tokens": 15263544.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.2159802436828615,
|
|
"epoch": 0.6497915425848719,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004968055632262223,
|
|
"loss": 4.9349,
|
|
"mean_token_accuracy": 0.1959513857960701,
|
|
"num_tokens": 15276294.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.268005228042602,
|
|
"epoch": 0.6503871351995235,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004967984042048317,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.19301596134901047,
|
|
"num_tokens": 15290352.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.272830152511597,
|
|
"epoch": 0.6509827278141751,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004967912372278928,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.18969148695468901,
|
|
"num_tokens": 15304607.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.282205295562744,
|
|
"epoch": 0.6515783204288267,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000496784062295663,
|
|
"loss": 5.0561,
|
|
"mean_token_accuracy": 0.18474604338407516,
|
|
"num_tokens": 15319846.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.286567640304566,
|
|
"epoch": 0.6521739130434783,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004967768794083994,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.1871288999915123,
|
|
"num_tokens": 15335668.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.233797836303711,
|
|
"epoch": 0.6527695056581299,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004967696885663597,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.18956888616085052,
|
|
"num_tokens": 15350839.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.212251806259156,
|
|
"epoch": 0.6533650982727814,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000496762489769802,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.19383188039064408,
|
|
"num_tokens": 15364289.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.188838911056519,
|
|
"epoch": 0.653960690887433,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967552830189842,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.19442096650600432,
|
|
"num_tokens": 15378042.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.3160505294799805,
|
|
"epoch": 0.6545562835020846,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967480683141651,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.18779717683792113,
|
|
"num_tokens": 15392128.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.297846412658691,
|
|
"epoch": 0.6551518761167362,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496740845655603,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.17973996996879577,
|
|
"num_tokens": 15406723.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.250408697128296,
|
|
"epoch": 0.6557474687313878,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004967336150435576,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.19129544496536255,
|
|
"num_tokens": 15421036.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.212464332580566,
|
|
"epoch": 0.6563430613460393,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004967263764782878,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.18914392292499543,
|
|
"num_tokens": 15434486.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.3145856857299805,
|
|
"epoch": 0.6569386539606908,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004967191299600535,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.18856205195188522,
|
|
"num_tokens": 15449378.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.328000545501709,
|
|
"epoch": 0.6575342465753424,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004967118754891144,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.19267208278179168,
|
|
"num_tokens": 15463983.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.267809057235718,
|
|
"epoch": 0.658129839189994,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004967046130657309,
|
|
"loss": 5.0437,
|
|
"mean_token_accuracy": 0.18885381668806075,
|
|
"num_tokens": 15478397.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.207084703445434,
|
|
"epoch": 0.6587254318046456,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004966973426901634,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.18576074242591858,
|
|
"num_tokens": 15491511.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.226274490356445,
|
|
"epoch": 0.6593210244192972,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966900643626726,
|
|
"loss": 4.944,
|
|
"mean_token_accuracy": 0.196894171833992,
|
|
"num_tokens": 15505103.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.279523324966431,
|
|
"epoch": 0.6599166170339488,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004966827780835197,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.18975903391838073,
|
|
"num_tokens": 15520216.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.181684255599976,
|
|
"epoch": 0.6605122096486004,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004966754838529659,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.19669175446033477,
|
|
"num_tokens": 15532879.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.256427955627442,
|
|
"epoch": 0.6611078022632519,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000496668181671273,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.19731294959783555,
|
|
"num_tokens": 15545600.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.25473837852478,
|
|
"epoch": 0.6617033948779035,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004966608715387029,
|
|
"loss": 5.0786,
|
|
"mean_token_accuracy": 0.18452006131410598,
|
|
"num_tokens": 15560910.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.34370985031128,
|
|
"epoch": 0.6622989874925551,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004966535534555175,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.18671540468931197,
|
|
"num_tokens": 15575041.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.218348121643066,
|
|
"epoch": 0.6628945801072067,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004966462274219797,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.19417762756347656,
|
|
"num_tokens": 15588399.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.179234790802002,
|
|
"epoch": 0.6634901727218583,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000496638893438352,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.20641662776470185,
|
|
"num_tokens": 15600010.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.294523906707764,
|
|
"epoch": 0.6640857653365099,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004966315515048977,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.19217442274093627,
|
|
"num_tokens": 15613703.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.306127309799194,
|
|
"epoch": 0.6646813579511615,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004966242016218799,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.18512095063924788,
|
|
"num_tokens": 15628198.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.272443056106567,
|
|
"epoch": 0.6652769505658129,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004966168437895624,
|
|
"loss": 5.0163,
|
|
"mean_token_accuracy": 0.1836185410618782,
|
|
"num_tokens": 15641410.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.172276830673217,
|
|
"epoch": 0.6658725431804645,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004966094780082089,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.19570461064577102,
|
|
"num_tokens": 15656052.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.242552042007446,
|
|
"epoch": 0.6664681357951161,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004966021042780837,
|
|
"loss": 5.0198,
|
|
"mean_token_accuracy": 0.19634895771741867,
|
|
"num_tokens": 15669319.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.241170120239258,
|
|
"epoch": 0.6670637284097677,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004965947225994516,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.1931735619902611,
|
|
"num_tokens": 15684951.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.249751329421997,
|
|
"epoch": 0.6676593210244193,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004965873329725769,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.18289056718349456,
|
|
"num_tokens": 15699352.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.2152252197265625,
|
|
"epoch": 0.6682549136390709,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004965799353977248,
|
|
"loss": 4.926,
|
|
"mean_token_accuracy": 0.19909475594758988,
|
|
"num_tokens": 15713183.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.280290269851685,
|
|
"epoch": 0.6688505062537224,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004965725298751608,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.1881798177957535,
|
|
"num_tokens": 15725985.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.2790521621704105,
|
|
"epoch": 0.669446098868374,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004965651164051504,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.1837506487965584,
|
|
"num_tokens": 15740146.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.226727676391602,
|
|
"epoch": 0.6700416914830256,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004965576949879594,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.19253317266702652,
|
|
"num_tokens": 15753590.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.23234748840332,
|
|
"epoch": 0.6706372840976772,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004965502656238543,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.19132742285728455,
|
|
"num_tokens": 15768018.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.226779365539551,
|
|
"epoch": 0.6712328767123288,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004965428283131013,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.1980260655283928,
|
|
"num_tokens": 15783112.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.276091146469116,
|
|
"epoch": 0.6718284693269804,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004965353830559671,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.19180409759283065,
|
|
"num_tokens": 15798730.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.215128469467163,
|
|
"epoch": 0.672424061941632,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004965279298527192,
|
|
"loss": 5.0364,
|
|
"mean_token_accuracy": 0.1981203407049179,
|
|
"num_tokens": 15812555.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.279513549804688,
|
|
"epoch": 0.6730196545562835,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004965204687036244,
|
|
"loss": 5.0632,
|
|
"mean_token_accuracy": 0.1966586321592331,
|
|
"num_tokens": 15824512.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.291729688644409,
|
|
"epoch": 0.6736152471709351,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004965129996089507,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.1806118220090866,
|
|
"num_tokens": 15839960.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.303473091125488,
|
|
"epoch": 0.6742108397855867,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004965055225689658,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.18702482879161836,
|
|
"num_tokens": 15854841.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.233872175216675,
|
|
"epoch": 0.6748064324002382,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004964980375839379,
|
|
"loss": 4.9845,
|
|
"mean_token_accuracy": 0.19708098471164703,
|
|
"num_tokens": 15866701.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.184519577026367,
|
|
"epoch": 0.6754020250148898,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004964905446541355,
|
|
"loss": 4.9684,
|
|
"mean_token_accuracy": 0.19654641300439835,
|
|
"num_tokens": 15880227.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.2238609313964846,
|
|
"epoch": 0.6759976176295414,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004964830437798276,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.18559536933898926,
|
|
"num_tokens": 15894748.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.235979509353638,
|
|
"epoch": 0.6765932102441929,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004964755349612829,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.19552299678325652,
|
|
"num_tokens": 15908103.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.2999091148376465,
|
|
"epoch": 0.6771888028588445,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004964680181987709,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.184394970536232,
|
|
"num_tokens": 15920996.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.267886734008789,
|
|
"epoch": 0.6777843954734961,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000496460493492561,
|
|
"loss": 5.0863,
|
|
"mean_token_accuracy": 0.18569493293762207,
|
|
"num_tokens": 15934922.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.258800411224366,
|
|
"epoch": 0.6783799880881477,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004964529608429234,
|
|
"loss": 5.0357,
|
|
"mean_token_accuracy": 0.18828275203704833,
|
|
"num_tokens": 15948903.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.3015834331512455,
|
|
"epoch": 0.6789755807027993,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004964454202501282,
|
|
"loss": 5.0726,
|
|
"mean_token_accuracy": 0.19011245667934418,
|
|
"num_tokens": 15963610.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.1792679786682125,
|
|
"epoch": 0.6795711733174509,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004964378717144458,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.19334629327058792,
|
|
"num_tokens": 15977247.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.161413908004761,
|
|
"epoch": 0.6801667659321025,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.000496430315236147,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.19741306751966475,
|
|
"num_tokens": 15991856.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.220260715484619,
|
|
"epoch": 0.680762358546754,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004964227508155027,
|
|
"loss": 5.0029,
|
|
"mean_token_accuracy": 0.19149223119020461,
|
|
"num_tokens": 16006071.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.226979446411133,
|
|
"epoch": 0.6813579511614056,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004964151784527844,
|
|
"loss": 5.0342,
|
|
"mean_token_accuracy": 0.19196676462888718,
|
|
"num_tokens": 16021164.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.247955989837647,
|
|
"epoch": 0.6819535437760572,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004964075981482637,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.19261963814496993,
|
|
"num_tokens": 16035251.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.212866926193238,
|
|
"epoch": 0.6825491363907088,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964000099022124,
|
|
"loss": 4.9918,
|
|
"mean_token_accuracy": 0.19760527908802034,
|
|
"num_tokens": 16048628.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.167464971542358,
|
|
"epoch": 0.6831447290053604,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004963924137149027,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.20154782235622407,
|
|
"num_tokens": 16061612.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.183085489273071,
|
|
"epoch": 0.6837403216200119,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963848095866072,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.19481744468212128,
|
|
"num_tokens": 16075506.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.267515659332275,
|
|
"epoch": 0.6843359142346634,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004963771975175984,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.1793405681848526,
|
|
"num_tokens": 16090629.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.195936822891236,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004963695775081495,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.1995197892189026,
|
|
"num_tokens": 16105219.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.232565069198609,
|
|
"epoch": 0.6855270994639666,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004963619495585338,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.19518732875585557,
|
|
"num_tokens": 16118851.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.163709545135498,
|
|
"epoch": 0.6861226920786182,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004963543136690247,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.19295049756765364,
|
|
"num_tokens": 16132435.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.180385780334473,
|
|
"epoch": 0.6867182846932698,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004963466698398965,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.19070562422275544,
|
|
"num_tokens": 16145922.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.1947588443756105,
|
|
"epoch": 0.6873138773079214,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004963390180714231,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.19403730183839799,
|
|
"num_tokens": 16158056.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.266003608703613,
|
|
"epoch": 0.687909469922573,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000496331358363879,
|
|
"loss": 5.046,
|
|
"mean_token_accuracy": 0.19434632509946823,
|
|
"num_tokens": 16172836.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.289444828033448,
|
|
"epoch": 0.6885050625372245,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004963236907175388,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.17846478372812272,
|
|
"num_tokens": 16187787.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.178939151763916,
|
|
"epoch": 0.6891006551518761,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004963160151326778,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.19745612442493438,
|
|
"num_tokens": 16201861.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.107771635055542,
|
|
"epoch": 0.6896962477665277,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004963083316095712,
|
|
"loss": 4.899,
|
|
"mean_token_accuracy": 0.19720693528652192,
|
|
"num_tokens": 16215447.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.200075244903564,
|
|
"epoch": 0.6902918403811793,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004963006401484945,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.19762418121099473,
|
|
"num_tokens": 16229127.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.27059497833252,
|
|
"epoch": 0.6908874329958309,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004962929407497236,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.19065853357315063,
|
|
"num_tokens": 16242911.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.268238258361817,
|
|
"epoch": 0.6914830256104825,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004962852334135348,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.18754418790340424,
|
|
"num_tokens": 16257430.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.152529907226563,
|
|
"epoch": 0.6920786182251341,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004962775181402044,
|
|
"loss": 4.8955,
|
|
"mean_token_accuracy": 0.20580868124961854,
|
|
"num_tokens": 16270187.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.264871120452881,
|
|
"epoch": 0.6926742108397855,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004962697949300093,
|
|
"loss": 5.0827,
|
|
"mean_token_accuracy": 0.1892458453774452,
|
|
"num_tokens": 16282750.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.23567419052124,
|
|
"epoch": 0.6932698034544371,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004962620637832263,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.1986319899559021,
|
|
"num_tokens": 16295985.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.2512218952178955,
|
|
"epoch": 0.6938653960690887,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004962543247001329,
|
|
"loss": 5.0618,
|
|
"mean_token_accuracy": 0.18572293519973754,
|
|
"num_tokens": 16308735.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.283103656768799,
|
|
"epoch": 0.6944609886837403,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004962465776810066,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.19015296548604965,
|
|
"num_tokens": 16322722.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.193598842620849,
|
|
"epoch": 0.6950565812983919,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004962388227261253,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.19867675602436066,
|
|
"num_tokens": 16336075.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.233902025222778,
|
|
"epoch": 0.6956521739130435,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004962310598357672,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.18685352206230163,
|
|
"num_tokens": 16351487.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.236039733886718,
|
|
"epoch": 0.696247766527695,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004962232890102106,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.19590164572000504,
|
|
"num_tokens": 16365518.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.179704761505127,
|
|
"epoch": 0.6968433591423466,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004962155102497342,
|
|
"loss": 5.0151,
|
|
"mean_token_accuracy": 0.19118821620941162,
|
|
"num_tokens": 16379665.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.320987176895142,
|
|
"epoch": 0.6974389517569982,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004962077235546173,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.19109077006578445,
|
|
"num_tokens": 16394540.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.212607383728027,
|
|
"epoch": 0.6980345443716498,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004961999289251389,
|
|
"loss": 5.0386,
|
|
"mean_token_accuracy": 0.19521069079637526,
|
|
"num_tokens": 16406628.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.176800537109375,
|
|
"epoch": 0.6986301369863014,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004961921263615788,
|
|
"loss": 4.9583,
|
|
"mean_token_accuracy": 0.20125830173492432,
|
|
"num_tokens": 16417516.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.163766956329345,
|
|
"epoch": 0.699225729600953,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004961843158642167,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.1979386940598488,
|
|
"num_tokens": 16431899.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.253143787384033,
|
|
"epoch": 0.6998213222156046,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004961764974333328,
|
|
"loss": 5.0949,
|
|
"mean_token_accuracy": 0.18762757033109664,
|
|
"num_tokens": 16444716.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.212019252777099,
|
|
"epoch": 0.7004169148302561,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004961686710692076,
|
|
"loss": 4.9366,
|
|
"mean_token_accuracy": 0.19871095716953277,
|
|
"num_tokens": 16459544.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.243808889389038,
|
|
"epoch": 0.7010125074449077,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004961608367721217,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.19384327679872512,
|
|
"num_tokens": 16472537.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.137933206558228,
|
|
"epoch": 0.7016081000595593,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004961529945423563,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.197707898914814,
|
|
"num_tokens": 16486184.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.1593376159667965,
|
|
"epoch": 0.7022036926742108,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004961451443801924,
|
|
"loss": 4.9758,
|
|
"mean_token_accuracy": 0.19458836913108826,
|
|
"num_tokens": 16499584.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.176172208786011,
|
|
"epoch": 0.7027992852888624,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004961372862859119,
|
|
"loss": 4.9443,
|
|
"mean_token_accuracy": 0.19392507076263427,
|
|
"num_tokens": 16512701.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.312985277175903,
|
|
"epoch": 0.703394877903514,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004961294202597962,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.1849490761756897,
|
|
"num_tokens": 16525019.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.249667024612426,
|
|
"epoch": 0.7039904705181655,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004961215463021281,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.19512701481580735,
|
|
"num_tokens": 16539335.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.178429412841797,
|
|
"epoch": 0.7045860631328171,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004961136644131894,
|
|
"loss": 4.9588,
|
|
"mean_token_accuracy": 0.19686115980148317,
|
|
"num_tokens": 16552680.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.136629962921143,
|
|
"epoch": 0.7051816557474687,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004961057745932633,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.20011175274848939,
|
|
"num_tokens": 16565819.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.221772193908691,
|
|
"epoch": 0.7057772483621203,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004960978768426323,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.1973884806036949,
|
|
"num_tokens": 16579280.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.210810708999634,
|
|
"epoch": 0.7063728409767719,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049608997116158,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.18434540331363677,
|
|
"num_tokens": 16594090.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.25242509841919,
|
|
"epoch": 0.7069684335914235,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.00049608205755039,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.1942136138677597,
|
|
"num_tokens": 16609287.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.238081264495849,
|
|
"epoch": 0.7075640262060751,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004960741360093459,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.18787476569414138,
|
|
"num_tokens": 16624873.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.188109016418457,
|
|
"epoch": 0.7081596188207266,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004960662065387322,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.19419119507074356,
|
|
"num_tokens": 16637885.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.2546460151672365,
|
|
"epoch": 0.7087552114353782,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000496058269138833,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.1934243619441986,
|
|
"num_tokens": 16650961.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.224667358398437,
|
|
"epoch": 0.7093508040500298,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004960503238099331,
|
|
"loss": 5.0464,
|
|
"mean_token_accuracy": 0.19252557456493377,
|
|
"num_tokens": 16665740.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.275289678573609,
|
|
"epoch": 0.7099463966646814,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004960423705523175,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.18924264907836913,
|
|
"num_tokens": 16679143.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.236150217056275,
|
|
"epoch": 0.710541989279333,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004960344093662714,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.1954708531498909,
|
|
"num_tokens": 16692460.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.209852266311645,
|
|
"epoch": 0.7111375818939845,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004960264402520804,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.20065396577119826,
|
|
"num_tokens": 16707037.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.26790418624878,
|
|
"epoch": 0.711733174508636,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004960184632100304,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.19775129109621048,
|
|
"num_tokens": 16719857.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.2152056217193605,
|
|
"epoch": 0.7123287671232876,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004960104782404075,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.19611058980226517,
|
|
"num_tokens": 16732221.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.245729064941406,
|
|
"epoch": 0.7129243597379392,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004960024853434982,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.1929053083062172,
|
|
"num_tokens": 16747384.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.2037725925445555,
|
|
"epoch": 0.7135199523525908,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000495994484519589,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.18775837868452072,
|
|
"num_tokens": 16761269.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.186244869232178,
|
|
"epoch": 0.7141155449672424,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004959864757689669,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.19541864544153215,
|
|
"num_tokens": 16775403.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.246415662765503,
|
|
"epoch": 0.714711137581894,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004959784590919192,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.19306568205356597,
|
|
"num_tokens": 16790740.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.714711137581894,
|
|
"eval_entropy": 4.940415644421472,
|
|
"eval_loss": 4.973916053771973,
|
|
"eval_mean_token_accuracy": 0.20525089036264577,
|
|
"eval_num_tokens": 16790740.0,
|
|
"eval_runtime": 18.485,
|
|
"eval_samples_per_second": 1380.201,
|
|
"eval_steps_per_second": 172.573,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.167508745193482,
|
|
"epoch": 0.7153067301965456,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004959704344887335,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.19130657762289047,
|
|
"num_tokens": 16805005.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.2230690002441404,
|
|
"epoch": 0.7159023228111971,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004959624019596976,
|
|
"loss": 5.0254,
|
|
"mean_token_accuracy": 0.19440141916275025,
|
|
"num_tokens": 16818227.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.2072625160217285,
|
|
"epoch": 0.7164979154258487,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004959543615050996,
|
|
"loss": 5.0052,
|
|
"mean_token_accuracy": 0.19660791456699372,
|
|
"num_tokens": 16831113.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.222737121582031,
|
|
"epoch": 0.7170935080405003,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004959463131252278,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.19122221916913987,
|
|
"num_tokens": 16844952.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.319234418869018,
|
|
"epoch": 0.7176891006551519,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004959382568203711,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.19028442800045015,
|
|
"num_tokens": 16858360.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.156467723846435,
|
|
"epoch": 0.7182846932698035,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004959301925908184,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.19866423755884172,
|
|
"num_tokens": 16869172.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.146221256256103,
|
|
"epoch": 0.7188802858844551,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004959221204368588,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.18832390159368514,
|
|
"num_tokens": 16884322.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.327645969390869,
|
|
"epoch": 0.7194758784991067,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004959140403587819,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.19371753484010695,
|
|
"num_tokens": 16896686.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.241466474533081,
|
|
"epoch": 0.7200714711137582,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004959059523568778,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.19565755724906922,
|
|
"num_tokens": 16912819.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.226687002182007,
|
|
"epoch": 0.7206670637284097,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004958978564314361,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.19182371646165847,
|
|
"num_tokens": 16926615.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.21510157585144,
|
|
"epoch": 0.7212626563430613,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004958897525827476,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.1957946538925171,
|
|
"num_tokens": 16940934.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.181780385971069,
|
|
"epoch": 0.7218582489577129,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004958816408111027,
|
|
"loss": 4.879,
|
|
"mean_token_accuracy": 0.20601600557565689,
|
|
"num_tokens": 16953016.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.133279275894165,
|
|
"epoch": 0.7224538415723645,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004958735211167926,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.19957727789878846,
|
|
"num_tokens": 16964460.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.238236999511718,
|
|
"epoch": 0.7230494341870161,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004958653935001083,
|
|
"loss": 5.0761,
|
|
"mean_token_accuracy": 0.18826861530542374,
|
|
"num_tokens": 16978307.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.2710285663604735,
|
|
"epoch": 0.7236450268016676,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004958572579613415,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.19542692601680756,
|
|
"num_tokens": 16992240.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.119581508636474,
|
|
"epoch": 0.7242406194163192,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000495849114500784,
|
|
"loss": 4.876,
|
|
"mean_token_accuracy": 0.20546600967645645,
|
|
"num_tokens": 17004865.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.197304153442383,
|
|
"epoch": 0.7248362120309708,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004958409631187278,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.2029432773590088,
|
|
"num_tokens": 17018377.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.140698337554932,
|
|
"epoch": 0.7254318046456224,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004958328038154652,
|
|
"loss": 4.8872,
|
|
"mean_token_accuracy": 0.20156844854354858,
|
|
"num_tokens": 17032487.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.230426263809204,
|
|
"epoch": 0.726027397260274,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004958246365912891,
|
|
"loss": 5.0276,
|
|
"mean_token_accuracy": 0.1968516767024994,
|
|
"num_tokens": 17045783.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.319394302368164,
|
|
"epoch": 0.7266229898749256,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004958164614464923,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.18237221390008926,
|
|
"num_tokens": 17060359.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.249917078018188,
|
|
"epoch": 0.7272185824895772,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.19599988013505937,
|
|
"num_tokens": 17074510.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.194752550125122,
|
|
"epoch": 0.7278141751042287,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004958000873962099,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.19430559277534484,
|
|
"num_tokens": 17088551.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.273688650131225,
|
|
"epoch": 0.7284097677188803,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004957918884913115,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.18327474147081374,
|
|
"num_tokens": 17102674.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.269916009902954,
|
|
"epoch": 0.7290053603335319,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004957836816669672,
|
|
"loss": 5.028,
|
|
"mean_token_accuracy": 0.19103916585445405,
|
|
"num_tokens": 17116891.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.239763402938843,
|
|
"epoch": 0.7296009529481834,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957754669234711,
|
|
"loss": 4.9638,
|
|
"mean_token_accuracy": 0.1953309416770935,
|
|
"num_tokens": 17129003.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.147449970245361,
|
|
"epoch": 0.730196545562835,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000495767244261118,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.20167790800333024,
|
|
"num_tokens": 17142225.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.194434452056885,
|
|
"epoch": 0.7307921381774866,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004957590136802028,
|
|
"loss": 5.0168,
|
|
"mean_token_accuracy": 0.19738942682743071,
|
|
"num_tokens": 17154849.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.200641679763794,
|
|
"epoch": 0.7313877307921381,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004957507751810207,
|
|
"loss": 4.9321,
|
|
"mean_token_accuracy": 0.198508320748806,
|
|
"num_tokens": 17170335.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.207217502593994,
|
|
"epoch": 0.7319833234067897,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004957425287638673,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.18515270054340363,
|
|
"num_tokens": 17185181.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.3468546867370605,
|
|
"epoch": 0.7325789160214413,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004957342744290381,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.19273507297039033,
|
|
"num_tokens": 17198960.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.281911706924438,
|
|
"epoch": 0.7331745086360929,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004957260121768296,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.19284442514181138,
|
|
"num_tokens": 17212233.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.224344778060913,
|
|
"epoch": 0.7337701012507445,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004957177420075377,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.1968523681163788,
|
|
"num_tokens": 17224012.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.156566476821899,
|
|
"epoch": 0.7343656938653961,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004957094639214594,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.18235350102186204,
|
|
"num_tokens": 17236943.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.294571208953857,
|
|
"epoch": 0.7349612864800477,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004957011779188915,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.1878274843096733,
|
|
"num_tokens": 17249835.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.307394123077392,
|
|
"epoch": 0.7355568790946992,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004956928840001312,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.1867114022374153,
|
|
"num_tokens": 17263260.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.286664295196533,
|
|
"epoch": 0.7361524717093508,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004956845821654758,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.191137632727623,
|
|
"num_tokens": 17277309.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.2535703659057615,
|
|
"epoch": 0.7367480643240024,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004956762724152234,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.19457209706306458,
|
|
"num_tokens": 17291354.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.196777582168579,
|
|
"epoch": 0.737343656938654,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004956679547496719,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.19505695700645448,
|
|
"num_tokens": 17305805.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.188502502441406,
|
|
"epoch": 0.7379392495533056,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004956596291691197,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.1996886521577835,
|
|
"num_tokens": 17319031.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.253202962875366,
|
|
"epoch": 0.7385348421679571,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004956512956738652,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.19299153238534927,
|
|
"num_tokens": 17332455.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.201680278778076,
|
|
"epoch": 0.7391304347826086,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004956429542642075,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.19257753044366838,
|
|
"num_tokens": 17346849.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.201982736587524,
|
|
"epoch": 0.7397260273972602,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004956346049404459,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.19815541952848434,
|
|
"num_tokens": 17360204.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.252338075637818,
|
|
"epoch": 0.7403216200119118,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004956262477028797,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.1929316520690918,
|
|
"num_tokens": 17373430.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.250050973892212,
|
|
"epoch": 0.7409172126265634,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004956178825518087,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.20340880751609802,
|
|
"num_tokens": 17386856.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.134352445602417,
|
|
"epoch": 0.741512805241215,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956095094875329,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.19527941346168518,
|
|
"num_tokens": 17401657.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.200413608551026,
|
|
"epoch": 0.7421083978558666,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004956011285103528,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.1915552094578743,
|
|
"num_tokens": 17415688.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.262109613418579,
|
|
"epoch": 0.7427039904705182,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004955927396205689,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.19540394842624664,
|
|
"num_tokens": 17428272.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.196072340011597,
|
|
"epoch": 0.7432995830851697,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000495584342818482,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.20016586035490036,
|
|
"num_tokens": 17440858.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.303284072875977,
|
|
"epoch": 0.7438951756998213,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004955759381043934,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.19344063401222228,
|
|
"num_tokens": 17453946.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.239511585235595,
|
|
"epoch": 0.7444907683144729,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004955675254786045,
|
|
"loss": 4.9992,
|
|
"mean_token_accuracy": 0.19466943591833114,
|
|
"num_tokens": 17470565.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.216199779510498,
|
|
"epoch": 0.7450863609291245,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004955591049414171,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.19631701111793518,
|
|
"num_tokens": 17484604.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.253848361968994,
|
|
"epoch": 0.7456819535437761,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004955506764931332,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.18659911006689073,
|
|
"num_tokens": 17500578.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.213921022415161,
|
|
"epoch": 0.7462775461584277,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004955422401340553,
|
|
"loss": 5.0662,
|
|
"mean_token_accuracy": 0.18858876675367356,
|
|
"num_tokens": 17516999.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.213530778884888,
|
|
"epoch": 0.7468731387730793,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004955337958644857,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.197228866815567,
|
|
"num_tokens": 17530943.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.161210584640503,
|
|
"epoch": 0.7474687313877308,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004955253436847273,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.20546384155750275,
|
|
"num_tokens": 17543698.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.083687829971313,
|
|
"epoch": 0.7480643240023823,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004955168835950835,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.20950689911842346,
|
|
"num_tokens": 17556141.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.159177207946778,
|
|
"epoch": 0.7486599166170339,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004955084155958576,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.2055245339870453,
|
|
"num_tokens": 17569186.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.256765460968017,
|
|
"epoch": 0.7492555092316855,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004954999396873534,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.1869715377688408,
|
|
"num_tokens": 17583826.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.237720346450805,
|
|
"epoch": 0.7498511018463371,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004954914558698748,
|
|
"loss": 4.9657,
|
|
"mean_token_accuracy": 0.1989605247974396,
|
|
"num_tokens": 17597196.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.2814994812011715,
|
|
"epoch": 0.7504466944609887,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004954829641437261,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.18891747742891313,
|
|
"num_tokens": 17611283.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.233958625793457,
|
|
"epoch": 0.7510422870756402,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004954744645092121,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.2020708292722702,
|
|
"num_tokens": 17626089.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.246726369857788,
|
|
"epoch": 0.7516378796902918,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004954659569666375,
|
|
"loss": 5.0737,
|
|
"mean_token_accuracy": 0.19530968517065048,
|
|
"num_tokens": 17639915.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.290156126022339,
|
|
"epoch": 0.7522334723049434,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004954574415163075,
|
|
"loss": 5.0494,
|
|
"mean_token_accuracy": 0.19318126738071442,
|
|
"num_tokens": 17654563.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.20617184638977,
|
|
"epoch": 0.752829064919595,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004954489181585275,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.19626425206661224,
|
|
"num_tokens": 17669132.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.152454423904419,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004954403868936032,
|
|
"loss": 4.9239,
|
|
"mean_token_accuracy": 0.19740720838308334,
|
|
"num_tokens": 17682794.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.257226037979126,
|
|
"epoch": 0.7540202501488982,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004954318477218406,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.19156909883022308,
|
|
"num_tokens": 17697325.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.236366128921508,
|
|
"epoch": 0.7546158427635498,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000495423300643546,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.1868755355477333,
|
|
"num_tokens": 17710136.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.195476627349853,
|
|
"epoch": 0.7552114353782013,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004954147456590262,
|
|
"loss": 4.9555,
|
|
"mean_token_accuracy": 0.19309208840131759,
|
|
"num_tokens": 17723138.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.187572574615478,
|
|
"epoch": 0.7558070279928529,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004954061827685877,
|
|
"loss": 4.944,
|
|
"mean_token_accuracy": 0.20160356014966965,
|
|
"num_tokens": 17735059.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.170554351806641,
|
|
"epoch": 0.7564026206075045,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004953976119725378,
|
|
"loss": 4.9844,
|
|
"mean_token_accuracy": 0.1945444792509079,
|
|
"num_tokens": 17750361.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.207920932769776,
|
|
"epoch": 0.756998213222156,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004953890332711839,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.1910410165786743,
|
|
"num_tokens": 17766597.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.318069314956665,
|
|
"epoch": 0.7575938058368076,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004953804466648337,
|
|
"loss": 5.042,
|
|
"mean_token_accuracy": 0.18902000337839125,
|
|
"num_tokens": 17780086.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.173790454864502,
|
|
"epoch": 0.7581893984514592,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953718521537952,
|
|
"loss": 4.9289,
|
|
"mean_token_accuracy": 0.20532690435647966,
|
|
"num_tokens": 17793316.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.229732656478882,
|
|
"epoch": 0.7587849910661107,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953632497383766,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.18840504437685013,
|
|
"num_tokens": 17807766.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.1557056427001955,
|
|
"epoch": 0.7593805836807623,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004953546394188867,
|
|
"loss": 4.9352,
|
|
"mean_token_accuracy": 0.2043674260377884,
|
|
"num_tokens": 17819778.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.247732162475586,
|
|
"epoch": 0.7599761762954139,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.000495346021195634,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.19394806325435637,
|
|
"num_tokens": 17835432.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.2031028270721436,
|
|
"epoch": 0.7605717689100655,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004953373950689279,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.20307695865631104,
|
|
"num_tokens": 17848861.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.216523170471191,
|
|
"epoch": 0.7611673615247171,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004953287610390775,
|
|
"loss": 4.9895,
|
|
"mean_token_accuracy": 0.19733566790819168,
|
|
"num_tokens": 17863173.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.1563797950744625,
|
|
"epoch": 0.7617629541393687,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004953201191063928,
|
|
"loss": 5.0271,
|
|
"mean_token_accuracy": 0.19484409391880037,
|
|
"num_tokens": 17876497.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.217193984985352,
|
|
"epoch": 0.7623585467540203,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004953114692711837,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.20320072323083876,
|
|
"num_tokens": 17890582.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.216400480270385,
|
|
"epoch": 0.7629541393686718,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004953028115337603,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.19127855598926544,
|
|
"num_tokens": 17905476.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.193920135498047,
|
|
"epoch": 0.7635497319833234,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952941458944333,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.19307632446289064,
|
|
"num_tokens": 17918571.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.193931722640992,
|
|
"epoch": 0.764145324597975,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004952854723535134,
|
|
"loss": 5.0635,
|
|
"mean_token_accuracy": 0.1926618680357933,
|
|
"num_tokens": 17932169.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.189862442016602,
|
|
"epoch": 0.7647409172126266,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004952767909113118,
|
|
"loss": 4.9169,
|
|
"mean_token_accuracy": 0.21033641397953035,
|
|
"num_tokens": 17944772.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.160337686538696,
|
|
"epoch": 0.7653365098272782,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004952681015681398,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.2048033967614174,
|
|
"num_tokens": 17957903.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.218353605270385,
|
|
"epoch": 0.7659321024419298,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952594043243092,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.19353794753551484,
|
|
"num_tokens": 17972214.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.1584851264953615,
|
|
"epoch": 0.7665276950565812,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952506991801319,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.20294411033391951,
|
|
"num_tokens": 17986722.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.217153263092041,
|
|
"epoch": 0.7671232876712328,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004952419861359201,
|
|
"loss": 5.0092,
|
|
"mean_token_accuracy": 0.2062564119696617,
|
|
"num_tokens": 17999392.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.216296863555908,
|
|
"epoch": 0.7677188802858844,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004952332651919864,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.19546557664871217,
|
|
"num_tokens": 18013560.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.3441825866699215,
|
|
"epoch": 0.768314472900536,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004952245363486435,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.18818190693855286,
|
|
"num_tokens": 18027631.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.164026117324829,
|
|
"epoch": 0.7689100655151876,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004952157996062046,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.19969597905874253,
|
|
"num_tokens": 18041618.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.225600719451904,
|
|
"epoch": 0.7695056581298392,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000495207054964983,
|
|
"loss": 4.9751,
|
|
"mean_token_accuracy": 0.19665047377347947,
|
|
"num_tokens": 18053783.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.21432056427002,
|
|
"epoch": 0.7701012507444908,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004951983024252924,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.1900701865553856,
|
|
"num_tokens": 18067471.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.218812561035156,
|
|
"epoch": 0.7706968433591423,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004951895419874466,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.19593874216079712,
|
|
"num_tokens": 18081173.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.306157350540161,
|
|
"epoch": 0.7712924359737939,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.00049518077365176,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.18314757496118544,
|
|
"num_tokens": 18094237.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.184618949890137,
|
|
"epoch": 0.7718880285884455,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000495171997418547,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.20103740841150283,
|
|
"num_tokens": 18109184.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.18105731010437,
|
|
"epoch": 0.7724836212030971,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004951632132881225,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.19993216097354888,
|
|
"num_tokens": 18122801.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.212755727767944,
|
|
"epoch": 0.7730792138177487,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004951544212608015,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.1965155303478241,
|
|
"num_tokens": 18135807.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.190378475189209,
|
|
"epoch": 0.7736748064324003,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004951456213368994,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.19493371546268462,
|
|
"num_tokens": 18149093.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.3449249267578125,
|
|
"epoch": 0.7742703990470519,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004951368135167316,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.18750405460596084,
|
|
"num_tokens": 18162878.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.207848739624024,
|
|
"epoch": 0.7748659916617034,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004951279978006143,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.19590355157852174,
|
|
"num_tokens": 18176443.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.141319322586059,
|
|
"epoch": 0.7754615842763549,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.0004951191741888638,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.19382061958312988,
|
|
"num_tokens": 18194684.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.157397365570068,
|
|
"epoch": 0.7760571768910065,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004951103426817961,
|
|
"loss": 4.8518,
|
|
"mean_token_accuracy": 0.20886114239692688,
|
|
"num_tokens": 18207667.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.189918851852417,
|
|
"epoch": 0.7766527695056581,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004951015032797286,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.19991605132818221,
|
|
"num_tokens": 18220594.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.157913017272949,
|
|
"epoch": 0.7772483621203097,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004950926559829778,
|
|
"loss": 4.9486,
|
|
"mean_token_accuracy": 0.19604713320732117,
|
|
"num_tokens": 18235193.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.218387031555176,
|
|
"epoch": 0.7778439547349613,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004950838007918615,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.20040399730205535,
|
|
"num_tokens": 18246647.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.170574522018432,
|
|
"epoch": 0.7784395473496128,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000495074937706697,
|
|
"loss": 4.9781,
|
|
"mean_token_accuracy": 0.1947624132037163,
|
|
"num_tokens": 18260255.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.189462900161743,
|
|
"epoch": 0.7790351399642644,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004950660667278023,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.20121008902788162,
|
|
"num_tokens": 18274505.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.19947304725647,
|
|
"epoch": 0.779630732578916,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004950571878554956,
|
|
"loss": 4.9635,
|
|
"mean_token_accuracy": 0.20336953103542327,
|
|
"num_tokens": 18288386.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.275217294692993,
|
|
"epoch": 0.7802263251935676,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004950483010900953,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.19346607029438018,
|
|
"num_tokens": 18303602.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.177950000762939,
|
|
"epoch": 0.7808219178082192,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004950394064319203,
|
|
"loss": 4.9962,
|
|
"mean_token_accuracy": 0.19990218579769134,
|
|
"num_tokens": 18318561.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.196379232406616,
|
|
"epoch": 0.7814175104228708,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004950305038812895,
|
|
"loss": 4.886,
|
|
"mean_token_accuracy": 0.20022922158241271,
|
|
"num_tokens": 18331903.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.117612838745117,
|
|
"epoch": 0.7820131030375224,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004950215934385223,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.2092200994491577,
|
|
"num_tokens": 18344958.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.244729280471802,
|
|
"epoch": 0.782608695652174,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004950126751039382,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.1904166355729103,
|
|
"num_tokens": 18359343.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.185728216171265,
|
|
"epoch": 0.7832042882668255,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004950037488778572,
|
|
"loss": 4.9603,
|
|
"mean_token_accuracy": 0.19252391457557677,
|
|
"num_tokens": 18372672.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.2596580505371096,
|
|
"epoch": 0.7837998808814771,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004949948147605996,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.19485182911157609,
|
|
"num_tokens": 18385013.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.261306858062744,
|
|
"epoch": 0.7843954734961287,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004949858727524855,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.19415438175201416,
|
|
"num_tokens": 18398411.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.177626419067383,
|
|
"epoch": 0.7849910661107802,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004949769228538359,
|
|
"loss": 4.9506,
|
|
"mean_token_accuracy": 0.19288806468248368,
|
|
"num_tokens": 18411317.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.292327117919922,
|
|
"epoch": 0.7855866587254318,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004949679650649717,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.190231154859066,
|
|
"num_tokens": 18426503.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.174467611312866,
|
|
"epoch": 0.7861822513400833,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004949589993862143,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.20611148029565812,
|
|
"num_tokens": 18439465.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.102931261062622,
|
|
"epoch": 0.7867778439547349,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004949500258178851,
|
|
"loss": 4.9009,
|
|
"mean_token_accuracy": 0.19426576495170594,
|
|
"num_tokens": 18452539.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.219004201889038,
|
|
"epoch": 0.7873734365693865,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004949410443603062,
|
|
"loss": 4.946,
|
|
"mean_token_accuracy": 0.2001374989748001,
|
|
"num_tokens": 18466040.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.256741046905518,
|
|
"epoch": 0.7879690291840381,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004949320550137996,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.19557258784770964,
|
|
"num_tokens": 18478621.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.240972280502319,
|
|
"epoch": 0.7885646217986897,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004949230577786877,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.20098492056131362,
|
|
"num_tokens": 18492000.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.087990236282349,
|
|
"epoch": 0.7891602144133413,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004949140526552934,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.2073688954114914,
|
|
"num_tokens": 18506459.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.125224876403808,
|
|
"epoch": 0.7897558070279929,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004949050396439395,
|
|
"loss": 4.8581,
|
|
"mean_token_accuracy": 0.20849994271993638,
|
|
"num_tokens": 18518325.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.178883981704712,
|
|
"epoch": 0.7903513996426444,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004948960187449495,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.20768900513648986,
|
|
"num_tokens": 18533329.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.216421604156494,
|
|
"epoch": 0.790946992257296,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004948869899586467,
|
|
"loss": 5.0182,
|
|
"mean_token_accuracy": 0.2045308381319046,
|
|
"num_tokens": 18544635.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.152740716934204,
|
|
"epoch": 0.7915425848719476,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004948779532853552,
|
|
"loss": 4.9627,
|
|
"mean_token_accuracy": 0.20945716351270677,
|
|
"num_tokens": 18558576.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.193213605880738,
|
|
"epoch": 0.7921381774865992,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004948689087253989,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.1911552891135216,
|
|
"num_tokens": 18573393.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.202578401565551,
|
|
"epoch": 0.7927337701012508,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004948598562791025,
|
|
"loss": 4.8841,
|
|
"mean_token_accuracy": 0.2067822188138962,
|
|
"num_tokens": 18586273.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.249826145172119,
|
|
"epoch": 0.7933293627159024,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004948507959467905,
|
|
"loss": 5.067,
|
|
"mean_token_accuracy": 0.19914352297782897,
|
|
"num_tokens": 18600040.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.14374737739563,
|
|
"epoch": 0.7939249553305538,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004948417277287877,
|
|
"loss": 4.8485,
|
|
"mean_token_accuracy": 0.20845488011837005,
|
|
"num_tokens": 18613723.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.205537271499634,
|
|
"epoch": 0.7945205479452054,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004948326516254197,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.1989010214805603,
|
|
"num_tokens": 18628575.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.240116882324219,
|
|
"epoch": 0.795116140559857,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000494823567637012,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.19002011716365813,
|
|
"num_tokens": 18642179.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.189844846725464,
|
|
"epoch": 0.7957117331745086,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004948144757638902,
|
|
"loss": 4.9619,
|
|
"mean_token_accuracy": 0.19549095630645752,
|
|
"num_tokens": 18655450.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.192246055603027,
|
|
"epoch": 0.7963073257891602,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004948053760063806,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.20517516434192656,
|
|
"num_tokens": 18668434.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.184614801406861,
|
|
"epoch": 0.7969029184038118,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004947962683648095,
|
|
"loss": 4.9529,
|
|
"mean_token_accuracy": 0.19955021291971206,
|
|
"num_tokens": 18683674.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.164677572250366,
|
|
"epoch": 0.7974985110184634,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004947871528395038,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.19832128435373306,
|
|
"num_tokens": 18697323.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.212483501434326,
|
|
"epoch": 0.798094103633115,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.00049477802943079,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.19775326550006866,
|
|
"num_tokens": 18711110.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.240968132019043,
|
|
"epoch": 0.7986896962477665,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004947688981389958,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.19157029688358307,
|
|
"num_tokens": 18725753.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.160842227935791,
|
|
"epoch": 0.7992852888624181,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004947597589644484,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.20104837864637376,
|
|
"num_tokens": 18740363.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.146410894393921,
|
|
"epoch": 0.7998808814770697,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004947506119074759,
|
|
"loss": 4.9029,
|
|
"mean_token_accuracy": 0.19810617417097093,
|
|
"num_tokens": 18755157.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.1218959331512455,
|
|
"epoch": 0.8004764740917213,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004947414569684062,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.20115058422088622,
|
|
"num_tokens": 18769828.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.197394704818725,
|
|
"epoch": 0.8010720667063729,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004947322941475677,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.19985956251621245,
|
|
"num_tokens": 18785810.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.260333585739136,
|
|
"epoch": 0.8016676593210245,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004947231234452891,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.18300077319145203,
|
|
"num_tokens": 18801730.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.188740062713623,
|
|
"epoch": 0.802263251935676,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004947139448618994,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.20209090262651444,
|
|
"num_tokens": 18816684.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.1887282371521,
|
|
"epoch": 0.8028588445503275,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004947047583977276,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.19222164899110794,
|
|
"num_tokens": 18832487.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.116547107696533,
|
|
"epoch": 0.8034544371649791,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004946955640531033,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.20503035932779312,
|
|
"num_tokens": 18845136.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.214083051681518,
|
|
"epoch": 0.8040500297796307,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004946863618283565,
|
|
"loss": 4.9297,
|
|
"mean_token_accuracy": 0.19984907507896424,
|
|
"num_tokens": 18859082.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.209629726409912,
|
|
"epoch": 0.8046456223942823,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004946771517238169,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.19937164038419725,
|
|
"num_tokens": 18872957.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.20362024307251,
|
|
"epoch": 0.8052412150089339,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004946679337398151,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.20129719823598863,
|
|
"num_tokens": 18887189.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.216832637786865,
|
|
"epoch": 0.8058368076235854,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004946587078766818,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.19818754643201827,
|
|
"num_tokens": 18900325.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.166711139678955,
|
|
"epoch": 0.806432400238237,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004946494741347476,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.19886155128479005,
|
|
"num_tokens": 18914583.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.208052349090576,
|
|
"epoch": 0.8070279928528886,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004946402325143439,
|
|
"loss": 5.0101,
|
|
"mean_token_accuracy": 0.19739667922258378,
|
|
"num_tokens": 18928796.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.185489368438721,
|
|
"epoch": 0.8076235854675402,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004946309830158024,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.193352310359478,
|
|
"num_tokens": 18942976.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.141387605667115,
|
|
"epoch": 0.8082191780821918,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946217256394544,
|
|
"loss": 4.9345,
|
|
"mean_token_accuracy": 0.20610932260751724,
|
|
"num_tokens": 18955384.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.231763887405395,
|
|
"epoch": 0.8088147706968434,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004946124603856322,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.19366343170404435,
|
|
"num_tokens": 18969149.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.158548307418823,
|
|
"epoch": 0.809410363311495,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004946031872546683,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.19997966140508652,
|
|
"num_tokens": 18982216.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.180615234375,
|
|
"epoch": 0.8100059559261465,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000494593906246895,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.19309812188148498,
|
|
"num_tokens": 18998075.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.112532138824463,
|
|
"epoch": 0.8106015485407981,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004945846173626453,
|
|
"loss": 4.8576,
|
|
"mean_token_accuracy": 0.20594166964292526,
|
|
"num_tokens": 19011088.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.1699967861175535,
|
|
"epoch": 0.8111971411554497,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004945753206022525,
|
|
"loss": 4.9655,
|
|
"mean_token_accuracy": 0.20013341754674913,
|
|
"num_tokens": 19025864.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.169614267349243,
|
|
"epoch": 0.8117927337701013,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004945660159660499,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.1953017607331276,
|
|
"num_tokens": 19039803.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.078014469146728,
|
|
"epoch": 0.8123883263847528,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945567034543712,
|
|
"loss": 4.9069,
|
|
"mean_token_accuracy": 0.20980737954378129,
|
|
"num_tokens": 19053784.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.161725854873657,
|
|
"epoch": 0.8129839189994044,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945473830675507,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.19564930647611617,
|
|
"num_tokens": 19068730.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.281051063537598,
|
|
"epoch": 0.813579511614056,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945380548059224,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.19808235466480256,
|
|
"num_tokens": 19082354.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.286688947677613,
|
|
"epoch": 0.8141751042287075,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004945287186698211,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.1937915563583374,
|
|
"num_tokens": 19095051.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.185162830352783,
|
|
"epoch": 0.8147706968433591,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004945193746595815,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.20006429702043532,
|
|
"num_tokens": 19110653.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.1859112739562985,
|
|
"epoch": 0.8153662894580107,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004945100227755389,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.19498492777347565,
|
|
"num_tokens": 19125112.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.2671980381011965,
|
|
"epoch": 0.8159618820726623,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004945006630180288,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.18735138475894927,
|
|
"num_tokens": 19140153.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.2187727928161625,
|
|
"epoch": 0.8165574746873139,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004944912953873865,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.19942758232355118,
|
|
"num_tokens": 19154423.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.1965680599212645,
|
|
"epoch": 0.8171530673019655,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004944819198839486,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.19912686944007874,
|
|
"num_tokens": 19169909.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.165954303741455,
|
|
"epoch": 0.817748659916617,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.000494472536508051,
|
|
"loss": 4.9519,
|
|
"mean_token_accuracy": 0.2020408555865288,
|
|
"num_tokens": 19184068.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.158046913146973,
|
|
"epoch": 0.8183442525312686,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004944631452600303,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.19725150465965272,
|
|
"num_tokens": 19199281.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.236583185195923,
|
|
"epoch": 0.8189398451459202,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004944537461402234,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.1877261593937874,
|
|
"num_tokens": 19213893.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.263673496246338,
|
|
"epoch": 0.8195354377605718,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004944443391489676,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.19104332476854324,
|
|
"num_tokens": 19227873.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.178918838500977,
|
|
"epoch": 0.8201310303752234,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004944349242865999,
|
|
"loss": 4.919,
|
|
"mean_token_accuracy": 0.21028520911931992,
|
|
"num_tokens": 19241287.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.185282135009766,
|
|
"epoch": 0.820726622989875,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004944255015534585,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.20108973383903503,
|
|
"num_tokens": 19255428.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.150266981124878,
|
|
"epoch": 0.8213222156045265,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000494416070949881,
|
|
"loss": 4.9167,
|
|
"mean_token_accuracy": 0.2015451192855835,
|
|
"num_tokens": 19268234.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.187671804428101,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004944066324762058,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.19600512981414794,
|
|
"num_tokens": 19281443.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.202685546875,
|
|
"epoch": 0.8225134008338296,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004943971861327713,
|
|
"loss": 4.8924,
|
|
"mean_token_accuracy": 0.20731243193149568,
|
|
"num_tokens": 19293791.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.170107316970825,
|
|
"epoch": 0.8231089934484812,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004943877319199167,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.20116084963083267,
|
|
"num_tokens": 19305634.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.2271058559417725,
|
|
"epoch": 0.8237045860631328,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004943782698379807,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.189031483232975,
|
|
"num_tokens": 19319719.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.142617654800415,
|
|
"epoch": 0.8243001786777844,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004943687998873029,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.21468710154294968,
|
|
"num_tokens": 19333596.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.117456674575806,
|
|
"epoch": 0.824895771292436,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004943593220682229,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.19865041077136994,
|
|
"num_tokens": 19347750.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.147422742843628,
|
|
"epoch": 0.8254913639070875,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004943498363810807,
|
|
"loss": 4.904,
|
|
"mean_token_accuracy": 0.2047455295920372,
|
|
"num_tokens": 19360584.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.156736135482788,
|
|
"epoch": 0.8260869565217391,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004943403428262164,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.20417164266109467,
|
|
"num_tokens": 19375113.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.157262849807739,
|
|
"epoch": 0.8266825491363907,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004943308414039708,
|
|
"loss": 5.0126,
|
|
"mean_token_accuracy": 0.18991622924804688,
|
|
"num_tokens": 19387748.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.249469947814942,
|
|
"epoch": 0.8272781417510423,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004943213321146843,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.19418000131845475,
|
|
"num_tokens": 19404374.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.163524341583252,
|
|
"epoch": 0.8278737343656939,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004943118149586984,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.20486054122447966,
|
|
"num_tokens": 19419209.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.143970251083374,
|
|
"epoch": 0.8284693269803455,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004943022899363542,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.2001874938607216,
|
|
"num_tokens": 19433127.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.205447244644165,
|
|
"epoch": 0.8290649195949971,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004942927570479934,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.19444992691278457,
|
|
"num_tokens": 19447718.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.160541296005249,
|
|
"epoch": 0.8296605122096486,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004942832162939581,
|
|
"loss": 4.8948,
|
|
"mean_token_accuracy": 0.2041360393166542,
|
|
"num_tokens": 19459193.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.106111240386963,
|
|
"epoch": 0.8302561048243002,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004942736676745902,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.19808810949325562,
|
|
"num_tokens": 19472791.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.265562295913696,
|
|
"epoch": 0.8308516974389517,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004942641111902324,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.19660953283309937,
|
|
"num_tokens": 19484903.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.1872107028961185,
|
|
"epoch": 0.8314472900536033,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004942545468412275,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.19705149233341218,
|
|
"num_tokens": 19499833.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.127726268768311,
|
|
"epoch": 0.8320428826682549,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004942449746279184,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.20868579298257828,
|
|
"num_tokens": 19511744.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.159153270721435,
|
|
"epoch": 0.8326384752829065,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004942353945506485,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.2082059934735298,
|
|
"num_tokens": 19525192.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.098970031738281,
|
|
"epoch": 0.833234067897558,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004942258066097617,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.1946823239326477,
|
|
"num_tokens": 19539397.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.129020690917969,
|
|
"epoch": 0.8338296605122096,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004942162108056015,
|
|
"loss": 4.9084,
|
|
"mean_token_accuracy": 0.2096063643693924,
|
|
"num_tokens": 19554322.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.234167671203613,
|
|
"epoch": 0.8344252531268612,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004942066071385122,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.1922169119119644,
|
|
"num_tokens": 19567652.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.204717206954956,
|
|
"epoch": 0.8350208457415128,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004941969956088383,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.19228022992610933,
|
|
"num_tokens": 19582921.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.181436681747437,
|
|
"epoch": 0.8356164383561644,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004941873762169246,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.19572365880012513,
|
|
"num_tokens": 19597298.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.2012396335601805,
|
|
"epoch": 0.836212030970816,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004941777489631161,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.19664670526981354,
|
|
"num_tokens": 19611200.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.181854581832885,
|
|
"epoch": 0.8368076235854676,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004941681138477582,
|
|
"loss": 4.8497,
|
|
"mean_token_accuracy": 0.20953864455223084,
|
|
"num_tokens": 19623910.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.102773571014405,
|
|
"epoch": 0.8374032162001191,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004941584708711962,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.2057928204536438,
|
|
"num_tokens": 19638308.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.123822975158691,
|
|
"epoch": 0.8379988088147707,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004941488200337763,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.19732289314270018,
|
|
"num_tokens": 19652987.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.199441432952881,
|
|
"epoch": 0.8385944014294223,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004941391613358444,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.1936160981655121,
|
|
"num_tokens": 19667789.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.234569692611695,
|
|
"epoch": 0.8391899940440739,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004941294947777473,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.19623250514268875,
|
|
"num_tokens": 19682775.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.211414480209351,
|
|
"epoch": 0.8397855866587254,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004941198203598314,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.20020330399274827,
|
|
"num_tokens": 19696714.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.130775690078735,
|
|
"epoch": 0.840381179273377,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004941101380824438,
|
|
"loss": 4.9167,
|
|
"mean_token_accuracy": 0.20109327435493468,
|
|
"num_tokens": 19711132.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.087300062179565,
|
|
"epoch": 0.8409767718880286,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004941004479459318,
|
|
"loss": 4.8234,
|
|
"mean_token_accuracy": 0.2063111647963524,
|
|
"num_tokens": 19726680.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.1805281162261965,
|
|
"epoch": 0.8415723645026801,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000494090749950643,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.1980413392186165,
|
|
"num_tokens": 19740152.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.214729833602905,
|
|
"epoch": 0.8421679571173317,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004940810440969253,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.19330805242061616,
|
|
"num_tokens": 19756233.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.128584480285644,
|
|
"epoch": 0.8427635497319833,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004940713303851265,
|
|
"loss": 4.862,
|
|
"mean_token_accuracy": 0.20172089338302612,
|
|
"num_tokens": 19771178.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.271034145355225,
|
|
"epoch": 0.8433591423466349,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004940616088155954,
|
|
"loss": 4.9724,
|
|
"mean_token_accuracy": 0.19161928147077562,
|
|
"num_tokens": 19786180.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.068975162506104,
|
|
"epoch": 0.8439547349612865,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004940518793886807,
|
|
"loss": 4.8505,
|
|
"mean_token_accuracy": 0.2094910353422165,
|
|
"num_tokens": 19800472.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.138592290878296,
|
|
"epoch": 0.8445503275759381,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004940421421047311,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.20622486025094985,
|
|
"num_tokens": 19816060.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.172881746292115,
|
|
"epoch": 0.8451459201905897,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000494032396964096,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.20144321769475937,
|
|
"num_tokens": 19832219.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.087926578521729,
|
|
"epoch": 0.8457415128052412,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000494022643967125,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.21398750841617584,
|
|
"num_tokens": 19844913.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.176878929138184,
|
|
"epoch": 0.8463371054198928,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004940128831141679,
|
|
"loss": 4.9235,
|
|
"mean_token_accuracy": 0.19802037328481675,
|
|
"num_tokens": 19858375.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.213673067092896,
|
|
"epoch": 0.8469326980345444,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004940031144055747,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.19598734229803086,
|
|
"num_tokens": 19872004.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.163327646255493,
|
|
"epoch": 0.847528290649196,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004939933378416959,
|
|
"loss": 4.8838,
|
|
"mean_token_accuracy": 0.19919876307249068,
|
|
"num_tokens": 19886340.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.198000764846801,
|
|
"epoch": 0.8481238832638476,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004939835534228821,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.2045590192079544,
|
|
"num_tokens": 19899185.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.199259424209595,
|
|
"epoch": 0.848719475878499,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004939737611494842,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.18782405257225038,
|
|
"num_tokens": 19912886.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.214553546905518,
|
|
"epoch": 0.8493150684931506,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004939639610218536,
|
|
"loss": 4.9773,
|
|
"mean_token_accuracy": 0.18926315903663635,
|
|
"num_tokens": 19927780.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.168109989166259,
|
|
"epoch": 0.8499106611078022,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004939541530403419,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.2045607641339302,
|
|
"num_tokens": 19940181.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.12690110206604,
|
|
"epoch": 0.8505062537224538,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004939443372053004,
|
|
"loss": 4.8973,
|
|
"mean_token_accuracy": 0.19709809273481368,
|
|
"num_tokens": 19952823.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.1767298698425295,
|
|
"epoch": 0.8511018463371054,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004939345135170818,
|
|
"loss": 5.0344,
|
|
"mean_token_accuracy": 0.1882709965109825,
|
|
"num_tokens": 19966528.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.248154973983764,
|
|
"epoch": 0.851697438951757,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000493924681976038,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.19386336505413054,
|
|
"num_tokens": 19981259.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.146277952194214,
|
|
"epoch": 0.8522930315664086,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004939148425825219,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.20037278681993484,
|
|
"num_tokens": 19995096.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.142520809173584,
|
|
"epoch": 0.8528886241810602,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004939049953368863,
|
|
"loss": 4.9401,
|
|
"mean_token_accuracy": 0.19382059276103974,
|
|
"num_tokens": 20008895.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.219720888137817,
|
|
"epoch": 0.8534842167957117,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004938951402394844,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.19996455311775208,
|
|
"num_tokens": 20023506.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.1646040916442875,
|
|
"epoch": 0.8540798094103633,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004938852772906697,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.19635888934135437,
|
|
"num_tokens": 20036810.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.16309552192688,
|
|
"epoch": 0.8546754020250149,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004938754064907961,
|
|
"loss": 4.8525,
|
|
"mean_token_accuracy": 0.20518708378076553,
|
|
"num_tokens": 20050653.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.149541807174683,
|
|
"epoch": 0.8552709946396665,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004938655278402175,
|
|
"loss": 4.9153,
|
|
"mean_token_accuracy": 0.20307961106300354,
|
|
"num_tokens": 20065361.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.082183408737182,
|
|
"epoch": 0.8558665872543181,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004938556413392882,
|
|
"loss": 4.8699,
|
|
"mean_token_accuracy": 0.21139221340417863,
|
|
"num_tokens": 20079160.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.169384002685547,
|
|
"epoch": 0.8564621798689697,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004938457469883629,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.20199144780635833,
|
|
"num_tokens": 20095036.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.114953184127808,
|
|
"epoch": 0.8570577724836212,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004938358447877966,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.2067757472395897,
|
|
"num_tokens": 20112319.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.164311027526855,
|
|
"epoch": 0.8576533650982728,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004938259347379442,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.19935424029827117,
|
|
"num_tokens": 20126683.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.1974780559539795,
|
|
"epoch": 0.8582489577129243,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004938160168391614,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.19651492834091186,
|
|
"num_tokens": 20142016.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.134807586669922,
|
|
"epoch": 0.8588445503275759,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004938060910918038,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.20476272106170654,
|
|
"num_tokens": 20156199.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.2619225025177006,
|
|
"epoch": 0.8594401429422275,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004937961574962274,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.1910216599702835,
|
|
"num_tokens": 20169443.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.129044389724731,
|
|
"epoch": 0.8600357355568791,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004937862160527887,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.20377827137708665,
|
|
"num_tokens": 20184187.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.1636748790740965,
|
|
"epoch": 0.8606313281715307,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004937762667618441,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.20472845137119294,
|
|
"num_tokens": 20198217.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.1480090618133545,
|
|
"epoch": 0.8612269207861822,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004937663096237505,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.20224204063415527,
|
|
"num_tokens": 20214253.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.123743629455566,
|
|
"epoch": 0.8618225134008338,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004937563446388652,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.20535139888525009,
|
|
"num_tokens": 20227880.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.055837774276734,
|
|
"epoch": 0.8624181060154854,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004937463718075453,
|
|
"loss": 4.8437,
|
|
"mean_token_accuracy": 0.21040962487459183,
|
|
"num_tokens": 20242642.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.088917875289917,
|
|
"epoch": 0.863013698630137,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004937363911301488,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.20503964573144912,
|
|
"num_tokens": 20255950.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.174100875854492,
|
|
"epoch": 0.8636092912447886,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004937264026070336,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.20366551131010055,
|
|
"num_tokens": 20270067.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.286001205444336,
|
|
"epoch": 0.8642048838594402,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000493716406238558,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.19882625937461854,
|
|
"num_tokens": 20283326.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.100559520721435,
|
|
"epoch": 0.8648004764740918,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004937064020250804,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.20179162919521332,
|
|
"num_tokens": 20296161.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.090710783004761,
|
|
"epoch": 0.8653960690887433,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004936963899669599,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.1996309846639633,
|
|
"num_tokens": 20310662.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.192110443115235,
|
|
"epoch": 0.8659916617033949,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004936863700645554,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.19874917715787888,
|
|
"num_tokens": 20324381.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.146421813964844,
|
|
"epoch": 0.8665872543180465,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004936763423182264,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.19659116715192795,
|
|
"num_tokens": 20338093.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.152958011627197,
|
|
"epoch": 0.867182846932698,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004936663067283325,
|
|
"loss": 4.8647,
|
|
"mean_token_accuracy": 0.20840763300657272,
|
|
"num_tokens": 20350534.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.094810867309571,
|
|
"epoch": 0.8677784395473496,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004936562632952337,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.20936393439769746,
|
|
"num_tokens": 20364230.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.2586547374725345,
|
|
"epoch": 0.8683740321620012,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004936462120192903,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.18948373794555665,
|
|
"num_tokens": 20380605.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.204036092758178,
|
|
"epoch": 0.8689696247766527,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004936361529008627,
|
|
"loss": 4.9727,
|
|
"mean_token_accuracy": 0.1979580357670784,
|
|
"num_tokens": 20392760.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.137707948684692,
|
|
"epoch": 0.8695652173913043,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004936260859403119,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.2031350091099739,
|
|
"num_tokens": 20408519.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.121989727020264,
|
|
"epoch": 0.8701608100059559,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004936160111379987,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.20652975291013717,
|
|
"num_tokens": 20421322.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.157418584823608,
|
|
"epoch": 0.8707564026206075,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004936059284942848,
|
|
"loss": 4.9231,
|
|
"mean_token_accuracy": 0.19750603586435317,
|
|
"num_tokens": 20436056.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.126880168914795,
|
|
"epoch": 0.8713519952352591,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004935958380095316,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.19979116916656495,
|
|
"num_tokens": 20449268.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.188067245483398,
|
|
"epoch": 0.8719475878499107,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000493585739684101,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.2011038437485695,
|
|
"num_tokens": 20462635.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.151953268051147,
|
|
"epoch": 0.8725431804645623,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004935756335183554,
|
|
"loss": 4.8944,
|
|
"mean_token_accuracy": 0.2064547762274742,
|
|
"num_tokens": 20476048.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.117564678192139,
|
|
"epoch": 0.8731387730792138,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004935655195126572,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.20720231682062148,
|
|
"num_tokens": 20488856.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.114104700088501,
|
|
"epoch": 0.8737343656938654,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004935553976673692,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.20091983824968337,
|
|
"num_tokens": 20503426.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.19834270477295,
|
|
"epoch": 0.874329958308517,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004935452679828545,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.1985922411084175,
|
|
"num_tokens": 20518305.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.104052448272705,
|
|
"epoch": 0.8749255509231686,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004935351304594763,
|
|
"loss": 4.8628,
|
|
"mean_token_accuracy": 0.20786418169736862,
|
|
"num_tokens": 20532310.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.160271310806275,
|
|
"epoch": 0.8755211435378202,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004935249850975983,
|
|
"loss": 4.9447,
|
|
"mean_token_accuracy": 0.19921597093343735,
|
|
"num_tokens": 20546149.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.17770619392395,
|
|
"epoch": 0.8761167361524718,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004935148318975843,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.20873825401067733,
|
|
"num_tokens": 20560077.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.260556268692016,
|
|
"epoch": 0.8767123287671232,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004935046708597986,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.19336255937814711,
|
|
"num_tokens": 20574657.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.100927400588989,
|
|
"epoch": 0.8773079213817748,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004934945019846057,
|
|
"loss": 4.8254,
|
|
"mean_token_accuracy": 0.20545119196176528,
|
|
"num_tokens": 20587091.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.137057495117188,
|
|
"epoch": 0.8779035139964264,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004934843252723702,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.2046142727136612,
|
|
"num_tokens": 20600537.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.229600524902343,
|
|
"epoch": 0.878499106611078,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004934741407234572,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.19335699826478958,
|
|
"num_tokens": 20614029.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.155656051635742,
|
|
"epoch": 0.8790946992257296,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000493463948338232,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.2026839792728424,
|
|
"num_tokens": 20627906.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.165369653701783,
|
|
"epoch": 0.8796902918403812,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004934537481170602,
|
|
"loss": 4.8923,
|
|
"mean_token_accuracy": 0.1987556606531143,
|
|
"num_tokens": 20642717.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.13789005279541,
|
|
"epoch": 0.8802858844550328,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004934435400603077,
|
|
"loss": 4.9127,
|
|
"mean_token_accuracy": 0.1991451248526573,
|
|
"num_tokens": 20657234.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.15365080833435,
|
|
"epoch": 0.8808814770696843,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004934333241683404,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.20178160518407823,
|
|
"num_tokens": 20672162.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.247027063369751,
|
|
"epoch": 0.8814770696843359,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004934231004415251,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.20047924369573594,
|
|
"num_tokens": 20684565.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.211897325515747,
|
|
"epoch": 0.8820726622989875,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004934128688802282,
|
|
"loss": 5.0113,
|
|
"mean_token_accuracy": 0.19821293652057648,
|
|
"num_tokens": 20699931.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.171431970596314,
|
|
"epoch": 0.8826682549136391,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004934026294848168,
|
|
"loss": 4.9338,
|
|
"mean_token_accuracy": 0.20023156255483626,
|
|
"num_tokens": 20715031.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.155258369445801,
|
|
"epoch": 0.8832638475282907,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004933923822556583,
|
|
"loss": 4.9342,
|
|
"mean_token_accuracy": 0.19958258420228958,
|
|
"num_tokens": 20730825.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.219849967956543,
|
|
"epoch": 0.8838594401429423,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.00049338212719312,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.2013201117515564,
|
|
"num_tokens": 20743287.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.18552598953247,
|
|
"epoch": 0.8844550327575939,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.00049337186429757,
|
|
"loss": 4.9482,
|
|
"mean_token_accuracy": 0.19571833163499833,
|
|
"num_tokens": 20759911.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.114535856246948,
|
|
"epoch": 0.8850506253722454,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004933615935693762,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.20583552718162537,
|
|
"num_tokens": 20772842.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.214235925674439,
|
|
"epoch": 0.8856462179868969,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004933513150089069,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.193477301299572,
|
|
"num_tokens": 20787524.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.122951555252075,
|
|
"epoch": 0.8862418106015485,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004933410286165311,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.21194293051958085,
|
|
"num_tokens": 20800332.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.158557462692261,
|
|
"epoch": 0.8868374032162001,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004933307343926177,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.20811442285776138,
|
|
"num_tokens": 20813231.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.222035217285156,
|
|
"epoch": 0.8874329958308517,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004933204323375358,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.1982417270541191,
|
|
"num_tokens": 20827116.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.271926307678223,
|
|
"epoch": 0.8880285884455033,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000493310122451655,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.19548407196998596,
|
|
"num_tokens": 20838536.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.104053497314453,
|
|
"epoch": 0.8886241810601548,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004932998047353449,
|
|
"loss": 4.8425,
|
|
"mean_token_accuracy": 0.21043538749217988,
|
|
"num_tokens": 20850849.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.128205156326294,
|
|
"epoch": 0.8892197736748064,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004932894791889759,
|
|
"loss": 4.8982,
|
|
"mean_token_accuracy": 0.20407332479953766,
|
|
"num_tokens": 20866140.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.147731113433838,
|
|
"epoch": 0.889815366289458,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004932791458129181,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.20002410113811492,
|
|
"num_tokens": 20879458.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.124208593368531,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004932688046075422,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.20428954511880876,
|
|
"num_tokens": 20893516.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.2379045486450195,
|
|
"epoch": 0.8910065515187612,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004932584555732192,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.190228471159935,
|
|
"num_tokens": 20908713.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.192844724655151,
|
|
"epoch": 0.8916021441334128,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004932480987103204,
|
|
"loss": 4.9157,
|
|
"mean_token_accuracy": 0.20541791766881942,
|
|
"num_tokens": 20922080.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.1689728736877445,
|
|
"epoch": 0.8921977367480644,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004932377340192169,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.19958229064941407,
|
|
"num_tokens": 20935484.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.2711019039154055,
|
|
"epoch": 0.8927933293627159,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004932273615002809,
|
|
"loss": 4.9981,
|
|
"mean_token_accuracy": 0.19082930386066438,
|
|
"num_tokens": 20948851.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.131562232971191,
|
|
"epoch": 0.8933889219773675,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004932169811538843,
|
|
"loss": 4.9443,
|
|
"mean_token_accuracy": 0.2004090815782547,
|
|
"num_tokens": 20961637.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.240088176727295,
|
|
"epoch": 0.8939845145920191,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004932065929803993,
|
|
"loss": 5.0025,
|
|
"mean_token_accuracy": 0.1903009831905365,
|
|
"num_tokens": 20976236.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.160513067245484,
|
|
"epoch": 0.8945801072066706,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004931961969801985,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.20021743029356004,
|
|
"num_tokens": 20990439.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.187777423858643,
|
|
"epoch": 0.8951756998213222,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000493185793153655,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.20091027468442918,
|
|
"num_tokens": 21003632.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.135032033920288,
|
|
"epoch": 0.8957712924359738,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004931753815011419,
|
|
"loss": 4.8909,
|
|
"mean_token_accuracy": 0.2077113837003708,
|
|
"num_tokens": 21017685.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.116024160385132,
|
|
"epoch": 0.8963668850506253,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004931649620230325,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.2107477754354477,
|
|
"num_tokens": 21029720.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.122563362121582,
|
|
"epoch": 0.8969624776652769,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004931545347197006,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.20440852344036103,
|
|
"num_tokens": 21044148.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.216667938232422,
|
|
"epoch": 0.8975580702799285,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004931440995915203,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.20074666291475296,
|
|
"num_tokens": 21059278.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.103487396240235,
|
|
"epoch": 0.8981536628945801,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004931336566388658,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.20388510078191757,
|
|
"num_tokens": 21074258.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.192672777175903,
|
|
"epoch": 0.8987492555092317,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004931232058621117,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.19489986896514894,
|
|
"num_tokens": 21087283.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.220127010345459,
|
|
"epoch": 0.8993448481238833,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004931127472616328,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.20450807958841324,
|
|
"num_tokens": 21101461.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.177894258499146,
|
|
"epoch": 0.8999404407385349,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004931022808378044,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.2034042075276375,
|
|
"num_tokens": 21115067.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.151477956771851,
|
|
"epoch": 0.9005360333531864,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004930918065910018,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.20054860264062882,
|
|
"num_tokens": 21129029.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.201594495773316,
|
|
"epoch": 0.901131625967838,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004930813245216005,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.19962978810071946,
|
|
"num_tokens": 21142037.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.170756387710571,
|
|
"epoch": 0.9017272185824896,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004930708346299769,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.20054658651351928,
|
|
"num_tokens": 21157036.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.19022388458252,
|
|
"epoch": 0.9023228111971412,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004930603369165069,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.19947717785835267,
|
|
"num_tokens": 21170025.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.177037954330444,
|
|
"epoch": 0.9029184038117928,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004930498313815672,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.20403429865837097,
|
|
"num_tokens": 21183664.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.0528747081756595,
|
|
"epoch": 0.9035139964264444,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004930393180255345,
|
|
"loss": 4.8431,
|
|
"mean_token_accuracy": 0.2092731177806854,
|
|
"num_tokens": 21198299.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.103593111038208,
|
|
"epoch": 0.9041095890410958,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000493028796848786,
|
|
"loss": 4.789,
|
|
"mean_token_accuracy": 0.21420642137527465,
|
|
"num_tokens": 21210133.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.174817132949829,
|
|
"epoch": 0.9047051816557474,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004930182678516992,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.20276188403367995,
|
|
"num_tokens": 21225813.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.274481582641601,
|
|
"epoch": 0.905300774270399,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004930077310346515,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.19923958033323289,
|
|
"num_tokens": 21238602.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.164350843429565,
|
|
"epoch": 0.9058963668850506,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004929971863980209,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.199314646422863,
|
|
"num_tokens": 21254367.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.241876888275146,
|
|
"epoch": 0.9064919594997022,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004929866339421857,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.19825731366872787,
|
|
"num_tokens": 21268285.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.101060009002685,
|
|
"epoch": 0.9070875521143538,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004929760736675243,
|
|
"loss": 4.9041,
|
|
"mean_token_accuracy": 0.1980912819504738,
|
|
"num_tokens": 21282398.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.208746290206909,
|
|
"epoch": 0.9076831447290054,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004929655055744157,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.19202795177698134,
|
|
"num_tokens": 21296991.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.198200225830078,
|
|
"epoch": 0.9082787373436569,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004929549296632387,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.19940607398748397,
|
|
"num_tokens": 21313677.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.151069641113281,
|
|
"epoch": 0.9088743299583085,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004929443459343728,
|
|
"loss": 4.8937,
|
|
"mean_token_accuracy": 0.20646460205316544,
|
|
"num_tokens": 21325252.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.1430309295654295,
|
|
"epoch": 0.9094699225729601,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004929337543881975,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.20131825357675553,
|
|
"num_tokens": 21341771.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.201722908020019,
|
|
"epoch": 0.9100655151876117,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004929231550250927,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.20166292786598206,
|
|
"num_tokens": 21356029.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.27152943611145,
|
|
"epoch": 0.9106611078022633,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004929125478454389,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.20222508907318115,
|
|
"num_tokens": 21369943.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.218910837173462,
|
|
"epoch": 0.9112567004169149,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004929019328496161,
|
|
"loss": 4.9696,
|
|
"mean_token_accuracy": 0.20571470260620117,
|
|
"num_tokens": 21385078.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.071431398391724,
|
|
"epoch": 0.9118522930315665,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004928913100380053,
|
|
"loss": 4.7232,
|
|
"mean_token_accuracy": 0.21606407612562178,
|
|
"num_tokens": 21398249.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.129451608657837,
|
|
"epoch": 0.912447885646218,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004928806794109875,
|
|
"loss": 4.9614,
|
|
"mean_token_accuracy": 0.20498874336481093,
|
|
"num_tokens": 21414773.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.247469472885132,
|
|
"epoch": 0.9130434782608695,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000492870040968944,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.19853055626153945,
|
|
"num_tokens": 21428551.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.154452705383301,
|
|
"epoch": 0.9136390708755211,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004928593947122564,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.19509592801332473,
|
|
"num_tokens": 21442916.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.194934225082397,
|
|
"epoch": 0.9142346634901727,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004928487406413065,
|
|
"loss": 4.895,
|
|
"mean_token_accuracy": 0.2002209261059761,
|
|
"num_tokens": 21457686.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.195427083969117,
|
|
"epoch": 0.9148302561048243,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004928380787564764,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.20670426338911058,
|
|
"num_tokens": 21473503.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.1257812023162845,
|
|
"epoch": 0.9154258487194759,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004928274090581486,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.20538197010755538,
|
|
"num_tokens": 21486362.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.096245050430298,
|
|
"epoch": 0.9160214413341274,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004928167315467059,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.20149521082639693,
|
|
"num_tokens": 21500445.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.18103985786438,
|
|
"epoch": 0.916617033948779,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004928060462225312,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.19944300055503844,
|
|
"num_tokens": 21513648.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.183280992507934,
|
|
"epoch": 0.9172126265634306,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004927953530860077,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.2016470417380333,
|
|
"num_tokens": 21528103.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.153290796279907,
|
|
"epoch": 0.9178082191780822,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004927846521375189,
|
|
"loss": 4.8477,
|
|
"mean_token_accuracy": 0.2130131796002388,
|
|
"num_tokens": 21542435.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.182994031906128,
|
|
"epoch": 0.9184038117927338,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004927739433774489,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.20480589866638182,
|
|
"num_tokens": 21557993.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.163361549377441,
|
|
"epoch": 0.9189994044073854,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004927632268061815,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.20079663693904876,
|
|
"num_tokens": 21573383.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.187111043930054,
|
|
"epoch": 0.919594997022037,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004927525024241013,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.2092558667063713,
|
|
"num_tokens": 21588179.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.133381319046021,
|
|
"epoch": 0.9201905896366885,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004927417702315928,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.2013625204563141,
|
|
"num_tokens": 21603595.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.184838962554932,
|
|
"epoch": 0.9207861822513401,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004927310302290411,
|
|
"loss": 4.934,
|
|
"mean_token_accuracy": 0.20356503278017044,
|
|
"num_tokens": 21618487.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.1615783214569095,
|
|
"epoch": 0.9213817748659917,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004927202824168313,
|
|
"loss": 4.8496,
|
|
"mean_token_accuracy": 0.2036508470773697,
|
|
"num_tokens": 21632970.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.184818267822266,
|
|
"epoch": 0.9219773674806433,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000492709526795349,
|
|
"loss": 4.9124,
|
|
"mean_token_accuracy": 0.2016807332634926,
|
|
"num_tokens": 21645943.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.139384031295776,
|
|
"epoch": 0.9225729600952948,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049269876336498,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.2088763028383255,
|
|
"num_tokens": 21658028.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.161565542221069,
|
|
"epoch": 0.9231685527099464,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004926879921261101,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.2042483150959015,
|
|
"num_tokens": 21672265.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.100625848770141,
|
|
"epoch": 0.9237641453245979,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004926772130791261,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.20385824888944626,
|
|
"num_tokens": 21685871.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.0828193664550785,
|
|
"epoch": 0.9243597379392495,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004926664262244143,
|
|
"loss": 4.7921,
|
|
"mean_token_accuracy": 0.21346231997013093,
|
|
"num_tokens": 21699783.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.171153736114502,
|
|
"epoch": 0.9249553305539011,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004926556315623617,
|
|
"loss": 4.9127,
|
|
"mean_token_accuracy": 0.2048138976097107,
|
|
"num_tokens": 21716144.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.198909902572632,
|
|
"epoch": 0.9255509231685527,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004926448290933555,
|
|
"loss": 4.9085,
|
|
"mean_token_accuracy": 0.20456106215715408,
|
|
"num_tokens": 21727334.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.187424278259277,
|
|
"epoch": 0.9261465157832043,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004926340188177831,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.1996648922562599,
|
|
"num_tokens": 21740989.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.183287763595581,
|
|
"epoch": 0.9267421083978559,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004926232007360324,
|
|
"loss": 4.9556,
|
|
"mean_token_accuracy": 0.19798339605331422,
|
|
"num_tokens": 21756776.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.2097574234008786,
|
|
"epoch": 0.9273377010125075,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004926123748484911,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.20227449536323547,
|
|
"num_tokens": 21771864.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.139037942886352,
|
|
"epoch": 0.927933293627159,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000492601541155548,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.20507404953241348,
|
|
"num_tokens": 21785161.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.23163743019104,
|
|
"epoch": 0.9285288862418106,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004925906996575912,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.18925505131483078,
|
|
"num_tokens": 21799350.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.224358797073364,
|
|
"epoch": 0.9291244788564622,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004925798503550099,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.20562706142663956,
|
|
"num_tokens": 21813925.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.138200855255127,
|
|
"epoch": 0.9297200714711138,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004925689932481931,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.20111260414123536,
|
|
"num_tokens": 21828356.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.07058892250061,
|
|
"epoch": 0.9303156640857654,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004925581283375303,
|
|
"loss": 4.7595,
|
|
"mean_token_accuracy": 0.21321394592523574,
|
|
"num_tokens": 21842667.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.176006269454956,
|
|
"epoch": 0.930911256700417,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004925472556234111,
|
|
"loss": 4.9432,
|
|
"mean_token_accuracy": 0.201265449821949,
|
|
"num_tokens": 21856116.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.176999425888061,
|
|
"epoch": 0.9315068493150684,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004925363751062256,
|
|
"loss": 4.9123,
|
|
"mean_token_accuracy": 0.20339296013116837,
|
|
"num_tokens": 21870630.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.223974084854126,
|
|
"epoch": 0.93210244192972,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000492525486786364,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.20349437594413758,
|
|
"num_tokens": 21884982.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.122536039352417,
|
|
"epoch": 0.9326980345443716,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004925145906642169,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.2069467067718506,
|
|
"num_tokens": 21899301.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.1309592723846436,
|
|
"epoch": 0.9332936271590232,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004925036867401751,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.20727040022611617,
|
|
"num_tokens": 21913903.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.116994857788086,
|
|
"epoch": 0.9338892197736748,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004924927750146296,
|
|
"loss": 4.8787,
|
|
"mean_token_accuracy": 0.20629644095897676,
|
|
"num_tokens": 21930123.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.121788883209229,
|
|
"epoch": 0.9344848123883264,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004924818554879718,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.2012730970978737,
|
|
"num_tokens": 21945164.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.1744256019592285,
|
|
"epoch": 0.935080405002978,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004924709281605938,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.19980432689189911,
|
|
"num_tokens": 21959341.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.1632630825042725,
|
|
"epoch": 0.9356759976176295,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004924599930328869,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.2094835564494133,
|
|
"num_tokens": 21973049.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.084960794448852,
|
|
"epoch": 0.9362715902322811,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004924490501052437,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.21566962599754333,
|
|
"num_tokens": 21985604.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.212312459945679,
|
|
"epoch": 0.9368671828469327,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004924380993780566,
|
|
"loss": 4.9563,
|
|
"mean_token_accuracy": 0.1968146815896034,
|
|
"num_tokens": 22000472.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.18281512260437,
|
|
"epoch": 0.9374627754615843,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004924271408517185,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.20772419422864913,
|
|
"num_tokens": 22014162.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.190010690689087,
|
|
"epoch": 0.9380583680762359,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004924161745266222,
|
|
"loss": 4.9071,
|
|
"mean_token_accuracy": 0.19506201446056365,
|
|
"num_tokens": 22026832.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.054138278961181,
|
|
"epoch": 0.9386539606908875,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004924052004031613,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.2083499699831009,
|
|
"num_tokens": 22038816.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.227738666534424,
|
|
"epoch": 0.939249553305539,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004923942184817293,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.19772869348526,
|
|
"num_tokens": 22053356.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.125162363052368,
|
|
"epoch": 0.9398451459201906,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004923832287627202,
|
|
"loss": 4.8904,
|
|
"mean_token_accuracy": 0.19789994657039642,
|
|
"num_tokens": 22066879.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.159626722335815,
|
|
"epoch": 0.9404407385348421,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004923722312465281,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.199508199095726,
|
|
"num_tokens": 22081036.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.206025695800781,
|
|
"epoch": 0.9410363311494937,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004923612259335476,
|
|
"loss": 4.969,
|
|
"mean_token_accuracy": 0.19389960616827012,
|
|
"num_tokens": 22095609.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.12523889541626,
|
|
"epoch": 0.9416319237641453,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923502128241732,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.20452393293380738,
|
|
"num_tokens": 22107539.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.124048519134521,
|
|
"epoch": 0.9422275163787969,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004923391919188001,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.210932220518589,
|
|
"num_tokens": 22120438.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.172843074798584,
|
|
"epoch": 0.9428231089934485,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004923281632178236,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.19242430180311204,
|
|
"num_tokens": 22134796.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.209022855758667,
|
|
"epoch": 0.9434187016081,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004923171267216392,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.19904885292053223,
|
|
"num_tokens": 22149178.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.138788652420044,
|
|
"epoch": 0.9440142942227516,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004923060824306428,
|
|
"loss": 4.9434,
|
|
"mean_token_accuracy": 0.20030947178602218,
|
|
"num_tokens": 22163652.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.236685705184937,
|
|
"epoch": 0.9446098868374032,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004922950303452306,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.19679114669561387,
|
|
"num_tokens": 22178116.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.126060247421265,
|
|
"epoch": 0.9452054794520548,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004922839704657988,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.21089723110198974,
|
|
"num_tokens": 22191750.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.199862337112426,
|
|
"epoch": 0.9458010720667064,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004922729027927444,
|
|
"loss": 4.9302,
|
|
"mean_token_accuracy": 0.20172469615936278,
|
|
"num_tokens": 22204889.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.143636226654053,
|
|
"epoch": 0.946396664681358,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004922618273264642,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.2046049192547798,
|
|
"num_tokens": 22218312.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.172827577590942,
|
|
"epoch": 0.9469922572960096,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004922507440673555,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.2017950162291527,
|
|
"num_tokens": 22232443.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.062731027603149,
|
|
"epoch": 0.9475878499106611,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004922396530158159,
|
|
"loss": 4.7096,
|
|
"mean_token_accuracy": 0.21881678104400634,
|
|
"num_tokens": 22245070.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.104772520065308,
|
|
"epoch": 0.9481834425253127,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004922285541722431,
|
|
"loss": 4.8364,
|
|
"mean_token_accuracy": 0.20839131325483323,
|
|
"num_tokens": 22257324.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.160326719284058,
|
|
"epoch": 0.9487790351399643,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004922174475370352,
|
|
"loss": 4.904,
|
|
"mean_token_accuracy": 0.2034693494439125,
|
|
"num_tokens": 22273438.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.172707223892212,
|
|
"epoch": 0.9493746277546159,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004922063331105907,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.20446984171867372,
|
|
"num_tokens": 22285824.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.055586528778076,
|
|
"epoch": 0.9499702203692674,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004921952108933083,
|
|
"loss": 4.842,
|
|
"mean_token_accuracy": 0.20966906398534774,
|
|
"num_tokens": 22299345.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.130138111114502,
|
|
"epoch": 0.950565812983919,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004921840808855865,
|
|
"loss": 4.8369,
|
|
"mean_token_accuracy": 0.2015565201640129,
|
|
"num_tokens": 22313684.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.178604507446289,
|
|
"epoch": 0.9511614055985705,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004921729430878252,
|
|
"loss": 4.9239,
|
|
"mean_token_accuracy": 0.20589034408330917,
|
|
"num_tokens": 22327474.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.164416885375976,
|
|
"epoch": 0.9517569982132221,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004921617975004233,
|
|
"loss": 4.9617,
|
|
"mean_token_accuracy": 0.19927801787853242,
|
|
"num_tokens": 22343026.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.142657518386841,
|
|
"epoch": 0.9523525908278737,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004921506441237809,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.2055016949772835,
|
|
"num_tokens": 22358734.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.155494213104248,
|
|
"epoch": 0.9529481834425253,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004921394829582979,
|
|
"loss": 4.8611,
|
|
"mean_token_accuracy": 0.20359614491462708,
|
|
"num_tokens": 22371840.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.081371641159057,
|
|
"epoch": 0.9535437760571769,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004921283140043748,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.2150975614786148,
|
|
"num_tokens": 22384450.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.0925039768219,
|
|
"epoch": 0.9541393686718285,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004921171372624121,
|
|
"loss": 4.8687,
|
|
"mean_token_accuracy": 0.20968499034643173,
|
|
"num_tokens": 22398988.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.09598298072815,
|
|
"epoch": 0.95473496128648,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004921059527328106,
|
|
"loss": 4.8209,
|
|
"mean_token_accuracy": 0.21253437995910646,
|
|
"num_tokens": 22411703.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.245681476593018,
|
|
"epoch": 0.9553305539011316,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004920947604159716,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.19802498668432236,
|
|
"num_tokens": 22427229.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.117247438430786,
|
|
"epoch": 0.9559261465157832,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004920835603122965,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.20804524123668672,
|
|
"num_tokens": 22439357.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.117840576171875,
|
|
"epoch": 0.9565217391304348,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004920723524221871,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.19851011633872986,
|
|
"num_tokens": 22453214.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.1265171527862545,
|
|
"epoch": 0.9571173317450864,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004920611367460453,
|
|
"loss": 4.8747,
|
|
"mean_token_accuracy": 0.20378010272979735,
|
|
"num_tokens": 22468030.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.207348346710205,
|
|
"epoch": 0.957712924359738,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004920499132842734,
|
|
"loss": 4.8642,
|
|
"mean_token_accuracy": 0.20335048139095308,
|
|
"num_tokens": 22481975.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.176688098907471,
|
|
"epoch": 0.9583085169743896,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004920386820372741,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.20494133681058885,
|
|
"num_tokens": 22495047.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.18166151046753,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004920274430054502,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.20546743720769883,
|
|
"num_tokens": 22509310.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.157048559188842,
|
|
"epoch": 0.9594997022036926,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004920161961892047,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.20335931777954103,
|
|
"num_tokens": 22525220.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.07274899482727,
|
|
"epoch": 0.9600952948183442,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004920049415889411,
|
|
"loss": 4.8186,
|
|
"mean_token_accuracy": 0.2204504758119583,
|
|
"num_tokens": 22538123.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.133922576904297,
|
|
"epoch": 0.9606908874329958,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004919936792050631,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.2025282561779022,
|
|
"num_tokens": 22552229.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.155880308151245,
|
|
"epoch": 0.9612864800476474,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004919824090379747,
|
|
"loss": 4.8679,
|
|
"mean_token_accuracy": 0.20475835353136063,
|
|
"num_tokens": 22566398.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.129514503479004,
|
|
"epoch": 0.961882072662299,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00049197113108808,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.20763185024261474,
|
|
"num_tokens": 22579736.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.047914457321167,
|
|
"epoch": 0.9624776652769506,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004919598453557836,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.2150944247841835,
|
|
"num_tokens": 22593325.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.1221473693847654,
|
|
"epoch": 0.9630732578916021,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004919485518414902,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.19957116693258287,
|
|
"num_tokens": 22607306.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.134184122085571,
|
|
"epoch": 0.9636688505062537,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004919372505456051,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.2082940384745598,
|
|
"num_tokens": 22620504.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.179799795150757,
|
|
"epoch": 0.9642644431209053,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004919259414685336,
|
|
"loss": 4.953,
|
|
"mean_token_accuracy": 0.1983841598033905,
|
|
"num_tokens": 22634097.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.225040245056152,
|
|
"epoch": 0.9648600357355569,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004919146246106812,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.1978405937552452,
|
|
"num_tokens": 22648457.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.166402196884155,
|
|
"epoch": 0.9654556283502085,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004919032999724539,
|
|
"loss": 4.8683,
|
|
"mean_token_accuracy": 0.20020982176065444,
|
|
"num_tokens": 22662128.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.058289861679077,
|
|
"epoch": 0.9660512209648601,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004918919675542579,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.2175946354866028,
|
|
"num_tokens": 22676085.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.160419607162476,
|
|
"epoch": 0.9666468135795117,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004918806273564996,
|
|
"loss": 4.8798,
|
|
"mean_token_accuracy": 0.20911625921726226,
|
|
"num_tokens": 22689672.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.180479860305786,
|
|
"epoch": 0.9672424061941632,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000491869279379586,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.2053300827741623,
|
|
"num_tokens": 22705240.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.123101758956909,
|
|
"epoch": 0.9678379988088148,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004918579236239238,
|
|
"loss": 4.9079,
|
|
"mean_token_accuracy": 0.20302197337150574,
|
|
"num_tokens": 22718532.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.135009717941284,
|
|
"epoch": 0.9684335914234663,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004918465600899205,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.19907732158899308,
|
|
"num_tokens": 22732146.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.144668054580689,
|
|
"epoch": 0.9690291840381179,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004918351887779837,
|
|
"loss": 4.8578,
|
|
"mean_token_accuracy": 0.20739332735538482,
|
|
"num_tokens": 22744590.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.146660947799683,
|
|
"epoch": 0.9696247766527695,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004918238096885213,
|
|
"loss": 4.8633,
|
|
"mean_token_accuracy": 0.202810201048851,
|
|
"num_tokens": 22758607.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.029603433609009,
|
|
"epoch": 0.9702203692674211,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004918124228219412,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.2115254133939743,
|
|
"num_tokens": 22771846.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.116102170944214,
|
|
"epoch": 0.9708159618820726,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004918010281786522,
|
|
"loss": 4.8221,
|
|
"mean_token_accuracy": 0.20801041275262833,
|
|
"num_tokens": 22784705.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.122978067398071,
|
|
"epoch": 0.9714115544967242,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004917896257590627,
|
|
"loss": 4.8673,
|
|
"mean_token_accuracy": 0.2069874107837677,
|
|
"num_tokens": 22799706.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.126592493057251,
|
|
"epoch": 0.9720071471113758,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004917782155635817,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.2016233429312706,
|
|
"num_tokens": 22813021.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.1057013988494875,
|
|
"epoch": 0.9726027397260274,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004917667975926187,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.20625873059034347,
|
|
"num_tokens": 22827936.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.189203834533691,
|
|
"epoch": 0.973198332340679,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004917553718465832,
|
|
"loss": 4.8969,
|
|
"mean_token_accuracy": 0.20302240252494813,
|
|
"num_tokens": 22842307.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.111174297332764,
|
|
"epoch": 0.9737939249553306,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004917439383258848,
|
|
"loss": 4.8336,
|
|
"mean_token_accuracy": 0.21007844060659409,
|
|
"num_tokens": 22856137.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.128695058822632,
|
|
"epoch": 0.9743895175699822,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004917324970309337,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.20106206834316254,
|
|
"num_tokens": 22870705.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.161596870422363,
|
|
"epoch": 0.9749851101846337,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004917210479621404,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.1973010390996933,
|
|
"num_tokens": 22883860.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.132380485534668,
|
|
"epoch": 0.9755807027992853,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004917095911199155,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.2078588053584099,
|
|
"num_tokens": 22897233.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.1388849258422855,
|
|
"epoch": 0.9761762954139369,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.00049169812650467,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.1961691215634346,
|
|
"num_tokens": 22911931.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.113099384307861,
|
|
"epoch": 0.9767718880285885,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004916866541168148,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.20882253646850585,
|
|
"num_tokens": 22925615.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.109107494354248,
|
|
"epoch": 0.97736748064324,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004916751739567617,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.20995472818613053,
|
|
"num_tokens": 22939178.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.167370891571045,
|
|
"epoch": 0.9779630732578916,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004916636860249225,
|
|
"loss": 4.9015,
|
|
"mean_token_accuracy": 0.20654659122228622,
|
|
"num_tokens": 22954681.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.1004133224487305,
|
|
"epoch": 0.9785586658725431,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000491652190321709,
|
|
"loss": 4.7839,
|
|
"mean_token_accuracy": 0.2092840313911438,
|
|
"num_tokens": 22965843.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.11631932258606,
|
|
"epoch": 0.9791542584871947,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004916406868475338,
|
|
"loss": 4.8668,
|
|
"mean_token_accuracy": 0.20195459425449372,
|
|
"num_tokens": 22980695.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.159639692306518,
|
|
"epoch": 0.9797498511018463,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004916291756028094,
|
|
"loss": 4.9537,
|
|
"mean_token_accuracy": 0.2037738159298897,
|
|
"num_tokens": 22994146.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.065694284439087,
|
|
"epoch": 0.9803454437164979,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004916176565879487,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.20535910427570342,
|
|
"num_tokens": 23008397.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.104378747940063,
|
|
"epoch": 0.9809410363311495,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004916061298033648,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.21251035779714583,
|
|
"num_tokens": 23020693.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.139512634277343,
|
|
"epoch": 0.9815366289458011,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004915945952494713,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.20690144449472428,
|
|
"num_tokens": 23035444.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.13489146232605,
|
|
"epoch": 0.9821322215604527,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004915830529266818,
|
|
"loss": 4.8788,
|
|
"mean_token_accuracy": 0.20919089913368225,
|
|
"num_tokens": 23050185.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.118703842163086,
|
|
"epoch": 0.9827278141751042,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004915715028354102,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.21309648752212523,
|
|
"num_tokens": 23063588.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.081256580352783,
|
|
"epoch": 0.9833234067897558,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004915599449760711,
|
|
"loss": 4.8235,
|
|
"mean_token_accuracy": 0.21496672183275223,
|
|
"num_tokens": 23076581.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.134102869033813,
|
|
"epoch": 0.9839189994044074,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004915483793490788,
|
|
"loss": 4.8978,
|
|
"mean_token_accuracy": 0.19896964132785797,
|
|
"num_tokens": 23089583.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.268817901611328,
|
|
"epoch": 0.984514592019059,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004915368059548482,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.18863581418991088,
|
|
"num_tokens": 23103029.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.165845680236816,
|
|
"epoch": 0.9851101846337106,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004915252247937944,
|
|
"loss": 4.9994,
|
|
"mean_token_accuracy": 0.19887207597494125,
|
|
"num_tokens": 23119056.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.160630369186402,
|
|
"epoch": 0.9857057772483622,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000491513635866333,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.20203275233507156,
|
|
"num_tokens": 23132774.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.123512697219849,
|
|
"epoch": 0.9863013698630136,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004915020391728792,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.20866781920194627,
|
|
"num_tokens": 23147666.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.130696058273315,
|
|
"epoch": 0.9868969624776652,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004914904347138495,
|
|
"loss": 4.8707,
|
|
"mean_token_accuracy": 0.2131431892514229,
|
|
"num_tokens": 23161868.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.119625759124756,
|
|
"epoch": 0.9874925550923168,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004914788224896599,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.20434631407260895,
|
|
"num_tokens": 23174938.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.086147308349609,
|
|
"epoch": 0.9880881477069684,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004914672025007269,
|
|
"loss": 4.8622,
|
|
"mean_token_accuracy": 0.1998431444168091,
|
|
"num_tokens": 23189294.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.2044493675231935,
|
|
"epoch": 0.98868374032162,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004914555747474673,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.20362543016672136,
|
|
"num_tokens": 23202715.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.083755111694336,
|
|
"epoch": 0.9892793329362716,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004914439392302981,
|
|
"loss": 4.8247,
|
|
"mean_token_accuracy": 0.2105051040649414,
|
|
"num_tokens": 23216216.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.126770877838135,
|
|
"epoch": 0.9898749255509232,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004914322959496367,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.2100026935338974,
|
|
"num_tokens": 23228795.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.1669329643249515,
|
|
"epoch": 0.9904705181655747,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004914206449059008,
|
|
"loss": 4.9147,
|
|
"mean_token_accuracy": 0.2001165747642517,
|
|
"num_tokens": 23244288.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.147449636459351,
|
|
"epoch": 0.9910661107802263,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004914089860995084,
|
|
"loss": 4.9221,
|
|
"mean_token_accuracy": 0.2072264313697815,
|
|
"num_tokens": 23259067.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.135837841033935,
|
|
"epoch": 0.9916617033948779,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004913973195308772,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.20832079648971558,
|
|
"num_tokens": 23270939.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.059817123413086,
|
|
"epoch": 0.9922572960095295,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004913856452004262,
|
|
"loss": 4.8096,
|
|
"mean_token_accuracy": 0.20970795303583145,
|
|
"num_tokens": 23285309.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.160462188720703,
|
|
"epoch": 0.9928528886241811,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004913739631085739,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.20631538480520248,
|
|
"num_tokens": 23299609.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.094571685791015,
|
|
"epoch": 0.9934484812388327,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004913622732557394,
|
|
"loss": 4.7659,
|
|
"mean_token_accuracy": 0.21267436891794206,
|
|
"num_tokens": 23312817.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.113551807403565,
|
|
"epoch": 0.9940440738534843,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004913505756423418,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.21212999969720842,
|
|
"num_tokens": 23324944.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.006036424636841,
|
|
"epoch": 0.9946396664681358,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004913388702688009,
|
|
"loss": 4.7286,
|
|
"mean_token_accuracy": 0.21768101006746293,
|
|
"num_tokens": 23338200.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.131504487991333,
|
|
"epoch": 0.9952352590827874,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004913271571355365,
|
|
"loss": 4.8458,
|
|
"mean_token_accuracy": 0.20577962845563888,
|
|
"num_tokens": 23352009.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.2044923305511475,
|
|
"epoch": 0.9958308516974389,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004913154362429686,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.19077352583408355,
|
|
"num_tokens": 23366680.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.092619800567627,
|
|
"epoch": 0.9964264443120905,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004913037075915178,
|
|
"loss": 4.881,
|
|
"mean_token_accuracy": 0.2102571740746498,
|
|
"num_tokens": 23379900.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.131239032745361,
|
|
"epoch": 0.9970220369267421,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004912919711816047,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.21425295025110244,
|
|
"num_tokens": 23393366.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.125626516342163,
|
|
"epoch": 0.9976176295413937,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004912802270136503,
|
|
"loss": 4.8694,
|
|
"mean_token_accuracy": 0.20147457867860794,
|
|
"num_tokens": 23407272.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.044153785705566,
|
|
"epoch": 0.9982132221560452,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004912684750880757,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.20625961869955062,
|
|
"num_tokens": 23421167.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.137872552871704,
|
|
"epoch": 0.9988088147706968,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004912567154053025,
|
|
"loss": 4.9827,
|
|
"mean_token_accuracy": 0.20144322514533997,
|
|
"num_tokens": 23434264.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.187752103805542,
|
|
"epoch": 0.9994044073853484,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004912449479657526,
|
|
"loss": 4.8808,
|
|
"mean_token_accuracy": 0.2050936073064804,
|
|
"num_tokens": 23448000.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.176060676574707,
|
|
"epoch": 1.0,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004912331727698481,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.20628693848848342,
|
|
"num_tokens": 23461012.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.136442565917969,
|
|
"epoch": 1.0005955926146515,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004912213898180111,
|
|
"loss": 4.8779,
|
|
"mean_token_accuracy": 0.19998240768909453,
|
|
"num_tokens": 23473230.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.196777248382569,
|
|
"epoch": 1.0011911852293032,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004912095991106644,
|
|
"loss": 4.9076,
|
|
"mean_token_accuracy": 0.19686558842658997,
|
|
"num_tokens": 23488201.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.2483603954315186,
|
|
"epoch": 1.0017867778439546,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004911978006482311,
|
|
"loss": 4.8322,
|
|
"mean_token_accuracy": 0.2002608746290207,
|
|
"num_tokens": 23505057.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.18873085975647,
|
|
"epoch": 1.0023823704586063,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004911859944311341,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.20979276448488235,
|
|
"num_tokens": 23518061.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.1693449974060055,
|
|
"epoch": 1.0029779630732578,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000491174180459797,
|
|
"loss": 4.9102,
|
|
"mean_token_accuracy": 0.20113812386989594,
|
|
"num_tokens": 23532902.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.0985006332397464,
|
|
"epoch": 1.0035735556879095,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004911623587346434,
|
|
"loss": 4.7026,
|
|
"mean_token_accuracy": 0.21948463171720506,
|
|
"num_tokens": 23546329.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.202975654602051,
|
|
"epoch": 1.004169148302561,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004911505292560977,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.2042056515812874,
|
|
"num_tokens": 23562153.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.127773714065552,
|
|
"epoch": 1.0047647409172127,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004911386920245837,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.21222690641880035,
|
|
"num_tokens": 23576582.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.145722198486328,
|
|
"epoch": 1.0053603335318642,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004911268470405263,
|
|
"loss": 4.8264,
|
|
"mean_token_accuracy": 0.2075497955083847,
|
|
"num_tokens": 23591007.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.112020635604859,
|
|
"epoch": 1.0059559261465159,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004911149943043504,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.21815158277750016,
|
|
"num_tokens": 23605269.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.169770574569702,
|
|
"epoch": 1.0065515187611673,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000491103133816481,
|
|
"loss": 4.8961,
|
|
"mean_token_accuracy": 0.20218004286289215,
|
|
"num_tokens": 23622448.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.049387502670288,
|
|
"epoch": 1.007147111375819,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004910912655773436,
|
|
"loss": 4.7463,
|
|
"mean_token_accuracy": 0.21600185036659242,
|
|
"num_tokens": 23636573.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.104780435562134,
|
|
"epoch": 1.0077427039904705,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004910793895873637,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.21923694014549255,
|
|
"num_tokens": 23649542.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.0665326595306395,
|
|
"epoch": 1.0083382966051222,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910675058469675,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.2127515360713005,
|
|
"num_tokens": 23662270.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.177072906494141,
|
|
"epoch": 1.0089338892197737,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910556143565812,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.20002064406871795,
|
|
"num_tokens": 23675998.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.239354801177979,
|
|
"epoch": 1.0095294818344251,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004910437151166312,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.20879549086093901,
|
|
"num_tokens": 23691511.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.056886911392212,
|
|
"epoch": 1.0101250744490768,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004910318081275445,
|
|
"loss": 4.7118,
|
|
"mean_token_accuracy": 0.2206580385565758,
|
|
"num_tokens": 23705412.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.0839372158050535,
|
|
"epoch": 1.0107206670637283,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000491019893389748,
|
|
"loss": 4.7691,
|
|
"mean_token_accuracy": 0.21029432117938995,
|
|
"num_tokens": 23721303.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.132709980010986,
|
|
"epoch": 1.01131625967838,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004910079709036692,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.21426697373390197,
|
|
"num_tokens": 23735018.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.1665081024169925,
|
|
"epoch": 1.0119118522930315,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004909960406697358,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.21062742322683334,
|
|
"num_tokens": 23747262.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.083658170700073,
|
|
"epoch": 1.0125074449076832,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004909841026883755,
|
|
"loss": 4.8304,
|
|
"mean_token_accuracy": 0.2109810918569565,
|
|
"num_tokens": 23761195.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.147108125686645,
|
|
"epoch": 1.0131030375223347,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004909721569600166,
|
|
"loss": 4.793,
|
|
"mean_token_accuracy": 0.20104781836271285,
|
|
"num_tokens": 23775789.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.071705007553101,
|
|
"epoch": 1.0136986301369864,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004909602034850875,
|
|
"loss": 4.717,
|
|
"mean_token_accuracy": 0.22341578006744384,
|
|
"num_tokens": 23788554.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.045306825637818,
|
|
"epoch": 1.0142942227516378,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004909482422640172,
|
|
"loss": 4.793,
|
|
"mean_token_accuracy": 0.21022316962480544,
|
|
"num_tokens": 23802033.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.190822792053223,
|
|
"epoch": 1.0148898153662895,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004909362732972344,
|
|
"loss": 4.9159,
|
|
"mean_token_accuracy": 0.20383305996656417,
|
|
"num_tokens": 23819250.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.173139476776123,
|
|
"epoch": 1.015485407980941,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004909242965851688,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.20450522303581237,
|
|
"num_tokens": 23833917.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.130035924911499,
|
|
"epoch": 1.0160810005955927,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004909123121282495,
|
|
"loss": 4.7277,
|
|
"mean_token_accuracy": 0.21165162920951844,
|
|
"num_tokens": 23848177.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.075819587707519,
|
|
"epoch": 1.0166765932102442,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004909003199269068,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.206368350982666,
|
|
"num_tokens": 23861640.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.028302574157715,
|
|
"epoch": 1.0172721858248959,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004908883199815705,
|
|
"loss": 4.7074,
|
|
"mean_token_accuracy": 0.21404478549957276,
|
|
"num_tokens": 23875580.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.060949516296387,
|
|
"epoch": 1.0178677784395473,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004908763122926712,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.2120327189564705,
|
|
"num_tokens": 23887977.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.111125946044922,
|
|
"epoch": 1.018463371054199,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004908642968606396,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.2047650471329689,
|
|
"num_tokens": 23902079.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.148727893829346,
|
|
"epoch": 1.0190589636688505,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004908522736859068,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.20443788468837737,
|
|
"num_tokens": 23915468.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.084004306793213,
|
|
"epoch": 1.019654556283502,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004908402427689037,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.21450404077768326,
|
|
"num_tokens": 23932059.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.154594373703003,
|
|
"epoch": 1.0202501488981537,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004908282041100621,
|
|
"loss": 4.8339,
|
|
"mean_token_accuracy": 0.21192444413900374,
|
|
"num_tokens": 23946730.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.221394634246826,
|
|
"epoch": 1.0208457415128052,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004908161577098137,
|
|
"loss": 4.9405,
|
|
"mean_token_accuracy": 0.19017888009548187,
|
|
"num_tokens": 23961298.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.122244834899902,
|
|
"epoch": 1.0214413341274569,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004908041035685907,
|
|
"loss": 4.7668,
|
|
"mean_token_accuracy": 0.2048646926879883,
|
|
"num_tokens": 23975419.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.101758432388306,
|
|
"epoch": 1.0220369267421083,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004907920416868253,
|
|
"loss": 4.7743,
|
|
"mean_token_accuracy": 0.20534600764513017,
|
|
"num_tokens": 23989563.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.196707487106323,
|
|
"epoch": 1.02263251935676,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004907799720649502,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.20685559809207915,
|
|
"num_tokens": 24004961.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.099379158020019,
|
|
"epoch": 1.0232281119714115,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004907678947033984,
|
|
"loss": 4.777,
|
|
"mean_token_accuracy": 0.21603196412324904,
|
|
"num_tokens": 24019636.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.13806004524231,
|
|
"epoch": 1.0238237045860632,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004907558096026031,
|
|
"loss": 4.7366,
|
|
"mean_token_accuracy": 0.2161066710948944,
|
|
"num_tokens": 24031406.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.081039619445801,
|
|
"epoch": 1.0244192972007147,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004907437167629976,
|
|
"loss": 4.7591,
|
|
"mean_token_accuracy": 0.21254531145095826,
|
|
"num_tokens": 24045468.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.0566709518432615,
|
|
"epoch": 1.0250148898153664,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004907316161850158,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.2081230953335762,
|
|
"num_tokens": 24059712.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.160747051239014,
|
|
"epoch": 1.0256104824300178,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004907195078690916,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.20502697229385375,
|
|
"num_tokens": 24073549.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.107241868972778,
|
|
"epoch": 1.0262060750446695,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004907073918156595,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.21136015951633452,
|
|
"num_tokens": 24085770.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.1574255466461185,
|
|
"epoch": 1.026801667659321,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004906952680251539,
|
|
"loss": 4.8843,
|
|
"mean_token_accuracy": 0.20026927590370178,
|
|
"num_tokens": 24102289.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.068690490722656,
|
|
"epoch": 1.0273972602739727,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004906831364980098,
|
|
"loss": 4.7663,
|
|
"mean_token_accuracy": 0.21471716463565826,
|
|
"num_tokens": 24116075.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.176452159881592,
|
|
"epoch": 1.0279928528886242,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004906709972346623,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.20752755850553511,
|
|
"num_tokens": 24129599.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.0878197193145756,
|
|
"epoch": 1.0285884455032757,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004906588502355467,
|
|
"loss": 4.7727,
|
|
"mean_token_accuracy": 0.20653905868530273,
|
|
"num_tokens": 24143322.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.135210084915161,
|
|
"epoch": 1.0291840381179274,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004906466955010988,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.2158731311559677,
|
|
"num_tokens": 24157431.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.102326107025147,
|
|
"epoch": 1.0297796307325788,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004906345330317546,
|
|
"loss": 4.7528,
|
|
"mean_token_accuracy": 0.20844392478466034,
|
|
"num_tokens": 24172228.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.03387336730957,
|
|
"epoch": 1.0303752233472305,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004906223628279502,
|
|
"loss": 4.715,
|
|
"mean_token_accuracy": 0.2141445979475975,
|
|
"num_tokens": 24184436.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.079369831085205,
|
|
"epoch": 1.030970815961882,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004906101848901224,
|
|
"loss": 4.7108,
|
|
"mean_token_accuracy": 0.215261110663414,
|
|
"num_tokens": 24197765.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.0715752124786375,
|
|
"epoch": 1.0315664085765337,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004905979992187076,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.21235434710979462,
|
|
"num_tokens": 24211336.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.1120506763458256,
|
|
"epoch": 1.0321620011911852,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004905858058141433,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.2026548907160759,
|
|
"num_tokens": 24226027.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.015224599838257,
|
|
"epoch": 1.0327575938058369,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004905736046768665,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.21744753867387773,
|
|
"num_tokens": 24240108.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.1732035160064695,
|
|
"epoch": 1.0333531864204883,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004905613958073151,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.20300986915826796,
|
|
"num_tokens": 24253664.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.136033725738526,
|
|
"epoch": 1.03394877903514,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.000490549179205927,
|
|
"loss": 4.7795,
|
|
"mean_token_accuracy": 0.2148702085018158,
|
|
"num_tokens": 24268958.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.108251571655273,
|
|
"epoch": 1.0345443716497915,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004905369548731402,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.20090168714523315,
|
|
"num_tokens": 24283750.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.1481507301330565,
|
|
"epoch": 1.0351399642644432,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004905247228093933,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.2041677102446556,
|
|
"num_tokens": 24298316.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.061338472366333,
|
|
"epoch": 1.0357355568790947,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000490512483015125,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.21628960072994233,
|
|
"num_tokens": 24311113.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.122244119644165,
|
|
"epoch": 1.0363311494937464,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004905002354907743,
|
|
"loss": 4.7637,
|
|
"mean_token_accuracy": 0.21095712184906007,
|
|
"num_tokens": 24326579.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.1031396865844725,
|
|
"epoch": 1.0369267421083979,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004904879802367806,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.20412065386772155,
|
|
"num_tokens": 24339208.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.142496633529663,
|
|
"epoch": 1.0375223347230493,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004904757172535833,
|
|
"loss": 4.8655,
|
|
"mean_token_accuracy": 0.20668528825044633,
|
|
"num_tokens": 24351659.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.132928514480591,
|
|
"epoch": 1.038117927337701,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004904634465416226,
|
|
"loss": 4.8012,
|
|
"mean_token_accuracy": 0.20869979560375213,
|
|
"num_tokens": 24365646.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.136101913452149,
|
|
"epoch": 1.0387135199523525,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004904511681013382,
|
|
"loss": 4.8385,
|
|
"mean_token_accuracy": 0.20708570033311843,
|
|
"num_tokens": 24379577.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.10656247138977,
|
|
"epoch": 1.0393091125670042,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004904388819331707,
|
|
"loss": 4.8005,
|
|
"mean_token_accuracy": 0.20908545702695847,
|
|
"num_tokens": 24394441.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.127030324935913,
|
|
"epoch": 1.0399047051816557,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004904265880375609,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.2126027375459671,
|
|
"num_tokens": 24408443.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.16377272605896,
|
|
"epoch": 1.0405002977963074,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004904142864149496,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.20641391724348068,
|
|
"num_tokens": 24423416.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.150284957885742,
|
|
"epoch": 1.0410958904109588,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000490401977065778,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.20657679289579392,
|
|
"num_tokens": 24436205.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.117693090438843,
|
|
"epoch": 1.0416914830256105,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004903896599904878,
|
|
"loss": 4.8211,
|
|
"mean_token_accuracy": 0.20828820019960403,
|
|
"num_tokens": 24449472.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.11019115447998,
|
|
"epoch": 1.042287075640262,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004903773351895206,
|
|
"loss": 4.7158,
|
|
"mean_token_accuracy": 0.21656163781881332,
|
|
"num_tokens": 24462861.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.159122896194458,
|
|
"epoch": 1.0428826682549137,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004903650026633187,
|
|
"loss": 4.7406,
|
|
"mean_token_accuracy": 0.2265960916876793,
|
|
"num_tokens": 24474981.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.013250160217285,
|
|
"epoch": 1.0434782608695652,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004903526624123243,
|
|
"loss": 4.6773,
|
|
"mean_token_accuracy": 0.2172481581568718,
|
|
"num_tokens": 24489283.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 4.992848253250122,
|
|
"epoch": 1.0440738534842169,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00049034031443698,
|
|
"loss": 4.6102,
|
|
"mean_token_accuracy": 0.21873778551816941,
|
|
"num_tokens": 24501859.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.111286783218384,
|
|
"epoch": 1.0446694460988684,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004903279587377287,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.21076543927192687,
|
|
"num_tokens": 24515586.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.184897136688233,
|
|
"epoch": 1.04526503871352,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004903155953150137,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.2028117746114731,
|
|
"num_tokens": 24531912.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.096513748168945,
|
|
"epoch": 1.0458606313281715,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004903032241692784,
|
|
"loss": 4.7897,
|
|
"mean_token_accuracy": 0.2122521474957466,
|
|
"num_tokens": 24544958.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.0598982810974125,
|
|
"epoch": 1.046456223942823,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004902908453009664,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.21561241894960403,
|
|
"num_tokens": 24556979.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.1843681812286375,
|
|
"epoch": 1.0470518165574747,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004902784587105218,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.19415746927261351,
|
|
"num_tokens": 24571299.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.15225658416748,
|
|
"epoch": 1.0476474091721262,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000490266064398389,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.21171940714120865,
|
|
"num_tokens": 24584292.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.116628789901734,
|
|
"epoch": 1.0482430017867779,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004902536623650125,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.2082578495144844,
|
|
"num_tokens": 24597245.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.028639030456543,
|
|
"epoch": 1.0488385944014293,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004902412526108371,
|
|
"loss": 4.6663,
|
|
"mean_token_accuracy": 0.2315194234251976,
|
|
"num_tokens": 24610388.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.1403624534606935,
|
|
"epoch": 1.049434187016081,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004902288351363079,
|
|
"loss": 4.8755,
|
|
"mean_token_accuracy": 0.20016805082559586,
|
|
"num_tokens": 24625939.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.107317781448364,
|
|
"epoch": 1.0500297796307325,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004902164099418703,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.21651236414909364,
|
|
"num_tokens": 24641133.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.06811752319336,
|
|
"epoch": 1.0506253722453842,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00049020397702797,
|
|
"loss": 4.7167,
|
|
"mean_token_accuracy": 0.21243818253278732,
|
|
"num_tokens": 24654555.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.052727460861206,
|
|
"epoch": 1.0512209648600357,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000490191536395053,
|
|
"loss": 4.7882,
|
|
"mean_token_accuracy": 0.21332450658082963,
|
|
"num_tokens": 24669048.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.093867206573487,
|
|
"epoch": 1.0518165574746874,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004901790880435655,
|
|
"loss": 4.7494,
|
|
"mean_token_accuracy": 0.21727802306413652,
|
|
"num_tokens": 24683420.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.135576963424683,
|
|
"epoch": 1.0524121500893389,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004901666319739537,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.20144369453191757,
|
|
"num_tokens": 24696972.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.051600551605224,
|
|
"epoch": 1.0530077427039906,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004901541681866649,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.21089925169944762,
|
|
"num_tokens": 24710581.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.040735054016113,
|
|
"epoch": 1.053603335318642,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004901416966821459,
|
|
"loss": 4.6867,
|
|
"mean_token_accuracy": 0.21958364844322203,
|
|
"num_tokens": 24723055.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.122497463226319,
|
|
"epoch": 1.0541989279332937,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000490129217460844,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.20972866266965867,
|
|
"num_tokens": 24738073.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.167162179946899,
|
|
"epoch": 1.0547945205479452,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004901167305232068,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.20195484310388565,
|
|
"num_tokens": 24751566.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.096008682250977,
|
|
"epoch": 1.0553901131625967,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004901042358696823,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.21978194266557693,
|
|
"num_tokens": 24765401.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.0686338424682615,
|
|
"epoch": 1.0559857057772484,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004900917335007186,
|
|
"loss": 4.7726,
|
|
"mean_token_accuracy": 0.21189576983451844,
|
|
"num_tokens": 24779180.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.101472282409668,
|
|
"epoch": 1.0565812983918998,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004900792234167642,
|
|
"loss": 4.8036,
|
|
"mean_token_accuracy": 0.209900926053524,
|
|
"num_tokens": 24794536.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.10550217628479,
|
|
"epoch": 1.0571768910065515,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004900667056182676,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.20769141167402266,
|
|
"num_tokens": 24809721.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.126291131973266,
|
|
"epoch": 1.057772483621203,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004900541801056781,
|
|
"loss": 4.8389,
|
|
"mean_token_accuracy": 0.2109765186905861,
|
|
"num_tokens": 24823818.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.074911451339721,
|
|
"epoch": 1.0583680762358547,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004900416468794446,
|
|
"loss": 4.7038,
|
|
"mean_token_accuracy": 0.2215084806084633,
|
|
"num_tokens": 24836028.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.013275241851806,
|
|
"epoch": 1.0589636688505062,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004900291059400171,
|
|
"loss": 4.7313,
|
|
"mean_token_accuracy": 0.21286247968673705,
|
|
"num_tokens": 24849957.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.105123472213745,
|
|
"epoch": 1.0595592614651579,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000490016557287845,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.20392756015062333,
|
|
"num_tokens": 24862123.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.106251287460327,
|
|
"epoch": 1.0601548540798094,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004900040009233787,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.2094264566898346,
|
|
"num_tokens": 24874584.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.149079942703247,
|
|
"epoch": 1.060750446694461,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004899914368470685,
|
|
"loss": 4.9068,
|
|
"mean_token_accuracy": 0.19997520595788956,
|
|
"num_tokens": 24890828.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.157776117324829,
|
|
"epoch": 1.0613460393091125,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004899788650593648,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.20981544405221939,
|
|
"num_tokens": 24905266.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.11357684135437,
|
|
"epoch": 1.0619416319237642,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004899662855607189,
|
|
"loss": 4.797,
|
|
"mean_token_accuracy": 0.2110016778111458,
|
|
"num_tokens": 24918867.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.092357587814331,
|
|
"epoch": 1.0625372245384157,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004899536983515819,
|
|
"loss": 4.8159,
|
|
"mean_token_accuracy": 0.20619207620620728,
|
|
"num_tokens": 24934619.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.215360403060913,
|
|
"epoch": 1.0631328171530674,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004899411034324051,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.20198035538196563,
|
|
"num_tokens": 24950582.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.125244855880737,
|
|
"epoch": 1.0637284097677189,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004899285008036406,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.21074910312891007,
|
|
"num_tokens": 24964456.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.06676607131958,
|
|
"epoch": 1.0643240023823703,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.00048991589046574,
|
|
"loss": 4.7576,
|
|
"mean_token_accuracy": 0.2130242884159088,
|
|
"num_tokens": 24977443.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.02127513885498,
|
|
"epoch": 1.064919594997022,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004899032724191559,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.22398424446582793,
|
|
"num_tokens": 24989343.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.111344814300537,
|
|
"epoch": 1.0655151876116735,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004898906466643409,
|
|
"loss": 4.7735,
|
|
"mean_token_accuracy": 0.21355585008859634,
|
|
"num_tokens": 25004157.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.064301013946533,
|
|
"epoch": 1.0661107802263252,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004898780132017478,
|
|
"loss": 4.8192,
|
|
"mean_token_accuracy": 0.21036376804113388,
|
|
"num_tokens": 25016292.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.152235889434815,
|
|
"epoch": 1.0667063728409767,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004898653720318296,
|
|
"loss": 4.8554,
|
|
"mean_token_accuracy": 0.20676702558994292,
|
|
"num_tokens": 25032374.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.166051387786865,
|
|
"epoch": 1.0673019654556284,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00048985272315504,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.2134851947426796,
|
|
"num_tokens": 25045290.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.051154327392578,
|
|
"epoch": 1.0678975580702799,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004898400665718325,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.2064426764845848,
|
|
"num_tokens": 25058733.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.032707357406617,
|
|
"epoch": 1.0684931506849316,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004898274022826611,
|
|
"loss": 4.7259,
|
|
"mean_token_accuracy": 0.21326858550310135,
|
|
"num_tokens": 25073274.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.131275701522827,
|
|
"epoch": 1.069088743299583,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004898147302879801,
|
|
"loss": 4.7763,
|
|
"mean_token_accuracy": 0.2084283709526062,
|
|
"num_tokens": 25088339.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.095667552947998,
|
|
"epoch": 1.0696843359142347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004898020505882441,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.22387228310108184,
|
|
"num_tokens": 25100031.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.162352228164673,
|
|
"epoch": 1.0702799285288862,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004897893631839076,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.19989098757505416,
|
|
"num_tokens": 25113070.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.144609689712524,
|
|
"epoch": 1.070875521143538,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000489776668075426,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.21411727517843246,
|
|
"num_tokens": 25126584.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.128993177413941,
|
|
"epoch": 1.0714711137581894,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004897639652632544,
|
|
"loss": 4.8138,
|
|
"mean_token_accuracy": 0.21786815971136092,
|
|
"num_tokens": 25139292.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.044837617874146,
|
|
"epoch": 1.072066706372841,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004897512547478487,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.20518420189619063,
|
|
"num_tokens": 25153590.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.072066706372841,
|
|
"eval_entropy": 4.851628258833691,
|
|
"eval_loss": 4.820348739624023,
|
|
"eval_mean_token_accuracy": 0.21951477543266962,
|
|
"eval_num_tokens": 25153590.0,
|
|
"eval_runtime": 18.511,
|
|
"eval_samples_per_second": 1378.263,
|
|
"eval_steps_per_second": 172.33,
|
|
"step": 9000
|
|
}
|
|
],
|
|
"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": 6647435666104320.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|