36101 lines
992 KiB
JSON
36101 lines
992 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.144133412745682,
|
|
"eval_steps": 3000,
|
|
"global_step": 18000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.691967391967774,
|
|
"epoch": 0.0005955926146515784,
|
|
"grad_norm": 10.875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8678,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 13933.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691935825347901,
|
|
"epoch": 0.0011911852293031567,
|
|
"grad_norm": 11.5,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.8021,
|
|
"mean_token_accuracy": 0.00011719739704858511,
|
|
"num_tokens": 28184.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691279220581055,
|
|
"epoch": 0.001786777843954735,
|
|
"grad_norm": 8.4375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.5969,
|
|
"mean_token_accuracy": 0.011063378886319697,
|
|
"num_tokens": 42481.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.686292362213134,
|
|
"epoch": 0.0023823704586063135,
|
|
"grad_norm": 6.125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.2992,
|
|
"mean_token_accuracy": 0.032997015863657,
|
|
"num_tokens": 58257.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.658948421478271,
|
|
"epoch": 0.0029779630732578916,
|
|
"grad_norm": 3.703125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.0254,
|
|
"mean_token_accuracy": 0.036169218644499776,
|
|
"num_tokens": 73037.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.626773452758789,
|
|
"epoch": 0.00357355568790947,
|
|
"grad_norm": 3.0625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.8967,
|
|
"mean_token_accuracy": 0.03464589659124613,
|
|
"num_tokens": 87144.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.629238891601563,
|
|
"epoch": 0.004169148302561048,
|
|
"grad_norm": 2.890625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.7956,
|
|
"mean_token_accuracy": 0.03592457864433527,
|
|
"num_tokens": 100908.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.63215684890747,
|
|
"epoch": 0.004764740917212627,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.7983,
|
|
"mean_token_accuracy": 0.03275683782994747,
|
|
"num_tokens": 116164.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.63164405822754,
|
|
"epoch": 0.005360333531864205,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.7592,
|
|
"mean_token_accuracy": 0.03141073621809483,
|
|
"num_tokens": 129754.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.622919845581055,
|
|
"epoch": 0.005955926146515783,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.6818,
|
|
"mean_token_accuracy": 0.034183095395565036,
|
|
"num_tokens": 143356.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.614870071411133,
|
|
"epoch": 0.006551518761167362,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.6591,
|
|
"mean_token_accuracy": 0.03321251459419727,
|
|
"num_tokens": 159656.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.610630130767822,
|
|
"epoch": 0.00714711137581894,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.5565,
|
|
"mean_token_accuracy": 0.03500598520040512,
|
|
"num_tokens": 176053.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.5836181640625,
|
|
"epoch": 0.007742703990470518,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.4621,
|
|
"mean_token_accuracy": 0.035244090110063554,
|
|
"num_tokens": 191011.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.557289028167725,
|
|
"epoch": 0.008338296605122097,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.3593,
|
|
"mean_token_accuracy": 0.03757428880780935,
|
|
"num_tokens": 203975.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.556610202789306,
|
|
"epoch": 0.008933889219773675,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.304,
|
|
"mean_token_accuracy": 0.03267980273813009,
|
|
"num_tokens": 216231.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.558743095397949,
|
|
"epoch": 0.009529481834425254,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.1969,
|
|
"mean_token_accuracy": 0.032431036792695524,
|
|
"num_tokens": 230525.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.510394096374512,
|
|
"epoch": 0.01012507444907683,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.075,
|
|
"mean_token_accuracy": 0.03401159159839153,
|
|
"num_tokens": 243197.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.47779130935669,
|
|
"epoch": 0.01072066706372841,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.9115,
|
|
"mean_token_accuracy": 0.039179544523358346,
|
|
"num_tokens": 257358.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.4499981880188,
|
|
"epoch": 0.011316259678379988,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.872,
|
|
"mean_token_accuracy": 0.036476068384945395,
|
|
"num_tokens": 271978.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.378599643707275,
|
|
"epoch": 0.011911852293031567,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.7057,
|
|
"mean_token_accuracy": 0.03978296536952257,
|
|
"num_tokens": 286644.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.311494064331054,
|
|
"epoch": 0.012507444907683145,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.6054,
|
|
"mean_token_accuracy": 0.04222038425505161,
|
|
"num_tokens": 299888.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.238801765441895,
|
|
"epoch": 0.013103037522334724,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.4037,
|
|
"mean_token_accuracy": 0.052524236217141154,
|
|
"num_tokens": 314062.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.12908477783203,
|
|
"epoch": 0.0136986301369863,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.2589,
|
|
"mean_token_accuracy": 0.05390131808817387,
|
|
"num_tokens": 326877.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.982657051086425,
|
|
"epoch": 0.01429422275163788,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.1461,
|
|
"mean_token_accuracy": 0.05713789314031601,
|
|
"num_tokens": 339831.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.870760536193847,
|
|
"epoch": 0.014889815366289458,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.051,
|
|
"mean_token_accuracy": 0.05943196974694729,
|
|
"num_tokens": 353316.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.712617683410645,
|
|
"epoch": 0.015485407980941036,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9186,
|
|
"mean_token_accuracy": 0.061891674250364306,
|
|
"num_tokens": 368263.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.51815185546875,
|
|
"epoch": 0.016081000595592615,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8752,
|
|
"mean_token_accuracy": 0.05740171670913696,
|
|
"num_tokens": 381899.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.339330005645753,
|
|
"epoch": 0.016676593210244194,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.7004,
|
|
"mean_token_accuracy": 0.06701527126133441,
|
|
"num_tokens": 393924.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.12987403869629,
|
|
"epoch": 0.017272185824895772,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.5471,
|
|
"mean_token_accuracy": 0.06982396468520165,
|
|
"num_tokens": 404670.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.909981822967529,
|
|
"epoch": 0.01786777843954735,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.5432,
|
|
"mean_token_accuracy": 0.06730130650103092,
|
|
"num_tokens": 418805.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.702024936676025,
|
|
"epoch": 0.01846337105419893,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.5437,
|
|
"mean_token_accuracy": 0.06560702323913574,
|
|
"num_tokens": 434053.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.516354179382324,
|
|
"epoch": 0.019058963668850508,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.4078,
|
|
"mean_token_accuracy": 0.06627187281847,
|
|
"num_tokens": 447771.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.340857219696044,
|
|
"epoch": 0.019654556283502083,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.2977,
|
|
"mean_token_accuracy": 0.0759556919336319,
|
|
"num_tokens": 462055.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.240561294555665,
|
|
"epoch": 0.02025014889815366,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.3047,
|
|
"mean_token_accuracy": 0.06914827115833759,
|
|
"num_tokens": 475573.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.14937391281128,
|
|
"epoch": 0.02084574151280524,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.2579,
|
|
"mean_token_accuracy": 0.07320506498217583,
|
|
"num_tokens": 490172.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.053140211105347,
|
|
"epoch": 0.02144133412745682,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.2607,
|
|
"mean_token_accuracy": 0.07395614869892597,
|
|
"num_tokens": 503073.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.983269691467285,
|
|
"epoch": 0.022036926742108397,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.127,
|
|
"mean_token_accuracy": 0.07421845197677612,
|
|
"num_tokens": 518422.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.918516826629639,
|
|
"epoch": 0.022632519356759976,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.1856,
|
|
"mean_token_accuracy": 0.07822260037064552,
|
|
"num_tokens": 531422.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.883159208297729,
|
|
"epoch": 0.023228111971411555,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.2726,
|
|
"mean_token_accuracy": 0.07234647311270237,
|
|
"num_tokens": 547556.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.007419109344482,
|
|
"epoch": 0.023823704586063133,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.1498,
|
|
"mean_token_accuracy": 0.07780812904238701,
|
|
"num_tokens": 559950.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.76445517539978,
|
|
"epoch": 0.024419297200714712,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.1008,
|
|
"mean_token_accuracy": 0.07941969707608224,
|
|
"num_tokens": 573158.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.831501293182373,
|
|
"epoch": 0.02501488981536629,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.1516,
|
|
"mean_token_accuracy": 0.07671068608760834,
|
|
"num_tokens": 587653.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.771380090713501,
|
|
"epoch": 0.02561048243001787,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1096,
|
|
"mean_token_accuracy": 0.08333899006247521,
|
|
"num_tokens": 599566.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.76031002998352,
|
|
"epoch": 0.026206075044669448,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.0062,
|
|
"mean_token_accuracy": 0.08164888247847557,
|
|
"num_tokens": 613870.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.723504686355591,
|
|
"epoch": 0.026801667659321026,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.0108,
|
|
"mean_token_accuracy": 0.08097214996814728,
|
|
"num_tokens": 625417.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.683968925476075,
|
|
"epoch": 0.0273972602739726,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.0763,
|
|
"mean_token_accuracy": 0.08478415682911873,
|
|
"num_tokens": 638091.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.6376079559326175,
|
|
"epoch": 0.02799285288862418,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.9876,
|
|
"mean_token_accuracy": 0.08382979407906532,
|
|
"num_tokens": 653733.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.57065052986145,
|
|
"epoch": 0.02858844550327576,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.0476,
|
|
"mean_token_accuracy": 0.07994345054030419,
|
|
"num_tokens": 667197.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.640932035446167,
|
|
"epoch": 0.029184038117927337,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.0211,
|
|
"mean_token_accuracy": 0.08348592296242714,
|
|
"num_tokens": 682333.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.631290578842163,
|
|
"epoch": 0.029779630732578916,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.0524,
|
|
"mean_token_accuracy": 0.07928600311279296,
|
|
"num_tokens": 698745.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.486025953292847,
|
|
"epoch": 0.030375223347230494,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.9029,
|
|
"mean_token_accuracy": 0.08653413355350495,
|
|
"num_tokens": 713585.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.528491258621216,
|
|
"epoch": 0.030970815961882073,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.96,
|
|
"mean_token_accuracy": 0.08368109464645386,
|
|
"num_tokens": 728735.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.535400867462158,
|
|
"epoch": 0.03156640857653365,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.9354,
|
|
"mean_token_accuracy": 0.08548845872282981,
|
|
"num_tokens": 742292.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.433577251434326,
|
|
"epoch": 0.03216200119118523,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.8344,
|
|
"mean_token_accuracy": 0.09271911159157753,
|
|
"num_tokens": 755915.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.414020729064942,
|
|
"epoch": 0.03275759380583681,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.9045,
|
|
"mean_token_accuracy": 0.09081559926271439,
|
|
"num_tokens": 769669.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.432183694839478,
|
|
"epoch": 0.03335318642048839,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9145,
|
|
"mean_token_accuracy": 0.08927777931094169,
|
|
"num_tokens": 782871.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.367679166793823,
|
|
"epoch": 0.033948779035139966,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.7969,
|
|
"mean_token_accuracy": 0.09545460492372512,
|
|
"num_tokens": 796354.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.451816034317017,
|
|
"epoch": 0.034544371649791544,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.954,
|
|
"mean_token_accuracy": 0.08782607764005661,
|
|
"num_tokens": 810833.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.360701417922973,
|
|
"epoch": 0.03513996426444312,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.7837,
|
|
"mean_token_accuracy": 0.09459315687417984,
|
|
"num_tokens": 824970.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.2989466190338135,
|
|
"epoch": 0.0357355568790947,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.7194,
|
|
"mean_token_accuracy": 0.09828391969203949,
|
|
"num_tokens": 838403.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.361730670928955,
|
|
"epoch": 0.03633114949374628,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.8981,
|
|
"mean_token_accuracy": 0.08661884889006614,
|
|
"num_tokens": 850970.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.281069564819336,
|
|
"epoch": 0.03692674210839786,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.8035,
|
|
"mean_token_accuracy": 0.09726258143782615,
|
|
"num_tokens": 864950.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.32599720954895,
|
|
"epoch": 0.03752233472304944,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8797,
|
|
"mean_token_accuracy": 0.09565327912569047,
|
|
"num_tokens": 876860.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.359777212142944,
|
|
"epoch": 0.038117927337701016,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8019,
|
|
"mean_token_accuracy": 0.09205329343676567,
|
|
"num_tokens": 890278.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.27224645614624,
|
|
"epoch": 0.03871351995235259,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8011,
|
|
"mean_token_accuracy": 0.09264332503080368,
|
|
"num_tokens": 903716.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.222869777679444,
|
|
"epoch": 0.039309112567004166,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.7269,
|
|
"mean_token_accuracy": 0.08918297439813613,
|
|
"num_tokens": 919346.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.239504337310791,
|
|
"epoch": 0.039904705181655745,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.7719,
|
|
"mean_token_accuracy": 0.0974351055920124,
|
|
"num_tokens": 931959.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.226378393173218,
|
|
"epoch": 0.04050029779630732,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.7018,
|
|
"mean_token_accuracy": 0.09081124737858773,
|
|
"num_tokens": 947237.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.213427495956421,
|
|
"epoch": 0.0410958904109589,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.7369,
|
|
"mean_token_accuracy": 0.09328288063406945,
|
|
"num_tokens": 961650.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.11381344795227,
|
|
"epoch": 0.04169148302561048,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.7433,
|
|
"mean_token_accuracy": 0.09167589917778969,
|
|
"num_tokens": 976138.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.209743070602417,
|
|
"epoch": 0.04228707564026206,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.7733,
|
|
"mean_token_accuracy": 0.0981741227209568,
|
|
"num_tokens": 991306.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.181589794158936,
|
|
"epoch": 0.04288266825491364,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.6926,
|
|
"mean_token_accuracy": 0.0967189110815525,
|
|
"num_tokens": 1006494.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.12306580543518,
|
|
"epoch": 0.043478260869565216,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.6381,
|
|
"mean_token_accuracy": 0.09580513834953308,
|
|
"num_tokens": 1020458.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.235243511199951,
|
|
"epoch": 0.044073853484216795,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.8132,
|
|
"mean_token_accuracy": 0.09217350855469704,
|
|
"num_tokens": 1035801.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 6.961404132843017,
|
|
"epoch": 0.04466944609886837,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.6168,
|
|
"mean_token_accuracy": 0.09042830914258956,
|
|
"num_tokens": 1051671.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.069963502883911,
|
|
"epoch": 0.04526503871351995,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.6006,
|
|
"mean_token_accuracy": 0.09585671946406364,
|
|
"num_tokens": 1065580.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.142119121551514,
|
|
"epoch": 0.04586063132817153,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.6047,
|
|
"mean_token_accuracy": 0.10200910568237305,
|
|
"num_tokens": 1078646.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.012524747848511,
|
|
"epoch": 0.04645622394282311,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.5973,
|
|
"mean_token_accuracy": 0.0973847821354866,
|
|
"num_tokens": 1090921.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.051640892028809,
|
|
"epoch": 0.04705181655747469,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.6221,
|
|
"mean_token_accuracy": 0.0985582411289215,
|
|
"num_tokens": 1103223.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.0754859924316404,
|
|
"epoch": 0.047647409172126266,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.5374,
|
|
"mean_token_accuracy": 0.10345466807484627,
|
|
"num_tokens": 1117103.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.924616861343384,
|
|
"epoch": 0.048243001786777845,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.6783,
|
|
"mean_token_accuracy": 0.09979898631572723,
|
|
"num_tokens": 1131452.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.070319175720215,
|
|
"epoch": 0.048838594401429423,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.6176,
|
|
"mean_token_accuracy": 0.10055162757635117,
|
|
"num_tokens": 1144755.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 6.934567308425903,
|
|
"epoch": 0.049434187016081,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.592,
|
|
"mean_token_accuracy": 0.09994840398430824,
|
|
"num_tokens": 1157544.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.011605834960937,
|
|
"epoch": 0.05002977963073258,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.5819,
|
|
"mean_token_accuracy": 0.09889719411730766,
|
|
"num_tokens": 1171753.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.896132326126098,
|
|
"epoch": 0.05062537224538416,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.5241,
|
|
"mean_token_accuracy": 0.09692821353673935,
|
|
"num_tokens": 1186570.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.021337413787842,
|
|
"epoch": 0.05122096486003574,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.6453,
|
|
"mean_token_accuracy": 0.09898117631673813,
|
|
"num_tokens": 1201674.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.860861730575562,
|
|
"epoch": 0.051816557474687316,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.4457,
|
|
"mean_token_accuracy": 0.10438253208994866,
|
|
"num_tokens": 1216060.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.875170612335205,
|
|
"epoch": 0.052412150089338895,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.5461,
|
|
"mean_token_accuracy": 0.10233776569366455,
|
|
"num_tokens": 1229736.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.959600353240967,
|
|
"epoch": 0.053007742703990474,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.5118,
|
|
"mean_token_accuracy": 0.10087570622563362,
|
|
"num_tokens": 1243253.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.890491151809693,
|
|
"epoch": 0.05360333531864205,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.5277,
|
|
"mean_token_accuracy": 0.10564899668097497,
|
|
"num_tokens": 1256399.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.944673728942871,
|
|
"epoch": 0.054198927933293624,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.5737,
|
|
"mean_token_accuracy": 0.10199703574180603,
|
|
"num_tokens": 1270676.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.83975043296814,
|
|
"epoch": 0.0547945205479452,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.511,
|
|
"mean_token_accuracy": 0.1067811518907547,
|
|
"num_tokens": 1283059.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.000147008895874,
|
|
"epoch": 0.05539011316259678,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.5615,
|
|
"mean_token_accuracy": 0.10038791224360466,
|
|
"num_tokens": 1297312.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.887468576431274,
|
|
"epoch": 0.05598570577724836,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.5319,
|
|
"mean_token_accuracy": 0.10475537925958633,
|
|
"num_tokens": 1309608.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.862203168869018,
|
|
"epoch": 0.05658129839189994,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.501,
|
|
"mean_token_accuracy": 0.10316896513104439,
|
|
"num_tokens": 1323605.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.885790872573852,
|
|
"epoch": 0.05717689100655152,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.5305,
|
|
"mean_token_accuracy": 0.10420851036906242,
|
|
"num_tokens": 1335742.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.839960384368896,
|
|
"epoch": 0.057772483621203095,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.5005,
|
|
"mean_token_accuracy": 0.10386336743831634,
|
|
"num_tokens": 1349190.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.835858154296875,
|
|
"epoch": 0.058368076235854674,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.5963,
|
|
"mean_token_accuracy": 0.10155056342482567,
|
|
"num_tokens": 1365737.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.844678258895874,
|
|
"epoch": 0.05896366885050625,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.5052,
|
|
"mean_token_accuracy": 0.10582002028822898,
|
|
"num_tokens": 1380591.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.774532651901245,
|
|
"epoch": 0.05955926146515783,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.4521,
|
|
"mean_token_accuracy": 0.107053741812706,
|
|
"num_tokens": 1394303.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.788577270507813,
|
|
"epoch": 0.06015485407980941,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.4108,
|
|
"mean_token_accuracy": 0.10436714813113213,
|
|
"num_tokens": 1407232.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.820324468612671,
|
|
"epoch": 0.06075044669446099,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.4875,
|
|
"mean_token_accuracy": 0.10461183115839959,
|
|
"num_tokens": 1421822.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.838621187210083,
|
|
"epoch": 0.06134603930911257,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5056,
|
|
"mean_token_accuracy": 0.10881137922406196,
|
|
"num_tokens": 1434555.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.69404706954956,
|
|
"epoch": 0.061941631923764146,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.4364,
|
|
"mean_token_accuracy": 0.11271098777651786,
|
|
"num_tokens": 1446221.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.732331085205078,
|
|
"epoch": 0.06253722453841572,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.3689,
|
|
"mean_token_accuracy": 0.11010837033391,
|
|
"num_tokens": 1459623.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.740880012512207,
|
|
"epoch": 0.0631328171530673,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.415,
|
|
"mean_token_accuracy": 0.11129370629787445,
|
|
"num_tokens": 1474618.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.658067750930786,
|
|
"epoch": 0.06372840976771887,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.3,
|
|
"mean_token_accuracy": 0.11396777108311654,
|
|
"num_tokens": 1486820.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.740281772613526,
|
|
"epoch": 0.06432400238237046,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.10134752914309501,
|
|
"num_tokens": 1500696.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.7233686447143555,
|
|
"epoch": 0.06491959499702203,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.3917,
|
|
"mean_token_accuracy": 0.1075817584991455,
|
|
"num_tokens": 1513926.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.718568801879883,
|
|
"epoch": 0.06551518761167362,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.455,
|
|
"mean_token_accuracy": 0.11105936244130135,
|
|
"num_tokens": 1527390.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.697780704498291,
|
|
"epoch": 0.06611078022632519,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.357,
|
|
"mean_token_accuracy": 0.10812488421797753,
|
|
"num_tokens": 1540631.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.773905611038208,
|
|
"epoch": 0.06670637284097677,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.4558,
|
|
"mean_token_accuracy": 0.10263804495334625,
|
|
"num_tokens": 1554822.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.566762208938599,
|
|
"epoch": 0.06730196545562835,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.3113,
|
|
"mean_token_accuracy": 0.10836630165576935,
|
|
"num_tokens": 1569702.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.687147521972657,
|
|
"epoch": 0.06789755807027993,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.3775,
|
|
"mean_token_accuracy": 0.10573874711990357,
|
|
"num_tokens": 1583023.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.6649863719940186,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.3623,
|
|
"mean_token_accuracy": 0.10345643982291222,
|
|
"num_tokens": 1597012.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.741729354858398,
|
|
"epoch": 0.06908874329958309,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.4588,
|
|
"mean_token_accuracy": 0.0996822901070118,
|
|
"num_tokens": 1610668.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.722759056091308,
|
|
"epoch": 0.06968433591423466,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.55,
|
|
"mean_token_accuracy": 0.09567253589630127,
|
|
"num_tokens": 1628312.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.592629432678223,
|
|
"epoch": 0.07027992852888625,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.3239,
|
|
"mean_token_accuracy": 0.10860228613018989,
|
|
"num_tokens": 1642933.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.639333915710449,
|
|
"epoch": 0.07087552114353782,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.10803045481443405,
|
|
"num_tokens": 1659141.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.660793972015381,
|
|
"epoch": 0.0714711137581894,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.3737,
|
|
"mean_token_accuracy": 0.10568737685680389,
|
|
"num_tokens": 1673555.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.687187433242798,
|
|
"epoch": 0.07206670637284097,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4534,
|
|
"mean_token_accuracy": 0.11027220264077187,
|
|
"num_tokens": 1688619.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.589902877807617,
|
|
"epoch": 0.07266229898749256,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.3203,
|
|
"mean_token_accuracy": 0.11680542826652526,
|
|
"num_tokens": 1702096.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.67415418624878,
|
|
"epoch": 0.07325789160214413,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.3974,
|
|
"mean_token_accuracy": 0.11306419894099236,
|
|
"num_tokens": 1716915.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.5232185363769535,
|
|
"epoch": 0.07385348421679572,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.2661,
|
|
"mean_token_accuracy": 0.1098593719303608,
|
|
"num_tokens": 1730743.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.609029483795166,
|
|
"epoch": 0.07444907683144729,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.2868,
|
|
"mean_token_accuracy": 0.1084153950214386,
|
|
"num_tokens": 1744537.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.58609824180603,
|
|
"epoch": 0.07504466944609887,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.2909,
|
|
"mean_token_accuracy": 0.10949683859944344,
|
|
"num_tokens": 1757394.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.457737970352173,
|
|
"epoch": 0.07564026206075045,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.2118,
|
|
"mean_token_accuracy": 0.12022669091820717,
|
|
"num_tokens": 1772966.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.571221446990966,
|
|
"epoch": 0.07623585467540203,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.3181,
|
|
"mean_token_accuracy": 0.116214369982481,
|
|
"num_tokens": 1786753.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.472329235076904,
|
|
"epoch": 0.0768314472900536,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.1524,
|
|
"mean_token_accuracy": 0.1182224191725254,
|
|
"num_tokens": 1799665.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.449941778182984,
|
|
"epoch": 0.07742703990470517,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.2861,
|
|
"mean_token_accuracy": 0.10726464316248893,
|
|
"num_tokens": 1813363.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.604919576644898,
|
|
"epoch": 0.07802263251935676,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.3685,
|
|
"mean_token_accuracy": 0.11135526970028878,
|
|
"num_tokens": 1827715.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.588877964019775,
|
|
"epoch": 0.07861822513400833,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.4342,
|
|
"mean_token_accuracy": 0.11303346082568169,
|
|
"num_tokens": 1842248.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.561273050308228,
|
|
"epoch": 0.07921381774865992,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.3145,
|
|
"mean_token_accuracy": 0.10637551471590996,
|
|
"num_tokens": 1855993.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.464603519439697,
|
|
"epoch": 0.07980941036331149,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.1997,
|
|
"mean_token_accuracy": 0.11398791596293449,
|
|
"num_tokens": 1869053.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.62538595199585,
|
|
"epoch": 0.08040500297796307,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.361,
|
|
"mean_token_accuracy": 0.10019897148013115,
|
|
"num_tokens": 1883371.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.573400783538818,
|
|
"epoch": 0.08100059559261465,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.3205,
|
|
"mean_token_accuracy": 0.10641836971044541,
|
|
"num_tokens": 1899299.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.333754158020019,
|
|
"epoch": 0.08159618820726623,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.1253,
|
|
"mean_token_accuracy": 0.11677459999918938,
|
|
"num_tokens": 1913908.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.4048743724823,
|
|
"epoch": 0.0821917808219178,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.2531,
|
|
"mean_token_accuracy": 0.11259785890579224,
|
|
"num_tokens": 1928379.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.497745704650879,
|
|
"epoch": 0.08278737343656939,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.2332,
|
|
"mean_token_accuracy": 0.11368018388748169,
|
|
"num_tokens": 1942308.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.412065887451172,
|
|
"epoch": 0.08338296605122096,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.04,
|
|
"mean_token_accuracy": 0.12043975815176963,
|
|
"num_tokens": 1954659.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.388837003707886,
|
|
"epoch": 0.08397855866587255,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.2229,
|
|
"mean_token_accuracy": 0.11098725870251655,
|
|
"num_tokens": 1969847.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.45836763381958,
|
|
"epoch": 0.08457415128052412,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.2452,
|
|
"mean_token_accuracy": 0.11239207908511162,
|
|
"num_tokens": 1983973.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.340896272659302,
|
|
"epoch": 0.0851697438951757,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.11823484003543853,
|
|
"num_tokens": 1997786.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.561270523071289,
|
|
"epoch": 0.08576533650982728,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.3362,
|
|
"mean_token_accuracy": 0.10667206645011902,
|
|
"num_tokens": 2012849.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.372331619262695,
|
|
"epoch": 0.08636092912447886,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.2284,
|
|
"mean_token_accuracy": 0.11489845290780068,
|
|
"num_tokens": 2026935.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.4450523853302,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.2017,
|
|
"mean_token_accuracy": 0.11551416665315628,
|
|
"num_tokens": 2039722.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.4527641296386715,
|
|
"epoch": 0.08755211435378202,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.2103,
|
|
"mean_token_accuracy": 0.12140938490629197,
|
|
"num_tokens": 2053064.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.492100572586059,
|
|
"epoch": 0.08814770696843359,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.3578,
|
|
"mean_token_accuracy": 0.10826176032423973,
|
|
"num_tokens": 2065401.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.357286357879639,
|
|
"epoch": 0.08874329958308518,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.1228,
|
|
"mean_token_accuracy": 0.11925248354673386,
|
|
"num_tokens": 2078975.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.369147396087646,
|
|
"epoch": 0.08933889219773675,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.11334023550152779,
|
|
"num_tokens": 2094427.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.350690126419067,
|
|
"epoch": 0.08993448481238833,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2442,
|
|
"mean_token_accuracy": 0.11245899572968483,
|
|
"num_tokens": 2108993.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.416349267959594,
|
|
"epoch": 0.0905300774270399,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.11984949856996537,
|
|
"num_tokens": 2121913.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.396230602264405,
|
|
"epoch": 0.09112567004169149,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.2116,
|
|
"mean_token_accuracy": 0.11517818719148636,
|
|
"num_tokens": 2135224.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.36370096206665,
|
|
"epoch": 0.09172126265634306,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.2371,
|
|
"mean_token_accuracy": 0.1134832501411438,
|
|
"num_tokens": 2150603.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.311854553222656,
|
|
"epoch": 0.09231685527099463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.1716,
|
|
"mean_token_accuracy": 0.11656383350491524,
|
|
"num_tokens": 2165710.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.293350124359131,
|
|
"epoch": 0.09291244788564622,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.1508,
|
|
"mean_token_accuracy": 0.11489418372511864,
|
|
"num_tokens": 2180477.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.355593204498291,
|
|
"epoch": 0.09350804050029779,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.1133,
|
|
"mean_token_accuracy": 0.11394583582878112,
|
|
"num_tokens": 2193654.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.310933446884155,
|
|
"epoch": 0.09410363311494938,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.125,
|
|
"mean_token_accuracy": 0.12292548045516014,
|
|
"num_tokens": 2208161.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.322223806381226,
|
|
"epoch": 0.09469922572960095,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.1681,
|
|
"mean_token_accuracy": 0.11686177551746368,
|
|
"num_tokens": 2222306.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.381310892105103,
|
|
"epoch": 0.09529481834425253,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.2851,
|
|
"mean_token_accuracy": 0.11463002189993858,
|
|
"num_tokens": 2237919.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.334206533432007,
|
|
"epoch": 0.0958904109589041,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.1257,
|
|
"mean_token_accuracy": 0.1175191193819046,
|
|
"num_tokens": 2253244.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.410386610031128,
|
|
"epoch": 0.09648600357355569,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.2192,
|
|
"mean_token_accuracy": 0.11312662363052368,
|
|
"num_tokens": 2267429.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.198392343521118,
|
|
"epoch": 0.09708159618820726,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.0735,
|
|
"mean_token_accuracy": 0.12144820094108581,
|
|
"num_tokens": 2281830.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.293162202835083,
|
|
"epoch": 0.09767718880285885,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.1642,
|
|
"mean_token_accuracy": 0.11794983372092246,
|
|
"num_tokens": 2297243.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.432693099975586,
|
|
"epoch": 0.09827278141751042,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.1627,
|
|
"mean_token_accuracy": 0.12036959826946259,
|
|
"num_tokens": 2308952.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.314801597595215,
|
|
"epoch": 0.098868374032162,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.1147,
|
|
"mean_token_accuracy": 0.12466569766402244,
|
|
"num_tokens": 2321645.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.203279209136963,
|
|
"epoch": 0.09946396664681358,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.1244,
|
|
"mean_token_accuracy": 0.12485404759645462,
|
|
"num_tokens": 2333309.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.305699110031128,
|
|
"epoch": 0.10005955926146516,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.1449,
|
|
"mean_token_accuracy": 0.11570195853710175,
|
|
"num_tokens": 2347843.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.344734764099121,
|
|
"epoch": 0.10065515187611673,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.12063974291086196,
|
|
"num_tokens": 2361024.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.191798877716065,
|
|
"epoch": 0.10125074449076832,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.1139,
|
|
"mean_token_accuracy": 0.11597833633422852,
|
|
"num_tokens": 2375498.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.281596279144287,
|
|
"epoch": 0.10184633710541989,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.12045025527477264,
|
|
"num_tokens": 2392063.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.249076175689697,
|
|
"epoch": 0.10244192972007148,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.0567,
|
|
"mean_token_accuracy": 0.12596114128828048,
|
|
"num_tokens": 2407267.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.237308311462402,
|
|
"epoch": 0.10303752233472305,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.12164935618638992,
|
|
"num_tokens": 2421814.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.212417030334473,
|
|
"epoch": 0.10363311494937463,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.12100224643945694,
|
|
"num_tokens": 2438931.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.235447740554809,
|
|
"epoch": 0.1042287075640262,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.0347,
|
|
"mean_token_accuracy": 0.12373126819729804,
|
|
"num_tokens": 2451210.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.189838409423828,
|
|
"epoch": 0.10482430017867779,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.1472,
|
|
"mean_token_accuracy": 0.12463530823588372,
|
|
"num_tokens": 2465343.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.208383464813233,
|
|
"epoch": 0.10541989279332936,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.0119,
|
|
"mean_token_accuracy": 0.12245457991957664,
|
|
"num_tokens": 2478732.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.193100881576538,
|
|
"epoch": 0.10601548540798095,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.0789,
|
|
"mean_token_accuracy": 0.12875348180532456,
|
|
"num_tokens": 2493362.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.232412338256836,
|
|
"epoch": 0.10661107802263252,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.1304,
|
|
"mean_token_accuracy": 0.12399234920740128,
|
|
"num_tokens": 2506154.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.281187200546265,
|
|
"epoch": 0.1072066706372841,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.12229079976677895,
|
|
"num_tokens": 2519189.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.139049673080445,
|
|
"epoch": 0.10780226325193568,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.12124882265925407,
|
|
"num_tokens": 2532486.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.27548360824585,
|
|
"epoch": 0.10839785586658725,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.0663,
|
|
"mean_token_accuracy": 0.12244808226823807,
|
|
"num_tokens": 2546239.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.232610034942627,
|
|
"epoch": 0.10899344848123883,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.11176685467362404,
|
|
"num_tokens": 2563054.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.1703064918518065,
|
|
"epoch": 0.1095890410958904,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.0916,
|
|
"mean_token_accuracy": 0.11885043680667877,
|
|
"num_tokens": 2577503.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.327150774002075,
|
|
"epoch": 0.11018463371054199,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.1836,
|
|
"mean_token_accuracy": 0.11800827980041503,
|
|
"num_tokens": 2591506.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.233006763458252,
|
|
"epoch": 0.11078022632519356,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.1318,
|
|
"mean_token_accuracy": 0.11485417336225509,
|
|
"num_tokens": 2607777.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.317490530014038,
|
|
"epoch": 0.11137581893984515,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.1651,
|
|
"mean_token_accuracy": 0.11726380065083504,
|
|
"num_tokens": 2619506.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.235444402694702,
|
|
"epoch": 0.11197141155449672,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.1517,
|
|
"mean_token_accuracy": 0.11761577725410462,
|
|
"num_tokens": 2634182.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.214152431488037,
|
|
"epoch": 0.1125670041691483,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.0698,
|
|
"mean_token_accuracy": 0.1202508769929409,
|
|
"num_tokens": 2649266.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.084998750686646,
|
|
"epoch": 0.11316259678379988,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.0328,
|
|
"mean_token_accuracy": 0.1233438141644001,
|
|
"num_tokens": 2662745.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.1725821018219,
|
|
"epoch": 0.11375818939845146,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 5.9905,
|
|
"mean_token_accuracy": 0.126254041492939,
|
|
"num_tokens": 2676071.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.155135011672973,
|
|
"epoch": 0.11435378201310303,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.0753,
|
|
"mean_token_accuracy": 0.12005074694752693,
|
|
"num_tokens": 2690511.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.183897399902344,
|
|
"epoch": 0.11494937462775462,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 5.9994,
|
|
"mean_token_accuracy": 0.12930835857987405,
|
|
"num_tokens": 2704891.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.103983640670776,
|
|
"epoch": 0.11554496724240619,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.0628,
|
|
"mean_token_accuracy": 0.11935378164052964,
|
|
"num_tokens": 2718288.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.1136575698852536,
|
|
"epoch": 0.11614055985705778,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.0033,
|
|
"mean_token_accuracy": 0.1262139581143856,
|
|
"num_tokens": 2732853.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.180597400665283,
|
|
"epoch": 0.11673615247170935,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.11941681355237961,
|
|
"num_tokens": 2746801.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.173189735412597,
|
|
"epoch": 0.11733174508636093,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.0134,
|
|
"mean_token_accuracy": 0.12111828774213791,
|
|
"num_tokens": 2760896.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.04111647605896,
|
|
"epoch": 0.1179273377010125,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 5.9918,
|
|
"mean_token_accuracy": 0.1181405246257782,
|
|
"num_tokens": 2774464.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.0556282043457035,
|
|
"epoch": 0.11852293031566409,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.0481,
|
|
"mean_token_accuracy": 0.12033342197537422,
|
|
"num_tokens": 2789696.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.132859325408935,
|
|
"epoch": 0.11911852293031566,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.12136000841856003,
|
|
"num_tokens": 2802830.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.017935371398925,
|
|
"epoch": 0.11971411554496725,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999974174771,
|
|
"loss": 5.9539,
|
|
"mean_token_accuracy": 0.12590551748871803,
|
|
"num_tokens": 2816983.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.1119976997375485,
|
|
"epoch": 0.12030970815961882,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999999869259778,
|
|
"loss": 6.0666,
|
|
"mean_token_accuracy": 0.12595007196068764,
|
|
"num_tokens": 2831192.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.176437473297119,
|
|
"epoch": 0.1209053007742704,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999999683640947,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.1277400679886341,
|
|
"num_tokens": 2844621.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.011213111877441,
|
|
"epoch": 0.12150089338892198,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999999417318286,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.12622107490897178,
|
|
"num_tokens": 2857056.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.151247024536133,
|
|
"epoch": 0.12209648600357356,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999999070291805,
|
|
"loss": 6.1272,
|
|
"mean_token_accuracy": 0.11918605118989944,
|
|
"num_tokens": 2870129.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.266168451309204,
|
|
"epoch": 0.12269207861822513,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004999998642561514,
|
|
"loss": 6.1127,
|
|
"mean_token_accuracy": 0.1182718813419342,
|
|
"num_tokens": 2883395.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.052407169342041,
|
|
"epoch": 0.1232876712328767,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999998134127432,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.13093072921037674,
|
|
"num_tokens": 2897295.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.010536146163941,
|
|
"epoch": 0.12388326384752829,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999997544989574,
|
|
"loss": 6.0211,
|
|
"mean_token_accuracy": 0.12300709486007691,
|
|
"num_tokens": 2910532.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.21044602394104,
|
|
"epoch": 0.12447885646217986,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999996875147963,
|
|
"loss": 6.0075,
|
|
"mean_token_accuracy": 0.12245981693267823,
|
|
"num_tokens": 2924713.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.143694257736206,
|
|
"epoch": 0.12507444907683143,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999996124602621,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.11757480576634408,
|
|
"num_tokens": 2941652.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.104994583129883,
|
|
"epoch": 0.12567004169148302,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999995293353578,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.12192811593413352,
|
|
"num_tokens": 2953863.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 5.991248655319214,
|
|
"epoch": 0.1262656343061346,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999994381400862,
|
|
"loss": 5.9468,
|
|
"mean_token_accuracy": 0.12996241971850395,
|
|
"num_tokens": 2965301.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.010249948501587,
|
|
"epoch": 0.1268612269207862,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999993388744504,
|
|
"loss": 5.9813,
|
|
"mean_token_accuracy": 0.12093813493847846,
|
|
"num_tokens": 2979693.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.011619615554809,
|
|
"epoch": 0.12745681953543775,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999992315384543,
|
|
"loss": 5.8799,
|
|
"mean_token_accuracy": 0.1338715597987175,
|
|
"num_tokens": 2993089.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.201226854324341,
|
|
"epoch": 0.12805241215008933,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999991161321014,
|
|
"loss": 6.1205,
|
|
"mean_token_accuracy": 0.12227544710040092,
|
|
"num_tokens": 3006201.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.040372133255005,
|
|
"epoch": 0.12864800476474092,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999989926553962,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.12250213697552681,
|
|
"num_tokens": 3021067.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 5.978237342834473,
|
|
"epoch": 0.1292435973793925,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499998861108343,
|
|
"loss": 6.0525,
|
|
"mean_token_accuracy": 0.125216144323349,
|
|
"num_tokens": 3035126.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.125109243392944,
|
|
"epoch": 0.12983918999404406,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999987214909464,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.12603542432188988,
|
|
"num_tokens": 3048811.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 5.972577285766602,
|
|
"epoch": 0.13043478260869565,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999985738032115,
|
|
"loss": 5.9434,
|
|
"mean_token_accuracy": 0.13011902645230294,
|
|
"num_tokens": 3061651.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.071717834472656,
|
|
"epoch": 0.13103037522334723,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999984180451436,
|
|
"loss": 5.9444,
|
|
"mean_token_accuracy": 0.12794605493545533,
|
|
"num_tokens": 3074075.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 5.986891984939575,
|
|
"epoch": 0.13162596783799882,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999982542167483,
|
|
"loss": 5.9221,
|
|
"mean_token_accuracy": 0.12738179862499238,
|
|
"num_tokens": 3086217.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.001612377166748,
|
|
"epoch": 0.13222156045265038,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999980823180314,
|
|
"loss": 5.9336,
|
|
"mean_token_accuracy": 0.12237837687134742,
|
|
"num_tokens": 3101375.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.050482177734375,
|
|
"epoch": 0.13281715306730196,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499997902348999,
|
|
"loss": 5.9538,
|
|
"mean_token_accuracy": 0.12822767794132234,
|
|
"num_tokens": 3116799.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.088452863693237,
|
|
"epoch": 0.13341274568195355,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999977143096578,
|
|
"loss": 6.0195,
|
|
"mean_token_accuracy": 0.12603393271565438,
|
|
"num_tokens": 3130224.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 5.989429140090943,
|
|
"epoch": 0.13400833829660513,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999975182000143,
|
|
"loss": 6.0461,
|
|
"mean_token_accuracy": 0.12389937937259674,
|
|
"num_tokens": 3145627.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 5.978799676895141,
|
|
"epoch": 0.1346039309112567,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999973140200759,
|
|
"loss": 5.8434,
|
|
"mean_token_accuracy": 0.1315501421689987,
|
|
"num_tokens": 3159927.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 5.834775781631469,
|
|
"epoch": 0.13519952352590828,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999971017698495,
|
|
"loss": 5.8297,
|
|
"mean_token_accuracy": 0.1343303680419922,
|
|
"num_tokens": 3174135.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 5.992903995513916,
|
|
"epoch": 0.13579511614055986,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999968814493428,
|
|
"loss": 5.8894,
|
|
"mean_token_accuracy": 0.13162622451782227,
|
|
"num_tokens": 3186673.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.051998519897461,
|
|
"epoch": 0.13639070875521145,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999966530585639,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.1176169365644455,
|
|
"num_tokens": 3201645.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 5.9471831798553465,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999964165975209,
|
|
"loss": 5.8975,
|
|
"mean_token_accuracy": 0.1292322188615799,
|
|
"num_tokens": 3215255.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.070828819274903,
|
|
"epoch": 0.1375818939845146,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999961720662221,
|
|
"loss": 5.8819,
|
|
"mean_token_accuracy": 0.13697948008775712,
|
|
"num_tokens": 3228207.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 5.940400075912476,
|
|
"epoch": 0.13817748659916618,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999959194646766,
|
|
"loss": 5.9781,
|
|
"mean_token_accuracy": 0.13348641321063043,
|
|
"num_tokens": 3242242.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.003660583496094,
|
|
"epoch": 0.13877307921381773,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999956587928932,
|
|
"loss": 5.9703,
|
|
"mean_token_accuracy": 0.130535851418972,
|
|
"num_tokens": 3257408.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.011662817001342,
|
|
"epoch": 0.13936867182846932,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999953900508814,
|
|
"loss": 5.8993,
|
|
"mean_token_accuracy": 0.13194626197218895,
|
|
"num_tokens": 3269991.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 5.873396396636963,
|
|
"epoch": 0.1399642644431209,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999951132386507,
|
|
"loss": 5.8992,
|
|
"mean_token_accuracy": 0.13144004121422767,
|
|
"num_tokens": 3285119.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 5.92068567276001,
|
|
"epoch": 0.1405598570577725,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999948283562111,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.1307962231338024,
|
|
"num_tokens": 3299102.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.083365345001221,
|
|
"epoch": 0.14115544967242405,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499994535403573,
|
|
"loss": 5.9952,
|
|
"mean_token_accuracy": 0.1276424139738083,
|
|
"num_tokens": 3313907.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 5.967456388473511,
|
|
"epoch": 0.14175104228707563,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999942343807465,
|
|
"loss": 5.9307,
|
|
"mean_token_accuracy": 0.127975545078516,
|
|
"num_tokens": 3326128.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.0017250061035154,
|
|
"epoch": 0.14234663490172722,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999939252877428,
|
|
"loss": 5.9658,
|
|
"mean_token_accuracy": 0.12806169763207437,
|
|
"num_tokens": 3339257.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.066575908660889,
|
|
"epoch": 0.1429422275163788,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999936081245727,
|
|
"loss": 5.9771,
|
|
"mean_token_accuracy": 0.12188303843140602,
|
|
"num_tokens": 3353893.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 5.983616638183594,
|
|
"epoch": 0.14353782013103036,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999932828912478,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.1307750090956688,
|
|
"num_tokens": 3370872.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 5.967948150634766,
|
|
"epoch": 0.14413341274568195,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999929495877796,
|
|
"loss": 5.9593,
|
|
"mean_token_accuracy": 0.1289232201874256,
|
|
"num_tokens": 3384741.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 5.9253734111785885,
|
|
"epoch": 0.14472900536033353,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999926082141801,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.1335388630628586,
|
|
"num_tokens": 3399813.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 5.970020484924317,
|
|
"epoch": 0.14532459797498512,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999922587704616,
|
|
"loss": 5.8543,
|
|
"mean_token_accuracy": 0.13579602688550949,
|
|
"num_tokens": 3413314.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 5.894476366043091,
|
|
"epoch": 0.14592019058963668,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999919012566366,
|
|
"loss": 5.8209,
|
|
"mean_token_accuracy": 0.13729397803545,
|
|
"num_tokens": 3427973.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 5.904055166244507,
|
|
"epoch": 0.14651578320428826,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999915356727179,
|
|
"loss": 5.8939,
|
|
"mean_token_accuracy": 0.13233924880623818,
|
|
"num_tokens": 3443097.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.0626458644866945,
|
|
"epoch": 0.14711137581893985,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999911620187186,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.12422171756625175,
|
|
"num_tokens": 3456922.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 5.923436546325684,
|
|
"epoch": 0.14770696843359143,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999907802946521,
|
|
"loss": 5.8587,
|
|
"mean_token_accuracy": 0.13794974982738495,
|
|
"num_tokens": 3471247.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 5.934363269805909,
|
|
"epoch": 0.148302561048243,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999903905005323,
|
|
"loss": 5.8093,
|
|
"mean_token_accuracy": 0.13638360425829887,
|
|
"num_tokens": 3485026.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 5.945780038833618,
|
|
"epoch": 0.14889815366289458,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999899926363729,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.13669515177607536,
|
|
"num_tokens": 3498012.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 5.966631603240967,
|
|
"epoch": 0.14949374627754616,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999895867021882,
|
|
"loss": 5.9398,
|
|
"mean_token_accuracy": 0.12825293093919754,
|
|
"num_tokens": 3511732.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 5.895903205871582,
|
|
"epoch": 0.15008933889219775,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999891726979928,
|
|
"loss": 5.8773,
|
|
"mean_token_accuracy": 0.13185990750789642,
|
|
"num_tokens": 3527204.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 5.942460823059082,
|
|
"epoch": 0.1506849315068493,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999887506238018,
|
|
"loss": 5.8632,
|
|
"mean_token_accuracy": 0.13052663579583168,
|
|
"num_tokens": 3540571.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 5.8213762760162355,
|
|
"epoch": 0.1512805241215009,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00049998832047963,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.13715839833021165,
|
|
"num_tokens": 3553888.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 5.9327925682067875,
|
|
"epoch": 0.15187611673615248,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999878822654929,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.13300956636667252,
|
|
"num_tokens": 3565304.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 5.958762168884277,
|
|
"epoch": 0.15247170935080406,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999874359814064,
|
|
"loss": 5.8872,
|
|
"mean_token_accuracy": 0.13404751643538476,
|
|
"num_tokens": 3580109.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 5.843689823150635,
|
|
"epoch": 0.15306730196545562,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999869816273863,
|
|
"loss": 5.8405,
|
|
"mean_token_accuracy": 0.13445746079087256,
|
|
"num_tokens": 3594204.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 5.902410650253296,
|
|
"epoch": 0.1536628945801072,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999865192034489,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.1304301716387272,
|
|
"num_tokens": 3608722.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 5.780779695510864,
|
|
"epoch": 0.1542584871947588,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499986048709611,
|
|
"loss": 5.7601,
|
|
"mean_token_accuracy": 0.13408881276845933,
|
|
"num_tokens": 3624597.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 5.9346781253814695,
|
|
"epoch": 0.15485407980941035,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999855701458893,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.12829659581184388,
|
|
"num_tokens": 3641733.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 5.895977020263672,
|
|
"epoch": 0.15544967242406194,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999850835123009,
|
|
"loss": 5.7888,
|
|
"mean_token_accuracy": 0.13964626640081407,
|
|
"num_tokens": 3654188.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 5.9648045063018795,
|
|
"epoch": 0.15604526503871352,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999845888088635,
|
|
"loss": 5.9397,
|
|
"mean_token_accuracy": 0.12868864387273787,
|
|
"num_tokens": 3667738.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 5.869993591308594,
|
|
"epoch": 0.1566408576533651,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999840860355946,
|
|
"loss": 5.8398,
|
|
"mean_token_accuracy": 0.13890996649861337,
|
|
"num_tokens": 3682616.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 5.905131673812866,
|
|
"epoch": 0.15723645026801666,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999835751925124,
|
|
"loss": 5.837,
|
|
"mean_token_accuracy": 0.13374283015727997,
|
|
"num_tokens": 3695873.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 5.9562804222106935,
|
|
"epoch": 0.15783204288266825,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999830562796351,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.13278477489948273,
|
|
"num_tokens": 3710117.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 5.969579458236694,
|
|
"epoch": 0.15842763549731984,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999825292969814,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.13280325531959533,
|
|
"num_tokens": 3723153.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 5.7928369522094725,
|
|
"epoch": 0.15902322811197142,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999819942445703,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.12821475490927697,
|
|
"num_tokens": 3736970.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 5.9771280765533445,
|
|
"epoch": 0.15961882072662298,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999814511224207,
|
|
"loss": 5.8666,
|
|
"mean_token_accuracy": 0.13198236748576164,
|
|
"num_tokens": 3750737.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.909372758865357,
|
|
"epoch": 0.16021441334127456,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999808999305523,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.1293421134352684,
|
|
"num_tokens": 3764955.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 5.925450801849365,
|
|
"epoch": 0.16081000595592615,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999803406689848,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.1376695491373539,
|
|
"num_tokens": 3780107.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 5.782152557373047,
|
|
"epoch": 0.16140559857057774,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004999797733377384,
|
|
"loss": 5.8254,
|
|
"mean_token_accuracy": 0.13390666246414185,
|
|
"num_tokens": 3794609.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 5.958142852783203,
|
|
"epoch": 0.1620011911852293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999791979368332,
|
|
"loss": 5.9038,
|
|
"mean_token_accuracy": 0.13763106614351273,
|
|
"num_tokens": 3808870.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 5.93758807182312,
|
|
"epoch": 0.16259678379988088,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999786144662899,
|
|
"loss": 5.8474,
|
|
"mean_token_accuracy": 0.13378554657101632,
|
|
"num_tokens": 3822608.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 5.8398536205291744,
|
|
"epoch": 0.16319237641453246,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999780229261295,
|
|
"loss": 5.7998,
|
|
"mean_token_accuracy": 0.1425967276096344,
|
|
"num_tokens": 3837175.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.789087390899658,
|
|
"epoch": 0.16378796902918405,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999774233163734,
|
|
"loss": 5.6984,
|
|
"mean_token_accuracy": 0.14636055529117584,
|
|
"num_tokens": 3851298.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 5.750665473937988,
|
|
"epoch": 0.1643835616438356,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999768156370428,
|
|
"loss": 5.7115,
|
|
"mean_token_accuracy": 0.13712267875671386,
|
|
"num_tokens": 3865396.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 5.803971290588379,
|
|
"epoch": 0.1649791542584872,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999761998881596,
|
|
"loss": 5.6813,
|
|
"mean_token_accuracy": 0.14352245777845382,
|
|
"num_tokens": 3876827.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.8912880420684814,
|
|
"epoch": 0.16557474687313878,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999755760697459,
|
|
"loss": 5.8598,
|
|
"mean_token_accuracy": 0.13499838411808013,
|
|
"num_tokens": 3892707.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.891392517089844,
|
|
"epoch": 0.16617033948779036,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499974944181824,
|
|
"loss": 5.7854,
|
|
"mean_token_accuracy": 0.13481153994798661,
|
|
"num_tokens": 3906193.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 5.679084730148316,
|
|
"epoch": 0.16676593210244192,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999743042244167,
|
|
"loss": 5.6997,
|
|
"mean_token_accuracy": 0.14833138585090638,
|
|
"num_tokens": 3919175.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 5.965096426010132,
|
|
"epoch": 0.1673615247170935,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499973656197547,
|
|
"loss": 5.9295,
|
|
"mean_token_accuracy": 0.12844299674034118,
|
|
"num_tokens": 3933207.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.754853296279907,
|
|
"epoch": 0.1679571173317451,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999730001012379,
|
|
"loss": 5.7413,
|
|
"mean_token_accuracy": 0.141977895796299,
|
|
"num_tokens": 3945962.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 5.789040899276733,
|
|
"epoch": 0.16855270994639668,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999723359355131,
|
|
"loss": 5.762,
|
|
"mean_token_accuracy": 0.14299167096614837,
|
|
"num_tokens": 3959645.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.883685874938965,
|
|
"epoch": 0.16914830256104824,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999716637003965,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.13606778979301454,
|
|
"num_tokens": 3975142.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.801122808456421,
|
|
"epoch": 0.16974389517569982,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499970983395912,
|
|
"loss": 5.7749,
|
|
"mean_token_accuracy": 0.1379993349313736,
|
|
"num_tokens": 3989214.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 5.8641180992126465,
|
|
"epoch": 0.1703394877903514,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999702950220841,
|
|
"loss": 5.8171,
|
|
"mean_token_accuracy": 0.13948396891355513,
|
|
"num_tokens": 4003753.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 5.813231992721557,
|
|
"epoch": 0.17093508040500296,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999695985789376,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.14068178609013557,
|
|
"num_tokens": 4018739.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 5.918139839172364,
|
|
"epoch": 0.17153067301965455,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999688940664972,
|
|
"loss": 5.8376,
|
|
"mean_token_accuracy": 0.13687685504555702,
|
|
"num_tokens": 4031822.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.734128141403199,
|
|
"epoch": 0.17212626563430614,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999681814847884,
|
|
"loss": 5.8234,
|
|
"mean_token_accuracy": 0.13391316756606103,
|
|
"num_tokens": 4044757.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 5.782984876632691,
|
|
"epoch": 0.17272185824895772,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999674608338367,
|
|
"loss": 5.7789,
|
|
"mean_token_accuracy": 0.1411241516470909,
|
|
"num_tokens": 4059795.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.888040351867676,
|
|
"epoch": 0.17331745086360928,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999667321136681,
|
|
"loss": 5.8173,
|
|
"mean_token_accuracy": 0.1328122280538082,
|
|
"num_tokens": 4074772.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 5.833181715011596,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999659953243085,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.13597047850489616,
|
|
"num_tokens": 4088534.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 5.796741914749146,
|
|
"epoch": 0.17450863609291245,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999652504657844,
|
|
"loss": 5.7593,
|
|
"mean_token_accuracy": 0.14187394827604294,
|
|
"num_tokens": 4101729.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.783657884597778,
|
|
"epoch": 0.17510422870756404,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999644975381226,
|
|
"loss": 5.6827,
|
|
"mean_token_accuracy": 0.14450945556163788,
|
|
"num_tokens": 4114463.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.774881029129029,
|
|
"epoch": 0.1756998213222156,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049996373654135,
|
|
"loss": 5.7424,
|
|
"mean_token_accuracy": 0.14521931260824203,
|
|
"num_tokens": 4125822.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.805322170257568,
|
|
"epoch": 0.17629541393686718,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999629674754939,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.1433507151901722,
|
|
"num_tokens": 4139385.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.848616600036621,
|
|
"epoch": 0.17689100655151876,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999621903405819,
|
|
"loss": 5.8574,
|
|
"mean_token_accuracy": 0.13608190417289734,
|
|
"num_tokens": 4153713.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.782891273498535,
|
|
"epoch": 0.17748659916617035,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999614051366421,
|
|
"loss": 5.8227,
|
|
"mean_token_accuracy": 0.14468563795089723,
|
|
"num_tokens": 4167030.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.82030348777771,
|
|
"epoch": 0.1780821917808219,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999606118637022,
|
|
"loss": 5.7238,
|
|
"mean_token_accuracy": 0.1424116462469101,
|
|
"num_tokens": 4179525.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.682341051101685,
|
|
"epoch": 0.1786777843954735,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999598105217911,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.14158212393522263,
|
|
"num_tokens": 4193234.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.924993562698364,
|
|
"epoch": 0.17927337701012508,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999590011109373,
|
|
"loss": 5.9474,
|
|
"mean_token_accuracy": 0.12760818526148796,
|
|
"num_tokens": 4207822.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.791831111907959,
|
|
"epoch": 0.17986896962477666,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049995818363117,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.14670312032103539,
|
|
"num_tokens": 4219990.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 5.646500873565674,
|
|
"epoch": 0.18046456223942822,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999573580825182,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.15209764167666434,
|
|
"num_tokens": 4232842.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.853263998031617,
|
|
"epoch": 0.1810601548540798,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999565244650119,
|
|
"loss": 5.7444,
|
|
"mean_token_accuracy": 0.1347513236105442,
|
|
"num_tokens": 4247750.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.776639366149903,
|
|
"epoch": 0.1816557474687314,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999556827786807,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.1356727160513401,
|
|
"num_tokens": 4260757.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.827703523635864,
|
|
"epoch": 0.18225134008338298,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999548330235549,
|
|
"loss": 5.8003,
|
|
"mean_token_accuracy": 0.13830092325806617,
|
|
"num_tokens": 4274430.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.752081108093262,
|
|
"epoch": 0.18284693269803454,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999539751996651,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.14565676748752593,
|
|
"num_tokens": 4288289.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.777690315246582,
|
|
"epoch": 0.18344252531268612,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499953109307042,
|
|
"loss": 5.8105,
|
|
"mean_token_accuracy": 0.13344356566667556,
|
|
"num_tokens": 4303460.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.801181411743164,
|
|
"epoch": 0.1840381179273377,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999522353457165,
|
|
"loss": 5.771,
|
|
"mean_token_accuracy": 0.13815060928463935,
|
|
"num_tokens": 4317812.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.818474054336548,
|
|
"epoch": 0.18463371054198927,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999513533157201,
|
|
"loss": 5.7267,
|
|
"mean_token_accuracy": 0.1442296251654625,
|
|
"num_tokens": 4331298.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.913740921020508,
|
|
"epoch": 0.18522930315664085,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999504632170844,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.13668199330568315,
|
|
"num_tokens": 4347241.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.761168909072876,
|
|
"epoch": 0.18582489577129244,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999495650498413,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.13772947415709497,
|
|
"num_tokens": 4363523.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.626205492019653,
|
|
"epoch": 0.18642048838594402,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999486588140231,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.14980704039335252,
|
|
"num_tokens": 4375701.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.837887191772461,
|
|
"epoch": 0.18701608100059558,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999477445096623,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.13793421611189843,
|
|
"num_tokens": 4388482.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 5.83662486076355,
|
|
"epoch": 0.18761167361524717,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999468221367916,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.14257378950715066,
|
|
"num_tokens": 4404275.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 5.731053400039673,
|
|
"epoch": 0.18820726622989875,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999458916954442,
|
|
"loss": 5.6802,
|
|
"mean_token_accuracy": 0.14752077162265778,
|
|
"num_tokens": 4418076.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.699216699600219,
|
|
"epoch": 0.18880285884455034,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999449531856532,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.14875944927334786,
|
|
"num_tokens": 4431241.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.754944276809693,
|
|
"epoch": 0.1893984514592019,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999440066074526,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.14274367392063142,
|
|
"num_tokens": 4443915.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.8164297580719,
|
|
"epoch": 0.18999404407385348,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999430519608762,
|
|
"loss": 5.8812,
|
|
"mean_token_accuracy": 0.13719657063484192,
|
|
"num_tokens": 4459976.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.859114503860473,
|
|
"epoch": 0.19058963668850507,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999420892459584,
|
|
"loss": 5.7933,
|
|
"mean_token_accuracy": 0.14052336663007736,
|
|
"num_tokens": 4473955.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.805715656280517,
|
|
"epoch": 0.19118522930315665,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999411184627334,
|
|
"loss": 5.7579,
|
|
"mean_token_accuracy": 0.13912855982780456,
|
|
"num_tokens": 4489008.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 5.654722356796265,
|
|
"epoch": 0.1917808219178082,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999401396112364,
|
|
"loss": 5.6527,
|
|
"mean_token_accuracy": 0.15566126704216005,
|
|
"num_tokens": 4502755.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.819410371780395,
|
|
"epoch": 0.1923764145324598,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.000499939152691502,
|
|
"loss": 5.804,
|
|
"mean_token_accuracy": 0.13783913254737853,
|
|
"num_tokens": 4518225.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.7462883472442625,
|
|
"epoch": 0.19297200714711138,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999381577035663,
|
|
"loss": 5.6551,
|
|
"mean_token_accuracy": 0.14321220964193343,
|
|
"num_tokens": 4533246.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.748630619049072,
|
|
"epoch": 0.19356759976176297,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999371546474643,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.13609145805239678,
|
|
"num_tokens": 4547726.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.843517255783081,
|
|
"epoch": 0.19416319237641452,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999361435232324,
|
|
"loss": 5.8287,
|
|
"mean_token_accuracy": 0.13276094049215317,
|
|
"num_tokens": 4564462.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.787928628921509,
|
|
"epoch": 0.1947587849910661,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999351243309069,
|
|
"loss": 5.7461,
|
|
"mean_token_accuracy": 0.13809694945812226,
|
|
"num_tokens": 4578846.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.655702304840088,
|
|
"epoch": 0.1953543776057177,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999340970705241,
|
|
"loss": 5.6239,
|
|
"mean_token_accuracy": 0.15109889954328537,
|
|
"num_tokens": 4593547.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.755260896682739,
|
|
"epoch": 0.19594997022036928,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999330617421209,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.1424178197979927,
|
|
"num_tokens": 4607466.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.723298645019531,
|
|
"epoch": 0.19654556283502084,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999320183457346,
|
|
"loss": 5.5985,
|
|
"mean_token_accuracy": 0.1444603107869625,
|
|
"num_tokens": 4621624.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.705548715591431,
|
|
"epoch": 0.19714115544967242,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999309668814024,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.14449623450636864,
|
|
"num_tokens": 4635720.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.70385103225708,
|
|
"epoch": 0.197736748064324,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999299073491623,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.14465972408652306,
|
|
"num_tokens": 4649614.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.704717636108398,
|
|
"epoch": 0.1983323406789756,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999288397490519,
|
|
"loss": 5.7262,
|
|
"mean_token_accuracy": 0.14485595375299454,
|
|
"num_tokens": 4661930.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.8053113460540775,
|
|
"epoch": 0.19892793329362715,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999277640811099,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.13924995958805084,
|
|
"num_tokens": 4677016.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.76533784866333,
|
|
"epoch": 0.19952352590827874,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999266803453747,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.13738572895526885,
|
|
"num_tokens": 4692780.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.859240913391114,
|
|
"epoch": 0.20011911852293032,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999255885418852,
|
|
"loss": 5.7529,
|
|
"mean_token_accuracy": 0.14031027108430863,
|
|
"num_tokens": 4707069.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.587999677658081,
|
|
"epoch": 0.20071471113758188,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999244886706804,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.1414187543094158,
|
|
"num_tokens": 4720658.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.747998857498169,
|
|
"epoch": 0.20131030375223347,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999233807318001,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.14377131387591363,
|
|
"num_tokens": 4735901.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.779743480682373,
|
|
"epoch": 0.20190589636688505,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999222647252837,
|
|
"loss": 5.8481,
|
|
"mean_token_accuracy": 0.1373508520424366,
|
|
"num_tokens": 4748725.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.85775933265686,
|
|
"epoch": 0.20250148898153664,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999211406511714,
|
|
"loss": 5.7419,
|
|
"mean_token_accuracy": 0.14132971242070197,
|
|
"num_tokens": 4761593.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.792934560775757,
|
|
"epoch": 0.2030970815961882,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999200085095035,
|
|
"loss": 5.7179,
|
|
"mean_token_accuracy": 0.14656025990843774,
|
|
"num_tokens": 4774304.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.6804450988769535,
|
|
"epoch": 0.20369267421083978,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999188683003207,
|
|
"loss": 5.7936,
|
|
"mean_token_accuracy": 0.1404182009398937,
|
|
"num_tokens": 4787350.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.73920841217041,
|
|
"epoch": 0.20428826682549137,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999177200236635,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.1406928777694702,
|
|
"num_tokens": 4801465.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.676250267028808,
|
|
"epoch": 0.20488385944014295,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999165636795736,
|
|
"loss": 5.6794,
|
|
"mean_token_accuracy": 0.1428268074989319,
|
|
"num_tokens": 4815757.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.738760232925415,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999153992680923,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.14227156564593316,
|
|
"num_tokens": 4830164.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.654473495483399,
|
|
"epoch": 0.2060750446694461,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999142267892612,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.14343090057373048,
|
|
"num_tokens": 4844459.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.766673851013183,
|
|
"epoch": 0.20667063728409768,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999130462431224,
|
|
"loss": 5.7361,
|
|
"mean_token_accuracy": 0.14459356814622878,
|
|
"num_tokens": 4859189.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.688421630859375,
|
|
"epoch": 0.20726622989874927,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999118576297185,
|
|
"loss": 5.6935,
|
|
"mean_token_accuracy": 0.14029275998473167,
|
|
"num_tokens": 4872911.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.72867169380188,
|
|
"epoch": 0.20786182251340082,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999106609490918,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.14949437230825424,
|
|
"num_tokens": 4886260.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.551301145553589,
|
|
"epoch": 0.2084574151280524,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999094562012855,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.15529464185237885,
|
|
"num_tokens": 4899177.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.7142641067504885,
|
|
"epoch": 0.209053007742704,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999082433863426,
|
|
"loss": 5.6899,
|
|
"mean_token_accuracy": 0.14636550471186638,
|
|
"num_tokens": 4912071.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.719062948226929,
|
|
"epoch": 0.20964860035735558,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999070225043068,
|
|
"loss": 5.633,
|
|
"mean_token_accuracy": 0.151872980594635,
|
|
"num_tokens": 4925247.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.700354337692261,
|
|
"epoch": 0.21024419297200714,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999057935552217,
|
|
"loss": 5.7197,
|
|
"mean_token_accuracy": 0.13777152076363564,
|
|
"num_tokens": 4940380.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.657257556915283,
|
|
"epoch": 0.21083978558665872,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999045565391313,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.14291160702705383,
|
|
"num_tokens": 4955868.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.669415378570557,
|
|
"epoch": 0.2114353782013103,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999033114560803,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.1378536157310009,
|
|
"num_tokens": 4969986.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.650237560272217,
|
|
"epoch": 0.2120309708159619,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999020583061132,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.14477901309728622,
|
|
"num_tokens": 4985980.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.543969392776489,
|
|
"epoch": 0.21262656343061345,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999007970892749,
|
|
"loss": 5.6714,
|
|
"mean_token_accuracy": 0.1439763016998768,
|
|
"num_tokens": 5001932.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.755097055435181,
|
|
"epoch": 0.21322215604526504,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998995278056107,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.1511471077799797,
|
|
"num_tokens": 5015375.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.699004793167115,
|
|
"epoch": 0.21381774865991662,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998982504551661,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.1431986965239048,
|
|
"num_tokens": 5030520.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.749127340316773,
|
|
"epoch": 0.2144133412745682,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998969650379869,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.14594390541315078,
|
|
"num_tokens": 5045020.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.673582410812378,
|
|
"epoch": 0.21500893388921977,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998956715541192,
|
|
"loss": 5.5861,
|
|
"mean_token_accuracy": 0.14868769645690919,
|
|
"num_tokens": 5058195.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.644132137298584,
|
|
"epoch": 0.21560452650387135,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004998943700036095,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.14966169148683547,
|
|
"num_tokens": 5071687.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.696914720535278,
|
|
"epoch": 0.21620011911852294,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998930603865042,
|
|
"loss": 5.6679,
|
|
"mean_token_accuracy": 0.14220030829310418,
|
|
"num_tokens": 5083817.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.642614126205444,
|
|
"epoch": 0.2167957117331745,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998917427028507,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.14766469597816467,
|
|
"num_tokens": 5097957.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.710134077072143,
|
|
"epoch": 0.21739130434782608,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998904169526959,
|
|
"loss": 5.6165,
|
|
"mean_token_accuracy": 0.14077215045690536,
|
|
"num_tokens": 5112681.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.687772035598755,
|
|
"epoch": 0.21798689696247767,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998890831360876,
|
|
"loss": 5.6713,
|
|
"mean_token_accuracy": 0.1482035130262375,
|
|
"num_tokens": 5126152.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.560128879547119,
|
|
"epoch": 0.21858248957712925,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998877412530735,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.14646678864955903,
|
|
"num_tokens": 5140452.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.74810299873352,
|
|
"epoch": 0.2191780821917808,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998863913037017,
|
|
"loss": 5.6919,
|
|
"mean_token_accuracy": 0.14428742378950118,
|
|
"num_tokens": 5155020.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.7484598636627195,
|
|
"epoch": 0.2197736748064324,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998850332880208,
|
|
"loss": 5.7132,
|
|
"mean_token_accuracy": 0.14533886685967445,
|
|
"num_tokens": 5169321.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.6707848072052,
|
|
"epoch": 0.22036926742108398,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998836672060795,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.1479350209236145,
|
|
"num_tokens": 5182156.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.610133266448974,
|
|
"epoch": 0.22096486003573557,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998822930579264,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.14574619606137276,
|
|
"num_tokens": 5196543.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.624956130981445,
|
|
"epoch": 0.22156045265038712,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998809108436112,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.14943063110113144,
|
|
"num_tokens": 5210454.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.747320365905762,
|
|
"epoch": 0.2221560452650387,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998795205631834,
|
|
"loss": 5.7551,
|
|
"mean_token_accuracy": 0.14024493992328643,
|
|
"num_tokens": 5226371.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.715463066101075,
|
|
"epoch": 0.2227516378796903,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998781222166929,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.15357023924589158,
|
|
"num_tokens": 5239182.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.556571531295776,
|
|
"epoch": 0.22334723049434188,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998767158041897,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.14915079325437547,
|
|
"num_tokens": 5254704.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.6563550472259525,
|
|
"epoch": 0.22394282310899344,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998753013257242,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.1510499246418476,
|
|
"num_tokens": 5267218.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.668066740036011,
|
|
"epoch": 0.22453841572364502,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998738787813475,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.14566683918237686,
|
|
"num_tokens": 5282376.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.6751463413238525,
|
|
"epoch": 0.2251340083382966,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998724481711103,
|
|
"loss": 5.6331,
|
|
"mean_token_accuracy": 0.1392289698123932,
|
|
"num_tokens": 5296135.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.619709253311157,
|
|
"epoch": 0.2257296009529482,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000499871009495064,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.14957272559404372,
|
|
"num_tokens": 5310347.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.670946788787842,
|
|
"epoch": 0.22632519356759975,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998695627532601,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.14258143156766892,
|
|
"num_tokens": 5324958.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.6233381748199465,
|
|
"epoch": 0.22692078618225134,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998681079457507,
|
|
"loss": 5.5784,
|
|
"mean_token_accuracy": 0.15065757185220718,
|
|
"num_tokens": 5338913.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.532181072235107,
|
|
"epoch": 0.22751637879690292,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499866645072588,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.15489899218082429,
|
|
"num_tokens": 5351151.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.557806491851807,
|
|
"epoch": 0.2281119714115545,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998651741338242,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.15164206326007842,
|
|
"num_tokens": 5365139.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.699223184585572,
|
|
"epoch": 0.22870756402620607,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998636951295122,
|
|
"loss": 5.643,
|
|
"mean_token_accuracy": 0.14435275942087172,
|
|
"num_tokens": 5378821.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.679220581054688,
|
|
"epoch": 0.22930315664085765,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998622080597052,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.14569860696792603,
|
|
"num_tokens": 5393912.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.733732461929321,
|
|
"epoch": 0.22989874925550924,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998607129244563,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.14999704211950302,
|
|
"num_tokens": 5406373.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.583739757537842,
|
|
"epoch": 0.23049434187016082,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004998592097238192,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.15077932178974152,
|
|
"num_tokens": 5421701.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.576291131973266,
|
|
"epoch": 0.23108993448481238,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998576984578479,
|
|
"loss": 5.6332,
|
|
"mean_token_accuracy": 0.14954315945506097,
|
|
"num_tokens": 5435584.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.653451013565063,
|
|
"epoch": 0.23168552709946397,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998561791265966,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.1414521925151348,
|
|
"num_tokens": 5451241.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.820071506500244,
|
|
"epoch": 0.23228111971411555,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998546517301196,
|
|
"loss": 5.783,
|
|
"mean_token_accuracy": 0.1384517103433609,
|
|
"num_tokens": 5465740.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.586044025421143,
|
|
"epoch": 0.2328767123287671,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499853116268472,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.1578419104218483,
|
|
"num_tokens": 5479142.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.779767656326294,
|
|
"epoch": 0.2334723049434187,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998515727417086,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.1537806749343872,
|
|
"num_tokens": 5491503.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.529689502716065,
|
|
"epoch": 0.23406789755807028,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998500211498848,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.14899630472064018,
|
|
"num_tokens": 5506817.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.6961085319519045,
|
|
"epoch": 0.23466349017272187,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998484614930566,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.15120958238840104,
|
|
"num_tokens": 5519223.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.654959869384766,
|
|
"epoch": 0.23525908278737342,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998468937712794,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.14365786761045457,
|
|
"num_tokens": 5534904.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.617275905609131,
|
|
"epoch": 0.235854675402025,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998453179846098,
|
|
"loss": 5.6027,
|
|
"mean_token_accuracy": 0.14905235320329666,
|
|
"num_tokens": 5548815.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.654763984680176,
|
|
"epoch": 0.2364502680166766,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998437341331043,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.1459970399737358,
|
|
"num_tokens": 5563277.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.587750196456909,
|
|
"epoch": 0.23704586063132818,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998421422168195,
|
|
"loss": 5.659,
|
|
"mean_token_accuracy": 0.14965421855449676,
|
|
"num_tokens": 5576083.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.706011724472046,
|
|
"epoch": 0.23764145324597974,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998405422358126,
|
|
"loss": 5.6356,
|
|
"mean_token_accuracy": 0.14720665365457536,
|
|
"num_tokens": 5592293.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.513312196731567,
|
|
"epoch": 0.23823704586063132,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998389341901411,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.1590567409992218,
|
|
"num_tokens": 5606088.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.579891490936279,
|
|
"epoch": 0.2388326384752829,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998373180798626,
|
|
"loss": 5.5975,
|
|
"mean_token_accuracy": 0.1506177693605423,
|
|
"num_tokens": 5620039.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.621408700942993,
|
|
"epoch": 0.2394282310899345,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998356939050351,
|
|
"loss": 5.6128,
|
|
"mean_token_accuracy": 0.15120112746953965,
|
|
"num_tokens": 5634738.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.612809419631958,
|
|
"epoch": 0.24002382370458605,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998340616657168,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.15441277325153352,
|
|
"num_tokens": 5649410.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.547980737686157,
|
|
"epoch": 0.24061941631923764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998324213619661,
|
|
"loss": 5.6117,
|
|
"mean_token_accuracy": 0.15096269100904464,
|
|
"num_tokens": 5662641.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.638765907287597,
|
|
"epoch": 0.24121500893388922,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998307729938423,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.14986175447702407,
|
|
"num_tokens": 5675558.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.576672315597534,
|
|
"epoch": 0.2418106015485408,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499829116561404,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.15497359335422517,
|
|
"num_tokens": 5690152.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.643048667907715,
|
|
"epoch": 0.24240619416319237,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998274520647109,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.1457630604505539,
|
|
"num_tokens": 5705378.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.586351442337036,
|
|
"epoch": 0.24300178677784395,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998257795038227,
|
|
"loss": 5.5812,
|
|
"mean_token_accuracy": 0.1412225842475891,
|
|
"num_tokens": 5718470.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.603373575210571,
|
|
"epoch": 0.24359737939249554,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998240988787992,
|
|
"loss": 5.5281,
|
|
"mean_token_accuracy": 0.15168666690587998,
|
|
"num_tokens": 5731073.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.561460399627686,
|
|
"epoch": 0.24419297200714712,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998224101897009,
|
|
"loss": 5.5096,
|
|
"mean_token_accuracy": 0.1544557362794876,
|
|
"num_tokens": 5744978.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.634655427932739,
|
|
"epoch": 0.24478856462179868,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998207134365883,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.1519363395869732,
|
|
"num_tokens": 5758723.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.579699611663818,
|
|
"epoch": 0.24538415723645027,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998190086195223,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.1522880531847477,
|
|
"num_tokens": 5773646.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.599841833114624,
|
|
"epoch": 0.24597974985110185,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998172957385638,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.15073204189538955,
|
|
"num_tokens": 5787226.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.643059778213501,
|
|
"epoch": 0.2465753424657534,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998155747937746,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.14982610195875168,
|
|
"num_tokens": 5801378.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.538309001922608,
|
|
"epoch": 0.247170935080405,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998138457852162,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.15543757528066635,
|
|
"num_tokens": 5815136.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.6487654685974125,
|
|
"epoch": 0.24776652769505658,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998121087129507,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.1503599464893341,
|
|
"num_tokens": 5830222.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.611774110794068,
|
|
"epoch": 0.24836212030970817,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998103635770404,
|
|
"loss": 5.5526,
|
|
"mean_token_accuracy": 0.14430395886301994,
|
|
"num_tokens": 5844289.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.639391088485718,
|
|
"epoch": 0.24895771292435973,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998086103775478,
|
|
"loss": 5.6029,
|
|
"mean_token_accuracy": 0.15167520940303802,
|
|
"num_tokens": 5857876.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.599852991104126,
|
|
"epoch": 0.2495533055390113,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998068491145359,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.1492688849568367,
|
|
"num_tokens": 5872032.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.57262692451477,
|
|
"epoch": 0.25014889815366287,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004998050797880678,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.15030869022011756,
|
|
"num_tokens": 5885478.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.667693948745727,
|
|
"epoch": 0.25074449076831445,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998033023982071,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.13999789506196975,
|
|
"num_tokens": 5900888.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.585479688644409,
|
|
"epoch": 0.25134008338296604,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004998015169450174,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.15590790659189224,
|
|
"num_tokens": 5917158.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.620886516571045,
|
|
"epoch": 0.2519356759976176,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997997234285627,
|
|
"loss": 5.6856,
|
|
"mean_token_accuracy": 0.14640604853630065,
|
|
"num_tokens": 5931879.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.519533967971801,
|
|
"epoch": 0.2525312686122692,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997979218489076,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.15180157423019408,
|
|
"num_tokens": 5947015.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.560195875167847,
|
|
"epoch": 0.2531268612269208,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997961122061164,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.1554577589035034,
|
|
"num_tokens": 5962063.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.503729009628296,
|
|
"epoch": 0.2537224538415724,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997942945002543,
|
|
"loss": 5.4802,
|
|
"mean_token_accuracy": 0.15521877706050874,
|
|
"num_tokens": 5977697.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.588429594039917,
|
|
"epoch": 0.25431804645622397,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997924687313862,
|
|
"loss": 5.561,
|
|
"mean_token_accuracy": 0.14824481457471847,
|
|
"num_tokens": 5994117.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.598195791244507,
|
|
"epoch": 0.2549136390708755,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997906348995777,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.14945415854454042,
|
|
"num_tokens": 6009878.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.562610387802124,
|
|
"epoch": 0.2555092316855271,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997887930048947,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.15528906434774398,
|
|
"num_tokens": 6021152.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.633448886871338,
|
|
"epoch": 0.25610482430017867,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997869430474033,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.148657363653183,
|
|
"num_tokens": 6035975.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.493651676177978,
|
|
"epoch": 0.25670041691483025,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997850850271696,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.15547298192977904,
|
|
"num_tokens": 6048326.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.714857149124145,
|
|
"epoch": 0.25729600952948184,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997832189442604,
|
|
"loss": 5.6453,
|
|
"mean_token_accuracy": 0.14458195567131044,
|
|
"num_tokens": 6063327.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.516817092895508,
|
|
"epoch": 0.2578916021441334,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997813447987426,
|
|
"loss": 5.5346,
|
|
"mean_token_accuracy": 0.15302059799432755,
|
|
"num_tokens": 6077207.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.557005834579468,
|
|
"epoch": 0.258487194758785,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997794625906834,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.14849791079759597,
|
|
"num_tokens": 6094691.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.544890403747559,
|
|
"epoch": 0.2590827873734366,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997775723201504,
|
|
"loss": 5.5917,
|
|
"mean_token_accuracy": 0.1523435041308403,
|
|
"num_tokens": 6108539.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.627376508712769,
|
|
"epoch": 0.2596783799880881,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004997756739872112,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.15201560631394387,
|
|
"num_tokens": 6122799.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.628005313873291,
|
|
"epoch": 0.2602739726027397,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997737675919344,
|
|
"loss": 5.535,
|
|
"mean_token_accuracy": 0.15769754499197006,
|
|
"num_tokens": 6137525.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.642975378036499,
|
|
"epoch": 0.2608695652173913,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997718531343877,
|
|
"loss": 5.6649,
|
|
"mean_token_accuracy": 0.15091277658939362,
|
|
"num_tokens": 6151418.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.647090005874634,
|
|
"epoch": 0.2614651578320429,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997699306146402,
|
|
"loss": 5.5524,
|
|
"mean_token_accuracy": 0.1532282918691635,
|
|
"num_tokens": 6164839.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.458707809448242,
|
|
"epoch": 0.26206075044669447,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997680000327607,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.15762893110513687,
|
|
"num_tokens": 6179641.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.622094058990479,
|
|
"epoch": 0.26265634306134605,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997660613888185,
|
|
"loss": 5.6756,
|
|
"mean_token_accuracy": 0.1433737836778164,
|
|
"num_tokens": 6196204.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.682926988601684,
|
|
"epoch": 0.26325193567599764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997641146828831,
|
|
"loss": 5.5642,
|
|
"mean_token_accuracy": 0.14888232350349426,
|
|
"num_tokens": 6210704.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.503525447845459,
|
|
"epoch": 0.26384752829064917,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997621599150244,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.15796472728252411,
|
|
"num_tokens": 6226028.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.652449989318848,
|
|
"epoch": 0.26444312090530075,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997601970853124,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.14928244948387145,
|
|
"num_tokens": 6242376.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.536260080337525,
|
|
"epoch": 0.26503871351995234,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997582261938177,
|
|
"loss": 5.5522,
|
|
"mean_token_accuracy": 0.1493092805147171,
|
|
"num_tokens": 6255471.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.567584276199341,
|
|
"epoch": 0.2656343061346039,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997562472406107,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.15504778176546097,
|
|
"num_tokens": 6268081.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.5058043003082275,
|
|
"epoch": 0.2662298987492555,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997542602257626,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.16001959890127182,
|
|
"num_tokens": 6281765.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.631291294097901,
|
|
"epoch": 0.2668254913639071,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997522651493447,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.15439495742321013,
|
|
"num_tokens": 6297392.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.440597629547119,
|
|
"epoch": 0.2674210839785587,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997502620114284,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.1568073809146881,
|
|
"num_tokens": 6310726.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.581234979629516,
|
|
"epoch": 0.26801667659321027,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997482508120856,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.15630035251379013,
|
|
"num_tokens": 6325290.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.534018611907959,
|
|
"epoch": 0.2686122692078618,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997462315513884,
|
|
"loss": 5.5575,
|
|
"mean_token_accuracy": 0.1511783219873905,
|
|
"num_tokens": 6340056.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.565044975280761,
|
|
"epoch": 0.2692078618225134,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997442042294095,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.15828397274017333,
|
|
"num_tokens": 6353378.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.499336910247803,
|
|
"epoch": 0.26980345443716497,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997421688462213,
|
|
"loss": 5.5197,
|
|
"mean_token_accuracy": 0.15514147728681565,
|
|
"num_tokens": 6365916.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.515630769729614,
|
|
"epoch": 0.27039904705181655,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997401254018969,
|
|
"loss": 5.5804,
|
|
"mean_token_accuracy": 0.15608943179249762,
|
|
"num_tokens": 6380274.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.63983187675476,
|
|
"epoch": 0.27099463966646814,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997380738965096,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.1525450125336647,
|
|
"num_tokens": 6394769.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.501612615585327,
|
|
"epoch": 0.2715902322811197,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499736014330133,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.15416092649102212,
|
|
"num_tokens": 6408980.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.562344121932983,
|
|
"epoch": 0.2721858248957713,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997339467028409,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.1564989537000656,
|
|
"num_tokens": 6424267.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.484875059127807,
|
|
"epoch": 0.2727814175104229,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997318710147076,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.1572253793478012,
|
|
"num_tokens": 6438827.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.504929876327514,
|
|
"epoch": 0.2733770101250744,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997297872658075,
|
|
"loss": 5.5557,
|
|
"mean_token_accuracy": 0.1523042641580105,
|
|
"num_tokens": 6453040.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.571640300750732,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997276954562152,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.15259954780340196,
|
|
"num_tokens": 6469960.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.524302244186401,
|
|
"epoch": 0.2745681953543776,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499725595586006,
|
|
"loss": 5.5148,
|
|
"mean_token_accuracy": 0.15153526440262793,
|
|
"num_tokens": 6483914.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.481719923019409,
|
|
"epoch": 0.2751637879690292,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499723487655255,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.1635773852467537,
|
|
"num_tokens": 6497290.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.451037263870239,
|
|
"epoch": 0.27575938058368077,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997213716640378,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.1593978598713875,
|
|
"num_tokens": 6512558.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.55248498916626,
|
|
"epoch": 0.27635497319833235,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997192476124306,
|
|
"loss": 5.5285,
|
|
"mean_token_accuracy": 0.1506356790661812,
|
|
"num_tokens": 6527786.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.489588832855224,
|
|
"epoch": 0.27695056581298394,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997171155005091,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.15420492514967918,
|
|
"num_tokens": 6540925.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.549788761138916,
|
|
"epoch": 0.27754615842763547,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997149753283502,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.15867618471384048,
|
|
"num_tokens": 6553945.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.546188163757324,
|
|
"epoch": 0.27814175104228706,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997128270960304,
|
|
"loss": 5.5361,
|
|
"mean_token_accuracy": 0.15756761133670807,
|
|
"num_tokens": 6568986.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.51469316482544,
|
|
"epoch": 0.27873734365693864,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997106708036268,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.15648434907197953,
|
|
"num_tokens": 6582219.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.514825820922852,
|
|
"epoch": 0.2793329362715902,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499708506451217,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.15382600873708724,
|
|
"num_tokens": 6597670.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.472731351852417,
|
|
"epoch": 0.2799285288862418,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997063340388783,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.1536533683538437,
|
|
"num_tokens": 6612923.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.654265832901001,
|
|
"epoch": 0.2805241215008934,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997041535666888,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.15547987520694734,
|
|
"num_tokens": 6624762.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.47929539680481,
|
|
"epoch": 0.281119714115545,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997019650347266,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.16410839110612868,
|
|
"num_tokens": 6637910.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.559927845001221,
|
|
"epoch": 0.28171530673019657,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996997684430703,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.15269914865493775,
|
|
"num_tokens": 6652212.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.607529926300049,
|
|
"epoch": 0.2823108993448481,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996975637917986,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.15335794538259506,
|
|
"num_tokens": 6665535.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.522451877593994,
|
|
"epoch": 0.2829064919594997,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996953510809906,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.1573646143078804,
|
|
"num_tokens": 6680013.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.474905681610108,
|
|
"epoch": 0.28350208457415127,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996931303107258,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.16218856275081633,
|
|
"num_tokens": 6692384.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.547728490829468,
|
|
"epoch": 0.28409767718880286,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996909014810837,
|
|
"loss": 5.5649,
|
|
"mean_token_accuracy": 0.15507043153047562,
|
|
"num_tokens": 6707127.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.550915861129761,
|
|
"epoch": 0.28469326980345444,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996886645921442,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.15639798492193221,
|
|
"num_tokens": 6720434.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.533693742752075,
|
|
"epoch": 0.285288862418106,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996864196439877,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.15171108916401863,
|
|
"num_tokens": 6734457.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.611560487747193,
|
|
"epoch": 0.2858844550327576,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996841666366947,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.1505224272608757,
|
|
"num_tokens": 6750351.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.568129014968872,
|
|
"epoch": 0.2864800476474092,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996819055703458,
|
|
"loss": 5.4893,
|
|
"mean_token_accuracy": 0.1573476240038872,
|
|
"num_tokens": 6765252.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.4718255519866945,
|
|
"epoch": 0.2870756402620607,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996796364450224,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.16412098705768585,
|
|
"num_tokens": 6778020.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.467345714569092,
|
|
"epoch": 0.2876712328767123,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996773592608057,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.15717938616871835,
|
|
"num_tokens": 6792233.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.631177234649658,
|
|
"epoch": 0.2882668254913639,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004996750740177775,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.1473295234143734,
|
|
"num_tokens": 6807781.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.487263298034668,
|
|
"epoch": 0.2888624181060155,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996727807160196,
|
|
"loss": 5.4252,
|
|
"mean_token_accuracy": 0.1559780791401863,
|
|
"num_tokens": 6822406.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.434000778198242,
|
|
"epoch": 0.28945801072066707,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996704793556144,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.15532006844878196,
|
|
"num_tokens": 6835192.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.5276360511779785,
|
|
"epoch": 0.29005360333531865,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996681699366443,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.1642896570265293,
|
|
"num_tokens": 6846921.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.449465227127075,
|
|
"epoch": 0.29064919594997024,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996658524591924,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.15894800424575806,
|
|
"num_tokens": 6864195.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.4732872486114506,
|
|
"epoch": 0.2912447885646218,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996635269233415,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.15463075190782546,
|
|
"num_tokens": 6879095.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.538870716094971,
|
|
"epoch": 0.29184038117927336,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996611933291752,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.15347446203231813,
|
|
"num_tokens": 6891853.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.488425540924072,
|
|
"epoch": 0.29243597379392494,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996588516767772,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.15637132674455642,
|
|
"num_tokens": 6905235.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.445037984848023,
|
|
"epoch": 0.2930315664085765,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996565019662315,
|
|
"loss": 5.4086,
|
|
"mean_token_accuracy": 0.1620157092809677,
|
|
"num_tokens": 6918438.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.556691694259643,
|
|
"epoch": 0.2936271590232281,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996541441976223,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.15580268949270248,
|
|
"num_tokens": 6931749.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.41625943183899,
|
|
"epoch": 0.2942227516378797,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996517783710342,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.1657080754637718,
|
|
"num_tokens": 6946114.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.464704513549805,
|
|
"epoch": 0.2948183442525313,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996494044865521,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.16308145672082902,
|
|
"num_tokens": 6959002.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.462369823455811,
|
|
"epoch": 0.29541393686718287,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996470225442611,
|
|
"loss": 5.4379,
|
|
"mean_token_accuracy": 0.1621774911880493,
|
|
"num_tokens": 6973248.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.439143276214599,
|
|
"epoch": 0.2960095294818344,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996446325442466,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.16134534627199174,
|
|
"num_tokens": 6985223.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.486586093902588,
|
|
"epoch": 0.296605122096486,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004996422344865945,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.1563646525144577,
|
|
"num_tokens": 6998948.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.529925155639648,
|
|
"epoch": 0.29720071471113757,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996398283713907,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.15724140554666519,
|
|
"num_tokens": 7011594.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.40319790840149,
|
|
"epoch": 0.29779630732578916,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996374141987215,
|
|
"loss": 5.3796,
|
|
"mean_token_accuracy": 0.15711069703102112,
|
|
"num_tokens": 7025451.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.460559272766114,
|
|
"epoch": 0.29839189994044074,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996349919686733,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.1557042881846428,
|
|
"num_tokens": 7038301.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.594391632080078,
|
|
"epoch": 0.2989874925550923,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996325616813334,
|
|
"loss": 5.5285,
|
|
"mean_token_accuracy": 0.15085733383893968,
|
|
"num_tokens": 7053777.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.475944328308105,
|
|
"epoch": 0.2995830851697439,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996301233367886,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.1506906270980835,
|
|
"num_tokens": 7069516.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.504354953765869,
|
|
"epoch": 0.3001786777843955,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996276769351265,
|
|
"loss": 5.4803,
|
|
"mean_token_accuracy": 0.1561206355690956,
|
|
"num_tokens": 7083514.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.483400201797485,
|
|
"epoch": 0.30077427039904703,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996252224764349,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.15447804406285287,
|
|
"num_tokens": 7096637.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.604618883132934,
|
|
"epoch": 0.3013698630136986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996227599608018,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.16393825262784958,
|
|
"num_tokens": 7111994.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.464579486846924,
|
|
"epoch": 0.3019654556283502,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996202893883156,
|
|
"loss": 5.4552,
|
|
"mean_token_accuracy": 0.1592838153243065,
|
|
"num_tokens": 7125148.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.523389482498169,
|
|
"epoch": 0.3025610482430018,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996178107590648,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.1515936940908432,
|
|
"num_tokens": 7140015.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.590457582473755,
|
|
"epoch": 0.30315664085765337,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996153240731381,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.15576473325490953,
|
|
"num_tokens": 7152939.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.509400939941406,
|
|
"epoch": 0.30375223347230496,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996128293306251,
|
|
"loss": 5.5119,
|
|
"mean_token_accuracy": 0.15211765915155412,
|
|
"num_tokens": 7167115.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.53568320274353,
|
|
"epoch": 0.30434782608695654,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996103265316152,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.1530660018324852,
|
|
"num_tokens": 7180455.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.474695062637329,
|
|
"epoch": 0.3049434187016081,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996078156761979,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.16150605976581572,
|
|
"num_tokens": 7193777.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.5531907081604,
|
|
"epoch": 0.30553901131625966,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996052967644636,
|
|
"loss": 5.4828,
|
|
"mean_token_accuracy": 0.16481659412384034,
|
|
"num_tokens": 7205851.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.5045738697052,
|
|
"epoch": 0.30613460393091124,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996027697965024,
|
|
"loss": 5.5714,
|
|
"mean_token_accuracy": 0.15137414932250975,
|
|
"num_tokens": 7221359.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.604192924499512,
|
|
"epoch": 0.3067301965455628,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499600234772405,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.15238548517227174,
|
|
"num_tokens": 7235583.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.501331186294555,
|
|
"epoch": 0.3073257891602144,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995976916922624,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.15776556432247163,
|
|
"num_tokens": 7250477.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.458456039428711,
|
|
"epoch": 0.307921381774866,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995951405561658,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.16063231080770493,
|
|
"num_tokens": 7264197.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.571944093704223,
|
|
"epoch": 0.3085169743895176,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995925813642068,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.15877436697483063,
|
|
"num_tokens": 7278989.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.435719156265259,
|
|
"epoch": 0.30911256700416917,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995900141164768,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.15821941047906876,
|
|
"num_tokens": 7293213.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.51680474281311,
|
|
"epoch": 0.3097081596188207,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995874388130683,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.16242762953042983,
|
|
"num_tokens": 7306774.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.41046462059021,
|
|
"epoch": 0.3103037522334723,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995848554540734,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.16144302636384963,
|
|
"num_tokens": 7321239.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.4373228549957275,
|
|
"epoch": 0.31089934484812387,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499582264039585,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.1644948422908783,
|
|
"num_tokens": 7335872.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.464707851409912,
|
|
"epoch": 0.31149493746277546,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499579664569696,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.15762485861778258,
|
|
"num_tokens": 7350523.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.537588214874267,
|
|
"epoch": 0.31209053007742704,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004995770570444996,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.16230142414569854,
|
|
"num_tokens": 7363201.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.514097690582275,
|
|
"epoch": 0.3126861226920786,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995744414640892,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.16228794306516647,
|
|
"num_tokens": 7375377.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.455860948562622,
|
|
"epoch": 0.3132817153067302,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995718178285587,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.15543222278356553,
|
|
"num_tokens": 7388871.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.485916185379028,
|
|
"epoch": 0.3138773079213818,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995691861380022,
|
|
"loss": 5.3968,
|
|
"mean_token_accuracy": 0.1618770629167557,
|
|
"num_tokens": 7402235.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.4327552318573,
|
|
"epoch": 0.31447290053603333,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995665463925142,
|
|
"loss": 5.4279,
|
|
"mean_token_accuracy": 0.16591655910015107,
|
|
"num_tokens": 7414673.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.462256574630738,
|
|
"epoch": 0.3150684931506849,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995638985921893,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.16255953460931777,
|
|
"num_tokens": 7429039.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.512005710601807,
|
|
"epoch": 0.3156640857653365,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995612427371224,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.15832149088382722,
|
|
"num_tokens": 7443060.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.415192031860352,
|
|
"epoch": 0.3162596783799881,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499558578827409,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.16247346252202988,
|
|
"num_tokens": 7456717.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.397000408172607,
|
|
"epoch": 0.31685527099463967,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995559068631444,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.15859031826257705,
|
|
"num_tokens": 7470878.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.45753698348999,
|
|
"epoch": 0.31745086360929126,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995532268444244,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.1597254678606987,
|
|
"num_tokens": 7486427.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.533625650405884,
|
|
"epoch": 0.31804645622394284,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004995505387713453,
|
|
"loss": 5.5064,
|
|
"mean_token_accuracy": 0.15825136750936508,
|
|
"num_tokens": 7500759.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.5083833694458,
|
|
"epoch": 0.3186420488385944,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995478426440037,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.16117209792137147,
|
|
"num_tokens": 7513224.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.415870523452758,
|
|
"epoch": 0.31923764145324596,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995451384624959,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.15855105221271515,
|
|
"num_tokens": 7528128.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.488669157028198,
|
|
"epoch": 0.31983323406789754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995424262269191,
|
|
"loss": 5.3644,
|
|
"mean_token_accuracy": 0.16409101635217666,
|
|
"num_tokens": 7541731.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.527408266067505,
|
|
"epoch": 0.32042882668254913,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995397059373704,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.15582113713026047,
|
|
"num_tokens": 7555938.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.455806255340576,
|
|
"epoch": 0.3210244192972007,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995369775939478,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.16162244826555253,
|
|
"num_tokens": 7570033.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.44084587097168,
|
|
"epoch": 0.3216200119118523,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995342411967487,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.15262447595596312,
|
|
"num_tokens": 7585131.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.485892486572266,
|
|
"epoch": 0.3222156045265039,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995314967458715,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.15848135203123093,
|
|
"num_tokens": 7600167.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.463599777221679,
|
|
"epoch": 0.32281119714115547,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995287442414145,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.16038483679294585,
|
|
"num_tokens": 7612301.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.579552793502808,
|
|
"epoch": 0.323406789755807,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995259836834767,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.15955429822206496,
|
|
"num_tokens": 7625837.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.464917993545532,
|
|
"epoch": 0.3240023823704586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995232150721568,
|
|
"loss": 5.4424,
|
|
"mean_token_accuracy": 0.1630013644695282,
|
|
"num_tokens": 7640555.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.32796196937561,
|
|
"epoch": 0.32459797498511017,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995204384075542,
|
|
"loss": 5.395,
|
|
"mean_token_accuracy": 0.1633957326412201,
|
|
"num_tokens": 7655395.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.514709234237671,
|
|
"epoch": 0.32519356759976176,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995176536897685,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.15324069410562516,
|
|
"num_tokens": 7670429.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.418760824203491,
|
|
"epoch": 0.32578916021441334,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995148609188997,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.15462717562913894,
|
|
"num_tokens": 7684240.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.622193336486816,
|
|
"epoch": 0.32638475282906493,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995120600950479,
|
|
"loss": 5.4976,
|
|
"mean_token_accuracy": 0.15276201218366622,
|
|
"num_tokens": 7698412.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.5449694156646725,
|
|
"epoch": 0.3269803454437165,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995092512183134,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.16160244196653367,
|
|
"num_tokens": 7712814.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.473204660415649,
|
|
"epoch": 0.3275759380583681,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995064342887972,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.16038311868906022,
|
|
"num_tokens": 7726740.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.475922775268555,
|
|
"epoch": 0.32817153067301963,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995036093066001,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.15509285628795624,
|
|
"num_tokens": 7741411.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.417195129394531,
|
|
"epoch": 0.3287671232876712,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004995007762718237,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.17503638118505477,
|
|
"num_tokens": 7753530.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.425090408325195,
|
|
"epoch": 0.3293627159023228,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994979351845693,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.16470912098884583,
|
|
"num_tokens": 7766924.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.459423446655274,
|
|
"epoch": 0.3299583085169744,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994950860449392,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.15680040270090104,
|
|
"num_tokens": 7781561.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.50134539604187,
|
|
"epoch": 0.33055390113162597,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994922288530353,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.1541897773742676,
|
|
"num_tokens": 7796254.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.439051675796509,
|
|
"epoch": 0.33114949374627756,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994893636089601,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.16132940202951432,
|
|
"num_tokens": 7808683.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.557245969772339,
|
|
"epoch": 0.33174508636092914,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994864903128164,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.15166468918323517,
|
|
"num_tokens": 7822688.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.51523871421814,
|
|
"epoch": 0.33234067897558073,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994836089647073,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.16210486739873886,
|
|
"num_tokens": 7838425.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.3984034061431885,
|
|
"epoch": 0.33293627159023226,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994807195647362,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.16299658864736558,
|
|
"num_tokens": 7851685.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.443256473541259,
|
|
"epoch": 0.33353186420488384,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994778221130066,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.16092008948326111,
|
|
"num_tokens": 7864735.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.407681083679199,
|
|
"epoch": 0.33412745681953543,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994749166096226,
|
|
"loss": 5.3142,
|
|
"mean_token_accuracy": 0.1613879010081291,
|
|
"num_tokens": 7880240.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.326388788223267,
|
|
"epoch": 0.334723049434187,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994720030546882,
|
|
"loss": 5.3899,
|
|
"mean_token_accuracy": 0.1579413443803787,
|
|
"num_tokens": 7893749.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.483776807785034,
|
|
"epoch": 0.3353186420488386,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994690814483081,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.1695275753736496,
|
|
"num_tokens": 7906132.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.370585346221924,
|
|
"epoch": 0.3359142346634902,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994661517905869,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.16688691973686218,
|
|
"num_tokens": 7919621.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.339296674728393,
|
|
"epoch": 0.33650982727814177,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994632140816299,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.16302681118249893,
|
|
"num_tokens": 7932882.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.449605989456177,
|
|
"epoch": 0.33710541989279336,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994602683215424,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.15975705534219742,
|
|
"num_tokens": 7946374.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.496216535568237,
|
|
"epoch": 0.3377010125074449,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049945731451043,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.15355465859174727,
|
|
"num_tokens": 7959766.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.440117406845093,
|
|
"epoch": 0.33829660512209647,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994543526483985,
|
|
"loss": 5.4283,
|
|
"mean_token_accuracy": 0.1599194288253784,
|
|
"num_tokens": 7974976.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.54617600440979,
|
|
"epoch": 0.33889219773674806,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994513827355546,
|
|
"loss": 5.4681,
|
|
"mean_token_accuracy": 0.1537953421473503,
|
|
"num_tokens": 7990605.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.390249967575073,
|
|
"epoch": 0.33948779035139964,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994484047720043,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.1614687994122505,
|
|
"num_tokens": 8004346.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.532868146896362,
|
|
"epoch": 0.34008338296605123,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994454187578547,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.16327487975358962,
|
|
"num_tokens": 8020219.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.523764133453369,
|
|
"epoch": 0.3406789755807028,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994424246932129,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.1491013839840889,
|
|
"num_tokens": 8034486.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.427282285690308,
|
|
"epoch": 0.3412745681953544,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994394225781863,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.15985246896743774,
|
|
"num_tokens": 8047661.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.444649314880371,
|
|
"epoch": 0.34187016081000593,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994364124128825,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.16245862245559692,
|
|
"num_tokens": 8063638.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.404064512252807,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994333941974094,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.16373136639595032,
|
|
"num_tokens": 8075743.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.490094518661499,
|
|
"epoch": 0.3430613460393091,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994303679318754,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.16108566969633104,
|
|
"num_tokens": 8090169.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.398551893234253,
|
|
"epoch": 0.3436569386539607,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994273336163891,
|
|
"loss": 5.3941,
|
|
"mean_token_accuracy": 0.15766267329454423,
|
|
"num_tokens": 8104919.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.458081388473511,
|
|
"epoch": 0.34425253126861227,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994242912510591,
|
|
"loss": 5.402,
|
|
"mean_token_accuracy": 0.16289524734020233,
|
|
"num_tokens": 8117893.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.454225873947143,
|
|
"epoch": 0.34484812388326386,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994212408359948,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.1511369079351425,
|
|
"num_tokens": 8133325.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.484027624130249,
|
|
"epoch": 0.34544371649791544,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994181823713054,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.1677608996629715,
|
|
"num_tokens": 8147728.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.4504319190979,
|
|
"epoch": 0.34603930911256703,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994151158571006,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.16273794770240785,
|
|
"num_tokens": 8163045.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.488362169265747,
|
|
"epoch": 0.34663490172721856,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994120412934906,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.15756225660443307,
|
|
"num_tokens": 8176946.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.444232225418091,
|
|
"epoch": 0.34723049434187014,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994089586805856,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.16667543798685075,
|
|
"num_tokens": 8189507.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.3928650379180905,
|
|
"epoch": 0.34782608695652173,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994058680184959,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.15729445964097977,
|
|
"num_tokens": 8203920.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.461070346832275,
|
|
"epoch": 0.3484216795711733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994027693073327,
|
|
"loss": 5.3564,
|
|
"mean_token_accuracy": 0.16075894087553025,
|
|
"num_tokens": 8217719.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.331908798217773,
|
|
"epoch": 0.3490172721858249,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993996625472071,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.16048271358013153,
|
|
"num_tokens": 8232796.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.525384187698364,
|
|
"epoch": 0.3496128648004765,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993965477382304,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.16117070913314818,
|
|
"num_tokens": 8244150.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.401209449768066,
|
|
"epoch": 0.35020845741512807,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993934248805143,
|
|
"loss": 5.3627,
|
|
"mean_token_accuracy": 0.16473608314990998,
|
|
"num_tokens": 8259070.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.384912967681885,
|
|
"epoch": 0.35080405002977966,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993902939741709,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.16211091727018356,
|
|
"num_tokens": 8273558.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.476204586029053,
|
|
"epoch": 0.3513996426444312,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993871550193126,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.15910796076059341,
|
|
"num_tokens": 8287816.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.464661931991577,
|
|
"epoch": 0.3519952352590828,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993840080160519,
|
|
"loss": 5.395,
|
|
"mean_token_accuracy": 0.1563792422413826,
|
|
"num_tokens": 8303047.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.381534147262573,
|
|
"epoch": 0.35259082787373436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993808529645016,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.16679915189743041,
|
|
"num_tokens": 8315907.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.387243747711182,
|
|
"epoch": 0.35318642048838594,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993776898647749,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.1756068602204323,
|
|
"num_tokens": 8329343.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.531315469741822,
|
|
"epoch": 0.35378201310303753,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993745187169852,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.15440596491098404,
|
|
"num_tokens": 8343698.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.486586570739746,
|
|
"epoch": 0.3543776057176891,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993713395212464,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.1589389443397522,
|
|
"num_tokens": 8357697.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.326037883758545,
|
|
"epoch": 0.3549731983323407,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993681522776725,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.16376715898513794,
|
|
"num_tokens": 8370743.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.353936386108399,
|
|
"epoch": 0.35556879094699223,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993649569863778,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.1763604387640953,
|
|
"num_tokens": 8383328.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.408966493606568,
|
|
"epoch": 0.3561643835616438,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993617536474768,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.16303879618644715,
|
|
"num_tokens": 8398539.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.438740825653076,
|
|
"epoch": 0.3567599761762954,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993585422610845,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.16724219173192978,
|
|
"num_tokens": 8411238.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.301597833633423,
|
|
"epoch": 0.357355568790947,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993553228273161,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.1715283453464508,
|
|
"num_tokens": 8424818.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.357355568790947,
|
|
"eval_entropy": 5.28683385026866,
|
|
"eval_loss": 5.370048999786377,
|
|
"eval_mean_token_accuracy": 0.17110598358416165,
|
|
"eval_num_tokens": 8424818.0,
|
|
"eval_runtime": 25.1053,
|
|
"eval_samples_per_second": 1016.239,
|
|
"eval_steps_per_second": 127.065,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.510521125793457,
|
|
"epoch": 0.3579511614055986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499352095346287,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.1555317111313343,
|
|
"num_tokens": 8438974.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.423871755599976,
|
|
"epoch": 0.35854675402025016,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993488598181131,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.16464045494794846,
|
|
"num_tokens": 8453583.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.434206867218018,
|
|
"epoch": 0.35914234663490174,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993456162429103,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.1691050723195076,
|
|
"num_tokens": 8467621.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.402159118652344,
|
|
"epoch": 0.35973793924955333,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993423646207951,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.16295197308063508,
|
|
"num_tokens": 8482697.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.436834335327148,
|
|
"epoch": 0.36033353186420486,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499339104951884,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.16257833689451218,
|
|
"num_tokens": 8495347.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.327873277664184,
|
|
"epoch": 0.36092912447885644,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993358372362939,
|
|
"loss": 5.3562,
|
|
"mean_token_accuracy": 0.16302821636199952,
|
|
"num_tokens": 8509132.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.505628252029419,
|
|
"epoch": 0.36152471709350803,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004993325614741421,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.1657652661204338,
|
|
"num_tokens": 8523563.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.308240461349487,
|
|
"epoch": 0.3621203097081596,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993292776655461,
|
|
"loss": 5.1971,
|
|
"mean_token_accuracy": 0.16572278887033462,
|
|
"num_tokens": 8536399.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.290839529037475,
|
|
"epoch": 0.3627159023228112,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993259858106236,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.1686759039759636,
|
|
"num_tokens": 8550969.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.4446611404418945,
|
|
"epoch": 0.3633114949374628,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993226859094927,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.154675255715847,
|
|
"num_tokens": 8567051.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.458184766769409,
|
|
"epoch": 0.36390708755211437,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993193779622719,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.1567184641957283,
|
|
"num_tokens": 8581255.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.420899343490601,
|
|
"epoch": 0.36450268016676596,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993160619690796,
|
|
"loss": 5.448,
|
|
"mean_token_accuracy": 0.15679514557123184,
|
|
"num_tokens": 8595640.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.50805435180664,
|
|
"epoch": 0.3650982727814175,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993127379300349,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.16860395073890685,
|
|
"num_tokens": 8609506.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.394361400604248,
|
|
"epoch": 0.3656938653960691,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499309405845257,
|
|
"loss": 5.3472,
|
|
"mean_token_accuracy": 0.16267415285110473,
|
|
"num_tokens": 8624691.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.344530296325684,
|
|
"epoch": 0.36628945801072066,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993060657148654,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.173505899310112,
|
|
"num_tokens": 8637218.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.378174686431885,
|
|
"epoch": 0.36688505062537224,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049930271753898,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.1596073791384697,
|
|
"num_tokens": 8650153.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.398423719406128,
|
|
"epoch": 0.36748064324002383,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992993613177208,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.16896606385707855,
|
|
"num_tokens": 8663280.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.3862169742584225,
|
|
"epoch": 0.3680762358546754,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992959970512082,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.16117600798606874,
|
|
"num_tokens": 8677266.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.393886423110962,
|
|
"epoch": 0.368671828469327,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992926247395627,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.16300708502531053,
|
|
"num_tokens": 8692660.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.474901866912842,
|
|
"epoch": 0.36926742108397853,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992892443829057,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.15842591226100922,
|
|
"num_tokens": 8706200.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.383607053756714,
|
|
"epoch": 0.3698630136986301,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499285855981358,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.17244553565979004,
|
|
"num_tokens": 8720421.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.316756629943848,
|
|
"epoch": 0.3704586063132817,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992824595350414,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.1651482105255127,
|
|
"num_tokens": 8732343.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.4371870994567875,
|
|
"epoch": 0.3710541989279333,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992790550440775,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.16226140558719634,
|
|
"num_tokens": 8746247.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.389555978775024,
|
|
"epoch": 0.3716497915425849,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992756425085887,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.16434690356254578,
|
|
"num_tokens": 8760964.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.30623722076416,
|
|
"epoch": 0.37224538415723646,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992722219286972,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.17037235647439958,
|
|
"num_tokens": 8774889.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.374737644195557,
|
|
"epoch": 0.37284097677188804,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992687933045258,
|
|
"loss": 5.3783,
|
|
"mean_token_accuracy": 0.1672949731349945,
|
|
"num_tokens": 8790479.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.443537712097168,
|
|
"epoch": 0.37343656938653963,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992653566361974,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.160555462539196,
|
|
"num_tokens": 8805129.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.371708917617798,
|
|
"epoch": 0.37403216200119116,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992619119238351,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.17055110782384872,
|
|
"num_tokens": 8818046.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.3937911033630375,
|
|
"epoch": 0.37462775461584275,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499258459167563,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.17161964774131774,
|
|
"num_tokens": 8830715.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.448086214065552,
|
|
"epoch": 0.37522334723049433,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992549983675043,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.16498690843582153,
|
|
"num_tokens": 8846349.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.362604236602783,
|
|
"epoch": 0.3758189398451459,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992515295237835,
|
|
"loss": 5.2723,
|
|
"mean_token_accuracy": 0.1705073207616806,
|
|
"num_tokens": 8861316.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.359233236312866,
|
|
"epoch": 0.3764145324597975,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499248052636525,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.16182974278926848,
|
|
"num_tokens": 8874349.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.440760231018066,
|
|
"epoch": 0.3770101250744491,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992445677058534,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.16338106840848923,
|
|
"num_tokens": 8887836.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.431506729125976,
|
|
"epoch": 0.3776057176891007,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992410747318938,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.16494905352592468,
|
|
"num_tokens": 8902009.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.362026023864746,
|
|
"epoch": 0.37820131030375226,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992375737147715,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.16695744842290877,
|
|
"num_tokens": 8915960.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.3468080997467045,
|
|
"epoch": 0.3787969029184038,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992340646546118,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.1662399634718895,
|
|
"num_tokens": 8930742.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.382139253616333,
|
|
"epoch": 0.3793924955330554,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000499230547551541,
|
|
"loss": 5.3352,
|
|
"mean_token_accuracy": 0.15858094692230223,
|
|
"num_tokens": 8943535.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.296666240692138,
|
|
"epoch": 0.37998808814770696,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992270224056849,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.17423150986433028,
|
|
"num_tokens": 8958187.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.382894849777221,
|
|
"epoch": 0.38058368076235854,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004992234892171702,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.16816554665565492,
|
|
"num_tokens": 8970409.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.431480550765992,
|
|
"epoch": 0.38117927337701013,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992199479861235,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.15303682982921601,
|
|
"num_tokens": 8982302.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.429977560043335,
|
|
"epoch": 0.3817748659916617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992163987126717,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.16806116700172424,
|
|
"num_tokens": 8996215.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.407671976089477,
|
|
"epoch": 0.3823704586063133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992128413969423,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.1612073600292206,
|
|
"num_tokens": 9011423.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.463384485244751,
|
|
"epoch": 0.3829660512209649,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992092760390628,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.15522129386663436,
|
|
"num_tokens": 9025322.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.43425726890564,
|
|
"epoch": 0.3835616438356164,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992057026391612,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.17161321192979812,
|
|
"num_tokens": 9039199.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.291681146621704,
|
|
"epoch": 0.384157236450268,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992021211973655,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.16936273276805877,
|
|
"num_tokens": 9051808.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.444154834747314,
|
|
"epoch": 0.3847528290649196,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004991985317138043,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.1604176014661789,
|
|
"num_tokens": 9066068.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.473998260498047,
|
|
"epoch": 0.3853484216795712,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991949341886063,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.16199745684862138,
|
|
"num_tokens": 9079209.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.380204868316651,
|
|
"epoch": 0.38594401429422276,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991913286219004,
|
|
"loss": 5.3081,
|
|
"mean_token_accuracy": 0.16668957620859146,
|
|
"num_tokens": 9092270.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.4295125007629395,
|
|
"epoch": 0.38653960690887434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991877150138162,
|
|
"loss": 5.364,
|
|
"mean_token_accuracy": 0.15739017724990845,
|
|
"num_tokens": 9106231.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.418775177001953,
|
|
"epoch": 0.38713519952352593,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991840933644831,
|
|
"loss": 5.3697,
|
|
"mean_token_accuracy": 0.1600486993789673,
|
|
"num_tokens": 9119325.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.35563292503357,
|
|
"epoch": 0.38773079213817746,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499180463674031,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.15927273035049438,
|
|
"num_tokens": 9132792.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.411444902420044,
|
|
"epoch": 0.38832638475282905,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991768259425903,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.1750268429517746,
|
|
"num_tokens": 9146659.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.385461473464966,
|
|
"epoch": 0.38892197736748063,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991731801702914,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.16790657341480256,
|
|
"num_tokens": 9161035.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.436224365234375,
|
|
"epoch": 0.3895175699821322,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991695263572648,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.1598617509007454,
|
|
"num_tokens": 9176057.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.367569017410278,
|
|
"epoch": 0.3901131625967838,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991658645036419,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.1672537848353386,
|
|
"num_tokens": 9191021.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.2798326969146725,
|
|
"epoch": 0.3907087552114354,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991621946095539,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.1774519056081772,
|
|
"num_tokens": 9204717.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.47446928024292,
|
|
"epoch": 0.391304347826087,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991585166751325,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.16155275106430053,
|
|
"num_tokens": 9218395.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.353788661956787,
|
|
"epoch": 0.39189994044073856,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991548307005094,
|
|
"loss": 5.4161,
|
|
"mean_token_accuracy": 0.16489644199609757,
|
|
"num_tokens": 9231419.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.371747779846191,
|
|
"epoch": 0.3924955330553901,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991511366858172,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.16137880384922026,
|
|
"num_tokens": 9246557.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.349221515655517,
|
|
"epoch": 0.3930911256700417,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991474346311879,
|
|
"loss": 5.3216,
|
|
"mean_token_accuracy": 0.16300324648618697,
|
|
"num_tokens": 9261173.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.432360887527466,
|
|
"epoch": 0.39368671828469326,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991437245367547,
|
|
"loss": 5.3479,
|
|
"mean_token_accuracy": 0.16291509866714476,
|
|
"num_tokens": 9274819.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.314003133773804,
|
|
"epoch": 0.39428231089934485,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991400064026506,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.1770612195134163,
|
|
"num_tokens": 9287219.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.315059041976928,
|
|
"epoch": 0.39487790351399643,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991362802290089,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.16053526997566223,
|
|
"num_tokens": 9301069.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.40190896987915,
|
|
"epoch": 0.395473496128648,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991325460159631,
|
|
"loss": 5.35,
|
|
"mean_token_accuracy": 0.16094670593738555,
|
|
"num_tokens": 9314807.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.329822063446045,
|
|
"epoch": 0.3960690887432996,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991288037636474,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.16747990101575852,
|
|
"num_tokens": 9328702.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.39456877708435,
|
|
"epoch": 0.3966646813579512,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991250534721959,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.16296709179878235,
|
|
"num_tokens": 9342949.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.394403648376465,
|
|
"epoch": 0.3972602739726027,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991212951417431,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.1725207105278969,
|
|
"num_tokens": 9357382.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.3801939487457275,
|
|
"epoch": 0.3978558665872543,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991175287724239,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.15581056028604506,
|
|
"num_tokens": 9371297.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.452669620513916,
|
|
"epoch": 0.3984514592019059,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991137543643733,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.15849246978759765,
|
|
"num_tokens": 9386213.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.3983907222747805,
|
|
"epoch": 0.3990470518165575,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991099719177268,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.1669553518295288,
|
|
"num_tokens": 9398166.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.323517322540283,
|
|
"epoch": 0.39964264443120906,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991061814326198,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.1685235545039177,
|
|
"num_tokens": 9411611.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.401799631118775,
|
|
"epoch": 0.40023823704586065,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991023829091887,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.16929986625909804,
|
|
"num_tokens": 9426461.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.321595239639282,
|
|
"epoch": 0.40083382966051223,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004990985763475694,
|
|
"loss": 5.319,
|
|
"mean_token_accuracy": 0.17373397946357727,
|
|
"num_tokens": 9437337.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.354121541976928,
|
|
"epoch": 0.40142942227516376,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990947617478984,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.170222769677639,
|
|
"num_tokens": 9450361.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.376477575302124,
|
|
"epoch": 0.40202501488981535,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990909391103127,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.16533191800117492,
|
|
"num_tokens": 9463336.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.446416234970092,
|
|
"epoch": 0.40262060750446693,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990871084349494,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.1671142652630806,
|
|
"num_tokens": 9476602.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.351249551773071,
|
|
"epoch": 0.4032162001191185,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990832697219459,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.16753333956003189,
|
|
"num_tokens": 9490355.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.375997734069824,
|
|
"epoch": 0.4038117927337701,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990794229714398,
|
|
"loss": 5.3663,
|
|
"mean_token_accuracy": 0.1648324817419052,
|
|
"num_tokens": 9502191.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.472232913970947,
|
|
"epoch": 0.4044073853484217,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990755681835693,
|
|
"loss": 5.425,
|
|
"mean_token_accuracy": 0.15671451911330223,
|
|
"num_tokens": 9515694.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.368155384063721,
|
|
"epoch": 0.4050029779630733,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990717053584723,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.16041674315929413,
|
|
"num_tokens": 9530146.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.40961651802063,
|
|
"epoch": 0.40559857057772486,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990678344962876,
|
|
"loss": 5.3456,
|
|
"mean_token_accuracy": 0.16427794843912125,
|
|
"num_tokens": 9541969.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.41700587272644,
|
|
"epoch": 0.4061941631923764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990639555971539,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.15889659523963928,
|
|
"num_tokens": 9555837.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.480150604248047,
|
|
"epoch": 0.406789755807028,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990600686612106,
|
|
"loss": 5.4252,
|
|
"mean_token_accuracy": 0.15957638025283813,
|
|
"num_tokens": 9570841.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.33478422164917,
|
|
"epoch": 0.40738534842167956,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990561736885968,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.1719391256570816,
|
|
"num_tokens": 9583342.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.404697561264038,
|
|
"epoch": 0.40798094103633115,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990522706794523,
|
|
"loss": 5.3177,
|
|
"mean_token_accuracy": 0.1689616933465004,
|
|
"num_tokens": 9597217.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.434438323974609,
|
|
"epoch": 0.40857653365098273,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990483596339174,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.16801101714372635,
|
|
"num_tokens": 9612251.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.345943546295166,
|
|
"epoch": 0.4091721262656343,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990444405521318,
|
|
"loss": 5.3885,
|
|
"mean_token_accuracy": 0.16262349337339402,
|
|
"num_tokens": 9625693.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.373858261108398,
|
|
"epoch": 0.4097677188802859,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990405134342366,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.1686413913965225,
|
|
"num_tokens": 9639687.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.39095401763916,
|
|
"epoch": 0.4103633114949375,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990365782803724,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.1629018872976303,
|
|
"num_tokens": 9652258.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.354955339431763,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990326350906803,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.17003926783800125,
|
|
"num_tokens": 9665946.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.336898851394653,
|
|
"epoch": 0.4115544967242406,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990286838653019,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.17107798904180527,
|
|
"num_tokens": 9680474.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.3738256931304935,
|
|
"epoch": 0.4121500893388922,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990247246043789,
|
|
"loss": 5.2971,
|
|
"mean_token_accuracy": 0.16664824038743972,
|
|
"num_tokens": 9693797.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.361837673187256,
|
|
"epoch": 0.4127456819535438,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990207573080533,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.16071335822343827,
|
|
"num_tokens": 9705875.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.43790488243103,
|
|
"epoch": 0.41334127456819536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990167819764672,
|
|
"loss": 5.454,
|
|
"mean_token_accuracy": 0.15546730160713196,
|
|
"num_tokens": 9720968.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.401946973800659,
|
|
"epoch": 0.41393686718284695,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990127986097636,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.16424839347600936,
|
|
"num_tokens": 9735586.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.382835865020752,
|
|
"epoch": 0.41453245979749853,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000499008807208085,
|
|
"loss": 5.3368,
|
|
"mean_token_accuracy": 0.16096460968255996,
|
|
"num_tokens": 9750253.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.398310613632202,
|
|
"epoch": 0.4151280524121501,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004990048077715746,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.16579122245311737,
|
|
"num_tokens": 9762814.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.40472445487976,
|
|
"epoch": 0.41572364502680165,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990008003003762,
|
|
"loss": 5.399,
|
|
"mean_token_accuracy": 0.15279862582683562,
|
|
"num_tokens": 9777144.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.389925575256347,
|
|
"epoch": 0.41631923764145323,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004989967847946331,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.16605382412672043,
|
|
"num_tokens": 9791746.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.386882543563843,
|
|
"epoch": 0.4169148302561048,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989927612544895,
|
|
"loss": 5.2651,
|
|
"mean_token_accuracy": 0.16906381845474244,
|
|
"num_tokens": 9804599.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.286116456985473,
|
|
"epoch": 0.4175104228707564,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989887296800899,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.17652947455644608,
|
|
"num_tokens": 9817030.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.451083183288574,
|
|
"epoch": 0.418106015485408,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989846900715786,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.15871664732694626,
|
|
"num_tokens": 9832478.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.372736501693725,
|
|
"epoch": 0.4187016081000596,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004989806424291008,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.17115395069122313,
|
|
"num_tokens": 9844534.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.283146858215332,
|
|
"epoch": 0.41929720071471116,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004989765867528014,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.1702785462141037,
|
|
"num_tokens": 9856610.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.301205587387085,
|
|
"epoch": 0.4198927933293627,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989725230428262,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.17059824913740157,
|
|
"num_tokens": 9870527.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.315949869155884,
|
|
"epoch": 0.4204883859440143,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989684512993205,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.174815534055233,
|
|
"num_tokens": 9883616.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.274326801300049,
|
|
"epoch": 0.42108397855866586,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989643715224307,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.17108384668827056,
|
|
"num_tokens": 9896261.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.390660953521729,
|
|
"epoch": 0.42167957117331745,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989602837123031,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.1642387256026268,
|
|
"num_tokens": 9910405.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.450772380828857,
|
|
"epoch": 0.42227516378796903,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989561878690842,
|
|
"loss": 5.3982,
|
|
"mean_token_accuracy": 0.16883279085159303,
|
|
"num_tokens": 9923932.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.33366289138794,
|
|
"epoch": 0.4228707564026206,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000498952083992921,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.16658556461334229,
|
|
"num_tokens": 9938132.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.331817674636841,
|
|
"epoch": 0.4234663490172722,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989479720839605,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.17616381943225862,
|
|
"num_tokens": 9952468.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.412946557998657,
|
|
"epoch": 0.4240619416319238,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989438521423506,
|
|
"loss": 5.4065,
|
|
"mean_token_accuracy": 0.16332354694604873,
|
|
"num_tokens": 9967269.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.282586765289307,
|
|
"epoch": 0.4246575342465753,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004989397241682387,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.16469956189393997,
|
|
"num_tokens": 9979776.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.476590347290039,
|
|
"epoch": 0.4252531268612269,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000498935588161773,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.16530849039554596,
|
|
"num_tokens": 9993276.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.33142786026001,
|
|
"epoch": 0.4258487194758785,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989314441231019,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.18153406232595443,
|
|
"num_tokens": 10005683.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.352495002746582,
|
|
"epoch": 0.4264443120905301,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989272920523741,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.17136275619268418,
|
|
"num_tokens": 10018526.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.369859504699707,
|
|
"epoch": 0.42703990470518166,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989231319497382,
|
|
"loss": 5.3329,
|
|
"mean_token_accuracy": 0.15797792822122575,
|
|
"num_tokens": 10034505.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.471003866195678,
|
|
"epoch": 0.42763549731983325,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989189638153437,
|
|
"loss": 5.332,
|
|
"mean_token_accuracy": 0.164971262216568,
|
|
"num_tokens": 10047465.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.360622882843018,
|
|
"epoch": 0.42823108993448483,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989147876493401,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.16481345593929292,
|
|
"num_tokens": 10061644.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.362998390197754,
|
|
"epoch": 0.4288266825491364,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989106034518771,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.15501452386379241,
|
|
"num_tokens": 10076672.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.446399593353272,
|
|
"epoch": 0.42942227516378795,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004989064112231049,
|
|
"loss": 5.4355,
|
|
"mean_token_accuracy": 0.15889764428138733,
|
|
"num_tokens": 10091784.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.376490354537964,
|
|
"epoch": 0.43001786777843953,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989022109631736,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.1682573825120926,
|
|
"num_tokens": 10104848.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.247719097137451,
|
|
"epoch": 0.4306134603930911,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988980026722341,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.16738879382610322,
|
|
"num_tokens": 10120561.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.408150672912598,
|
|
"epoch": 0.4312090530077427,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988937863504373,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.1619812175631523,
|
|
"num_tokens": 10135692.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.347686910629273,
|
|
"epoch": 0.4318046456223943,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988895619979344,
|
|
"loss": 5.2447,
|
|
"mean_token_accuracy": 0.1714229926466942,
|
|
"num_tokens": 10148768.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.342931747436523,
|
|
"epoch": 0.4324002382370459,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498885329614877,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.17463257908821106,
|
|
"num_tokens": 10162234.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.336144495010376,
|
|
"epoch": 0.43299583085169746,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004988810892014168,
|
|
"loss": 5.334,
|
|
"mean_token_accuracy": 0.17050167620182038,
|
|
"num_tokens": 10177588.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.377119064331055,
|
|
"epoch": 0.433591423466349,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988768407577058,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.17181164920330047,
|
|
"num_tokens": 10190324.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.210611200332641,
|
|
"epoch": 0.4341870160810006,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988725842838968,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.1684074193239212,
|
|
"num_tokens": 10204790.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.356572055816651,
|
|
"epoch": 0.43478260869565216,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498868319780142,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.16781956553459168,
|
|
"num_tokens": 10219777.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.33964204788208,
|
|
"epoch": 0.43537820131030375,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988640472465947,
|
|
"loss": 5.3154,
|
|
"mean_token_accuracy": 0.16276252418756484,
|
|
"num_tokens": 10234477.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.236456727981567,
|
|
"epoch": 0.43597379392495533,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988597666834078,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.17583647668361663,
|
|
"num_tokens": 10247196.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.418797397613526,
|
|
"epoch": 0.4365693865396069,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004988554780907353,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.16695199608802797,
|
|
"num_tokens": 10260752.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.277998447418213,
|
|
"epoch": 0.4371649791542585,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988511814687306,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.16410964876413345,
|
|
"num_tokens": 10274500.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.398269844055176,
|
|
"epoch": 0.4377605717689101,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988468768175479,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.1677264541387558,
|
|
"num_tokens": 10290271.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.369424057006836,
|
|
"epoch": 0.4383561643835616,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988425641373418,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.15863254815340042,
|
|
"num_tokens": 10305645.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.320975255966187,
|
|
"epoch": 0.4389517569982132,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988382434282668,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.17314812242984773,
|
|
"num_tokens": 10321267.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.425780248641968,
|
|
"epoch": 0.4395473496128648,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498833914690478,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.1664855882525444,
|
|
"num_tokens": 10336597.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.368607902526856,
|
|
"epoch": 0.4401429422275164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988295779241306,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.16743993610143662,
|
|
"num_tokens": 10351887.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.302034330368042,
|
|
"epoch": 0.44073853484216796,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988252331293802,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.16697003096342086,
|
|
"num_tokens": 10366078.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.29266939163208,
|
|
"epoch": 0.44133412745681955,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988208803063827,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.17260511666536332,
|
|
"num_tokens": 10380382.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.34239091873169,
|
|
"epoch": 0.44192972007147113,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988165194552939,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.17081304639577866,
|
|
"num_tokens": 10394554.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.305882787704467,
|
|
"epoch": 0.4425253126861227,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988121505762706,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.16865146160125732,
|
|
"num_tokens": 10408803.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.370451259613037,
|
|
"epoch": 0.44312090530077425,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988077736694693,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.1695753112435341,
|
|
"num_tokens": 10421577.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.349305248260498,
|
|
"epoch": 0.44371649791542583,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988033887350471,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.16450923681259155,
|
|
"num_tokens": 10435117.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.372316980361939,
|
|
"epoch": 0.4443120905300774,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987989957731611,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.1628807932138443,
|
|
"num_tokens": 10448762.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.387575006484985,
|
|
"epoch": 0.444907683144729,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987945947839691,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.16484364569187165,
|
|
"num_tokens": 10462722.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.401480054855346,
|
|
"epoch": 0.4455032757593806,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498790185767629,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.16520836502313613,
|
|
"num_tokens": 10477834.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.322182512283325,
|
|
"epoch": 0.4460988683740322,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987857687242986,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.1774500772356987,
|
|
"num_tokens": 10490807.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.233447122573852,
|
|
"epoch": 0.44669446098868376,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004987813436541366,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.17568996250629426,
|
|
"num_tokens": 10505064.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.283840656280518,
|
|
"epoch": 0.4472900536033353,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987769105573016,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.1719667762517929,
|
|
"num_tokens": 10517567.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.4917889595031735,
|
|
"epoch": 0.4478856462179869,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987724694339526,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.16753512173891066,
|
|
"num_tokens": 10533697.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.348692226409912,
|
|
"epoch": 0.44848123883263846,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987680202842491,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.164593930542469,
|
|
"num_tokens": 10547533.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.390475416183472,
|
|
"epoch": 0.44907683144729005,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004987635631083505,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.16794802397489547,
|
|
"num_tokens": 10562193.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.301377964019776,
|
|
"epoch": 0.44967242406194163,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004987590979064167,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.17162537276744844,
|
|
"num_tokens": 10575202.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.396148777008056,
|
|
"epoch": 0.4502680166765932,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987546246786078,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.16565940976142884,
|
|
"num_tokens": 10589064.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.434869050979614,
|
|
"epoch": 0.4508636092912448,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987501434250844,
|
|
"loss": 5.4142,
|
|
"mean_token_accuracy": 0.16147760897874833,
|
|
"num_tokens": 10602837.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.346148729324341,
|
|
"epoch": 0.4514592019058964,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498745654146007,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.16787297576665877,
|
|
"num_tokens": 10618200.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.4024049758911135,
|
|
"epoch": 0.4520547945205479,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000498741156841537,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.1679690182209015,
|
|
"num_tokens": 10631804.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.369621992111206,
|
|
"epoch": 0.4526503871351995,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987366515118353,
|
|
"loss": 5.3161,
|
|
"mean_token_accuracy": 0.16293373107910156,
|
|
"num_tokens": 10647066.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.345077848434448,
|
|
"epoch": 0.4532459797498511,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004987321381570638,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.1664928287267685,
|
|
"num_tokens": 10661436.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.428229331970215,
|
|
"epoch": 0.4538415723645027,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987276167773842,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.1639347106218338,
|
|
"num_tokens": 10675299.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.2407598972320555,
|
|
"epoch": 0.45443716497915426,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004987230873729588,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.17269673496484755,
|
|
"num_tokens": 10689073.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.206661128997803,
|
|
"epoch": 0.45503275759380585,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049871854994395,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.17685958743095398,
|
|
"num_tokens": 10703017.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.471341753005982,
|
|
"epoch": 0.45562835020845743,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987140044905205,
|
|
"loss": 5.4678,
|
|
"mean_token_accuracy": 0.1586658850312233,
|
|
"num_tokens": 10718151.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.368370103836059,
|
|
"epoch": 0.456223942823109,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987094510128335,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.1731274515390396,
|
|
"num_tokens": 10731299.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.259741592407226,
|
|
"epoch": 0.45681953543776055,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987048895110522,
|
|
"loss": 5.2393,
|
|
"mean_token_accuracy": 0.17204798012971878,
|
|
"num_tokens": 10745152.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.284659814834595,
|
|
"epoch": 0.45741512805241213,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987003199853401,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.17092401087284087,
|
|
"num_tokens": 10758557.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.388708305358887,
|
|
"epoch": 0.4580107206670637,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004986957424358613,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.16851244270801544,
|
|
"num_tokens": 10773647.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.3533824443817135,
|
|
"epoch": 0.4586063132817153,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00049869115686278,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.16786985844373703,
|
|
"num_tokens": 10786973.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.400770664215088,
|
|
"epoch": 0.4592019058963669,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986865632662606,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.16653241217136383,
|
|
"num_tokens": 10800521.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.418367338180542,
|
|
"epoch": 0.4597974985110185,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004986819616464678,
|
|
"loss": 5.339,
|
|
"mean_token_accuracy": 0.17088744193315505,
|
|
"num_tokens": 10814934.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.331961154937744,
|
|
"epoch": 0.46039309112567006,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986773520035667,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.17171419113874437,
|
|
"num_tokens": 10830156.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.329433584213257,
|
|
"epoch": 0.46098868374032165,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986727343377227,
|
|
"loss": 5.2541,
|
|
"mean_token_accuracy": 0.1718049705028534,
|
|
"num_tokens": 10844354.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.347067880630493,
|
|
"epoch": 0.4615842763549732,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986681086491014,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.17421215176582336,
|
|
"num_tokens": 10855978.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.312961053848267,
|
|
"epoch": 0.46217986896962476,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986634749378686,
|
|
"loss": 5.1769,
|
|
"mean_token_accuracy": 0.17878348827362062,
|
|
"num_tokens": 10869395.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.238617086410523,
|
|
"epoch": 0.46277546158427635,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986588332041908,
|
|
"loss": 5.2528,
|
|
"mean_token_accuracy": 0.16964956969022751,
|
|
"num_tokens": 10884817.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.2788983345031735,
|
|
"epoch": 0.46337105419892793,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986541834482342,
|
|
"loss": 5.2017,
|
|
"mean_token_accuracy": 0.17764887511730193,
|
|
"num_tokens": 10898435.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.319885110855102,
|
|
"epoch": 0.4639666468135795,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986495256701657,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.16424282193183898,
|
|
"num_tokens": 10911777.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.322612237930298,
|
|
"epoch": 0.4645622394282311,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004986448598701523,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.16876413375139238,
|
|
"num_tokens": 10925025.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.302981853485107,
|
|
"epoch": 0.4651578320428827,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986401860483615,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.16906245946884155,
|
|
"num_tokens": 10940019.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.414742422103882,
|
|
"epoch": 0.4657534246575342,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986355042049608,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.16494245380163192,
|
|
"num_tokens": 10954702.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.3491918563842775,
|
|
"epoch": 0.4663490172721858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986308143401181,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.17217278629541397,
|
|
"num_tokens": 10970231.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.3056398868560795,
|
|
"epoch": 0.4669446098868374,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986261164540018,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.16697956025600433,
|
|
"num_tokens": 10986561.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.39390001296997,
|
|
"epoch": 0.467540202501489,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986214105467801,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.173395511507988,
|
|
"num_tokens": 11000246.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.2844517707824705,
|
|
"epoch": 0.46813579511614056,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986166966186223,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.18146094381809236,
|
|
"num_tokens": 11012590.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.176774406433106,
|
|
"epoch": 0.46873138773079215,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986119746696969,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.1831041842699051,
|
|
"num_tokens": 11025620.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.253212356567383,
|
|
"epoch": 0.46932698034544373,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986072447001736,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.17425810247659684,
|
|
"num_tokens": 11038352.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.225285291671753,
|
|
"epoch": 0.4699225729600953,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004986025067102221,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.1799553483724594,
|
|
"num_tokens": 11051226.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.324039506912231,
|
|
"epoch": 0.47051816557474685,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985977607000121,
|
|
"loss": 5.2844,
|
|
"mean_token_accuracy": 0.1698211222887039,
|
|
"num_tokens": 11065910.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.347030830383301,
|
|
"epoch": 0.47111375818939843,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004985930066697141,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.1771480843424797,
|
|
"num_tokens": 11078804.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.35353045463562,
|
|
"epoch": 0.47170935080405,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985882446194984,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.18080739825963973,
|
|
"num_tokens": 11090903.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.370579195022583,
|
|
"epoch": 0.4723049434187016,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498583474549536,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.16129955351352693,
|
|
"num_tokens": 11106914.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.344801330566407,
|
|
"epoch": 0.4729005360333532,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985786964599978,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.1740461066365242,
|
|
"num_tokens": 11121471.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.235055208206177,
|
|
"epoch": 0.4734961286480048,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004985739103510553,
|
|
"loss": 5.2201,
|
|
"mean_token_accuracy": 0.17757604718208314,
|
|
"num_tokens": 11135553.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.306499195098877,
|
|
"epoch": 0.47409172126265636,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985691162228802,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.16754851192235948,
|
|
"num_tokens": 11149335.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.368616151809692,
|
|
"epoch": 0.47468731387730795,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985643140756442,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.16929043382406234,
|
|
"num_tokens": 11161589.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.241770505905151,
|
|
"epoch": 0.4752829064919595,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00049855950390952,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.16392724066972733,
|
|
"num_tokens": 11175094.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.323491954803467,
|
|
"epoch": 0.47587849910661106,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004985546857246797,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.16841986477375032,
|
|
"num_tokens": 11191452.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.316299057006836,
|
|
"epoch": 0.47647409172126265,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985498595212964,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.16988371908664704,
|
|
"num_tokens": 11203831.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.361827945709228,
|
|
"epoch": 0.47706968433591423,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985450252995431,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.1635650649666786,
|
|
"num_tokens": 11218022.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.327618980407715,
|
|
"epoch": 0.4776652769505658,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985401830595932,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.17187195867300034,
|
|
"num_tokens": 11229993.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.39026403427124,
|
|
"epoch": 0.4782608695652174,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985353328016204,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.17107531577348709,
|
|
"num_tokens": 11243089.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.384813976287842,
|
|
"epoch": 0.478856462179869,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985304745257986,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.16056402325630187,
|
|
"num_tokens": 11260349.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.345159387588501,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985256082323022,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.17406837046146392,
|
|
"num_tokens": 11275875.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.368736457824707,
|
|
"epoch": 0.4800476474091721,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985207339213057,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.16748691499233245,
|
|
"num_tokens": 11289611.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.330052661895752,
|
|
"epoch": 0.4806432400238237,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985158515929837,
|
|
"loss": 5.3226,
|
|
"mean_token_accuracy": 0.17192085832357407,
|
|
"num_tokens": 11303917.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.317273807525635,
|
|
"epoch": 0.4812388326384753,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985109612475116,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.16884059011936187,
|
|
"num_tokens": 11317400.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.281553649902344,
|
|
"epoch": 0.48183442525312686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004985060628850648,
|
|
"loss": 5.2358,
|
|
"mean_token_accuracy": 0.17207540720701217,
|
|
"num_tokens": 11330771.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.328374195098877,
|
|
"epoch": 0.48243001786777845,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985011565058189,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.17196484059095382,
|
|
"num_tokens": 11344430.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.432625102996826,
|
|
"epoch": 0.48302561048243003,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004984962421099498,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.16481828838586807,
|
|
"num_tokens": 11358940.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.373032569885254,
|
|
"epoch": 0.4836212030970816,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000498491319697634,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.1740773633122444,
|
|
"num_tokens": 11371772.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.297433567047119,
|
|
"epoch": 0.48421679571173315,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498486389269048,
|
|
"loss": 5.2756,
|
|
"mean_token_accuracy": 0.16610733568668365,
|
|
"num_tokens": 11383976.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.365703105926514,
|
|
"epoch": 0.48481238832638474,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984814508243685,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.16569238156080246,
|
|
"num_tokens": 11398659.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.518905735015869,
|
|
"epoch": 0.4854079809410363,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004984765043637727,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.15935877859592437,
|
|
"num_tokens": 11413083.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.307703924179077,
|
|
"epoch": 0.4860035735556879,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498471549887438,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.1749643713235855,
|
|
"num_tokens": 11426408.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.30105242729187,
|
|
"epoch": 0.4865991661703395,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004984665873955422,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.16604604125022887,
|
|
"num_tokens": 11440609.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.339760875701904,
|
|
"epoch": 0.4871947587849911,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984616168882632,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.17506766617298125,
|
|
"num_tokens": 11454795.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.355580759048462,
|
|
"epoch": 0.48779035139964266,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004984566383657794,
|
|
"loss": 5.2335,
|
|
"mean_token_accuracy": 0.17618702203035355,
|
|
"num_tokens": 11468695.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.257555723190308,
|
|
"epoch": 0.48838594401429425,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984516518282692,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.17628935128450393,
|
|
"num_tokens": 11483601.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.4627368450164795,
|
|
"epoch": 0.4889815366289458,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984466572759117,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.1604067414999008,
|
|
"num_tokens": 11497860.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.282142114639282,
|
|
"epoch": 0.48957712924359736,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984416547088858,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.17720022946596145,
|
|
"num_tokens": 11512582.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.2370819568634035,
|
|
"epoch": 0.49017272185824895,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004984366441273711,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.17021116465330124,
|
|
"num_tokens": 11525480.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.293650674819946,
|
|
"epoch": 0.49076831447290054,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004984316255315472,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.1706745967268944,
|
|
"num_tokens": 11540465.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.307094621658325,
|
|
"epoch": 0.4913639070875521,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984265989215942,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.1650402158498764,
|
|
"num_tokens": 11555622.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.251779842376709,
|
|
"epoch": 0.4919594997022037,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984215642976923,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.17843125611543656,
|
|
"num_tokens": 11569547.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.348175859451294,
|
|
"epoch": 0.4925550923168553,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984165216600224,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.17571659684181212,
|
|
"num_tokens": 11583464.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.290053176879883,
|
|
"epoch": 0.4931506849315068,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984114710087648,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.17520453333854674,
|
|
"num_tokens": 11597639.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.287267637252808,
|
|
"epoch": 0.4937462775461584,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004984064123441011,
|
|
"loss": 5.2946,
|
|
"mean_token_accuracy": 0.16929041147232055,
|
|
"num_tokens": 11610645.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.381995344161988,
|
|
"epoch": 0.49434187016081,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984013456662127,
|
|
"loss": 5.2633,
|
|
"mean_token_accuracy": 0.16720440834760666,
|
|
"num_tokens": 11624802.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.327679109573364,
|
|
"epoch": 0.4949374627754616,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983962709752812,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.17095032930374146,
|
|
"num_tokens": 11638538.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.366896438598633,
|
|
"epoch": 0.49553305539011316,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004983911882714886,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.17078501582145691,
|
|
"num_tokens": 11651639.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.39895544052124,
|
|
"epoch": 0.49612864800476475,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004983860975550174,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.16364601105451584,
|
|
"num_tokens": 11668784.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.375655460357666,
|
|
"epoch": 0.49672424061941634,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983809988260501,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.16907925754785538,
|
|
"num_tokens": 11682737.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.2627991199493405,
|
|
"epoch": 0.4973198332340679,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004983758920847696,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.17550883442163467,
|
|
"num_tokens": 11697666.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.375076866149902,
|
|
"epoch": 0.49791542584871945,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983707773313589,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.16207095384597778,
|
|
"num_tokens": 11712747.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.355130052566528,
|
|
"epoch": 0.49851101846337104,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004983656545660016,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.16776809245347976,
|
|
"num_tokens": 11727233.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.311269617080688,
|
|
"epoch": 0.4991066110780226,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983605237888815,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.16131766587495805,
|
|
"num_tokens": 11743677.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.383014583587647,
|
|
"epoch": 0.4997022036926742,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004983553850001826,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.17459794729948044,
|
|
"num_tokens": 11756362.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.221938419342041,
|
|
"epoch": 0.5002977963073257,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983502382000892,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.1691034644842148,
|
|
"num_tokens": 11769955.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.219119358062744,
|
|
"epoch": 0.5008933889219773,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983450833887859,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.1823839321732521,
|
|
"num_tokens": 11783617.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.333247280120849,
|
|
"epoch": 0.5014889815366289,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004983399205664575,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.16367279291152953,
|
|
"num_tokens": 11797408.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.387611436843872,
|
|
"epoch": 0.5020845741512805,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004983347497332894,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.16103374511003493,
|
|
"num_tokens": 11810058.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.290585374832153,
|
|
"epoch": 0.5026801667659321,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983295708894668,
|
|
"loss": 5.2653,
|
|
"mean_token_accuracy": 0.16865108609199525,
|
|
"num_tokens": 11822921.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.331950426101685,
|
|
"epoch": 0.5032757593805837,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983243840351757,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.16634429842233658,
|
|
"num_tokens": 11837189.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.368002700805664,
|
|
"epoch": 0.5038713519952353,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983191891706021,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.17443966567516328,
|
|
"num_tokens": 11851579.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.249510765075684,
|
|
"epoch": 0.5044669446098868,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004983139862959322,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.1760208249092102,
|
|
"num_tokens": 11867013.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.209208583831787,
|
|
"epoch": 0.5050625372245384,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004983087754113527,
|
|
"loss": 5.127,
|
|
"mean_token_accuracy": 0.18138794749975204,
|
|
"num_tokens": 11879566.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.304442071914673,
|
|
"epoch": 0.50565812983919,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004983035565170505,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.170038440823555,
|
|
"num_tokens": 11893103.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.261818218231201,
|
|
"epoch": 0.5062537224538416,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004982983296132128,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.17363337576389312,
|
|
"num_tokens": 11907396.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.274723052978516,
|
|
"epoch": 0.5068493150684932,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004982930947000271,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.17339481860399247,
|
|
"num_tokens": 11921674.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.369744729995728,
|
|
"epoch": 0.5074449076831448,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982878517776812,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.17737799882888794,
|
|
"num_tokens": 11933739.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.169911956787109,
|
|
"epoch": 0.5080405002977963,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498282600846363,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.1773676797747612,
|
|
"num_tokens": 11946686.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.311216497421265,
|
|
"epoch": 0.5086360929124479,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000498277341906261,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.17049076557159423,
|
|
"num_tokens": 11962112.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.312559938430786,
|
|
"epoch": 0.5092316855270994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982720749575637,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.17459303885698318,
|
|
"num_tokens": 11976094.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.28771333694458,
|
|
"epoch": 0.509827278141751,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004982668000004602,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.1663972944021225,
|
|
"num_tokens": 11991969.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.369864988327026,
|
|
"epoch": 0.5104228707564026,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004982615170351395,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.1649647369980812,
|
|
"num_tokens": 12007588.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.311190223693847,
|
|
"epoch": 0.5110184633710542,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982562260617912,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.17173132598400115,
|
|
"num_tokens": 12021658.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.350609207153321,
|
|
"epoch": 0.5116140559857058,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982509270806052,
|
|
"loss": 5.2712,
|
|
"mean_token_accuracy": 0.16774573773145676,
|
|
"num_tokens": 12035216.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.325018644332886,
|
|
"epoch": 0.5122096486003573,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004982456200917712,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.1769700065255165,
|
|
"num_tokens": 12047435.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.338725471496582,
|
|
"epoch": 0.5128052412150089,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00049824030509548,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.1656378373503685,
|
|
"num_tokens": 12060314.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.428376197814941,
|
|
"epoch": 0.5134008338296605,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498234982091922,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.16355352103710175,
|
|
"num_tokens": 12076829.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.325110340118409,
|
|
"epoch": 0.5139964264443121,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982296510812879,
|
|
"loss": 5.1797,
|
|
"mean_token_accuracy": 0.17521792948246,
|
|
"num_tokens": 12090008.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.29318904876709,
|
|
"epoch": 0.5145920190589637,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982243120637694,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.16349251121282576,
|
|
"num_tokens": 12103163.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.415233325958252,
|
|
"epoch": 0.5151876116736153,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982189650395577,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.16468654125928878,
|
|
"num_tokens": 12117398.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.2736067295074465,
|
|
"epoch": 0.5157832042882668,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982136100088447,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.17426990270614623,
|
|
"num_tokens": 12132649.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.254623794555664,
|
|
"epoch": 0.5163787969029184,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982082469718224,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.17167138010263444,
|
|
"num_tokens": 12146385.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.291803979873658,
|
|
"epoch": 0.51697438951757,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004982028759286831,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.17808098047971727,
|
|
"num_tokens": 12159928.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.242493772506714,
|
|
"epoch": 0.5175699821322216,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004981974968796197,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.17220935076475144,
|
|
"num_tokens": 12174624.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.258213233947754,
|
|
"epoch": 0.5181655747468732,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004981921098248249,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.18022371083498,
|
|
"num_tokens": 12187383.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.2853821277618405,
|
|
"epoch": 0.5187611673615247,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498186714764492,
|
|
"loss": 5.2552,
|
|
"mean_token_accuracy": 0.17141323536634445,
|
|
"num_tokens": 12200381.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.401632022857666,
|
|
"epoch": 0.5193567599761763,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981813116988145,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.1674005776643753,
|
|
"num_tokens": 12216497.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.324771118164063,
|
|
"epoch": 0.5199523525908278,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981759006279864,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.17510557174682617,
|
|
"num_tokens": 12230368.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.328401756286621,
|
|
"epoch": 0.5205479452054794,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004981704815522014,
|
|
"loss": 5.3119,
|
|
"mean_token_accuracy": 0.16506524682044982,
|
|
"num_tokens": 12246492.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.339684391021729,
|
|
"epoch": 0.521143537820131,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004981650544716542,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.17002587243914605,
|
|
"num_tokens": 12260486.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.245989513397217,
|
|
"epoch": 0.5217391304347826,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981596193865393,
|
|
"loss": 5.1339,
|
|
"mean_token_accuracy": 0.17725353837013244,
|
|
"num_tokens": 12275001.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.285380220413208,
|
|
"epoch": 0.5223347230494342,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004981541762970517,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.1734144851565361,
|
|
"num_tokens": 12289690.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.291140413284301,
|
|
"epoch": 0.5229303156640858,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004981487252033866,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.16941753625869752,
|
|
"num_tokens": 12304098.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.265702104568481,
|
|
"epoch": 0.5235259082787374,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004981432661057396,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.17372489720582962,
|
|
"num_tokens": 12318583.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.416699361801148,
|
|
"epoch": 0.5241215008933889,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004981377990043064,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.17035623639822006,
|
|
"num_tokens": 12332239.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.245785093307495,
|
|
"epoch": 0.5247170935080405,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004981323238992831,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.17071955949068068,
|
|
"num_tokens": 12344730.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.306457901000977,
|
|
"epoch": 0.5253126861226921,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981268407908662,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.1670900508761406,
|
|
"num_tokens": 12358661.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.339504861831665,
|
|
"epoch": 0.5259082787373437,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981213496792523,
|
|
"loss": 5.2562,
|
|
"mean_token_accuracy": 0.17089206874370574,
|
|
"num_tokens": 12372876.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.371891593933105,
|
|
"epoch": 0.5265038713519953,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004981158505646383,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.16624298691749573,
|
|
"num_tokens": 12386960.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.264818429946899,
|
|
"epoch": 0.5270994639666469,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004981103434472216,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.18444036841392517,
|
|
"num_tokens": 12400497.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.320007991790772,
|
|
"epoch": 0.5276950565812983,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004981048283271997,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.17471126168966294,
|
|
"num_tokens": 12415013.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.352529716491699,
|
|
"epoch": 0.5282906491959499,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004980993052047701,
|
|
"loss": 5.2098,
|
|
"mean_token_accuracy": 0.1728607162833214,
|
|
"num_tokens": 12427915.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.217759227752685,
|
|
"epoch": 0.5288862418106015,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004980937740801313,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.1731308788061142,
|
|
"num_tokens": 12440136.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.2971789836883545,
|
|
"epoch": 0.5294818344252531,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004980882349534816,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.1695054739713669,
|
|
"num_tokens": 12454190.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.451108455657959,
|
|
"epoch": 0.5300774270399047,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980826878250195,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.16728104501962662,
|
|
"num_tokens": 12470069.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.31320161819458,
|
|
"epoch": 0.5306730196545563,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980771326949442,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.16851064711809158,
|
|
"num_tokens": 12485349.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.351583051681518,
|
|
"epoch": 0.5312686122692079,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004980715695634549,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.16711016297340392,
|
|
"num_tokens": 12500690.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.34506893157959,
|
|
"epoch": 0.5318642048838594,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004980659984307511,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.16992588862776756,
|
|
"num_tokens": 12512619.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.431726026535034,
|
|
"epoch": 0.532459797498511,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980604192970325,
|
|
"loss": 5.3382,
|
|
"mean_token_accuracy": 0.16809598505496978,
|
|
"num_tokens": 12527193.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.321417808532715,
|
|
"epoch": 0.5330553901131626,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980548321624993,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.1724133923649788,
|
|
"num_tokens": 12540127.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.2727799892425535,
|
|
"epoch": 0.5336509827278142,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498049237027352,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.17359897792339324,
|
|
"num_tokens": 12555818.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.324391317367554,
|
|
"epoch": 0.5342465753424658,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004980436338917914,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.16728706061840057,
|
|
"num_tokens": 12568337.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.267132425308228,
|
|
"epoch": 0.5348421679571174,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498038022756018,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.17018399387598038,
|
|
"num_tokens": 12581368.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.3149120807647705,
|
|
"epoch": 0.535437760571769,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980324036202335,
|
|
"loss": 5.2586,
|
|
"mean_token_accuracy": 0.16953773945569992,
|
|
"num_tokens": 12595738.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.258403062820435,
|
|
"epoch": 0.5360333531864205,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980267764846393,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.17874420434236526,
|
|
"num_tokens": 12609736.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.24589958190918,
|
|
"epoch": 0.5366289458010721,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980211413494373,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.17298338264226915,
|
|
"num_tokens": 12624101.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.228546190261841,
|
|
"epoch": 0.5372245384157236,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004980154982148296,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.17985584139823912,
|
|
"num_tokens": 12639126.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.25352725982666,
|
|
"epoch": 0.5378201310303752,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980098470810185,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.17458005100488663,
|
|
"num_tokens": 12652532.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.247041940689087,
|
|
"epoch": 0.5384157236450268,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004980041879482068,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.1760489821434021,
|
|
"num_tokens": 12666270.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.317198371887207,
|
|
"epoch": 0.5390113162596784,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004979985208165975,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.176473705470562,
|
|
"num_tokens": 12682393.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.381557273864746,
|
|
"epoch": 0.5396069088743299,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004979928456863937,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.17199707329273223,
|
|
"num_tokens": 12696685.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.215045499801636,
|
|
"epoch": 0.5402025014889815,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004979871625577991,
|
|
"loss": 5.1768,
|
|
"mean_token_accuracy": 0.1778786838054657,
|
|
"num_tokens": 12711091.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.315591716766358,
|
|
"epoch": 0.5407980941036331,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004979814714310177,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.17453586906194687,
|
|
"num_tokens": 12725041.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.298194217681885,
|
|
"epoch": 0.5413936867182847,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004979757723062533,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.17083319872617722,
|
|
"num_tokens": 12738318.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.294803953170776,
|
|
"epoch": 0.5419892793329363,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004979700651837107,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.1749401330947876,
|
|
"num_tokens": 12750695.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.28676176071167,
|
|
"epoch": 0.5425848719475879,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004979643500635942,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.17572510093450547,
|
|
"num_tokens": 12764779.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.281265306472778,
|
|
"epoch": 0.5431804645622395,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004979586269461089,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.1695711076259613,
|
|
"num_tokens": 12779197.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.266466903686523,
|
|
"epoch": 0.543776057176891,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004979528958314604,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.17766521275043487,
|
|
"num_tokens": 12791140.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.229823970794678,
|
|
"epoch": 0.5443716497915426,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979471567198539,
|
|
"loss": 5.1148,
|
|
"mean_token_accuracy": 0.18232055455446244,
|
|
"num_tokens": 12806382.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.36400842666626,
|
|
"epoch": 0.5449672424061942,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004979414096114953,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.17644681930541992,
|
|
"num_tokens": 12819095.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.120955848693848,
|
|
"epoch": 0.5455628350208458,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000497935654506591,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.18453386425971985,
|
|
"num_tokens": 12831562.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.344570922851562,
|
|
"epoch": 0.5461584276354973,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497929891405347,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.16621461212635041,
|
|
"num_tokens": 12845535.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.253591823577881,
|
|
"epoch": 0.5467540202501489,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004979241203079705,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.17461739331483841,
|
|
"num_tokens": 12859067.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.316888475418091,
|
|
"epoch": 0.5473496128648004,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004979183412146681,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.17469116747379304,
|
|
"num_tokens": 12872712.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.286416292190552,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979125541256474,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.17231532633304597,
|
|
"num_tokens": 12886701.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.256505060195923,
|
|
"epoch": 0.5485407980941036,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979067590411157,
|
|
"loss": 5.2083,
|
|
"mean_token_accuracy": 0.17644156962633134,
|
|
"num_tokens": 12900041.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.264682912826538,
|
|
"epoch": 0.5491363907087552,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000497900955961281,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.17593718469142913,
|
|
"num_tokens": 12912454.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.3814715385437015,
|
|
"epoch": 0.5497319833234068,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004978951448863514,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.1750325620174408,
|
|
"num_tokens": 12926373.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.335750865936279,
|
|
"epoch": 0.5503275759380584,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004978893258165354,
|
|
"loss": 5.2674,
|
|
"mean_token_accuracy": 0.17575511187314988,
|
|
"num_tokens": 12939837.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.245766830444336,
|
|
"epoch": 0.55092316855271,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978834987520417,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.17340973317623137,
|
|
"num_tokens": 12952904.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.352421474456787,
|
|
"epoch": 0.5515187611673615,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978776636930792,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.16467048674821855,
|
|
"num_tokens": 12966896.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.3068138599395756,
|
|
"epoch": 0.5521143537820131,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978718206398574,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.1763380780816078,
|
|
"num_tokens": 12980841.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.21550874710083,
|
|
"epoch": 0.5527099463966647,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004978659695925856,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.17739854902029037,
|
|
"num_tokens": 12994506.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.25582537651062,
|
|
"epoch": 0.5533055390113163,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004978601105514739,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.17436138540506363,
|
|
"num_tokens": 13008817.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.3168446063995365,
|
|
"epoch": 0.5539011316259679,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004978542435167324,
|
|
"loss": 5.2341,
|
|
"mean_token_accuracy": 0.1735334277153015,
|
|
"num_tokens": 13024227.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.274542427062988,
|
|
"epoch": 0.5544967242406195,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004978483684885716,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.18451839685440063,
|
|
"num_tokens": 13037448.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.150850582122803,
|
|
"epoch": 0.5550923168552709,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004978424854672021,
|
|
"loss": 5.1021,
|
|
"mean_token_accuracy": 0.18179431259632112,
|
|
"num_tokens": 13050582.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.290941286087036,
|
|
"epoch": 0.5556879094699225,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004978365944528349,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.17829543650150298,
|
|
"num_tokens": 13063059.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.3626429557800295,
|
|
"epoch": 0.5562835020845741,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004978306954456814,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.17048961371183396,
|
|
"num_tokens": 13077193.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.294120168685913,
|
|
"epoch": 0.5568790946992257,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978247884459532,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.1663368508219719,
|
|
"num_tokens": 13091462.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.299335861206055,
|
|
"epoch": 0.5574746873138773,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004978188734538621,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.16766809076070785,
|
|
"num_tokens": 13107406.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.325074481964111,
|
|
"epoch": 0.5580702799285289,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978129504696203,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.17293520420789718,
|
|
"num_tokens": 13123623.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.227014827728271,
|
|
"epoch": 0.5586658725431805,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978070194934402,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.17049912959337235,
|
|
"num_tokens": 13138644.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.325120639801026,
|
|
"epoch": 0.559261465157832,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004978010805255347,
|
|
"loss": 5.3519,
|
|
"mean_token_accuracy": 0.16697487980127335,
|
|
"num_tokens": 13152485.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.353164482116699,
|
|
"epoch": 0.5598570577724836,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977951335661165,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.17868136912584304,
|
|
"num_tokens": 13165766.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.1698767185211185,
|
|
"epoch": 0.5604526503871352,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004977891786153992,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.16931375563144685,
|
|
"num_tokens": 13180298.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.297531270980835,
|
|
"epoch": 0.5610482430017868,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004977832156735963,
|
|
"loss": 5.3233,
|
|
"mean_token_accuracy": 0.1656366392970085,
|
|
"num_tokens": 13194925.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.347880029678345,
|
|
"epoch": 0.5616438356164384,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004977772447409217,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.17721495926380157,
|
|
"num_tokens": 13208486.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.278501892089844,
|
|
"epoch": 0.56223942823109,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004977712658175894,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.17331082373857498,
|
|
"num_tokens": 13222428.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.263060474395752,
|
|
"epoch": 0.5628350208457416,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004977652789038142,
|
|
"loss": 5.2225,
|
|
"mean_token_accuracy": 0.1695805549621582,
|
|
"num_tokens": 13237341.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.2851673603057865,
|
|
"epoch": 0.5634306134603931,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004977592839998105,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.17178732603788377,
|
|
"num_tokens": 13251085.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.310550737380981,
|
|
"epoch": 0.5640262060750447,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004977532811057936,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.17437066435813903,
|
|
"num_tokens": 13266660.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.317284679412841,
|
|
"epoch": 0.5646217986896962,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004977472702219786,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.1769043505191803,
|
|
"num_tokens": 13280550.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.262067699432373,
|
|
"epoch": 0.5652173913043478,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004977412513485812,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.18211816400289535,
|
|
"num_tokens": 13292905.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.233112621307373,
|
|
"epoch": 0.5658129839189994,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004977352244858172,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.18318653255701065,
|
|
"num_tokens": 13305271.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.302807807922363,
|
|
"epoch": 0.566408576533651,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004977291896339029,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.16958033442497253,
|
|
"num_tokens": 13319904.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.3023487567901615,
|
|
"epoch": 0.5670041691483025,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004977231467930546,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.17836320400238037,
|
|
"num_tokens": 13331799.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.308155584335327,
|
|
"epoch": 0.5675997617629541,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977170959634893,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.17886223196983336,
|
|
"num_tokens": 13345269.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.236552095413208,
|
|
"epoch": 0.5681953543776057,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004977110371454239,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.17568017542362213,
|
|
"num_tokens": 13358555.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.335853862762451,
|
|
"epoch": 0.5687909469922573,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977049703390755,
|
|
"loss": 5.2912,
|
|
"mean_token_accuracy": 0.17120511084794998,
|
|
"num_tokens": 13373444.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.320463800430298,
|
|
"epoch": 0.5693865396069089,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004976988955446622,
|
|
"loss": 5.2377,
|
|
"mean_token_accuracy": 0.17114159911870958,
|
|
"num_tokens": 13387530.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.282199907302856,
|
|
"epoch": 0.5699821322215605,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004976928127624013,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.17118949741125106,
|
|
"num_tokens": 13402718.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.3631573677062985,
|
|
"epoch": 0.570577724836212,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004976867219925116,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.1681893140077591,
|
|
"num_tokens": 13416076.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.2490002632141115,
|
|
"epoch": 0.5711733174508636,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497680623235211,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.18470903784036635,
|
|
"num_tokens": 13428286.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.235005187988281,
|
|
"epoch": 0.5717689100655152,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004976745164907185,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.16941055059432983,
|
|
"num_tokens": 13442801.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.349837732315064,
|
|
"epoch": 0.5723645026801668,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004976684017592533,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.17438929229974748,
|
|
"num_tokens": 13457796.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.272896099090576,
|
|
"epoch": 0.5729600952948184,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004976622790410345,
|
|
"loss": 5.2438,
|
|
"mean_token_accuracy": 0.17719511240720748,
|
|
"num_tokens": 13473291.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.2146588325500485,
|
|
"epoch": 0.5735556879094699,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004976561483362818,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.17478664815425873,
|
|
"num_tokens": 13487275.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.252813005447388,
|
|
"epoch": 0.5741512805241215,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000497650009645215,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.179751193523407,
|
|
"num_tokens": 13500148.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.258257150650024,
|
|
"epoch": 0.574746873138773,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004976438629680543,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.1799370363354683,
|
|
"num_tokens": 13514231.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.297312593460083,
|
|
"epoch": 0.5753424657534246,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976377083050204,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.16721879839897155,
|
|
"num_tokens": 13528691.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.266164541244507,
|
|
"epoch": 0.5759380583680762,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976315456563339,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.177544204890728,
|
|
"num_tokens": 13542115.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.299746417999268,
|
|
"epoch": 0.5765336509827278,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004976253750222157,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.17480504214763642,
|
|
"num_tokens": 13556269.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.390791893005371,
|
|
"epoch": 0.5771292435973794,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004976191964028874,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.16887204647064208,
|
|
"num_tokens": 13571853.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.321684551239014,
|
|
"epoch": 0.577724836212031,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004976130097985703,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.1697498857975006,
|
|
"num_tokens": 13587631.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.3115157127380375,
|
|
"epoch": 0.5783204288266826,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004976068152094867,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.174340058863163,
|
|
"num_tokens": 13603140.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.199744033813476,
|
|
"epoch": 0.5789160214413341,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004976006126358584,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.18753324449062347,
|
|
"num_tokens": 13617606.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.349912548065186,
|
|
"epoch": 0.5795116140559857,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004975944020779082,
|
|
"loss": 5.2528,
|
|
"mean_token_accuracy": 0.16865813583135605,
|
|
"num_tokens": 13632244.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.325191640853882,
|
|
"epoch": 0.5801072066706373,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004975881835358586,
|
|
"loss": 5.2384,
|
|
"mean_token_accuracy": 0.1719406709074974,
|
|
"num_tokens": 13646166.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.3085957050323485,
|
|
"epoch": 0.5807027992852889,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975819570099328,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.17428722381591796,
|
|
"num_tokens": 13661141.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.309556388854981,
|
|
"epoch": 0.5812983918999405,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497575722500354,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.17746633291244507,
|
|
"num_tokens": 13675007.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.266643953323364,
|
|
"epoch": 0.5818939845145921,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497569480007346,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.17363881319761276,
|
|
"num_tokens": 13690679.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.221466684341431,
|
|
"epoch": 0.5824895771292437,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004975632295311327,
|
|
"loss": 5.1936,
|
|
"mean_token_accuracy": 0.17407945543527603,
|
|
"num_tokens": 13705068.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.271433782577515,
|
|
"epoch": 0.5830851697438951,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004975569710719382,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.17641925811767578,
|
|
"num_tokens": 13719550.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.293432092666626,
|
|
"epoch": 0.5836807623585467,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004975507046299869,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.17028291672468185,
|
|
"num_tokens": 13733516.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.389757871627808,
|
|
"epoch": 0.5842763549731983,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004975444302055038,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.16588335782289504,
|
|
"num_tokens": 13747242.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.244137477874756,
|
|
"epoch": 0.5848719475878499,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004975381477987136,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.17476743310689927,
|
|
"num_tokens": 13761434.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.379440784454346,
|
|
"epoch": 0.5854675402025015,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004975318574098422,
|
|
"loss": 5.3153,
|
|
"mean_token_accuracy": 0.17479705959558486,
|
|
"num_tokens": 13773942.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.270811080932617,
|
|
"epoch": 0.586063132817153,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004975255590391147,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.18179279416799546,
|
|
"num_tokens": 13787217.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.293763113021851,
|
|
"epoch": 0.5866587254318046,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004975192526867572,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.17522521913051606,
|
|
"num_tokens": 13801444.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.306093168258667,
|
|
"epoch": 0.5872543180464562,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004975129383529959,
|
|
"loss": 5.2811,
|
|
"mean_token_accuracy": 0.17177170068025588,
|
|
"num_tokens": 13814453.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.252437019348145,
|
|
"epoch": 0.5878499106611078,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004975066160380573,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.1723177969455719,
|
|
"num_tokens": 13829620.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.243211650848389,
|
|
"epoch": 0.5884455032757594,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004975002857421681,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.17892846018075942,
|
|
"num_tokens": 13842005.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.188482189178467,
|
|
"epoch": 0.589041095890411,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004974939474655554,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.18103287667036055,
|
|
"num_tokens": 13854299.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.206177282333374,
|
|
"epoch": 0.5896366885050626,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004974876012084468,
|
|
"loss": 5.1132,
|
|
"mean_token_accuracy": 0.17805931121110916,
|
|
"num_tokens": 13866294.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.282791042327881,
|
|
"epoch": 0.5902322811197142,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004974812469710694,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.17739191353321077,
|
|
"num_tokens": 13879820.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.29354043006897,
|
|
"epoch": 0.5908278737343657,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004974748847536516,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.16754303127527237,
|
|
"num_tokens": 13894664.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.274734592437744,
|
|
"epoch": 0.5914234663490173,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004974685145564213,
|
|
"loss": 5.2261,
|
|
"mean_token_accuracy": 0.16944496780633928,
|
|
"num_tokens": 13908706.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.2160248279571535,
|
|
"epoch": 0.5920190589636688,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004974621363796071,
|
|
"loss": 5.123,
|
|
"mean_token_accuracy": 0.18300386071205138,
|
|
"num_tokens": 13921402.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.279775524139405,
|
|
"epoch": 0.5926146515783204,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004974557502234378,
|
|
"loss": 5.2129,
|
|
"mean_token_accuracy": 0.1716919645667076,
|
|
"num_tokens": 13934731.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.32079119682312,
|
|
"epoch": 0.593210244192972,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974493560881423,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.1728757157921791,
|
|
"num_tokens": 13947990.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.2941478252410885,
|
|
"epoch": 0.5938058368076236,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004974429539739502,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.18083310425281524,
|
|
"num_tokens": 13961167.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.2404032230377195,
|
|
"epoch": 0.5944014294222751,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004974365438810911,
|
|
"loss": 5.1439,
|
|
"mean_token_accuracy": 0.18069044053554534,
|
|
"num_tokens": 13974136.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.211938142776489,
|
|
"epoch": 0.5949970220369267,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004974301258097948,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.17402159571647643,
|
|
"num_tokens": 13989229.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.363648128509522,
|
|
"epoch": 0.5955926146515783,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004974236997602915,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.16377746313810349,
|
|
"num_tokens": 14003136.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.244558906555175,
|
|
"epoch": 0.5961882072662299,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004974172657328116,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.17638401091098785,
|
|
"num_tokens": 14017712.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.354072093963623,
|
|
"epoch": 0.5967837998808815,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000497410823727586,
|
|
"loss": 5.2796,
|
|
"mean_token_accuracy": 0.17095719128847123,
|
|
"num_tokens": 14032740.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.2810557842254635,
|
|
"epoch": 0.5973793924955331,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000497404373744846,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.17525134980678558,
|
|
"num_tokens": 14048059.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.251811695098877,
|
|
"epoch": 0.5979749851101847,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004973979157848227,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.1775208368897438,
|
|
"num_tokens": 14062318.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.357703113555909,
|
|
"epoch": 0.5985705777248362,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004973914498477475,
|
|
"loss": 5.2479,
|
|
"mean_token_accuracy": 0.16990814507007598,
|
|
"num_tokens": 14076617.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.297600936889649,
|
|
"epoch": 0.5991661703394878,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004973849759338527,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.16754772812128066,
|
|
"num_tokens": 14092067.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.293257522583008,
|
|
"epoch": 0.5997617629541394,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004973784940433706,
|
|
"loss": 5.2301,
|
|
"mean_token_accuracy": 0.16913847923278807,
|
|
"num_tokens": 14106969.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.2666483402252195,
|
|
"epoch": 0.600357355568791,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004973720041765332,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.17801895439624787,
|
|
"num_tokens": 14119877.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.2857410430908205,
|
|
"epoch": 0.6009529481834425,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004973655063335736,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.17118658423423766,
|
|
"num_tokens": 14133831.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.300510883331299,
|
|
"epoch": 0.6015485407980941,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000497359000514725,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.1746649146080017,
|
|
"num_tokens": 14147482.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.179050350189209,
|
|
"epoch": 0.6021441334127456,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004973524867202205,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.17852700650691986,
|
|
"num_tokens": 14162276.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.2645927429199215,
|
|
"epoch": 0.6027397260273972,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004973459649502939,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.1715109184384346,
|
|
"num_tokens": 14177129.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.327297306060791,
|
|
"epoch": 0.6033353186420488,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004973394352051789,
|
|
"loss": 5.1975,
|
|
"mean_token_accuracy": 0.18072985857725143,
|
|
"num_tokens": 14191104.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.2598557472229,
|
|
"epoch": 0.6039309112567004,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00049733289748511,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.1756446823477745,
|
|
"num_tokens": 14205703.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.188370323181152,
|
|
"epoch": 0.604526503871352,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004973263517903213,
|
|
"loss": 5.0214,
|
|
"mean_token_accuracy": 0.1910773128271103,
|
|
"num_tokens": 14219108.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.308261251449585,
|
|
"epoch": 0.6051220964860036,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004973197981210481,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.173814158141613,
|
|
"num_tokens": 14231677.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.1808576583862305,
|
|
"epoch": 0.6057176891006552,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004973132364775252,
|
|
"loss": 5.0792,
|
|
"mean_token_accuracy": 0.18430269807577132,
|
|
"num_tokens": 14246844.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.308371114730835,
|
|
"epoch": 0.6063132817153067,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004973066668599879,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.16899402141571046,
|
|
"num_tokens": 14261879.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.34621295928955,
|
|
"epoch": 0.6069088743299583,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004973000892686719,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.1716870293021202,
|
|
"num_tokens": 14276884.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.241523933410645,
|
|
"epoch": 0.6075044669446099,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004972935037038131,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.17546847611665725,
|
|
"num_tokens": 14291997.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.291032123565674,
|
|
"epoch": 0.6081000595592615,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004972869101656478,
|
|
"loss": 5.1095,
|
|
"mean_token_accuracy": 0.18453371226787568,
|
|
"num_tokens": 14304407.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.213338184356689,
|
|
"epoch": 0.6086956521739131,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972803086544125,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.17609335482120514,
|
|
"num_tokens": 14317948.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.260320615768433,
|
|
"epoch": 0.6092912447885647,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004972736991703439,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.1777164086699486,
|
|
"num_tokens": 14330100.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.212447547912598,
|
|
"epoch": 0.6098868374032163,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004972670817136791,
|
|
"loss": 5.174,
|
|
"mean_token_accuracy": 0.17592280507087707,
|
|
"num_tokens": 14343655.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.240213108062744,
|
|
"epoch": 0.6104824300178677,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004972604562846554,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.17885151207447053,
|
|
"num_tokens": 14357049.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.282596492767334,
|
|
"epoch": 0.6110780226325193,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004972538228835106,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.17270536720752716,
|
|
"num_tokens": 14371184.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.36376805305481,
|
|
"epoch": 0.6116736152471709,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004972471815104825,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.16974403709173203,
|
|
"num_tokens": 14385076.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.242397308349609,
|
|
"epoch": 0.6122692078618225,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972405321658094,
|
|
"loss": 5.2047,
|
|
"mean_token_accuracy": 0.17376460134983063,
|
|
"num_tokens": 14400071.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.338957357406616,
|
|
"epoch": 0.6128648004764741,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004972338748497297,
|
|
"loss": 5.2435,
|
|
"mean_token_accuracy": 0.17573502212762832,
|
|
"num_tokens": 14414203.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.370514059066773,
|
|
"epoch": 0.6134603930911257,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004972272095624822,
|
|
"loss": 5.2544,
|
|
"mean_token_accuracy": 0.1682635024189949,
|
|
"num_tokens": 14429325.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.290705251693725,
|
|
"epoch": 0.6140559857057772,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000497220536304306,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.1775890976190567,
|
|
"num_tokens": 14443432.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.323477172851563,
|
|
"epoch": 0.6146515783204288,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004972138550754405,
|
|
"loss": 5.1646,
|
|
"mean_token_accuracy": 0.17248053550720216,
|
|
"num_tokens": 14457251.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.246008968353271,
|
|
"epoch": 0.6152471709350804,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004972071658761254,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.17151902467012406,
|
|
"num_tokens": 14472931.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.292934417724609,
|
|
"epoch": 0.615842763549732,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972004687066005,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.17614313066005707,
|
|
"num_tokens": 14484689.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.250682067871094,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004971937635671061,
|
|
"loss": 5.1705,
|
|
"mean_token_accuracy": 0.17789831012487411,
|
|
"num_tokens": 14499522.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.278428792953491,
|
|
"epoch": 0.6170339487790352,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004971870504578825,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.17528192847967147,
|
|
"num_tokens": 14513347.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.187355995178223,
|
|
"epoch": 0.6176295413936868,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004971803293791708,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.1745859295129776,
|
|
"num_tokens": 14526741.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.153700256347657,
|
|
"epoch": 0.6182251340083383,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004971736003312119,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.18086738139390945,
|
|
"num_tokens": 14540317.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.2340291976928714,
|
|
"epoch": 0.6188207266229899,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004971668633142472,
|
|
"loss": 5.1835,
|
|
"mean_token_accuracy": 0.17786173522472382,
|
|
"num_tokens": 14553468.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.295296669006348,
|
|
"epoch": 0.6194163192376414,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004971601183285183,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.17800217717885972,
|
|
"num_tokens": 14566294.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.323761796951294,
|
|
"epoch": 0.620011911852293,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004971533653742672,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.17776500582695007,
|
|
"num_tokens": 14581603.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.256529426574707,
|
|
"epoch": 0.6206075044669446,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497146604451736,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.1765766441822052,
|
|
"num_tokens": 14596957.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.193475770950317,
|
|
"epoch": 0.6212030970815962,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004971398355611674,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.18411577492952347,
|
|
"num_tokens": 14609228.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.23244686126709,
|
|
"epoch": 0.6217986896962477,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000497133058702804,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.17471662312746047,
|
|
"num_tokens": 14621928.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.241820049285889,
|
|
"epoch": 0.6223942823108993,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000497126273876889,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.17659086883068084,
|
|
"num_tokens": 14634896.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.262858772277832,
|
|
"epoch": 0.6229898749255509,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004971194810836657,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.17696063220500946,
|
|
"num_tokens": 14648867.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.336976051330566,
|
|
"epoch": 0.6235854675402025,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004971126803233778,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.16731467396020888,
|
|
"num_tokens": 14664360.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.247632026672363,
|
|
"epoch": 0.6241810601548541,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004971058715962691,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.17362555414438247,
|
|
"num_tokens": 14678173.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.288340950012207,
|
|
"epoch": 0.6247766527695057,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000497099054902584,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.17454540729522705,
|
|
"num_tokens": 14690710.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.242592000961304,
|
|
"epoch": 0.6253722453841573,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004970922302425669,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.17462283968925477,
|
|
"num_tokens": 14705678.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.220586681365967,
|
|
"epoch": 0.6259678379988088,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004970853976164624,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.17382548302412032,
|
|
"num_tokens": 14719357.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.2034961700439455,
|
|
"epoch": 0.6265634306134604,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000497078557024516,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.18411754071712494,
|
|
"num_tokens": 14732176.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.270791912078858,
|
|
"epoch": 0.627159023228112,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970717084669728,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.18009524941444396,
|
|
"num_tokens": 14746789.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.202559518814087,
|
|
"epoch": 0.6277546158427636,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004970648519440785,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.17455288469791413,
|
|
"num_tokens": 14759233.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.2855072021484375,
|
|
"epoch": 0.6283502084574152,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004970579874560789,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.17193642854690552,
|
|
"num_tokens": 14773187.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.4334992408752445,
|
|
"epoch": 0.6289458010720667,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004970511150032205,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.16571492105722427,
|
|
"num_tokens": 14788501.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.204394817352295,
|
|
"epoch": 0.6295413936867182,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004970442345857495,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.17159572541713713,
|
|
"num_tokens": 14802945.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.355725860595703,
|
|
"epoch": 0.6301369863013698,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004970373462039128,
|
|
"loss": 5.3506,
|
|
"mean_token_accuracy": 0.1681552141904831,
|
|
"num_tokens": 14818572.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.34833607673645,
|
|
"epoch": 0.6307325789160214,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004970304498579576,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.1728329047560692,
|
|
"num_tokens": 14832962.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.237042570114136,
|
|
"epoch": 0.631328171530673,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004970235455481312,
|
|
"loss": 5.1248,
|
|
"mean_token_accuracy": 0.18213633298873902,
|
|
"num_tokens": 14846181.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.191067123413086,
|
|
"epoch": 0.6319237641453246,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004970166332746811,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.1834474578499794,
|
|
"num_tokens": 14858859.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.247312688827515,
|
|
"epoch": 0.6325193567599762,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004970097130378554,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.17783977836370468,
|
|
"num_tokens": 14873858.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.232142591476441,
|
|
"epoch": 0.6331149493746278,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004970027848379023,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.18353971987962722,
|
|
"num_tokens": 14888287.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.208676290512085,
|
|
"epoch": 0.6337105419892793,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004969958486750702,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.1775114506483078,
|
|
"num_tokens": 14903261.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.220968389511109,
|
|
"epoch": 0.6343061346039309,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000496988904549608,
|
|
"loss": 5.146,
|
|
"mean_token_accuracy": 0.17986845672130586,
|
|
"num_tokens": 14917788.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.314776372909546,
|
|
"epoch": 0.6349017272185825,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004969819524617647,
|
|
"loss": 5.214,
|
|
"mean_token_accuracy": 0.17816781997680664,
|
|
"num_tokens": 14930975.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.359452533721924,
|
|
"epoch": 0.6354973198332341,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004969749924117896,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.1749282509088516,
|
|
"num_tokens": 14945904.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.254864931106567,
|
|
"epoch": 0.6360929124478857,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969680243999325,
|
|
"loss": 5.1627,
|
|
"mean_token_accuracy": 0.18259824961423873,
|
|
"num_tokens": 14960885.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.185154628753662,
|
|
"epoch": 0.6366885050625373,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004969610484264433,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.18272535651922225,
|
|
"num_tokens": 14973061.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.26742844581604,
|
|
"epoch": 0.6372840976771889,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969540644915721,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.17805005460977555,
|
|
"num_tokens": 14985921.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.299582433700562,
|
|
"epoch": 0.6378796902918403,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004969470725955695,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.17010295391082764,
|
|
"num_tokens": 15000008.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.274208736419678,
|
|
"epoch": 0.6384752829064919,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969400727386864,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.16947222948074342,
|
|
"num_tokens": 15014175.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.2563680648803714,
|
|
"epoch": 0.6390708755211435,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004969330649211737,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.1724191576242447,
|
|
"num_tokens": 15027872.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.356392669677734,
|
|
"epoch": 0.6396664681357951,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004969260491432826,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.17443400323390962,
|
|
"num_tokens": 15041295.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.266040325164795,
|
|
"epoch": 0.6402620607504467,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004969190254052651,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.18029980957508088,
|
|
"num_tokens": 15055756.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.291396808624268,
|
|
"epoch": 0.6408576533650983,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004969119937073731,
|
|
"loss": 5.1696,
|
|
"mean_token_accuracy": 0.17696785926818848,
|
|
"num_tokens": 15070375.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.219432926177978,
|
|
"epoch": 0.6414532459797498,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004969049540498585,
|
|
"loss": 5.1353,
|
|
"mean_token_accuracy": 0.186016646027565,
|
|
"num_tokens": 15084580.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.150923585891723,
|
|
"epoch": 0.6420488385944014,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004968979064329741,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.1771887242794037,
|
|
"num_tokens": 15097137.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.264317798614502,
|
|
"epoch": 0.642644431209053,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004968908508569725,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.17895198613405228,
|
|
"num_tokens": 15112375.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.321389293670654,
|
|
"epoch": 0.6432400238237046,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004968837873221069,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.1721085026860237,
|
|
"num_tokens": 15126356.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.274231100082398,
|
|
"epoch": 0.6438356164383562,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004968767158286306,
|
|
"loss": 5.1872,
|
|
"mean_token_accuracy": 0.17295642346143722,
|
|
"num_tokens": 15140626.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.25229172706604,
|
|
"epoch": 0.6444312090530078,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004968696363767972,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.16706711500883104,
|
|
"num_tokens": 15155131.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.29266095161438,
|
|
"epoch": 0.6450268016676594,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004968625489668607,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.17028987407684326,
|
|
"num_tokens": 15170488.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.27967209815979,
|
|
"epoch": 0.6456223942823109,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004968554535990754,
|
|
"loss": 5.1214,
|
|
"mean_token_accuracy": 0.18514140397310258,
|
|
"num_tokens": 15182905.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.2903303623199465,
|
|
"epoch": 0.6462179868969625,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004968483502736956,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.17535352259874343,
|
|
"num_tokens": 15196341.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.24964542388916,
|
|
"epoch": 0.646813579511614,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004968412389909762,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.1763901263475418,
|
|
"num_tokens": 15208973.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.260818958282471,
|
|
"epoch": 0.6474091721262656,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004968341197511722,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.17202088981866837,
|
|
"num_tokens": 15225122.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.28341326713562,
|
|
"epoch": 0.6480047647409172,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004968269925545391,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.1726364701986313,
|
|
"num_tokens": 15236932.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.276095724105835,
|
|
"epoch": 0.6486003573555688,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004968198574013323,
|
|
"loss": 5.1152,
|
|
"mean_token_accuracy": 0.17545382380485536,
|
|
"num_tokens": 15249060.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.25116720199585,
|
|
"epoch": 0.6491959499702203,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004968127142918081,
|
|
"loss": 5.1437,
|
|
"mean_token_accuracy": 0.1719391718506813,
|
|
"num_tokens": 15263544.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.207317209243774,
|
|
"epoch": 0.6497915425848719,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004968055632262223,
|
|
"loss": 5.0638,
|
|
"mean_token_accuracy": 0.1818058341741562,
|
|
"num_tokens": 15276294.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.295772695541382,
|
|
"epoch": 0.6503871351995235,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004967984042048317,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.1768563210964203,
|
|
"num_tokens": 15290352.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.316025686264038,
|
|
"epoch": 0.6509827278141751,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004967912372278928,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.17522146105766295,
|
|
"num_tokens": 15304607.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.25055627822876,
|
|
"epoch": 0.6515783204288267,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000496784062295663,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.16945648789405823,
|
|
"num_tokens": 15319846.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.318081998825074,
|
|
"epoch": 0.6521739130434783,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004967768794083994,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.17167151868343353,
|
|
"num_tokens": 15335668.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.256131887435913,
|
|
"epoch": 0.6527695056581299,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004967696885663597,
|
|
"loss": 5.2042,
|
|
"mean_token_accuracy": 0.17611437737941743,
|
|
"num_tokens": 15350839.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.234712314605713,
|
|
"epoch": 0.6533650982727814,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000496762489769802,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.17627657800912858,
|
|
"num_tokens": 15364289.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.215084362030029,
|
|
"epoch": 0.653960690887433,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004967552830189842,
|
|
"loss": 5.1022,
|
|
"mean_token_accuracy": 0.18103786259889604,
|
|
"num_tokens": 15378042.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.297262954711914,
|
|
"epoch": 0.6545562835020846,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004967480683141651,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.1727676585316658,
|
|
"num_tokens": 15392128.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.303278636932373,
|
|
"epoch": 0.6551518761167362,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000496740845655603,
|
|
"loss": 5.2982,
|
|
"mean_token_accuracy": 0.16688822507858275,
|
|
"num_tokens": 15406723.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.244821357727051,
|
|
"epoch": 0.6557474687313878,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004967336150435576,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.17940400838851928,
|
|
"num_tokens": 15421036.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.237602090835571,
|
|
"epoch": 0.6563430613460393,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004967263764782878,
|
|
"loss": 5.1892,
|
|
"mean_token_accuracy": 0.172034415602684,
|
|
"num_tokens": 15434486.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.31434850692749,
|
|
"epoch": 0.6569386539606908,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004967191299600535,
|
|
"loss": 5.2726,
|
|
"mean_token_accuracy": 0.16809257715940476,
|
|
"num_tokens": 15449378.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.37506856918335,
|
|
"epoch": 0.6575342465753424,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004967118754891144,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.17728877812623978,
|
|
"num_tokens": 15463983.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.239032649993897,
|
|
"epoch": 0.658129839189994,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004967046130657309,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.16959753930568694,
|
|
"num_tokens": 15478397.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.269223308563232,
|
|
"epoch": 0.6587254318046456,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004966973426901634,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.16762853860855104,
|
|
"num_tokens": 15491511.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.262848234176635,
|
|
"epoch": 0.6593210244192972,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004966900643626726,
|
|
"loss": 5.0638,
|
|
"mean_token_accuracy": 0.18268539607524872,
|
|
"num_tokens": 15505103.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.204114198684692,
|
|
"epoch": 0.6599166170339488,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004966827780835197,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.17175271809101106,
|
|
"num_tokens": 15520216.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.204130983352661,
|
|
"epoch": 0.6605122096486004,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004966754838529659,
|
|
"loss": 5.1265,
|
|
"mean_token_accuracy": 0.177274252474308,
|
|
"num_tokens": 15532879.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.275674629211426,
|
|
"epoch": 0.6611078022632519,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000496668181671273,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.18592740893363952,
|
|
"num_tokens": 15545600.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.2772743701934814,
|
|
"epoch": 0.6617033948779035,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004966608715387029,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.17208917438983917,
|
|
"num_tokens": 15560910.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.359844207763672,
|
|
"epoch": 0.6622989874925551,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004966535534555175,
|
|
"loss": 5.2919,
|
|
"mean_token_accuracy": 0.17054711133241654,
|
|
"num_tokens": 15575041.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.246930885314941,
|
|
"epoch": 0.6628945801072067,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004966462274219797,
|
|
"loss": 5.1481,
|
|
"mean_token_accuracy": 0.1833227679133415,
|
|
"num_tokens": 15588399.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.176308727264404,
|
|
"epoch": 0.6634901727218583,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000496638893438352,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.19580963850021363,
|
|
"num_tokens": 15600010.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.303543996810913,
|
|
"epoch": 0.6640857653365099,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004966315515048977,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.1818844884634018,
|
|
"num_tokens": 15613703.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.3508154392242435,
|
|
"epoch": 0.6646813579511615,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004966242016218799,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.16877596974372863,
|
|
"num_tokens": 15628198.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.289147567749024,
|
|
"epoch": 0.6652769505658129,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004966168437895624,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.16936313956975937,
|
|
"num_tokens": 15641410.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.206103897094726,
|
|
"epoch": 0.6658725431804645,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004966094780082089,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.18527144491672515,
|
|
"num_tokens": 15656052.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.2781455516815186,
|
|
"epoch": 0.6664681357951161,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004966021042780837,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.17972885966300964,
|
|
"num_tokens": 15669319.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.243108606338501,
|
|
"epoch": 0.6670637284097677,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004965947225994516,
|
|
"loss": 5.1603,
|
|
"mean_token_accuracy": 0.17580400705337523,
|
|
"num_tokens": 15684951.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.210223054885864,
|
|
"epoch": 0.6676593210244193,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004965873329725769,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.16744268536567689,
|
|
"num_tokens": 15699352.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.247168064117432,
|
|
"epoch": 0.6682549136390709,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004965799353977248,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.18507222682237626,
|
|
"num_tokens": 15713183.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.260070037841797,
|
|
"epoch": 0.6688505062537224,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004965725298751608,
|
|
"loss": 5.1836,
|
|
"mean_token_accuracy": 0.1750590056180954,
|
|
"num_tokens": 15725985.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.278530168533325,
|
|
"epoch": 0.669446098868374,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004965651164051504,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.17156305760145188,
|
|
"num_tokens": 15740146.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.240599155426025,
|
|
"epoch": 0.6700416914830256,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004965576949879594,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.17673333883285522,
|
|
"num_tokens": 15753590.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.27260012626648,
|
|
"epoch": 0.6706372840976772,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004965502656238543,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.17479356080293657,
|
|
"num_tokens": 15768018.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.26133394241333,
|
|
"epoch": 0.6712328767123288,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004965428283131013,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.18158396035432817,
|
|
"num_tokens": 15783112.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.308488273620606,
|
|
"epoch": 0.6718284693269804,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004965353830559671,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.1742812544107437,
|
|
"num_tokens": 15798730.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.181888771057129,
|
|
"epoch": 0.672424061941632,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004965279298527192,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.18498864024877548,
|
|
"num_tokens": 15812555.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.3095481395721436,
|
|
"epoch": 0.6730196545562835,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004965204687036244,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.17621926069259644,
|
|
"num_tokens": 15824512.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.3290040493011475,
|
|
"epoch": 0.6736152471709351,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004965129996089507,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.16889175921678543,
|
|
"num_tokens": 15839960.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.336944723129273,
|
|
"epoch": 0.6742108397855867,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004965055225689658,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.1736688196659088,
|
|
"num_tokens": 15854841.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.198430013656616,
|
|
"epoch": 0.6748064324002382,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004964980375839379,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.1848810076713562,
|
|
"num_tokens": 15866701.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.18293867111206,
|
|
"epoch": 0.6754020250148898,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004964905446541355,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.1819382756948471,
|
|
"num_tokens": 15880227.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.244812536239624,
|
|
"epoch": 0.6759976176295414,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004964830437798276,
|
|
"loss": 5.2312,
|
|
"mean_token_accuracy": 0.17188685536384582,
|
|
"num_tokens": 15894748.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.270194625854492,
|
|
"epoch": 0.6765932102441929,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004964755349612829,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.18038902729749678,
|
|
"num_tokens": 15908103.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.30793080329895,
|
|
"epoch": 0.6771888028588445,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004964680181987709,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.16952954679727555,
|
|
"num_tokens": 15920996.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.279721975326538,
|
|
"epoch": 0.6777843954734961,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000496460493492561,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.16780340671539307,
|
|
"num_tokens": 15934922.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.302792024612427,
|
|
"epoch": 0.6783799880881477,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004964529608429234,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.1761642128229141,
|
|
"num_tokens": 15948903.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.272900342941284,
|
|
"epoch": 0.6789755807027993,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004964454202501282,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.17429507672786712,
|
|
"num_tokens": 15963610.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.188199806213379,
|
|
"epoch": 0.6795711733174509,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004964378717144458,
|
|
"loss": 5.0557,
|
|
"mean_token_accuracy": 0.18079013824462892,
|
|
"num_tokens": 15977247.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.1593859672546385,
|
|
"epoch": 0.6801667659321025,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000496430315236147,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.17782935053110122,
|
|
"num_tokens": 15991856.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.28056902885437,
|
|
"epoch": 0.680762358546754,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004964227508155027,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.1803913652896881,
|
|
"num_tokens": 16006071.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.218461418151856,
|
|
"epoch": 0.6813579511614056,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004964151784527844,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.17430185675621032,
|
|
"num_tokens": 16021164.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.259990215301514,
|
|
"epoch": 0.6819535437760572,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004964075981482637,
|
|
"loss": 5.1593,
|
|
"mean_token_accuracy": 0.17553398460149766,
|
|
"num_tokens": 16035251.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.2750194549560545,
|
|
"epoch": 0.6825491363907088,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004964000099022124,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.1796842023730278,
|
|
"num_tokens": 16048628.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.2417799949646,
|
|
"epoch": 0.6831447290053604,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004963924137149027,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.18654934614896773,
|
|
"num_tokens": 16061612.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.226237440109253,
|
|
"epoch": 0.6837403216200119,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004963848095866072,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.17730426490306855,
|
|
"num_tokens": 16075506.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.249377059936523,
|
|
"epoch": 0.6843359142346634,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004963771975175984,
|
|
"loss": 5.2629,
|
|
"mean_token_accuracy": 0.16570603251457214,
|
|
"num_tokens": 16090629.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.184660911560059,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004963695775081495,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.18043677061796187,
|
|
"num_tokens": 16105219.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.2330903053283695,
|
|
"epoch": 0.6855270994639666,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004963619495585338,
|
|
"loss": 5.0892,
|
|
"mean_token_accuracy": 0.18218498229980468,
|
|
"num_tokens": 16118851.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.208267068862915,
|
|
"epoch": 0.6861226920786182,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004963543136690247,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.17185743451118468,
|
|
"num_tokens": 16132435.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.215328884124756,
|
|
"epoch": 0.6867182846932698,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004963466698398965,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.17482507675886155,
|
|
"num_tokens": 16145922.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.181134653091431,
|
|
"epoch": 0.6873138773079214,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004963390180714231,
|
|
"loss": 5.1128,
|
|
"mean_token_accuracy": 0.180326247215271,
|
|
"num_tokens": 16158056.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.275094032287598,
|
|
"epoch": 0.687909469922573,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000496331358363879,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.17582519352436066,
|
|
"num_tokens": 16172836.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.3480244159698485,
|
|
"epoch": 0.6885050625372245,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004963236907175388,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.16353725045919418,
|
|
"num_tokens": 16187787.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.182116270065308,
|
|
"epoch": 0.6891006551518761,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004963160151326778,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.1797486037015915,
|
|
"num_tokens": 16201861.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.132825613021851,
|
|
"epoch": 0.6896962477665277,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004963083316095712,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.18159980326890945,
|
|
"num_tokens": 16215447.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.1891406059265135,
|
|
"epoch": 0.6902918403811793,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004963006401484945,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.17977793514728546,
|
|
"num_tokens": 16229127.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.325561952590943,
|
|
"epoch": 0.6908874329958309,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004962929407497236,
|
|
"loss": 5.1509,
|
|
"mean_token_accuracy": 0.17249090522527694,
|
|
"num_tokens": 16242911.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.285350751876831,
|
|
"epoch": 0.6914830256104825,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004962852334135348,
|
|
"loss": 5.1959,
|
|
"mean_token_accuracy": 0.1710536614060402,
|
|
"num_tokens": 16257430.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.140864849090576,
|
|
"epoch": 0.6920786182251341,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004962775181402044,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.18882557153701782,
|
|
"num_tokens": 16270187.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.298103141784668,
|
|
"epoch": 0.6926742108397855,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004962697949300093,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.17519900649785997,
|
|
"num_tokens": 16282750.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.276250267028809,
|
|
"epoch": 0.6932698034544371,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004962620637832263,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.17921461611986161,
|
|
"num_tokens": 16295985.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.245151376724243,
|
|
"epoch": 0.6938653960690887,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004962543247001329,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.1746102273464203,
|
|
"num_tokens": 16308735.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.271404838562011,
|
|
"epoch": 0.6944609886837403,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004962465776810066,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.17137764841318132,
|
|
"num_tokens": 16322722.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.229788160324096,
|
|
"epoch": 0.6950565812983919,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004962388227261253,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.18146976828575134,
|
|
"num_tokens": 16336075.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.265410089492798,
|
|
"epoch": 0.6956521739130435,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004962310598357672,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.17210624665021895,
|
|
"num_tokens": 16351487.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.282583475112915,
|
|
"epoch": 0.696247766527695,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004962232890102106,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.1769305169582367,
|
|
"num_tokens": 16365518.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.196423530578613,
|
|
"epoch": 0.6968433591423466,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004962155102497342,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.17759597599506377,
|
|
"num_tokens": 16379665.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.338124322891235,
|
|
"epoch": 0.6974389517569982,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004962077235546173,
|
|
"loss": 5.236,
|
|
"mean_token_accuracy": 0.17211214154958726,
|
|
"num_tokens": 16394540.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.252950382232666,
|
|
"epoch": 0.6980345443716498,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004961999289251389,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.17966118305921555,
|
|
"num_tokens": 16406628.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.158681917190552,
|
|
"epoch": 0.6986301369863014,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004961921263615788,
|
|
"loss": 5.1075,
|
|
"mean_token_accuracy": 0.18705936819314956,
|
|
"num_tokens": 16417516.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.205069065093994,
|
|
"epoch": 0.699225729600953,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004961843158642167,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.1775630921125412,
|
|
"num_tokens": 16431899.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.257345724105835,
|
|
"epoch": 0.6998213222156046,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004961764974333328,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.17272573858499526,
|
|
"num_tokens": 16444716.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.246624612808228,
|
|
"epoch": 0.7004169148302561,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004961686710692076,
|
|
"loss": 5.0743,
|
|
"mean_token_accuracy": 0.18247440606355667,
|
|
"num_tokens": 16459544.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.261850309371948,
|
|
"epoch": 0.7010125074449077,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004961608367721217,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.1797902300953865,
|
|
"num_tokens": 16472537.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.16389422416687,
|
|
"epoch": 0.7016081000595593,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004961529945423563,
|
|
"loss": 5.1087,
|
|
"mean_token_accuracy": 0.18068212270736694,
|
|
"num_tokens": 16486184.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.19044451713562,
|
|
"epoch": 0.7022036926742108,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004961451443801924,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.17794415950775147,
|
|
"num_tokens": 16499584.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.1667228698730465,
|
|
"epoch": 0.7027992852888624,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004961372862859119,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.1811469167470932,
|
|
"num_tokens": 16512701.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.311200475692749,
|
|
"epoch": 0.703394877903514,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004961294202597962,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.17223948538303374,
|
|
"num_tokens": 16525019.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.304340744018555,
|
|
"epoch": 0.7039904705181655,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004961215463021281,
|
|
"loss": 5.1656,
|
|
"mean_token_accuracy": 0.17983602732419968,
|
|
"num_tokens": 16539335.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.209858226776123,
|
|
"epoch": 0.7045860631328171,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004961136644131894,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.18081254363059998,
|
|
"num_tokens": 16552680.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.143716430664062,
|
|
"epoch": 0.7051816557474687,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004961057745932633,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.18253085166215896,
|
|
"num_tokens": 16565819.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.217004585266113,
|
|
"epoch": 0.7057772483621203,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004960978768426323,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.18213992565870285,
|
|
"num_tokens": 16579280.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.22933259010315,
|
|
"epoch": 0.7063728409767719,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00049608997116158,
|
|
"loss": 5.2734,
|
|
"mean_token_accuracy": 0.1655406653881073,
|
|
"num_tokens": 16594090.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.265399742126465,
|
|
"epoch": 0.7069684335914235,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00049608205755039,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.1752513274550438,
|
|
"num_tokens": 16609287.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.279241037368775,
|
|
"epoch": 0.7075640262060751,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004960741360093459,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.1697498306632042,
|
|
"num_tokens": 16624873.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.20526876449585,
|
|
"epoch": 0.7081596188207266,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004960662065387322,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.18157046884298325,
|
|
"num_tokens": 16637885.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.296694278717041,
|
|
"epoch": 0.7087552114353782,
|
|
"grad_norm": 4.53125,
|
|
"learning_rate": 0.000496058269138833,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.17910298854112625,
|
|
"num_tokens": 16650961.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.296485567092896,
|
|
"epoch": 0.7093508040500298,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004960503238099331,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.17117286920547486,
|
|
"num_tokens": 16665740.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.271303510665893,
|
|
"epoch": 0.7099463966646814,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004960423705523175,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.1742124781012535,
|
|
"num_tokens": 16679143.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.237654161453247,
|
|
"epoch": 0.710541989279333,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004960344093662714,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.1780328020453453,
|
|
"num_tokens": 16692460.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.247082376480103,
|
|
"epoch": 0.7111375818939845,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004960264402520804,
|
|
"loss": 5.1424,
|
|
"mean_token_accuracy": 0.1801220029592514,
|
|
"num_tokens": 16707037.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.25597243309021,
|
|
"epoch": 0.711733174508636,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004960184632100304,
|
|
"loss": 5.0991,
|
|
"mean_token_accuracy": 0.18343783020973206,
|
|
"num_tokens": 16719857.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.214465761184693,
|
|
"epoch": 0.7123287671232876,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004960104782404075,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.17904621362686157,
|
|
"num_tokens": 16732221.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.269077777862549,
|
|
"epoch": 0.7129243597379392,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004960024853434982,
|
|
"loss": 5.2074,
|
|
"mean_token_accuracy": 0.17510833740234374,
|
|
"num_tokens": 16747384.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.237616300582886,
|
|
"epoch": 0.7135199523525908,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000495994484519589,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.1762905716896057,
|
|
"num_tokens": 16761269.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.217718315124512,
|
|
"epoch": 0.7141155449672424,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004959864757689669,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.18566448092460633,
|
|
"num_tokens": 16775403.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.271542882919311,
|
|
"epoch": 0.714711137581894,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004959784590919192,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.17921701669692994,
|
|
"num_tokens": 16790740.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.714711137581894,
|
|
"eval_entropy": 5.0943578341911575,
|
|
"eval_loss": 5.136335372924805,
|
|
"eval_mean_token_accuracy": 0.18697582095989893,
|
|
"eval_num_tokens": 16790740.0,
|
|
"eval_runtime": 24.1814,
|
|
"eval_samples_per_second": 1055.065,
|
|
"eval_steps_per_second": 131.919,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.262171649932862,
|
|
"epoch": 0.7153067301965456,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004959704344887335,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.17520833015441895,
|
|
"num_tokens": 16805005.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.2468914031982425,
|
|
"epoch": 0.7159023228111971,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004959624019596976,
|
|
"loss": 5.1705,
|
|
"mean_token_accuracy": 0.17943359464406966,
|
|
"num_tokens": 16818227.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.229400968551635,
|
|
"epoch": 0.7164979154258487,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004959543615050996,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.18386687338352203,
|
|
"num_tokens": 16831113.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.21410608291626,
|
|
"epoch": 0.7170935080405003,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004959463131252278,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.17656571567058563,
|
|
"num_tokens": 16844952.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.32748851776123,
|
|
"epoch": 0.7176891006551519,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004959382568203711,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.17945383191108705,
|
|
"num_tokens": 16858360.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.217812252044678,
|
|
"epoch": 0.7182846932698035,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004959301925908184,
|
|
"loss": 5.071,
|
|
"mean_token_accuracy": 0.18626186102628708,
|
|
"num_tokens": 16869172.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.14674596786499,
|
|
"epoch": 0.7188802858844551,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004959221204368588,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.17655732482671738,
|
|
"num_tokens": 16884322.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.313143062591553,
|
|
"epoch": 0.7194758784991067,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004959140403587819,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.18400016725063323,
|
|
"num_tokens": 16896686.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.247745418548584,
|
|
"epoch": 0.7200714711137582,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004959059523568778,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.18097992688417436,
|
|
"num_tokens": 16912819.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.257614326477051,
|
|
"epoch": 0.7206670637284097,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004958978564314361,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.17423434406518937,
|
|
"num_tokens": 16926615.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.213832521438599,
|
|
"epoch": 0.7212626563430613,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004958897525827476,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.18125573694705963,
|
|
"num_tokens": 16940934.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.191055250167847,
|
|
"epoch": 0.7218582489577129,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004958816408111027,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.19383281022310256,
|
|
"num_tokens": 16953016.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.1797624111175535,
|
|
"epoch": 0.7224538415723645,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004958735211167926,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.18215177357196807,
|
|
"num_tokens": 16964460.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.228898334503174,
|
|
"epoch": 0.7230494341870161,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004958653935001083,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.1707054227590561,
|
|
"num_tokens": 16978307.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.2650548934936525,
|
|
"epoch": 0.7236450268016676,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004958572579613415,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.1797358825802803,
|
|
"num_tokens": 16992240.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.142966175079346,
|
|
"epoch": 0.7242406194163192,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000495849114500784,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.1886210635304451,
|
|
"num_tokens": 17004865.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.215324354171753,
|
|
"epoch": 0.7248362120309708,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004958409631187278,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.19094699919223784,
|
|
"num_tokens": 17018377.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.163234567642212,
|
|
"epoch": 0.7254318046456224,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004958328038154652,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.18635840564966202,
|
|
"num_tokens": 17032487.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.237206363677979,
|
|
"epoch": 0.726027397260274,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004958246365912891,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.1796349659562111,
|
|
"num_tokens": 17045783.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.381899642944336,
|
|
"epoch": 0.7266229898749256,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004958164614464923,
|
|
"loss": 5.2884,
|
|
"mean_token_accuracy": 0.16914476603269576,
|
|
"num_tokens": 17060359.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.2594358921051025,
|
|
"epoch": 0.7272185824895772,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000495808278381368,
|
|
"loss": 5.136,
|
|
"mean_token_accuracy": 0.1786664456129074,
|
|
"num_tokens": 17074510.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.17710542678833,
|
|
"epoch": 0.7278141751042287,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004958000873962099,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.17839185744524003,
|
|
"num_tokens": 17088551.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.301362323760986,
|
|
"epoch": 0.7284097677188803,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004957918884913115,
|
|
"loss": 5.26,
|
|
"mean_token_accuracy": 0.16442033797502517,
|
|
"num_tokens": 17102674.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.349546432495117,
|
|
"epoch": 0.7290053603335319,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004957836816669672,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.17182278484106064,
|
|
"num_tokens": 17116891.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.2675577163696286,
|
|
"epoch": 0.7296009529481834,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004957754669234711,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.18273969739675522,
|
|
"num_tokens": 17129003.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.153927755355835,
|
|
"epoch": 0.730196545562835,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000495767244261118,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.1883746027946472,
|
|
"num_tokens": 17142225.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.212651062011719,
|
|
"epoch": 0.7307921381774866,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004957590136802028,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.18223844915628434,
|
|
"num_tokens": 17154849.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.21303358078003,
|
|
"epoch": 0.7313877307921381,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004957507751810207,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.17863920331001282,
|
|
"num_tokens": 17170335.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.240776395797729,
|
|
"epoch": 0.7319833234067897,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004957425287638673,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.16922955960035324,
|
|
"num_tokens": 17185181.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.436229801177978,
|
|
"epoch": 0.7325789160214413,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004957342744290381,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.1738339841365814,
|
|
"num_tokens": 17198960.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.314759159088135,
|
|
"epoch": 0.7331745086360929,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004957260121768296,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.17716477662324906,
|
|
"num_tokens": 17212233.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.150838184356689,
|
|
"epoch": 0.7337701012507445,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004957177420075377,
|
|
"loss": 5.0395,
|
|
"mean_token_accuracy": 0.18400600254535676,
|
|
"num_tokens": 17224012.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.1978003025054935,
|
|
"epoch": 0.7343656938653961,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004957094639214594,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.16954431384801866,
|
|
"num_tokens": 17236943.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.321937084197998,
|
|
"epoch": 0.7349612864800477,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004957011779188915,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.17298595756292343,
|
|
"num_tokens": 17249835.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.280431127548217,
|
|
"epoch": 0.7355568790946992,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004956928840001312,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.1724871501326561,
|
|
"num_tokens": 17263260.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.368339109420776,
|
|
"epoch": 0.7361524717093508,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004956845821654758,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.17789730578660964,
|
|
"num_tokens": 17277309.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.273785734176636,
|
|
"epoch": 0.7367480643240024,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004956762724152234,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.1779945582151413,
|
|
"num_tokens": 17291354.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.171925783157349,
|
|
"epoch": 0.737343656938654,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004956679547496719,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.17972863763570784,
|
|
"num_tokens": 17305805.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.203984546661377,
|
|
"epoch": 0.7379392495533056,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004956596291691197,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.17681454569101335,
|
|
"num_tokens": 17319031.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.242416858673096,
|
|
"epoch": 0.7385348421679571,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004956512956738652,
|
|
"loss": 5.201,
|
|
"mean_token_accuracy": 0.18119876831769943,
|
|
"num_tokens": 17332455.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.2511293411254885,
|
|
"epoch": 0.7391304347826086,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004956429542642075,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.1771877259016037,
|
|
"num_tokens": 17346849.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.249085235595703,
|
|
"epoch": 0.7397260273972602,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004956346049404459,
|
|
"loss": 5.2033,
|
|
"mean_token_accuracy": 0.1824793353676796,
|
|
"num_tokens": 17360204.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.303784132003784,
|
|
"epoch": 0.7403216200119118,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004956262477028797,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.17812341451644897,
|
|
"num_tokens": 17373430.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.277988576889038,
|
|
"epoch": 0.7409172126265634,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004956178825518087,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.18806812167167664,
|
|
"num_tokens": 17386856.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.156893014907837,
|
|
"epoch": 0.741512805241215,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004956095094875329,
|
|
"loss": 5.1246,
|
|
"mean_token_accuracy": 0.17744432687759398,
|
|
"num_tokens": 17401657.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.225132846832276,
|
|
"epoch": 0.7421083978558666,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004956011285103528,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.17655558586120607,
|
|
"num_tokens": 17415688.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.2593669414520265,
|
|
"epoch": 0.7427039904705182,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004955927396205689,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.17734746187925338,
|
|
"num_tokens": 17428272.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.205744934082031,
|
|
"epoch": 0.7432995830851697,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000495584342818482,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.17989810109138488,
|
|
"num_tokens": 17440858.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.27973313331604,
|
|
"epoch": 0.7438951756998213,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004955759381043934,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.17858007699251174,
|
|
"num_tokens": 17453946.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.276264333724976,
|
|
"epoch": 0.7444907683144729,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004955675254786045,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.1738366886973381,
|
|
"num_tokens": 17470565.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.251806640625,
|
|
"epoch": 0.7450863609291245,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004955591049414171,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.18005384206771852,
|
|
"num_tokens": 17484604.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.3440694332122805,
|
|
"epoch": 0.7456819535437761,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004955506764931332,
|
|
"loss": 5.214,
|
|
"mean_token_accuracy": 0.1704939216375351,
|
|
"num_tokens": 17500578.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.268947982788086,
|
|
"epoch": 0.7462775461584277,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004955422401340553,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.17151904255151748,
|
|
"num_tokens": 17516999.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.20690951347351,
|
|
"epoch": 0.7468731387730793,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004955337958644857,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.18017496466636657,
|
|
"num_tokens": 17530943.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.167717313766479,
|
|
"epoch": 0.7474687313877308,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004955253436847273,
|
|
"loss": 5.0154,
|
|
"mean_token_accuracy": 0.18924202471971513,
|
|
"num_tokens": 17543698.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.138778877258301,
|
|
"epoch": 0.7480643240023823,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004955168835950835,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.19163981080055237,
|
|
"num_tokens": 17556141.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.211375379562378,
|
|
"epoch": 0.7486599166170339,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004955084155958576,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.18967200070619583,
|
|
"num_tokens": 17569186.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.27057032585144,
|
|
"epoch": 0.7492555092316855,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004954999396873534,
|
|
"loss": 5.1692,
|
|
"mean_token_accuracy": 0.17317333519458772,
|
|
"num_tokens": 17583826.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.272788333892822,
|
|
"epoch": 0.7498511018463371,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004954914558698748,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.18047518879175187,
|
|
"num_tokens": 17597196.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.330962514877319,
|
|
"epoch": 0.7504466944609887,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004954829641437261,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.1723018392920494,
|
|
"num_tokens": 17611283.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.263182973861694,
|
|
"epoch": 0.7510422870756402,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004954744645092121,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.18135177940130234,
|
|
"num_tokens": 17626089.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.292476987838745,
|
|
"epoch": 0.7516378796902918,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004954659569666375,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.1786133110523224,
|
|
"num_tokens": 17639915.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.314774227142334,
|
|
"epoch": 0.7522334723049434,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004954574415163075,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.1769965559244156,
|
|
"num_tokens": 17654563.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.23230471611023,
|
|
"epoch": 0.752829064919595,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004954489181585275,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.1825282484292984,
|
|
"num_tokens": 17669132.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.171199083328247,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004954403868936032,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.17713045328855515,
|
|
"num_tokens": 17682794.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.218078374862671,
|
|
"epoch": 0.7540202501488982,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004954318477218406,
|
|
"loss": 5.1426,
|
|
"mean_token_accuracy": 0.173923522233963,
|
|
"num_tokens": 17697325.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.274148988723755,
|
|
"epoch": 0.7546158427635498,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000495423300643546,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.17143461853265762,
|
|
"num_tokens": 17710136.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.22655553817749,
|
|
"epoch": 0.7552114353782013,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004954147456590262,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.18159240931272508,
|
|
"num_tokens": 17723138.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.189457368850708,
|
|
"epoch": 0.7558070279928529,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004954061827685877,
|
|
"loss": 5.097,
|
|
"mean_token_accuracy": 0.183753402531147,
|
|
"num_tokens": 17735059.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.2097944736480715,
|
|
"epoch": 0.7564026206075045,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004953976119725378,
|
|
"loss": 5.1391,
|
|
"mean_token_accuracy": 0.17683360874652862,
|
|
"num_tokens": 17750361.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.172784042358399,
|
|
"epoch": 0.756998213222156,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004953890332711839,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.17386312186717987,
|
|
"num_tokens": 17766597.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.332663202285767,
|
|
"epoch": 0.7575938058368076,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004953804466648337,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.17079635113477706,
|
|
"num_tokens": 17780086.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.2260607242584225,
|
|
"epoch": 0.7581893984514592,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004953718521537952,
|
|
"loss": 5.0821,
|
|
"mean_token_accuracy": 0.18949958086013793,
|
|
"num_tokens": 17793316.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.2503448009490965,
|
|
"epoch": 0.7587849910661107,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004953632497383766,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.17113634198904037,
|
|
"num_tokens": 17807766.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.215949010848999,
|
|
"epoch": 0.7593805836807623,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004953546394188867,
|
|
"loss": 5.1058,
|
|
"mean_token_accuracy": 0.18321122825145722,
|
|
"num_tokens": 17819778.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.265564775466919,
|
|
"epoch": 0.7599761762954139,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.000495346021195634,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.1787905290722847,
|
|
"num_tokens": 17835432.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.219515037536621,
|
|
"epoch": 0.7605717689100655,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004953373950689279,
|
|
"loss": 5.1355,
|
|
"mean_token_accuracy": 0.18652450144290925,
|
|
"num_tokens": 17848861.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.277059173583984,
|
|
"epoch": 0.7611673615247171,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004953287610390775,
|
|
"loss": 5.1324,
|
|
"mean_token_accuracy": 0.18211468905210496,
|
|
"num_tokens": 17863173.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.199348258972168,
|
|
"epoch": 0.7617629541393687,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004953201191063928,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.18027573823928833,
|
|
"num_tokens": 17876497.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.209763765335083,
|
|
"epoch": 0.7623585467540203,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004953114692711837,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.18778831362724305,
|
|
"num_tokens": 17890582.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.204202651977539,
|
|
"epoch": 0.7629541393686718,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004953028115337603,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.17545359432697297,
|
|
"num_tokens": 17905476.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.222776460647583,
|
|
"epoch": 0.7635497319833234,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004952941458944333,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.17692117542028427,
|
|
"num_tokens": 17918571.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.273083829879761,
|
|
"epoch": 0.764145324597975,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004952854723535134,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.17590197175741196,
|
|
"num_tokens": 17932169.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.2182084083557125,
|
|
"epoch": 0.7647409172126266,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004952767909113118,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.19220718294382094,
|
|
"num_tokens": 17944772.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.202535247802734,
|
|
"epoch": 0.7653365098272782,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004952681015681398,
|
|
"loss": 5.0967,
|
|
"mean_token_accuracy": 0.1827477589249611,
|
|
"num_tokens": 17957903.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.233345794677734,
|
|
"epoch": 0.7659321024419298,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004952594043243092,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.17379918694496155,
|
|
"num_tokens": 17972214.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.2010167121887205,
|
|
"epoch": 0.7665276950565812,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004952506991801319,
|
|
"loss": 5.077,
|
|
"mean_token_accuracy": 0.18618561774492265,
|
|
"num_tokens": 17986722.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.259037446975708,
|
|
"epoch": 0.7671232876712328,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004952419861359201,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.18312462270259858,
|
|
"num_tokens": 17999392.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.248780298233032,
|
|
"epoch": 0.7677188802858844,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004952332651919864,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.17645585387945176,
|
|
"num_tokens": 18013560.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.4116010665893555,
|
|
"epoch": 0.768314472900536,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004952245363486435,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.17604258060455322,
|
|
"num_tokens": 18027631.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.224458646774292,
|
|
"epoch": 0.7689100655151876,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004952157996062046,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.1868421196937561,
|
|
"num_tokens": 18041618.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.233840608596802,
|
|
"epoch": 0.7695056581298392,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000495207054964983,
|
|
"loss": 5.128,
|
|
"mean_token_accuracy": 0.18091214895248414,
|
|
"num_tokens": 18053783.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.272752285003662,
|
|
"epoch": 0.7701012507444908,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004951983024252924,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.17165665030479432,
|
|
"num_tokens": 18067471.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.255411672592163,
|
|
"epoch": 0.7706968433591423,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004951895419874466,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.18178182244300842,
|
|
"num_tokens": 18081173.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.292251539230347,
|
|
"epoch": 0.7712924359737939,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00049518077365176,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.16596365571022034,
|
|
"num_tokens": 18094237.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.231148624420166,
|
|
"epoch": 0.7718880285884455,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000495171997418547,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.1815025880932808,
|
|
"num_tokens": 18109184.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.1793781280517575,
|
|
"epoch": 0.7724836212030971,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004951632132881225,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.17878124862909317,
|
|
"num_tokens": 18122801.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.2789201736450195,
|
|
"epoch": 0.7730792138177487,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004951544212608015,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.1808562234044075,
|
|
"num_tokens": 18135807.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.257011747360229,
|
|
"epoch": 0.7736748064324003,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004951456213368994,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.17655223309993745,
|
|
"num_tokens": 18149093.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.323028469085694,
|
|
"epoch": 0.7742703990470519,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004951368135167316,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.16839107871055603,
|
|
"num_tokens": 18162878.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.242344999313355,
|
|
"epoch": 0.7748659916617034,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004951279978006143,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.17694514989852905,
|
|
"num_tokens": 18176443.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.216059160232544,
|
|
"epoch": 0.7754615842763549,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004951191741888638,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.17514225095510483,
|
|
"num_tokens": 18194684.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.200347471237182,
|
|
"epoch": 0.7760571768910065,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004951103426817961,
|
|
"loss": 5.0186,
|
|
"mean_token_accuracy": 0.18769593983888627,
|
|
"num_tokens": 18207667.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.185047721862793,
|
|
"epoch": 0.7766527695056581,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004951015032797286,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.1823843613266945,
|
|
"num_tokens": 18220594.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.135990047454834,
|
|
"epoch": 0.7772483621203097,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004950926559829778,
|
|
"loss": 5.1007,
|
|
"mean_token_accuracy": 0.18168915659189225,
|
|
"num_tokens": 18235193.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.258762836456299,
|
|
"epoch": 0.7778439547349613,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004950838007918615,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.18424176275730134,
|
|
"num_tokens": 18246647.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.144938707351685,
|
|
"epoch": 0.7784395473496128,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000495074937706697,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.1815197229385376,
|
|
"num_tokens": 18260255.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.208507871627807,
|
|
"epoch": 0.7790351399642644,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004950660667278023,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.18078023791313172,
|
|
"num_tokens": 18274505.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.2928688526153564,
|
|
"epoch": 0.779630732578916,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004950571878554956,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.18525624573230742,
|
|
"num_tokens": 18288386.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.259256315231323,
|
|
"epoch": 0.7802263251935676,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004950483010900953,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.17895604372024537,
|
|
"num_tokens": 18303602.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.1657233238220215,
|
|
"epoch": 0.7808219178082192,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004950394064319203,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.1806628957390785,
|
|
"num_tokens": 18318561.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.201634359359741,
|
|
"epoch": 0.7814175104228708,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004950305038812895,
|
|
"loss": 5.0484,
|
|
"mean_token_accuracy": 0.18409526199102402,
|
|
"num_tokens": 18331903.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.1610852718353275,
|
|
"epoch": 0.7820131030375224,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004950215934385223,
|
|
"loss": 5.0702,
|
|
"mean_token_accuracy": 0.1873168632388115,
|
|
"num_tokens": 18344958.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.270832538604736,
|
|
"epoch": 0.782608695652174,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004950126751039382,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.17428603172302246,
|
|
"num_tokens": 18359343.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.256022691726685,
|
|
"epoch": 0.7832042882668255,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004950037488778572,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.17548177093267442,
|
|
"num_tokens": 18372672.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.287987136840821,
|
|
"epoch": 0.7837998808814771,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004949948147605996,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.18061645627021788,
|
|
"num_tokens": 18385013.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.274853324890136,
|
|
"epoch": 0.7843954734961287,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004949858727524855,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.175605009496212,
|
|
"num_tokens": 18398411.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.234839248657226,
|
|
"epoch": 0.7849910661107802,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004949769228538359,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.17787238359451293,
|
|
"num_tokens": 18411317.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.306866550445557,
|
|
"epoch": 0.7855866587254318,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004949679650649717,
|
|
"loss": 5.2235,
|
|
"mean_token_accuracy": 0.1695517584681511,
|
|
"num_tokens": 18426503.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.1873842716217045,
|
|
"epoch": 0.7861822513400833,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004949589993862143,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.188169227540493,
|
|
"num_tokens": 18439465.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.194348478317261,
|
|
"epoch": 0.7867778439547349,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004949500258178851,
|
|
"loss": 5.066,
|
|
"mean_token_accuracy": 0.18075745552778244,
|
|
"num_tokens": 18452539.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.238447093963623,
|
|
"epoch": 0.7873734365693865,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004949410443603062,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.1833100974559784,
|
|
"num_tokens": 18466040.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.265850687026978,
|
|
"epoch": 0.7879690291840381,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004949320550137996,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.17576845586299897,
|
|
"num_tokens": 18478621.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.232444477081299,
|
|
"epoch": 0.7885646217986897,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004949230577786877,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.18300653994083405,
|
|
"num_tokens": 18492000.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.142419242858887,
|
|
"epoch": 0.7891602144133413,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004949140526552934,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.1889595940709114,
|
|
"num_tokens": 18506459.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.14818115234375,
|
|
"epoch": 0.7897558070279929,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004949050396439395,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.19013550132513046,
|
|
"num_tokens": 18518325.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.141176700592041,
|
|
"epoch": 0.7903513996426444,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004948960187449495,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.19180200546979903,
|
|
"num_tokens": 18533329.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.235082530975342,
|
|
"epoch": 0.790946992257296,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004948869899586467,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.18970775306224824,
|
|
"num_tokens": 18544635.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.182636165618897,
|
|
"epoch": 0.7915425848719476,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004948779532853552,
|
|
"loss": 5.1289,
|
|
"mean_token_accuracy": 0.19305191487073897,
|
|
"num_tokens": 18558576.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.266385126113891,
|
|
"epoch": 0.7921381774865992,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004948689087253989,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.17846463173627852,
|
|
"num_tokens": 18573393.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.188985013961792,
|
|
"epoch": 0.7927337701012508,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004948598562791025,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.1907246932387352,
|
|
"num_tokens": 18586273.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.284608840942383,
|
|
"epoch": 0.7933293627159024,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004948507959467905,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.1715007483959198,
|
|
"num_tokens": 18600040.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.171895599365234,
|
|
"epoch": 0.7939249553305538,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004948417277287877,
|
|
"loss": 5.0083,
|
|
"mean_token_accuracy": 0.18789801448583604,
|
|
"num_tokens": 18613723.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.195236778259277,
|
|
"epoch": 0.7945205479452054,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004948326516254197,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.18130462169647216,
|
|
"num_tokens": 18628575.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.257724809646606,
|
|
"epoch": 0.795116140559857,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000494823567637012,
|
|
"loss": 5.1784,
|
|
"mean_token_accuracy": 0.17398256659507752,
|
|
"num_tokens": 18642179.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.204999160766602,
|
|
"epoch": 0.7957117331745086,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004948144757638902,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.1775403469800949,
|
|
"num_tokens": 18655450.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.195954656600952,
|
|
"epoch": 0.7963073257891602,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004948053760063806,
|
|
"loss": 5.1181,
|
|
"mean_token_accuracy": 0.187526199221611,
|
|
"num_tokens": 18668434.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.226202821731567,
|
|
"epoch": 0.7969029184038118,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004947962683648095,
|
|
"loss": 5.1165,
|
|
"mean_token_accuracy": 0.17872676998376846,
|
|
"num_tokens": 18683674.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.275168991088867,
|
|
"epoch": 0.7974985110184634,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004947871528395038,
|
|
"loss": 5.0944,
|
|
"mean_token_accuracy": 0.1826059028506279,
|
|
"num_tokens": 18697323.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.214400148391723,
|
|
"epoch": 0.798094103633115,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00049477802943079,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.1783431887626648,
|
|
"num_tokens": 18711110.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.202420425415039,
|
|
"epoch": 0.7986896962477665,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004947688981389958,
|
|
"loss": 5.1999,
|
|
"mean_token_accuracy": 0.1747357428073883,
|
|
"num_tokens": 18725753.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.202334928512573,
|
|
"epoch": 0.7992852888624181,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004947597589644484,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.18280501663684845,
|
|
"num_tokens": 18740363.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.187631130218506,
|
|
"epoch": 0.7998808814770697,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004947506119074759,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.18084446638822554,
|
|
"num_tokens": 18755157.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.179488754272461,
|
|
"epoch": 0.8004764740917213,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004947414569684062,
|
|
"loss": 5.1071,
|
|
"mean_token_accuracy": 0.1839499890804291,
|
|
"num_tokens": 18769828.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.213893890380859,
|
|
"epoch": 0.8010720667063729,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004947322941475677,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.18282704800367355,
|
|
"num_tokens": 18785810.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.305316829681397,
|
|
"epoch": 0.8016676593210245,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004947231234452891,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.16901029646396637,
|
|
"num_tokens": 18801730.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.2317132472991945,
|
|
"epoch": 0.802263251935676,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004947139448618994,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.18172652423381805,
|
|
"num_tokens": 18816684.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.1992124080657955,
|
|
"epoch": 0.8028588445503275,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004947047583977276,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.17296577095985413,
|
|
"num_tokens": 18832487.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.142750072479248,
|
|
"epoch": 0.8034544371649791,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004946955640531033,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.18837968111038209,
|
|
"num_tokens": 18845136.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.190511226654053,
|
|
"epoch": 0.8040500297796307,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004946863618283565,
|
|
"loss": 5.086,
|
|
"mean_token_accuracy": 0.1804311379790306,
|
|
"num_tokens": 18859082.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.266516065597534,
|
|
"epoch": 0.8046456223942823,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004946771517238169,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.18061110973358155,
|
|
"num_tokens": 18872957.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.242583227157593,
|
|
"epoch": 0.8052412150089339,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004946679337398151,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.18060423731803893,
|
|
"num_tokens": 18887189.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.228593873977661,
|
|
"epoch": 0.8058368076235854,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004946587078766818,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.1817886248230934,
|
|
"num_tokens": 18900325.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.203487205505371,
|
|
"epoch": 0.806432400238237,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004946494741347476,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.18260599821805953,
|
|
"num_tokens": 18914583.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.235302972793579,
|
|
"epoch": 0.8070279928528886,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004946402325143439,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.1761715218424797,
|
|
"num_tokens": 18928796.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.235739088058471,
|
|
"epoch": 0.8076235854675402,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004946309830158024,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.17933788448572158,
|
|
"num_tokens": 18942976.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.167638635635376,
|
|
"epoch": 0.8082191780821918,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004946217256394544,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.18620040714740754,
|
|
"num_tokens": 18955384.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.277500820159912,
|
|
"epoch": 0.8088147706968434,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004946124603856322,
|
|
"loss": 5.1602,
|
|
"mean_token_accuracy": 0.17369710952043532,
|
|
"num_tokens": 18969149.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.18670883178711,
|
|
"epoch": 0.809410363311495,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004946031872546683,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.18069493472576142,
|
|
"num_tokens": 18982216.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.2391510009765625,
|
|
"epoch": 0.8100059559261465,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000494593906246895,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.17458948791027068,
|
|
"num_tokens": 18998075.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.134884881973266,
|
|
"epoch": 0.8106015485407981,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004945846173626453,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.18899261802434922,
|
|
"num_tokens": 19011088.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.184320449829102,
|
|
"epoch": 0.8111971411554497,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004945753206022525,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.1795993059873581,
|
|
"num_tokens": 19025864.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.195252132415772,
|
|
"epoch": 0.8117927337701013,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004945660159660499,
|
|
"loss": 5.0688,
|
|
"mean_token_accuracy": 0.17785895019769668,
|
|
"num_tokens": 19039803.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.089031171798706,
|
|
"epoch": 0.8123883263847528,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004945567034543712,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.19303781688213348,
|
|
"num_tokens": 19053784.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.206723260879516,
|
|
"epoch": 0.8129839189994044,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004945473830675507,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.18023905158042908,
|
|
"num_tokens": 19068730.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.286882209777832,
|
|
"epoch": 0.813579511614056,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004945380548059224,
|
|
"loss": 5.2181,
|
|
"mean_token_accuracy": 0.17993007600307465,
|
|
"num_tokens": 19082354.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.297438430786133,
|
|
"epoch": 0.8141751042287075,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004945287186698211,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.17740806192159653,
|
|
"num_tokens": 19095051.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.254546403884888,
|
|
"epoch": 0.8147706968433591,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004945193746595815,
|
|
"loss": 5.1367,
|
|
"mean_token_accuracy": 0.1798209398984909,
|
|
"num_tokens": 19110653.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.171179962158203,
|
|
"epoch": 0.8153662894580107,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004945100227755389,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.17451908439397812,
|
|
"num_tokens": 19125112.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.3125895977020265,
|
|
"epoch": 0.8159618820726623,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004945006630180288,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.17127869427204132,
|
|
"num_tokens": 19140153.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.263261938095093,
|
|
"epoch": 0.8165574746873139,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004944912953873865,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.18081953823566438,
|
|
"num_tokens": 19154423.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.208758306503296,
|
|
"epoch": 0.8171530673019655,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004944819198839486,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.18131930828094484,
|
|
"num_tokens": 19169909.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.225088167190552,
|
|
"epoch": 0.817748659916617,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000494472536508051,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.18382230252027512,
|
|
"num_tokens": 19184068.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.208056879043579,
|
|
"epoch": 0.8183442525312686,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004944631452600303,
|
|
"loss": 5.1381,
|
|
"mean_token_accuracy": 0.1795888751745224,
|
|
"num_tokens": 19199281.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.264560031890869,
|
|
"epoch": 0.8189398451459202,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004944537461402234,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.1719518005847931,
|
|
"num_tokens": 19213893.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.229583787918091,
|
|
"epoch": 0.8195354377605718,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004944443391489676,
|
|
"loss": 5.2088,
|
|
"mean_token_accuracy": 0.17298655211925507,
|
|
"num_tokens": 19227873.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.250295114517212,
|
|
"epoch": 0.8201310303752234,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004944349242865999,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.18695535361766816,
|
|
"num_tokens": 19241287.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.271874237060547,
|
|
"epoch": 0.820726622989875,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004944255015534585,
|
|
"loss": 5.0966,
|
|
"mean_token_accuracy": 0.18217684030532838,
|
|
"num_tokens": 19255428.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.160023260116577,
|
|
"epoch": 0.8213222156045265,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000494416070949881,
|
|
"loss": 5.0729,
|
|
"mean_token_accuracy": 0.18300410658121108,
|
|
"num_tokens": 19268234.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.289574432373047,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004944066324762058,
|
|
"loss": 5.0876,
|
|
"mean_token_accuracy": 0.18349677324295044,
|
|
"num_tokens": 19281443.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.217981052398682,
|
|
"epoch": 0.8225134008338296,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004943971861327713,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.18581587672233582,
|
|
"num_tokens": 19293791.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.131737279891968,
|
|
"epoch": 0.8231089934484812,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004943877319199167,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.18827794641256332,
|
|
"num_tokens": 19305634.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.229514932632446,
|
|
"epoch": 0.8237045860631328,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004943782698379807,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.17456303536891937,
|
|
"num_tokens": 19319719.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.19350004196167,
|
|
"epoch": 0.8243001786777844,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004943687998873029,
|
|
"loss": 4.9246,
|
|
"mean_token_accuracy": 0.1979609787464142,
|
|
"num_tokens": 19333596.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.141911029815674,
|
|
"epoch": 0.824895771292436,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004943593220682229,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.18359212428331376,
|
|
"num_tokens": 19347750.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.151154804229736,
|
|
"epoch": 0.8254913639070875,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004943498363810807,
|
|
"loss": 5.0673,
|
|
"mean_token_accuracy": 0.19199034571647644,
|
|
"num_tokens": 19360584.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.205457448959351,
|
|
"epoch": 0.8260869565217391,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004943403428262164,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.18870752155780793,
|
|
"num_tokens": 19375113.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.182704925537109,
|
|
"epoch": 0.8266825491363907,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004943308414039708,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.1809633582830429,
|
|
"num_tokens": 19387748.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.280330657958984,
|
|
"epoch": 0.8272781417510423,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004943213321146843,
|
|
"loss": 5.1044,
|
|
"mean_token_accuracy": 0.17473697066307067,
|
|
"num_tokens": 19404374.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.2320784568786625,
|
|
"epoch": 0.8278737343656939,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004943118149586984,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.1858845368027687,
|
|
"num_tokens": 19419209.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.149306058883667,
|
|
"epoch": 0.8284693269803455,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004943022899363542,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.17767641991376876,
|
|
"num_tokens": 19433127.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.236229610443115,
|
|
"epoch": 0.8290649195949971,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004942927570479934,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.17997422218322753,
|
|
"num_tokens": 19447718.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.211940002441406,
|
|
"epoch": 0.8296605122096486,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004942832162939581,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.18703040182590486,
|
|
"num_tokens": 19459193.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.115537548065186,
|
|
"epoch": 0.8302561048243002,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004942736676745902,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.17990631908178328,
|
|
"num_tokens": 19472791.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.291986989974975,
|
|
"epoch": 0.8308516974389517,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004942641111902324,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.1823587417602539,
|
|
"num_tokens": 19484903.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.202627468109131,
|
|
"epoch": 0.8314472900536033,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004942545468412275,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.17919373661279678,
|
|
"num_tokens": 19499833.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.142165231704712,
|
|
"epoch": 0.8320428826682549,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004942449746279184,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.19038299918174745,
|
|
"num_tokens": 19511744.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.1782478332519535,
|
|
"epoch": 0.8326384752829065,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004942353945506485,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.19353238195180894,
|
|
"num_tokens": 19525192.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.123580360412598,
|
|
"epoch": 0.833234067897558,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004942258066097617,
|
|
"loss": 5.016,
|
|
"mean_token_accuracy": 0.18150029182434083,
|
|
"num_tokens": 19539397.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.173374843597412,
|
|
"epoch": 0.8338296605122096,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004942162108056015,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.19369393736124038,
|
|
"num_tokens": 19554322.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.303508663177491,
|
|
"epoch": 0.8344252531268612,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004942066071385122,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.1706014797091484,
|
|
"num_tokens": 19567652.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.239338827133179,
|
|
"epoch": 0.8350208457415128,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004941969956088383,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.17405661046504975,
|
|
"num_tokens": 19582921.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.238234186172486,
|
|
"epoch": 0.8356164383561644,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004941873762169246,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.1805899277329445,
|
|
"num_tokens": 19597298.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.259975624084473,
|
|
"epoch": 0.836212030970816,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004941777489631161,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.17605861872434617,
|
|
"num_tokens": 19611200.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.209328460693359,
|
|
"epoch": 0.8368076235854676,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004941681138477582,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.19109131544828414,
|
|
"num_tokens": 19623910.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.156640958786011,
|
|
"epoch": 0.8374032162001191,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004941584708711962,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.1906242474913597,
|
|
"num_tokens": 19638308.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.1406105041503904,
|
|
"epoch": 0.8379988088147707,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004941488200337763,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.17900160998106002,
|
|
"num_tokens": 19652987.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.219503593444824,
|
|
"epoch": 0.8385944014294223,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004941391613358444,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.18006860464811325,
|
|
"num_tokens": 19667789.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.281614494323731,
|
|
"epoch": 0.8391899940440739,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004941294947777473,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.17228772938251496,
|
|
"num_tokens": 19682775.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.2238208770751955,
|
|
"epoch": 0.8397855866587254,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004941198203598314,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.18416610211133957,
|
|
"num_tokens": 19696714.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.130797100067139,
|
|
"epoch": 0.840381179273377,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004941101380824438,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.17936749905347824,
|
|
"num_tokens": 19711132.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.135294818878174,
|
|
"epoch": 0.8409767718880286,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004941004479459318,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.18914208561182022,
|
|
"num_tokens": 19726680.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.223226737976074,
|
|
"epoch": 0.8415723645026801,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000494090749950643,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.17710803002119063,
|
|
"num_tokens": 19740152.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.2102679252624515,
|
|
"epoch": 0.8421679571173317,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004940810440969253,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.17095423936843873,
|
|
"num_tokens": 19756233.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.196094560623169,
|
|
"epoch": 0.8427635497319833,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004940713303851265,
|
|
"loss": 5.0286,
|
|
"mean_token_accuracy": 0.1855952888727188,
|
|
"num_tokens": 19771178.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.285997581481934,
|
|
"epoch": 0.8433591423466349,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004940616088155954,
|
|
"loss": 5.1514,
|
|
"mean_token_accuracy": 0.17885922342538835,
|
|
"num_tokens": 19786180.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.1132392406463625,
|
|
"epoch": 0.8439547349612865,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004940518793886807,
|
|
"loss": 5.0036,
|
|
"mean_token_accuracy": 0.1877557411789894,
|
|
"num_tokens": 19800472.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.184009265899658,
|
|
"epoch": 0.8445503275759381,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004940421421047311,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.1912670388817787,
|
|
"num_tokens": 19816060.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.257329750061035,
|
|
"epoch": 0.8451459201905897,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000494032396964096,
|
|
"loss": 5.1361,
|
|
"mean_token_accuracy": 0.18121372759342194,
|
|
"num_tokens": 19832219.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.074743604660034,
|
|
"epoch": 0.8457415128052412,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000494022643967125,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.19376613050699235,
|
|
"num_tokens": 19844913.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.179271078109741,
|
|
"epoch": 0.8463371054198928,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004940128831141679,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.1794682115316391,
|
|
"num_tokens": 19858375.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.274112701416016,
|
|
"epoch": 0.8469326980345444,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004940031144055747,
|
|
"loss": 5.1272,
|
|
"mean_token_accuracy": 0.1793677717447281,
|
|
"num_tokens": 19872004.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.196272563934326,
|
|
"epoch": 0.847528290649196,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004939933378416959,
|
|
"loss": 5.0549,
|
|
"mean_token_accuracy": 0.18480359613895417,
|
|
"num_tokens": 19886340.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.2366941452026365,
|
|
"epoch": 0.8481238832638476,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004939835534228821,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.18393071442842485,
|
|
"num_tokens": 19899185.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.225280618667602,
|
|
"epoch": 0.848719475878499,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004939737611494842,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.17272197008132933,
|
|
"num_tokens": 19912886.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.256770324707031,
|
|
"epoch": 0.8493150684931506,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004939639610218536,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.17124029844999314,
|
|
"num_tokens": 19927780.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.224159383773804,
|
|
"epoch": 0.8499106611078022,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004939541530403419,
|
|
"loss": 5.0651,
|
|
"mean_token_accuracy": 0.18767995834350587,
|
|
"num_tokens": 19940181.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.19455509185791,
|
|
"epoch": 0.8505062537224538,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004939443372053004,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.1791049510240555,
|
|
"num_tokens": 19952823.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.2374958992004395,
|
|
"epoch": 0.8511018463371054,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004939345135170818,
|
|
"loss": 5.2088,
|
|
"mean_token_accuracy": 0.17334190607070923,
|
|
"num_tokens": 19966528.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.294004344940186,
|
|
"epoch": 0.851697438951757,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000493924681976038,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.17587825357913972,
|
|
"num_tokens": 19981259.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.218479776382447,
|
|
"epoch": 0.8522930315664086,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004939148425825219,
|
|
"loss": 5.158,
|
|
"mean_token_accuracy": 0.1789134457707405,
|
|
"num_tokens": 19995096.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.18101487159729,
|
|
"epoch": 0.8528886241810602,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004939049953368863,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.18060832172632219,
|
|
"num_tokens": 20008895.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.256049346923828,
|
|
"epoch": 0.8534842167957117,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004938951402394844,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.1783613830804825,
|
|
"num_tokens": 20023506.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.215874910354614,
|
|
"epoch": 0.8540798094103633,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004938852772906697,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.18582986444234847,
|
|
"num_tokens": 20036810.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.193774175643921,
|
|
"epoch": 0.8546754020250149,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004938754064907961,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.18837936967611313,
|
|
"num_tokens": 20050653.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.186962842941284,
|
|
"epoch": 0.8552709946396665,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004938655278402175,
|
|
"loss": 5.0943,
|
|
"mean_token_accuracy": 0.1865772619843483,
|
|
"num_tokens": 20065361.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.12246527671814,
|
|
"epoch": 0.8558665872543181,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004938556413392882,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.19439612030982972,
|
|
"num_tokens": 20079160.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.206735610961914,
|
|
"epoch": 0.8564621798689697,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004938457469883629,
|
|
"loss": 5.0384,
|
|
"mean_token_accuracy": 0.1829827144742012,
|
|
"num_tokens": 20095036.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.133657503128052,
|
|
"epoch": 0.8570577724836212,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004938358447877966,
|
|
"loss": 5.0487,
|
|
"mean_token_accuracy": 0.19104191809892654,
|
|
"num_tokens": 20112319.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.187980651855469,
|
|
"epoch": 0.8576533650982728,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004938259347379442,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.17840091735124589,
|
|
"num_tokens": 20126683.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.2349340438842775,
|
|
"epoch": 0.8582489577129243,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004938160168391614,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.17747076004743575,
|
|
"num_tokens": 20142016.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.216857290267944,
|
|
"epoch": 0.8588445503275759,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004938060910918038,
|
|
"loss": 5.0856,
|
|
"mean_token_accuracy": 0.18634457588195802,
|
|
"num_tokens": 20156199.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.282405805587769,
|
|
"epoch": 0.8594401429422275,
|
|
"grad_norm": 2.921875,
|
|
"learning_rate": 0.0004937961574962274,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.17512128502130508,
|
|
"num_tokens": 20169443.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.127078008651734,
|
|
"epoch": 0.8600357355568791,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004937862160527887,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.1828817382454872,
|
|
"num_tokens": 20184187.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.22017469406128,
|
|
"epoch": 0.8606313281715307,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004937762667618441,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.18617113530635834,
|
|
"num_tokens": 20198217.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.195673894882202,
|
|
"epoch": 0.8612269207861822,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004937663096237505,
|
|
"loss": 5.0704,
|
|
"mean_token_accuracy": 0.18644584864377975,
|
|
"num_tokens": 20214253.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.1419579029083256,
|
|
"epoch": 0.8618225134008338,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004937563446388652,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.1880979135632515,
|
|
"num_tokens": 20227880.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.0796538352966305,
|
|
"epoch": 0.8624181060154854,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004937463718075453,
|
|
"loss": 5.0247,
|
|
"mean_token_accuracy": 0.18917743116617203,
|
|
"num_tokens": 20242642.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.144789409637451,
|
|
"epoch": 0.863013698630137,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004937363911301488,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.1851380944252014,
|
|
"num_tokens": 20255950.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.263351154327393,
|
|
"epoch": 0.8636092912447886,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004937264026070336,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.1854444995522499,
|
|
"num_tokens": 20270067.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.289241933822632,
|
|
"epoch": 0.8642048838594402,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000493716406238558,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.17850937694311142,
|
|
"num_tokens": 20283326.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.092835807800293,
|
|
"epoch": 0.8648004764740918,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004937064020250804,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.18397517800331115,
|
|
"num_tokens": 20296161.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.104546785354614,
|
|
"epoch": 0.8653960690887433,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004936963899669599,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.18461733162403107,
|
|
"num_tokens": 20310662.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.243007659912109,
|
|
"epoch": 0.8659916617033949,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004936863700645554,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.18042291551828385,
|
|
"num_tokens": 20324381.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.193395042419434,
|
|
"epoch": 0.8665872543180465,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004936763423182264,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.184426411986351,
|
|
"num_tokens": 20338093.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.20997838973999,
|
|
"epoch": 0.867182846932698,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004936663067283325,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.19372705966234208,
|
|
"num_tokens": 20350534.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.115779781341553,
|
|
"epoch": 0.8677784395473496,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004936562632952337,
|
|
"loss": 5.0224,
|
|
"mean_token_accuracy": 0.1890186309814453,
|
|
"num_tokens": 20364230.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.2419709205627445,
|
|
"epoch": 0.8683740321620012,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004936462120192903,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.17629176378250122,
|
|
"num_tokens": 20380605.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.25690541267395,
|
|
"epoch": 0.8689696247766527,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004936361529008627,
|
|
"loss": 5.148,
|
|
"mean_token_accuracy": 0.1806987166404724,
|
|
"num_tokens": 20392760.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.170257997512818,
|
|
"epoch": 0.8695652173913043,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004936260859403119,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.181083482503891,
|
|
"num_tokens": 20408519.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.095888376235962,
|
|
"epoch": 0.8701608100059559,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004936160111379987,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.18824821412563325,
|
|
"num_tokens": 20421322.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.197620296478272,
|
|
"epoch": 0.8707564026206075,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004936059284942848,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.1816544771194458,
|
|
"num_tokens": 20436056.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.20635724067688,
|
|
"epoch": 0.8713519952352591,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004935958380095316,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.18455056697130204,
|
|
"num_tokens": 20449268.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.233606386184692,
|
|
"epoch": 0.8719475878499107,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000493585739684101,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.1804738685488701,
|
|
"num_tokens": 20462635.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.224104690551758,
|
|
"epoch": 0.8725431804645623,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004935756335183554,
|
|
"loss": 5.0634,
|
|
"mean_token_accuracy": 0.18596356064081193,
|
|
"num_tokens": 20476048.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.1410167694091795,
|
|
"epoch": 0.8731387730792138,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004935655195126572,
|
|
"loss": 5.0277,
|
|
"mean_token_accuracy": 0.18407767713069917,
|
|
"num_tokens": 20488856.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.1703447818756105,
|
|
"epoch": 0.8737343656938654,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004935553976673692,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.18192342072725295,
|
|
"num_tokens": 20503426.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.254005241394043,
|
|
"epoch": 0.874329958308517,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004935452679828545,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.18211258351802825,
|
|
"num_tokens": 20518305.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.176205968856811,
|
|
"epoch": 0.8749255509231686,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004935351304594763,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.190836164355278,
|
|
"num_tokens": 20532310.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.194339752197266,
|
|
"epoch": 0.8755211435378202,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004935249850975983,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.17845725566148757,
|
|
"num_tokens": 20546149.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.185348558425903,
|
|
"epoch": 0.8761167361524718,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004935148318975843,
|
|
"loss": 5.0804,
|
|
"mean_token_accuracy": 0.18624706119298934,
|
|
"num_tokens": 20560077.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.276123523712158,
|
|
"epoch": 0.8767123287671232,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004935046708597986,
|
|
"loss": 5.2079,
|
|
"mean_token_accuracy": 0.17563845664262773,
|
|
"num_tokens": 20574657.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.167912101745605,
|
|
"epoch": 0.8773079213817748,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004934945019846057,
|
|
"loss": 4.9869,
|
|
"mean_token_accuracy": 0.18970226645469665,
|
|
"num_tokens": 20587091.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.138029479980469,
|
|
"epoch": 0.8779035139964264,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004934843252723702,
|
|
"loss": 5.1037,
|
|
"mean_token_accuracy": 0.1862097203731537,
|
|
"num_tokens": 20600537.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.277370929718018,
|
|
"epoch": 0.878499106611078,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004934741407234572,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.18139087855815889,
|
|
"num_tokens": 20614029.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.203844165802002,
|
|
"epoch": 0.8790946992257296,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000493463948338232,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.18305605202913283,
|
|
"num_tokens": 20627906.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.142110061645508,
|
|
"epoch": 0.8796902918403812,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004934537481170602,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.18689161092042922,
|
|
"num_tokens": 20642717.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.15441107749939,
|
|
"epoch": 0.8802858844550328,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004934435400603077,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.1821290746331215,
|
|
"num_tokens": 20657234.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.214570808410644,
|
|
"epoch": 0.8808814770696843,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004934333241683404,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.18210953176021577,
|
|
"num_tokens": 20672162.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.310224199295044,
|
|
"epoch": 0.8814770696843359,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004934231004415251,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.18403857052326203,
|
|
"num_tokens": 20684565.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.212579727172852,
|
|
"epoch": 0.8820726622989875,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004934128688802282,
|
|
"loss": 5.1884,
|
|
"mean_token_accuracy": 0.1781950682401657,
|
|
"num_tokens": 20699931.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.151624631881714,
|
|
"epoch": 0.8826682549136391,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004934026294848168,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.18193231672048568,
|
|
"num_tokens": 20715031.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.181616735458374,
|
|
"epoch": 0.8832638475282907,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004933923822556583,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.1848944291472435,
|
|
"num_tokens": 20730825.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.286242389678955,
|
|
"epoch": 0.8838594401429423,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00049338212719312,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.18294578641653061,
|
|
"num_tokens": 20743287.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.222881507873535,
|
|
"epoch": 0.8844550327575939,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00049337186429757,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.17619587928056718,
|
|
"num_tokens": 20759911.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.160513591766358,
|
|
"epoch": 0.8850506253722454,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004933615935693762,
|
|
"loss": 5.0415,
|
|
"mean_token_accuracy": 0.18271573781967163,
|
|
"num_tokens": 20772842.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.22256908416748,
|
|
"epoch": 0.8856462179868969,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004933513150089069,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.1772781118750572,
|
|
"num_tokens": 20787524.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.123204040527344,
|
|
"epoch": 0.8862418106015485,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004933410286165311,
|
|
"loss": 4.979,
|
|
"mean_token_accuracy": 0.19761269837617873,
|
|
"num_tokens": 20800332.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.215382528305054,
|
|
"epoch": 0.8868374032162001,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004933307343926177,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.19060770571231841,
|
|
"num_tokens": 20813231.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.265911102294922,
|
|
"epoch": 0.8874329958308517,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004933204323375358,
|
|
"loss": 5.2121,
|
|
"mean_token_accuracy": 0.17624540477991105,
|
|
"num_tokens": 20827116.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.352156066894532,
|
|
"epoch": 0.8880285884455033,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000493310122451655,
|
|
"loss": 5.2099,
|
|
"mean_token_accuracy": 0.17725474387407303,
|
|
"num_tokens": 20838536.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.1370094299316404,
|
|
"epoch": 0.8886241810601548,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004932998047353449,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.18985231667757035,
|
|
"num_tokens": 20850849.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.121904754638672,
|
|
"epoch": 0.8892197736748064,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004932894791889759,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.18624509871006012,
|
|
"num_tokens": 20866140.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.202115678787232,
|
|
"epoch": 0.889815366289458,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004932791458129181,
|
|
"loss": 5.0989,
|
|
"mean_token_accuracy": 0.18393292874097825,
|
|
"num_tokens": 20879458.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.179807090759278,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004932688046075422,
|
|
"loss": 5.0527,
|
|
"mean_token_accuracy": 0.18209971636533737,
|
|
"num_tokens": 20893516.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.256492233276367,
|
|
"epoch": 0.8910065515187612,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004932584555732192,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.17650620639324188,
|
|
"num_tokens": 20908713.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.276069974899292,
|
|
"epoch": 0.8916021441334128,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004932480987103204,
|
|
"loss": 5.0796,
|
|
"mean_token_accuracy": 0.1850678578019142,
|
|
"num_tokens": 20922080.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.1992466926574705,
|
|
"epoch": 0.8921977367480644,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004932377340192169,
|
|
"loss": 5.0929,
|
|
"mean_token_accuracy": 0.18156949281692505,
|
|
"num_tokens": 20935484.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.253864717483521,
|
|
"epoch": 0.8927933293627159,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004932273615002809,
|
|
"loss": 5.1549,
|
|
"mean_token_accuracy": 0.17903856337070465,
|
|
"num_tokens": 20948851.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.178297233581543,
|
|
"epoch": 0.8933889219773675,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004932169811538843,
|
|
"loss": 5.0933,
|
|
"mean_token_accuracy": 0.183717580139637,
|
|
"num_tokens": 20961637.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.257936286926269,
|
|
"epoch": 0.8939845145920191,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004932065929803993,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.17254547476768495,
|
|
"num_tokens": 20976236.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.194496011734008,
|
|
"epoch": 0.8945801072066706,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004931961969801985,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.18168222159147263,
|
|
"num_tokens": 20990439.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.225243330001831,
|
|
"epoch": 0.8951756998213222,
|
|
"grad_norm": 3.28125,
|
|
"learning_rate": 0.000493185793153655,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.17975667417049407,
|
|
"num_tokens": 21003632.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.2023632526397705,
|
|
"epoch": 0.8957712924359738,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004931753815011419,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.1813985139131546,
|
|
"num_tokens": 21017685.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.16142897605896,
|
|
"epoch": 0.8963668850506253,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004931649620230325,
|
|
"loss": 5.058,
|
|
"mean_token_accuracy": 0.19038666039705276,
|
|
"num_tokens": 21029720.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.189581680297851,
|
|
"epoch": 0.8969624776652769,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004931545347197006,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.1794983297586441,
|
|
"num_tokens": 21044148.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.248789072036743,
|
|
"epoch": 0.8975580702799285,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004931440995915203,
|
|
"loss": 5.1092,
|
|
"mean_token_accuracy": 0.1790762260556221,
|
|
"num_tokens": 21059278.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.123855209350586,
|
|
"epoch": 0.8981536628945801,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004931336566388658,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.18212720155715942,
|
|
"num_tokens": 21074258.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.225326204299927,
|
|
"epoch": 0.8987492555092317,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004931232058621117,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.17388959228992462,
|
|
"num_tokens": 21087283.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.265724611282349,
|
|
"epoch": 0.8993448481238833,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004931127472616328,
|
|
"loss": 5.0779,
|
|
"mean_token_accuracy": 0.18224076330661773,
|
|
"num_tokens": 21101461.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.187210464477539,
|
|
"epoch": 0.8999404407385349,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004931022808378044,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.18295302540063857,
|
|
"num_tokens": 21115067.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.238268613815308,
|
|
"epoch": 0.9005360333531864,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004930918065910018,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.18265732675790786,
|
|
"num_tokens": 21129029.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.234867954254151,
|
|
"epoch": 0.901131625967838,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004930813245216005,
|
|
"loss": 5.1176,
|
|
"mean_token_accuracy": 0.18347528725862502,
|
|
"num_tokens": 21142037.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.211436414718628,
|
|
"epoch": 0.9017272185824896,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004930708346299769,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.1812220260500908,
|
|
"num_tokens": 21157036.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.201026868820191,
|
|
"epoch": 0.9023228111971412,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004930603369165069,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.18414091616868972,
|
|
"num_tokens": 21170025.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.162506008148194,
|
|
"epoch": 0.9029184038117928,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004930498313815672,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.18383913785219191,
|
|
"num_tokens": 21183664.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.099540090560913,
|
|
"epoch": 0.9035139964264444,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004930393180255345,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.18482149243354798,
|
|
"num_tokens": 21198299.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.137762355804443,
|
|
"epoch": 0.9041095890410958,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000493028796848786,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.19554013460874559,
|
|
"num_tokens": 21210133.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.169166851043701,
|
|
"epoch": 0.9047051816557474,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004930182678516992,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.1837372064590454,
|
|
"num_tokens": 21225813.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.3316749095916744,
|
|
"epoch": 0.905300774270399,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004930077310346515,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.1792012184858322,
|
|
"num_tokens": 21238602.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.229163265228271,
|
|
"epoch": 0.9058963668850506,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004929971863980209,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.18264689445495605,
|
|
"num_tokens": 21254367.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.207023191452026,
|
|
"epoch": 0.9064919594997022,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004929866339421857,
|
|
"loss": 5.1235,
|
|
"mean_token_accuracy": 0.18198444992303847,
|
|
"num_tokens": 21268285.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.1856566905975345,
|
|
"epoch": 0.9070875521143538,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004929760736675243,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.1794467717409134,
|
|
"num_tokens": 21282398.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.299195623397827,
|
|
"epoch": 0.9076831447290054,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004929655055744157,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.17682634443044662,
|
|
"num_tokens": 21296991.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.238634538650513,
|
|
"epoch": 0.9082787373436569,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004929549296632387,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.18398913145065307,
|
|
"num_tokens": 21313677.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.1897680282592775,
|
|
"epoch": 0.9088743299583085,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004929443459343728,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.18569311499595642,
|
|
"num_tokens": 21325252.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.167136144638062,
|
|
"epoch": 0.9094699225729601,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004929337543881975,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.18212943971157075,
|
|
"num_tokens": 21341771.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.269829988479614,
|
|
"epoch": 0.9100655151876117,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004929231550250927,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.18317921459674835,
|
|
"num_tokens": 21356029.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.3068865776062015,
|
|
"epoch": 0.9106611078022633,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004929125478454389,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.1805462121963501,
|
|
"num_tokens": 21369943.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.313466882705688,
|
|
"epoch": 0.9112567004169149,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004929019328496161,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.1857174500823021,
|
|
"num_tokens": 21385078.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.09163761138916,
|
|
"epoch": 0.9118522930315665,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004928913100380053,
|
|
"loss": 4.888,
|
|
"mean_token_accuracy": 0.1926531508564949,
|
|
"num_tokens": 21398249.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.140061569213867,
|
|
"epoch": 0.912447885646218,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004928806794109875,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.18281231224536895,
|
|
"num_tokens": 21414773.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.286297559738159,
|
|
"epoch": 0.9130434782608695,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000492870040968944,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.18083200454711915,
|
|
"num_tokens": 21428551.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.228904438018799,
|
|
"epoch": 0.9136390708755211,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004928593947122564,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.17726798951625825,
|
|
"num_tokens": 21442916.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.2341498851776125,
|
|
"epoch": 0.9142346634901727,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004928487406413065,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.1756560131907463,
|
|
"num_tokens": 21457686.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.25686206817627,
|
|
"epoch": 0.9148302561048243,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004928380787564764,
|
|
"loss": 5.11,
|
|
"mean_token_accuracy": 0.18776333183050156,
|
|
"num_tokens": 21473503.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.174749517440796,
|
|
"epoch": 0.9154258487194759,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004928274090581486,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.18190868943929672,
|
|
"num_tokens": 21486362.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.135950088500977,
|
|
"epoch": 0.9160214413341274,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004928167315467059,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.18440365940332412,
|
|
"num_tokens": 21500445.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.199371814727783,
|
|
"epoch": 0.916617033948779,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004928060462225312,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.18091883957386018,
|
|
"num_tokens": 21513648.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.252010202407837,
|
|
"epoch": 0.9172126265634306,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004927953530860077,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.1837008371949196,
|
|
"num_tokens": 21528103.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.203017616271973,
|
|
"epoch": 0.9178082191780822,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004927846521375189,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.19731593430042266,
|
|
"num_tokens": 21542435.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.2272303104400635,
|
|
"epoch": 0.9184038117927338,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004927739433774489,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.18570508062839508,
|
|
"num_tokens": 21557993.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.220523309707642,
|
|
"epoch": 0.9189994044073854,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004927632268061815,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.17930447608232497,
|
|
"num_tokens": 21573383.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.246750974655152,
|
|
"epoch": 0.919594997022037,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004927525024241013,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.18726846873760222,
|
|
"num_tokens": 21588179.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.18770580291748,
|
|
"epoch": 0.9201905896366885,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004927417702315928,
|
|
"loss": 5.1084,
|
|
"mean_token_accuracy": 0.18216793686151506,
|
|
"num_tokens": 21603595.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.223182678222656,
|
|
"epoch": 0.9207861822513401,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004927310302290411,
|
|
"loss": 5.0994,
|
|
"mean_token_accuracy": 0.1837053894996643,
|
|
"num_tokens": 21618487.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.180555248260498,
|
|
"epoch": 0.9213817748659917,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004927202824168313,
|
|
"loss": 5.0269,
|
|
"mean_token_accuracy": 0.18593628108501434,
|
|
"num_tokens": 21632970.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.203290271759033,
|
|
"epoch": 0.9219773674806433,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000492709526795349,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.18153996914625167,
|
|
"num_tokens": 21645943.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.1577467918396,
|
|
"epoch": 0.9225729600952948,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00049269876336498,
|
|
"loss": 4.9584,
|
|
"mean_token_accuracy": 0.19280207753181458,
|
|
"num_tokens": 21658028.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.2371738910675045,
|
|
"epoch": 0.9231685527099464,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004926879921261101,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.18613174706697463,
|
|
"num_tokens": 21672265.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.144713354110718,
|
|
"epoch": 0.9237641453245979,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004926772130791261,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.18349528908729554,
|
|
"num_tokens": 21685871.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.114120864868164,
|
|
"epoch": 0.9243597379392495,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004926664262244143,
|
|
"loss": 4.9606,
|
|
"mean_token_accuracy": 0.19322317093610764,
|
|
"num_tokens": 21699783.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.226307916641235,
|
|
"epoch": 0.9249553305539011,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004926556315623617,
|
|
"loss": 5.0897,
|
|
"mean_token_accuracy": 0.18413880914449693,
|
|
"num_tokens": 21716144.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.234931087493896,
|
|
"epoch": 0.9255509231685527,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004926448290933555,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.1825464352965355,
|
|
"num_tokens": 21727334.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.2042066097259525,
|
|
"epoch": 0.9261465157832043,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004926340188177831,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.18692791759967803,
|
|
"num_tokens": 21740989.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.218502044677734,
|
|
"epoch": 0.9267421083978559,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004926232007360324,
|
|
"loss": 5.142,
|
|
"mean_token_accuracy": 0.1765047565102577,
|
|
"num_tokens": 21756776.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.2456153392791744,
|
|
"epoch": 0.9273377010125075,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004926123748484911,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.18415207117795945,
|
|
"num_tokens": 21771864.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.163418292999268,
|
|
"epoch": 0.927933293627159,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000492601541155548,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.18642560243606568,
|
|
"num_tokens": 21785161.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.2313775539398195,
|
|
"epoch": 0.9285288862418106,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004925906996575912,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.17554867565631865,
|
|
"num_tokens": 21799350.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.342170572280883,
|
|
"epoch": 0.9291244788564622,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004925798503550099,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.18386175185441972,
|
|
"num_tokens": 21813925.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.247431230545044,
|
|
"epoch": 0.9297200714711138,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004925689932481931,
|
|
"loss": 5.149,
|
|
"mean_token_accuracy": 0.18200182169675827,
|
|
"num_tokens": 21828356.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.084236812591553,
|
|
"epoch": 0.9303156640857654,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004925581283375303,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.18916328400373458,
|
|
"num_tokens": 21842667.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.1930304050445555,
|
|
"epoch": 0.930911256700417,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004925472556234111,
|
|
"loss": 5.1286,
|
|
"mean_token_accuracy": 0.18124072700738908,
|
|
"num_tokens": 21856116.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.242581844329834,
|
|
"epoch": 0.9315068493150684,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004925363751062256,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.18673061579465866,
|
|
"num_tokens": 21870630.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.239479637145996,
|
|
"epoch": 0.93210244192972,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000492525486786364,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.18532093316316606,
|
|
"num_tokens": 21884982.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.210445928573608,
|
|
"epoch": 0.9326980345443716,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004925145906642169,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.18863595277071,
|
|
"num_tokens": 21899301.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.187036180496216,
|
|
"epoch": 0.9332936271590232,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004925036867401751,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.18359658718109131,
|
|
"num_tokens": 21913903.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.173808622360229,
|
|
"epoch": 0.9338892197736748,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004924927750146296,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.18350591361522675,
|
|
"num_tokens": 21930123.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.175187397003174,
|
|
"epoch": 0.9344848123883264,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004924818554879718,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.17902842462062835,
|
|
"num_tokens": 21945164.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.207448816299438,
|
|
"epoch": 0.935080405002978,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004924709281605938,
|
|
"loss": 5.1108,
|
|
"mean_token_accuracy": 0.17550349086523057,
|
|
"num_tokens": 21959341.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.17921667098999,
|
|
"epoch": 0.9356759976176295,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004924599930328869,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.18170306086540222,
|
|
"num_tokens": 21973049.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.105161857604981,
|
|
"epoch": 0.9362715902322811,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004924490501052437,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.19313179552555085,
|
|
"num_tokens": 21985604.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.26577787399292,
|
|
"epoch": 0.9368671828469327,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004924380993780566,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.17579843625426292,
|
|
"num_tokens": 22000472.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.21081919670105,
|
|
"epoch": 0.9374627754615843,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004924271408517185,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.18503688126802445,
|
|
"num_tokens": 22014162.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.200260877609253,
|
|
"epoch": 0.9380583680762359,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004924161745266222,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.18060000389814376,
|
|
"num_tokens": 22026832.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.118302536010742,
|
|
"epoch": 0.9386539606908875,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004924052004031613,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.19247023910284042,
|
|
"num_tokens": 22038816.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.239597511291504,
|
|
"epoch": 0.939249553305539,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004923942184817293,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.17970820665359497,
|
|
"num_tokens": 22053356.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.218827581405639,
|
|
"epoch": 0.9398451459201906,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004923832287627202,
|
|
"loss": 5.0579,
|
|
"mean_token_accuracy": 0.17989009916782378,
|
|
"num_tokens": 22066879.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.214664173126221,
|
|
"epoch": 0.9404407385348421,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004923722312465281,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.17892047464847566,
|
|
"num_tokens": 22081036.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.256146812438965,
|
|
"epoch": 0.9410363311494937,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004923612259335476,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.17687799483537675,
|
|
"num_tokens": 22095609.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.140742063522339,
|
|
"epoch": 0.9416319237641453,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004923502128241732,
|
|
"loss": 4.9848,
|
|
"mean_token_accuracy": 0.1911427214741707,
|
|
"num_tokens": 22107539.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.1610020160675045,
|
|
"epoch": 0.9422275163787969,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004923391919188001,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.18476383239030839,
|
|
"num_tokens": 22120438.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.2361503601074215,
|
|
"epoch": 0.9428231089934485,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004923281632178236,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.17076935321092607,
|
|
"num_tokens": 22134796.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.297043323516846,
|
|
"epoch": 0.9434187016081,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004923171267216392,
|
|
"loss": 5.1026,
|
|
"mean_token_accuracy": 0.18478514850139618,
|
|
"num_tokens": 22149178.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.176437473297119,
|
|
"epoch": 0.9440142942227516,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004923060824306428,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.18009829372167588,
|
|
"num_tokens": 22163652.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.238694286346435,
|
|
"epoch": 0.9446098868374032,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004922950303452306,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.1780875250697136,
|
|
"num_tokens": 22178116.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.175779151916504,
|
|
"epoch": 0.9452054794520548,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004922839704657988,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.18950692266225816,
|
|
"num_tokens": 22191750.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.207122755050659,
|
|
"epoch": 0.9458010720667064,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004922729027927444,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.18254588842391967,
|
|
"num_tokens": 22204889.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.171549367904663,
|
|
"epoch": 0.946396664681358,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004922618273264642,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.18280642181634904,
|
|
"num_tokens": 22218312.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.214089059829712,
|
|
"epoch": 0.9469922572960096,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004922507440673555,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.17951544970273972,
|
|
"num_tokens": 22232443.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.102374601364136,
|
|
"epoch": 0.9475878499106611,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004922396530158159,
|
|
"loss": 4.8843,
|
|
"mean_token_accuracy": 0.2040122091770172,
|
|
"num_tokens": 22245070.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.128661251068115,
|
|
"epoch": 0.9481834425253127,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004922285541722431,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.1887748122215271,
|
|
"num_tokens": 22257324.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.212119770050049,
|
|
"epoch": 0.9487790351399643,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004922174475370352,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.1813521683216095,
|
|
"num_tokens": 22273438.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.217840909957886,
|
|
"epoch": 0.9493746277546159,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004922063331105907,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.18610650002956391,
|
|
"num_tokens": 22285824.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.095248031616211,
|
|
"epoch": 0.9499702203692674,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004921952108933083,
|
|
"loss": 5.001,
|
|
"mean_token_accuracy": 0.18938365429639817,
|
|
"num_tokens": 22299345.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.170162916183472,
|
|
"epoch": 0.950565812983919,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004921840808855865,
|
|
"loss": 5.028,
|
|
"mean_token_accuracy": 0.18439690470695497,
|
|
"num_tokens": 22313684.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.206250858306885,
|
|
"epoch": 0.9511614055985705,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004921729430878252,
|
|
"loss": 5.1001,
|
|
"mean_token_accuracy": 0.18525363206863404,
|
|
"num_tokens": 22327474.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.234527587890625,
|
|
"epoch": 0.9517569982132221,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004921617975004233,
|
|
"loss": 5.1415,
|
|
"mean_token_accuracy": 0.1850573316216469,
|
|
"num_tokens": 22343026.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.20321216583252,
|
|
"epoch": 0.9523525908278737,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004921506441237809,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.18126197457313536,
|
|
"num_tokens": 22358734.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.223925065994263,
|
|
"epoch": 0.9529481834425253,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004921394829582979,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.1829545944929123,
|
|
"num_tokens": 22371840.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.057163572311401,
|
|
"epoch": 0.9535437760571769,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004921283140043748,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.19890958815813065,
|
|
"num_tokens": 22384450.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.123828411102295,
|
|
"epoch": 0.9541393686718285,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004921171372624121,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.18837044835090638,
|
|
"num_tokens": 22398988.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.133691644668579,
|
|
"epoch": 0.95473496128648,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004921059527328106,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.19349369555711746,
|
|
"num_tokens": 22411703.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.25251407623291,
|
|
"epoch": 0.9553305539011316,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004920947604159716,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.17898729741573333,
|
|
"num_tokens": 22427229.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.115692663192749,
|
|
"epoch": 0.9559261465157832,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004920835603122965,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.18863215744495393,
|
|
"num_tokens": 22439357.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.169746255874633,
|
|
"epoch": 0.9565217391304348,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004920723524221871,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.1749936208128929,
|
|
"num_tokens": 22453214.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.211483955383301,
|
|
"epoch": 0.9571173317450864,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004920611367460453,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.18574672490358352,
|
|
"num_tokens": 22468030.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.228881883621216,
|
|
"epoch": 0.957712924359738,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004920499132842734,
|
|
"loss": 5.0519,
|
|
"mean_token_accuracy": 0.18463194966316224,
|
|
"num_tokens": 22481975.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.180058574676513,
|
|
"epoch": 0.9583085169743896,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004920386820372741,
|
|
"loss": 5.1563,
|
|
"mean_token_accuracy": 0.1792103409767151,
|
|
"num_tokens": 22495047.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.249046039581299,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004920274430054502,
|
|
"loss": 5.1497,
|
|
"mean_token_accuracy": 0.1838125005364418,
|
|
"num_tokens": 22509310.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.204021167755127,
|
|
"epoch": 0.9594997022036926,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004920161961892047,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.18693994581699372,
|
|
"num_tokens": 22525220.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.091725873947143,
|
|
"epoch": 0.9600952948183442,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004920049415889411,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.2003035843372345,
|
|
"num_tokens": 22538123.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.156713581085205,
|
|
"epoch": 0.9606908874329958,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004919936792050631,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.18167585432529448,
|
|
"num_tokens": 22552229.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.179902505874634,
|
|
"epoch": 0.9612864800476474,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004919824090379747,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.18483498692512512,
|
|
"num_tokens": 22566398.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.200600290298462,
|
|
"epoch": 0.961882072662299,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00049197113108808,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.18917882293462754,
|
|
"num_tokens": 22579736.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.058507299423217,
|
|
"epoch": 0.9624776652769506,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004919598453557836,
|
|
"loss": 4.921,
|
|
"mean_token_accuracy": 0.1973540559411049,
|
|
"num_tokens": 22593325.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.156733989715576,
|
|
"epoch": 0.9630732578916021,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004919485518414902,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.18080828189849854,
|
|
"num_tokens": 22607306.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.162451934814453,
|
|
"epoch": 0.9636688505062537,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004919372505456051,
|
|
"loss": 5.1009,
|
|
"mean_token_accuracy": 0.1853577271103859,
|
|
"num_tokens": 22620504.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.1776055812835695,
|
|
"epoch": 0.9642644431209053,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004919259414685336,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.1774609714746475,
|
|
"num_tokens": 22634097.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.268498659133911,
|
|
"epoch": 0.9648600357355569,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004919146246106812,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.17866310626268386,
|
|
"num_tokens": 22648457.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.200460624694824,
|
|
"epoch": 0.9654556283502085,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004919032999724539,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.18141051828861238,
|
|
"num_tokens": 22662128.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.087506246566773,
|
|
"epoch": 0.9660512209648601,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004918919675542579,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.1967153787612915,
|
|
"num_tokens": 22676085.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.1989397525787355,
|
|
"epoch": 0.9666468135795117,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004918806273564996,
|
|
"loss": 5.0543,
|
|
"mean_token_accuracy": 0.1873525172472,
|
|
"num_tokens": 22689672.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.2525536060333256,
|
|
"epoch": 0.9672424061941632,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000491869279379586,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.18349346816539763,
|
|
"num_tokens": 22705240.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.179974508285523,
|
|
"epoch": 0.9678379988088148,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004918579236239238,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.1847851663827896,
|
|
"num_tokens": 22718532.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.154495143890381,
|
|
"epoch": 0.9684335914234663,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004918465600899205,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.17892357856035232,
|
|
"num_tokens": 22732146.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.163152027130127,
|
|
"epoch": 0.9690291840381179,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004918351887779837,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.18857681155204772,
|
|
"num_tokens": 22744590.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.174869251251221,
|
|
"epoch": 0.9696247766527695,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004918238096885213,
|
|
"loss": 5.0549,
|
|
"mean_token_accuracy": 0.18118514120578766,
|
|
"num_tokens": 22758607.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.114116525650024,
|
|
"epoch": 0.9702203692674211,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004918124228219412,
|
|
"loss": 4.9681,
|
|
"mean_token_accuracy": 0.1939116433262825,
|
|
"num_tokens": 22771846.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.1433594703674315,
|
|
"epoch": 0.9708159618820726,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004918010281786522,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.18839030265808104,
|
|
"num_tokens": 22784705.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.117093324661255,
|
|
"epoch": 0.9714115544967242,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004917896257590627,
|
|
"loss": 5.0354,
|
|
"mean_token_accuracy": 0.18904283046722412,
|
|
"num_tokens": 22799706.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.16018123626709,
|
|
"epoch": 0.9720071471113758,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004917782155635817,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.18137320280075073,
|
|
"num_tokens": 22813021.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.196865653991699,
|
|
"epoch": 0.9726027397260274,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004917667975926187,
|
|
"loss": 5.0958,
|
|
"mean_token_accuracy": 0.1845630332827568,
|
|
"num_tokens": 22827936.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.219106578826905,
|
|
"epoch": 0.973198332340679,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004917553718465832,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.1806523934006691,
|
|
"num_tokens": 22842307.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.138340902328491,
|
|
"epoch": 0.9737939249553306,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004917439383258848,
|
|
"loss": 5.017,
|
|
"mean_token_accuracy": 0.19214527308940887,
|
|
"num_tokens": 22856137.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.170317697525024,
|
|
"epoch": 0.9743895175699822,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004917324970309337,
|
|
"loss": 5.0693,
|
|
"mean_token_accuracy": 0.1818946972489357,
|
|
"num_tokens": 22870705.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.203219890594482,
|
|
"epoch": 0.9749851101846337,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004917210479621404,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.17926887273788453,
|
|
"num_tokens": 22883860.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.136599731445313,
|
|
"epoch": 0.9755807027992853,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004917095911199155,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.18665598034858705,
|
|
"num_tokens": 22897233.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.210995721817016,
|
|
"epoch": 0.9761762954139369,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00049169812650467,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.18094064444303512,
|
|
"num_tokens": 22911931.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.17420392036438,
|
|
"epoch": 0.9767718880285885,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004916866541168148,
|
|
"loss": 5.0169,
|
|
"mean_token_accuracy": 0.19388737678527831,
|
|
"num_tokens": 22925615.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.162692451477051,
|
|
"epoch": 0.97736748064324,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004916751739567617,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.18831334859132767,
|
|
"num_tokens": 22939178.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.222155332565308,
|
|
"epoch": 0.9779630732578916,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004916636860249225,
|
|
"loss": 5.103,
|
|
"mean_token_accuracy": 0.18128952085971833,
|
|
"num_tokens": 22954681.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.159671211242676,
|
|
"epoch": 0.9785586658725431,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000491652190321709,
|
|
"loss": 4.9634,
|
|
"mean_token_accuracy": 0.18565545380115508,
|
|
"num_tokens": 22965843.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.165215730667114,
|
|
"epoch": 0.9791542584871947,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004916406868475338,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.18489527851343154,
|
|
"num_tokens": 22980695.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.212627315521241,
|
|
"epoch": 0.9797498511018463,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004916291756028094,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.18303926289081573,
|
|
"num_tokens": 22994146.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.073563528060913,
|
|
"epoch": 0.9803454437164979,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004916176565879487,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.18486330062150955,
|
|
"num_tokens": 23008397.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.099366474151611,
|
|
"epoch": 0.9809410363311495,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004916061298033648,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.19185294657945634,
|
|
"num_tokens": 23020693.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.177516794204712,
|
|
"epoch": 0.9815366289458011,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004915945952494713,
|
|
"loss": 5.1034,
|
|
"mean_token_accuracy": 0.1894285961985588,
|
|
"num_tokens": 23035444.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.234980869293213,
|
|
"epoch": 0.9821322215604527,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004915830529266818,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.19073054641485215,
|
|
"num_tokens": 23050185.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.16627311706543,
|
|
"epoch": 0.9827278141751042,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004915715028354102,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.1918097898364067,
|
|
"num_tokens": 23063588.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.087980461120606,
|
|
"epoch": 0.9833234067897558,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004915599449760711,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.19644397497177124,
|
|
"num_tokens": 23076581.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.167741584777832,
|
|
"epoch": 0.9839189994044074,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004915483793490788,
|
|
"loss": 5.084,
|
|
"mean_token_accuracy": 0.17872364670038224,
|
|
"num_tokens": 23089583.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.318000555038452,
|
|
"epoch": 0.984514592019059,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004915368059548482,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.1733751952648163,
|
|
"num_tokens": 23103029.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.235243844985962,
|
|
"epoch": 0.9851101846337106,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004915252247937944,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.17573686689138412,
|
|
"num_tokens": 23119056.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.2122434139251705,
|
|
"epoch": 0.9857057772483622,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000491513635866333,
|
|
"loss": 5.0897,
|
|
"mean_token_accuracy": 0.17975735515356064,
|
|
"num_tokens": 23132774.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.145533609390259,
|
|
"epoch": 0.9863013698630136,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004915020391728792,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.18731940388679505,
|
|
"num_tokens": 23147666.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.165627145767212,
|
|
"epoch": 0.9868969624776652,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004914904347138495,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.19233127683401108,
|
|
"num_tokens": 23161868.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.159043645858764,
|
|
"epoch": 0.9874925550923168,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004914788224896599,
|
|
"loss": 5.0472,
|
|
"mean_token_accuracy": 0.18691762536764145,
|
|
"num_tokens": 23174938.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.111989831924438,
|
|
"epoch": 0.9880881477069684,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004914672025007269,
|
|
"loss": 5.0217,
|
|
"mean_token_accuracy": 0.1859242931008339,
|
|
"num_tokens": 23189294.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.278003597259522,
|
|
"epoch": 0.98868374032162,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004914555747474673,
|
|
"loss": 5.1085,
|
|
"mean_token_accuracy": 0.18337891697883607,
|
|
"num_tokens": 23202715.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.103140163421631,
|
|
"epoch": 0.9892793329362716,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004914439392302981,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.18938592523336412,
|
|
"num_tokens": 23216216.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.149814414978027,
|
|
"epoch": 0.9898749255509232,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004914322959496367,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.18956870436668397,
|
|
"num_tokens": 23228795.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.282868385314941,
|
|
"epoch": 0.9904705181655747,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004914206449059008,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.18057057559490203,
|
|
"num_tokens": 23244288.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.223291492462158,
|
|
"epoch": 0.9910661107802263,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004914089860995084,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.1845860093832016,
|
|
"num_tokens": 23259067.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.1546858787536625,
|
|
"epoch": 0.9916617033948779,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004913973195308772,
|
|
"loss": 5.0165,
|
|
"mean_token_accuracy": 0.18659621477127075,
|
|
"num_tokens": 23270939.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.130451250076294,
|
|
"epoch": 0.9922572960095295,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004913856452004262,
|
|
"loss": 4.9937,
|
|
"mean_token_accuracy": 0.190006785094738,
|
|
"num_tokens": 23285309.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.19246654510498,
|
|
"epoch": 0.9928528886241811,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004913739631085739,
|
|
"loss": 5.0663,
|
|
"mean_token_accuracy": 0.18899031728506088,
|
|
"num_tokens": 23299609.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.176688718795776,
|
|
"epoch": 0.9934484812388327,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004913622732557394,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.19332962036132811,
|
|
"num_tokens": 23312817.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.138957071304321,
|
|
"epoch": 0.9940440738534843,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004913505756423418,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.18868686258792877,
|
|
"num_tokens": 23324944.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.0530195236206055,
|
|
"epoch": 0.9946396664681358,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004913388702688009,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.19915838539600372,
|
|
"num_tokens": 23338200.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.133010339736939,
|
|
"epoch": 0.9952352590827874,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004913271571355365,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.19025438129901887,
|
|
"num_tokens": 23352009.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.2646198749542235,
|
|
"epoch": 0.9958308516974389,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004913154362429686,
|
|
"loss": 5.1451,
|
|
"mean_token_accuracy": 0.17300199419260026,
|
|
"num_tokens": 23366680.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.133079910278321,
|
|
"epoch": 0.9964264443120905,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004913037075915178,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.18959100395441056,
|
|
"num_tokens": 23379900.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.138922595977784,
|
|
"epoch": 0.9970220369267421,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004912919711816047,
|
|
"loss": 5.0274,
|
|
"mean_token_accuracy": 0.19089099019765854,
|
|
"num_tokens": 23393366.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.2340967655181885,
|
|
"epoch": 0.9976176295413937,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004912802270136503,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.18358882814645766,
|
|
"num_tokens": 23407272.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.115890216827393,
|
|
"epoch": 0.9982132221560452,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004912684750880757,
|
|
"loss": 4.9833,
|
|
"mean_token_accuracy": 0.18850027769804,
|
|
"num_tokens": 23421167.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.164920139312744,
|
|
"epoch": 0.9988088147706968,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004912567154053025,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.18170070350170137,
|
|
"num_tokens": 23434264.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.230263614654541,
|
|
"epoch": 0.9994044073853484,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004912449479657526,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.1821625679731369,
|
|
"num_tokens": 23448000.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.203503751754761,
|
|
"epoch": 1.0,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004912331727698481,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.18871794044971466,
|
|
"num_tokens": 23461012.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.175820684432983,
|
|
"epoch": 1.0005955926146515,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004912213898180111,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.1839595228433609,
|
|
"num_tokens": 23473230.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.250376987457275,
|
|
"epoch": 1.0011911852293032,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004912095991106644,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.1779637336730957,
|
|
"num_tokens": 23488201.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.291243648529052,
|
|
"epoch": 1.0017867778439546,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004911978006482311,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.17278873175382614,
|
|
"num_tokens": 23505057.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.195608615875244,
|
|
"epoch": 1.0023823704586063,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004911859944311341,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.18659887909889222,
|
|
"num_tokens": 23518061.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.19868278503418,
|
|
"epoch": 1.0029779630732578,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000491174180459797,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.18241386860609055,
|
|
"num_tokens": 23532902.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.149937677383423,
|
|
"epoch": 1.0035735556879095,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004911623587346434,
|
|
"loss": 4.8816,
|
|
"mean_token_accuracy": 0.1970641255378723,
|
|
"num_tokens": 23546329.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.216020202636718,
|
|
"epoch": 1.004169148302561,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004911505292560977,
|
|
"loss": 5.0428,
|
|
"mean_token_accuracy": 0.18128323405981064,
|
|
"num_tokens": 23562153.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.1906797885894775,
|
|
"epoch": 1.0047647409172127,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004911386920245837,
|
|
"loss": 5.0018,
|
|
"mean_token_accuracy": 0.18828960359096528,
|
|
"num_tokens": 23576582.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.170406770706177,
|
|
"epoch": 1.0053603335318642,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004911268470405263,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.1853877857327461,
|
|
"num_tokens": 23591007.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.153563356399536,
|
|
"epoch": 1.0059559261465159,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004911149943043504,
|
|
"loss": 4.9148,
|
|
"mean_token_accuracy": 0.19515921622514726,
|
|
"num_tokens": 23605269.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.209007024765015,
|
|
"epoch": 1.0065515187611673,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000491103133816481,
|
|
"loss": 5.1138,
|
|
"mean_token_accuracy": 0.17860855758190156,
|
|
"num_tokens": 23622448.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.106032657623291,
|
|
"epoch": 1.007147111375819,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004910912655773436,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.19341960549354553,
|
|
"num_tokens": 23636573.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.130080127716065,
|
|
"epoch": 1.0077427039904705,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004910793895873637,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.19848729223012923,
|
|
"num_tokens": 23649542.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.117915105819702,
|
|
"epoch": 1.0083382966051222,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004910675058469675,
|
|
"loss": 4.9364,
|
|
"mean_token_accuracy": 0.18992458730936052,
|
|
"num_tokens": 23662270.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.244546413421631,
|
|
"epoch": 1.0089338892197737,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004910556143565812,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.18174291402101517,
|
|
"num_tokens": 23675998.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.269423484802246,
|
|
"epoch": 1.0095294818344251,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004910437151166312,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.18314208686351777,
|
|
"num_tokens": 23691511.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.0912652015686035,
|
|
"epoch": 1.0101250744490768,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004910318081275445,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.193769608438015,
|
|
"num_tokens": 23705412.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.120598649978637,
|
|
"epoch": 1.0107206670637283,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000491019893389748,
|
|
"loss": 4.9778,
|
|
"mean_token_accuracy": 0.1854744330048561,
|
|
"num_tokens": 23721303.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.191865587234497,
|
|
"epoch": 1.01131625967838,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004910079709036692,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.19462897181510924,
|
|
"num_tokens": 23735018.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.142121028900147,
|
|
"epoch": 1.0119118522930315,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004909960406697358,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.19134933799505233,
|
|
"num_tokens": 23747262.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.131539916992187,
|
|
"epoch": 1.0125074449076832,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004909841026883755,
|
|
"loss": 5.0209,
|
|
"mean_token_accuracy": 0.18999698460102082,
|
|
"num_tokens": 23761195.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.190923738479614,
|
|
"epoch": 1.0131030375223347,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004909721569600166,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.18603003919124603,
|
|
"num_tokens": 23775789.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.123444557189941,
|
|
"epoch": 1.0136986301369864,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004909602034850875,
|
|
"loss": 4.8818,
|
|
"mean_token_accuracy": 0.19930715411901473,
|
|
"num_tokens": 23788554.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.114092779159546,
|
|
"epoch": 1.0142942227516378,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004909482422640172,
|
|
"loss": 4.9519,
|
|
"mean_token_accuracy": 0.19120087772607802,
|
|
"num_tokens": 23802033.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.166739177703858,
|
|
"epoch": 1.0148898153662895,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004909362732972344,
|
|
"loss": 5.1086,
|
|
"mean_token_accuracy": 0.18422054797410964,
|
|
"num_tokens": 23819250.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.229998159408569,
|
|
"epoch": 1.015485407980941,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004909242965851688,
|
|
"loss": 5.0283,
|
|
"mean_token_accuracy": 0.1816399559378624,
|
|
"num_tokens": 23833917.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.180958700180054,
|
|
"epoch": 1.0160810005955927,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004909123121282495,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.18734592497348784,
|
|
"num_tokens": 23848177.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.116328334808349,
|
|
"epoch": 1.0166765932102442,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004909003199269068,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.1897170752286911,
|
|
"num_tokens": 23861640.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.078144216537476,
|
|
"epoch": 1.0172721858248959,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004908883199815705,
|
|
"loss": 4.9088,
|
|
"mean_token_accuracy": 0.19404664933681487,
|
|
"num_tokens": 23875580.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.077391052246094,
|
|
"epoch": 1.0178677784395473,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004908763122926712,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.1972418248653412,
|
|
"num_tokens": 23887977.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.152505207061767,
|
|
"epoch": 1.018463371054199,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004908642968606396,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.18234228640794753,
|
|
"num_tokens": 23902079.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.1425248146057125,
|
|
"epoch": 1.0190589636688505,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004908522736859068,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.18139560371637345,
|
|
"num_tokens": 23915468.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.12307300567627,
|
|
"epoch": 1.019654556283502,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004908402427689037,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.1884551852941513,
|
|
"num_tokens": 23932059.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.180387687683106,
|
|
"epoch": 1.0202501488981537,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004908282041100621,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.1897447094321251,
|
|
"num_tokens": 23946730.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.246572017669678,
|
|
"epoch": 1.0208457415128052,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004908161577098137,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.1735483705997467,
|
|
"num_tokens": 23961298.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.161297130584717,
|
|
"epoch": 1.0214413341274569,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004908041035685907,
|
|
"loss": 4.9542,
|
|
"mean_token_accuracy": 0.18704470694065095,
|
|
"num_tokens": 23975419.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.132228374481201,
|
|
"epoch": 1.0220369267421083,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004907920416868253,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.18346039950847626,
|
|
"num_tokens": 23989563.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.239127922058105,
|
|
"epoch": 1.02263251935676,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004907799720649502,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.18267569243907927,
|
|
"num_tokens": 24004961.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.103913688659668,
|
|
"epoch": 1.0232281119714115,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004907678947033984,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.19176202565431594,
|
|
"num_tokens": 24019636.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.1784271717071535,
|
|
"epoch": 1.0238237045860632,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004907558096026031,
|
|
"loss": 4.925,
|
|
"mean_token_accuracy": 0.190475432574749,
|
|
"num_tokens": 24031406.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.0914435386657715,
|
|
"epoch": 1.0244192972007147,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004907437167629976,
|
|
"loss": 4.9491,
|
|
"mean_token_accuracy": 0.18842807561159133,
|
|
"num_tokens": 24045468.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.094630479812622,
|
|
"epoch": 1.0250148898153664,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004907316161850158,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.18729132413864136,
|
|
"num_tokens": 24059712.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.182222509384156,
|
|
"epoch": 1.0256104824300178,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004907195078690916,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.1825200855731964,
|
|
"num_tokens": 24073549.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.16229362487793,
|
|
"epoch": 1.0262060750446695,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004907073918156595,
|
|
"loss": 4.9452,
|
|
"mean_token_accuracy": 0.1939864620566368,
|
|
"num_tokens": 24085770.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.165714502334595,
|
|
"epoch": 1.026801667659321,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004906952680251539,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.18077094554901124,
|
|
"num_tokens": 24102289.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.075763082504272,
|
|
"epoch": 1.0273972602739727,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004906831364980098,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.19573108553886415,
|
|
"num_tokens": 24116075.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.203357744216919,
|
|
"epoch": 1.0279928528886242,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004906709972346623,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.18766329288482667,
|
|
"num_tokens": 24129599.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.112076950073242,
|
|
"epoch": 1.0285884455032757,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004906588502355467,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.19119848906993867,
|
|
"num_tokens": 24143322.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.154024982452393,
|
|
"epoch": 1.0291840381179274,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004906466955010988,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.193417589366436,
|
|
"num_tokens": 24157431.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.18427357673645,
|
|
"epoch": 1.0297796307325788,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004906345330317546,
|
|
"loss": 4.9595,
|
|
"mean_token_accuracy": 0.18775807172060013,
|
|
"num_tokens": 24172228.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.038060903549194,
|
|
"epoch": 1.0303752233472305,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004906223628279502,
|
|
"loss": 4.8885,
|
|
"mean_token_accuracy": 0.1947827771306038,
|
|
"num_tokens": 24184436.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.136770296096802,
|
|
"epoch": 1.030970815961882,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004906101848901224,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.19485484659671784,
|
|
"num_tokens": 24197765.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.11870551109314,
|
|
"epoch": 1.0315664085765337,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004905979992187076,
|
|
"loss": 4.9237,
|
|
"mean_token_accuracy": 0.19018592685461044,
|
|
"num_tokens": 24211336.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.134997940063476,
|
|
"epoch": 1.0321620011911852,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004905858058141433,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.18627962470054626,
|
|
"num_tokens": 24226027.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.085556221008301,
|
|
"epoch": 1.0327575938058369,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004905736046768665,
|
|
"loss": 4.8955,
|
|
"mean_token_accuracy": 0.1949202835559845,
|
|
"num_tokens": 24240108.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.211629152297974,
|
|
"epoch": 1.0333531864204883,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004905613958073151,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.18124729096889497,
|
|
"num_tokens": 24253664.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.175166034698487,
|
|
"epoch": 1.03394877903514,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000490549179205927,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.1925927519798279,
|
|
"num_tokens": 24268958.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.143438148498535,
|
|
"epoch": 1.0345443716497915,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004905369548731402,
|
|
"loss": 5.016,
|
|
"mean_token_accuracy": 0.18428985327482222,
|
|
"num_tokens": 24283750.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.216162633895874,
|
|
"epoch": 1.0351399642644432,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004905247228093933,
|
|
"loss": 5.0296,
|
|
"mean_token_accuracy": 0.1820251986384392,
|
|
"num_tokens": 24298316.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.0776896476745605,
|
|
"epoch": 1.0357355568790947,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.000490512483015125,
|
|
"loss": 4.9193,
|
|
"mean_token_accuracy": 0.19568825364112855,
|
|
"num_tokens": 24311113.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.150892639160157,
|
|
"epoch": 1.0363311494937464,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004905002354907743,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.18615822046995162,
|
|
"num_tokens": 24326579.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.143530464172363,
|
|
"epoch": 1.0369267421083979,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004904879802367806,
|
|
"loss": 4.9965,
|
|
"mean_token_accuracy": 0.1895935282111168,
|
|
"num_tokens": 24339208.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.148705673217774,
|
|
"epoch": 1.0375223347230493,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004904757172535833,
|
|
"loss": 5.0241,
|
|
"mean_token_accuracy": 0.18592625260353088,
|
|
"num_tokens": 24351659.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.191915798187256,
|
|
"epoch": 1.038117927337701,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004904634465416226,
|
|
"loss": 5.0007,
|
|
"mean_token_accuracy": 0.18757051527500151,
|
|
"num_tokens": 24365646.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.160832834243775,
|
|
"epoch": 1.0387135199523525,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004904511681013382,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.18407343477010726,
|
|
"num_tokens": 24379577.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.13055305480957,
|
|
"epoch": 1.0393091125670042,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004904388819331707,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.19159749895334244,
|
|
"num_tokens": 24394441.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.1771515846252445,
|
|
"epoch": 1.0399047051816557,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004904265880375609,
|
|
"loss": 4.9729,
|
|
"mean_token_accuracy": 0.19077286273241043,
|
|
"num_tokens": 24408443.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.229399728775024,
|
|
"epoch": 1.0405002977963074,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004904142864149496,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.186554217338562,
|
|
"num_tokens": 24423416.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.165746831893921,
|
|
"epoch": 1.0410958904109588,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000490401977065778,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.18473605066537857,
|
|
"num_tokens": 24436205.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.12567138671875,
|
|
"epoch": 1.0416914830256105,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004903896599904878,
|
|
"loss": 5.0036,
|
|
"mean_token_accuracy": 0.18673911690711975,
|
|
"num_tokens": 24449472.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.127761125564575,
|
|
"epoch": 1.042287075640262,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004903773351895206,
|
|
"loss": 4.9154,
|
|
"mean_token_accuracy": 0.19367776364088057,
|
|
"num_tokens": 24462861.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.17410831451416,
|
|
"epoch": 1.0428826682549137,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004903650026633187,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.20246231853961943,
|
|
"num_tokens": 24474981.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.046451044082642,
|
|
"epoch": 1.0434782608695652,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004903526624123243,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.19540585577487946,
|
|
"num_tokens": 24489283.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.029241275787354,
|
|
"epoch": 1.0440738534842169,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00049034031443698,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.1924195781350136,
|
|
"num_tokens": 24501859.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.166736078262329,
|
|
"epoch": 1.0446694460988684,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004903279587377287,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.18517534285783768,
|
|
"num_tokens": 24515586.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.221512413024902,
|
|
"epoch": 1.04526503871352,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004903155953150137,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.1809518352150917,
|
|
"num_tokens": 24531912.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.15241174697876,
|
|
"epoch": 1.0458606313281715,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004903032241692784,
|
|
"loss": 4.9777,
|
|
"mean_token_accuracy": 0.19099113792181016,
|
|
"num_tokens": 24544958.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.10282301902771,
|
|
"epoch": 1.046456223942823,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004902908453009664,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.1957913726568222,
|
|
"num_tokens": 24556979.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.247539329528808,
|
|
"epoch": 1.0470518165574747,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004902784587105218,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.17808691561222076,
|
|
"num_tokens": 24571299.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.1303181648254395,
|
|
"epoch": 1.0476474091721262,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000490266064398389,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.19052683115005492,
|
|
"num_tokens": 24584292.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.151078081130981,
|
|
"epoch": 1.0482430017867779,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004902536623650125,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.18685214966535568,
|
|
"num_tokens": 24597245.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.0795470714569095,
|
|
"epoch": 1.0488385944014293,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004902412526108371,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.20515020340681075,
|
|
"num_tokens": 24610388.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.167324638366699,
|
|
"epoch": 1.049434187016081,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004902288351363079,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.18265511691570283,
|
|
"num_tokens": 24625939.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.163259649276734,
|
|
"epoch": 1.0500297796307325,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004902164099418703,
|
|
"loss": 4.9139,
|
|
"mean_token_accuracy": 0.1957081601023674,
|
|
"num_tokens": 24641133.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.09255690574646,
|
|
"epoch": 1.0506253722453842,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00049020397702797,
|
|
"loss": 4.897,
|
|
"mean_token_accuracy": 0.18797782063484192,
|
|
"num_tokens": 24654555.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.109451103210449,
|
|
"epoch": 1.0512209648600357,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000490191536395053,
|
|
"loss": 4.9635,
|
|
"mean_token_accuracy": 0.19301121979951857,
|
|
"num_tokens": 24669048.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.123154973983764,
|
|
"epoch": 1.0518165574746874,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004901790880435655,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.1934168353676796,
|
|
"num_tokens": 24683420.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.1608202934265135,
|
|
"epoch": 1.0524121500893389,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004901666319739537,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.1815462276339531,
|
|
"num_tokens": 24696972.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.072604990005493,
|
|
"epoch": 1.0530077427039906,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004901541681866649,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.189915269613266,
|
|
"num_tokens": 24710581.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.077222204208374,
|
|
"epoch": 1.053603335318642,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004901416966821459,
|
|
"loss": 4.8736,
|
|
"mean_token_accuracy": 0.20124314576387406,
|
|
"num_tokens": 24723055.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.165861749649048,
|
|
"epoch": 1.0541989279332937,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000490129217460844,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.18604139983654022,
|
|
"num_tokens": 24738073.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.186701726913452,
|
|
"epoch": 1.0547945205479452,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004901167305232068,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.1842569038271904,
|
|
"num_tokens": 24751566.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.120365571975708,
|
|
"epoch": 1.0553901131625967,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004901042358696823,
|
|
"loss": 4.8781,
|
|
"mean_token_accuracy": 0.1934254825115204,
|
|
"num_tokens": 24765401.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.101422595977783,
|
|
"epoch": 1.0559857057772484,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004900917335007186,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.19462051540613173,
|
|
"num_tokens": 24779180.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.153604221343994,
|
|
"epoch": 1.0565812983918998,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004900792234167642,
|
|
"loss": 4.9809,
|
|
"mean_token_accuracy": 0.19155022352933884,
|
|
"num_tokens": 24794536.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.157957649230957,
|
|
"epoch": 1.0571768910065515,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004900667056182676,
|
|
"loss": 4.9541,
|
|
"mean_token_accuracy": 0.18901954889297484,
|
|
"num_tokens": 24809721.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.101894569396973,
|
|
"epoch": 1.057772483621203,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004900541801056781,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.18906707614660262,
|
|
"num_tokens": 24823818.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.181896829605103,
|
|
"epoch": 1.0583680762358547,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004900416468794446,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.19671599864959716,
|
|
"num_tokens": 24836028.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.107559156417847,
|
|
"epoch": 1.0589636688505062,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004900291059400171,
|
|
"loss": 4.9157,
|
|
"mean_token_accuracy": 0.1938898578286171,
|
|
"num_tokens": 24849957.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.082164525985718,
|
|
"epoch": 1.0595592614651579,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000490016557287845,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.18450929671525956,
|
|
"num_tokens": 24862123.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.182081842422486,
|
|
"epoch": 1.0601548540798094,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004900040009233787,
|
|
"loss": 4.9361,
|
|
"mean_token_accuracy": 0.19133677333593369,
|
|
"num_tokens": 24874584.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.235712194442749,
|
|
"epoch": 1.060750446694461,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004899914368470685,
|
|
"loss": 5.1239,
|
|
"mean_token_accuracy": 0.17538886219263078,
|
|
"num_tokens": 24890828.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.226597261428833,
|
|
"epoch": 1.0613460393091125,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004899788650593648,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.1876695692539215,
|
|
"num_tokens": 24905266.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.153964185714722,
|
|
"epoch": 1.0619416319237642,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004899662855607189,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.18806610703468324,
|
|
"num_tokens": 24918867.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.112710332870483,
|
|
"epoch": 1.0625372245384157,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004899536983515819,
|
|
"loss": 5.0085,
|
|
"mean_token_accuracy": 0.18515326529741288,
|
|
"num_tokens": 24934619.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.276426362991333,
|
|
"epoch": 1.0631328171530674,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004899411034324051,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.1806840181350708,
|
|
"num_tokens": 24950582.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.161322784423828,
|
|
"epoch": 1.0637284097677189,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004899285008036406,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.1885943666100502,
|
|
"num_tokens": 24964456.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.130282258987426,
|
|
"epoch": 1.0643240023823703,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048991589046574,
|
|
"loss": 4.9329,
|
|
"mean_token_accuracy": 0.19497232288122177,
|
|
"num_tokens": 24977443.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.064626407623291,
|
|
"epoch": 1.064919594997022,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004899032724191559,
|
|
"loss": 4.8393,
|
|
"mean_token_accuracy": 0.1996411919593811,
|
|
"num_tokens": 24989343.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.135550403594971,
|
|
"epoch": 1.0655151876116735,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004898906466643409,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.19274517744779587,
|
|
"num_tokens": 25004157.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.2030257225036625,
|
|
"epoch": 1.0661107802263252,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004898780132017478,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.18689849227666855,
|
|
"num_tokens": 25016292.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.180984687805176,
|
|
"epoch": 1.0667063728409767,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004898653720318296,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.1835171103477478,
|
|
"num_tokens": 25032374.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.179262113571167,
|
|
"epoch": 1.0673019654556284,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048985272315504,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.19111132770776748,
|
|
"num_tokens": 25045290.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.0683269023895265,
|
|
"epoch": 1.0678975580702799,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004898400665718325,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.18514718264341354,
|
|
"num_tokens": 25058733.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.084171390533447,
|
|
"epoch": 1.0684931506849316,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004898274022826611,
|
|
"loss": 4.9146,
|
|
"mean_token_accuracy": 0.19661027640104295,
|
|
"num_tokens": 25073274.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.154380369186401,
|
|
"epoch": 1.069088743299583,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004898147302879801,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.1920701652765274,
|
|
"num_tokens": 25088339.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.158627605438232,
|
|
"epoch": 1.0696843359142347,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004898020505882441,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.20376540273427962,
|
|
"num_tokens": 25100031.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.1950499534606935,
|
|
"epoch": 1.0702799285288862,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004897893631839076,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.18228566646575928,
|
|
"num_tokens": 25113070.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.155407857894898,
|
|
"epoch": 1.070875521143538,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000489776668075426,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.19103750437498093,
|
|
"num_tokens": 25126584.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.14116063117981,
|
|
"epoch": 1.0714711137581894,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004897639652632544,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.19633928686380386,
|
|
"num_tokens": 25139292.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.097061204910278,
|
|
"epoch": 1.072066706372841,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004897512547478487,
|
|
"loss": 4.9839,
|
|
"mean_token_accuracy": 0.18102959245443345,
|
|
"num_tokens": 25153590.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.072066706372841,
|
|
"eval_entropy": 4.887853504198846,
|
|
"eval_loss": 5.027402877807617,
|
|
"eval_mean_token_accuracy": 0.19576801751976758,
|
|
"eval_num_tokens": 25153590.0,
|
|
"eval_runtime": 24.5906,
|
|
"eval_samples_per_second": 1037.509,
|
|
"eval_steps_per_second": 129.724,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.130313968658447,
|
|
"epoch": 1.0726622989874925,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004897385365296645,
|
|
"loss": 5.0312,
|
|
"mean_token_accuracy": 0.181413035094738,
|
|
"num_tokens": 25168050.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.15574083328247,
|
|
"epoch": 1.073257891602144,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004897258106091582,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.19171320497989655,
|
|
"num_tokens": 25182650.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.1211694240570065,
|
|
"epoch": 1.0738534842167957,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004897130769867862,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.196321702003479,
|
|
"num_tokens": 25196264.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.059478521347046,
|
|
"epoch": 1.0744490768314472,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004897003356630052,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.18270889222621917,
|
|
"num_tokens": 25214240.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.249770593643189,
|
|
"epoch": 1.0750446694460989,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004896875866382723,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.18171207010746002,
|
|
"num_tokens": 25229866.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.20835919380188,
|
|
"epoch": 1.0756402620607504,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004896748299130447,
|
|
"loss": 5.0011,
|
|
"mean_token_accuracy": 0.18391937017440796,
|
|
"num_tokens": 25244046.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.163422155380249,
|
|
"epoch": 1.076235854675402,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048966206548778,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.18462022691965102,
|
|
"num_tokens": 25261180.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.149279832839966,
|
|
"epoch": 1.0768314472900535,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000489649293362936,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.18875399529933928,
|
|
"num_tokens": 25274905.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.102065849304199,
|
|
"epoch": 1.0774270399047052,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004896365135389709,
|
|
"loss": 4.8778,
|
|
"mean_token_accuracy": 0.19757312387228013,
|
|
"num_tokens": 25288236.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.1708392143249515,
|
|
"epoch": 1.0780226325193567,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000489623726016343,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.18660286366939544,
|
|
"num_tokens": 25301362.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.261985015869141,
|
|
"epoch": 1.0786182251340084,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000489610930795511,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.17946022599935532,
|
|
"num_tokens": 25316951.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.150081777572632,
|
|
"epoch": 1.0792138177486599,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000489598127876934,
|
|
"loss": 5.0061,
|
|
"mean_token_accuracy": 0.18795938938856124,
|
|
"num_tokens": 25330417.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.1319879531860355,
|
|
"epoch": 1.0798094103633116,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004895853172610709,
|
|
"loss": 4.9524,
|
|
"mean_token_accuracy": 0.19709673672914504,
|
|
"num_tokens": 25344857.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.119398975372315,
|
|
"epoch": 1.080405002977963,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004895724989483814,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.18856310993432998,
|
|
"num_tokens": 25359353.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.140283870697021,
|
|
"epoch": 1.0810005955926147,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004895596729393252,
|
|
"loss": 4.9758,
|
|
"mean_token_accuracy": 0.19203881174325943,
|
|
"num_tokens": 25373661.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.110469913482666,
|
|
"epoch": 1.0815961882072662,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004895468392343623,
|
|
"loss": 4.8548,
|
|
"mean_token_accuracy": 0.20248825401067733,
|
|
"num_tokens": 25387384.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.0478160858154295,
|
|
"epoch": 1.0821917808219177,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004895339978339534,
|
|
"loss": 4.8885,
|
|
"mean_token_accuracy": 0.19920784085989,
|
|
"num_tokens": 25400677.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.166805458068848,
|
|
"epoch": 1.0827873734365694,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004895211487385586,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.180427648127079,
|
|
"num_tokens": 25416345.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.1966465473175045,
|
|
"epoch": 1.0833829660512209,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000489508291948639,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.18672772347927094,
|
|
"num_tokens": 25430685.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.160430145263672,
|
|
"epoch": 1.0839785586658726,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004894954274646557,
|
|
"loss": 5.0004,
|
|
"mean_token_accuracy": 0.1857392519712448,
|
|
"num_tokens": 25444527.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.176412677764892,
|
|
"epoch": 1.084574151280524,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004894825552870703,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.19224816858768462,
|
|
"num_tokens": 25457556.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.1483722686767575,
|
|
"epoch": 1.0851697438951757,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004894696754163442,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.18894597440958022,
|
|
"num_tokens": 25471357.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.1687158107757565,
|
|
"epoch": 1.0857653365098272,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004894567878529397,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.18614188134670256,
|
|
"num_tokens": 25484443.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.26250581741333,
|
|
"epoch": 1.086360929124479,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004894438925973189,
|
|
"loss": 5.0093,
|
|
"mean_token_accuracy": 0.18872172087430955,
|
|
"num_tokens": 25497515.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.130481290817261,
|
|
"epoch": 1.0869565217391304,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 0.0004894309896499443,
|
|
"loss": 4.9092,
|
|
"mean_token_accuracy": 0.19429878741502762,
|
|
"num_tokens": 25512398.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 4.989810562133789,
|
|
"epoch": 1.087552114353782,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004894180790112787,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.20486121326684953,
|
|
"num_tokens": 25525339.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.149105501174927,
|
|
"epoch": 1.0881477069684335,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004894051606817851,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.18620843291282654,
|
|
"num_tokens": 25539622.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.320186185836792,
|
|
"epoch": 1.0887432995830852,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004893922346619272,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.1756857767701149,
|
|
"num_tokens": 25555066.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.101219177246094,
|
|
"epoch": 1.0893388921977367,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004893793009521684,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.19653569012880326,
|
|
"num_tokens": 25567324.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.059576892852784,
|
|
"epoch": 1.0899344848123884,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004893663595529725,
|
|
"loss": 4.8702,
|
|
"mean_token_accuracy": 0.1950229287147522,
|
|
"num_tokens": 25581530.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.133328628540039,
|
|
"epoch": 1.09053007742704,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000489353410464804,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.18317395001649855,
|
|
"num_tokens": 25594769.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.0507889747619625,
|
|
"epoch": 1.0911256700416916,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004893404536881271,
|
|
"loss": 4.9018,
|
|
"mean_token_accuracy": 0.19755921512842178,
|
|
"num_tokens": 25609212.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.136660814285278,
|
|
"epoch": 1.091721262656343,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004893274892234066,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.1822850689291954,
|
|
"num_tokens": 25624203.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.159630632400512,
|
|
"epoch": 1.0923168552709945,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004893145170711075,
|
|
"loss": 5.0381,
|
|
"mean_token_accuracy": 0.1848960518836975,
|
|
"num_tokens": 25639040.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.340586709976196,
|
|
"epoch": 1.0929124478856462,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004893015372316953,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.17826444804668426,
|
|
"num_tokens": 25653145.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.163386631011963,
|
|
"epoch": 1.0935080405002977,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004892885497056353,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.1904471516609192,
|
|
"num_tokens": 25666691.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.1215509414672855,
|
|
"epoch": 1.0941036331149494,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004892755544933934,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.19732676297426224,
|
|
"num_tokens": 25681140.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.088916444778443,
|
|
"epoch": 1.0946992257296009,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004892625515954357,
|
|
"loss": 4.863,
|
|
"mean_token_accuracy": 0.20079190880060196,
|
|
"num_tokens": 25695835.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.053756761550903,
|
|
"epoch": 1.0952948183442526,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004892495410122288,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.19291579425334932,
|
|
"num_tokens": 25710395.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.0799171924591064,
|
|
"epoch": 1.095890410958904,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004892365227442392,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.18915008306503295,
|
|
"num_tokens": 25724804.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.184023904800415,
|
|
"epoch": 1.0964860035735557,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004892234967919337,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.1938503786921501,
|
|
"num_tokens": 25737025.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.0828369617462155,
|
|
"epoch": 1.0970815961882072,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004892104631557797,
|
|
"loss": 4.9541,
|
|
"mean_token_accuracy": 0.19430125653743743,
|
|
"num_tokens": 25751737.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.102542352676392,
|
|
"epoch": 1.097677188802859,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004891974218362448,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.19255532324314117,
|
|
"num_tokens": 25764187.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.203891944885254,
|
|
"epoch": 1.0982727814175104,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004891843728337965,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.17358979135751723,
|
|
"num_tokens": 25778500.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.183661317825317,
|
|
"epoch": 1.098868374032162,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004891713161489031,
|
|
"loss": 5.06,
|
|
"mean_token_accuracy": 0.1875401958823204,
|
|
"num_tokens": 25791964.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.151712894439697,
|
|
"epoch": 1.0994639666468136,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004891582517820328,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.18670142590999603,
|
|
"num_tokens": 25806730.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.213738489151001,
|
|
"epoch": 1.1000595592614653,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004891451797336541,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.18909095823764802,
|
|
"num_tokens": 25821507.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.088689279556275,
|
|
"epoch": 1.1006551518761167,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004891321000042361,
|
|
"loss": 4.9091,
|
|
"mean_token_accuracy": 0.1938463643193245,
|
|
"num_tokens": 25834710.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.137584066390991,
|
|
"epoch": 1.1012507444907684,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004891190125942478,
|
|
"loss": 4.9638,
|
|
"mean_token_accuracy": 0.1876716822385788,
|
|
"num_tokens": 25849138.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.192215251922607,
|
|
"epoch": 1.10184633710542,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004891059175041586,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.188570336997509,
|
|
"num_tokens": 25862026.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.119067049026489,
|
|
"epoch": 1.1024419297200714,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004890928147344383,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.18188547641038894,
|
|
"num_tokens": 25875791.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.0985182762146,
|
|
"epoch": 1.103037522334723,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004890797042855569,
|
|
"loss": 4.9183,
|
|
"mean_token_accuracy": 0.19065024852752685,
|
|
"num_tokens": 25888648.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.062660789489746,
|
|
"epoch": 1.1036331149493745,
|
|
"grad_norm": 6.0625,
|
|
"learning_rate": 0.0004890665861579845,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.185217946767807,
|
|
"num_tokens": 25902307.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.1190821647644045,
|
|
"epoch": 1.1042287075640262,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004890534603521917,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.18851815164089203,
|
|
"num_tokens": 25915401.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.216704797744751,
|
|
"epoch": 1.1048243001786777,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004890403268686494,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.18536789268255233,
|
|
"num_tokens": 25929692.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.194955062866211,
|
|
"epoch": 1.1054198927933294,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004890271857078285,
|
|
"loss": 4.991,
|
|
"mean_token_accuracy": 0.19258683025836945,
|
|
"num_tokens": 25943789.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.175568342208862,
|
|
"epoch": 1.106015485407981,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004890140368702003,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.18250191062688828,
|
|
"num_tokens": 25958662.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.1393599033355715,
|
|
"epoch": 1.1066110780226326,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004890008803562368,
|
|
"loss": 4.9806,
|
|
"mean_token_accuracy": 0.18815995007753372,
|
|
"num_tokens": 25974176.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.129190587997437,
|
|
"epoch": 1.107206670637284,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004889877161664096,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.19756459593772888,
|
|
"num_tokens": 25988513.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.179361248016358,
|
|
"epoch": 1.1078022632519358,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004889745443011909,
|
|
"loss": 4.9248,
|
|
"mean_token_accuracy": 0.1916690796613693,
|
|
"num_tokens": 26002117.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.120261192321777,
|
|
"epoch": 1.1083978558665872,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004889613647610532,
|
|
"loss": 4.9578,
|
|
"mean_token_accuracy": 0.19227243661880494,
|
|
"num_tokens": 26016092.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.110382127761841,
|
|
"epoch": 1.108993448481239,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004889481775464692,
|
|
"loss": 4.9005,
|
|
"mean_token_accuracy": 0.1919640690088272,
|
|
"num_tokens": 26030237.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.068282890319824,
|
|
"epoch": 1.1095890410958904,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000488934982657912,
|
|
"loss": 4.8807,
|
|
"mean_token_accuracy": 0.1988028794527054,
|
|
"num_tokens": 26041848.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.10098032951355,
|
|
"epoch": 1.110184633710542,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004889217800958548,
|
|
"loss": 4.9357,
|
|
"mean_token_accuracy": 0.1961563780903816,
|
|
"num_tokens": 26056123.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.101327610015869,
|
|
"epoch": 1.1107802263251936,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004889085698607711,
|
|
"loss": 4.9277,
|
|
"mean_token_accuracy": 0.19511800557374953,
|
|
"num_tokens": 26071043.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.053564929962159,
|
|
"epoch": 1.111375818939845,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004888953519531349,
|
|
"loss": 4.884,
|
|
"mean_token_accuracy": 0.20050545632839203,
|
|
"num_tokens": 26083946.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.106979656219482,
|
|
"epoch": 1.1119714115544967,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048888212637342,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.1956620082259178,
|
|
"num_tokens": 26099631.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.094206142425537,
|
|
"epoch": 1.1125670041691482,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004888688931221012,
|
|
"loss": 4.8887,
|
|
"mean_token_accuracy": 0.1998849481344223,
|
|
"num_tokens": 26113613.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.039048480987549,
|
|
"epoch": 1.1131625967838,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004888556521996529,
|
|
"loss": 4.8427,
|
|
"mean_token_accuracy": 0.19407909363508224,
|
|
"num_tokens": 26127357.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.132419538497925,
|
|
"epoch": 1.1137581893984514,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048884240360655,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.19185114949941634,
|
|
"num_tokens": 26142087.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.138953971862793,
|
|
"epoch": 1.114353782013103,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004888291473432678,
|
|
"loss": 4.9601,
|
|
"mean_token_accuracy": 0.18592994213104247,
|
|
"num_tokens": 26157153.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.094040870666504,
|
|
"epoch": 1.1149493746277546,
|
|
"grad_norm": 2.625,
|
|
"learning_rate": 0.0004888158834102816,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.19643050581216812,
|
|
"num_tokens": 26170573.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.060034561157226,
|
|
"epoch": 1.1155449672424063,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004888026118080675,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.19408942013978958,
|
|
"num_tokens": 26185201.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.177839517593384,
|
|
"epoch": 1.1161405598570577,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004887893325371013,
|
|
"loss": 4.9885,
|
|
"mean_token_accuracy": 0.19422133415937423,
|
|
"num_tokens": 26199016.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.103407478332519,
|
|
"epoch": 1.1167361524717094,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004887760455978592,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.19731869101524352,
|
|
"num_tokens": 26213077.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.112622261047363,
|
|
"epoch": 1.117331745086361,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000488762750990818,
|
|
"loss": 4.9482,
|
|
"mean_token_accuracy": 0.19428687989711763,
|
|
"num_tokens": 26228281.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.191945505142212,
|
|
"epoch": 1.1179273377010126,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004887494487164546,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.18997853696346284,
|
|
"num_tokens": 26242258.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.184604120254517,
|
|
"epoch": 1.118522930315664,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004887361387752459,
|
|
"loss": 4.956,
|
|
"mean_token_accuracy": 0.18911240100860596,
|
|
"num_tokens": 26257028.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.105703639984131,
|
|
"epoch": 1.1191185229303158,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004887228211676694,
|
|
"loss": 4.9096,
|
|
"mean_token_accuracy": 0.19670521169900895,
|
|
"num_tokens": 26269965.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.129568767547608,
|
|
"epoch": 1.1197141155449672,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004887094958942029,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.19056240171194078,
|
|
"num_tokens": 26283833.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.1235586643219,
|
|
"epoch": 1.1203097081596187,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004886961629553242,
|
|
"loss": 4.923,
|
|
"mean_token_accuracy": 0.19256728738546372,
|
|
"num_tokens": 26296526.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.170863914489746,
|
|
"epoch": 1.1209053007742704,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004886828223515115,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.18437173515558242,
|
|
"num_tokens": 26311426.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.098204040527344,
|
|
"epoch": 1.121500893388922,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004886694740832434,
|
|
"loss": 4.9756,
|
|
"mean_token_accuracy": 0.1872018277645111,
|
|
"num_tokens": 26324260.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.136823558807373,
|
|
"epoch": 1.1220964860035736,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004886561181509988,
|
|
"loss": 4.9539,
|
|
"mean_token_accuracy": 0.19473805874586106,
|
|
"num_tokens": 26337964.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.113220691680908,
|
|
"epoch": 1.122692078618225,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004886427545552567,
|
|
"loss": 4.9682,
|
|
"mean_token_accuracy": 0.18613171577453613,
|
|
"num_tokens": 26352293.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.115389251708985,
|
|
"epoch": 1.1232876712328768,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004886293832964961,
|
|
"loss": 4.9343,
|
|
"mean_token_accuracy": 0.18910593539476395,
|
|
"num_tokens": 26368979.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.1473418235778805,
|
|
"epoch": 1.1238832638475282,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000488616004375197,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.19679009169340134,
|
|
"num_tokens": 26382230.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.113736391067505,
|
|
"epoch": 1.12447885646218,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000488602617791839,
|
|
"loss": 4.9153,
|
|
"mean_token_accuracy": 0.19668288975954057,
|
|
"num_tokens": 26396046.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.11190390586853,
|
|
"epoch": 1.1250744490768314,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004885892235469026,
|
|
"loss": 4.9177,
|
|
"mean_token_accuracy": 0.18485175222158431,
|
|
"num_tokens": 26408774.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.117647361755371,
|
|
"epoch": 1.125670041691483,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.000488575821640868,
|
|
"loss": 4.9286,
|
|
"mean_token_accuracy": 0.19223731607198716,
|
|
"num_tokens": 26423261.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.139785718917847,
|
|
"epoch": 1.1262656343061346,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004885624120742158,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.1983252003788948,
|
|
"num_tokens": 26435834.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.157489061355591,
|
|
"epoch": 1.1268612269207863,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004885489948474272,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.18453088849782945,
|
|
"num_tokens": 26450522.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.044536495208741,
|
|
"epoch": 1.1274568195354377,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004885355699609834,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.18538135886192322,
|
|
"num_tokens": 26465375.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.096642208099365,
|
|
"epoch": 1.1280524121500894,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004885221374153657,
|
|
"loss": 4.9569,
|
|
"mean_token_accuracy": 0.1856625571846962,
|
|
"num_tokens": 26477408.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.141009140014648,
|
|
"epoch": 1.128648004764741,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004885086972110563,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.1981191709637642,
|
|
"num_tokens": 26490057.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.141994905471802,
|
|
"epoch": 1.1292435973793924,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000488495249348537,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.18711912781000137,
|
|
"num_tokens": 26503020.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.13955397605896,
|
|
"epoch": 1.129839189994044,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 0.0004884817938282902,
|
|
"loss": 4.9236,
|
|
"mean_token_accuracy": 0.19214523881673812,
|
|
"num_tokens": 26517527.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.227650499343872,
|
|
"epoch": 1.1304347826086956,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004884683306507987,
|
|
"loss": 4.986,
|
|
"mean_token_accuracy": 0.1959200382232666,
|
|
"num_tokens": 26532101.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.1417945384979244,
|
|
"epoch": 1.1310303752233473,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000488454859816545,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.1829814925789833,
|
|
"num_tokens": 26544232.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.097066593170166,
|
|
"epoch": 1.1316259678379987,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004884413813260127,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.19080306887626647,
|
|
"num_tokens": 26558731.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.159481763839722,
|
|
"epoch": 1.1322215604526504,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004884278951796851,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.1827486351132393,
|
|
"num_tokens": 26572784.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.124829959869385,
|
|
"epoch": 1.132817153067302,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004884144013780459,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.18925589174032212,
|
|
"num_tokens": 26585847.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.132622718811035,
|
|
"epoch": 1.1334127456819536,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004884008999215792,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.18583379834890365,
|
|
"num_tokens": 26600996.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.226812505722046,
|
|
"epoch": 1.134008338296605,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000488387390810769,
|
|
"loss": 5.0767,
|
|
"mean_token_accuracy": 0.17498932480812074,
|
|
"num_tokens": 26613550.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.1659623146057125,
|
|
"epoch": 1.1346039309112568,
|
|
"grad_norm": 2.46875,
|
|
"learning_rate": 0.0004883738740461001,
|
|
"loss": 5.0014,
|
|
"mean_token_accuracy": 0.18704167753458023,
|
|
"num_tokens": 26627453.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.106309032440185,
|
|
"epoch": 1.1351995235259082,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004883603496280573,
|
|
"loss": 5.019,
|
|
"mean_token_accuracy": 0.1868916630744934,
|
|
"num_tokens": 26642659.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.147479009628296,
|
|
"epoch": 1.13579511614056,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004883468175571256,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.18681011348962784,
|
|
"num_tokens": 26655995.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.164314317703247,
|
|
"epoch": 1.1363907087552114,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004883332778337905,
|
|
"loss": 4.8875,
|
|
"mean_token_accuracy": 0.19459299147129058,
|
|
"num_tokens": 26669619.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.1339164733886715,
|
|
"epoch": 1.1369863013698631,
|
|
"grad_norm": 3.359375,
|
|
"learning_rate": 0.0004883197304585376,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.18508109897375108,
|
|
"num_tokens": 26684168.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.173122787475586,
|
|
"epoch": 1.1375818939845146,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004883061754318528,
|
|
"loss": 4.9162,
|
|
"mean_token_accuracy": 0.19490453451871873,
|
|
"num_tokens": 26696891.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.1964850425720215,
|
|
"epoch": 1.138177486599166,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004882926127542222,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.18680599629878997,
|
|
"num_tokens": 26712523.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.123870086669922,
|
|
"epoch": 1.1387730792138178,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004882790424261325,
|
|
"loss": 5.0,
|
|
"mean_token_accuracy": 0.19042570292949676,
|
|
"num_tokens": 26726393.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.140379953384399,
|
|
"epoch": 1.1393686718284692,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004882654644480702,
|
|
"loss": 4.9914,
|
|
"mean_token_accuracy": 0.1831674501299858,
|
|
"num_tokens": 26742567.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.1835424423217775,
|
|
"epoch": 1.139964264443121,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004882518788205225,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.18139970749616624,
|
|
"num_tokens": 26755052.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.03087306022644,
|
|
"epoch": 1.1405598570577724,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048823828554397664,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.20256316810846328,
|
|
"num_tokens": 26767194.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.050366544723511,
|
|
"epoch": 1.141155449672424,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004882246846189202,
|
|
"loss": 4.9552,
|
|
"mean_token_accuracy": 0.18831042498350142,
|
|
"num_tokens": 26779744.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.229615068435669,
|
|
"epoch": 1.1417510422870756,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048821107604584096,
|
|
"loss": 5.0666,
|
|
"mean_token_accuracy": 0.18170764297246933,
|
|
"num_tokens": 26793413.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.208401536941528,
|
|
"epoch": 1.1423466349017273,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004881974598252271,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.18971624374389648,
|
|
"num_tokens": 26809168.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.17251672744751,
|
|
"epoch": 1.1429422275163788,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000488183835957567,
|
|
"loss": 4.9415,
|
|
"mean_token_accuracy": 0.1936861827969551,
|
|
"num_tokens": 26821597.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.163082122802734,
|
|
"epoch": 1.1435378201310304,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048817020444334936,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.18788497447967528,
|
|
"num_tokens": 26835971.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.146780920028687,
|
|
"epoch": 1.144133412745682,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048815656528306304,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.19325950145721435,
|
|
"num_tokens": 26849787.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.186962985992432,
|
|
"epoch": 1.1447290053603336,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004881429184771973,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.1848955988883972,
|
|
"num_tokens": 26863886.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.212792778015137,
|
|
"epoch": 1.145324597974985,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004881292640262416,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.19239893108606337,
|
|
"num_tokens": 26877249.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.17923412322998,
|
|
"epoch": 1.1459201905896368,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004881156019306857,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.18602932393550872,
|
|
"num_tokens": 26891882.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.257860326766968,
|
|
"epoch": 1.1465157832042883,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004881019321910198,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.1896733194589615,
|
|
"num_tokens": 26907990.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.107918930053711,
|
|
"epoch": 1.1471113758189397,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048808825480773396,
|
|
"loss": 4.9122,
|
|
"mean_token_accuracy": 0.19305707067251204,
|
|
"num_tokens": 26922302.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.164584016799926,
|
|
"epoch": 1.1477069684335914,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004880745697813189,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.18972861021757126,
|
|
"num_tokens": 26935849.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.27087435722351,
|
|
"epoch": 1.148302561048243,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004880608771122654,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.17289034724235536,
|
|
"num_tokens": 26949413.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.246993446350098,
|
|
"epoch": 1.1488981536628946,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048804717680106475,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.18341839015483857,
|
|
"num_tokens": 26963901.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.0627494812011715,
|
|
"epoch": 1.149493746277546,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004880334688482082,
|
|
"loss": 4.8993,
|
|
"mean_token_accuracy": 0.19487012028694153,
|
|
"num_tokens": 26977963.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.266376876831055,
|
|
"epoch": 1.1500893388921978,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004880197532541875,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.1782903254032135,
|
|
"num_tokens": 26992282.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.144223308563232,
|
|
"epoch": 1.1506849315068493,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004880060300194947,
|
|
"loss": 4.9432,
|
|
"mean_token_accuracy": 0.19864037185907363,
|
|
"num_tokens": 27006397.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.122386884689331,
|
|
"epoch": 1.151280524121501,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004879922991446218,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.1914861708879471,
|
|
"num_tokens": 27021030.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.122970008850098,
|
|
"epoch": 1.1518761167361524,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048797856063006144,
|
|
"loss": 4.8768,
|
|
"mean_token_accuracy": 0.18842388242483138,
|
|
"num_tokens": 27034446.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.163775777816772,
|
|
"epoch": 1.1524717093508041,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048796481447630646,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.18561324328184128,
|
|
"num_tokens": 27046748.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.1291553497314455,
|
|
"epoch": 1.1530673019654556,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048795106068384985,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.18840519934892655,
|
|
"num_tokens": 27060253.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.118038511276245,
|
|
"epoch": 1.1536628945801073,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004879372992531849,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.1998577132821083,
|
|
"num_tokens": 27072877.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.167638778686523,
|
|
"epoch": 1.1542584871947588,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004879235301848052,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.18903363794088363,
|
|
"num_tokens": 27085396.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.13258171081543,
|
|
"epoch": 1.1548540798094105,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004879097534792047,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.19529889076948165,
|
|
"num_tokens": 27100810.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.15435562133789,
|
|
"epoch": 1.155449672424062,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004878959691368776,
|
|
"loss": 4.9837,
|
|
"mean_token_accuracy": 0.1900956153869629,
|
|
"num_tokens": 27115704.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.072057485580444,
|
|
"epoch": 1.1560452650387134,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004878821771583181,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.19985717982053758,
|
|
"num_tokens": 27128500.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.123120641708374,
|
|
"epoch": 1.156640857653365,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.00048786837754402114,
|
|
"loss": 4.9157,
|
|
"mean_token_accuracy": 0.1926003262400627,
|
|
"num_tokens": 27141259.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.136770820617675,
|
|
"epoch": 1.1572364502680166,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004878545702944815,
|
|
"loss": 4.9487,
|
|
"mean_token_accuracy": 0.1905627578496933,
|
|
"num_tokens": 27155355.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.139217185974121,
|
|
"epoch": 1.1578320428826683,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048784075541019454,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.19378303438425065,
|
|
"num_tokens": 27170044.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.135121631622314,
|
|
"epoch": 1.1584276354973198,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004878269328916557,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.1872600570321083,
|
|
"num_tokens": 27186018.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.013774871826172,
|
|
"epoch": 1.1590232281119714,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004878131027393609,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.19791895300149917,
|
|
"num_tokens": 27200336.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.138242435455322,
|
|
"epoch": 1.159618820726623,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000487799264953806,
|
|
"loss": 4.9715,
|
|
"mean_token_accuracy": 0.18922825157642365,
|
|
"num_tokens": 27214941.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.102726602554322,
|
|
"epoch": 1.1602144133412746,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048778541953548753,
|
|
"loss": 4.9015,
|
|
"mean_token_accuracy": 0.19791963547468186,
|
|
"num_tokens": 27228441.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.01713342666626,
|
|
"epoch": 1.160810005955926,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000487771566484902,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.19838908165693284,
|
|
"num_tokens": 27244524.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.178373575210571,
|
|
"epoch": 1.1614055985705778,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048775770580254636,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.18931414186954498,
|
|
"num_tokens": 27259109.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.156593465805054,
|
|
"epoch": 1.1620011911852293,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048774383748891774,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.1916480243206024,
|
|
"num_tokens": 27273746.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.22333927154541,
|
|
"epoch": 1.162596783799881,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048772996154451356,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.1904100701212883,
|
|
"num_tokens": 27288414.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.131468009948731,
|
|
"epoch": 1.1631923764145324,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004877160779698315,
|
|
"loss": 5.0065,
|
|
"mean_token_accuracy": 0.18465885221958162,
|
|
"num_tokens": 27302274.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.203831624984741,
|
|
"epoch": 1.1637879690291841,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048770218676536957,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.18361999690532685,
|
|
"num_tokens": 27316960.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.203382110595703,
|
|
"epoch": 1.1643835616438356,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048768828793162614,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.18757408261299133,
|
|
"num_tokens": 27331861.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.133708572387695,
|
|
"epoch": 1.164979154258487,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004876743814690995,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.1914074718952179,
|
|
"num_tokens": 27345248.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.151339673995972,
|
|
"epoch": 1.1655747468731388,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004876604673782887,
|
|
"loss": 4.9364,
|
|
"mean_token_accuracy": 0.1914597660303116,
|
|
"num_tokens": 27359579.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.063805866241455,
|
|
"epoch": 1.1661703394877905,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004876465456596926,
|
|
"loss": 4.9165,
|
|
"mean_token_accuracy": 0.19451852291822433,
|
|
"num_tokens": 27374595.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.042675638198853,
|
|
"epoch": 1.166765932102442,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048763261631381075,
|
|
"loss": 4.8576,
|
|
"mean_token_accuracy": 0.20286153107881547,
|
|
"num_tokens": 27386446.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.132558536529541,
|
|
"epoch": 1.1673615247170934,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004876186793411426,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.18624312281608582,
|
|
"num_tokens": 27400307.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.095197248458862,
|
|
"epoch": 1.1679571173317451,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048760473474218814,
|
|
"loss": 4.9033,
|
|
"mean_token_accuracy": 0.1958324730396271,
|
|
"num_tokens": 27412495.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.162922334671021,
|
|
"epoch": 1.1685527099463966,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048759078251744747,
|
|
"loss": 5.0559,
|
|
"mean_token_accuracy": 0.1798691987991333,
|
|
"num_tokens": 27426201.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.2344578266143795,
|
|
"epoch": 1.1691483025610483,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048757682266742115,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.188311567902565,
|
|
"num_tokens": 27440418.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.048924589157105,
|
|
"epoch": 1.1697438951756998,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004875628551926098,
|
|
"loss": 4.7997,
|
|
"mean_token_accuracy": 0.21217274963855742,
|
|
"num_tokens": 27452756.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.020747137069702,
|
|
"epoch": 1.1703394877903515,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004875488800935144,
|
|
"loss": 4.8395,
|
|
"mean_token_accuracy": 0.20147184729576112,
|
|
"num_tokens": 27465245.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.092300081253052,
|
|
"epoch": 1.170935080405003,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004875348973706363,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.19695802181959152,
|
|
"num_tokens": 27480054.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.271135473251343,
|
|
"epoch": 1.1715306730196546,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000487520907024477,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.1720071017742157,
|
|
"num_tokens": 27493963.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.175400352478027,
|
|
"epoch": 1.172126265634306,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048750690905553833,
|
|
"loss": 5.036,
|
|
"mean_token_accuracy": 0.19252091348171235,
|
|
"num_tokens": 27508072.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.082281112670898,
|
|
"epoch": 1.1727218582489578,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004874929034643223,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.19611283987760544,
|
|
"num_tokens": 27520354.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.071269464492798,
|
|
"epoch": 1.1733174508636093,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004874788902513314,
|
|
"loss": 4.9299,
|
|
"mean_token_accuracy": 0.19816491156816482,
|
|
"num_tokens": 27534486.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.178412389755249,
|
|
"epoch": 1.1739130434782608,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004874648694170681,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.18535427004098892,
|
|
"num_tokens": 27548821.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.213463354110718,
|
|
"epoch": 1.1745086360929125,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048745084096203536,
|
|
"loss": 4.9569,
|
|
"mean_token_accuracy": 0.1943567216396332,
|
|
"num_tokens": 27561534.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.059633111953735,
|
|
"epoch": 1.1751042287075641,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004874368048867364,
|
|
"loss": 4.88,
|
|
"mean_token_accuracy": 0.19357097446918486,
|
|
"num_tokens": 27573858.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.096966028213501,
|
|
"epoch": 1.1756998213222156,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048742276119167463,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.18670955151319504,
|
|
"num_tokens": 27588376.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.135232734680176,
|
|
"epoch": 1.176295413936867,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048740870987735383,
|
|
"loss": 4.835,
|
|
"mean_token_accuracy": 0.19306504279375075,
|
|
"num_tokens": 27601233.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.041066646575928,
|
|
"epoch": 1.1768910065515188,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004873946509442779,
|
|
"loss": 4.9097,
|
|
"mean_token_accuracy": 0.19249315112829207,
|
|
"num_tokens": 27614878.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.105250072479248,
|
|
"epoch": 1.1774865991661703,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004873805843929512,
|
|
"loss": 4.9435,
|
|
"mean_token_accuracy": 0.19221719801425935,
|
|
"num_tokens": 27629588.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.1124368667602536,
|
|
"epoch": 1.178082191780822,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004873665102238783,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.20171712040901185,
|
|
"num_tokens": 27643068.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.010074424743652,
|
|
"epoch": 1.1786777843954734,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048735242843756394,
|
|
"loss": 4.9467,
|
|
"mean_token_accuracy": 0.19214946776628494,
|
|
"num_tokens": 27657404.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.086208963394165,
|
|
"epoch": 1.1792733770101251,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004873383390345132,
|
|
"loss": 4.8611,
|
|
"mean_token_accuracy": 0.202032570540905,
|
|
"num_tokens": 27672145.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.176962661743164,
|
|
"epoch": 1.1798689696247766,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048732424201523156,
|
|
"loss": 5.0101,
|
|
"mean_token_accuracy": 0.18543822467327117,
|
|
"num_tokens": 27686542.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.079168224334717,
|
|
"epoch": 1.1804645622394283,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004873101373802245,
|
|
"loss": 4.9046,
|
|
"mean_token_accuracy": 0.20310645252466203,
|
|
"num_tokens": 27700783.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.159026002883911,
|
|
"epoch": 1.1810601548540798,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004872960251299981,
|
|
"loss": 5.0011,
|
|
"mean_token_accuracy": 0.18216738402843474,
|
|
"num_tokens": 27714604.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.182132005691528,
|
|
"epoch": 1.1816557474687315,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048728190526505834,
|
|
"loss": 4.9617,
|
|
"mean_token_accuracy": 0.1926859587430954,
|
|
"num_tokens": 27728690.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.078340530395508,
|
|
"epoch": 1.182251340083383,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048726777778591184,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.19153549075126647,
|
|
"num_tokens": 27740603.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.057116413116455,
|
|
"epoch": 1.1828469326980344,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004872536426930653,
|
|
"loss": 4.8939,
|
|
"mean_token_accuracy": 0.20472517609596252,
|
|
"num_tokens": 27753541.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.114748525619507,
|
|
"epoch": 1.1834425253126861,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004872394999870256,
|
|
"loss": 4.8999,
|
|
"mean_token_accuracy": 0.19722477495670318,
|
|
"num_tokens": 27766459.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.172559690475464,
|
|
"epoch": 1.1840381179273378,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048722534966830027,
|
|
"loss": 5.0816,
|
|
"mean_token_accuracy": 0.18780736923217772,
|
|
"num_tokens": 27779427.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.182930946350098,
|
|
"epoch": 1.1846337105419893,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048721119173739667,
|
|
"loss": 5.0008,
|
|
"mean_token_accuracy": 0.187907837331295,
|
|
"num_tokens": 27793075.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.103871154785156,
|
|
"epoch": 1.1852293031566408,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048719702619482255,
|
|
"loss": 4.9292,
|
|
"mean_token_accuracy": 0.19401364773511887,
|
|
"num_tokens": 27807738.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.186120796203613,
|
|
"epoch": 1.1858248957712925,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048718285304108613,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.18356092721223832,
|
|
"num_tokens": 27823047.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.111335897445679,
|
|
"epoch": 1.186420488385944,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004871686722766958,
|
|
"loss": 4.8476,
|
|
"mean_token_accuracy": 0.19420154094696046,
|
|
"num_tokens": 27837918.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.032206058502197,
|
|
"epoch": 1.1870160810005956,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048715448390216015,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.19023932814598082,
|
|
"num_tokens": 27851649.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.121145153045655,
|
|
"epoch": 1.187611673615247,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048714028791798817,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.19567328244447707,
|
|
"num_tokens": 27863579.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.152437925338745,
|
|
"epoch": 1.1882072662298988,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004871260843246889,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.19338561594486237,
|
|
"num_tokens": 27877526.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.108931398391723,
|
|
"epoch": 1.1888028588445503,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048711187312277187,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.19387413561344147,
|
|
"num_tokens": 27890425.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.182053327560425,
|
|
"epoch": 1.189398451459202,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048709765431274686,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.19469887167215347,
|
|
"num_tokens": 27903247.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.115084934234619,
|
|
"epoch": 1.1899940440738535,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004870834278951238,
|
|
"loss": 4.9695,
|
|
"mean_token_accuracy": 0.1902052119374275,
|
|
"num_tokens": 27916387.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.120326328277588,
|
|
"epoch": 1.1905896366885051,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004870691938704131,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.1921469748020172,
|
|
"num_tokens": 27930647.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.0975213050842285,
|
|
"epoch": 1.1911852293031566,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004870549522391252,
|
|
"loss": 4.9043,
|
|
"mean_token_accuracy": 0.1979265034198761,
|
|
"num_tokens": 27943881.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.104777860641479,
|
|
"epoch": 1.191780821917808,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048704070300177094,
|
|
"loss": 4.9054,
|
|
"mean_token_accuracy": 0.19914431869983673,
|
|
"num_tokens": 27958428.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.039322853088379,
|
|
"epoch": 1.1923764145324598,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048702644615886137,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.19736329466104507,
|
|
"num_tokens": 27972342.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.162056016921997,
|
|
"epoch": 1.1929720071471115,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004870121817109079,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.1893478214740753,
|
|
"num_tokens": 27986153.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.159114074707031,
|
|
"epoch": 1.193567599761763,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048699790965842224,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.18605547100305558,
|
|
"num_tokens": 27999375.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.1381758689880375,
|
|
"epoch": 1.1941631923764144,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004869836300019162,
|
|
"loss": 5.0134,
|
|
"mean_token_accuracy": 0.18730900734663009,
|
|
"num_tokens": 28014309.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.1078918933868405,
|
|
"epoch": 1.1947587849910661,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004869693427419021,
|
|
"loss": 4.8807,
|
|
"mean_token_accuracy": 0.19596084356307983,
|
|
"num_tokens": 28027779.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.100890588760376,
|
|
"epoch": 1.1953543776057176,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004869550478788922,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.1872792586684227,
|
|
"num_tokens": 28043500.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.184985017776489,
|
|
"epoch": 1.1959499702203693,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048694074541339946,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.19313663840293885,
|
|
"num_tokens": 28058561.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.1045286655426025,
|
|
"epoch": 1.1965455628350208,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048692643534593665,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.20299677103757857,
|
|
"num_tokens": 28072409.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.178034973144531,
|
|
"epoch": 1.1971411554496725,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004869121176770173,
|
|
"loss": 5.0292,
|
|
"mean_token_accuracy": 0.18986198902130128,
|
|
"num_tokens": 28085164.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.0720662593841555,
|
|
"epoch": 1.197736748064324,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048689779240715484,
|
|
"loss": 4.9367,
|
|
"mean_token_accuracy": 0.19218358099460603,
|
|
"num_tokens": 28099908.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.185003328323364,
|
|
"epoch": 1.1983323406789756,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048688345953686296,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.188821941614151,
|
|
"num_tokens": 28114558.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.177262449264527,
|
|
"epoch": 1.1989279332936271,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048686911906665597,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.19253239184617996,
|
|
"num_tokens": 28129468.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.117025375366211,
|
|
"epoch": 1.1995235259082788,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048685477099704816,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.19764088094234467,
|
|
"num_tokens": 28141810.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.092833757400513,
|
|
"epoch": 1.2001191185229303,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048684041532855415,
|
|
"loss": 4.924,
|
|
"mean_token_accuracy": 0.19605555832386018,
|
|
"num_tokens": 28154848.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.148453426361084,
|
|
"epoch": 1.2007147111375818,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004868260520616889,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.19599180221557616,
|
|
"num_tokens": 28168625.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.12807183265686,
|
|
"epoch": 1.2013103037522335,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048681168119696757,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.18031271398067475,
|
|
"num_tokens": 28183551.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.1816915512084964,
|
|
"epoch": 1.2019058963668852,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004867973027349056,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.1783999353647232,
|
|
"num_tokens": 28197839.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.18011212348938,
|
|
"epoch": 1.2025014889815366,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004867829166760188,
|
|
"loss": 4.8555,
|
|
"mean_token_accuracy": 0.19980338513851165,
|
|
"num_tokens": 28210662.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.080910158157349,
|
|
"epoch": 1.2030970815961881,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048676852302082305,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.18727964609861375,
|
|
"num_tokens": 28225553.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.079334163665772,
|
|
"epoch": 1.2036926742108398,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004867541217698347,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.19395116120576858,
|
|
"num_tokens": 28239732.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.071263456344605,
|
|
"epoch": 1.2042882668254913,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048673971292357025,
|
|
"loss": 4.8669,
|
|
"mean_token_accuracy": 0.19971770346164702,
|
|
"num_tokens": 28254929.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.161974143981934,
|
|
"epoch": 1.204883859440143,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004867252964825467,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.18565506041049956,
|
|
"num_tokens": 28272111.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.276380586624145,
|
|
"epoch": 1.2054794520547945,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048671087244728093,
|
|
"loss": 5.0385,
|
|
"mean_token_accuracy": 0.182584448158741,
|
|
"num_tokens": 28286533.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.156871557235718,
|
|
"epoch": 1.2060750446694462,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048669644081829035,
|
|
"loss": 5.0399,
|
|
"mean_token_accuracy": 0.1839819595217705,
|
|
"num_tokens": 28299272.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.0473103523254395,
|
|
"epoch": 1.2066706372840976,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048668200159609267,
|
|
"loss": 4.9671,
|
|
"mean_token_accuracy": 0.19069107472896576,
|
|
"num_tokens": 28316388.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.155528020858765,
|
|
"epoch": 1.2072662298987493,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048666755478120576,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.1902372345328331,
|
|
"num_tokens": 28330575.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.144584846496582,
|
|
"epoch": 1.2078618225134008,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048665310037414777,
|
|
"loss": 4.9038,
|
|
"mean_token_accuracy": 0.1978926971554756,
|
|
"num_tokens": 28343678.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.175637292861938,
|
|
"epoch": 1.2084574151280525,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004866386383754373,
|
|
"loss": 4.9849,
|
|
"mean_token_accuracy": 0.18579451888799667,
|
|
"num_tokens": 28357401.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.094144344329834,
|
|
"epoch": 1.209053007742704,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004866241687855929,
|
|
"loss": 4.89,
|
|
"mean_token_accuracy": 0.1971745252609253,
|
|
"num_tokens": 28370676.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.17147741317749,
|
|
"epoch": 1.2096486003573557,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048660969160513367,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.1869088366627693,
|
|
"num_tokens": 28385167.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.11931414604187,
|
|
"epoch": 1.2102441929720071,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004865952068345788,
|
|
"loss": 4.843,
|
|
"mean_token_accuracy": 0.19426177591085433,
|
|
"num_tokens": 28399940.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.11419415473938,
|
|
"epoch": 1.2108397855866588,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048658071447444794,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.1848515748977661,
|
|
"num_tokens": 28413525.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.021789264678955,
|
|
"epoch": 1.2114353782013103,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004865662145252609,
|
|
"loss": 4.8256,
|
|
"mean_token_accuracy": 0.20302426367998122,
|
|
"num_tokens": 28428273.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.143552207946778,
|
|
"epoch": 1.2120309708159618,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048655170698753774,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.1920157864689827,
|
|
"num_tokens": 28442030.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.167579078674317,
|
|
"epoch": 1.2126265634306135,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048653719186179874,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.1804181754589081,
|
|
"num_tokens": 28457514.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.126653718948364,
|
|
"epoch": 1.213222156045265,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004865226691485646,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.19119589179754257,
|
|
"num_tokens": 28471833.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.14599838256836,
|
|
"epoch": 1.2138177486599167,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048650813884835634,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.19054916352033616,
|
|
"num_tokens": 28486769.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.063129949569702,
|
|
"epoch": 1.2144133412745681,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004864936009616949,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.19538177847862243,
|
|
"num_tokens": 28501668.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.199819564819336,
|
|
"epoch": 1.2150089338892198,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000486479055489102,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.1944701924920082,
|
|
"num_tokens": 28515844.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.094656229019165,
|
|
"epoch": 1.2156045265038713,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004864645024310991,
|
|
"loss": 4.9141,
|
|
"mean_token_accuracy": 0.19414029866456986,
|
|
"num_tokens": 28531910.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.132700443267822,
|
|
"epoch": 1.216200119118523,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004864499417882084,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.1924610286951065,
|
|
"num_tokens": 28547044.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.1448201656341555,
|
|
"epoch": 1.2167957117331745,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000486435373560952,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.19353503733873367,
|
|
"num_tokens": 28560684.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.164681768417358,
|
|
"epoch": 1.2173913043478262,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048642079774985255,
|
|
"loss": 4.9472,
|
|
"mean_token_accuracy": 0.1909800112247467,
|
|
"num_tokens": 28574889.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.087970733642578,
|
|
"epoch": 1.2179868969624776,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048640621435543286,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.19364268630743026,
|
|
"num_tokens": 28588740.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.153825759887695,
|
|
"epoch": 1.2185824895771293,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.000486391623378216,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.18476815670728683,
|
|
"num_tokens": 28601908.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.173853969573974,
|
|
"epoch": 1.2191780821917808,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004863770248187253,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.18426222056150438,
|
|
"num_tokens": 28617025.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.1907695770263675,
|
|
"epoch": 1.2197736748064325,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004863624186774844,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.17696938067674636,
|
|
"num_tokens": 28630432.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.152749347686767,
|
|
"epoch": 1.220369267421084,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004863478049550171,
|
|
"loss": 5.0234,
|
|
"mean_token_accuracy": 0.18725897371768951,
|
|
"num_tokens": 28644815.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.137101459503174,
|
|
"epoch": 1.2209648600357355,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048633318365184783,
|
|
"loss": 4.9508,
|
|
"mean_token_accuracy": 0.19041585624217988,
|
|
"num_tokens": 28658368.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.073555183410645,
|
|
"epoch": 1.2215604526503872,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048631855476850074,
|
|
"loss": 4.882,
|
|
"mean_token_accuracy": 0.1970379814505577,
|
|
"num_tokens": 28672934.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.14451494216919,
|
|
"epoch": 1.2221560452650386,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048630391830550076,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.18917714506387712,
|
|
"num_tokens": 28688855.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.1540436267852785,
|
|
"epoch": 1.2227516378796903,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004862892742633727,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.19406917840242385,
|
|
"num_tokens": 28703184.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.068678951263427,
|
|
"epoch": 1.2233472304943418,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000486274622642642,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.1956460565328598,
|
|
"num_tokens": 28718237.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.120703172683716,
|
|
"epoch": 1.2239428231089935,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048625996344383405,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.1962318792939186,
|
|
"num_tokens": 28731911.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.134293937683106,
|
|
"epoch": 1.224538415723645,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004862452966674747,
|
|
"loss": 4.9312,
|
|
"mean_token_accuracy": 0.1980457827448845,
|
|
"num_tokens": 28744844.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.21360216140747,
|
|
"epoch": 1.2251340083382967,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004862306223140901,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.19015358984470368,
|
|
"num_tokens": 28761011.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.194985723495483,
|
|
"epoch": 1.2257296009529481,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004862159403842064,
|
|
"loss": 5.0052,
|
|
"mean_token_accuracy": 0.18585200905799865,
|
|
"num_tokens": 28775425.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.099919366836548,
|
|
"epoch": 1.2263251935675998,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048620125087835045,
|
|
"loss": 4.947,
|
|
"mean_token_accuracy": 0.1969999298453331,
|
|
"num_tokens": 28790054.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.132819414138794,
|
|
"epoch": 1.2269207861822513,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004861865537970489,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.18250067830085753,
|
|
"num_tokens": 28805604.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.034299325942993,
|
|
"epoch": 1.227516378796903,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004861718491408291,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.1966621145606041,
|
|
"num_tokens": 28820986.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.172768545150757,
|
|
"epoch": 1.2281119714115545,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004861571369102184,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.18533677011728286,
|
|
"num_tokens": 28836305.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.11511549949646,
|
|
"epoch": 1.2287075640262062,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004861424171057445,
|
|
"loss": 4.9557,
|
|
"mean_token_accuracy": 0.1933588907122612,
|
|
"num_tokens": 28849303.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.217194700241089,
|
|
"epoch": 1.2293031566408577,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004861276897279354,
|
|
"loss": 4.8921,
|
|
"mean_token_accuracy": 0.19045213609933853,
|
|
"num_tokens": 28863682.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.055678033828736,
|
|
"epoch": 1.2298987492555091,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004861129547773194,
|
|
"loss": 4.8746,
|
|
"mean_token_accuracy": 0.1971342757344246,
|
|
"num_tokens": 28878533.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.038612318038941,
|
|
"epoch": 1.2304943418701608,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048609821225442494,
|
|
"loss": 4.897,
|
|
"mean_token_accuracy": 0.19628540873527528,
|
|
"num_tokens": 28893837.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.12513484954834,
|
|
"epoch": 1.2310899344848123,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004860834621597808,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.1873547449707985,
|
|
"num_tokens": 28907754.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.230114936828613,
|
|
"epoch": 1.231685527099464,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048606870449391604,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.19537370204925536,
|
|
"num_tokens": 28920994.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.106244134902954,
|
|
"epoch": 1.2322811197141155,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004860539392573601,
|
|
"loss": 4.9483,
|
|
"mean_token_accuracy": 0.18772909194231033,
|
|
"num_tokens": 28937298.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.082954978942871,
|
|
"epoch": 1.2328767123287672,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048603916645064256,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.19575023502111435,
|
|
"num_tokens": 28951050.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.230524682998658,
|
|
"epoch": 1.2334723049434186,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048602438607429313,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.18501271307468414,
|
|
"num_tokens": 28965054.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.0849165439605715,
|
|
"epoch": 1.2340678975580703,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048600959812884217,
|
|
"loss": 4.8478,
|
|
"mean_token_accuracy": 0.20640473663806916,
|
|
"num_tokens": 28978162.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.149931240081787,
|
|
"epoch": 1.2346634901727218,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004859948026148199,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.1873646065592766,
|
|
"num_tokens": 28991426.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.138615369796753,
|
|
"epoch": 1.2352590827873735,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048597999953275717,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.19116950333118438,
|
|
"num_tokens": 29005159.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.129180097579956,
|
|
"epoch": 1.235854675402025,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048596518888318485,
|
|
"loss": 4.8886,
|
|
"mean_token_accuracy": 0.19713667929172515,
|
|
"num_tokens": 29020957.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.161021709442139,
|
|
"epoch": 1.2364502680166767,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048595037066663434,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.18556340783834457,
|
|
"num_tokens": 29035133.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.154315185546875,
|
|
"epoch": 1.2370458606313282,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004859355448836369,
|
|
"loss": 4.8974,
|
|
"mean_token_accuracy": 0.19272943139076232,
|
|
"num_tokens": 29047351.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.041894483566284,
|
|
"epoch": 1.2376414532459799,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048592071153472446,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.1939241573214531,
|
|
"num_tokens": 29061395.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.171082210540772,
|
|
"epoch": 1.2382370458606313,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048590587062042907,
|
|
"loss": 4.9858,
|
|
"mean_token_accuracy": 0.186885803937912,
|
|
"num_tokens": 29074952.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.12546854019165,
|
|
"epoch": 1.2388326384752828,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004858910221412829,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.1923009365797043,
|
|
"num_tokens": 29087954.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.100540447235107,
|
|
"epoch": 1.2394282310899345,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004858761660978188,
|
|
"loss": 4.9677,
|
|
"mean_token_accuracy": 0.1897154614329338,
|
|
"num_tokens": 29102437.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.133990335464477,
|
|
"epoch": 1.240023823704586,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004858613024905694,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.1970515474677086,
|
|
"num_tokens": 29116652.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.098670387268067,
|
|
"epoch": 1.2406194163192377,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004858464313200679,
|
|
"loss": 4.9664,
|
|
"mean_token_accuracy": 0.19028078764677048,
|
|
"num_tokens": 29131866.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.14440393447876,
|
|
"epoch": 1.2412150089338891,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004858315525868478,
|
|
"loss": 4.9645,
|
|
"mean_token_accuracy": 0.19309511482715608,
|
|
"num_tokens": 29145512.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.067187070846558,
|
|
"epoch": 1.2418106015485408,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004858166662914426,
|
|
"loss": 4.8564,
|
|
"mean_token_accuracy": 0.2000403180718422,
|
|
"num_tokens": 29158789.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.047319936752319,
|
|
"epoch": 1.2424061941631923,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004858017724343864,
|
|
"loss": 4.8827,
|
|
"mean_token_accuracy": 0.19204841256141664,
|
|
"num_tokens": 29172536.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.035496044158935,
|
|
"epoch": 1.243001786777844,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048578687101621346,
|
|
"loss": 4.8753,
|
|
"mean_token_accuracy": 0.19986779540777205,
|
|
"num_tokens": 29185837.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.090672445297241,
|
|
"epoch": 1.2435973793924955,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000485771962037458,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.1877087578177452,
|
|
"num_tokens": 29198821.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.10644006729126,
|
|
"epoch": 1.2441929720071472,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048575704549865505,
|
|
"loss": 4.9119,
|
|
"mean_token_accuracy": 0.1971004843711853,
|
|
"num_tokens": 29211240.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.106947422027588,
|
|
"epoch": 1.2447885646217987,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048574212140033965,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.19171909093856812,
|
|
"num_tokens": 29225413.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.042904090881348,
|
|
"epoch": 1.2453841572364504,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048572718974304683,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.19818879663944244,
|
|
"num_tokens": 29236804.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.053231143951416,
|
|
"epoch": 1.2459797498511018,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048571225052731245,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.1986499547958374,
|
|
"num_tokens": 29249884.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.111733055114746,
|
|
"epoch": 1.2465753424657535,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048569730375367217,
|
|
"loss": 4.964,
|
|
"mean_token_accuracy": 0.18629031181335448,
|
|
"num_tokens": 29266123.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.124049425125122,
|
|
"epoch": 1.247170935080405,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048568234942266217,
|
|
"loss": 4.9362,
|
|
"mean_token_accuracy": 0.1940636083483696,
|
|
"num_tokens": 29281222.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.108401584625244,
|
|
"epoch": 1.2477665276950565,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048566738753481886,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.1987742230296135,
|
|
"num_tokens": 29293855.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.138285064697266,
|
|
"epoch": 1.2483621203097082,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004856524180906789,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.19661826640367508,
|
|
"num_tokens": 29305968.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.14177680015564,
|
|
"epoch": 1.2489577129243596,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048563744109077916,
|
|
"loss": 4.9715,
|
|
"mean_token_accuracy": 0.1890563875436783,
|
|
"num_tokens": 29320806.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.069611501693726,
|
|
"epoch": 1.2495533055390113,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004856224565356569,
|
|
"loss": 4.9281,
|
|
"mean_token_accuracy": 0.19652082473039628,
|
|
"num_tokens": 29334727.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.109821557998657,
|
|
"epoch": 1.2501488981536628,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048560746442584965,
|
|
"loss": 4.8885,
|
|
"mean_token_accuracy": 0.19744015038013457,
|
|
"num_tokens": 29348362.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.095419263839721,
|
|
"epoch": 1.2507444907683145,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000485592464761895,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.198392815887928,
|
|
"num_tokens": 29360919.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.063381862640381,
|
|
"epoch": 1.251340083382966,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004855774575443311,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.19551804661750793,
|
|
"num_tokens": 29374627.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.142061996459961,
|
|
"epoch": 1.2519356759976177,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004855624427736961,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.18830792605876923,
|
|
"num_tokens": 29386660.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.119283008575439,
|
|
"epoch": 1.2525312686122692,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004855474204505287,
|
|
"loss": 4.9144,
|
|
"mean_token_accuracy": 0.19209926426410676,
|
|
"num_tokens": 29401521.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.070280742645264,
|
|
"epoch": 1.2531268612269209,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048553239057536757,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.19909923076629638,
|
|
"num_tokens": 29414629.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.138099098205567,
|
|
"epoch": 1.2537224538415723,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048551735314875203,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.1888735756278038,
|
|
"num_tokens": 29428049.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.139592218399048,
|
|
"epoch": 1.254318046456224,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004855023081712212,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.18901781141757965,
|
|
"num_tokens": 29441656.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.119496059417725,
|
|
"epoch": 1.2549136390708755,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004854872556433149,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.18641121834516525,
|
|
"num_tokens": 29455613.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.226960277557373,
|
|
"epoch": 1.2555092316855272,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004854721955655729,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.18431681245565415,
|
|
"num_tokens": 29470322.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.204705476760864,
|
|
"epoch": 1.2561048243001787,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048545712793853554,
|
|
"loss": 4.9304,
|
|
"mean_token_accuracy": 0.1933782458305359,
|
|
"num_tokens": 29484288.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.164027166366577,
|
|
"epoch": 1.2567004169148301,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004854420527627431,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.1940569683909416,
|
|
"num_tokens": 29497311.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.101694202423095,
|
|
"epoch": 1.2572960095294818,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048542697003873636,
|
|
"loss": 4.9645,
|
|
"mean_token_accuracy": 0.20030895471572877,
|
|
"num_tokens": 29510352.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.157558917999268,
|
|
"epoch": 1.2578916021441335,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048541187976705645,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.19240826666355132,
|
|
"num_tokens": 29523888.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.145823764801025,
|
|
"epoch": 1.258487194758785,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004853967819482445,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.19233480095863342,
|
|
"num_tokens": 29536219.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.06051926612854,
|
|
"epoch": 1.2590827873734365,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000485381676582842,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.1988365352153778,
|
|
"num_tokens": 29549570.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.181809139251709,
|
|
"epoch": 1.2596783799880882,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048536656367139085,
|
|
"loss": 4.9153,
|
|
"mean_token_accuracy": 0.1937191069126129,
|
|
"num_tokens": 29563278.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.112481546401978,
|
|
"epoch": 1.2602739726027397,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048535144321443317,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.19304080605506896,
|
|
"num_tokens": 29580363.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.087042713165284,
|
|
"epoch": 1.2608695652173914,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048533631521251115,
|
|
"loss": 4.8056,
|
|
"mean_token_accuracy": 0.19975836127996444,
|
|
"num_tokens": 29594339.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.145871591567993,
|
|
"epoch": 1.2614651578320428,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004853211796661675,
|
|
"loss": 5.0432,
|
|
"mean_token_accuracy": 0.18655804842710494,
|
|
"num_tokens": 29606678.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.13882417678833,
|
|
"epoch": 1.2620607504466945,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004853060365759451,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.19519291818141937,
|
|
"num_tokens": 29621791.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.135624980926513,
|
|
"epoch": 1.262656343061346,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048529088594238714,
|
|
"loss": 4.898,
|
|
"mean_token_accuracy": 0.1958639830350876,
|
|
"num_tokens": 29633679.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.118842077255249,
|
|
"epoch": 1.2632519356759977,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004852757277660369,
|
|
"loss": 4.9907,
|
|
"mean_token_accuracy": 0.19390431195497512,
|
|
"num_tokens": 29648218.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.117125034332275,
|
|
"epoch": 1.2638475282906492,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048526056204743827,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.18703146725893022,
|
|
"num_tokens": 29662819.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.090409946441651,
|
|
"epoch": 1.2644431209053009,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048524538878713517,
|
|
"loss": 4.9247,
|
|
"mean_token_accuracy": 0.19355367571115495,
|
|
"num_tokens": 29678298.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.086959886550903,
|
|
"epoch": 1.2650387135199523,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004852302079856718,
|
|
"loss": 4.8637,
|
|
"mean_token_accuracy": 0.2028035432100296,
|
|
"num_tokens": 29692001.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.080755090713501,
|
|
"epoch": 1.2656343061346038,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004852150196435927,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.19222489148378372,
|
|
"num_tokens": 29706641.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.085950803756714,
|
|
"epoch": 1.2662298987492555,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048519982376144254,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.200680735707283,
|
|
"num_tokens": 29719694.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.066592454910278,
|
|
"epoch": 1.2668254913639072,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048518462033976653,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.1973487839102745,
|
|
"num_tokens": 29733769.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.087183284759521,
|
|
"epoch": 1.2674210839785587,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048516940937910996,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.18654653131961824,
|
|
"num_tokens": 29748419.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.1174437522888185,
|
|
"epoch": 1.2680166765932102,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004851541908800184,
|
|
"loss": 4.9491,
|
|
"mean_token_accuracy": 0.19362797141075133,
|
|
"num_tokens": 29761356.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.123054647445679,
|
|
"epoch": 1.2686122692078619,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048513896484303763,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.1988004818558693,
|
|
"num_tokens": 29774245.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.0351806640625,
|
|
"epoch": 1.2692078618225133,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048512373126871383,
|
|
"loss": 4.9265,
|
|
"mean_token_accuracy": 0.1932410016655922,
|
|
"num_tokens": 29788153.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.195326852798462,
|
|
"epoch": 1.269803454437165,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004851084901575935,
|
|
"loss": 5.0218,
|
|
"mean_token_accuracy": 0.18815116584300995,
|
|
"num_tokens": 29802299.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.107382202148438,
|
|
"epoch": 1.2703990470518165,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048509324151022325,
|
|
"loss": 4.8309,
|
|
"mean_token_accuracy": 0.20385271012783052,
|
|
"num_tokens": 29815461.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.041505336761475,
|
|
"epoch": 1.2709946396664682,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048507798532715005,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.1939813420176506,
|
|
"num_tokens": 29829341.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.002719974517822,
|
|
"epoch": 1.2715902322811197,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000485062721608921,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.20110052227973937,
|
|
"num_tokens": 29842520.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.175295829772949,
|
|
"epoch": 1.2721858248957714,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004850474503560837,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.19418989717960358,
|
|
"num_tokens": 29857950.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.15669994354248,
|
|
"epoch": 1.2727814175104228,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004850321715691858,
|
|
"loss": 4.9234,
|
|
"mean_token_accuracy": 0.19232296645641328,
|
|
"num_tokens": 29872558.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.145205736160278,
|
|
"epoch": 1.2733770101250745,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048501688524877555,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.19820033609867097,
|
|
"num_tokens": 29884083.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.086570501327515,
|
|
"epoch": 1.273972602739726,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000485001591395401,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.1940536081790924,
|
|
"num_tokens": 29898088.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.032482290267945,
|
|
"epoch": 1.2745681953543775,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004849862900096108,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.19985633194446564,
|
|
"num_tokens": 29911394.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.228085708618164,
|
|
"epoch": 1.2751637879690292,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048497098109195387,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.186139315366745,
|
|
"num_tokens": 29925968.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.152057790756226,
|
|
"epoch": 1.2757593805836809,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048495566464297913,
|
|
"loss": 4.921,
|
|
"mean_token_accuracy": 0.18998936116695403,
|
|
"num_tokens": 29939853.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.064109897613525,
|
|
"epoch": 1.2763549731983324,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004849403406632361,
|
|
"loss": 4.882,
|
|
"mean_token_accuracy": 0.19743597507476807,
|
|
"num_tokens": 29953512.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.107710886001587,
|
|
"epoch": 1.2769505658129838,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004849250091532744,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.1939012497663498,
|
|
"num_tokens": 29967681.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.254292058944702,
|
|
"epoch": 1.2775461584276355,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048490967011364394,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.18663498461246492,
|
|
"num_tokens": 29982726.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.09841103553772,
|
|
"epoch": 1.278141751042287,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048489432354489496,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.19768776446580888,
|
|
"num_tokens": 29997881.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.083865451812744,
|
|
"epoch": 1.2787373436569387,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048487896944757777,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.19222706258296968,
|
|
"num_tokens": 30012707.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.148039054870606,
|
|
"epoch": 1.2793329362715902,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004848636078222433,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.1869815930724144,
|
|
"num_tokens": 30027098.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.139608526229859,
|
|
"epoch": 1.2799285288862419,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004848482386694424,
|
|
"loss": 4.9289,
|
|
"mean_token_accuracy": 0.19606860876083373,
|
|
"num_tokens": 30042228.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.132561254501343,
|
|
"epoch": 1.2805241215008933,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048483286198972627,
|
|
"loss": 4.8584,
|
|
"mean_token_accuracy": 0.19980076253414153,
|
|
"num_tokens": 30055789.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.0195777893066404,
|
|
"epoch": 1.281119714115545,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004848174777836466,
|
|
"loss": 4.8279,
|
|
"mean_token_accuracy": 0.1984833613038063,
|
|
"num_tokens": 30068129.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.124315357208252,
|
|
"epoch": 1.2817153067301965,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004848020860517552,
|
|
"loss": 4.9624,
|
|
"mean_token_accuracy": 0.18865440785884857,
|
|
"num_tokens": 30081922.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.0828999996185305,
|
|
"epoch": 1.2823108993448482,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000484786686794604,
|
|
"loss": 4.8691,
|
|
"mean_token_accuracy": 0.19923902153968812,
|
|
"num_tokens": 30095277.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.105973482131958,
|
|
"epoch": 1.2829064919594997,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048477128001274557,
|
|
"loss": 4.9722,
|
|
"mean_token_accuracy": 0.18406190872192382,
|
|
"num_tokens": 30110490.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.14471025466919,
|
|
"epoch": 1.2835020845741512,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048475586570673223,
|
|
"loss": 4.9613,
|
|
"mean_token_accuracy": 0.19586156755685807,
|
|
"num_tokens": 30124082.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.151168155670166,
|
|
"epoch": 1.2840976771888029,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004847404438771172,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.19142893254756926,
|
|
"num_tokens": 30137617.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.067321634292602,
|
|
"epoch": 1.2846932698034546,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048472501452445334,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.1954121008515358,
|
|
"num_tokens": 30151354.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.032710886001587,
|
|
"epoch": 1.285288862418106,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004847095776492942,
|
|
"loss": 4.9202,
|
|
"mean_token_accuracy": 0.1939186692237854,
|
|
"num_tokens": 30165067.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.112872648239136,
|
|
"epoch": 1.2858844550327575,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048469413325219355,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.19617506265640258,
|
|
"num_tokens": 30177484.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.116362524032593,
|
|
"epoch": 1.2864800476474092,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048467868133370527,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.18747712075710296,
|
|
"num_tokens": 30192765.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.035600471496582,
|
|
"epoch": 1.2870756402620607,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048466322189438354,
|
|
"loss": 4.8992,
|
|
"mean_token_accuracy": 0.19591509252786637,
|
|
"num_tokens": 30207569.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.102675867080689,
|
|
"epoch": 1.2876712328767124,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048464775493478303,
|
|
"loss": 4.9116,
|
|
"mean_token_accuracy": 0.1916748106479645,
|
|
"num_tokens": 30221741.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.042803764343262,
|
|
"epoch": 1.2882668254913638,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048463228045545837,
|
|
"loss": 4.8414,
|
|
"mean_token_accuracy": 0.20096640884876252,
|
|
"num_tokens": 30237107.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.176201105117798,
|
|
"epoch": 1.2888624181060155,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048461679845696466,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.19226899445056916,
|
|
"num_tokens": 30251748.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.18750319480896,
|
|
"epoch": 1.289458010720667,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004846013089398572,
|
|
"loss": 4.9172,
|
|
"mean_token_accuracy": 0.19336709082126619,
|
|
"num_tokens": 30265333.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.0977379322052006,
|
|
"epoch": 1.2900536033353187,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048458581190469153,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.19338064044713973,
|
|
"num_tokens": 30279320.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.106905841827393,
|
|
"epoch": 1.2906491959499702,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004845703073520236,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.1956945076584816,
|
|
"num_tokens": 30292233.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.033199310302734,
|
|
"epoch": 1.2912447885646219,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004845547952824095,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.1936190128326416,
|
|
"num_tokens": 30305729.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.1078667640686035,
|
|
"epoch": 1.2918403811792734,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048453927569640557,
|
|
"loss": 4.8886,
|
|
"mean_token_accuracy": 0.1957963526248932,
|
|
"num_tokens": 30319856.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.13967227935791,
|
|
"epoch": 1.2924359737939248,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048452374859456855,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.19258890599012374,
|
|
"num_tokens": 30334774.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.188610410690307,
|
|
"epoch": 1.2930315664085765,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004845082139774553,
|
|
"loss": 4.9821,
|
|
"mean_token_accuracy": 0.1847788870334625,
|
|
"num_tokens": 30349321.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.039261102676392,
|
|
"epoch": 1.2936271590232282,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004844926718456231,
|
|
"loss": 4.8562,
|
|
"mean_token_accuracy": 0.20476224571466445,
|
|
"num_tokens": 30362403.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.080943155288696,
|
|
"epoch": 1.2942227516378797,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004844771221996293,
|
|
"loss": 4.9557,
|
|
"mean_token_accuracy": 0.19133392721414566,
|
|
"num_tokens": 30375156.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.171406078338623,
|
|
"epoch": 1.2948183442525312,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004844615650400318,
|
|
"loss": 4.9365,
|
|
"mean_token_accuracy": 0.1918689265847206,
|
|
"num_tokens": 30390900.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.223014402389526,
|
|
"epoch": 1.2954139368671829,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048444600036738844,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.18200865089893342,
|
|
"num_tokens": 30405578.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.070127058029175,
|
|
"epoch": 1.2960095294818343,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048443042818225766,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.19495888650417328,
|
|
"num_tokens": 30417539.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.0695273876190186,
|
|
"epoch": 1.296605122096486,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048441484848519786,
|
|
"loss": 4.9269,
|
|
"mean_token_accuracy": 0.18960365056991577,
|
|
"num_tokens": 30429638.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.15777587890625,
|
|
"epoch": 1.2972007147111375,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048439926127676796,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.18474468290805818,
|
|
"num_tokens": 30444586.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.119330835342407,
|
|
"epoch": 1.2977963073257892,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048438366655752707,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.19558183550834657,
|
|
"num_tokens": 30459758.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.074956655502319,
|
|
"epoch": 1.2983918999404407,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004843680643280345,
|
|
"loss": 4.8855,
|
|
"mean_token_accuracy": 0.198907071352005,
|
|
"num_tokens": 30473022.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.07827582359314,
|
|
"epoch": 1.2989874925550924,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004843524545888498,
|
|
"loss": 4.9397,
|
|
"mean_token_accuracy": 0.1961773619055748,
|
|
"num_tokens": 30487008.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.168912506103515,
|
|
"epoch": 1.2995830851697439,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000484336837340533,
|
|
"loss": 4.9543,
|
|
"mean_token_accuracy": 0.1895797699689865,
|
|
"num_tokens": 30500512.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.07794156074524,
|
|
"epoch": 1.3001786777843956,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048432121258364417,
|
|
"loss": 4.9324,
|
|
"mean_token_accuracy": 0.19300722926855088,
|
|
"num_tokens": 30513754.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.012874603271484,
|
|
"epoch": 1.300774270399047,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004843055803187438,
|
|
"loss": 4.9144,
|
|
"mean_token_accuracy": 0.19602941870689392,
|
|
"num_tokens": 30529102.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.123136377334594,
|
|
"epoch": 1.3013698630136985,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048428994054639256,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.21028940975666047,
|
|
"num_tokens": 30541595.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.045237970352173,
|
|
"epoch": 1.3019654556283502,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004842742932671514,
|
|
"loss": 4.7993,
|
|
"mean_token_accuracy": 0.20684683322906494,
|
|
"num_tokens": 30554439.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.044347858428955,
|
|
"epoch": 1.302561048243002,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004842586384815817,
|
|
"loss": 4.8872,
|
|
"mean_token_accuracy": 0.19781895130872726,
|
|
"num_tokens": 30569662.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.109290599822998,
|
|
"epoch": 1.3031566408576534,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004842429761902448,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.19803367853164672,
|
|
"num_tokens": 30582815.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.14205265045166,
|
|
"epoch": 1.3037522334723048,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048422730639370256,
|
|
"loss": 4.9237,
|
|
"mean_token_accuracy": 0.1917114421725273,
|
|
"num_tokens": 30598455.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.098524904251098,
|
|
"epoch": 1.3043478260869565,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004842116290925171,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.1880191147327423,
|
|
"num_tokens": 30613063.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.087962245941162,
|
|
"epoch": 1.3049434187016082,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004841959442872505,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.1926803320646286,
|
|
"num_tokens": 30628330.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.142624711990356,
|
|
"epoch": 1.3055390113162597,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004841802519784656,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.1842277765274048,
|
|
"num_tokens": 30643329.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.074787855148315,
|
|
"epoch": 1.3061346039309112,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048416455216672525,
|
|
"loss": 4.9083,
|
|
"mean_token_accuracy": 0.19247938245534896,
|
|
"num_tokens": 30658285.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.032155609130859,
|
|
"epoch": 1.3067301965455629,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048414884485259235,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.20010832846164703,
|
|
"num_tokens": 30673531.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.0875767230987545,
|
|
"epoch": 1.3073257891602144,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004841331300366306,
|
|
"loss": 4.9056,
|
|
"mean_token_accuracy": 0.19320069700479509,
|
|
"num_tokens": 30686339.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.083446645736695,
|
|
"epoch": 1.307921381774866,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004841174077194033,
|
|
"loss": 4.8521,
|
|
"mean_token_accuracy": 0.2024978756904602,
|
|
"num_tokens": 30699265.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.077634239196778,
|
|
"epoch": 1.3085169743895175,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004841016779014747,
|
|
"loss": 4.8503,
|
|
"mean_token_accuracy": 0.2007881745696068,
|
|
"num_tokens": 30712796.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.089562606811524,
|
|
"epoch": 1.3091125670041692,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048408594058340894,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.2002420499920845,
|
|
"num_tokens": 30725986.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.194956111907959,
|
|
"epoch": 1.3097081596188207,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048407019576577037,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.1893106520175934,
|
|
"num_tokens": 30739015.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.090553712844849,
|
|
"epoch": 1.3103037522334722,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004840544434491238,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.20341548770666124,
|
|
"num_tokens": 30751762.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.073529291152954,
|
|
"epoch": 1.3108993448481239,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048403868363403437,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.19892001748085023,
|
|
"num_tokens": 30765015.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.106461000442505,
|
|
"epoch": 1.3114949374627756,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004840229163210671,
|
|
"loss": 4.9247,
|
|
"mean_token_accuracy": 0.1969834417104721,
|
|
"num_tokens": 30777662.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.119413995742798,
|
|
"epoch": 1.312090530077427,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048400714151078774,
|
|
"loss": 4.9177,
|
|
"mean_token_accuracy": 0.18909145295619964,
|
|
"num_tokens": 30790501.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.128649425506592,
|
|
"epoch": 1.3126861226920785,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048399135920376197,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.19671610444784166,
|
|
"num_tokens": 30803410.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.140560245513916,
|
|
"epoch": 1.3132817153067302,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000483975569400556,
|
|
"loss": 4.9253,
|
|
"mean_token_accuracy": 0.193812295794487,
|
|
"num_tokens": 30818312.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.1469042778015135,
|
|
"epoch": 1.313877307921382,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048395977210173607,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.19436452835798262,
|
|
"num_tokens": 30832555.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.081915616989136,
|
|
"epoch": 1.3144729005360334,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004839439673078689,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.1960500031709671,
|
|
"num_tokens": 30847786.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.103499794006348,
|
|
"epoch": 1.3150684931506849,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004839281550195214,
|
|
"loss": 4.9161,
|
|
"mean_token_accuracy": 0.1996523216366768,
|
|
"num_tokens": 30860512.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.119392061233521,
|
|
"epoch": 1.3156640857653366,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004839123352372606,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.19708553552627564,
|
|
"num_tokens": 30876290.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.113661575317383,
|
|
"epoch": 1.316259678379988,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048389650796165407,
|
|
"loss": 4.9456,
|
|
"mean_token_accuracy": 0.19154740273952484,
|
|
"num_tokens": 30890561.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.032300281524658,
|
|
"epoch": 1.3168552709946397,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048388067319326937,
|
|
"loss": 4.8826,
|
|
"mean_token_accuracy": 0.20380615293979645,
|
|
"num_tokens": 30905149.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.127493906021118,
|
|
"epoch": 1.3174508636092912,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048386483093267464,
|
|
"loss": 4.9269,
|
|
"mean_token_accuracy": 0.19785792678594588,
|
|
"num_tokens": 30918591.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.147409248352051,
|
|
"epoch": 1.318046456223943,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004838489811804379,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.18717621713876725,
|
|
"num_tokens": 30933452.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.130752182006836,
|
|
"epoch": 1.3186420488385944,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048383312393712784,
|
|
"loss": 4.9239,
|
|
"mean_token_accuracy": 0.19477907419204712,
|
|
"num_tokens": 30946904.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.071676588058471,
|
|
"epoch": 1.3192376414532458,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004838172592033132,
|
|
"loss": 4.8631,
|
|
"mean_token_accuracy": 0.19648851901292802,
|
|
"num_tokens": 30960598.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.084071159362793,
|
|
"epoch": 1.3198332340678975,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048380138697956294,
|
|
"loss": 4.9068,
|
|
"mean_token_accuracy": 0.190736722946167,
|
|
"num_tokens": 30973978.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.139641666412354,
|
|
"epoch": 1.3204288266825492,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048378550726644644,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.18859562873840333,
|
|
"num_tokens": 30986543.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.147053003311157,
|
|
"epoch": 1.3210244192972007,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048376962006453324,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.1841759815812111,
|
|
"num_tokens": 31000389.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.142340517044067,
|
|
"epoch": 1.3216200119118522,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004837537253743932,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.19444802403450012,
|
|
"num_tokens": 31014252.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.087283611297607,
|
|
"epoch": 1.3222156045265039,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004837378231965965,
|
|
"loss": 4.9461,
|
|
"mean_token_accuracy": 0.19530680030584335,
|
|
"num_tokens": 31027482.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.0704892635345455,
|
|
"epoch": 1.3228111971411556,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048372191353171333,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.19711674749851227,
|
|
"num_tokens": 31041804.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.056217002868652,
|
|
"epoch": 1.323406789755807,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048370599638031464,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.19555213898420334,
|
|
"num_tokens": 31054558.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.1680042266845705,
|
|
"epoch": 1.3240023823704585,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048369007174297115,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.18856329172849656,
|
|
"num_tokens": 31069922.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.164851570129395,
|
|
"epoch": 1.3245979749851102,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000483674139620254,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.1872720718383789,
|
|
"num_tokens": 31082170.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.101436901092529,
|
|
"epoch": 1.3251935675997617,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004836582000127349,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.20228228867053985,
|
|
"num_tokens": 31095269.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.149924802780151,
|
|
"epoch": 1.3257891602144134,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004836422529209853,
|
|
"loss": 4.8801,
|
|
"mean_token_accuracy": 0.2021287351846695,
|
|
"num_tokens": 31107682.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.140673685073852,
|
|
"epoch": 1.3263847528290649,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048362629834557743,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.19063564985990525,
|
|
"num_tokens": 31123619.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.1525359630584715,
|
|
"epoch": 1.3269803454437166,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048361033628708334,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.19241231828927993,
|
|
"num_tokens": 31138806.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.126251363754273,
|
|
"epoch": 1.327575938058368,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048359436674607573,
|
|
"loss": 4.9748,
|
|
"mean_token_accuracy": 0.19266110211610793,
|
|
"num_tokens": 31153488.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.1936839580535885,
|
|
"epoch": 1.3281715306730195,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004835783897231273,
|
|
"loss": 4.9754,
|
|
"mean_token_accuracy": 0.1947360396385193,
|
|
"num_tokens": 31168073.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.039539384841919,
|
|
"epoch": 1.3287671232876712,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048356240521881113,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.20448276847600938,
|
|
"num_tokens": 31181269.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.0166185855865475,
|
|
"epoch": 1.329362715902323,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004835464132337007,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.19929327666759492,
|
|
"num_tokens": 31196690.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.1356165409088135,
|
|
"epoch": 1.3299583085169744,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048353041376836937,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.19012127071619034,
|
|
"num_tokens": 31212832.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.08653826713562,
|
|
"epoch": 1.3305539011316259,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048351440682339126,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.19435697197914123,
|
|
"num_tokens": 31225538.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.075869703292847,
|
|
"epoch": 1.3311494937462776,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048349839239934035,
|
|
"loss": 4.8868,
|
|
"mean_token_accuracy": 0.19686997383832933,
|
|
"num_tokens": 31238911.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.096521091461182,
|
|
"epoch": 1.3317450863609293,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048348237049679105,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.19627442806959153,
|
|
"num_tokens": 31253284.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.100472736358642,
|
|
"epoch": 1.3323406789755807,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004834663411163182,
|
|
"loss": 4.8721,
|
|
"mean_token_accuracy": 0.19604527354240417,
|
|
"num_tokens": 31267925.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.104363679885864,
|
|
"epoch": 1.3329362715902322,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004834503042584966,
|
|
"loss": 5.0074,
|
|
"mean_token_accuracy": 0.18641296923160552,
|
|
"num_tokens": 31281957.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.107834053039551,
|
|
"epoch": 1.333531864204884,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004834342599239015,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.19162838459014891,
|
|
"num_tokens": 31297411.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.13696699142456,
|
|
"epoch": 1.3341274568195354,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048341820811310834,
|
|
"loss": 4.9501,
|
|
"mean_token_accuracy": 0.1925147920846939,
|
|
"num_tokens": 31311695.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.16484522819519,
|
|
"epoch": 1.334723049434187,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048340214882669296,
|
|
"loss": 4.9462,
|
|
"mean_token_accuracy": 0.19371204525232316,
|
|
"num_tokens": 31325149.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.090535974502563,
|
|
"epoch": 1.3353186420488385,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004833860820652314,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.18597864955663682,
|
|
"num_tokens": 31339653.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.147240924835205,
|
|
"epoch": 1.3359142346634902,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004833700078292998,
|
|
"loss": 4.9071,
|
|
"mean_token_accuracy": 0.20142904967069625,
|
|
"num_tokens": 31352592.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.1140974998474125,
|
|
"epoch": 1.3365098272781417,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004833539261194749,
|
|
"loss": 4.9158,
|
|
"mean_token_accuracy": 0.1934174656867981,
|
|
"num_tokens": 31366276.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 4.9991250991821286,
|
|
"epoch": 1.3371054198927934,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004833378369363333,
|
|
"loss": 4.7977,
|
|
"mean_token_accuracy": 0.199055914580822,
|
|
"num_tokens": 31380152.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.06251745223999,
|
|
"epoch": 1.3377010125074449,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004833217402804523,
|
|
"loss": 4.9775,
|
|
"mean_token_accuracy": 0.1911313369870186,
|
|
"num_tokens": 31395388.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.146400880813599,
|
|
"epoch": 1.3382966051220966,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004833056361524092,
|
|
"loss": 4.8793,
|
|
"mean_token_accuracy": 0.19629994481801988,
|
|
"num_tokens": 31409327.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.031855154037475,
|
|
"epoch": 1.338892197736748,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004832895245527816,
|
|
"loss": 4.9202,
|
|
"mean_token_accuracy": 0.19645329415798188,
|
|
"num_tokens": 31423069.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.028249073028564,
|
|
"epoch": 1.3394877903513995,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004832734054821474,
|
|
"loss": 4.807,
|
|
"mean_token_accuracy": 0.2072947844862938,
|
|
"num_tokens": 31436494.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.113928890228271,
|
|
"epoch": 1.3400833829660512,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048325727894108487,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.19423623085021974,
|
|
"num_tokens": 31450520.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.127938175201416,
|
|
"epoch": 1.340678975580703,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004832411449301723,
|
|
"loss": 4.8549,
|
|
"mean_token_accuracy": 0.19947062581777572,
|
|
"num_tokens": 31463681.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.056179046630859,
|
|
"epoch": 1.3412745681953544,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004832250034499884,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.1898348331451416,
|
|
"num_tokens": 31479677.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.0880509376525875,
|
|
"epoch": 1.3418701608100059,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004832088545011122,
|
|
"loss": 4.9324,
|
|
"mean_token_accuracy": 0.19421091079711914,
|
|
"num_tokens": 31493880.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.064404439926148,
|
|
"epoch": 1.3424657534246576,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004831926980841229,
|
|
"loss": 4.858,
|
|
"mean_token_accuracy": 0.19512905180454254,
|
|
"num_tokens": 31507044.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.0325737476348875,
|
|
"epoch": 1.343061346039309,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048317653419960007,
|
|
"loss": 4.8312,
|
|
"mean_token_accuracy": 0.2026189610362053,
|
|
"num_tokens": 31519903.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.09281096458435,
|
|
"epoch": 1.3436569386539607,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048316036284812335,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.20032116621732712,
|
|
"num_tokens": 31534015.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 4.993605518341065,
|
|
"epoch": 1.3442525312686122,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004831441840302729,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.20311526209115982,
|
|
"num_tokens": 31549980.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.138371133804322,
|
|
"epoch": 1.344848123883264,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048312799774662905,
|
|
"loss": 4.9314,
|
|
"mean_token_accuracy": 0.19356394708156585,
|
|
"num_tokens": 31563550.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.069172048568726,
|
|
"epoch": 1.3454437164979154,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004831118039977722,
|
|
"loss": 4.812,
|
|
"mean_token_accuracy": 0.20481640845537186,
|
|
"num_tokens": 31576552.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.076359128952026,
|
|
"epoch": 1.346039309112567,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004830956027842834,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.19497105926275254,
|
|
"num_tokens": 31592423.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.14306755065918,
|
|
"epoch": 1.3466349017272186,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004830793941067437,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.19617584496736526,
|
|
"num_tokens": 31606166.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.077589130401611,
|
|
"epoch": 1.3472304943418703,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048306317796573426,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.19400243759155272,
|
|
"num_tokens": 31622342.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.074541854858398,
|
|
"epoch": 1.3478260869565217,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004830469543618371,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.19576854705810548,
|
|
"num_tokens": 31634784.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.145302772521973,
|
|
"epoch": 1.3484216795711732,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004830307232956339,
|
|
"loss": 4.938,
|
|
"mean_token_accuracy": 0.1878011018037796,
|
|
"num_tokens": 31648871.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.167843532562256,
|
|
"epoch": 1.349017272185825,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004830144847677069,
|
|
"loss": 4.9221,
|
|
"mean_token_accuracy": 0.19947739094495773,
|
|
"num_tokens": 31662066.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.0483557224273685,
|
|
"epoch": 1.3496128648004766,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048299823877863857,
|
|
"loss": 4.862,
|
|
"mean_token_accuracy": 0.19699215441942214,
|
|
"num_tokens": 31675439.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.1129615783691404,
|
|
"epoch": 1.350208457415128,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004829819853290116,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.20161108523607255,
|
|
"num_tokens": 31688670.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.0471117973327635,
|
|
"epoch": 1.3508040500297795,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004829657244194089,
|
|
"loss": 4.9257,
|
|
"mean_token_accuracy": 0.1959942474961281,
|
|
"num_tokens": 31704749.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.117101860046387,
|
|
"epoch": 1.3513996426444312,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048294945605041384,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.19679025262594224,
|
|
"num_tokens": 31717530.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.115055751800537,
|
|
"epoch": 1.3519952352590827,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048293318022260995,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.1899126723408699,
|
|
"num_tokens": 31731683.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.044075393676758,
|
|
"epoch": 1.3525908278737344,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004829168969365809,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.19576948881149292,
|
|
"num_tokens": 31745841.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.120117664337158,
|
|
"epoch": 1.3531864204883859,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048290060619291084,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.1893761560320854,
|
|
"num_tokens": 31760634.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.068332576751709,
|
|
"epoch": 1.3537820131030376,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048288430799218394,
|
|
"loss": 4.8211,
|
|
"mean_token_accuracy": 0.20079720616340638,
|
|
"num_tokens": 31774759.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.129632472991943,
|
|
"epoch": 1.354377605717689,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004828680023349851,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.17974084317684175,
|
|
"num_tokens": 31789531.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.058013439178467,
|
|
"epoch": 1.3549731983323408,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048285168922189886,
|
|
"loss": 4.8599,
|
|
"mean_token_accuracy": 0.1939476326107979,
|
|
"num_tokens": 31802896.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.1556963443756105,
|
|
"epoch": 1.3555687909469922,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048283536865351053,
|
|
"loss": 4.9745,
|
|
"mean_token_accuracy": 0.19147203117609024,
|
|
"num_tokens": 31816205.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.0805275440216064,
|
|
"epoch": 1.356164383561644,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004828190406304054,
|
|
"loss": 4.8918,
|
|
"mean_token_accuracy": 0.1955757349729538,
|
|
"num_tokens": 31831590.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.146202850341797,
|
|
"epoch": 1.3567599761762954,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004828027051531692,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.19092735052108764,
|
|
"num_tokens": 31845063.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.106775760650635,
|
|
"epoch": 1.3573555687909469,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048278636222238785,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.19621411412954332,
|
|
"num_tokens": 31858417.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.033360004425049,
|
|
"epoch": 1.3579511614055986,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048277001183864756,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.19715975672006608,
|
|
"num_tokens": 31874634.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.089888334274292,
|
|
"epoch": 1.3585467540202503,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004827536540025347,
|
|
"loss": 4.9561,
|
|
"mean_token_accuracy": 0.19314033091068267,
|
|
"num_tokens": 31888020.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.1648266315460205,
|
|
"epoch": 1.3591423466349017,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004827372887146361,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.1852279096841812,
|
|
"num_tokens": 31903634.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.168850612640381,
|
|
"epoch": 1.3597379392495532,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048272091597553865,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.18210994303226472,
|
|
"num_tokens": 31918844.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.158623933792114,
|
|
"epoch": 1.360333531864205,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048270453578582974,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.19236608892679213,
|
|
"num_tokens": 31932752.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.1353919506073,
|
|
"epoch": 1.3609291244788564,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004826881481460968,
|
|
"loss": 4.9888,
|
|
"mean_token_accuracy": 0.20088437646627427,
|
|
"num_tokens": 31945630.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.1426409721374515,
|
|
"epoch": 1.361524717093508,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048267175305692774,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.19905636906623841,
|
|
"num_tokens": 31958640.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.154058218002319,
|
|
"epoch": 1.3621203097081596,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004826553505189104,
|
|
"loss": 5.0469,
|
|
"mean_token_accuracy": 0.18236859142780304,
|
|
"num_tokens": 31975502.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.070655679702758,
|
|
"epoch": 1.3627159023228113,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004826389405326334,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.19171358197927474,
|
|
"num_tokens": 31990017.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.1130297660827635,
|
|
"epoch": 1.3633114949374627,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004826225230986851,
|
|
"loss": 4.95,
|
|
"mean_token_accuracy": 0.19262524396181108,
|
|
"num_tokens": 32002924.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.162645292282105,
|
|
"epoch": 1.3639070875521144,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048260609821765456,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.19314580261707306,
|
|
"num_tokens": 32017769.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.153284168243408,
|
|
"epoch": 1.364502680166766,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004825896658901308,
|
|
"loss": 4.9423,
|
|
"mean_token_accuracy": 0.19687776863574982,
|
|
"num_tokens": 32031991.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.1065844058990475,
|
|
"epoch": 1.3650982727814176,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048257322611670324,
|
|
"loss": 4.8832,
|
|
"mean_token_accuracy": 0.1944314181804657,
|
|
"num_tokens": 32046294.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.021896266937256,
|
|
"epoch": 1.365693865396069,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048255677889796157,
|
|
"loss": 4.8249,
|
|
"mean_token_accuracy": 0.19587493687868118,
|
|
"num_tokens": 32059737.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.044566345214844,
|
|
"epoch": 1.3662894580107205,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004825403242344957,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.199658539891243,
|
|
"num_tokens": 32074372.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.115760612487793,
|
|
"epoch": 1.3668850506253722,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004825238621268958,
|
|
"loss": 4.943,
|
|
"mean_token_accuracy": 0.1878608539700508,
|
|
"num_tokens": 32089770.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.067019271850586,
|
|
"epoch": 1.367480643240024,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004825073925757524,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.19701360315084457,
|
|
"num_tokens": 32106162.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.164706373214722,
|
|
"epoch": 1.3680762358546754,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004824909155816562,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.18512849658727645,
|
|
"num_tokens": 32120103.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.07608847618103,
|
|
"epoch": 1.368671828469327,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048247443114519825,
|
|
"loss": 4.8751,
|
|
"mean_token_accuracy": 0.20231465697288514,
|
|
"num_tokens": 32133866.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.195048236846924,
|
|
"epoch": 1.3692674210839786,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004824579392669698,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.18636256009340285,
|
|
"num_tokens": 32148287.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.102644252777099,
|
|
"epoch": 1.36986301369863,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048244143994756233,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.19573951810598372,
|
|
"num_tokens": 32161838.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.0597316265106205,
|
|
"epoch": 1.3704586063132818,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004824249331875677,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.1990711510181427,
|
|
"num_tokens": 32175792.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.0197831153869625,
|
|
"epoch": 1.3710541989279332,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048240841898757796,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.19930978119373322,
|
|
"num_tokens": 32189976.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.086741876602173,
|
|
"epoch": 1.371649791542585,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004823918973481855,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.1899543434381485,
|
|
"num_tokens": 32204446.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.178653907775879,
|
|
"epoch": 1.3722453841572364,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048237536826998287,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.1875748872756958,
|
|
"num_tokens": 32218988.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.104406309127808,
|
|
"epoch": 1.372840976771888,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.000482358831753563,
|
|
"loss": 4.9435,
|
|
"mean_token_accuracy": 0.19424008429050446,
|
|
"num_tokens": 32231659.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.031632328033448,
|
|
"epoch": 1.3734365693865396,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048234228779951883,
|
|
"loss": 4.8482,
|
|
"mean_token_accuracy": 0.19991947412490846,
|
|
"num_tokens": 32245026.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.069449806213379,
|
|
"epoch": 1.3740321620011913,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048232573640844407,
|
|
"loss": 4.8824,
|
|
"mean_token_accuracy": 0.1971641182899475,
|
|
"num_tokens": 32259580.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.151341438293457,
|
|
"epoch": 1.3746277546158427,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004823091775809321,
|
|
"loss": 4.9142,
|
|
"mean_token_accuracy": 0.19721683710813523,
|
|
"num_tokens": 32272329.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.088805866241455,
|
|
"epoch": 1.3752233472304942,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048229261131757707,
|
|
"loss": 4.9281,
|
|
"mean_token_accuracy": 0.1991070255637169,
|
|
"num_tokens": 32288036.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.182235050201416,
|
|
"epoch": 1.375818939845146,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00048227603761897316,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.18796818405389787,
|
|
"num_tokens": 32302517.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.084646320343017,
|
|
"epoch": 1.3764145324597976,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048225945648571475,
|
|
"loss": 4.8638,
|
|
"mean_token_accuracy": 0.2027122363448143,
|
|
"num_tokens": 32315576.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.06609354019165,
|
|
"epoch": 1.377010125074449,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048224286791839657,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.1975117266178131,
|
|
"num_tokens": 32330321.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.097505950927735,
|
|
"epoch": 1.3776057176891006,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004822262719176137,
|
|
"loss": 4.9008,
|
|
"mean_token_accuracy": 0.20036935657262803,
|
|
"num_tokens": 32344397.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.13082447052002,
|
|
"epoch": 1.3782013103037523,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048220966848396137,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.19409196376800536,
|
|
"num_tokens": 32360071.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.170826148986817,
|
|
"epoch": 1.3787969029184037,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004821930576180352,
|
|
"loss": 4.9685,
|
|
"mean_token_accuracy": 0.18541094064712524,
|
|
"num_tokens": 32375577.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.162027311325073,
|
|
"epoch": 1.3793924955330554,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004821764393204308,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.19098661690950394,
|
|
"num_tokens": 32389481.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.045474195480347,
|
|
"epoch": 1.379988088147707,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004821598135917445,
|
|
"loss": 4.9205,
|
|
"mean_token_accuracy": 0.19794675558805466,
|
|
"num_tokens": 32401993.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.143177700042725,
|
|
"epoch": 1.3805836807623586,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048214318043257246,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.1930268555879593,
|
|
"num_tokens": 32416074.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.168594455718994,
|
|
"epoch": 1.38117927337701,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004821265398435113,
|
|
"loss": 4.9098,
|
|
"mean_token_accuracy": 0.1904453828930855,
|
|
"num_tokens": 32430477.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.102259492874145,
|
|
"epoch": 1.3817748659916618,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000482109891825158,
|
|
"loss": 4.9182,
|
|
"mean_token_accuracy": 0.19356056451797485,
|
|
"num_tokens": 32443649.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.006829643249512,
|
|
"epoch": 1.3823704586063132,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004820932363781096,
|
|
"loss": 4.8126,
|
|
"mean_token_accuracy": 0.20881776213645936,
|
|
"num_tokens": 32456250.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.004025316238403,
|
|
"epoch": 1.382966051220965,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048207657350296345,
|
|
"loss": 4.7828,
|
|
"mean_token_accuracy": 0.2077149972319603,
|
|
"num_tokens": 32469634.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.056896734237671,
|
|
"epoch": 1.3835616438356164,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048205990320031734,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.1992377057671547,
|
|
"num_tokens": 32484222.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.113908052444458,
|
|
"epoch": 1.384157236450268,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048204322547076915,
|
|
"loss": 4.9044,
|
|
"mean_token_accuracy": 0.196673247218132,
|
|
"num_tokens": 32498736.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.085492515563965,
|
|
"epoch": 1.3847528290649196,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048202654031491714,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.19661125391721726,
|
|
"num_tokens": 32513267.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.169391345977783,
|
|
"epoch": 1.3853484216795713,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048200984773335973,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.19256188422441484,
|
|
"num_tokens": 32527398.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.118876838684082,
|
|
"epoch": 1.3859440142942228,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004819931477266956,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.20291800796985626,
|
|
"num_tokens": 32539167.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.048439979553223,
|
|
"epoch": 1.3865396069088742,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004819764402955239,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.1941373363137245,
|
|
"num_tokens": 32553336.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.051851654052735,
|
|
"epoch": 1.387135199523526,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048195972544044373,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.2055027812719345,
|
|
"num_tokens": 32567753.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.155615711212159,
|
|
"epoch": 1.3877307921381774,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048194300316205474,
|
|
"loss": 4.9388,
|
|
"mean_token_accuracy": 0.19314008355140685,
|
|
"num_tokens": 32583662.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.091282749176026,
|
|
"epoch": 1.388326384752829,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004819262734609567,
|
|
"loss": 4.9438,
|
|
"mean_token_accuracy": 0.18935332149267198,
|
|
"num_tokens": 32597430.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.046212291717529,
|
|
"epoch": 1.3889219773674806,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004819095363377496,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.1923812970519066,
|
|
"num_tokens": 32610753.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 4.984257173538208,
|
|
"epoch": 1.3895175699821323,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004818927917930339,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.20345028191804887,
|
|
"num_tokens": 32625296.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.02621021270752,
|
|
"epoch": 1.3901131625967837,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048187603982741015,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.2003889113664627,
|
|
"num_tokens": 32638333.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.042192173004151,
|
|
"epoch": 1.3907087552114354,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004818592804414792,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.2035539999604225,
|
|
"num_tokens": 32650230.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.065965795516968,
|
|
"epoch": 1.391304347826087,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004818425136358422,
|
|
"loss": 4.9154,
|
|
"mean_token_accuracy": 0.19427675604820252,
|
|
"num_tokens": 32664641.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 4.998140478134156,
|
|
"epoch": 1.3918999404407386,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048182573941110056,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.1983642175793648,
|
|
"num_tokens": 32678576.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.112429094314575,
|
|
"epoch": 1.39249553305539,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004818089577678559,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.19629136174917222,
|
|
"num_tokens": 32692072.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.179966735839844,
|
|
"epoch": 1.3930911256700416,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004817921687067102,
|
|
"loss": 4.9791,
|
|
"mean_token_accuracy": 0.18919486850500106,
|
|
"num_tokens": 32705926.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.028616094589234,
|
|
"epoch": 1.3936867182846933,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004817753722282656,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.20211651772260666,
|
|
"num_tokens": 32720028.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.068598651885987,
|
|
"epoch": 1.394282310899345,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048175856833312464,
|
|
"loss": 4.8767,
|
|
"mean_token_accuracy": 0.1995529994368553,
|
|
"num_tokens": 32732690.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.0818134307861325,
|
|
"epoch": 1.3948779035139964,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048174175702189,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.19879720360040665,
|
|
"num_tokens": 32747239.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.048429012298584,
|
|
"epoch": 1.395473496128648,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048172493829516465,
|
|
"loss": 4.8793,
|
|
"mean_token_accuracy": 0.19739387929439545,
|
|
"num_tokens": 32760354.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.089606904983521,
|
|
"epoch": 1.3960690887432996,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004817081121535518,
|
|
"loss": 4.9102,
|
|
"mean_token_accuracy": 0.19408032149076462,
|
|
"num_tokens": 32774123.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.192386674880981,
|
|
"epoch": 1.3966646813579513,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004816912785976552,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.19565215855836868,
|
|
"num_tokens": 32786507.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.090840625762939,
|
|
"epoch": 1.3972602739726028,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048167443762807844,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.18559511005878448,
|
|
"num_tokens": 32801897.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.090625381469726,
|
|
"epoch": 1.3978558665872542,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004816575892454256,
|
|
"loss": 4.8472,
|
|
"mean_token_accuracy": 0.20037642121315002,
|
|
"num_tokens": 32815177.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.04788122177124,
|
|
"epoch": 1.398451459201906,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000481640733450301,
|
|
"loss": 4.8628,
|
|
"mean_token_accuracy": 0.19813018590211867,
|
|
"num_tokens": 32830167.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.090689420700073,
|
|
"epoch": 1.3990470518165574,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004816238702433094,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.19138024002313614,
|
|
"num_tokens": 32844125.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.070165205001831,
|
|
"epoch": 1.3996426444312091,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048160699962505546,
|
|
"loss": 4.92,
|
|
"mean_token_accuracy": 0.20237033665180207,
|
|
"num_tokens": 32857939.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.058046483993531,
|
|
"epoch": 1.4002382370458606,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048159012159614434,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.1926035463809967,
|
|
"num_tokens": 32871251.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.137855005264282,
|
|
"epoch": 1.4008338296605123,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004815732361571815,
|
|
"loss": 4.9436,
|
|
"mean_token_accuracy": 0.193677918612957,
|
|
"num_tokens": 32885202.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.151924753189087,
|
|
"epoch": 1.4014294222751638,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048155634330877253,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.20098892599344254,
|
|
"num_tokens": 32898538.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.102667570114136,
|
|
"epoch": 1.4020250148898152,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004815394430515234,
|
|
"loss": 4.9148,
|
|
"mean_token_accuracy": 0.18939500004053117,
|
|
"num_tokens": 32913902.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.093113756179809,
|
|
"epoch": 1.402620607504467,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004815225353860402,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.19471451938152312,
|
|
"num_tokens": 32927830.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.07987003326416,
|
|
"epoch": 1.4032162001191186,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004815056203129294,
|
|
"loss": 4.9183,
|
|
"mean_token_accuracy": 0.20304875075817108,
|
|
"num_tokens": 32942808.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.184471178054809,
|
|
"epoch": 1.40381179273377,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004814886978327978,
|
|
"loss": 4.8956,
|
|
"mean_token_accuracy": 0.1943587765097618,
|
|
"num_tokens": 32955300.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.042125082015991,
|
|
"epoch": 1.4044073853484216,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048147176794625235,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.19435079544782638,
|
|
"num_tokens": 32970138.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.147257900238037,
|
|
"epoch": 1.4050029779630733,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004814548306539003,
|
|
"loss": 4.899,
|
|
"mean_token_accuracy": 0.20154993683099748,
|
|
"num_tokens": 32983476.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.079189014434815,
|
|
"epoch": 1.405598570577725,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048143788595634917,
|
|
"loss": 4.8748,
|
|
"mean_token_accuracy": 0.19691213816404343,
|
|
"num_tokens": 32996026.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.008667993545532,
|
|
"epoch": 1.4061941631923764,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004814209338542067,
|
|
"loss": 4.8329,
|
|
"mean_token_accuracy": 0.1971006602048874,
|
|
"num_tokens": 33008470.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.05773229598999,
|
|
"epoch": 1.406789755807028,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048140397434808094,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.19484224617481233,
|
|
"num_tokens": 33022753.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.105011701583862,
|
|
"epoch": 1.4073853484216796,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048138700743858014,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.20170621424913407,
|
|
"num_tokens": 33036426.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.059801530838013,
|
|
"epoch": 1.407980941036331,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048137003312631306,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.19998858869075775,
|
|
"num_tokens": 33050906.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.101298522949219,
|
|
"epoch": 1.4085765336509828,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004813530514118884,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.19169580638408662,
|
|
"num_tokens": 33066188.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.0209572315216064,
|
|
"epoch": 1.4091721262656343,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048133606229591524,
|
|
"loss": 4.7887,
|
|
"mean_token_accuracy": 0.20364614427089692,
|
|
"num_tokens": 33080169.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 4.97596549987793,
|
|
"epoch": 1.409767718880286,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004813190657790031,
|
|
"loss": 4.8524,
|
|
"mean_token_accuracy": 0.20110474526882172,
|
|
"num_tokens": 33093764.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.073312044143677,
|
|
"epoch": 1.4103633114949374,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048130206186176145,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.1994575247168541,
|
|
"num_tokens": 33105689.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.132469558715821,
|
|
"epoch": 1.410958904109589,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048128505054480036,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.20178509801626204,
|
|
"num_tokens": 33119600.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.125113201141358,
|
|
"epoch": 1.4115544967242406,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004812680318287298,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.1930893689393997,
|
|
"num_tokens": 33133531.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.05572247505188,
|
|
"epoch": 1.4121500893388923,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004812510057141603,
|
|
"loss": 4.8434,
|
|
"mean_token_accuracy": 0.20208818316459656,
|
|
"num_tokens": 33147856.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.042782926559449,
|
|
"epoch": 1.4127456819535438,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004812339722017027,
|
|
"loss": 4.8737,
|
|
"mean_token_accuracy": 0.1997864931821823,
|
|
"num_tokens": 33162842.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.056982755661011,
|
|
"epoch": 1.4133412745681952,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004812169312919677,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.19733578711748123,
|
|
"num_tokens": 33176125.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.01579532623291,
|
|
"epoch": 1.413936867182847,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048119988298556674,
|
|
"loss": 4.7516,
|
|
"mean_token_accuracy": 0.20917680561542512,
|
|
"num_tokens": 33188738.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.028995227813721,
|
|
"epoch": 1.4145324597974986,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004811828272831112,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.20431580096483232,
|
|
"num_tokens": 33201176.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.107737493515015,
|
|
"epoch": 1.4151280524121501,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004811657641852129,
|
|
"loss": 4.9472,
|
|
"mean_token_accuracy": 0.1963052824139595,
|
|
"num_tokens": 33216250.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.053865575790406,
|
|
"epoch": 1.4157236450268016,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048114869369248386,
|
|
"loss": 4.8744,
|
|
"mean_token_accuracy": 0.19973356723785402,
|
|
"num_tokens": 33229327.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.0435706615448,
|
|
"epoch": 1.4163192376414533,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004811316158055363,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.20624715685844422,
|
|
"num_tokens": 33241008.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.097147226333618,
|
|
"epoch": 1.4169148302561048,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004811145305249828,
|
|
"loss": 4.8864,
|
|
"mean_token_accuracy": 0.2015396237373352,
|
|
"num_tokens": 33254294.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.062324333190918,
|
|
"epoch": 1.4175104228707565,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048109743785143636,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.20209551453590394,
|
|
"num_tokens": 33265769.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.066175079345703,
|
|
"epoch": 1.418106015485408,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004810803377855098,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.1981505796313286,
|
|
"num_tokens": 33279410.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.080475616455078,
|
|
"epoch": 1.4187016081000596,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004810632303278166,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.18891774713993073,
|
|
"num_tokens": 33295324.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.108650064468383,
|
|
"epoch": 1.419297200714711,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004810461154789704,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.19085636287927626,
|
|
"num_tokens": 33308592.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.211396074295044,
|
|
"epoch": 1.4198927933293626,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000481028993239585,
|
|
"loss": 4.9816,
|
|
"mean_token_accuracy": 0.1907342940568924,
|
|
"num_tokens": 33323711.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.04191222190857,
|
|
"epoch": 1.4204883859440143,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004810118636102747,
|
|
"loss": 4.8976,
|
|
"mean_token_accuracy": 0.19076189696788787,
|
|
"num_tokens": 33337170.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.0607678413391115,
|
|
"epoch": 1.421083978558666,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004809947265916537,
|
|
"loss": 4.9507,
|
|
"mean_token_accuracy": 0.19710449427366256,
|
|
"num_tokens": 33351458.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.075964164733887,
|
|
"epoch": 1.4216795711733174,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048097758218433687,
|
|
"loss": 4.7803,
|
|
"mean_token_accuracy": 0.21017860472202302,
|
|
"num_tokens": 33364274.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.077854108810425,
|
|
"epoch": 1.422275163787969,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048096043038893895,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.19953414052724838,
|
|
"num_tokens": 33376599.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.075327777862549,
|
|
"epoch": 1.4228707564026206,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048094327120607534,
|
|
"loss": 4.9503,
|
|
"mean_token_accuracy": 0.1944582611322403,
|
|
"num_tokens": 33391350.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.100714302062988,
|
|
"epoch": 1.4234663490172723,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048092610463636143,
|
|
"loss": 4.8577,
|
|
"mean_token_accuracy": 0.1954167127609253,
|
|
"num_tokens": 33404892.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.02305417060852,
|
|
"epoch": 1.4240619416319238,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000480908930680413,
|
|
"loss": 4.8179,
|
|
"mean_token_accuracy": 0.20302421748638153,
|
|
"num_tokens": 33419051.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.050801229476929,
|
|
"epoch": 1.4246575342465753,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048089174933884597,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.19677211046218873,
|
|
"num_tokens": 33430871.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.047206592559815,
|
|
"epoch": 1.425253126861227,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048087456061227666,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.2024669587612152,
|
|
"num_tokens": 33442616.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.2212286472320555,
|
|
"epoch": 1.4258487194758784,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048085736450132155,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.19090158939361573,
|
|
"num_tokens": 33456087.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.0945757865905765,
|
|
"epoch": 1.4264443120905301,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048084016100659755,
|
|
"loss": 4.8925,
|
|
"mean_token_accuracy": 0.1982961043715477,
|
|
"num_tokens": 33468369.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.038468980789185,
|
|
"epoch": 1.4270399047051816,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004808229501287216,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.20244679749011993,
|
|
"num_tokens": 33482281.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.111290073394775,
|
|
"epoch": 1.4276354973198333,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048080573186831113,
|
|
"loss": 4.8863,
|
|
"mean_token_accuracy": 0.19647455364465713,
|
|
"num_tokens": 33495863.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.116775608062744,
|
|
"epoch": 1.4282310899344848,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048078850622598355,
|
|
"loss": 4.8942,
|
|
"mean_token_accuracy": 0.19538683146238328,
|
|
"num_tokens": 33510069.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.011566925048828,
|
|
"epoch": 1.4288266825491365,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048077127320235696,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.20494753271341323,
|
|
"num_tokens": 33521835.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.042483139038086,
|
|
"epoch": 1.429422275163788,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048075403279804934,
|
|
"loss": 4.9545,
|
|
"mean_token_accuracy": 0.19382627159357071,
|
|
"num_tokens": 33535239.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.429422275163788,
|
|
"eval_entropy": 4.912313226921057,
|
|
"eval_loss": 4.9416704177856445,
|
|
"eval_mean_token_accuracy": 0.20385776370366726,
|
|
"eval_num_tokens": 33535239.0,
|
|
"eval_runtime": 24.3082,
|
|
"eval_samples_per_second": 1049.565,
|
|
"eval_steps_per_second": 131.232,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.067429685592652,
|
|
"epoch": 1.4300178677784396,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004807367850136791,
|
|
"loss": 4.8115,
|
|
"mean_token_accuracy": 0.20663004368543625,
|
|
"num_tokens": 33548212.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.098349332809448,
|
|
"epoch": 1.4306134603930911,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004807195298498649,
|
|
"loss": 4.9431,
|
|
"mean_token_accuracy": 0.19513694941997528,
|
|
"num_tokens": 33562316.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.098588323593139,
|
|
"epoch": 1.4312090530077426,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004807022673072257,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.1905798777937889,
|
|
"num_tokens": 33576278.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.086912441253662,
|
|
"epoch": 1.4318046456223943,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048068499738638046,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.198725888133049,
|
|
"num_tokens": 33591021.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.025033283233642,
|
|
"epoch": 1.432400238237046,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004806677200879489,
|
|
"loss": 4.8882,
|
|
"mean_token_accuracy": 0.19868384897708893,
|
|
"num_tokens": 33605225.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.156198501586914,
|
|
"epoch": 1.4329958308516975,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004806504354125505,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.19640801697969437,
|
|
"num_tokens": 33618586.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.186586141586304,
|
|
"epoch": 1.433591423466349,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048063314336080554,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.19479359686374664,
|
|
"num_tokens": 33631036.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.070966720581055,
|
|
"epoch": 1.4341870160810006,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004806158439333339,
|
|
"loss": 4.8757,
|
|
"mean_token_accuracy": 0.19676871746778488,
|
|
"num_tokens": 33644942.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.054546928405761,
|
|
"epoch": 1.434782608695652,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048059853713075637,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.1959149420261383,
|
|
"num_tokens": 33659005.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.106022310256958,
|
|
"epoch": 1.4353782013103038,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048058122295369354,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.19575738906860352,
|
|
"num_tokens": 33672345.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.123365497589111,
|
|
"epoch": 1.4359737939249553,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004805639014027665,
|
|
"loss": 4.9322,
|
|
"mean_token_accuracy": 0.19951179921627044,
|
|
"num_tokens": 33686938.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.075331735610962,
|
|
"epoch": 1.436569386539607,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004805465724785966,
|
|
"loss": 4.8941,
|
|
"mean_token_accuracy": 0.19142646789550782,
|
|
"num_tokens": 33702145.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.0782684803009035,
|
|
"epoch": 1.4371649791542584,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004805292361818053,
|
|
"loss": 4.8959,
|
|
"mean_token_accuracy": 0.1937618911266327,
|
|
"num_tokens": 33716127.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.099997043609619,
|
|
"epoch": 1.4377605717689101,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048051189251301443,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.19407561123371125,
|
|
"num_tokens": 33731309.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.058351755142212,
|
|
"epoch": 1.4383561643835616,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004804945414728461,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.1984553262591362,
|
|
"num_tokens": 33745632.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.091528129577637,
|
|
"epoch": 1.4389517569982133,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004804771830619227,
|
|
"loss": 4.876,
|
|
"mean_token_accuracy": 0.19429363012313844,
|
|
"num_tokens": 33757623.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.145417928695679,
|
|
"epoch": 1.4395473496128648,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048045981728086687,
|
|
"loss": 4.9826,
|
|
"mean_token_accuracy": 0.19386824369430541,
|
|
"num_tokens": 33772072.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.1182585716247555,
|
|
"epoch": 1.4401429422275163,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004804424441303015,
|
|
"loss": 4.9054,
|
|
"mean_token_accuracy": 0.188898204267025,
|
|
"num_tokens": 33786548.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.026247501373291,
|
|
"epoch": 1.440738534842168,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004804250636108496,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.19951406121253967,
|
|
"num_tokens": 33800872.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.169313955307007,
|
|
"epoch": 1.4413341274568197,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004804076757231347,
|
|
"loss": 4.9247,
|
|
"mean_token_accuracy": 0.19477715939283372,
|
|
"num_tokens": 33813487.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.038895845413208,
|
|
"epoch": 1.4419297200714711,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048039028046778043,
|
|
"loss": 4.7752,
|
|
"mean_token_accuracy": 0.20234012603759766,
|
|
"num_tokens": 33827971.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 4.993108558654785,
|
|
"epoch": 1.4425253126861226,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004803728778454108,
|
|
"loss": 4.8191,
|
|
"mean_token_accuracy": 0.2047451451420784,
|
|
"num_tokens": 33841454.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.0112251281738285,
|
|
"epoch": 1.4431209053007743,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048035546785664987,
|
|
"loss": 4.7734,
|
|
"mean_token_accuracy": 0.20202205181121827,
|
|
"num_tokens": 33855893.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.096031045913696,
|
|
"epoch": 1.4437164979154258,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004803380505021222,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.19303159266710282,
|
|
"num_tokens": 33869803.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.077349424362183,
|
|
"epoch": 1.4443120905300775,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048032062578245256,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.19155652076005936,
|
|
"num_tokens": 33882898.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 4.998797225952148,
|
|
"epoch": 1.444907683144729,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048030319369826594,
|
|
"loss": 4.8372,
|
|
"mean_token_accuracy": 0.19450991302728654,
|
|
"num_tokens": 33897738.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 4.999191093444824,
|
|
"epoch": 1.4455032757593806,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004802857542501875,
|
|
"loss": 4.7759,
|
|
"mean_token_accuracy": 0.20393698513507844,
|
|
"num_tokens": 33911450.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.0752640724182125,
|
|
"epoch": 1.4460988683740321,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048026830743884283,
|
|
"loss": 4.9238,
|
|
"mean_token_accuracy": 0.20022774785757064,
|
|
"num_tokens": 33924879.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.115023803710938,
|
|
"epoch": 1.4466944609886838,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004802508532648578,
|
|
"loss": 4.8797,
|
|
"mean_token_accuracy": 0.19822093099355698,
|
|
"num_tokens": 33938450.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.0737847805023195,
|
|
"epoch": 1.4472900536033353,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004802333917288583,
|
|
"loss": 4.9954,
|
|
"mean_token_accuracy": 0.19129661619663238,
|
|
"num_tokens": 33952263.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.028934288024902,
|
|
"epoch": 1.447885646217987,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048021592283147073,
|
|
"loss": 4.8786,
|
|
"mean_token_accuracy": 0.1989601209759712,
|
|
"num_tokens": 33964501.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.028714799880982,
|
|
"epoch": 1.4484812388326385,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048019844657332166,
|
|
"loss": 4.8696,
|
|
"mean_token_accuracy": 0.2026026576757431,
|
|
"num_tokens": 33979755.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.160545444488525,
|
|
"epoch": 1.44907683144729,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000480180962955038,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.19278474748134614,
|
|
"num_tokens": 33995351.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.089278841018677,
|
|
"epoch": 1.4496724240619416,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048016347197724676,
|
|
"loss": 4.8772,
|
|
"mean_token_accuracy": 0.20069044679403306,
|
|
"num_tokens": 34008245.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.136579704284668,
|
|
"epoch": 1.4502680166765933,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004801459736405754,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.19421831667423248,
|
|
"num_tokens": 34022434.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.062407493591309,
|
|
"epoch": 1.4508636092912448,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048012846794565143,
|
|
"loss": 4.8617,
|
|
"mean_token_accuracy": 0.2016781598329544,
|
|
"num_tokens": 34036240.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.011302804946899,
|
|
"epoch": 1.4514592019058963,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004801109548931029,
|
|
"loss": 4.8539,
|
|
"mean_token_accuracy": 0.20274409800767898,
|
|
"num_tokens": 34049163.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.0854856967926025,
|
|
"epoch": 1.452054794520548,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004800934344835579,
|
|
"loss": 4.9994,
|
|
"mean_token_accuracy": 0.19696486443281175,
|
|
"num_tokens": 34063121.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.113769292831421,
|
|
"epoch": 1.4526503871351995,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004800759067176448,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.19710831642150878,
|
|
"num_tokens": 34076197.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.0909497261047365,
|
|
"epoch": 1.4532459797498511,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004800583715959924,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.1854727566242218,
|
|
"num_tokens": 34090273.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.121284294128418,
|
|
"epoch": 1.4538415723645026,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004800408291192297,
|
|
"loss": 4.9399,
|
|
"mean_token_accuracy": 0.19851916134357453,
|
|
"num_tokens": 34104907.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.054780721664429,
|
|
"epoch": 1.4544371649791543,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004800232792879858,
|
|
"loss": 4.7688,
|
|
"mean_token_accuracy": 0.208526411652565,
|
|
"num_tokens": 34118629.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 4.9983439445495605,
|
|
"epoch": 1.4550327575938058,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048000572210289016,
|
|
"loss": 4.8949,
|
|
"mean_token_accuracy": 0.19787897616624833,
|
|
"num_tokens": 34132359.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.1066834926605225,
|
|
"epoch": 1.4556283502084575,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047998815756457265,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.19295645654201507,
|
|
"num_tokens": 34144410.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.059017133712769,
|
|
"epoch": 1.456223942823109,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00047997058567366313,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.20112348049879075,
|
|
"num_tokens": 34159462.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.025352668762207,
|
|
"epoch": 1.4568195354377607,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004799530064307921,
|
|
"loss": 4.8588,
|
|
"mean_token_accuracy": 0.19714813232421874,
|
|
"num_tokens": 34173604.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.113565254211426,
|
|
"epoch": 1.4574151280524121,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047993541983658983,
|
|
"loss": 4.8695,
|
|
"mean_token_accuracy": 0.20420139133930207,
|
|
"num_tokens": 34186378.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.091687250137329,
|
|
"epoch": 1.4580107206670636,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047991782589168724,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.19682114720344543,
|
|
"num_tokens": 34199377.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.031019449234009,
|
|
"epoch": 1.4586063132817153,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004799002245967156,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.2068015918135643,
|
|
"num_tokens": 34213081.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.136888551712036,
|
|
"epoch": 1.459201905896367,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047988261595230587,
|
|
"loss": 4.9698,
|
|
"mean_token_accuracy": 0.18959058523178102,
|
|
"num_tokens": 34228750.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.116028451919556,
|
|
"epoch": 1.4597974985110185,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047986499995908996,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.19245352149009703,
|
|
"num_tokens": 34241517.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.042967128753662,
|
|
"epoch": 1.46039309112567,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004798473766176994,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.1967308849096298,
|
|
"num_tokens": 34254182.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.081711673736573,
|
|
"epoch": 1.4609886837403216,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047982974592876665,
|
|
"loss": 4.8793,
|
|
"mean_token_accuracy": 0.20490729361772536,
|
|
"num_tokens": 34267781.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.067195415496826,
|
|
"epoch": 1.4615842763549731,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047981210789292396,
|
|
"loss": 4.8465,
|
|
"mean_token_accuracy": 0.19432325065135955,
|
|
"num_tokens": 34282182.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.0150721073150635,
|
|
"epoch": 1.4621798689696248,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004797944625108039,
|
|
"loss": 4.7729,
|
|
"mean_token_accuracy": 0.20976054072380065,
|
|
"num_tokens": 34296199.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.146273469924926,
|
|
"epoch": 1.4627754615842763,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047977680978303946,
|
|
"loss": 4.9967,
|
|
"mean_token_accuracy": 0.19253967106342315,
|
|
"num_tokens": 34311066.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.148640775680542,
|
|
"epoch": 1.463371054198928,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004797591497102638,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.19572353214025498,
|
|
"num_tokens": 34325910.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.105310535430908,
|
|
"epoch": 1.4639666468135795,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047974148229311034,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.2012073278427124,
|
|
"num_tokens": 34338621.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.10991644859314,
|
|
"epoch": 1.4645622394282312,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004797238075322128,
|
|
"loss": 4.8355,
|
|
"mean_token_accuracy": 0.2065172791481018,
|
|
"num_tokens": 34352895.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.104197645187378,
|
|
"epoch": 1.4651578320428826,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004797061254282052,
|
|
"loss": 4.8869,
|
|
"mean_token_accuracy": 0.1989985629916191,
|
|
"num_tokens": 34367070.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.0155921459198,
|
|
"epoch": 1.4657534246575343,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004796884359817217,
|
|
"loss": 4.842,
|
|
"mean_token_accuracy": 0.2012215495109558,
|
|
"num_tokens": 34381080.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.007543325424194,
|
|
"epoch": 1.4663490172721858,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004796707391933967,
|
|
"loss": 4.7997,
|
|
"mean_token_accuracy": 0.2043159633874893,
|
|
"num_tokens": 34393658.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.046040487289429,
|
|
"epoch": 1.4669446098868373,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004796530350638652,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.20110260248184203,
|
|
"num_tokens": 34406301.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.120523929595947,
|
|
"epoch": 1.467540202501489,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000479635323593762,
|
|
"loss": 5.0061,
|
|
"mean_token_accuracy": 0.18909891545772553,
|
|
"num_tokens": 34421774.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.097057437896728,
|
|
"epoch": 1.4681357951161407,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047961760478372245,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.19536200910806656,
|
|
"num_tokens": 34434256.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.070156145095825,
|
|
"epoch": 1.4687313877307921,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047959987863438214,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.2045823484659195,
|
|
"num_tokens": 34447351.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.092617988586426,
|
|
"epoch": 1.4693269803454436,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004795821451463769,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.1899266168475151,
|
|
"num_tokens": 34461915.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.176477670669556,
|
|
"epoch": 1.4699225729600953,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047956440432034265,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.1846576064825058,
|
|
"num_tokens": 34477451.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.140437412261963,
|
|
"epoch": 1.4705181655747468,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047954665615691577,
|
|
"loss": 4.8782,
|
|
"mean_token_accuracy": 0.19384331852197648,
|
|
"num_tokens": 34492316.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.080441284179687,
|
|
"epoch": 1.4711137581893985,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004795289006567331,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.1944213405251503,
|
|
"num_tokens": 34507284.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.086479425430298,
|
|
"epoch": 1.47170935080405,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047951113782043113,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.1903740793466568,
|
|
"num_tokens": 34521149.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.102617263793945,
|
|
"epoch": 1.4723049434187017,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004794933676486472,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.2005569338798523,
|
|
"num_tokens": 34535827.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.086589288711548,
|
|
"epoch": 1.4729005360333531,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004794755901420187,
|
|
"loss": 4.9444,
|
|
"mean_token_accuracy": 0.19219590723514557,
|
|
"num_tokens": 34548726.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.0260851860046385,
|
|
"epoch": 1.4734961286480048,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004794578053011833,
|
|
"loss": 4.8106,
|
|
"mean_token_accuracy": 0.20034802109003066,
|
|
"num_tokens": 34563382.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.102978515625,
|
|
"epoch": 1.4740917212626563,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047944001312677867,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.19537833482027053,
|
|
"num_tokens": 34575887.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.039721918106079,
|
|
"epoch": 1.474687313877308,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047942221361944333,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.1978761851787567,
|
|
"num_tokens": 34589694.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.060530281066894,
|
|
"epoch": 1.4752829064919595,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047940440677981546,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.19917038977146148,
|
|
"num_tokens": 34602765.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.0655293464660645,
|
|
"epoch": 1.475878499106611,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004793865926085339,
|
|
"loss": 4.8737,
|
|
"mean_token_accuracy": 0.20006729811429977,
|
|
"num_tokens": 34616633.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.114224052429199,
|
|
"epoch": 1.4764740917212626,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004793687711062376,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.1967107817530632,
|
|
"num_tokens": 34630095.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.047637033462524,
|
|
"epoch": 1.4770696843359143,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004793509422735657,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.20017796605825425,
|
|
"num_tokens": 34643838.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.097149276733399,
|
|
"epoch": 1.4776652769505658,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047933310611115776,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.1954151213169098,
|
|
"num_tokens": 34658122.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.127599859237671,
|
|
"epoch": 1.4782608695652173,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047931526261965363,
|
|
"loss": 4.9138,
|
|
"mean_token_accuracy": 0.19096167236566544,
|
|
"num_tokens": 34674228.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 4.9750231266021725,
|
|
"epoch": 1.478856462179869,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004792974117996931,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.19768683314323426,
|
|
"num_tokens": 34687624.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 4.9758647918701175,
|
|
"epoch": 1.4794520547945205,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004792795536519167,
|
|
"loss": 4.8096,
|
|
"mean_token_accuracy": 0.2090550556778908,
|
|
"num_tokens": 34702749.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.111031198501587,
|
|
"epoch": 1.4800476474091722,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047926168817696477,
|
|
"loss": 4.8589,
|
|
"mean_token_accuracy": 0.19519663602113724,
|
|
"num_tokens": 34716174.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.041985130310058,
|
|
"epoch": 1.4806432400238236,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004792438153754782,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.19552251249551772,
|
|
"num_tokens": 34731065.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.058709812164307,
|
|
"epoch": 1.4812388326384753,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047922593524809805,
|
|
"loss": 4.8333,
|
|
"mean_token_accuracy": 0.20071442127227784,
|
|
"num_tokens": 34745167.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.072683429718017,
|
|
"epoch": 1.4818344252531268,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004792080477954657,
|
|
"loss": 4.8566,
|
|
"mean_token_accuracy": 0.19922332763671874,
|
|
"num_tokens": 34758243.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.074614524841309,
|
|
"epoch": 1.4824300178677785,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047919015301822255,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.19545771777629853,
|
|
"num_tokens": 34771511.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.058106565475464,
|
|
"epoch": 1.48302561048243,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004791722509170108,
|
|
"loss": 4.8405,
|
|
"mean_token_accuracy": 0.20134710967540742,
|
|
"num_tokens": 34784480.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.092716360092163,
|
|
"epoch": 1.4836212030970817,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047915434149247224,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.19244660437107086,
|
|
"num_tokens": 34799501.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.0955909252166744,
|
|
"epoch": 1.4842167957117332,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047913642474524946,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.19447962045669556,
|
|
"num_tokens": 34813020.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.095021152496338,
|
|
"epoch": 1.4848123883263846,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047911850067598494,
|
|
"loss": 4.8617,
|
|
"mean_token_accuracy": 0.1932941570878029,
|
|
"num_tokens": 34826214.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.0670746803283695,
|
|
"epoch": 1.4854079809410363,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047910056928532173,
|
|
"loss": 4.8775,
|
|
"mean_token_accuracy": 0.20518416911363602,
|
|
"num_tokens": 34839999.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.130933332443237,
|
|
"epoch": 1.486003573555688,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000479082630573903,
|
|
"loss": 4.9073,
|
|
"mean_token_accuracy": 0.19825432151556016,
|
|
"num_tokens": 34854272.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.108645343780518,
|
|
"epoch": 1.4865991661703395,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004790646845423721,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.19329133331775666,
|
|
"num_tokens": 34870855.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.072538042068482,
|
|
"epoch": 1.487194758784991,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004790467311913727,
|
|
"loss": 4.9304,
|
|
"mean_token_accuracy": 0.1931159868836403,
|
|
"num_tokens": 34884171.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.073329162597656,
|
|
"epoch": 1.4877903513996427,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047902877052154885,
|
|
"loss": 4.8775,
|
|
"mean_token_accuracy": 0.19821361899375917,
|
|
"num_tokens": 34897642.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.117548227310181,
|
|
"epoch": 1.4883859440142944,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047901080253354476,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.19177166372537613,
|
|
"num_tokens": 34911737.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.002050065994263,
|
|
"epoch": 1.4889815366289458,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047899282722800487,
|
|
"loss": 4.8073,
|
|
"mean_token_accuracy": 0.2030245393514633,
|
|
"num_tokens": 34925423.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.1664379119873045,
|
|
"epoch": 1.4895771292435973,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047897484460557397,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.18545585870742798,
|
|
"num_tokens": 34938895.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.100258779525757,
|
|
"epoch": 1.490172721858249,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000478956854666897,
|
|
"loss": 4.9625,
|
|
"mean_token_accuracy": 0.19102677553892136,
|
|
"num_tokens": 34952365.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.147782897949218,
|
|
"epoch": 1.4907683144729005,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047893885741261924,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.18565695583820344,
|
|
"num_tokens": 34968134.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.100422286987305,
|
|
"epoch": 1.4913639070875522,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004789208528433862,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.19324470162391663,
|
|
"num_tokens": 34982572.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.093729782104492,
|
|
"epoch": 1.4919594997022037,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004789028409598438,
|
|
"loss": 4.808,
|
|
"mean_token_accuracy": 0.20357076972723007,
|
|
"num_tokens": 34995403.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.045497465133667,
|
|
"epoch": 1.4925550923168553,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047888482176263803,
|
|
"loss": 4.8905,
|
|
"mean_token_accuracy": 0.19915167093276978,
|
|
"num_tokens": 35008537.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 4.982853412628174,
|
|
"epoch": 1.4931506849315068,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00047886679525241524,
|
|
"loss": 4.8144,
|
|
"mean_token_accuracy": 0.20220445990562438,
|
|
"num_tokens": 35021988.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.0365743160247805,
|
|
"epoch": 1.4937462775461583,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004788487614298219,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.19633273929357528,
|
|
"num_tokens": 35037381.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.038672924041748,
|
|
"epoch": 1.49434187016081,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047883072029550496,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.20956461280584335,
|
|
"num_tokens": 35052556.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.135049819946289,
|
|
"epoch": 1.4949374627754617,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047881267185011147,
|
|
"loss": 4.9653,
|
|
"mean_token_accuracy": 0.1865813612937927,
|
|
"num_tokens": 35066001.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.138626623153686,
|
|
"epoch": 1.4955330553901132,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047879461609428876,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.1934197276830673,
|
|
"num_tokens": 35080733.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.080583095550537,
|
|
"epoch": 1.4961286480047646,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004787765530286846,
|
|
"loss": 4.8891,
|
|
"mean_token_accuracy": 0.19231707155704497,
|
|
"num_tokens": 35095142.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.047094297409058,
|
|
"epoch": 1.4967242406194163,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004787584826539468,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.20527826398611068,
|
|
"num_tokens": 35108151.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.136677074432373,
|
|
"epoch": 1.497319833234068,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004787404049707235,
|
|
"loss": 4.9507,
|
|
"mean_token_accuracy": 0.18851322680711746,
|
|
"num_tokens": 35125011.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 4.988978910446167,
|
|
"epoch": 1.4979154258487195,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047872231997966316,
|
|
"loss": 4.9005,
|
|
"mean_token_accuracy": 0.19982920438051224,
|
|
"num_tokens": 35138949.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.126208877563476,
|
|
"epoch": 1.498511018463371,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004787042276814144,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.19727025032043458,
|
|
"num_tokens": 35152299.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.088830041885376,
|
|
"epoch": 1.4991066110780227,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047868612807662616,
|
|
"loss": 4.8541,
|
|
"mean_token_accuracy": 0.2026504784822464,
|
|
"num_tokens": 35165643.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.03585000038147,
|
|
"epoch": 1.4997022036926742,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047866802116594776,
|
|
"loss": 4.9001,
|
|
"mean_token_accuracy": 0.19799810349941255,
|
|
"num_tokens": 35179214.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.160584211349487,
|
|
"epoch": 1.5002977963073256,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004786499069500286,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.1847259521484375,
|
|
"num_tokens": 35194040.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.164212465286255,
|
|
"epoch": 1.5008933889219773,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047863178542951833,
|
|
"loss": 4.9272,
|
|
"mean_token_accuracy": 0.19603139907121658,
|
|
"num_tokens": 35207572.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.074868631362915,
|
|
"epoch": 1.501488981536629,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000478613656605067,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.1957961216568947,
|
|
"num_tokens": 35221637.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.149375152587891,
|
|
"epoch": 1.5020845741512805,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047859552047732493,
|
|
"loss": 5.0024,
|
|
"mean_token_accuracy": 0.19041089862585067,
|
|
"num_tokens": 35234905.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.109248876571655,
|
|
"epoch": 1.502680166765932,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047857737704694255,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.20224559754133226,
|
|
"num_tokens": 35248773.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.0813675880432125,
|
|
"epoch": 1.5032757593805837,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004785592263145705,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.1999616488814354,
|
|
"num_tokens": 35261978.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 4.988046407699585,
|
|
"epoch": 1.5038713519952354,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047854106828086016,
|
|
"loss": 4.8524,
|
|
"mean_token_accuracy": 0.19956487268209458,
|
|
"num_tokens": 35278130.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.099100160598755,
|
|
"epoch": 1.5044669446098868,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047852290294646255,
|
|
"loss": 4.9186,
|
|
"mean_token_accuracy": 0.1897153303027153,
|
|
"num_tokens": 35289988.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.097513246536255,
|
|
"epoch": 1.5050625372245383,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047850473031202937,
|
|
"loss": 4.8602,
|
|
"mean_token_accuracy": 0.2001725435256958,
|
|
"num_tokens": 35303555.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.057037734985352,
|
|
"epoch": 1.50565812983919,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004784865503782124,
|
|
"loss": 4.8035,
|
|
"mean_token_accuracy": 0.20827633142471313,
|
|
"num_tokens": 35316802.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.090446519851684,
|
|
"epoch": 1.5062537224538417,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047846836314566356,
|
|
"loss": 4.8746,
|
|
"mean_token_accuracy": 0.19497212171554565,
|
|
"num_tokens": 35329538.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.1447478294372555,
|
|
"epoch": 1.5068493150684932,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047845016861503556,
|
|
"loss": 4.9414,
|
|
"mean_token_accuracy": 0.1893742024898529,
|
|
"num_tokens": 35345213.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.048174095153809,
|
|
"epoch": 1.5074449076831447,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047843196678698063,
|
|
"loss": 4.8848,
|
|
"mean_token_accuracy": 0.20452943444252014,
|
|
"num_tokens": 35358554.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.152668094635009,
|
|
"epoch": 1.5080405002977963,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004784137576621519,
|
|
"loss": 5.0406,
|
|
"mean_token_accuracy": 0.19194261878728866,
|
|
"num_tokens": 35371015.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.117406749725342,
|
|
"epoch": 1.508636092912448,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004783955412412024,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.19986075907945633,
|
|
"num_tokens": 35384308.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.048277997970581,
|
|
"epoch": 1.5092316855270993,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004783773175247856,
|
|
"loss": 4.8544,
|
|
"mean_token_accuracy": 0.20092513412237167,
|
|
"num_tokens": 35399686.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.084872055053711,
|
|
"epoch": 1.509827278141751,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047835908651355503,
|
|
"loss": 4.9637,
|
|
"mean_token_accuracy": 0.19554429799318312,
|
|
"num_tokens": 35412809.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.148139095306396,
|
|
"epoch": 1.5104228707564027,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004783408482081646,
|
|
"loss": 4.8794,
|
|
"mean_token_accuracy": 0.1991798996925354,
|
|
"num_tokens": 35428362.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.120615434646607,
|
|
"epoch": 1.5110184633710542,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004783226026092687,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.19915635585784913,
|
|
"num_tokens": 35442381.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.020775604248047,
|
|
"epoch": 1.5116140559857056,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004783043497175215,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.20235821306705476,
|
|
"num_tokens": 35457537.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.088416481018067,
|
|
"epoch": 1.5122096486003573,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004782860895335779,
|
|
"loss": 4.9264,
|
|
"mean_token_accuracy": 0.19411651343107222,
|
|
"num_tokens": 35471970.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.026466131210327,
|
|
"epoch": 1.512805241215009,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004782678220580928,
|
|
"loss": 4.8801,
|
|
"mean_token_accuracy": 0.19930312931537628,
|
|
"num_tokens": 35485483.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.0935328006744385,
|
|
"epoch": 1.5134008338296605,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047824954729172136,
|
|
"loss": 4.8632,
|
|
"mean_token_accuracy": 0.20032692700624466,
|
|
"num_tokens": 35499766.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.1127121925354,
|
|
"epoch": 1.513996426444312,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047823126523511916,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.18584171533584595,
|
|
"num_tokens": 35514670.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.124258804321289,
|
|
"epoch": 1.5145920190589637,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004782129758889419,
|
|
"loss": 4.8962,
|
|
"mean_token_accuracy": 0.19542768448591233,
|
|
"num_tokens": 35528522.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.083000373840332,
|
|
"epoch": 1.5151876116736154,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047819467925384564,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.2020082429051399,
|
|
"num_tokens": 35542328.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.115117168426513,
|
|
"epoch": 1.5157832042882668,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004781763753304866,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.1900417372584343,
|
|
"num_tokens": 35556835.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.104057264328003,
|
|
"epoch": 1.5163787969029183,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004781580641195213,
|
|
"loss": 4.9606,
|
|
"mean_token_accuracy": 0.19206645637750625,
|
|
"num_tokens": 35572542.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.145046520233154,
|
|
"epoch": 1.51697438951757,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047813974562160654,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.1963489517569542,
|
|
"num_tokens": 35585620.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.085039186477661,
|
|
"epoch": 1.5175699821322217,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004781214198373994,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.19810651987791061,
|
|
"num_tokens": 35598367.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.066609573364258,
|
|
"epoch": 1.5181655747468732,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004781030867675572,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.19660244435071944,
|
|
"num_tokens": 35613098.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.158791971206665,
|
|
"epoch": 1.5187611673615247,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047808474641273743,
|
|
"loss": 4.9896,
|
|
"mean_token_accuracy": 0.18896398991346358,
|
|
"num_tokens": 35627243.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 4.949002027511597,
|
|
"epoch": 1.5193567599761764,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00047806639877359805,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.2041085109114647,
|
|
"num_tokens": 35639832.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.083643770217895,
|
|
"epoch": 1.5199523525908278,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004780480438507972,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.19305769652128218,
|
|
"num_tokens": 35654045.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.135514831542968,
|
|
"epoch": 1.5205479452054793,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000478029681644993,
|
|
"loss": 4.878,
|
|
"mean_token_accuracy": 0.19538603723049164,
|
|
"num_tokens": 35667900.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.0158278465271,
|
|
"epoch": 1.521143537820131,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004780113121568443,
|
|
"loss": 4.7759,
|
|
"mean_token_accuracy": 0.20630345791578292,
|
|
"num_tokens": 35680751.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.061348628997803,
|
|
"epoch": 1.5217391304347827,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047799293538700993,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.19806008040905,
|
|
"num_tokens": 35694828.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.084419775009155,
|
|
"epoch": 1.5223347230494342,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047797455133614903,
|
|
"loss": 4.8692,
|
|
"mean_token_accuracy": 0.19238579273223877,
|
|
"num_tokens": 35711587.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.07410454750061,
|
|
"epoch": 1.5229303156640857,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047795616000492086,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.1948552593588829,
|
|
"num_tokens": 35726085.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.076065540313721,
|
|
"epoch": 1.5235259082787374,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047793776139398535,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.19905059039592743,
|
|
"num_tokens": 35739748.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.139515781402588,
|
|
"epoch": 1.524121500893389,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004779193555040023,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.19353375136852263,
|
|
"num_tokens": 35752789.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.100356960296631,
|
|
"epoch": 1.5247170935080405,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047790094233563185,
|
|
"loss": 4.9487,
|
|
"mean_token_accuracy": 0.19859860390424727,
|
|
"num_tokens": 35766847.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.017546224594116,
|
|
"epoch": 1.525312686122692,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047788252188953447,
|
|
"loss": 4.8057,
|
|
"mean_token_accuracy": 0.20673452019691468,
|
|
"num_tokens": 35779590.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 4.99959077835083,
|
|
"epoch": 1.5259082787373437,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004778640941663709,
|
|
"loss": 4.8051,
|
|
"mean_token_accuracy": 0.20750753879547118,
|
|
"num_tokens": 35792387.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.013500213623047,
|
|
"epoch": 1.5265038713519954,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047784565916680216,
|
|
"loss": 4.78,
|
|
"mean_token_accuracy": 0.2061402752995491,
|
|
"num_tokens": 35806317.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.009354066848755,
|
|
"epoch": 1.5270994639666469,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047782721689148936,
|
|
"loss": 4.8191,
|
|
"mean_token_accuracy": 0.1976335436105728,
|
|
"num_tokens": 35819655.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.062789011001587,
|
|
"epoch": 1.5276950565812983,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004778087673410942,
|
|
"loss": 4.8942,
|
|
"mean_token_accuracy": 0.1934947207570076,
|
|
"num_tokens": 35835502.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.122384405136108,
|
|
"epoch": 1.52829064919595,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004777903105162782,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.19561211317777633,
|
|
"num_tokens": 35849118.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.005442762374878,
|
|
"epoch": 1.5288862418106015,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004777718464177035,
|
|
"loss": 4.8495,
|
|
"mean_token_accuracy": 0.20295441895723343,
|
|
"num_tokens": 35863186.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.073773813247681,
|
|
"epoch": 1.529481834425253,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004777533750460323,
|
|
"loss": 4.865,
|
|
"mean_token_accuracy": 0.20022812038660048,
|
|
"num_tokens": 35877221.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.037168312072754,
|
|
"epoch": 1.5300774270399047,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047773489640192724,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.19673855155706405,
|
|
"num_tokens": 35891422.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.078576517105103,
|
|
"epoch": 1.5306730196545564,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047771641048605107,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.19355324059724807,
|
|
"num_tokens": 35904705.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.132600545883179,
|
|
"epoch": 1.5312686122692079,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047769791729906685,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.20250805467367172,
|
|
"num_tokens": 35920736.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.063893890380859,
|
|
"epoch": 1.5318642048838593,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000477679416841638,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.21012482047080994,
|
|
"num_tokens": 35933878.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.090882062911987,
|
|
"epoch": 1.532459797498511,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047766090911442787,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.19970156997442245,
|
|
"num_tokens": 35949478.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.154268980026245,
|
|
"epoch": 1.5330553901131627,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004776423941181005,
|
|
"loss": 4.921,
|
|
"mean_token_accuracy": 0.1971915543079376,
|
|
"num_tokens": 35962703.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.093446540832519,
|
|
"epoch": 1.5336509827278142,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004776238718533199,
|
|
"loss": 4.8925,
|
|
"mean_token_accuracy": 0.19653392285108567,
|
|
"num_tokens": 35976670.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.100395584106446,
|
|
"epoch": 1.5342465753424657,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047760534232075045,
|
|
"loss": 4.8752,
|
|
"mean_token_accuracy": 0.20155117958784102,
|
|
"num_tokens": 35990274.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 4.986606597900391,
|
|
"epoch": 1.5348421679571174,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004775868055210568,
|
|
"loss": 4.8362,
|
|
"mean_token_accuracy": 0.2008060783147812,
|
|
"num_tokens": 36005085.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.168574810028076,
|
|
"epoch": 1.535437760571769,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047756826145490383,
|
|
"loss": 4.9511,
|
|
"mean_token_accuracy": 0.195148466527462,
|
|
"num_tokens": 36018108.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.113889932632446,
|
|
"epoch": 1.5360333531864205,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047754971012295666,
|
|
"loss": 4.8845,
|
|
"mean_token_accuracy": 0.20440611541271209,
|
|
"num_tokens": 36030541.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.045461368560791,
|
|
"epoch": 1.536628945801072,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004775311515258807,
|
|
"loss": 4.936,
|
|
"mean_token_accuracy": 0.19574854969978334,
|
|
"num_tokens": 36047250.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.133573961257935,
|
|
"epoch": 1.5372245384157237,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047751258566434176,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.18459916710853577,
|
|
"num_tokens": 36062429.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.065912961959839,
|
|
"epoch": 1.5378201310303752,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004774940125390055,
|
|
"loss": 4.8132,
|
|
"mean_token_accuracy": 0.2047448441386223,
|
|
"num_tokens": 36074431.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.088284683227539,
|
|
"epoch": 1.5384157236450267,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004774754321505383,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.20023768544197082,
|
|
"num_tokens": 36088323.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.058957052230835,
|
|
"epoch": 1.5390113162596784,
|
|
"grad_norm": 2.5625,
|
|
"learning_rate": 0.00047745684449960655,
|
|
"loss": 4.7911,
|
|
"mean_token_accuracy": 0.20438530892133713,
|
|
"num_tokens": 36101762.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.06342716217041,
|
|
"epoch": 1.53960690887433,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047743824958687694,
|
|
"loss": 4.8596,
|
|
"mean_token_accuracy": 0.20178034752607346,
|
|
"num_tokens": 36115969.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.081117486953735,
|
|
"epoch": 1.5402025014889815,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004774196474130165,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.19445479810237884,
|
|
"num_tokens": 36130179.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.094296073913574,
|
|
"epoch": 1.540798094103633,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047740103797869237,
|
|
"loss": 4.7935,
|
|
"mean_token_accuracy": 0.21048871278762818,
|
|
"num_tokens": 36143156.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.138580322265625,
|
|
"epoch": 1.5413936867182847,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047738242128457216,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.19592310935258866,
|
|
"num_tokens": 36158073.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.140140104293823,
|
|
"epoch": 1.5419892793329364,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047736379733132343,
|
|
"loss": 4.9745,
|
|
"mean_token_accuracy": 0.19191049188375472,
|
|
"num_tokens": 36172519.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.085516357421875,
|
|
"epoch": 1.5425848719475879,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047734516611961443,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.19205285012722015,
|
|
"num_tokens": 36187603.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.091636896133423,
|
|
"epoch": 1.5431804645622393,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004773265276501133,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.18963288962841035,
|
|
"num_tokens": 36200785.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.18850793838501,
|
|
"epoch": 1.543776057176891,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047730788192348856,
|
|
"loss": 4.9256,
|
|
"mean_token_accuracy": 0.19456165432929992,
|
|
"num_tokens": 36214087.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 4.994956350326538,
|
|
"epoch": 1.5443716497915427,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047728922894040905,
|
|
"loss": 4.7773,
|
|
"mean_token_accuracy": 0.2004445806145668,
|
|
"num_tokens": 36228949.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.025054979324341,
|
|
"epoch": 1.5449672424061942,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004772705687015437,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.19205513149499892,
|
|
"num_tokens": 36244637.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.138743162155151,
|
|
"epoch": 1.5455628350208457,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047725190120756207,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.19521253407001496,
|
|
"num_tokens": 36257306.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.1054627895355225,
|
|
"epoch": 1.5461584276354974,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047723322645913354,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.19241826981306076,
|
|
"num_tokens": 36271947.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.087371683120727,
|
|
"epoch": 1.5467540202501489,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047721454445692795,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.19818034768104553,
|
|
"num_tokens": 36285883.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.161929368972778,
|
|
"epoch": 1.5473496128648003,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047719585520161544,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.19280912578105927,
|
|
"num_tokens": 36303042.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.119277572631836,
|
|
"epoch": 1.547945205479452,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004771771586938664,
|
|
"loss": 4.9168,
|
|
"mean_token_accuracy": 0.19675056487321854,
|
|
"num_tokens": 36314837.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.023831033706665,
|
|
"epoch": 1.5485407980941037,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047715845493435135,
|
|
"loss": 4.8736,
|
|
"mean_token_accuracy": 0.20446984618902206,
|
|
"num_tokens": 36328836.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.114997053146363,
|
|
"epoch": 1.5491363907087552,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004771397439237412,
|
|
"loss": 4.8602,
|
|
"mean_token_accuracy": 0.20281538367271423,
|
|
"num_tokens": 36342231.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 4.986851215362549,
|
|
"epoch": 1.5497319833234067,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047712102566270715,
|
|
"loss": 4.7836,
|
|
"mean_token_accuracy": 0.2025586411356926,
|
|
"num_tokens": 36357346.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.088832712173462,
|
|
"epoch": 1.5503275759380584,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047710230015192054,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.20129512399435043,
|
|
"num_tokens": 36370476.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.1055714130401615,
|
|
"epoch": 1.55092316855271,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047708356739205294,
|
|
"loss": 4.8423,
|
|
"mean_token_accuracy": 0.19437628537416457,
|
|
"num_tokens": 36386519.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.007422399520874,
|
|
"epoch": 1.5515187611673615,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004770648273837764,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.20017735809087753,
|
|
"num_tokens": 36400725.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.109236764907837,
|
|
"epoch": 1.552114353782013,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000477046080127763,
|
|
"loss": 4.9462,
|
|
"mean_token_accuracy": 0.19073260873556136,
|
|
"num_tokens": 36414503.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.089413022994995,
|
|
"epoch": 1.5527099463966647,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004770273256246853,
|
|
"loss": 4.8595,
|
|
"mean_token_accuracy": 0.193435201048851,
|
|
"num_tokens": 36428580.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.05739951133728,
|
|
"epoch": 1.5533055390113164,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047700856387521585,
|
|
"loss": 4.8548,
|
|
"mean_token_accuracy": 0.20254828482866288,
|
|
"num_tokens": 36442971.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.051519536972046,
|
|
"epoch": 1.5539011316259679,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004769897948800276,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.20545885860919952,
|
|
"num_tokens": 36456335.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.122750329971313,
|
|
"epoch": 1.5544967242406194,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047697101863979394,
|
|
"loss": 4.9113,
|
|
"mean_token_accuracy": 0.1983325242996216,
|
|
"num_tokens": 36472934.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.041743421554566,
|
|
"epoch": 1.555092316855271,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004769522351551882,
|
|
"loss": 4.8266,
|
|
"mean_token_accuracy": 0.20691166669130326,
|
|
"num_tokens": 36485740.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.008358430862427,
|
|
"epoch": 1.5556879094699225,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004769334444268841,
|
|
"loss": 4.782,
|
|
"mean_token_accuracy": 0.19929418414831163,
|
|
"num_tokens": 36500403.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.048457765579224,
|
|
"epoch": 1.556283502084574,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047691464645555564,
|
|
"loss": 4.8727,
|
|
"mean_token_accuracy": 0.20282562971115112,
|
|
"num_tokens": 36513840.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.085481929779053,
|
|
"epoch": 1.5568790946992257,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004768958412418772,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.1987747997045517,
|
|
"num_tokens": 36526436.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 4.988798475265503,
|
|
"epoch": 1.5574746873138774,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047687702878652303,
|
|
"loss": 4.8222,
|
|
"mean_token_accuracy": 0.20122110545635224,
|
|
"num_tokens": 36541331.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.031552648544311,
|
|
"epoch": 1.5580702799285289,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00047685820909016823,
|
|
"loss": 4.8353,
|
|
"mean_token_accuracy": 0.20917263329029084,
|
|
"num_tokens": 36556309.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.128270101547241,
|
|
"epoch": 1.5586658725431803,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004768393821534877,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.19437406212091446,
|
|
"num_tokens": 36571888.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.19595046043396,
|
|
"epoch": 1.559261465157832,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004768205479771566,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.19441626816987992,
|
|
"num_tokens": 36584525.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.100781059265136,
|
|
"epoch": 1.5598570577724837,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004768017065618506,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.19827931821346284,
|
|
"num_tokens": 36598298.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.145093297958374,
|
|
"epoch": 1.5604526503871352,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047678285790824556,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.19762335419654847,
|
|
"num_tokens": 36611723.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.070038843154907,
|
|
"epoch": 1.5610482430017867,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004767640020170174,
|
|
"loss": 4.8782,
|
|
"mean_token_accuracy": 0.19869468361139297,
|
|
"num_tokens": 36625932.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.082231521606445,
|
|
"epoch": 1.5616438356164384,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004767451388888426,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.2119242012500763,
|
|
"num_tokens": 36637604.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.16679539680481,
|
|
"epoch": 1.56223942823109,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004767262685243976,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.19216007888317108,
|
|
"num_tokens": 36653078.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.089038896560669,
|
|
"epoch": 1.5628350208457416,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004767073909243594,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.1919484555721283,
|
|
"num_tokens": 36668593.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.1226564884185795,
|
|
"epoch": 1.563430613460393,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047668850608940504,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.19547672271728517,
|
|
"num_tokens": 36680442.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.090287351608277,
|
|
"epoch": 1.5640262060750447,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004766696140202119,
|
|
"loss": 4.8669,
|
|
"mean_token_accuracy": 0.20293573588132857,
|
|
"num_tokens": 36694236.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.0836035251617435,
|
|
"epoch": 1.5646217986896962,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047665071471745754,
|
|
"loss": 4.9392,
|
|
"mean_token_accuracy": 0.19980323761701585,
|
|
"num_tokens": 36709202.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.135467863082885,
|
|
"epoch": 1.5652173913043477,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047663180818181995,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.19608333557844163,
|
|
"num_tokens": 36722997.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.126704740524292,
|
|
"epoch": 1.5658129839189994,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047661289441397724,
|
|
"loss": 4.8816,
|
|
"mean_token_accuracy": 0.1970559075474739,
|
|
"num_tokens": 36736400.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 4.960795497894287,
|
|
"epoch": 1.566408576533651,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004765939734146078,
|
|
"loss": 4.8827,
|
|
"mean_token_accuracy": 0.20267634391784667,
|
|
"num_tokens": 36748844.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.0985860347747805,
|
|
"epoch": 1.5670041691483025,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004765750451843904,
|
|
"loss": 4.9264,
|
|
"mean_token_accuracy": 0.20580388009548187,
|
|
"num_tokens": 36761074.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.038354396820068,
|
|
"epoch": 1.567599761762954,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004765561097240037,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.20751319974660873,
|
|
"num_tokens": 36775492.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.092207908630371,
|
|
"epoch": 1.5681953543776057,
|
|
"grad_norm": 3.140625,
|
|
"learning_rate": 0.00047653716703412717,
|
|
"loss": 4.9058,
|
|
"mean_token_accuracy": 0.1977632075548172,
|
|
"num_tokens": 36789087.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.106161832809448,
|
|
"epoch": 1.5687909469922574,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004765182171154401,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.19692017436027526,
|
|
"num_tokens": 36804241.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.039064693450928,
|
|
"epoch": 1.5693865396069089,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004764992599686222,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.20138464570045472,
|
|
"num_tokens": 36820056.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.036371850967408,
|
|
"epoch": 1.5699821322215604,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004764802955943535,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.20423773527145386,
|
|
"num_tokens": 36834419.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.203927421569825,
|
|
"epoch": 1.570577724836212,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047646132399331413,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.19408781230449676,
|
|
"num_tokens": 36848712.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.17857084274292,
|
|
"epoch": 1.5711733174508637,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047644234516618474,
|
|
"loss": 4.9921,
|
|
"mean_token_accuracy": 0.19065269380807875,
|
|
"num_tokens": 36861773.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.128724050521851,
|
|
"epoch": 1.5717689100655152,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047642335911364585,
|
|
"loss": 4.9127,
|
|
"mean_token_accuracy": 0.19438065737485885,
|
|
"num_tokens": 36875794.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 4.998484659194946,
|
|
"epoch": 1.5723645026801667,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047640436583637865,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.2161849096417427,
|
|
"num_tokens": 36889707.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.0898443222045895,
|
|
"epoch": 1.5729600952948184,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047638536533506424,
|
|
"loss": 4.9947,
|
|
"mean_token_accuracy": 0.19422034472227095,
|
|
"num_tokens": 36904224.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.148716831207276,
|
|
"epoch": 1.5735556879094699,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047636635761038427,
|
|
"loss": 4.9635,
|
|
"mean_token_accuracy": 0.1894811972975731,
|
|
"num_tokens": 36919757.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.103899002075195,
|
|
"epoch": 1.5741512805241213,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047634734266302037,
|
|
"loss": 4.9235,
|
|
"mean_token_accuracy": 0.19757663309574128,
|
|
"num_tokens": 36933991.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.0225622177124025,
|
|
"epoch": 1.574746873138773,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004763283204936547,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.2045900985598564,
|
|
"num_tokens": 36947546.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.095321750640869,
|
|
"epoch": 1.5753424657534247,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004763092911029695,
|
|
"loss": 4.9337,
|
|
"mean_token_accuracy": 0.19823913425207138,
|
|
"num_tokens": 36963541.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.11603569984436,
|
|
"epoch": 1.5759380583680762,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004762902544916474,
|
|
"loss": 4.8998,
|
|
"mean_token_accuracy": 0.19683201611042023,
|
|
"num_tokens": 36977781.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.121506261825561,
|
|
"epoch": 1.5765336509827277,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004762712106603711,
|
|
"loss": 4.9059,
|
|
"mean_token_accuracy": 0.19403170943260192,
|
|
"num_tokens": 36991883.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.115797710418701,
|
|
"epoch": 1.5771292435973794,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047625215960982376,
|
|
"loss": 4.942,
|
|
"mean_token_accuracy": 0.1966868594288826,
|
|
"num_tokens": 37006815.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.052497148513794,
|
|
"epoch": 1.577724836212031,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047623310134068867,
|
|
"loss": 4.8398,
|
|
"mean_token_accuracy": 0.2053801715373993,
|
|
"num_tokens": 37020653.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.091080188751221,
|
|
"epoch": 1.5783204288266826,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004762140358536493,
|
|
"loss": 4.9493,
|
|
"mean_token_accuracy": 0.19465979039669037,
|
|
"num_tokens": 37034906.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.080391979217529,
|
|
"epoch": 1.578916021441334,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047619496314938977,
|
|
"loss": 4.8527,
|
|
"mean_token_accuracy": 0.19682304412126542,
|
|
"num_tokens": 37049611.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.047097969055176,
|
|
"epoch": 1.5795116140559857,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.00047617588322859395,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.20440133810043334,
|
|
"num_tokens": 37063506.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.014849758148193,
|
|
"epoch": 1.5801072066706374,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004761567960919463,
|
|
"loss": 4.8386,
|
|
"mean_token_accuracy": 0.20118388682603836,
|
|
"num_tokens": 37077100.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.122416639328003,
|
|
"epoch": 1.580702799285289,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00047613770174013146,
|
|
"loss": 4.905,
|
|
"mean_token_accuracy": 0.1964996337890625,
|
|
"num_tokens": 37090342.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.1583634376525875,
|
|
"epoch": 1.5812983918999404,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004761186001738342,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.19353241324424744,
|
|
"num_tokens": 37107377.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.085981130599976,
|
|
"epoch": 1.581893984514592,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047609949139373994,
|
|
"loss": 4.922,
|
|
"mean_token_accuracy": 0.19553768038749694,
|
|
"num_tokens": 37122160.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.063647127151489,
|
|
"epoch": 1.5824895771292438,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004760803754005337,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.19305215477943422,
|
|
"num_tokens": 37135762.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.100393772125244,
|
|
"epoch": 1.583085169743895,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004760612521949014,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.1949346110224724,
|
|
"num_tokens": 37150319.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.164216566085815,
|
|
"epoch": 1.5836807623585467,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047604212177752885,
|
|
"loss": 4.932,
|
|
"mean_token_accuracy": 0.19660891890525817,
|
|
"num_tokens": 37165629.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.116502189636231,
|
|
"epoch": 1.5842763549731984,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047602298414910237,
|
|
"loss": 4.869,
|
|
"mean_token_accuracy": 0.1965995565056801,
|
|
"num_tokens": 37179189.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.034310293197632,
|
|
"epoch": 1.5848719475878499,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047600383931030823,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.19793066531419753,
|
|
"num_tokens": 37192200.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.147958660125733,
|
|
"epoch": 1.5854675402025014,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004759846872618332,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.19286248683929444,
|
|
"num_tokens": 37205549.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.1327691078186035,
|
|
"epoch": 1.586063132817153,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047596552800436426,
|
|
"loss": 4.9299,
|
|
"mean_token_accuracy": 0.20100051909685135,
|
|
"num_tokens": 37218179.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.079767894744873,
|
|
"epoch": 1.5866587254318048,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047594636153858844,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.2084451749920845,
|
|
"num_tokens": 37232078.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.086145687103271,
|
|
"epoch": 1.5872543180464562,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047592718786519347,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.19691917002201081,
|
|
"num_tokens": 37245962.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.136071014404297,
|
|
"epoch": 1.5878499106611077,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047590800698486693,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.19358332306146622,
|
|
"num_tokens": 37262644.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.108914518356324,
|
|
"epoch": 1.5884455032757594,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004758888188982969,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.20081949681043626,
|
|
"num_tokens": 37275421.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.1033477783203125,
|
|
"epoch": 1.589041095890411,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004758696236061715,
|
|
"loss": 4.8341,
|
|
"mean_token_accuracy": 0.20166611224412917,
|
|
"num_tokens": 37289117.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.039321374893189,
|
|
"epoch": 1.5896366885050626,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004758504211091793,
|
|
"loss": 4.8868,
|
|
"mean_token_accuracy": 0.1973323255777359,
|
|
"num_tokens": 37303221.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.069297981262207,
|
|
"epoch": 1.590232281119714,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047583121140800906,
|
|
"loss": 4.8648,
|
|
"mean_token_accuracy": 0.20087196826934814,
|
|
"num_tokens": 37317798.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.090925598144532,
|
|
"epoch": 1.5908278737343657,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004758119945033497,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.1914900630712509,
|
|
"num_tokens": 37333226.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.064612293243409,
|
|
"epoch": 1.5914234663490174,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004757927703958907,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.20462786853313447,
|
|
"num_tokens": 37346124.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.113408517837525,
|
|
"epoch": 1.5920190589636687,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047577353908632156,
|
|
"loss": 4.8578,
|
|
"mean_token_accuracy": 0.21059556156396866,
|
|
"num_tokens": 37359937.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.051901054382324,
|
|
"epoch": 1.5926146515783204,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004757543005753319,
|
|
"loss": 4.8566,
|
|
"mean_token_accuracy": 0.198633548617363,
|
|
"num_tokens": 37372306.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 4.9946937084198,
|
|
"epoch": 1.593210244192972,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047573505486361183,
|
|
"loss": 4.7747,
|
|
"mean_token_accuracy": 0.20921981185674668,
|
|
"num_tokens": 37385071.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.082876777648925,
|
|
"epoch": 1.5938058368076236,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004757158019518519,
|
|
"loss": 4.924,
|
|
"mean_token_accuracy": 0.2026761770248413,
|
|
"num_tokens": 37397621.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.150379467010498,
|
|
"epoch": 1.594401429422275,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004756965418407424,
|
|
"loss": 4.9652,
|
|
"mean_token_accuracy": 0.1926722764968872,
|
|
"num_tokens": 37412813.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.090430402755738,
|
|
"epoch": 1.5949970220369267,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047567727453097427,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.19548633843660354,
|
|
"num_tokens": 37425664.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 4.932177591323852,
|
|
"epoch": 1.5955926146515784,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004756580000232385,
|
|
"loss": 4.6943,
|
|
"mean_token_accuracy": 0.21197393238544465,
|
|
"num_tokens": 37438600.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.046216249465942,
|
|
"epoch": 1.59618820726623,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047563871831822664,
|
|
"loss": 4.8994,
|
|
"mean_token_accuracy": 0.20444712191820144,
|
|
"num_tokens": 37453138.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.071835279464722,
|
|
"epoch": 1.5967837998808814,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004756194294166301,
|
|
"loss": 4.8482,
|
|
"mean_token_accuracy": 0.20283937603235244,
|
|
"num_tokens": 37467592.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.022615575790406,
|
|
"epoch": 1.597379392495533,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004756001333191409,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.20463694185018538,
|
|
"num_tokens": 37480652.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.094541358947754,
|
|
"epoch": 1.5979749851101848,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047558083002645097,
|
|
"loss": 4.8476,
|
|
"mean_token_accuracy": 0.1980630040168762,
|
|
"num_tokens": 37494504.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.080187511444092,
|
|
"epoch": 1.5985705777248362,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047556151953925287,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.20680505484342576,
|
|
"num_tokens": 37507261.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.096374988555908,
|
|
"epoch": 1.5991661703394877,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004755422018582391,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.19314075708389283,
|
|
"num_tokens": 37519371.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 4.99801549911499,
|
|
"epoch": 1.5997617629541394,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047552287698410267,
|
|
"loss": 4.8175,
|
|
"mean_token_accuracy": 0.2040196716785431,
|
|
"num_tokens": 37532659.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.016440057754517,
|
|
"epoch": 1.600357355568791,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004755035449175366,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.2013173520565033,
|
|
"num_tokens": 37545734.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.061909198760986,
|
|
"epoch": 1.6009529481834424,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004754842056592344,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.20173531472682954,
|
|
"num_tokens": 37560210.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.108305263519287,
|
|
"epoch": 1.601548540798094,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047546485920988975,
|
|
"loss": 4.8857,
|
|
"mean_token_accuracy": 0.18627936094999314,
|
|
"num_tokens": 37573937.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.111904811859131,
|
|
"epoch": 1.6021441334127458,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004754455055701965,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.2010327622294426,
|
|
"num_tokens": 37587615.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.093404483795166,
|
|
"epoch": 1.6027397260273972,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004754261447408489,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.2002284750342369,
|
|
"num_tokens": 37601394.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.1422137260437015,
|
|
"epoch": 1.6033353186420487,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004754067767225413,
|
|
"loss": 4.8682,
|
|
"mean_token_accuracy": 0.19522122889757157,
|
|
"num_tokens": 37616352.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.075344705581665,
|
|
"epoch": 1.6039309112567004,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004753874015159685,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.19929636716842652,
|
|
"num_tokens": 37629669.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.173255348205567,
|
|
"epoch": 1.604526503871352,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004753680191218254,
|
|
"loss": 4.9129,
|
|
"mean_token_accuracy": 0.19392754137516022,
|
|
"num_tokens": 37645468.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.092462730407715,
|
|
"epoch": 1.6051220964860036,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004753486295408073,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.19428254216909407,
|
|
"num_tokens": 37659194.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.07524356842041,
|
|
"epoch": 1.605717689100655,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004753292327736095,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.1983368292450905,
|
|
"num_tokens": 37673910.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.080113267898559,
|
|
"epoch": 1.6063132817153067,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047530982882092794,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.20176528692245482,
|
|
"num_tokens": 37687110.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.119588565826416,
|
|
"epoch": 1.6069088743299584,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004752904176834584,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.19788432717323304,
|
|
"num_tokens": 37701175.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.061201429367065,
|
|
"epoch": 1.60750446694461,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047527099936189735,
|
|
"loss": 4.8525,
|
|
"mean_token_accuracy": 0.20015624016523362,
|
|
"num_tokens": 37715301.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.044998216629028,
|
|
"epoch": 1.6081000595592614,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000475251573856941,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.20200703740119935,
|
|
"num_tokens": 37730151.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.090300798416138,
|
|
"epoch": 1.608695652173913,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004752321411692864,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.19897058755159377,
|
|
"num_tokens": 37745682.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.140941143035889,
|
|
"epoch": 1.6092912447885648,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047521270129963043,
|
|
"loss": 4.8541,
|
|
"mean_token_accuracy": 0.19424390494823457,
|
|
"num_tokens": 37759585.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.078868103027344,
|
|
"epoch": 1.6098868374032163,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004751932542486705,
|
|
"loss": 4.8601,
|
|
"mean_token_accuracy": 0.19586458802223206,
|
|
"num_tokens": 37773881.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 4.92992787361145,
|
|
"epoch": 1.6104824300178677,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004751738000171039,
|
|
"loss": 4.7005,
|
|
"mean_token_accuracy": 0.20804729163646699,
|
|
"num_tokens": 37787439.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.089940118789673,
|
|
"epoch": 1.6110780226325194,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047515433860562855,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.19237551093101501,
|
|
"num_tokens": 37800064.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.09416971206665,
|
|
"epoch": 1.611673615247171,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047513487001494257,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.20785860419273378,
|
|
"num_tokens": 37813484.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 4.97655029296875,
|
|
"epoch": 1.6122692078618224,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004751153942457442,
|
|
"loss": 4.7613,
|
|
"mean_token_accuracy": 0.20806830525398254,
|
|
"num_tokens": 37826039.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.0028393268585205,
|
|
"epoch": 1.612864800476474,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000475095911298732,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.2030883848667145,
|
|
"num_tokens": 37839940.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.076757717132568,
|
|
"epoch": 1.6134603930911258,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004750764211746048,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.19705112725496293,
|
|
"num_tokens": 37853012.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.068364095687866,
|
|
"epoch": 1.6140559857057772,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047505692387406163,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.19758325219154357,
|
|
"num_tokens": 37866594.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.091483640670776,
|
|
"epoch": 1.6146515783204287,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047503741939780195,
|
|
"loss": 4.9097,
|
|
"mean_token_accuracy": 0.19806176871061326,
|
|
"num_tokens": 37880436.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.110069417953492,
|
|
"epoch": 1.6152471709350804,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004750179077465252,
|
|
"loss": 4.9126,
|
|
"mean_token_accuracy": 0.19755036532878875,
|
|
"num_tokens": 37895336.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.031553888320923,
|
|
"epoch": 1.615842763549732,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.00047499838892093134,
|
|
"loss": 4.8689,
|
|
"mean_token_accuracy": 0.20071905553340913,
|
|
"num_tokens": 37908571.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.03922472000122,
|
|
"epoch": 1.6164383561643836,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047497886292172044,
|
|
"loss": 4.9157,
|
|
"mean_token_accuracy": 0.19568819552659988,
|
|
"num_tokens": 37924330.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.090070724487305,
|
|
"epoch": 1.617033948779035,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.00047495932974959287,
|
|
"loss": 4.9022,
|
|
"mean_token_accuracy": 0.19580791890621185,
|
|
"num_tokens": 37937489.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.091767883300781,
|
|
"epoch": 1.6176295413936868,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004749397894052493,
|
|
"loss": 4.9207,
|
|
"mean_token_accuracy": 0.18861685544252396,
|
|
"num_tokens": 37951875.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.078736686706543,
|
|
"epoch": 1.6182251340083385,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047492024188939056,
|
|
"loss": 4.8715,
|
|
"mean_token_accuracy": 0.19986453801393508,
|
|
"num_tokens": 37965808.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.1002415180206295,
|
|
"epoch": 1.61882072662299,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004749006872027178,
|
|
"loss": 4.8839,
|
|
"mean_token_accuracy": 0.20478852093219757,
|
|
"num_tokens": 37979244.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.066554737091065,
|
|
"epoch": 1.6194163192376414,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004748811253459324,
|
|
"loss": 4.8689,
|
|
"mean_token_accuracy": 0.2038577228784561,
|
|
"num_tokens": 37992177.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.107511234283447,
|
|
"epoch": 1.620011911852293,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004748615563197359,
|
|
"loss": 4.9102,
|
|
"mean_token_accuracy": 0.20059595704078675,
|
|
"num_tokens": 38006221.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.122767210006714,
|
|
"epoch": 1.6206075044669446,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004748419801248304,
|
|
"loss": 4.8844,
|
|
"mean_token_accuracy": 0.19313591718673706,
|
|
"num_tokens": 38020808.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.021298360824585,
|
|
"epoch": 1.621203097081596,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004748223967619181,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.20780519098043443,
|
|
"num_tokens": 38032467.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.082465934753418,
|
|
"epoch": 1.6217986896962477,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047480280623170116,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.19295841604471206,
|
|
"num_tokens": 38047784.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.085538911819458,
|
|
"epoch": 1.6223942823108994,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047478320853488256,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.19325836449861528,
|
|
"num_tokens": 38061754.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.0898950576782225,
|
|
"epoch": 1.622989874925551,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047476360367216505,
|
|
"loss": 4.849,
|
|
"mean_token_accuracy": 0.20461996644735336,
|
|
"num_tokens": 38076447.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.095056533813477,
|
|
"epoch": 1.6235854675402024,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004747439916442518,
|
|
"loss": 4.8552,
|
|
"mean_token_accuracy": 0.20077843219041824,
|
|
"num_tokens": 38089845.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.071923112869262,
|
|
"epoch": 1.624181060154854,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004747243724518465,
|
|
"loss": 4.8141,
|
|
"mean_token_accuracy": 0.19990082532167436,
|
|
"num_tokens": 38104180.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.016085004806518,
|
|
"epoch": 1.6247766527695058,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004747047460956525,
|
|
"loss": 4.8345,
|
|
"mean_token_accuracy": 0.19639270305633544,
|
|
"num_tokens": 38117421.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.012281703948974,
|
|
"epoch": 1.6253722453841573,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004746851125763741,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.20919621735811234,
|
|
"num_tokens": 38131131.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.055369710922241,
|
|
"epoch": 1.6259678379988087,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047466547189471534,
|
|
"loss": 4.8231,
|
|
"mean_token_accuracy": 0.201895809173584,
|
|
"num_tokens": 38143905.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.046844720840454,
|
|
"epoch": 1.6265634306134604,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004746458240513807,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.20223674774169922,
|
|
"num_tokens": 38159068.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.1307799339294435,
|
|
"epoch": 1.6271590232281121,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000474626169047075,
|
|
"loss": 4.8746,
|
|
"mean_token_accuracy": 0.1977249026298523,
|
|
"num_tokens": 38174522.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.091549110412598,
|
|
"epoch": 1.6277546158427636,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004746065068825032,
|
|
"loss": 4.8324,
|
|
"mean_token_accuracy": 0.20221926271915436,
|
|
"num_tokens": 38189376.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.105182886123657,
|
|
"epoch": 1.628350208457415,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047458683755837046,
|
|
"loss": 4.9347,
|
|
"mean_token_accuracy": 0.19552338719367982,
|
|
"num_tokens": 38203260.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.083043718338013,
|
|
"epoch": 1.6289458010720668,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004745671610753824,
|
|
"loss": 4.863,
|
|
"mean_token_accuracy": 0.19329403340816498,
|
|
"num_tokens": 38219526.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.052480983734131,
|
|
"epoch": 1.6295413936867182,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004745474774342448,
|
|
"loss": 4.8156,
|
|
"mean_token_accuracy": 0.20495111644268035,
|
|
"num_tokens": 38232957.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.039803314208984,
|
|
"epoch": 1.6301369863013697,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004745277866356636,
|
|
"loss": 4.8788,
|
|
"mean_token_accuracy": 0.19949815720319747,
|
|
"num_tokens": 38246772.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.058307123184204,
|
|
"epoch": 1.6307325789160214,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004745080886803451,
|
|
"loss": 4.8726,
|
|
"mean_token_accuracy": 0.2017684131860733,
|
|
"num_tokens": 38260680.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.037156248092652,
|
|
"epoch": 1.631328171530673,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004744883835689958,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.20061321556568146,
|
|
"num_tokens": 38273666.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.086575269699097,
|
|
"epoch": 1.6319237641453246,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047446867130232257,
|
|
"loss": 4.7993,
|
|
"mean_token_accuracy": 0.19919858276844024,
|
|
"num_tokens": 38287047.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.132299137115479,
|
|
"epoch": 1.632519356759976,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004744489518810324,
|
|
"loss": 4.9359,
|
|
"mean_token_accuracy": 0.1941615179181099,
|
|
"num_tokens": 38300622.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.1138832569122314,
|
|
"epoch": 1.6331149493746278,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047442922530583265,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.19854434281587602,
|
|
"num_tokens": 38316543.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.044647693634033,
|
|
"epoch": 1.6337105419892795,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004744094915774308,
|
|
"loss": 4.8657,
|
|
"mean_token_accuracy": 0.1975424826145172,
|
|
"num_tokens": 38330217.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.1216999053955075,
|
|
"epoch": 1.634306134603931,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047438975069653475,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.19458555579185485,
|
|
"num_tokens": 38345314.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.094735240936279,
|
|
"epoch": 1.6349017272185824,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004743700026638525,
|
|
"loss": 4.8415,
|
|
"mean_token_accuracy": 0.20213041305541993,
|
|
"num_tokens": 38358910.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.099934148788452,
|
|
"epoch": 1.635497319833234,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004743502474800924,
|
|
"loss": 4.9597,
|
|
"mean_token_accuracy": 0.20121959298849107,
|
|
"num_tokens": 38372039.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.056139278411865,
|
|
"epoch": 1.6360929124478858,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047433048514596303,
|
|
"loss": 4.8308,
|
|
"mean_token_accuracy": 0.20156718492507936,
|
|
"num_tokens": 38386517.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.067936134338379,
|
|
"epoch": 1.6366885050625373,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004743107156621733,
|
|
"loss": 4.8665,
|
|
"mean_token_accuracy": 0.19996165931224824,
|
|
"num_tokens": 38401884.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.035918807983398,
|
|
"epoch": 1.6372840976771887,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047429093902943227,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.20722704380750656,
|
|
"num_tokens": 38415006.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.0929594993591305,
|
|
"epoch": 1.6378796902918404,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004742711552484492,
|
|
"loss": 4.8806,
|
|
"mean_token_accuracy": 0.20109869688749313,
|
|
"num_tokens": 38429914.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.109129428863525,
|
|
"epoch": 1.638475282906492,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004742513643199339,
|
|
"loss": 4.968,
|
|
"mean_token_accuracy": 0.1914359912276268,
|
|
"num_tokens": 38443805.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.033179807662964,
|
|
"epoch": 1.6390708755211434,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000474231566244596,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.20029585659503937,
|
|
"num_tokens": 38457667.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.130716943740845,
|
|
"epoch": 1.639666468135795,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047421176102314586,
|
|
"loss": 4.8878,
|
|
"mean_token_accuracy": 0.20122166723012924,
|
|
"num_tokens": 38470560.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.09956545829773,
|
|
"epoch": 1.6402620607504468,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047419194865629366,
|
|
"loss": 4.8752,
|
|
"mean_token_accuracy": 0.2019347444176674,
|
|
"num_tokens": 38483128.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.031976509094238,
|
|
"epoch": 1.6408576533650983,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047417212914475015,
|
|
"loss": 4.934,
|
|
"mean_token_accuracy": 0.19685108661651612,
|
|
"num_tokens": 38496237.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.03973798751831,
|
|
"epoch": 1.6414532459797497,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047415230248922625,
|
|
"loss": 4.8081,
|
|
"mean_token_accuracy": 0.20592691004276276,
|
|
"num_tokens": 38510464.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.0520528793334964,
|
|
"epoch": 1.6420488385944014,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004741324686904331,
|
|
"loss": 4.8002,
|
|
"mean_token_accuracy": 0.21309539228677749,
|
|
"num_tokens": 38524695.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.075418329238891,
|
|
"epoch": 1.6426444312090531,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047411262774908194,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.19872433096170425,
|
|
"num_tokens": 38540391.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 4.98745059967041,
|
|
"epoch": 1.6432400238237046,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004740927796658846,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.19644293338060378,
|
|
"num_tokens": 38553816.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.009047269821167,
|
|
"epoch": 1.643835616438356,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000474072924441553,
|
|
"loss": 4.7422,
|
|
"mean_token_accuracy": 0.21435914188623428,
|
|
"num_tokens": 38567794.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.034976863861084,
|
|
"epoch": 1.6444312090530078,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047405306207679926,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.20505087971687316,
|
|
"num_tokens": 38580427.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.092157983779908,
|
|
"epoch": 1.6450268016676595,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047403319257233585,
|
|
"loss": 4.8569,
|
|
"mean_token_accuracy": 0.2011756107211113,
|
|
"num_tokens": 38593875.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 4.993200445175171,
|
|
"epoch": 1.645622394282311,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004740133159288753,
|
|
"loss": 4.838,
|
|
"mean_token_accuracy": 0.197309610247612,
|
|
"num_tokens": 38609201.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.001065731048584,
|
|
"epoch": 1.6462179868969624,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004739934321471308,
|
|
"loss": 4.7758,
|
|
"mean_token_accuracy": 0.2048857405781746,
|
|
"num_tokens": 38622953.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.075225400924682,
|
|
"epoch": 1.6468135795116141,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004739735412278154,
|
|
"loss": 4.8577,
|
|
"mean_token_accuracy": 0.20040785074234008,
|
|
"num_tokens": 38638018.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.116125011444092,
|
|
"epoch": 1.6474091721262656,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004739536431716427,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.19507577568292617,
|
|
"num_tokens": 38650546.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.111659717559815,
|
|
"epoch": 1.648004764740917,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047393373797932614,
|
|
"loss": 4.8648,
|
|
"mean_token_accuracy": 0.19831298738718034,
|
|
"num_tokens": 38667662.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.052183723449707,
|
|
"epoch": 1.6486003573555688,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047391382565157994,
|
|
"loss": 4.8978,
|
|
"mean_token_accuracy": 0.19577550143003464,
|
|
"num_tokens": 38681431.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.081569528579712,
|
|
"epoch": 1.6491959499702205,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004738939061891182,
|
|
"loss": 4.9011,
|
|
"mean_token_accuracy": 0.1998455822467804,
|
|
"num_tokens": 38694116.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.047997951507568,
|
|
"epoch": 1.649791542584872,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004738739795926554,
|
|
"loss": 4.8043,
|
|
"mean_token_accuracy": 0.20501065105199814,
|
|
"num_tokens": 38708194.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.068067979812622,
|
|
"epoch": 1.6503871351995234,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004738540458629063,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.1897590696811676,
|
|
"num_tokens": 38722499.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.157134914398194,
|
|
"epoch": 1.650982727814175,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004738341050005859,
|
|
"loss": 4.9976,
|
|
"mean_token_accuracy": 0.19621627479791642,
|
|
"num_tokens": 38737231.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.108859920501709,
|
|
"epoch": 1.6515783204288268,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047381415700640953,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.20335627645254134,
|
|
"num_tokens": 38751922.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.024528121948242,
|
|
"epoch": 1.6521739130434783,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047379420188109245,
|
|
"loss": 4.8117,
|
|
"mean_token_accuracy": 0.20350469648838043,
|
|
"num_tokens": 38765039.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.0874590396881105,
|
|
"epoch": 1.6527695056581297,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004737742396253506,
|
|
"loss": 4.8996,
|
|
"mean_token_accuracy": 0.19461786597967148,
|
|
"num_tokens": 38777996.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 4.99974513053894,
|
|
"epoch": 1.6533650982727814,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004737542702399,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.2129928156733513,
|
|
"num_tokens": 38791015.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 4.977034854888916,
|
|
"epoch": 1.6539606908874331,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047373429372545695,
|
|
"loss": 4.777,
|
|
"mean_token_accuracy": 0.2103282704949379,
|
|
"num_tokens": 38804859.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.063204622268676,
|
|
"epoch": 1.6545562835020846,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004737143100827378,
|
|
"loss": 4.9444,
|
|
"mean_token_accuracy": 0.20009055286645888,
|
|
"num_tokens": 38817352.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.084086322784424,
|
|
"epoch": 1.655151876116736,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004736943193124595,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.20445796251296997,
|
|
"num_tokens": 38830966.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.023739957809449,
|
|
"epoch": 1.6557474687313878,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000473674321415339,
|
|
"loss": 4.8171,
|
|
"mean_token_accuracy": 0.20077931731939316,
|
|
"num_tokens": 38845609.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.049885034561157,
|
|
"epoch": 1.6563430613460393,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004736543163920936,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.20084660947322847,
|
|
"num_tokens": 38859675.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.0903736591339115,
|
|
"epoch": 1.6569386539606907,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004736343042434409,
|
|
"loss": 4.8605,
|
|
"mean_token_accuracy": 0.19897715747356415,
|
|
"num_tokens": 38872625.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.116831207275391,
|
|
"epoch": 1.6575342465753424,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004736142849700986,
|
|
"loss": 4.8949,
|
|
"mean_token_accuracy": 0.20107684135437012,
|
|
"num_tokens": 38886970.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.089191913604736,
|
|
"epoch": 1.6581298391899941,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047359425857278485,
|
|
"loss": 4.8452,
|
|
"mean_token_accuracy": 0.20103989243507386,
|
|
"num_tokens": 38901611.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.110720157623291,
|
|
"epoch": 1.6587254318046456,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000473574225052218,
|
|
"loss": 4.9369,
|
|
"mean_token_accuracy": 0.18908626735210418,
|
|
"num_tokens": 38917296.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.170002365112305,
|
|
"epoch": 1.659321024419297,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004735541844091165,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.19651541560888292,
|
|
"num_tokens": 38933556.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.124974107742309,
|
|
"epoch": 1.6599166170339488,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004735341366441993,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.19290522634983062,
|
|
"num_tokens": 38946598.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.121433973312378,
|
|
"epoch": 1.6605122096486005,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00047351408175818537,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.20682621747255325,
|
|
"num_tokens": 38960346.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.066410255432129,
|
|
"epoch": 1.661107802263252,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004734940197517941,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.19716883152723313,
|
|
"num_tokens": 38973764.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.1225498676300045,
|
|
"epoch": 1.6617033948779034,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000473473950625745,
|
|
"loss": 4.9688,
|
|
"mean_token_accuracy": 0.19831221103668212,
|
|
"num_tokens": 38987616.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.130171632766723,
|
|
"epoch": 1.6622989874925551,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047345387438075805,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.19463881552219392,
|
|
"num_tokens": 39000726.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.005768346786499,
|
|
"epoch": 1.6628945801072068,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004734337910175533,
|
|
"loss": 4.8101,
|
|
"mean_token_accuracy": 0.19958731830120086,
|
|
"num_tokens": 39015288.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.042069339752198,
|
|
"epoch": 1.6634901727218583,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047341370053685113,
|
|
"loss": 4.8937,
|
|
"mean_token_accuracy": 0.2069912776350975,
|
|
"num_tokens": 39028683.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.242082309722901,
|
|
"epoch": 1.6640857653365098,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004733936029393721,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.18712208569049835,
|
|
"num_tokens": 39045066.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.088954925537109,
|
|
"epoch": 1.6646813579511615,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004733734982258371,
|
|
"loss": 4.8366,
|
|
"mean_token_accuracy": 0.2036761835217476,
|
|
"num_tokens": 39059455.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.031809949874878,
|
|
"epoch": 1.665276950565813,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047335338639696724,
|
|
"loss": 4.8856,
|
|
"mean_token_accuracy": 0.20368121564388275,
|
|
"num_tokens": 39072611.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 4.990837621688843,
|
|
"epoch": 1.6658725431804644,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004733332674534839,
|
|
"loss": 4.7364,
|
|
"mean_token_accuracy": 0.21065500527620315,
|
|
"num_tokens": 39085790.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.002561759948731,
|
|
"epoch": 1.666468135795116,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004733131413961087,
|
|
"loss": 4.7497,
|
|
"mean_token_accuracy": 0.20549301952123641,
|
|
"num_tokens": 39099466.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.007187938690185,
|
|
"epoch": 1.6670637284097678,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047329300822556363,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.2025858387351036,
|
|
"num_tokens": 39114278.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.021530437469482,
|
|
"epoch": 1.6676593210244193,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004732728679425707,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.19851020872592925,
|
|
"num_tokens": 39128438.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.137137985229492,
|
|
"epoch": 1.6682549136390707,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004732527205478524,
|
|
"loss": 4.9675,
|
|
"mean_token_accuracy": 0.1942400723695755,
|
|
"num_tokens": 39143113.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.142505741119384,
|
|
"epoch": 1.6688505062537224,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004732325660421314,
|
|
"loss": 4.8809,
|
|
"mean_token_accuracy": 0.20149146765470505,
|
|
"num_tokens": 39156850.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 4.996710729598999,
|
|
"epoch": 1.6694460988683741,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004732124044261304,
|
|
"loss": 4.8394,
|
|
"mean_token_accuracy": 0.2059812992811203,
|
|
"num_tokens": 39169036.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.005569076538086,
|
|
"epoch": 1.6700416914830256,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047319223570057293,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.20683875679969788,
|
|
"num_tokens": 39182838.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.04729151725769,
|
|
"epoch": 1.670637284097677,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004731720598661821,
|
|
"loss": 4.7783,
|
|
"mean_token_accuracy": 0.20497834235429763,
|
|
"num_tokens": 39195369.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.012418270111084,
|
|
"epoch": 1.6712328767123288,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047315187692368167,
|
|
"loss": 4.8263,
|
|
"mean_token_accuracy": 0.2085931196808815,
|
|
"num_tokens": 39208266.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.025934553146362,
|
|
"epoch": 1.6718284693269805,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004731316868737957,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.1990950733423233,
|
|
"num_tokens": 39220947.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.125570297241211,
|
|
"epoch": 1.672424061941632,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047311148971724816,
|
|
"loss": 4.9209,
|
|
"mean_token_accuracy": 0.19704416394233704,
|
|
"num_tokens": 39236361.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.119481754302979,
|
|
"epoch": 1.6730196545562834,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004730912854547636,
|
|
"loss": 4.9025,
|
|
"mean_token_accuracy": 0.20051200240850447,
|
|
"num_tokens": 39249879.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.022060823440552,
|
|
"epoch": 1.6736152471709351,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004730710740870667,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.2072951540350914,
|
|
"num_tokens": 39264211.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.07978401184082,
|
|
"epoch": 1.6742108397855868,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047305085561488247,
|
|
"loss": 4.8464,
|
|
"mean_token_accuracy": 0.20477864891290665,
|
|
"num_tokens": 39277583.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.03390851020813,
|
|
"epoch": 1.674806432400238,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047303063003893605,
|
|
"loss": 4.8843,
|
|
"mean_token_accuracy": 0.20588296502828599,
|
|
"num_tokens": 39291121.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.011673021316528,
|
|
"epoch": 1.6754020250148898,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004730103973599529,
|
|
"loss": 4.8063,
|
|
"mean_token_accuracy": 0.20318807810544967,
|
|
"num_tokens": 39306386.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.110676622390747,
|
|
"epoch": 1.6759976176295415,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004729901575786588,
|
|
"loss": 4.8528,
|
|
"mean_token_accuracy": 0.2002200350165367,
|
|
"num_tokens": 39319720.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.142493724822998,
|
|
"epoch": 1.676593210244193,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047296991069577953,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.1975611165165901,
|
|
"num_tokens": 39334588.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.106358242034912,
|
|
"epoch": 1.6771888028588444,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004729496567120415,
|
|
"loss": 4.8579,
|
|
"mean_token_accuracy": 0.2014059007167816,
|
|
"num_tokens": 39348516.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.070221996307373,
|
|
"epoch": 1.6777843954734961,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047292939562817115,
|
|
"loss": 4.7862,
|
|
"mean_token_accuracy": 0.19931680858135223,
|
|
"num_tokens": 39362376.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.143262100219727,
|
|
"epoch": 1.6783799880881478,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004729091274448952,
|
|
"loss": 4.9582,
|
|
"mean_token_accuracy": 0.1918693006038666,
|
|
"num_tokens": 39375942.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.042103815078735,
|
|
"epoch": 1.6789755807027993,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004728888521629406,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.19638753235340117,
|
|
"num_tokens": 39389169.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.115233087539673,
|
|
"epoch": 1.6795711733174508,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047286856978303465,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.19286517202854156,
|
|
"num_tokens": 39400875.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.085996437072754,
|
|
"epoch": 1.6801667659321025,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004728482803059048,
|
|
"loss": 4.8089,
|
|
"mean_token_accuracy": 0.20221593379974365,
|
|
"num_tokens": 39415905.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 4.961945486068726,
|
|
"epoch": 1.6807623585467542,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004728279837322788,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.2084258273243904,
|
|
"num_tokens": 39428204.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.033016490936279,
|
|
"epoch": 1.6813579511614056,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004728076800628847,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.20937342345714569,
|
|
"num_tokens": 39441637.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.1169603824615475,
|
|
"epoch": 1.681953543776057,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004727873692984507,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.20318597555160522,
|
|
"num_tokens": 39456018.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.0537820816040036,
|
|
"epoch": 1.6825491363907088,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004727670514397054,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.19489926993846893,
|
|
"num_tokens": 39469871.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.046130895614624,
|
|
"epoch": 1.6831447290053605,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004727467264873775,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.1830432653427124,
|
|
"num_tokens": 39483749.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.2264035701751705,
|
|
"epoch": 1.6837403216200117,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000472726394442196,
|
|
"loss": 4.9795,
|
|
"mean_token_accuracy": 0.20309483706951142,
|
|
"num_tokens": 39496233.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.147860717773438,
|
|
"epoch": 1.6843359142346634,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047270605530489026,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.2033548355102539,
|
|
"num_tokens": 39510240.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.005387687683106,
|
|
"epoch": 1.6849315068493151,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047268570907618967,
|
|
"loss": 4.7948,
|
|
"mean_token_accuracy": 0.20620527863502502,
|
|
"num_tokens": 39523735.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 4.974678373336792,
|
|
"epoch": 1.6855270994639666,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004726653557568242,
|
|
"loss": 4.7206,
|
|
"mean_token_accuracy": 0.21991985738277436,
|
|
"num_tokens": 39538358.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.014265251159668,
|
|
"epoch": 1.686122692078618,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00047264499534752384,
|
|
"loss": 4.8253,
|
|
"mean_token_accuracy": 0.20647913068532944,
|
|
"num_tokens": 39552364.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.044498538970947,
|
|
"epoch": 1.6867182846932698,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047262462784901875,
|
|
"loss": 4.7974,
|
|
"mean_token_accuracy": 0.20582636147737504,
|
|
"num_tokens": 39563748.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.026322364807129,
|
|
"epoch": 1.6873138773079215,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047260425326203965,
|
|
"loss": 4.8119,
|
|
"mean_token_accuracy": 0.20919303148984908,
|
|
"num_tokens": 39575042.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.123529529571533,
|
|
"epoch": 1.687909469922573,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004725838715873172,
|
|
"loss": 4.9682,
|
|
"mean_token_accuracy": 0.1943197503685951,
|
|
"num_tokens": 39589617.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.065047073364258,
|
|
"epoch": 1.6885050625372244,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047256348282558264,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.20749929994344712,
|
|
"num_tokens": 39603466.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.102658653259278,
|
|
"epoch": 1.6891006551518761,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047254308697756704,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.20082052797079086,
|
|
"num_tokens": 39616253.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 4.98819146156311,
|
|
"epoch": 1.6896962477665278,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004725226840440022,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.20517327636480331,
|
|
"num_tokens": 39630943.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.095724582672119,
|
|
"epoch": 1.6902918403811793,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047250227402561976,
|
|
"loss": 4.9139,
|
|
"mean_token_accuracy": 0.19405139833688737,
|
|
"num_tokens": 39645769.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.047719144821167,
|
|
"epoch": 1.6908874329958308,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004724818569231519,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.20849099457263948,
|
|
"num_tokens": 39659102.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.042581224441529,
|
|
"epoch": 1.6914830256104825,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047246143273733097,
|
|
"loss": 4.9123,
|
|
"mean_token_accuracy": 0.2000250533223152,
|
|
"num_tokens": 39673868.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 4.994673252105713,
|
|
"epoch": 1.6920786182251342,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004724410014688894,
|
|
"loss": 4.7322,
|
|
"mean_token_accuracy": 0.21664153039455414,
|
|
"num_tokens": 39687219.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.078763437271118,
|
|
"epoch": 1.6926742108397854,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047242056311856017,
|
|
"loss": 4.8545,
|
|
"mean_token_accuracy": 0.20265747606754303,
|
|
"num_tokens": 39701535.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.049409055709839,
|
|
"epoch": 1.6932698034544371,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 0.0004724001176870764,
|
|
"loss": 4.8417,
|
|
"mean_token_accuracy": 0.1987129420042038,
|
|
"num_tokens": 39714807.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.031736278533936,
|
|
"epoch": 1.6938653960690888,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004723796651751713,
|
|
"loss": 4.7914,
|
|
"mean_token_accuracy": 0.20825732201337815,
|
|
"num_tokens": 39727383.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.0285004615783695,
|
|
"epoch": 1.6944609886837403,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004723592055835784,
|
|
"loss": 4.7917,
|
|
"mean_token_accuracy": 0.20643370449543,
|
|
"num_tokens": 39740919.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.054819202423095,
|
|
"epoch": 1.6950565812983918,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047233873891303193,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.19377916753292085,
|
|
"num_tokens": 39754675.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.044053602218628,
|
|
"epoch": 1.6956521739130435,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047231826516426554,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.20056963264942168,
|
|
"num_tokens": 39768277.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.115881013870239,
|
|
"epoch": 1.6962477665276952,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004722977843380139,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.19613471776247024,
|
|
"num_tokens": 39781736.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.150641679763794,
|
|
"epoch": 1.6968433591423466,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004722772964350115,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.19422992020845414,
|
|
"num_tokens": 39797715.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.085607051849365,
|
|
"epoch": 1.697438951756998,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047225680145599326,
|
|
"loss": 4.8578,
|
|
"mean_token_accuracy": 0.20515982508659364,
|
|
"num_tokens": 39811264.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.052194738388062,
|
|
"epoch": 1.6980345443716498,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004722362994016942,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.20515314638614654,
|
|
"num_tokens": 39825217.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.034286785125732,
|
|
"epoch": 1.6986301369863015,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004722157902728498,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.19786033481359483,
|
|
"num_tokens": 39839568.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.145158386230468,
|
|
"epoch": 1.699225729600953,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047219527407019575,
|
|
"loss": 4.9183,
|
|
"mean_token_accuracy": 0.1916250079870224,
|
|
"num_tokens": 39854648.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.019842052459717,
|
|
"epoch": 1.6998213222156044,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047217475079446773,
|
|
"loss": 4.7978,
|
|
"mean_token_accuracy": 0.20915224105119706,
|
|
"num_tokens": 39868419.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.0159525871276855,
|
|
"epoch": 1.7004169148302561,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000472154220446402,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.20590732395648956,
|
|
"num_tokens": 39882105.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.063427877426148,
|
|
"epoch": 1.7010125074449078,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047213368302673496,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.20204195529222488,
|
|
"num_tokens": 39897146.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.042366361618042,
|
|
"epoch": 1.7016081000595593,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004721131385362033,
|
|
"loss": 4.7679,
|
|
"mean_token_accuracy": 0.2120565578341484,
|
|
"num_tokens": 39909801.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.006779384613037,
|
|
"epoch": 1.7022036926742108,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004720925869755437,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.20470519363880157,
|
|
"num_tokens": 39921708.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 4.9595005989074705,
|
|
"epoch": 1.7027992852888625,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047207202834549357,
|
|
"loss": 4.7534,
|
|
"mean_token_accuracy": 0.21206887662410737,
|
|
"num_tokens": 39935033.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.084029197692871,
|
|
"epoch": 1.703394877903514,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047205146264679015,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.19869384467601775,
|
|
"num_tokens": 39950212.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 4.966366767883301,
|
|
"epoch": 1.7039904705181654,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047203088988017114,
|
|
"loss": 4.7966,
|
|
"mean_token_accuracy": 0.2111593946814537,
|
|
"num_tokens": 39964091.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.143579387664795,
|
|
"epoch": 1.7045860631328171,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00047201031004637445,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.1958382397890091,
|
|
"num_tokens": 39978523.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.119328117370605,
|
|
"epoch": 1.7051816557474688,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004719897231461383,
|
|
"loss": 4.8316,
|
|
"mean_token_accuracy": 0.2011496603488922,
|
|
"num_tokens": 39992741.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.068933582305908,
|
|
"epoch": 1.7057772483621203,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004719691291802011,
|
|
"loss": 4.8603,
|
|
"mean_token_accuracy": 0.19299955517053605,
|
|
"num_tokens": 40007002.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.050206279754638,
|
|
"epoch": 1.7063728409767718,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047194852814930145,
|
|
"loss": 4.8951,
|
|
"mean_token_accuracy": 0.1946726217865944,
|
|
"num_tokens": 40021516.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.008648920059204,
|
|
"epoch": 1.7069684335914235,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047192792005417827,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.2058384045958519,
|
|
"num_tokens": 40035123.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.014572811126709,
|
|
"epoch": 1.7075640262060752,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004719073048955709,
|
|
"loss": 4.8043,
|
|
"mean_token_accuracy": 0.19846327155828475,
|
|
"num_tokens": 40047985.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 4.984854125976563,
|
|
"epoch": 1.7081596188207266,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004718866826742185,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.20393472909927368,
|
|
"num_tokens": 40064974.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.0643219470977785,
|
|
"epoch": 1.7087552114353781,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000471866053390861,
|
|
"loss": 4.7981,
|
|
"mean_token_accuracy": 0.2037579223513603,
|
|
"num_tokens": 40077737.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.081917190551758,
|
|
"epoch": 1.7093508040500298,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047184541704623823,
|
|
"loss": 4.8036,
|
|
"mean_token_accuracy": 0.20796612054109573,
|
|
"num_tokens": 40091183.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 4.990171909332275,
|
|
"epoch": 1.7099463966646815,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047182477364109045,
|
|
"loss": 4.7671,
|
|
"mean_token_accuracy": 0.20922620892524718,
|
|
"num_tokens": 40103992.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.055445194244385,
|
|
"epoch": 1.710541989279333,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000471804123176158,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.19793630093336106,
|
|
"num_tokens": 40118916.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.000980281829834,
|
|
"epoch": 1.7111375818939845,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004717834656521816,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.19903061389923096,
|
|
"num_tokens": 40132953.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.021615934371948,
|
|
"epoch": 1.7117331745086362,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047176280106990233,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.19634135514497758,
|
|
"num_tokens": 40148570.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.124772834777832,
|
|
"epoch": 1.7123287671232876,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004717421294300612,
|
|
"loss": 4.901,
|
|
"mean_token_accuracy": 0.19633707851171495,
|
|
"num_tokens": 40162295.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 4.9781828880310055,
|
|
"epoch": 1.712924359737939,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004717214507333999,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.20184316188097,
|
|
"num_tokens": 40176972.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.020621299743652,
|
|
"epoch": 1.7135199523525908,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047170076498066,
|
|
"loss": 4.844,
|
|
"mean_token_accuracy": 0.20355890244245528,
|
|
"num_tokens": 40191152.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.0135103225708,
|
|
"epoch": 1.7141155449672425,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004716800721725834,
|
|
"loss": 4.7757,
|
|
"mean_token_accuracy": 0.20091981142759324,
|
|
"num_tokens": 40205526.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.045491361618042,
|
|
"epoch": 1.714711137581894,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004716593723099124,
|
|
"loss": 4.8232,
|
|
"mean_token_accuracy": 0.19938148707151412,
|
|
"num_tokens": 40219365.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.092276382446289,
|
|
"epoch": 1.7153067301965454,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047163866539338945,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.19896950274705888,
|
|
"num_tokens": 40234505.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.055456209182739,
|
|
"epoch": 1.7159023228111971,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00047161795142375735,
|
|
"loss": 4.8713,
|
|
"mean_token_accuracy": 0.20182319581508637,
|
|
"num_tokens": 40249041.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.072894763946533,
|
|
"epoch": 1.7164979154258488,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047159723040175896,
|
|
"loss": 4.8256,
|
|
"mean_token_accuracy": 0.20536286234855652,
|
|
"num_tokens": 40263718.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 4.921898698806762,
|
|
"epoch": 1.7170935080405003,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004715765023281376,
|
|
"loss": 4.6778,
|
|
"mean_token_accuracy": 0.22390561997890474,
|
|
"num_tokens": 40276478.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 4.977628755569458,
|
|
"epoch": 1.7176891006551518,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004715557672036367,
|
|
"loss": 4.7789,
|
|
"mean_token_accuracy": 0.21226072907447815,
|
|
"num_tokens": 40288176.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.069623756408691,
|
|
"epoch": 1.7182846932698035,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047153502502899995,
|
|
"loss": 4.8515,
|
|
"mean_token_accuracy": 0.20522261410951614,
|
|
"num_tokens": 40302483.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.04928560256958,
|
|
"epoch": 1.7188802858844552,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047151427580497155,
|
|
"loss": 4.7997,
|
|
"mean_token_accuracy": 0.20519303381443024,
|
|
"num_tokens": 40314927.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.061735153198242,
|
|
"epoch": 1.7194758784991067,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004714935195322954,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.20201535522937775,
|
|
"num_tokens": 40328327.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.033892583847046,
|
|
"epoch": 1.7200714711137581,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004714727562117163,
|
|
"loss": 4.8392,
|
|
"mean_token_accuracy": 0.19391790479421617,
|
|
"num_tokens": 40344616.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.165708732604981,
|
|
"epoch": 1.7206670637284098,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047145198584397884,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.19428298622369766,
|
|
"num_tokens": 40358804.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.059184789657593,
|
|
"epoch": 1.7212626563430613,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004714312084298281,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.2024843454360962,
|
|
"num_tokens": 40372527.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 4.999536323547363,
|
|
"epoch": 1.7218582489577128,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004714104239700093,
|
|
"loss": 4.851,
|
|
"mean_token_accuracy": 0.19557270854711534,
|
|
"num_tokens": 40387115.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.124322891235352,
|
|
"epoch": 1.7224538415723645,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004713896324652679,
|
|
"loss": 4.943,
|
|
"mean_token_accuracy": 0.19119505435228348,
|
|
"num_tokens": 40401657.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.0621764183044435,
|
|
"epoch": 1.7230494341870162,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047136883391634966,
|
|
"loss": 4.8547,
|
|
"mean_token_accuracy": 0.20385043025016786,
|
|
"num_tokens": 40416283.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.0535660743713375,
|
|
"epoch": 1.7236450268016676,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004713480283240007,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.2003778874874115,
|
|
"num_tokens": 40432132.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.056285047531128,
|
|
"epoch": 1.7242406194163191,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004713272156889672,
|
|
"loss": 4.7745,
|
|
"mean_token_accuracy": 0.21287451833486556,
|
|
"num_tokens": 40446105.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.046526861190796,
|
|
"epoch": 1.7248362120309708,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004713063960119956,
|
|
"loss": 4.7708,
|
|
"mean_token_accuracy": 0.2060517907142639,
|
|
"num_tokens": 40460152.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.045825433731079,
|
|
"epoch": 1.7254318046456225,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047128556929383283,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.1974760413169861,
|
|
"num_tokens": 40474934.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.006016206741333,
|
|
"epoch": 1.726027397260274,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047126473553522576,
|
|
"loss": 4.8462,
|
|
"mean_token_accuracy": 0.2057500049471855,
|
|
"num_tokens": 40488966.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.187839460372925,
|
|
"epoch": 1.7266229898749255,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004712438947369218,
|
|
"loss": 5.0103,
|
|
"mean_token_accuracy": 0.19806994795799254,
|
|
"num_tokens": 40504380.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.082800436019897,
|
|
"epoch": 1.7272185824895772,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004712230468996684,
|
|
"loss": 4.7588,
|
|
"mean_token_accuracy": 0.21588925570249556,
|
|
"num_tokens": 40517230.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 4.960556697845459,
|
|
"epoch": 1.7278141751042289,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004712021920242133,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.20569829046726226,
|
|
"num_tokens": 40530029.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 4.95529351234436,
|
|
"epoch": 1.7284097677188803,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047118133011130465,
|
|
"loss": 4.7432,
|
|
"mean_token_accuracy": 0.2076209843158722,
|
|
"num_tokens": 40542863.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.104475498199463,
|
|
"epoch": 1.7290053603335318,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004711604611616905,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.19625477790832518,
|
|
"num_tokens": 40557112.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.0672372341156,
|
|
"epoch": 1.7296009529481835,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004711395851761198,
|
|
"loss": 4.8137,
|
|
"mean_token_accuracy": 0.20088469833135605,
|
|
"num_tokens": 40570374.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.044078063964844,
|
|
"epoch": 1.730196545562835,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004711187021553409,
|
|
"loss": 4.8036,
|
|
"mean_token_accuracy": 0.20173290967941285,
|
|
"num_tokens": 40583814.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.033246803283691,
|
|
"epoch": 1.7307921381774864,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047109781210010306,
|
|
"loss": 4.8614,
|
|
"mean_token_accuracy": 0.20115313529968262,
|
|
"num_tokens": 40600054.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.124696159362793,
|
|
"epoch": 1.7313877307921381,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047107691501115556,
|
|
"loss": 4.9302,
|
|
"mean_token_accuracy": 0.19444452226161957,
|
|
"num_tokens": 40614727.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.054619455337525,
|
|
"epoch": 1.7319833234067898,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004710560108892479,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.1983904391527176,
|
|
"num_tokens": 40630103.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.0354798316955565,
|
|
"epoch": 1.7325789160214413,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047103509973513,
|
|
"loss": 4.7692,
|
|
"mean_token_accuracy": 0.2050994172692299,
|
|
"num_tokens": 40642148.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.033196926116943,
|
|
"epoch": 1.7331745086360928,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047101418154955166,
|
|
"loss": 4.7535,
|
|
"mean_token_accuracy": 0.2039859563112259,
|
|
"num_tokens": 40655324.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.038624382019043,
|
|
"epoch": 1.7337701012507445,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004709932563332633,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.20048636347055435,
|
|
"num_tokens": 40669709.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 4.98468976020813,
|
|
"epoch": 1.7343656938653962,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047097232408701564,
|
|
"loss": 4.9023,
|
|
"mean_token_accuracy": 0.1972325101494789,
|
|
"num_tokens": 40684829.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.165124559402466,
|
|
"epoch": 1.7349612864800477,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047095138481155924,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.20441149175167084,
|
|
"num_tokens": 40698737.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.117588996887207,
|
|
"epoch": 1.7355568790946991,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047093043850764533,
|
|
"loss": 4.8784,
|
|
"mean_token_accuracy": 0.20298220366239547,
|
|
"num_tokens": 40713550.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.0191937446594235,
|
|
"epoch": 1.7361524717093508,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004709094851760251,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.1976804941892624,
|
|
"num_tokens": 40726023.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 4.988307285308838,
|
|
"epoch": 1.7367480643240025,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004708885248174503,
|
|
"loss": 4.7555,
|
|
"mean_token_accuracy": 0.20828238129615784,
|
|
"num_tokens": 40739053.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.027887392044067,
|
|
"epoch": 1.737343656938654,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004708675574326724,
|
|
"loss": 4.7819,
|
|
"mean_token_accuracy": 0.20748382657766343,
|
|
"num_tokens": 40752146.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.069736289978027,
|
|
"epoch": 1.7379392495533055,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004708465830224438,
|
|
"loss": 4.8199,
|
|
"mean_token_accuracy": 0.20658381283283234,
|
|
"num_tokens": 40766266.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 4.980482959747315,
|
|
"epoch": 1.7385348421679572,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047082560158751675,
|
|
"loss": 4.7226,
|
|
"mean_token_accuracy": 0.2178283751010895,
|
|
"num_tokens": 40780362.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 4.959571743011475,
|
|
"epoch": 1.7391304347826086,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047080461312864363,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.21088866889476776,
|
|
"num_tokens": 40793929.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 4.926495027542114,
|
|
"epoch": 1.7397260273972601,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047078361764657745,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.206706964969635,
|
|
"num_tokens": 40807401.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.083877277374268,
|
|
"epoch": 1.7403216200119118,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004707626151420713,
|
|
"loss": 4.902,
|
|
"mean_token_accuracy": 0.20243957340717317,
|
|
"num_tokens": 40820223.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.030933237075805,
|
|
"epoch": 1.7409172126265635,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047074160561587835,
|
|
"loss": 4.8131,
|
|
"mean_token_accuracy": 0.20797197818756102,
|
|
"num_tokens": 40833736.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.0352884292602536,
|
|
"epoch": 1.741512805241215,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004707205890687523,
|
|
"loss": 4.7575,
|
|
"mean_token_accuracy": 0.21391280889511108,
|
|
"num_tokens": 40848448.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.029790306091309,
|
|
"epoch": 1.7421083978558665,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004706995655014469,
|
|
"loss": 4.8454,
|
|
"mean_token_accuracy": 0.2018750011920929,
|
|
"num_tokens": 40863316.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.0365338802337645,
|
|
"epoch": 1.7427039904705182,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004706785349147163,
|
|
"loss": 4.8871,
|
|
"mean_token_accuracy": 0.20503995269536973,
|
|
"num_tokens": 40877946.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.110221290588379,
|
|
"epoch": 1.7432995830851699,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047065749730931485,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.20555474162101744,
|
|
"num_tokens": 40893388.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.092961931228638,
|
|
"epoch": 1.7438951756998213,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004706364526859971,
|
|
"loss": 4.8696,
|
|
"mean_token_accuracy": 0.1954895883798599,
|
|
"num_tokens": 40908878.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.074105596542358,
|
|
"epoch": 1.7444907683144728,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004706154010455178,
|
|
"loss": 4.8831,
|
|
"mean_token_accuracy": 0.2053709164261818,
|
|
"num_tokens": 40921226.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 4.98919825553894,
|
|
"epoch": 1.7450863609291245,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00047059434238863206,
|
|
"loss": 4.7574,
|
|
"mean_token_accuracy": 0.20727279484272004,
|
|
"num_tokens": 40935508.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.0021223545074465,
|
|
"epoch": 1.7456819535437762,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004705732767160954,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.20420173406600953,
|
|
"num_tokens": 40949167.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.128546619415284,
|
|
"epoch": 1.7462775461584277,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004705522040286632,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.19769555032253266,
|
|
"num_tokens": 40962359.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.102536010742187,
|
|
"epoch": 1.7468731387730791,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004705311243270915,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.2038013905286789,
|
|
"num_tokens": 40977964.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.010082960128784,
|
|
"epoch": 1.7474687313877308,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004705100376121362,
|
|
"loss": 4.9209,
|
|
"mean_token_accuracy": 0.1974055826663971,
|
|
"num_tokens": 40990565.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.000252342224121,
|
|
"epoch": 1.7480643240023823,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004704889438845537,
|
|
"loss": 4.8347,
|
|
"mean_token_accuracy": 0.1999487519264221,
|
|
"num_tokens": 41003701.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.063540363311768,
|
|
"epoch": 1.7486599166170338,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047046784314510074,
|
|
"loss": 4.8442,
|
|
"mean_token_accuracy": 0.19944265037775039,
|
|
"num_tokens": 41017646.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.056274509429931,
|
|
"epoch": 1.7492555092316855,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000470446735394534,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.20496161580085753,
|
|
"num_tokens": 41030933.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.002418661117554,
|
|
"epoch": 1.7498511018463372,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004704256206336106,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.20566710382699965,
|
|
"num_tokens": 41045412.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.075624561309814,
|
|
"epoch": 1.7504466944609887,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000470404498863088,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.1969432935118675,
|
|
"num_tokens": 41058870.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.076484870910645,
|
|
"epoch": 1.7510422870756401,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00047038337008372365,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.2016424760222435,
|
|
"num_tokens": 41072210.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.038082695007324,
|
|
"epoch": 1.7516378796902918,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047036223429627557,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.20771125555038453,
|
|
"num_tokens": 41084996.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.144012928009033,
|
|
"epoch": 1.7522334723049435,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047034109150150184,
|
|
"loss": 4.9363,
|
|
"mean_token_accuracy": 0.19243746250867844,
|
|
"num_tokens": 41100190.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.034255504608154,
|
|
"epoch": 1.752829064919595,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004703199417001607,
|
|
"loss": 4.8215,
|
|
"mean_token_accuracy": 0.20585354119539262,
|
|
"num_tokens": 41114560.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.072002983093261,
|
|
"epoch": 1.7534246575342465,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047029878489301074,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.20761846750974655,
|
|
"num_tokens": 41128110.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.033764123916626,
|
|
"epoch": 1.7540202501488982,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004702776210808109,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.20484055429697037,
|
|
"num_tokens": 41142519.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.060101842880249,
|
|
"epoch": 1.7546158427635499,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004702564502643204,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.20871875286102295,
|
|
"num_tokens": 41156671.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.029228925704956,
|
|
"epoch": 1.7552114353782013,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047023527244429846,
|
|
"loss": 4.8715,
|
|
"mean_token_accuracy": 0.20498670637607574,
|
|
"num_tokens": 41169406.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.064826965332031,
|
|
"epoch": 1.7558070279928528,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004702140876215047,
|
|
"loss": 4.8559,
|
|
"mean_token_accuracy": 0.20712914019823075,
|
|
"num_tokens": 41183183.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.023925685882569,
|
|
"epoch": 1.7564026206075045,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004701928957966991,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.19812337160110474,
|
|
"num_tokens": 41198550.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.029681873321533,
|
|
"epoch": 1.756998213222156,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004701716969706416,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.20120100378990174,
|
|
"num_tokens": 41211231.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.062645530700683,
|
|
"epoch": 1.7575938058368075,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004701504911440927,
|
|
"loss": 4.8103,
|
|
"mean_token_accuracy": 0.2020858719944954,
|
|
"num_tokens": 41224934.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.087074232101441,
|
|
"epoch": 1.7581893984514592,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004701292783178129,
|
|
"loss": 4.8891,
|
|
"mean_token_accuracy": 0.20211613327264785,
|
|
"num_tokens": 41238615.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.07342677116394,
|
|
"epoch": 1.7587849910661109,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004701080584925633,
|
|
"loss": 4.7995,
|
|
"mean_token_accuracy": 0.20542702823877335,
|
|
"num_tokens": 41252952.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 4.982471942901611,
|
|
"epoch": 1.7593805836807623,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047008683166910477,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.20644691288471223,
|
|
"num_tokens": 41265141.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.009025812149048,
|
|
"epoch": 1.7599761762954138,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004700655978481988,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.197976453602314,
|
|
"num_tokens": 41277544.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.105761194229126,
|
|
"epoch": 1.7605717689100655,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000470044357030607,
|
|
"loss": 4.9423,
|
|
"mean_token_accuracy": 0.20255808383226395,
|
|
"num_tokens": 41289500.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.149639987945557,
|
|
"epoch": 1.7611673615247172,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047002310921709123,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.20100335478782655,
|
|
"num_tokens": 41304148.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.075824165344239,
|
|
"epoch": 1.7617629541393687,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004700018544084136,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.19369958490133285,
|
|
"num_tokens": 41319423.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.040430974960327,
|
|
"epoch": 1.7623585467540201,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004699805926053365,
|
|
"loss": 4.7937,
|
|
"mean_token_accuracy": 0.2095121145248413,
|
|
"num_tokens": 41334503.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.023937177658081,
|
|
"epoch": 1.7629541393686718,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046995932380862254,
|
|
"loss": 4.7879,
|
|
"mean_token_accuracy": 0.2084934026002884,
|
|
"num_tokens": 41347486.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.085358667373657,
|
|
"epoch": 1.7635497319833235,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046993804801903475,
|
|
"loss": 4.8241,
|
|
"mean_token_accuracy": 0.20583789944648742,
|
|
"num_tokens": 41360917.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.049644041061401,
|
|
"epoch": 1.764145324597975,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046991676523733603,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.1987168475985527,
|
|
"num_tokens": 41374212.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.031882333755493,
|
|
"epoch": 1.7647409172126265,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046989547546428986,
|
|
"loss": 4.85,
|
|
"mean_token_accuracy": 0.2037990763783455,
|
|
"num_tokens": 41389444.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 4.998984670639038,
|
|
"epoch": 1.7653365098272782,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046987417870065985,
|
|
"loss": 4.6947,
|
|
"mean_token_accuracy": 0.2055189162492752,
|
|
"num_tokens": 41403262.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.024224090576172,
|
|
"epoch": 1.7659321024419299,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004698528749472099,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.19977712482213975,
|
|
"num_tokens": 41416756.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.1099364280700685,
|
|
"epoch": 1.7665276950565811,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004698315642047042,
|
|
"loss": 4.9677,
|
|
"mean_token_accuracy": 0.1939038947224617,
|
|
"num_tokens": 41431321.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.120618486404419,
|
|
"epoch": 1.7671232876712328,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000469810246473907,
|
|
"loss": 4.8583,
|
|
"mean_token_accuracy": 0.19392747730016707,
|
|
"num_tokens": 41446845.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.083966684341431,
|
|
"epoch": 1.7677188802858845,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046978892175558295,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.19904444068670274,
|
|
"num_tokens": 41460601.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.030071973800659,
|
|
"epoch": 1.768314472900536,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004697675900504971,
|
|
"loss": 4.8023,
|
|
"mean_token_accuracy": 0.20509195923805237,
|
|
"num_tokens": 41475361.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.067873191833496,
|
|
"epoch": 1.7689100655151875,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046974625135941445,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.20833873897790908,
|
|
"num_tokens": 41489400.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.009091901779175,
|
|
"epoch": 1.7695056581298392,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046972490568310043,
|
|
"loss": 4.7776,
|
|
"mean_token_accuracy": 0.20869524478912355,
|
|
"num_tokens": 41504791.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.0556450366973875,
|
|
"epoch": 1.7701012507444909,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046970355302232056,
|
|
"loss": 4.8329,
|
|
"mean_token_accuracy": 0.2060161352157593,
|
|
"num_tokens": 41516570.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.094145488739014,
|
|
"epoch": 1.7706968433591423,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046968219337784083,
|
|
"loss": 4.8914,
|
|
"mean_token_accuracy": 0.19843126982450485,
|
|
"num_tokens": 41530112.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.068334579467773,
|
|
"epoch": 1.7712924359737938,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046966082675042745,
|
|
"loss": 4.8553,
|
|
"mean_token_accuracy": 0.204281947016716,
|
|
"num_tokens": 41543429.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.002330160140991,
|
|
"epoch": 1.7718880285884455,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004696394531408466,
|
|
"loss": 4.7956,
|
|
"mean_token_accuracy": 0.21060043573379517,
|
|
"num_tokens": 41555705.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.012880849838257,
|
|
"epoch": 1.7724836212030972,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046961807254986503,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.1939667731523514,
|
|
"num_tokens": 41570084.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.103959226608277,
|
|
"epoch": 1.7730792138177487,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004695966849782497,
|
|
"loss": 4.874,
|
|
"mean_token_accuracy": 0.20019011497497557,
|
|
"num_tokens": 41583394.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.059953594207764,
|
|
"epoch": 1.7736748064324002,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004695752904267676,
|
|
"loss": 4.8767,
|
|
"mean_token_accuracy": 0.20467797815799713,
|
|
"num_tokens": 41595183.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.104719638824463,
|
|
"epoch": 1.7742703990470519,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004695538888961862,
|
|
"loss": 4.809,
|
|
"mean_token_accuracy": 0.20838824808597564,
|
|
"num_tokens": 41609180.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 4.970718717575073,
|
|
"epoch": 1.7748659916617036,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004695324803872732,
|
|
"loss": 4.7282,
|
|
"mean_token_accuracy": 0.21385655105113982,
|
|
"num_tokens": 41622249.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.01264328956604,
|
|
"epoch": 1.7754615842763548,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046951106490079636,
|
|
"loss": 4.8782,
|
|
"mean_token_accuracy": 0.20765226632356643,
|
|
"num_tokens": 41636393.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.131542491912842,
|
|
"epoch": 1.7760571768910065,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046948964243752393,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.2013857677578926,
|
|
"num_tokens": 41650391.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.105438566207885,
|
|
"epoch": 1.7766527695056582,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046946821299822416,
|
|
"loss": 4.9123,
|
|
"mean_token_accuracy": 0.19585323929786683,
|
|
"num_tokens": 41664690.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.035468673706054,
|
|
"epoch": 1.7772483621203097,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004694467765836659,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.20390160977840424,
|
|
"num_tokens": 41679299.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.036499929428101,
|
|
"epoch": 1.7778439547349612,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004694253331946178,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.21408053636550903,
|
|
"num_tokens": 41692567.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.033022356033325,
|
|
"epoch": 1.7784395473496128,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004694038828318492,
|
|
"loss": 4.7867,
|
|
"mean_token_accuracy": 0.21265470385551452,
|
|
"num_tokens": 41705335.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.06465163230896,
|
|
"epoch": 1.7790351399642645,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004693824254961294,
|
|
"loss": 4.8961,
|
|
"mean_token_accuracy": 0.2014566957950592,
|
|
"num_tokens": 41718991.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 4.979478549957276,
|
|
"epoch": 1.779630732578916,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046936096118822796,
|
|
"loss": 4.7803,
|
|
"mean_token_accuracy": 0.2094866693019867,
|
|
"num_tokens": 41732196.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.005263614654541,
|
|
"epoch": 1.7802263251935675,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004693394899089149,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.1996877074241638,
|
|
"num_tokens": 41743850.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.01551399230957,
|
|
"epoch": 1.7808219178082192,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046931801165896035,
|
|
"loss": 4.8219,
|
|
"mean_token_accuracy": 0.20879429280757905,
|
|
"num_tokens": 41756440.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.08512020111084,
|
|
"epoch": 1.7814175104228709,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004692965264391346,
|
|
"loss": 4.8604,
|
|
"mean_token_accuracy": 0.20656492114067077,
|
|
"num_tokens": 41770858.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.059608030319214,
|
|
"epoch": 1.7820131030375224,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046927503425020847,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.201640522480011,
|
|
"num_tokens": 41786116.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 4.95216932296753,
|
|
"epoch": 1.7826086956521738,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004692535350929525,
|
|
"loss": 4.7731,
|
|
"mean_token_accuracy": 0.20840897560119628,
|
|
"num_tokens": 41801457.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.05643663406372,
|
|
"epoch": 1.7832042882668255,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046923202896813825,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.20091734379529952,
|
|
"num_tokens": 41815603.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.068238258361816,
|
|
"epoch": 1.7837998808814772,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004692105158765369,
|
|
"loss": 4.8586,
|
|
"mean_token_accuracy": 0.20242681801319123,
|
|
"num_tokens": 41829977.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 4.885245895385742,
|
|
"epoch": 1.7843954734961287,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004691889958189201,
|
|
"loss": 4.6868,
|
|
"mean_token_accuracy": 0.21621190160512924,
|
|
"num_tokens": 41842340.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.0624627590179445,
|
|
"epoch": 1.7849910661107802,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046916746879605974,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.1988784998655319,
|
|
"num_tokens": 41857040.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.008996105194091,
|
|
"epoch": 1.7855866587254319,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000469145934808728,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.21402890831232071,
|
|
"num_tokens": 41871827.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.043787956237793,
|
|
"epoch": 1.7861822513400833,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046912439385769723,
|
|
"loss": 4.8639,
|
|
"mean_token_accuracy": 0.203367680311203,
|
|
"num_tokens": 41885845.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 4.998316144943237,
|
|
"epoch": 1.7867778439547348,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004691028459437401,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.2031516283750534,
|
|
"num_tokens": 41900057.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.7867778439547348,
|
|
"eval_entropy": 4.817572024847647,
|
|
"eval_loss": 4.85698127746582,
|
|
"eval_mean_token_accuracy": 0.21201130075140806,
|
|
"eval_num_tokens": 41900057.0,
|
|
"eval_runtime": 24.0805,
|
|
"eval_samples_per_second": 1059.49,
|
|
"eval_steps_per_second": 132.473,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.092764806747437,
|
|
"epoch": 1.7873734365693865,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004690812910676294,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.19909383356571198,
|
|
"num_tokens": 41913983.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.0783178329467775,
|
|
"epoch": 1.7879690291840382,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004690597292301384,
|
|
"loss": 4.8047,
|
|
"mean_token_accuracy": 0.2089241623878479,
|
|
"num_tokens": 41927554.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.096574449539185,
|
|
"epoch": 1.7885646217986897,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046903816043204045,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.19140900671482086,
|
|
"num_tokens": 41941367.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.196870040893555,
|
|
"epoch": 1.7891602144133412,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004690165846741092,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.19092142283916474,
|
|
"num_tokens": 41956173.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.066376447677612,
|
|
"epoch": 1.7897558070279929,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046899500195711843,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.20506010055541993,
|
|
"num_tokens": 41969788.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 4.966058588027954,
|
|
"epoch": 1.7903513996426446,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046897341228184237,
|
|
"loss": 4.7004,
|
|
"mean_token_accuracy": 0.21382632553577424,
|
|
"num_tokens": 41982369.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.091334819793701,
|
|
"epoch": 1.790946992257296,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004689518156490554,
|
|
"loss": 4.9318,
|
|
"mean_token_accuracy": 0.19652052372694015,
|
|
"num_tokens": 41995143.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.018825197219849,
|
|
"epoch": 1.7915425848719475,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004689302120595322,
|
|
"loss": 4.8018,
|
|
"mean_token_accuracy": 0.2030792325735092,
|
|
"num_tokens": 42009290.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.053527116775513,
|
|
"epoch": 1.7921381774865992,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046890860151404753,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.19829327911138533,
|
|
"num_tokens": 42024164.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.0405497550964355,
|
|
"epoch": 1.792733770101251,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046888698401337665,
|
|
"loss": 4.8038,
|
|
"mean_token_accuracy": 0.20086032450199126,
|
|
"num_tokens": 42039738.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.010481214523315,
|
|
"epoch": 1.7933293627159024,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046886535955829487,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.21151747107505797,
|
|
"num_tokens": 42054853.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.121837520599366,
|
|
"epoch": 1.7939249553305538,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004688437281495779,
|
|
"loss": 4.9249,
|
|
"mean_token_accuracy": 0.19858645349740983,
|
|
"num_tokens": 42069926.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 4.97145414352417,
|
|
"epoch": 1.7945205479452055,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004688220897880015,
|
|
"loss": 4.7132,
|
|
"mean_token_accuracy": 0.20834652334451675,
|
|
"num_tokens": 42084072.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.011292314529419,
|
|
"epoch": 1.795116140559857,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004688004444743419,
|
|
"loss": 4.79,
|
|
"mean_token_accuracy": 0.21148386150598525,
|
|
"num_tokens": 42098212.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 4.9633289813995365,
|
|
"epoch": 1.7957117331745085,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046877879220937546,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.20859402567148208,
|
|
"num_tokens": 42111402.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.070432710647583,
|
|
"epoch": 1.7963073257891602,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004687571329938788,
|
|
"loss": 4.8838,
|
|
"mean_token_accuracy": 0.20547055900096894,
|
|
"num_tokens": 42124724.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.090626811981201,
|
|
"epoch": 1.7969029184038119,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046873546682862883,
|
|
"loss": 4.8192,
|
|
"mean_token_accuracy": 0.2100800856947899,
|
|
"num_tokens": 42141562.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.012280559539795,
|
|
"epoch": 1.7974985110184634,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046871379371440263,
|
|
"loss": 4.8671,
|
|
"mean_token_accuracy": 0.19581255167722703,
|
|
"num_tokens": 42155455.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.033775329589844,
|
|
"epoch": 1.7980941036331148,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004686921136519777,
|
|
"loss": 4.8493,
|
|
"mean_token_accuracy": 0.19953034222126007,
|
|
"num_tokens": 42170207.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.0456444263458256,
|
|
"epoch": 1.7986896962477665,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004686704266421314,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.2096468538045883,
|
|
"num_tokens": 42183723.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 4.9745259284973145,
|
|
"epoch": 1.7992852888624182,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004686487326856419,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.20738542079925537,
|
|
"num_tokens": 42198651.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.02652759552002,
|
|
"epoch": 1.7998808814770697,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004686270317832872,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.202200485765934,
|
|
"num_tokens": 42212736.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.010409021377564,
|
|
"epoch": 1.8004764740917212,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004686053239358457,
|
|
"loss": 4.8201,
|
|
"mean_token_accuracy": 0.1975531980395317,
|
|
"num_tokens": 42228573.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.042472410202026,
|
|
"epoch": 1.8010720667063729,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046858360914409596,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.196801994740963,
|
|
"num_tokens": 42244736.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 4.982268381118774,
|
|
"epoch": 1.8016676593210246,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000468561887408817,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.21284958720207214,
|
|
"num_tokens": 42260131.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.003627061843872,
|
|
"epoch": 1.802263251935676,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004685401587307879,
|
|
"loss": 4.7699,
|
|
"mean_token_accuracy": 0.20430953651666642,
|
|
"num_tokens": 42274928.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.130970573425293,
|
|
"epoch": 1.8028588445503275,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004685184231107878,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.2003781482577324,
|
|
"num_tokens": 42289245.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.1017828464508055,
|
|
"epoch": 1.8034544371649792,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004684966805495966,
|
|
"loss": 4.8906,
|
|
"mean_token_accuracy": 0.20383484810590743,
|
|
"num_tokens": 42302964.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 4.987970352172852,
|
|
"epoch": 1.8040500297796307,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000468474931047994,
|
|
"loss": 4.7798,
|
|
"mean_token_accuracy": 0.20474220663309098,
|
|
"num_tokens": 42315456.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.012906932830811,
|
|
"epoch": 1.8046456223942822,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046845317460676033,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.20836093425750732,
|
|
"num_tokens": 42328628.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 4.99201340675354,
|
|
"epoch": 1.8052412150089339,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046843141122667576,
|
|
"loss": 4.8085,
|
|
"mean_token_accuracy": 0.20381063520908355,
|
|
"num_tokens": 42341166.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 4.997985744476319,
|
|
"epoch": 1.8058368076235856,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046840964090852095,
|
|
"loss": 4.7605,
|
|
"mean_token_accuracy": 0.20875226557254792,
|
|
"num_tokens": 42356235.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.00770902633667,
|
|
"epoch": 1.806432400238237,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004683878636530768,
|
|
"loss": 4.8067,
|
|
"mean_token_accuracy": 0.20780086368322373,
|
|
"num_tokens": 42369457.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.0451438426971436,
|
|
"epoch": 1.8070279928528885,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004683660794611244,
|
|
"loss": 4.8357,
|
|
"mean_token_accuracy": 0.20096202492713927,
|
|
"num_tokens": 42383857.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.129430913925171,
|
|
"epoch": 1.8076235854675402,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004683442883334451,
|
|
"loss": 4.9235,
|
|
"mean_token_accuracy": 0.19297796487808228,
|
|
"num_tokens": 42399035.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.039810276031494,
|
|
"epoch": 1.808219178082192,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004683224902708206,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.2009924679994583,
|
|
"num_tokens": 42415048.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.027324295043945,
|
|
"epoch": 1.8088147706968434,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004683006852740326,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.20717345476150512,
|
|
"num_tokens": 42429295.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.011815690994263,
|
|
"epoch": 1.8094103633114949,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004682788733438634,
|
|
"loss": 4.7559,
|
|
"mean_token_accuracy": 0.21758993417024614,
|
|
"num_tokens": 42442584.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 4.939699125289917,
|
|
"epoch": 1.8100059559261465,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004682570544810952,
|
|
"loss": 4.7483,
|
|
"mean_token_accuracy": 0.20729128122329712,
|
|
"num_tokens": 42455953.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.045422077178955,
|
|
"epoch": 1.8106015485407982,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046823522868651076,
|
|
"loss": 4.8638,
|
|
"mean_token_accuracy": 0.20762375146150588,
|
|
"num_tokens": 42470331.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.101368856430054,
|
|
"epoch": 1.8111971411554497,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004682133959608928,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.20037167519330978,
|
|
"num_tokens": 42482987.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.072637701034546,
|
|
"epoch": 1.8117927337701012,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004681915563050245,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.19174865782260894,
|
|
"num_tokens": 42496947.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.073622989654541,
|
|
"epoch": 1.812388326384753,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046816970971968916,
|
|
"loss": 4.8154,
|
|
"mean_token_accuracy": 0.20363427698612213,
|
|
"num_tokens": 42512003.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 4.954482126235962,
|
|
"epoch": 1.8129839189994044,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046814785620567036,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.21576798409223558,
|
|
"num_tokens": 42524776.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.0559680461883545,
|
|
"epoch": 1.8135795116140558,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046812599576375206,
|
|
"loss": 4.8645,
|
|
"mean_token_accuracy": 0.2020370289683342,
|
|
"num_tokens": 42537767.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.091223907470703,
|
|
"epoch": 1.8141751042287075,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004681041283947182,
|
|
"loss": 4.9019,
|
|
"mean_token_accuracy": 0.1966802328824997,
|
|
"num_tokens": 42551611.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 4.999936628341675,
|
|
"epoch": 1.8147706968433592,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004680822540993534,
|
|
"loss": 4.804,
|
|
"mean_token_accuracy": 0.2064656764268875,
|
|
"num_tokens": 42565183.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.077424430847168,
|
|
"epoch": 1.8153662894580107,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046806037287844195,
|
|
"loss": 4.8715,
|
|
"mean_token_accuracy": 0.2022034838795662,
|
|
"num_tokens": 42579001.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.096960544586182,
|
|
"epoch": 1.8159618820726622,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004680384847327689,
|
|
"loss": 4.9481,
|
|
"mean_token_accuracy": 0.20518635362386703,
|
|
"num_tokens": 42593549.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.062947797775268,
|
|
"epoch": 1.8165574746873139,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00046801658966311914,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.20100394189357756,
|
|
"num_tokens": 42607610.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.050371551513672,
|
|
"epoch": 1.8171530673019656,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046799468767027826,
|
|
"loss": 4.8833,
|
|
"mean_token_accuracy": 0.19898575991392137,
|
|
"num_tokens": 42621239.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.147041606903076,
|
|
"epoch": 1.817748659916617,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046797277875503164,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.1884286120533943,
|
|
"num_tokens": 42635350.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.046321868896484,
|
|
"epoch": 1.8183442525312685,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046795086291816516,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.2135651409626007,
|
|
"num_tokens": 42650718.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.0813477516174315,
|
|
"epoch": 1.8189398451459202,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004679289401604651,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.19284690916538239,
|
|
"num_tokens": 42663615.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.129022550582886,
|
|
"epoch": 1.819535437760572,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004679070104827176,
|
|
"loss": 4.8692,
|
|
"mean_token_accuracy": 0.2000892460346222,
|
|
"num_tokens": 42677661.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.070479059219361,
|
|
"epoch": 1.8201310303752234,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004678850738857092,
|
|
"loss": 4.828,
|
|
"mean_token_accuracy": 0.20554797500371932,
|
|
"num_tokens": 42692499.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 4.959032011032105,
|
|
"epoch": 1.8207266229898749,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004678631303702268,
|
|
"loss": 4.7572,
|
|
"mean_token_accuracy": 0.20926925390958787,
|
|
"num_tokens": 42707501.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.054843950271606,
|
|
"epoch": 1.8213222156045266,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046784117993705753,
|
|
"loss": 4.8491,
|
|
"mean_token_accuracy": 0.19781594723463058,
|
|
"num_tokens": 42720703.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.090386772155762,
|
|
"epoch": 1.821917808219178,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004678192225869888,
|
|
"loss": 4.8445,
|
|
"mean_token_accuracy": 0.20472602993249894,
|
|
"num_tokens": 42735839.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.067442512512207,
|
|
"epoch": 1.8225134008338295,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046779725832080793,
|
|
"loss": 4.8756,
|
|
"mean_token_accuracy": 0.20367955565452575,
|
|
"num_tokens": 42750631.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.116540431976318,
|
|
"epoch": 1.8231089934484812,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046777528713930287,
|
|
"loss": 4.9557,
|
|
"mean_token_accuracy": 0.20017902553081512,
|
|
"num_tokens": 42763972.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.0971520900726315,
|
|
"epoch": 1.823704586063133,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004677533090432617,
|
|
"loss": 4.8774,
|
|
"mean_token_accuracy": 0.20073076337575912,
|
|
"num_tokens": 42778087.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.055634212493897,
|
|
"epoch": 1.8243001786777844,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004677313240334727,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.20449997931718827,
|
|
"num_tokens": 42793447.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.150169467926025,
|
|
"epoch": 1.8248957712924359,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004677093321107245,
|
|
"loss": 4.9621,
|
|
"mean_token_accuracy": 0.20201774537563325,
|
|
"num_tokens": 42809930.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 4.99437198638916,
|
|
"epoch": 1.8254913639070875,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046768733327580593,
|
|
"loss": 4.8133,
|
|
"mean_token_accuracy": 0.20653431117534637,
|
|
"num_tokens": 42822469.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.010363960266114,
|
|
"epoch": 1.8260869565217392,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046766532752950604,
|
|
"loss": 4.7281,
|
|
"mean_token_accuracy": 0.21571974605321884,
|
|
"num_tokens": 42837857.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.047833442687988,
|
|
"epoch": 1.8266825491363907,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000467643314872614,
|
|
"loss": 4.847,
|
|
"mean_token_accuracy": 0.20054883360862732,
|
|
"num_tokens": 42852251.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.011827421188355,
|
|
"epoch": 1.8272781417510422,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004676212953059195,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.20545185655355452,
|
|
"num_tokens": 42864792.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.042355585098266,
|
|
"epoch": 1.827873734365694,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046759926883021234,
|
|
"loss": 4.8444,
|
|
"mean_token_accuracy": 0.20185721963644027,
|
|
"num_tokens": 42880172.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 4.994881010055542,
|
|
"epoch": 1.8284693269803456,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046757723544628253,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.20950357019901275,
|
|
"num_tokens": 42894265.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 4.999503803253174,
|
|
"epoch": 1.829064919594997,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004675551951549204,
|
|
"loss": 4.8136,
|
|
"mean_token_accuracy": 0.20642011165618895,
|
|
"num_tokens": 42907656.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.009849739074707,
|
|
"epoch": 1.8296605122096485,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046753314795691653,
|
|
"loss": 4.7593,
|
|
"mean_token_accuracy": 0.20734854638576508,
|
|
"num_tokens": 42920913.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 4.949502849578858,
|
|
"epoch": 1.8302561048243002,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004675110938530617,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.21001679748296737,
|
|
"num_tokens": 42934377.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 4.968737649917602,
|
|
"epoch": 1.8308516974389517,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004674890328441469,
|
|
"loss": 4.8244,
|
|
"mean_token_accuracy": 0.20438458472490312,
|
|
"num_tokens": 42947270.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.081299543380737,
|
|
"epoch": 1.8314472900536032,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004674669649309634,
|
|
"loss": 4.8841,
|
|
"mean_token_accuracy": 0.2019726201891899,
|
|
"num_tokens": 42961767.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.169591665267944,
|
|
"epoch": 1.8320428826682549,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004674448901143029,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.20003897994756697,
|
|
"num_tokens": 42977319.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.052952289581299,
|
|
"epoch": 1.8326384752829066,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004674228083949571,
|
|
"loss": 4.7949,
|
|
"mean_token_accuracy": 0.20847809612751006,
|
|
"num_tokens": 42990124.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 4.9970128536224365,
|
|
"epoch": 1.833234067897558,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004674007197737179,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.20240163654088975,
|
|
"num_tokens": 43004445.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.02396593093872,
|
|
"epoch": 1.8338296605122095,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004673786242513778,
|
|
"loss": 4.8038,
|
|
"mean_token_accuracy": 0.2039292797446251,
|
|
"num_tokens": 43018872.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 4.983705520629883,
|
|
"epoch": 1.8344252531268612,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046735652182872925,
|
|
"loss": 4.7267,
|
|
"mean_token_accuracy": 0.21259789913892746,
|
|
"num_tokens": 43030747.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 4.9683459281921385,
|
|
"epoch": 1.835020845741513,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046733441250656495,
|
|
"loss": 4.772,
|
|
"mean_token_accuracy": 0.20852876156568528,
|
|
"num_tokens": 43045409.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.032045459747314,
|
|
"epoch": 1.8356164383561644,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000467312296285678,
|
|
"loss": 4.7269,
|
|
"mean_token_accuracy": 0.20850714445114135,
|
|
"num_tokens": 43058336.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.012839651107788,
|
|
"epoch": 1.8362120309708159,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004672901731668617,
|
|
"loss": 4.7479,
|
|
"mean_token_accuracy": 0.21007650345563889,
|
|
"num_tokens": 43071065.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 4.93783860206604,
|
|
"epoch": 1.8368076235854676,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046726804315090956,
|
|
"loss": 4.8011,
|
|
"mean_token_accuracy": 0.2044554889202118,
|
|
"num_tokens": 43083751.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.000395393371582,
|
|
"epoch": 1.8374032162001193,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004672459062386152,
|
|
"loss": 4.7187,
|
|
"mean_token_accuracy": 0.21047423630952836,
|
|
"num_tokens": 43096494.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.044170713424682,
|
|
"epoch": 1.8379988088147707,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004672237624307729,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.20733675509691238,
|
|
"num_tokens": 43109988.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.026517486572265,
|
|
"epoch": 1.8385944014294222,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004672016117281767,
|
|
"loss": 4.7786,
|
|
"mean_token_accuracy": 0.20994656383991242,
|
|
"num_tokens": 43123152.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 4.975161933898926,
|
|
"epoch": 1.839189994044074,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004671794541316212,
|
|
"loss": 4.8108,
|
|
"mean_token_accuracy": 0.20958647429943084,
|
|
"num_tokens": 43137531.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.126315069198609,
|
|
"epoch": 1.8397855866587254,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004671572896419011,
|
|
"loss": 4.9114,
|
|
"mean_token_accuracy": 0.19091763645410537,
|
|
"num_tokens": 43150127.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.028310394287109,
|
|
"epoch": 1.8403811792733769,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004671351182598116,
|
|
"loss": 4.8308,
|
|
"mean_token_accuracy": 0.20507358014583588,
|
|
"num_tokens": 43165499.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.1146238327026365,
|
|
"epoch": 1.8409767718880286,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004671129399861476,
|
|
"loss": 4.9455,
|
|
"mean_token_accuracy": 0.19169019758701325,
|
|
"num_tokens": 43179701.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.058581590652466,
|
|
"epoch": 1.8415723645026802,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046709075482170495,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.20859154164791108,
|
|
"num_tokens": 43194285.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.023321533203125,
|
|
"epoch": 1.8421679571173317,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004670685627672792,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.19967232495546341,
|
|
"num_tokens": 43209741.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 4.981366777420044,
|
|
"epoch": 1.8427635497319832,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046704636382366633,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.2041671931743622,
|
|
"num_tokens": 43223183.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.081002426147461,
|
|
"epoch": 1.843359142346635,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004670241579916627,
|
|
"loss": 4.8071,
|
|
"mean_token_accuracy": 0.20524547696113588,
|
|
"num_tokens": 43236767.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 4.9824248313903805,
|
|
"epoch": 1.8439547349612866,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046700194527206476,
|
|
"loss": 4.8088,
|
|
"mean_token_accuracy": 0.21156783998012543,
|
|
"num_tokens": 43250288.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 4.993885564804077,
|
|
"epoch": 1.844550327575938,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046697972566566917,
|
|
"loss": 4.8687,
|
|
"mean_token_accuracy": 0.19652832597494124,
|
|
"num_tokens": 43264137.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.024452829360962,
|
|
"epoch": 1.8451459201905895,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046695749917327297,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.2120300754904747,
|
|
"num_tokens": 43278662.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.096864032745361,
|
|
"epoch": 1.8457415128052412,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046693526579567337,
|
|
"loss": 4.8872,
|
|
"mean_token_accuracy": 0.1984162896871567,
|
|
"num_tokens": 43293818.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.032222843170166,
|
|
"epoch": 1.846337105419893,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046691302553366785,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.20131053477525712,
|
|
"num_tokens": 43307333.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.174279594421387,
|
|
"epoch": 1.8469326980345444,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004668907783880542,
|
|
"loss": 4.9904,
|
|
"mean_token_accuracy": 0.19344663321971894,
|
|
"num_tokens": 43321440.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.022248268127441,
|
|
"epoch": 1.8475282906491959,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046686852435963016,
|
|
"loss": 4.7415,
|
|
"mean_token_accuracy": 0.20631516426801683,
|
|
"num_tokens": 43335918.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.024427127838135,
|
|
"epoch": 1.8481238832638476,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004668462634491943,
|
|
"loss": 4.8671,
|
|
"mean_token_accuracy": 0.19426950067281723,
|
|
"num_tokens": 43351816.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.029455184936523,
|
|
"epoch": 1.848719475878499,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004668239956575448,
|
|
"loss": 4.7836,
|
|
"mean_token_accuracy": 0.20875495821237564,
|
|
"num_tokens": 43365693.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.090226697921753,
|
|
"epoch": 1.8493150684931505,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046680172098548044,
|
|
"loss": 4.839,
|
|
"mean_token_accuracy": 0.20498604625463485,
|
|
"num_tokens": 43380780.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.078619384765625,
|
|
"epoch": 1.8499106611078022,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046677943943380023,
|
|
"loss": 4.8887,
|
|
"mean_token_accuracy": 0.2044103264808655,
|
|
"num_tokens": 43394625.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 4.98905200958252,
|
|
"epoch": 1.850506253722454,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004667571510033034,
|
|
"loss": 4.8394,
|
|
"mean_token_accuracy": 0.2098179653286934,
|
|
"num_tokens": 43407844.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.012880182266235,
|
|
"epoch": 1.8511018463371054,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004667348556947893,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.2093776449561119,
|
|
"num_tokens": 43420553.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.1245924949646,
|
|
"epoch": 1.8516974389517569,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004667125535090577,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.2062707632780075,
|
|
"num_tokens": 43434333.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.166625070571899,
|
|
"epoch": 1.8522930315664086,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004666902444469084,
|
|
"loss": 4.9781,
|
|
"mean_token_accuracy": 0.19401106238365173,
|
|
"num_tokens": 43449504.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 4.990184688568116,
|
|
"epoch": 1.8528886241810603,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004666679285091418,
|
|
"loss": 4.8087,
|
|
"mean_token_accuracy": 0.2007865086197853,
|
|
"num_tokens": 43463875.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.034211301803589,
|
|
"epoch": 1.8534842167957117,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046664560569655825,
|
|
"loss": 4.8141,
|
|
"mean_token_accuracy": 0.20530770868062972,
|
|
"num_tokens": 43476051.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.12332067489624,
|
|
"epoch": 1.8540798094103632,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004666232760099583,
|
|
"loss": 4.8834,
|
|
"mean_token_accuracy": 0.19594452977180482,
|
|
"num_tokens": 43491117.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.044435787200928,
|
|
"epoch": 1.854675402025015,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046660093945014307,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.20027008056640624,
|
|
"num_tokens": 43505312.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.008489084243775,
|
|
"epoch": 1.8552709946396666,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046657859601791367,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.20949994623661042,
|
|
"num_tokens": 43521038.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.11854510307312,
|
|
"epoch": 1.855866587254318,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004665562457140715,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.1978548675775528,
|
|
"num_tokens": 43534204.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 4.996516132354737,
|
|
"epoch": 1.8564621798689696,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004665338885394183,
|
|
"loss": 4.7478,
|
|
"mean_token_accuracy": 0.22110508233308793,
|
|
"num_tokens": 43548346.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 4.98769736289978,
|
|
"epoch": 1.8570577724836212,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004665115244947559,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.20818423926830293,
|
|
"num_tokens": 43562796.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.065461254119873,
|
|
"epoch": 1.857653365098273,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004664891535808865,
|
|
"loss": 4.812,
|
|
"mean_token_accuracy": 0.20659711956977844,
|
|
"num_tokens": 43576460.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 4.998768901824951,
|
|
"epoch": 1.8582489577129242,
|
|
"grad_norm": 3.1875,
|
|
"learning_rate": 0.00046646677579861254,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.207825468480587,
|
|
"num_tokens": 43591090.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.155946969985962,
|
|
"epoch": 1.858844550327576,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004664443911487366,
|
|
"loss": 4.9332,
|
|
"mean_token_accuracy": 0.18927718847990035,
|
|
"num_tokens": 43605190.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.088804149627686,
|
|
"epoch": 1.8594401429422276,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046642199963206155,
|
|
"loss": 4.8571,
|
|
"mean_token_accuracy": 0.20407462418079375,
|
|
"num_tokens": 43619432.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 4.956280946731567,
|
|
"epoch": 1.860035735556879,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046639960124939076,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.21470839381217957,
|
|
"num_tokens": 43631677.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.016633129119873,
|
|
"epoch": 1.8606313281715305,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046637719600152737,
|
|
"loss": 4.7794,
|
|
"mean_token_accuracy": 0.2125173345208168,
|
|
"num_tokens": 43646838.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.087804079055786,
|
|
"epoch": 1.8612269207861822,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004663547838892751,
|
|
"loss": 4.8372,
|
|
"mean_token_accuracy": 0.20623137354850768,
|
|
"num_tokens": 43660533.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.056377601623535,
|
|
"epoch": 1.861822513400834,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004663323649134379,
|
|
"loss": 4.8691,
|
|
"mean_token_accuracy": 0.2019108533859253,
|
|
"num_tokens": 43675232.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.0835577011108395,
|
|
"epoch": 1.8624181060154854,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004663099390748199,
|
|
"loss": 4.8041,
|
|
"mean_token_accuracy": 0.20370250046253205,
|
|
"num_tokens": 43687189.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.015808773040772,
|
|
"epoch": 1.8630136986301369,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046628750637422534,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.20183703154325486,
|
|
"num_tokens": 43700783.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.085223913192749,
|
|
"epoch": 1.8636092912447886,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000466265066812459,
|
|
"loss": 4.8081,
|
|
"mean_token_accuracy": 0.2057995542883873,
|
|
"num_tokens": 43713110.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.041206741333008,
|
|
"epoch": 1.8642048838594403,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046624262039032566,
|
|
"loss": 4.8082,
|
|
"mean_token_accuracy": 0.2069166511297226,
|
|
"num_tokens": 43726163.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.042698574066162,
|
|
"epoch": 1.8648004764740918,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046622016710863053,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.1980504035949707,
|
|
"num_tokens": 43740571.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.114529132843018,
|
|
"epoch": 1.8653960690887432,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004661977069681789,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.20586452186107634,
|
|
"num_tokens": 43752930.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.024721002578735,
|
|
"epoch": 1.865991661703395,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004661752399697763,
|
|
"loss": 4.7475,
|
|
"mean_token_accuracy": 0.21340713351964952,
|
|
"num_tokens": 43765626.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.033119153976441,
|
|
"epoch": 1.8665872543180466,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046615276611422876,
|
|
"loss": 4.8513,
|
|
"mean_token_accuracy": 0.1970193788409233,
|
|
"num_tokens": 43779281.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.135880708694458,
|
|
"epoch": 1.8671828469326979,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046613028540234226,
|
|
"loss": 4.9066,
|
|
"mean_token_accuracy": 0.20265544950962067,
|
|
"num_tokens": 43792809.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.068829870223999,
|
|
"epoch": 1.8677784395473496,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004661077978349232,
|
|
"loss": 4.8248,
|
|
"mean_token_accuracy": 0.20417143702507018,
|
|
"num_tokens": 43806416.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.002416515350342,
|
|
"epoch": 1.8683740321620013,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004660853034127781,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.20916095823049546,
|
|
"num_tokens": 43822068.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.091314458847046,
|
|
"epoch": 1.8689696247766527,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004660628021367139,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.20130055397748947,
|
|
"num_tokens": 43837166.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.042851495742798,
|
|
"epoch": 1.8695652173913042,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004660402940075377,
|
|
"loss": 4.8002,
|
|
"mean_token_accuracy": 0.20385462194681167,
|
|
"num_tokens": 43850432.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.008450555801391,
|
|
"epoch": 1.870160810005956,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004660177790260567,
|
|
"loss": 4.8272,
|
|
"mean_token_accuracy": 0.2053321748971939,
|
|
"num_tokens": 43866508.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 4.954208564758301,
|
|
"epoch": 1.8707564026206076,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004659952571930785,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.21662557423114776,
|
|
"num_tokens": 43880188.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.08935694694519,
|
|
"epoch": 1.871351995235259,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046597272850941104,
|
|
"loss": 4.8567,
|
|
"mean_token_accuracy": 0.20007851868867874,
|
|
"num_tokens": 43892869.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 4.98866901397705,
|
|
"epoch": 1.8719475878499106,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046595019297586226,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.2076892852783203,
|
|
"num_tokens": 43905989.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.025725603103638,
|
|
"epoch": 1.8725431804645623,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004659276505932405,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.1924239695072174,
|
|
"num_tokens": 43919478.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.065151691436768,
|
|
"epoch": 1.873138773079214,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046590510136235435,
|
|
"loss": 4.7565,
|
|
"mean_token_accuracy": 0.2074211299419403,
|
|
"num_tokens": 43933724.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.071544218063354,
|
|
"epoch": 1.8737343656938654,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046588254528401264,
|
|
"loss": 4.8357,
|
|
"mean_token_accuracy": 0.20560646802186966,
|
|
"num_tokens": 43947770.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.025215673446655,
|
|
"epoch": 1.874329958308517,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046585998235902437,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.20037735998630524,
|
|
"num_tokens": 43963126.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.131620931625366,
|
|
"epoch": 1.8749255509231686,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046583741258819894,
|
|
"loss": 4.9088,
|
|
"mean_token_accuracy": 0.2001703590154648,
|
|
"num_tokens": 43975767.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.056848382949829,
|
|
"epoch": 1.8755211435378203,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004658148359723457,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.2100555419921875,
|
|
"num_tokens": 43987772.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 4.971350288391113,
|
|
"epoch": 1.8761167361524718,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004657922525122746,
|
|
"loss": 4.7471,
|
|
"mean_token_accuracy": 0.2131744936108589,
|
|
"num_tokens": 44001441.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.087222862243652,
|
|
"epoch": 1.8767123287671232,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004657696622087955,
|
|
"loss": 4.8185,
|
|
"mean_token_accuracy": 0.20107708126306534,
|
|
"num_tokens": 44015503.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.003170299530029,
|
|
"epoch": 1.877307921381775,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004657470650627189,
|
|
"loss": 4.8088,
|
|
"mean_token_accuracy": 0.2068217784166336,
|
|
"num_tokens": 44031106.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.0216302394866945,
|
|
"epoch": 1.8779035139964264,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046572446107485515,
|
|
"loss": 4.8114,
|
|
"mean_token_accuracy": 0.21011373847723008,
|
|
"num_tokens": 44043449.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.036474609375,
|
|
"epoch": 1.8784991066110779,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004657018502460152,
|
|
"loss": 4.7702,
|
|
"mean_token_accuracy": 0.2092340975999832,
|
|
"num_tokens": 44056475.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.069646596908569,
|
|
"epoch": 1.8790946992257296,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046567923257700983,
|
|
"loss": 4.8466,
|
|
"mean_token_accuracy": 0.20389257073402406,
|
|
"num_tokens": 44070143.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.094007873535157,
|
|
"epoch": 1.8796902918403813,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004656566080686504,
|
|
"loss": 4.8834,
|
|
"mean_token_accuracy": 0.1942105382680893,
|
|
"num_tokens": 44084800.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.060668182373047,
|
|
"epoch": 1.8802858844550328,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004656339767217485,
|
|
"loss": 4.788,
|
|
"mean_token_accuracy": 0.20498759299516678,
|
|
"num_tokens": 44098784.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 4.960750246047974,
|
|
"epoch": 1.8808814770696842,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046561133853711576,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.20749442428350448,
|
|
"num_tokens": 44111708.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 4.986237049102783,
|
|
"epoch": 1.881477069684336,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004655886935155643,
|
|
"loss": 4.7469,
|
|
"mean_token_accuracy": 0.20927949398756027,
|
|
"num_tokens": 44126219.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.060215330123901,
|
|
"epoch": 1.8820726622989876,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004655660416579062,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.20436826050281526,
|
|
"num_tokens": 44141723.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.025767850875854,
|
|
"epoch": 1.882668254913639,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000465543382964954,
|
|
"loss": 4.7841,
|
|
"mean_token_accuracy": 0.21472963094711303,
|
|
"num_tokens": 44155410.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 4.962956666946411,
|
|
"epoch": 1.8832638475282906,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046552071743752055,
|
|
"loss": 4.8062,
|
|
"mean_token_accuracy": 0.20657219290733336,
|
|
"num_tokens": 44170626.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.026548290252686,
|
|
"epoch": 1.8838594401429423,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004654980450764186,
|
|
"loss": 4.8004,
|
|
"mean_token_accuracy": 0.20781328976154329,
|
|
"num_tokens": 44182342.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 4.967398309707642,
|
|
"epoch": 1.884455032757594,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046547536588246167,
|
|
"loss": 4.6641,
|
|
"mean_token_accuracy": 0.21219332069158553,
|
|
"num_tokens": 44195903.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.075927066802978,
|
|
"epoch": 1.8850506253722454,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046545267985646294,
|
|
"loss": 4.9155,
|
|
"mean_token_accuracy": 0.19865305870771408,
|
|
"num_tokens": 44210024.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.061227130889892,
|
|
"epoch": 1.885646217986897,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046542998699923625,
|
|
"loss": 4.8328,
|
|
"mean_token_accuracy": 0.20255055874586106,
|
|
"num_tokens": 44222847.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 4.976748418807984,
|
|
"epoch": 1.8862418106015486,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004654072873115956,
|
|
"loss": 4.7283,
|
|
"mean_token_accuracy": 0.2061124250292778,
|
|
"num_tokens": 44236547.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.029715061187744,
|
|
"epoch": 1.8868374032162,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046538458079435516,
|
|
"loss": 4.8151,
|
|
"mean_token_accuracy": 0.2059916228055954,
|
|
"num_tokens": 44250192.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.04608039855957,
|
|
"epoch": 1.8874329958308516,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004653618674483293,
|
|
"loss": 4.7922,
|
|
"mean_token_accuracy": 0.20630911886692047,
|
|
"num_tokens": 44264834.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.02704644203186,
|
|
"epoch": 1.8880285884455033,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046533914727433276,
|
|
"loss": 4.7755,
|
|
"mean_token_accuracy": 0.20277747362852097,
|
|
"num_tokens": 44280375.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.052482271194458,
|
|
"epoch": 1.888624181060155,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004653164202731804,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.21722620725631714,
|
|
"num_tokens": 44294670.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.001254892349243,
|
|
"epoch": 1.8892197736748064,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046529368644568765,
|
|
"loss": 4.7778,
|
|
"mean_token_accuracy": 0.20575715899467467,
|
|
"num_tokens": 44306709.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 4.950494337081909,
|
|
"epoch": 1.889815366289458,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004652709457926697,
|
|
"loss": 4.7436,
|
|
"mean_token_accuracy": 0.21291275769472123,
|
|
"num_tokens": 44320902.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.040596914291382,
|
|
"epoch": 1.8904109589041096,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046524819831494224,
|
|
"loss": 4.7403,
|
|
"mean_token_accuracy": 0.21070693135261537,
|
|
"num_tokens": 44334524.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.006803178787232,
|
|
"epoch": 1.8910065515187613,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004652254440133213,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.20979863703250884,
|
|
"num_tokens": 44349278.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.0006516456604,
|
|
"epoch": 1.8916021441334128,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004652026828886229,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.205709832906723,
|
|
"num_tokens": 44364295.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.000531196594238,
|
|
"epoch": 1.8921977367480642,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004651799149416636,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.2105781689286232,
|
|
"num_tokens": 44376551.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.074296140670777,
|
|
"epoch": 1.892793329362716,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004651571401732599,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.21013049334287642,
|
|
"num_tokens": 44391378.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.0818743228912355,
|
|
"epoch": 1.8933889219773676,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004651343585842287,
|
|
"loss": 4.8773,
|
|
"mean_token_accuracy": 0.19915627539157868,
|
|
"num_tokens": 44406164.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.036726713180542,
|
|
"epoch": 1.893984514592019,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004651115701753873,
|
|
"loss": 4.8729,
|
|
"mean_token_accuracy": 0.20325402915477753,
|
|
"num_tokens": 44420567.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.083971309661865,
|
|
"epoch": 1.8945801072066706,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046508877494755296,
|
|
"loss": 4.8399,
|
|
"mean_token_accuracy": 0.2039625331759453,
|
|
"num_tokens": 44434170.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.142092657089234,
|
|
"epoch": 1.8951756998213223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046506597290154337,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.2004133626818657,
|
|
"num_tokens": 44448067.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.069651412963867,
|
|
"epoch": 1.8957712924359738,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046504316403817627,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.20134636014699936,
|
|
"num_tokens": 44462266.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.045570802688599,
|
|
"epoch": 1.8963668850506252,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004650203483582699,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.2030819907784462,
|
|
"num_tokens": 44476180.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.055240201950073,
|
|
"epoch": 1.896962477665277,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046499752586264264,
|
|
"loss": 4.8754,
|
|
"mean_token_accuracy": 0.1917853593826294,
|
|
"num_tokens": 44490682.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.079914617538452,
|
|
"epoch": 1.8975580702799286,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004649746965521129,
|
|
"loss": 4.7691,
|
|
"mean_token_accuracy": 0.20727960020303726,
|
|
"num_tokens": 44506128.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.090889167785645,
|
|
"epoch": 1.89815366289458,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004649518604274999,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.20499004423618317,
|
|
"num_tokens": 44520435.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.094339036941529,
|
|
"epoch": 1.8987492555092316,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004649290174896223,
|
|
"loss": 4.9293,
|
|
"mean_token_accuracy": 0.19653512239456178,
|
|
"num_tokens": 44533852.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.132557964324951,
|
|
"epoch": 1.8993448481238833,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004649061677392998,
|
|
"loss": 4.9102,
|
|
"mean_token_accuracy": 0.20242013931274414,
|
|
"num_tokens": 44548523.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.014028406143188,
|
|
"epoch": 1.899940440738535,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046488331117735176,
|
|
"loss": 4.7693,
|
|
"mean_token_accuracy": 0.2117680460214615,
|
|
"num_tokens": 44562411.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.058494520187378,
|
|
"epoch": 1.9005360333531864,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004648604478045981,
|
|
"loss": 4.8644,
|
|
"mean_token_accuracy": 0.20135024487972258,
|
|
"num_tokens": 44574831.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.033396244049072,
|
|
"epoch": 1.901131625967838,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046483757762185877,
|
|
"loss": 4.7726,
|
|
"mean_token_accuracy": 0.20388297885656356,
|
|
"num_tokens": 44591353.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.1150353908538815,
|
|
"epoch": 1.9017272185824896,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004648147006299543,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.21168587356805801,
|
|
"num_tokens": 44605498.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.040933895111084,
|
|
"epoch": 1.9023228111971413,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004647918168297051,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.20899601578712462,
|
|
"num_tokens": 44621042.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.01348910331726,
|
|
"epoch": 1.9029184038117928,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046476892622193206,
|
|
"loss": 4.8489,
|
|
"mean_token_accuracy": 0.19925750344991683,
|
|
"num_tokens": 44635819.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.0880523204803465,
|
|
"epoch": 1.9035139964264443,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004647460288074562,
|
|
"loss": 4.8509,
|
|
"mean_token_accuracy": 0.20131459087133408,
|
|
"num_tokens": 44649578.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.141515064239502,
|
|
"epoch": 1.904109589041096,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004647231245870987,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.20868157893419265,
|
|
"num_tokens": 44662788.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 4.990918731689453,
|
|
"epoch": 1.9047051816557474,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046470021356168116,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.2017669215798378,
|
|
"num_tokens": 44675976.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.047395706176758,
|
|
"epoch": 1.905300774270399,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046467729573202555,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.19724637567996978,
|
|
"num_tokens": 44690350.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.149002027511597,
|
|
"epoch": 1.9058963668850506,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046465437109895365,
|
|
"loss": 4.876,
|
|
"mean_token_accuracy": 0.1964278683066368,
|
|
"num_tokens": 44703959.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.074619960784912,
|
|
"epoch": 1.9064919594997023,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004646314396632878,
|
|
"loss": 4.819,
|
|
"mean_token_accuracy": 0.20599519908428193,
|
|
"num_tokens": 44719925.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 4.9673171043396,
|
|
"epoch": 1.9070875521143538,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004646085014258506,
|
|
"loss": 4.8031,
|
|
"mean_token_accuracy": 0.2028201177716255,
|
|
"num_tokens": 44735039.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 4.997867059707642,
|
|
"epoch": 1.9076831447290052,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046458555638746464,
|
|
"loss": 4.8025,
|
|
"mean_token_accuracy": 0.20175711661577225,
|
|
"num_tokens": 44749194.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.056426572799682,
|
|
"epoch": 1.908278737343657,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046456260454895307,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.20793986171483994,
|
|
"num_tokens": 44762177.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.029423379898072,
|
|
"epoch": 1.9088743299583086,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046453964591113906,
|
|
"loss": 4.783,
|
|
"mean_token_accuracy": 0.20407882779836656,
|
|
"num_tokens": 44776524.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.02022271156311,
|
|
"epoch": 1.90946992257296,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004645166804748462,
|
|
"loss": 4.7432,
|
|
"mean_token_accuracy": 0.21321771144866944,
|
|
"num_tokens": 44789657.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.028439378738403,
|
|
"epoch": 1.9100655151876116,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046449370824089807,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.21172522753477097,
|
|
"num_tokens": 44804121.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.0124046325683596,
|
|
"epoch": 1.9106611078022633,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046447072921011875,
|
|
"loss": 4.7429,
|
|
"mean_token_accuracy": 0.2155429169535637,
|
|
"num_tokens": 44816181.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.0339593410491945,
|
|
"epoch": 1.911256700416915,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046444774338333253,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.20554554909467698,
|
|
"num_tokens": 44828430.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.017057132720947,
|
|
"epoch": 1.9118522930315665,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004644247507613636,
|
|
"loss": 4.8013,
|
|
"mean_token_accuracy": 0.20550681203603743,
|
|
"num_tokens": 44842711.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.017498397827149,
|
|
"epoch": 1.912447885646218,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000464401751345037,
|
|
"loss": 4.7757,
|
|
"mean_token_accuracy": 0.21598124206066133,
|
|
"num_tokens": 44855890.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 4.994491100311279,
|
|
"epoch": 1.9130434782608696,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004643787451351774,
|
|
"loss": 4.8566,
|
|
"mean_token_accuracy": 0.20824402272701265,
|
|
"num_tokens": 44869982.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.0260364532470705,
|
|
"epoch": 1.913639070875521,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004643557321326102,
|
|
"loss": 4.8105,
|
|
"mean_token_accuracy": 0.21388463377952577,
|
|
"num_tokens": 44882799.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.068569850921631,
|
|
"epoch": 1.9142346634901726,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004643327123381607,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.20401326417922974,
|
|
"num_tokens": 44898309.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 4.929578351974487,
|
|
"epoch": 1.9148302561048243,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004643096857526547,
|
|
"loss": 4.662,
|
|
"mean_token_accuracy": 0.22814976871013642,
|
|
"num_tokens": 44909869.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.000197458267212,
|
|
"epoch": 1.915425848719476,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046428665237691806,
|
|
"loss": 4.8891,
|
|
"mean_token_accuracy": 0.19947086423635482,
|
|
"num_tokens": 44925134.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 4.989859867095947,
|
|
"epoch": 1.9160214413341274,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000464263612211777,
|
|
"loss": 4.7382,
|
|
"mean_token_accuracy": 0.21091488003730774,
|
|
"num_tokens": 44938599.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.010462522506714,
|
|
"epoch": 1.916617033948779,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004642405652580578,
|
|
"loss": 4.7473,
|
|
"mean_token_accuracy": 0.2132188707590103,
|
|
"num_tokens": 44953313.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.060311508178711,
|
|
"epoch": 1.9172126265634306,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004642175115165873,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.1930466666817665,
|
|
"num_tokens": 44966850.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.066232824325562,
|
|
"epoch": 1.9178082191780823,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046419445098819223,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.2061186447739601,
|
|
"num_tokens": 44979661.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.020945501327515,
|
|
"epoch": 1.9184038117927338,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046417138367369995,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.21187428385019302,
|
|
"num_tokens": 44994530.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.097028207778931,
|
|
"epoch": 1.9189994044073853,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046414830957393756,
|
|
"loss": 4.7835,
|
|
"mean_token_accuracy": 0.2092294991016388,
|
|
"num_tokens": 45007605.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.040738487243653,
|
|
"epoch": 1.919594997022037,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046412522868973297,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.20692363381385803,
|
|
"num_tokens": 45022057.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.0501728534698485,
|
|
"epoch": 1.9201905896366886,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004641021410219138,
|
|
"loss": 4.7748,
|
|
"mean_token_accuracy": 0.20707305371761323,
|
|
"num_tokens": 45035430.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.00273699760437,
|
|
"epoch": 1.9207861822513401,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046407904657130833,
|
|
"loss": 4.7556,
|
|
"mean_token_accuracy": 0.20184715539216996,
|
|
"num_tokens": 45049741.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.022162294387817,
|
|
"epoch": 1.9213817748659916,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004640559453387449,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.21571224331855773,
|
|
"num_tokens": 45063430.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 4.993875646591187,
|
|
"epoch": 1.9219773674806433,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004640328373250521,
|
|
"loss": 4.7749,
|
|
"mean_token_accuracy": 0.21140048801898956,
|
|
"num_tokens": 45078367.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.0562395572662355,
|
|
"epoch": 1.9225729600952948,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046400972253105884,
|
|
"loss": 4.8054,
|
|
"mean_token_accuracy": 0.20344460904598236,
|
|
"num_tokens": 45091908.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.019262218475342,
|
|
"epoch": 1.9231685527099462,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000463986600957594,
|
|
"loss": 4.7664,
|
|
"mean_token_accuracy": 0.20925761610269547,
|
|
"num_tokens": 45105557.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.087881469726563,
|
|
"epoch": 1.923764145324598,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046396347260548715,
|
|
"loss": 4.8874,
|
|
"mean_token_accuracy": 0.1994252860546112,
|
|
"num_tokens": 45118462.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.058427047729492,
|
|
"epoch": 1.9243597379392496,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004639403374755678,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.21166480779647828,
|
|
"num_tokens": 45131594.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 4.99936466217041,
|
|
"epoch": 1.9249553305539011,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004639171955686657,
|
|
"loss": 4.7146,
|
|
"mean_token_accuracy": 0.22048877626657487,
|
|
"num_tokens": 45144524.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 4.984987497329712,
|
|
"epoch": 1.9255509231685526,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004638940468856109,
|
|
"loss": 4.76,
|
|
"mean_token_accuracy": 0.21739891022443772,
|
|
"num_tokens": 45159979.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.040240669250489,
|
|
"epoch": 1.9261465157832043,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046387089142723386,
|
|
"loss": 4.8514,
|
|
"mean_token_accuracy": 0.2035962536931038,
|
|
"num_tokens": 45174134.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.086945962905884,
|
|
"epoch": 1.926742108397856,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046384772919436497,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.21305812895298004,
|
|
"num_tokens": 45187648.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.089099740982055,
|
|
"epoch": 1.9273377010125075,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046382456018783513,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.20539558082818984,
|
|
"num_tokens": 45202000.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.0978411674499515,
|
|
"epoch": 1.927933293627159,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004638013844084753,
|
|
"loss": 4.9069,
|
|
"mean_token_accuracy": 0.19316545128822327,
|
|
"num_tokens": 45218379.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.0886492252349855,
|
|
"epoch": 1.9285288862418106,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004637782018571167,
|
|
"loss": 4.8838,
|
|
"mean_token_accuracy": 0.19495782256126404,
|
|
"num_tokens": 45233571.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.049827909469604,
|
|
"epoch": 1.9291244788564623,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004637550125345911,
|
|
"loss": 4.7774,
|
|
"mean_token_accuracy": 0.20669048130512238,
|
|
"num_tokens": 45247322.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.038447332382202,
|
|
"epoch": 1.9297200714711138,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046373181644173,
|
|
"loss": 4.8348,
|
|
"mean_token_accuracy": 0.2107880562543869,
|
|
"num_tokens": 45259496.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.040180921554565,
|
|
"epoch": 1.9303156640857653,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004637086135793655,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.2038801819086075,
|
|
"num_tokens": 45274661.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.062154245376587,
|
|
"epoch": 1.930911256700417,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004636854039483299,
|
|
"loss": 4.8223,
|
|
"mean_token_accuracy": 0.2036331281065941,
|
|
"num_tokens": 45289166.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.023340702056885,
|
|
"epoch": 1.9315068493150684,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046366218754945556,
|
|
"loss": 4.7997,
|
|
"mean_token_accuracy": 0.20863302648067475,
|
|
"num_tokens": 45302220.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.05563588142395,
|
|
"epoch": 1.93210244192972,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004636389643835754,
|
|
"loss": 4.8684,
|
|
"mean_token_accuracy": 0.20124190151691437,
|
|
"num_tokens": 45316299.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 4.9936573028564455,
|
|
"epoch": 1.9326980345443716,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046361573445152224,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.20830822587013245,
|
|
"num_tokens": 45330176.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.104841852188111,
|
|
"epoch": 1.9332936271590233,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046359249775412934,
|
|
"loss": 4.8958,
|
|
"mean_token_accuracy": 0.20103648900985718,
|
|
"num_tokens": 45344243.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 4.963304424285889,
|
|
"epoch": 1.9338892197736748,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004635692542922302,
|
|
"loss": 4.7527,
|
|
"mean_token_accuracy": 0.20610989332199098,
|
|
"num_tokens": 45360093.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 4.9613463401794435,
|
|
"epoch": 1.9344848123883263,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046354600406665853,
|
|
"loss": 4.7711,
|
|
"mean_token_accuracy": 0.20764055252075195,
|
|
"num_tokens": 45373990.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 4.948494386672974,
|
|
"epoch": 1.935080405002978,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046352274707824823,
|
|
"loss": 4.7065,
|
|
"mean_token_accuracy": 0.21776996105909346,
|
|
"num_tokens": 45386842.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.015946340560913,
|
|
"epoch": 1.9356759976176297,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004634994833278334,
|
|
"loss": 4.8817,
|
|
"mean_token_accuracy": 0.20375698059797287,
|
|
"num_tokens": 45400629.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.006033658981323,
|
|
"epoch": 1.9362715902322811,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004634762128162487,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.20604207068681718,
|
|
"num_tokens": 45413228.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.025374698638916,
|
|
"epoch": 1.9368671828469326,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004634529355443287,
|
|
"loss": 4.7936,
|
|
"mean_token_accuracy": 0.20436130613088607,
|
|
"num_tokens": 45426773.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.119101858139038,
|
|
"epoch": 1.9374627754615843,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046342965151290836,
|
|
"loss": 4.8117,
|
|
"mean_token_accuracy": 0.20794612318277358,
|
|
"num_tokens": 45440241.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.060360622406006,
|
|
"epoch": 1.938058368076236,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046340636072282273,
|
|
"loss": 4.8332,
|
|
"mean_token_accuracy": 0.20852288156747817,
|
|
"num_tokens": 45453788.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 4.910380220413208,
|
|
"epoch": 1.9386539606908875,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004633830631749072,
|
|
"loss": 4.7379,
|
|
"mean_token_accuracy": 0.21075813919305803,
|
|
"num_tokens": 45468679.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 4.975214529037475,
|
|
"epoch": 1.939249553305539,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046335975886999754,
|
|
"loss": 4.7293,
|
|
"mean_token_accuracy": 0.21674661785364152,
|
|
"num_tokens": 45482821.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 4.9753947257995605,
|
|
"epoch": 1.9398451459201906,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004633364478089296,
|
|
"loss": 4.7093,
|
|
"mean_token_accuracy": 0.2184829294681549,
|
|
"num_tokens": 45495936.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 4.99604549407959,
|
|
"epoch": 1.9404407385348421,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004633131299925395,
|
|
"loss": 4.8032,
|
|
"mean_token_accuracy": 0.20714469105005265,
|
|
"num_tokens": 45510839.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 4.998528099060058,
|
|
"epoch": 1.9410363311494936,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004632898054216636,
|
|
"loss": 4.7503,
|
|
"mean_token_accuracy": 0.2112959936261177,
|
|
"num_tokens": 45523901.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.012446641921997,
|
|
"epoch": 1.9416319237641453,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046326647409713844,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.20718994587659836,
|
|
"num_tokens": 45538796.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 4.971538639068603,
|
|
"epoch": 1.942227516378797,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046324313601980106,
|
|
"loss": 4.6275,
|
|
"mean_token_accuracy": 0.2215508908033371,
|
|
"num_tokens": 45551641.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 4.9788555145263675,
|
|
"epoch": 1.9428231089934485,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004632197911904884,
|
|
"loss": 4.7306,
|
|
"mean_token_accuracy": 0.21338596642017366,
|
|
"num_tokens": 45566275.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.06475419998169,
|
|
"epoch": 1.9434187016081,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046319643961003785,
|
|
"loss": 4.9267,
|
|
"mean_token_accuracy": 0.2036326676607132,
|
|
"num_tokens": 45581035.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.106286573410034,
|
|
"epoch": 1.9440142942227516,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046317308127928706,
|
|
"loss": 4.7939,
|
|
"mean_token_accuracy": 0.21067938804626465,
|
|
"num_tokens": 45593791.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.010844326019287,
|
|
"epoch": 1.9446098868374033,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004631497161990738,
|
|
"loss": 4.8036,
|
|
"mean_token_accuracy": 0.21405947506427764,
|
|
"num_tokens": 45607840.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 4.964909458160401,
|
|
"epoch": 1.9452054794520548,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004631263443702361,
|
|
"loss": 4.7519,
|
|
"mean_token_accuracy": 0.21289167404174805,
|
|
"num_tokens": 45623360.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.064013528823852,
|
|
"epoch": 1.9458010720667063,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046310296579361225,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.1993170917034149,
|
|
"num_tokens": 45635794.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.009247827529907,
|
|
"epoch": 1.946396664681358,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004630795804700409,
|
|
"loss": 4.8203,
|
|
"mean_token_accuracy": 0.20291856676340103,
|
|
"num_tokens": 45650348.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.0474742412567135,
|
|
"epoch": 1.9469922572960097,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004630561884003608,
|
|
"loss": 4.8022,
|
|
"mean_token_accuracy": 0.20186519771814346,
|
|
"num_tokens": 45665295.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 4.946544551849366,
|
|
"epoch": 1.9475878499106611,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000463032789585411,
|
|
"loss": 4.7459,
|
|
"mean_token_accuracy": 0.2069941833615303,
|
|
"num_tokens": 45681510.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.034610462188721,
|
|
"epoch": 1.9481834425253126,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004630093840260307,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.20486048758029937,
|
|
"num_tokens": 45696459.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.005713701248169,
|
|
"epoch": 1.9487790351399643,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046298597172305956,
|
|
"loss": 4.7896,
|
|
"mean_token_accuracy": 0.20756202191114426,
|
|
"num_tokens": 45709989.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.004195022583008,
|
|
"epoch": 1.949374627754616,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004629625526773372,
|
|
"loss": 4.7856,
|
|
"mean_token_accuracy": 0.21616522818803788,
|
|
"num_tokens": 45723090.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.044202852249145,
|
|
"epoch": 1.9499702203692673,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004629391268897037,
|
|
"loss": 4.7299,
|
|
"mean_token_accuracy": 0.21063594073057174,
|
|
"num_tokens": 45736406.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 4.893872833251953,
|
|
"epoch": 1.950565812983919,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004629156943609993,
|
|
"loss": 4.7027,
|
|
"mean_token_accuracy": 0.21225218772888182,
|
|
"num_tokens": 45749730.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 4.995239639282227,
|
|
"epoch": 1.9511614055985707,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046289225509206445,
|
|
"loss": 4.7493,
|
|
"mean_token_accuracy": 0.21149684637784957,
|
|
"num_tokens": 45762124.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.02793927192688,
|
|
"epoch": 1.9517569982132221,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004628688090837399,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.21433626115322113,
|
|
"num_tokens": 45777749.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.004784822463989,
|
|
"epoch": 1.9523525908278736,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004628453563368666,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.2093291237950325,
|
|
"num_tokens": 45792944.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.0572271823883055,
|
|
"epoch": 1.9529481834425253,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004628218968522859,
|
|
"loss": 4.8855,
|
|
"mean_token_accuracy": 0.19478965997695924,
|
|
"num_tokens": 45807909.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.040044355392456,
|
|
"epoch": 1.953543776057177,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004627984306308391,
|
|
"loss": 4.8261,
|
|
"mean_token_accuracy": 0.2083934426307678,
|
|
"num_tokens": 45819735.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.011477279663086,
|
|
"epoch": 1.9541393686718285,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046277495767336785,
|
|
"loss": 4.7085,
|
|
"mean_token_accuracy": 0.2108275130391121,
|
|
"num_tokens": 45833552.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 4.940410470962524,
|
|
"epoch": 1.95473496128648,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004627514779807142,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.2166459932923317,
|
|
"num_tokens": 45845984.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.030755615234375,
|
|
"epoch": 1.9553305539011316,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004627279915537204,
|
|
"loss": 4.7737,
|
|
"mean_token_accuracy": 0.20580071210861206,
|
|
"num_tokens": 45859035.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.051555824279785,
|
|
"epoch": 1.9559261465157833,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046270449839322863,
|
|
"loss": 4.8248,
|
|
"mean_token_accuracy": 0.20032026916742324,
|
|
"num_tokens": 45872507.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.0224779605865475,
|
|
"epoch": 1.9565217391304348,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046268099850008175,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.212682344019413,
|
|
"num_tokens": 45884352.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.121536159515381,
|
|
"epoch": 1.9571173317450863,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004626574918751226,
|
|
"loss": 4.8487,
|
|
"mean_token_accuracy": 0.2104421839118004,
|
|
"num_tokens": 45897390.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.000356435775757,
|
|
"epoch": 1.957712924359738,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004626339785191944,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.20791281908750534,
|
|
"num_tokens": 45911371.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.028610038757324,
|
|
"epoch": 1.9583085169743897,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004626104584331404,
|
|
"loss": 4.8275,
|
|
"mean_token_accuracy": 0.2050138905644417,
|
|
"num_tokens": 45924228.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.072548866271973,
|
|
"epoch": 1.958904109589041,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004625869316178043,
|
|
"loss": 4.8602,
|
|
"mean_token_accuracy": 0.20483348071575164,
|
|
"num_tokens": 45938951.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.048641061782837,
|
|
"epoch": 1.9594997022036926,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046256339807403,
|
|
"loss": 4.7724,
|
|
"mean_token_accuracy": 0.2078660696744919,
|
|
"num_tokens": 45953344.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 4.994582271575927,
|
|
"epoch": 1.9600952948183443,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004625398578026615,
|
|
"loss": 4.7615,
|
|
"mean_token_accuracy": 0.20893128216266632,
|
|
"num_tokens": 45968007.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.0094311237335205,
|
|
"epoch": 1.9606908874329958,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046251631080454324,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.21116065233945847,
|
|
"num_tokens": 45981016.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.109887647628784,
|
|
"epoch": 1.9612864800476473,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004624927570805198,
|
|
"loss": 4.8572,
|
|
"mean_token_accuracy": 0.20320896357297896,
|
|
"num_tokens": 45995711.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.1085797309875485,
|
|
"epoch": 1.961882072662299,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046246919663143603,
|
|
"loss": 4.8678,
|
|
"mean_token_accuracy": 0.2074504718184471,
|
|
"num_tokens": 46010430.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.059387445449829,
|
|
"epoch": 1.9624776652769507,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000462445629458137,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.19957096576690675,
|
|
"num_tokens": 46026069.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.055945348739624,
|
|
"epoch": 1.9630732578916021,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046242205556146795,
|
|
"loss": 4.7703,
|
|
"mean_token_accuracy": 0.20406728684902192,
|
|
"num_tokens": 46039988.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 4.926572179794311,
|
|
"epoch": 1.9636688505062536,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004623984749422745,
|
|
"loss": 4.6496,
|
|
"mean_token_accuracy": 0.21894851624965667,
|
|
"num_tokens": 46052854.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 4.979602670669555,
|
|
"epoch": 1.9642644431209053,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004623748876014025,
|
|
"loss": 4.75,
|
|
"mean_token_accuracy": 0.2146783083677292,
|
|
"num_tokens": 46066199.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.0314239978790285,
|
|
"epoch": 1.964860035735557,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004623512935396979,
|
|
"loss": 4.7698,
|
|
"mean_token_accuracy": 0.20596810877323152,
|
|
"num_tokens": 46079817.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.016704559326172,
|
|
"epoch": 1.9654556283502085,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000462327692758007,
|
|
"loss": 4.7979,
|
|
"mean_token_accuracy": 0.20731931030750275,
|
|
"num_tokens": 46096088.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.029107666015625,
|
|
"epoch": 1.96605122096486,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004623040852571764,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.2017705962061882,
|
|
"num_tokens": 46110493.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 4.993372249603271,
|
|
"epoch": 1.9666468135795117,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046228047103805277,
|
|
"loss": 4.7355,
|
|
"mean_token_accuracy": 0.2131028175354004,
|
|
"num_tokens": 46123671.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.058421087265015,
|
|
"epoch": 1.9672424061941634,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004622568501014831,
|
|
"loss": 4.8205,
|
|
"mean_token_accuracy": 0.2044118359684944,
|
|
"num_tokens": 46138491.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.011902093887329,
|
|
"epoch": 1.9678379988088148,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00046223322244831475,
|
|
"loss": 4.7432,
|
|
"mean_token_accuracy": 0.2154802829027176,
|
|
"num_tokens": 46151391.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 4.986075687408447,
|
|
"epoch": 1.9684335914234663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000462209588079395,
|
|
"loss": 4.7384,
|
|
"mean_token_accuracy": 0.2135264739394188,
|
|
"num_tokens": 46165061.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.069362020492553,
|
|
"epoch": 1.969029184038118,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004621859469955718,
|
|
"loss": 4.8882,
|
|
"mean_token_accuracy": 0.20517573058605193,
|
|
"num_tokens": 46179753.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 4.912892055511475,
|
|
"epoch": 1.9696247766527695,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046216229919769305,
|
|
"loss": 4.6712,
|
|
"mean_token_accuracy": 0.21933912932872773,
|
|
"num_tokens": 46194928.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.029429149627686,
|
|
"epoch": 1.970220369267421,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000462138644686607,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.20643067359924316,
|
|
"num_tokens": 46208380.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 4.999358129501343,
|
|
"epoch": 1.9708159618820726,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046211498346316194,
|
|
"loss": 4.8177,
|
|
"mean_token_accuracy": 0.20903850942850113,
|
|
"num_tokens": 46222224.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.029954433441162,
|
|
"epoch": 1.9714115544967243,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004620913155282066,
|
|
"loss": 4.7625,
|
|
"mean_token_accuracy": 0.21340505927801132,
|
|
"num_tokens": 46234198.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 4.985206985473633,
|
|
"epoch": 1.9720071471113758,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046206764088259003,
|
|
"loss": 4.8481,
|
|
"mean_token_accuracy": 0.2031572163105011,
|
|
"num_tokens": 46252100.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.084663343429566,
|
|
"epoch": 1.9726027397260273,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004620439595271613,
|
|
"loss": 4.8595,
|
|
"mean_token_accuracy": 0.20279811322689056,
|
|
"num_tokens": 46267789.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 4.969597721099854,
|
|
"epoch": 1.973198332340679,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004620202714627699,
|
|
"loss": 4.7413,
|
|
"mean_token_accuracy": 0.209657946228981,
|
|
"num_tokens": 46280966.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.070480728149414,
|
|
"epoch": 1.9737939249553307,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004619965766902654,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.19967751055955887,
|
|
"num_tokens": 46295252.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.0811079978942875,
|
|
"epoch": 1.9743895175699822,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046197287521049777,
|
|
"loss": 4.8541,
|
|
"mean_token_accuracy": 0.20810705572366714,
|
|
"num_tokens": 46310567.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.05247311592102,
|
|
"epoch": 1.9749851101846336,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004619491670243171,
|
|
"loss": 4.8771,
|
|
"mean_token_accuracy": 0.20792249739170074,
|
|
"num_tokens": 46324294.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.1387786865234375,
|
|
"epoch": 1.9755807027992853,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046192545213257375,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.20334510654211044,
|
|
"num_tokens": 46338259.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 4.908939599990845,
|
|
"epoch": 1.976176295413937,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004619017305361184,
|
|
"loss": 4.6558,
|
|
"mean_token_accuracy": 0.22333632707595824,
|
|
"num_tokens": 46350719.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.045803499221802,
|
|
"epoch": 1.9767718880285885,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004618780022358018,
|
|
"loss": 4.8129,
|
|
"mean_token_accuracy": 0.21156854629516603,
|
|
"num_tokens": 46365059.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.069293689727783,
|
|
"epoch": 1.97736748064324,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004618542672324751,
|
|
"loss": 4.7524,
|
|
"mean_token_accuracy": 0.21267629265785218,
|
|
"num_tokens": 46379567.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 4.968688917160034,
|
|
"epoch": 1.9779630732578917,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046183052552698975,
|
|
"loss": 4.7682,
|
|
"mean_token_accuracy": 0.21425448656082152,
|
|
"num_tokens": 46393578.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.030109024047851,
|
|
"epoch": 1.9785586658725431,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046180677712019707,
|
|
"loss": 4.903,
|
|
"mean_token_accuracy": 0.193560691177845,
|
|
"num_tokens": 46409534.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.13677134513855,
|
|
"epoch": 1.9791542584871946,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004617830220129491,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.1965933308005333,
|
|
"num_tokens": 46422022.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 4.947597885131836,
|
|
"epoch": 1.9797498511018463,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004617592602060979,
|
|
"loss": 4.7623,
|
|
"mean_token_accuracy": 0.20888123214244841,
|
|
"num_tokens": 46435061.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.085011720657349,
|
|
"epoch": 1.980345443716498,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046173549170049554,
|
|
"loss": 4.7989,
|
|
"mean_token_accuracy": 0.20969770103693008,
|
|
"num_tokens": 46448593.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.097485828399658,
|
|
"epoch": 1.9809410363311495,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004617117164969948,
|
|
"loss": 4.894,
|
|
"mean_token_accuracy": 0.1999311551451683,
|
|
"num_tokens": 46463356.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.029121398925781,
|
|
"epoch": 1.981536628945801,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046168793459644837,
|
|
"loss": 4.8527,
|
|
"mean_token_accuracy": 0.20229172855615615,
|
|
"num_tokens": 46475858.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.173962020874024,
|
|
"epoch": 1.9821322215604527,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004616641459997092,
|
|
"loss": 4.9304,
|
|
"mean_token_accuracy": 0.1989092707633972,
|
|
"num_tokens": 46489482.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.022016954421997,
|
|
"epoch": 1.9827278141751044,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004616403507076306,
|
|
"loss": 4.7735,
|
|
"mean_token_accuracy": 0.2067370295524597,
|
|
"num_tokens": 46504203.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 4.996089601516724,
|
|
"epoch": 1.9833234067897558,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004616165487210661,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.2077302888035774,
|
|
"num_tokens": 46518373.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 4.9521831512451175,
|
|
"epoch": 1.9839189994044073,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004615927400408695,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.21549921929836274,
|
|
"num_tokens": 46531823.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 4.977762842178345,
|
|
"epoch": 1.984514592019059,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004615689246678946,
|
|
"loss": 4.7274,
|
|
"mean_token_accuracy": 0.21008067280054094,
|
|
"num_tokens": 46547138.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.005952167510986,
|
|
"epoch": 1.9851101846337107,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004615451026029957,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.21013095676898957,
|
|
"num_tokens": 46560732.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 4.986295413970947,
|
|
"epoch": 1.9857057772483622,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004615212738470273,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.20828319936990738,
|
|
"num_tokens": 46574186.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 4.9927653789520265,
|
|
"epoch": 1.9863013698630136,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046149743840084406,
|
|
"loss": 4.7414,
|
|
"mean_token_accuracy": 0.214046111702919,
|
|
"num_tokens": 46590389.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.056434106826782,
|
|
"epoch": 1.9868969624776653,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046147359626530103,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.20806037485599518,
|
|
"num_tokens": 46603010.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 4.954455184936523,
|
|
"epoch": 1.9874925550923168,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004614497474412532,
|
|
"loss": 4.7138,
|
|
"mean_token_accuracy": 0.21307220607995986,
|
|
"num_tokens": 46617840.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.047729015350342,
|
|
"epoch": 1.9880881477069683,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004614258919295561,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.20787208378314972,
|
|
"num_tokens": 46631601.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.04165096282959,
|
|
"epoch": 1.98868374032162,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004614020297310654,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.2085794448852539,
|
|
"num_tokens": 46644565.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.034688997268677,
|
|
"epoch": 1.9892793329362717,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004613781608466369,
|
|
"loss": 4.8109,
|
|
"mean_token_accuracy": 0.21107377707958222,
|
|
"num_tokens": 46658200.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.1086688995361325,
|
|
"epoch": 1.9898749255509232,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004613542852771269,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.19752187877893448,
|
|
"num_tokens": 46673480.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.024243974685669,
|
|
"epoch": 1.9904705181655746,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046133040302339155,
|
|
"loss": 4.7616,
|
|
"mean_token_accuracy": 0.20650235563516617,
|
|
"num_tokens": 46687451.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.066032886505127,
|
|
"epoch": 1.9910661107802263,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004613065140862877,
|
|
"loss": 4.8992,
|
|
"mean_token_accuracy": 0.1908334717154503,
|
|
"num_tokens": 46702821.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.154671955108642,
|
|
"epoch": 1.991661703394878,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000461282618466672,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.19922153055667877,
|
|
"num_tokens": 46718505.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.031462240219116,
|
|
"epoch": 1.9922572960095295,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046125871616540165,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.21007272005081176,
|
|
"num_tokens": 46733689.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 4.97739315032959,
|
|
"epoch": 1.992852888624181,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004612348071833341,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.2099022701382637,
|
|
"num_tokens": 46749255.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.112185764312744,
|
|
"epoch": 1.9934484812388327,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004612108915213268,
|
|
"loss": 4.9083,
|
|
"mean_token_accuracy": 0.19944363981485366,
|
|
"num_tokens": 46762916.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.05819673538208,
|
|
"epoch": 1.9940440738534844,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046118696918023757,
|
|
"loss": 4.8192,
|
|
"mean_token_accuracy": 0.20144983679056166,
|
|
"num_tokens": 46777640.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.014961004257202,
|
|
"epoch": 1.9946396664681358,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046116304016092445,
|
|
"loss": 4.7563,
|
|
"mean_token_accuracy": 0.2048999324440956,
|
|
"num_tokens": 46792077.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.010759019851685,
|
|
"epoch": 1.9952352590827873,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004611391044642458,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.21146003603935243,
|
|
"num_tokens": 46807922.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.030118083953857,
|
|
"epoch": 1.995830851697439,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046111516209106004,
|
|
"loss": 4.8166,
|
|
"mean_token_accuracy": 0.2078807070851326,
|
|
"num_tokens": 46822514.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.071529197692871,
|
|
"epoch": 1.9964264443120905,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046109121304222607,
|
|
"loss": 4.8491,
|
|
"mean_token_accuracy": 0.20591614097356797,
|
|
"num_tokens": 46835152.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 4.973959493637085,
|
|
"epoch": 1.997022036926742,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004610672573186029,
|
|
"loss": 4.7391,
|
|
"mean_token_accuracy": 0.21743963211774825,
|
|
"num_tokens": 46848297.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.034055900573731,
|
|
"epoch": 1.9976176295413937,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046104329492104967,
|
|
"loss": 4.7774,
|
|
"mean_token_accuracy": 0.20779021382331847,
|
|
"num_tokens": 46860651.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.0384420394897464,
|
|
"epoch": 1.9982132221560454,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046101932585042597,
|
|
"loss": 4.7565,
|
|
"mean_token_accuracy": 0.20274911373853682,
|
|
"num_tokens": 46876456.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.016902303695678,
|
|
"epoch": 1.9988088147706968,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004609953501075915,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.20361756384372712,
|
|
"num_tokens": 46890883.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.025696229934693,
|
|
"epoch": 1.9994044073853483,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004609713676934062,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.19586631804704666,
|
|
"num_tokens": 46906179.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.106628656387329,
|
|
"epoch": 2.0,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004609473786087303,
|
|
"loss": 4.912,
|
|
"mean_token_accuracy": 0.20006809532642364,
|
|
"num_tokens": 46922024.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.00177230834961,
|
|
"epoch": 2.0005955926146517,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004609233828544243,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.21349263638257981,
|
|
"num_tokens": 46936943.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.072814989089966,
|
|
"epoch": 2.001191185229303,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004608993804313489,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.20236144214868546,
|
|
"num_tokens": 46950048.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 4.9847430229187015,
|
|
"epoch": 2.0017867778439546,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046087537134036484,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.22186533510684966,
|
|
"num_tokens": 46963398.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.050351142883301,
|
|
"epoch": 2.0023823704586063,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046085135558233357,
|
|
"loss": 4.8194,
|
|
"mean_token_accuracy": 0.20355330407619476,
|
|
"num_tokens": 46976496.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.007481813430786,
|
|
"epoch": 2.002977963073258,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046082733315811625,
|
|
"loss": 4.6461,
|
|
"mean_token_accuracy": 0.21700208634138107,
|
|
"num_tokens": 46990688.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.061182975769043,
|
|
"epoch": 2.0035735556879093,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046080330406857465,
|
|
"loss": 4.7075,
|
|
"mean_token_accuracy": 0.2148892641067505,
|
|
"num_tokens": 47005028.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.017285633087158,
|
|
"epoch": 2.004169148302561,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00046077926831457073,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.21014507561922074,
|
|
"num_tokens": 47020503.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 4.898106622695923,
|
|
"epoch": 2.0047647409172127,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046075522589696636,
|
|
"loss": 4.6117,
|
|
"mean_token_accuracy": 0.21764541119337083,
|
|
"num_tokens": 47035091.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.011799716949463,
|
|
"epoch": 2.0053603335318644,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046073117681662414,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.21737694144248962,
|
|
"num_tokens": 47048193.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 4.984625291824341,
|
|
"epoch": 2.0059559261465156,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004607071210744066,
|
|
"loss": 4.6145,
|
|
"mean_token_accuracy": 0.2112296402454376,
|
|
"num_tokens": 47061703.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.028363037109375,
|
|
"epoch": 2.0065515187611673,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046068305867117657,
|
|
"loss": 4.7546,
|
|
"mean_token_accuracy": 0.21377712041139602,
|
|
"num_tokens": 47074990.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 4.988195180892944,
|
|
"epoch": 2.007147111375819,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046065898960779704,
|
|
"loss": 4.6544,
|
|
"mean_token_accuracy": 0.22271069139242172,
|
|
"num_tokens": 47089686.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 4.89334020614624,
|
|
"epoch": 2.0077427039904707,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046063491388513144,
|
|
"loss": 4.6424,
|
|
"mean_token_accuracy": 0.22242608517408372,
|
|
"num_tokens": 47102011.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.011680173873901,
|
|
"epoch": 2.008338296605122,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004606108315040434,
|
|
"loss": 4.7426,
|
|
"mean_token_accuracy": 0.20695834308862687,
|
|
"num_tokens": 47115599.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.094801568984986,
|
|
"epoch": 2.0089338892197737,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046058674246539653,
|
|
"loss": 4.7178,
|
|
"mean_token_accuracy": 0.2173265978693962,
|
|
"num_tokens": 47128902.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 4.932806348800659,
|
|
"epoch": 2.0095294818344254,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004605626467700551,
|
|
"loss": 4.686,
|
|
"mean_token_accuracy": 0.21167436391115188,
|
|
"num_tokens": 47144218.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 4.97559003829956,
|
|
"epoch": 2.0101250744490766,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046053854441888305,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.215124648809433,
|
|
"num_tokens": 47157710.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.04047908782959,
|
|
"epoch": 2.0107206670637283,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004605144354127451,
|
|
"loss": 4.7714,
|
|
"mean_token_accuracy": 0.20797016620635986,
|
|
"num_tokens": 47173073.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 4.969204235076904,
|
|
"epoch": 2.01131625967838,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000460490319752506,
|
|
"loss": 4.6179,
|
|
"mean_token_accuracy": 0.22252145260572434,
|
|
"num_tokens": 47186303.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.00994029045105,
|
|
"epoch": 2.0119118522930317,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046046619743903087,
|
|
"loss": 4.7611,
|
|
"mean_token_accuracy": 0.20380060076713563,
|
|
"num_tokens": 47199954.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 4.981207275390625,
|
|
"epoch": 2.012507444907683,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046044206847318457,
|
|
"loss": 4.6816,
|
|
"mean_token_accuracy": 0.21958411931991578,
|
|
"num_tokens": 47214366.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 4.940611124038696,
|
|
"epoch": 2.0131030375223347,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004604179328558329,
|
|
"loss": 4.6827,
|
|
"mean_token_accuracy": 0.21759154200553893,
|
|
"num_tokens": 47229144.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.027839231491089,
|
|
"epoch": 2.0136986301369864,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004603937905878414,
|
|
"loss": 4.7262,
|
|
"mean_token_accuracy": 0.21629002839326858,
|
|
"num_tokens": 47244043.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.051263332366943,
|
|
"epoch": 2.014294222751638,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046036964167007615,
|
|
"loss": 4.741,
|
|
"mean_token_accuracy": 0.21259437948465348,
|
|
"num_tokens": 47256255.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 4.980270862579346,
|
|
"epoch": 2.0148898153662893,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046034548610340316,
|
|
"loss": 4.6905,
|
|
"mean_token_accuracy": 0.21414277255535125,
|
|
"num_tokens": 47270379.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 4.998183727264404,
|
|
"epoch": 2.015485407980941,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046032132388868895,
|
|
"loss": 4.7359,
|
|
"mean_token_accuracy": 0.20688252449035643,
|
|
"num_tokens": 47285927.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.0271659851074215,
|
|
"epoch": 2.0160810005955927,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004602971550268002,
|
|
"loss": 4.7588,
|
|
"mean_token_accuracy": 0.21399820148944854,
|
|
"num_tokens": 47299791.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.076056385040284,
|
|
"epoch": 2.0166765932102444,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004602729795186038,
|
|
"loss": 4.7207,
|
|
"mean_token_accuracy": 0.21309517323970795,
|
|
"num_tokens": 47313388.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 4.990561771392822,
|
|
"epoch": 2.0172721858248956,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046024879736496677,
|
|
"loss": 4.6982,
|
|
"mean_token_accuracy": 0.21657618284225463,
|
|
"num_tokens": 47325690.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.0006818771362305,
|
|
"epoch": 2.0178677784395473,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046022460856675663,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.21366832852363588,
|
|
"num_tokens": 47340137.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.046556282043457,
|
|
"epoch": 2.018463371054199,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004602004131248409,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.20446837097406387,
|
|
"num_tokens": 47354451.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.063408279418946,
|
|
"epoch": 2.0190589636688503,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004601762110400875,
|
|
"loss": 4.8251,
|
|
"mean_token_accuracy": 0.20100048333406448,
|
|
"num_tokens": 47368621.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.060431861877442,
|
|
"epoch": 2.019654556283502,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046015200231336453,
|
|
"loss": 4.711,
|
|
"mean_token_accuracy": 0.20773955285549164,
|
|
"num_tokens": 47383476.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.15815749168396,
|
|
"epoch": 2.0202501488981537,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004601277869455402,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.19633473157882692,
|
|
"num_tokens": 47398009.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 4.915419483184815,
|
|
"epoch": 2.0208457415128054,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046010356493748325,
|
|
"loss": 4.681,
|
|
"mean_token_accuracy": 0.2142249897122383,
|
|
"num_tokens": 47411898.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 4.97752947807312,
|
|
"epoch": 2.0214413341274566,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046007933629006227,
|
|
"loss": 4.7161,
|
|
"mean_token_accuracy": 0.2094321921467781,
|
|
"num_tokens": 47428020.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.01295838356018,
|
|
"epoch": 2.0220369267421083,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004600551010041464,
|
|
"loss": 4.7519,
|
|
"mean_token_accuracy": 0.21232880204916,
|
|
"num_tokens": 47440316.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.079066610336303,
|
|
"epoch": 2.02263251935676,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046003085908060505,
|
|
"loss": 4.7907,
|
|
"mean_token_accuracy": 0.19972857385873793,
|
|
"num_tokens": 47455793.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.0910139083862305,
|
|
"epoch": 2.0232281119714117,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046000661052030765,
|
|
"loss": 4.7923,
|
|
"mean_token_accuracy": 0.20939843803644181,
|
|
"num_tokens": 47470149.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 4.974321365356445,
|
|
"epoch": 2.023823704586063,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004599823553241238,
|
|
"loss": 4.6012,
|
|
"mean_token_accuracy": 0.22205080091953278,
|
|
"num_tokens": 47481372.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.010765027999878,
|
|
"epoch": 2.0244192972007147,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004599580934929237,
|
|
"loss": 4.7087,
|
|
"mean_token_accuracy": 0.2195463165640831,
|
|
"num_tokens": 47494672.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 4.984207439422607,
|
|
"epoch": 2.0250148898153664,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004599338250275775,
|
|
"loss": 4.7052,
|
|
"mean_token_accuracy": 0.21020514965057374,
|
|
"num_tokens": 47510225.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.018287277221679,
|
|
"epoch": 2.025610482430018,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045990954992895566,
|
|
"loss": 4.7987,
|
|
"mean_token_accuracy": 0.20620921552181243,
|
|
"num_tokens": 47524969.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 4.999781084060669,
|
|
"epoch": 2.0262060750446693,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045988526819792897,
|
|
"loss": 4.6125,
|
|
"mean_token_accuracy": 0.21932644993066788,
|
|
"num_tokens": 47539013.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 4.999780321121216,
|
|
"epoch": 2.026801667659321,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004598609798353683,
|
|
"loss": 4.8284,
|
|
"mean_token_accuracy": 0.2029191881418228,
|
|
"num_tokens": 47553905.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 4.952426195144653,
|
|
"epoch": 2.0273972602739727,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004598366848421447,
|
|
"loss": 4.6684,
|
|
"mean_token_accuracy": 0.21613191217184066,
|
|
"num_tokens": 47569788.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 4.952792739868164,
|
|
"epoch": 2.027992852888624,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004598123832191299,
|
|
"loss": 4.6575,
|
|
"mean_token_accuracy": 0.21497473865747452,
|
|
"num_tokens": 47586553.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.052327632904053,
|
|
"epoch": 2.0285884455032757,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004597880749671954,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.20215025246143342,
|
|
"num_tokens": 47602275.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 4.961650276184082,
|
|
"epoch": 2.0291840381179274,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045976376008721303,
|
|
"loss": 4.6729,
|
|
"mean_token_accuracy": 0.21810028553009034,
|
|
"num_tokens": 47615354.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 4.993419456481933,
|
|
"epoch": 2.029779630732579,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000459739438580055,
|
|
"loss": 4.7374,
|
|
"mean_token_accuracy": 0.2062709614634514,
|
|
"num_tokens": 47629619.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 4.984374284744263,
|
|
"epoch": 2.0303752233472303,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045971511044659374,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.2101731479167938,
|
|
"num_tokens": 47642923.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 4.909465742111206,
|
|
"epoch": 2.030970815961882,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004596907756877018,
|
|
"loss": 4.585,
|
|
"mean_token_accuracy": 0.22008670419454573,
|
|
"num_tokens": 47656768.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 4.984188508987427,
|
|
"epoch": 2.0315664085765337,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045966643430425197,
|
|
"loss": 4.7312,
|
|
"mean_token_accuracy": 0.21137033104896547,
|
|
"num_tokens": 47673391.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 4.9423705577850345,
|
|
"epoch": 2.0321620011911854,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004596420862971174,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.2158183291554451,
|
|
"num_tokens": 47688986.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.0358466625213625,
|
|
"epoch": 2.0327575938058366,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004596177316671714,
|
|
"loss": 4.6955,
|
|
"mean_token_accuracy": 0.21222844272851943,
|
|
"num_tokens": 47702761.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.012483358383179,
|
|
"epoch": 2.0333531864204883,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045959337041528753,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.20371941477060318,
|
|
"num_tokens": 47716940.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.099688196182251,
|
|
"epoch": 2.03394877903514,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004595690025423396,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.2051595851778984,
|
|
"num_tokens": 47732587.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.053244543075562,
|
|
"epoch": 2.0345443716497917,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004595446280492017,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.20711003243923187,
|
|
"num_tokens": 47746536.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 4.969959306716919,
|
|
"epoch": 2.035139964264443,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045952024693674795,
|
|
"loss": 4.7316,
|
|
"mean_token_accuracy": 0.20746273249387742,
|
|
"num_tokens": 47761095.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.022707223892212,
|
|
"epoch": 2.0357355568790947,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045949585920585304,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.20758082419633866,
|
|
"num_tokens": 47775841.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 4.98195743560791,
|
|
"epoch": 2.0363311494937464,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045947146485739155,
|
|
"loss": 4.6612,
|
|
"mean_token_accuracy": 0.22135393023490907,
|
|
"num_tokens": 47789385.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.031534433364868,
|
|
"epoch": 2.036926742108398,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045944706389223854,
|
|
"loss": 4.7477,
|
|
"mean_token_accuracy": 0.21242232471704484,
|
|
"num_tokens": 47803207.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 4.9974476337432865,
|
|
"epoch": 2.0375223347230493,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045942265631126935,
|
|
"loss": 4.6775,
|
|
"mean_token_accuracy": 0.21687645614147186,
|
|
"num_tokens": 47816706.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.032212400436402,
|
|
"epoch": 2.038117927337701,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045939824211535925,
|
|
"loss": 4.7629,
|
|
"mean_token_accuracy": 0.21050213426351547,
|
|
"num_tokens": 47831052.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.0052289962768555,
|
|
"epoch": 2.0387135199523527,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000459373821305384,
|
|
"loss": 4.6914,
|
|
"mean_token_accuracy": 0.22326392084360122,
|
|
"num_tokens": 47843563.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.015951251983642,
|
|
"epoch": 2.039309112567004,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045934939388221966,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.20935099422931672,
|
|
"num_tokens": 47856928.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.015728425979614,
|
|
"epoch": 2.0399047051816557,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045932495984674223,
|
|
"loss": 4.7582,
|
|
"mean_token_accuracy": 0.20972610861063004,
|
|
"num_tokens": 47870240.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 4.968251895904541,
|
|
"epoch": 2.0405002977963074,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045930051919982815,
|
|
"loss": 4.7973,
|
|
"mean_token_accuracy": 0.20326294749975204,
|
|
"num_tokens": 47882640.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.004197263717652,
|
|
"epoch": 2.041095890410959,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004592760719423541,
|
|
"loss": 4.7411,
|
|
"mean_token_accuracy": 0.20761077404022216,
|
|
"num_tokens": 47896192.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.026990985870361,
|
|
"epoch": 2.0416914830256103,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000459251618075197,
|
|
"loss": 4.7126,
|
|
"mean_token_accuracy": 0.20844468623399734,
|
|
"num_tokens": 47911283.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.077114486694336,
|
|
"epoch": 2.042287075640262,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045922715759923394,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.20763334780931472,
|
|
"num_tokens": 47928171.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 4.996045112609863,
|
|
"epoch": 2.0428826682549137,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045920269051534225,
|
|
"loss": 4.6934,
|
|
"mean_token_accuracy": 0.21556097716093064,
|
|
"num_tokens": 47943368.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 4.961014127731323,
|
|
"epoch": 2.0434782608695654,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045917821682439955,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.21172407567501067,
|
|
"num_tokens": 47956729.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.0028454780578615,
|
|
"epoch": 2.0440738534842167,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004591537365272837,
|
|
"loss": 4.6907,
|
|
"mean_token_accuracy": 0.21697249114513398,
|
|
"num_tokens": 47970324.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.021339702606201,
|
|
"epoch": 2.0446694460988684,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045912924962487276,
|
|
"loss": 4.7151,
|
|
"mean_token_accuracy": 0.21782103180885315,
|
|
"num_tokens": 47982218.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.0105390548706055,
|
|
"epoch": 2.04526503871352,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045910475611804486,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.20537627786397933,
|
|
"num_tokens": 47996193.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.01760630607605,
|
|
"epoch": 2.0458606313281713,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045908025600767887,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.20476895719766616,
|
|
"num_tokens": 48010320.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.03776330947876,
|
|
"epoch": 2.046456223942823,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004590557492946533,
|
|
"loss": 4.7468,
|
|
"mean_token_accuracy": 0.2064707800745964,
|
|
"num_tokens": 48026207.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 4.993001794815063,
|
|
"epoch": 2.0470518165574747,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045903123597984725,
|
|
"loss": 4.6425,
|
|
"mean_token_accuracy": 0.21612842679023742,
|
|
"num_tokens": 48040102.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 4.99500093460083,
|
|
"epoch": 2.0476474091721264,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045900671606414003,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.2094307467341423,
|
|
"num_tokens": 48053488.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.046487188339233,
|
|
"epoch": 2.0482430017867777,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000458982189548411,
|
|
"loss": 4.8156,
|
|
"mean_token_accuracy": 0.2093148872256279,
|
|
"num_tokens": 48068061.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.0485011577606205,
|
|
"epoch": 2.0488385944014293,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004589576564335401,
|
|
"loss": 4.7616,
|
|
"mean_token_accuracy": 0.21430427581071854,
|
|
"num_tokens": 48080633.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 4.964154672622681,
|
|
"epoch": 2.049434187016081,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004589331167204071,
|
|
"loss": 4.6739,
|
|
"mean_token_accuracy": 0.22067014425992965,
|
|
"num_tokens": 48093567.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 4.91996660232544,
|
|
"epoch": 2.0500297796307327,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004589085704098922,
|
|
"loss": 4.6842,
|
|
"mean_token_accuracy": 0.21225682497024537,
|
|
"num_tokens": 48105859.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.038562536239624,
|
|
"epoch": 2.050625372245384,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000458884017502876,
|
|
"loss": 4.7694,
|
|
"mean_token_accuracy": 0.20910233706235887,
|
|
"num_tokens": 48120950.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 4.957375621795654,
|
|
"epoch": 2.0512209648600357,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045885945800023896,
|
|
"loss": 4.6515,
|
|
"mean_token_accuracy": 0.21493473947048186,
|
|
"num_tokens": 48136708.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 4.893150186538696,
|
|
"epoch": 2.0518165574746874,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045883489190286214,
|
|
"loss": 4.6295,
|
|
"mean_token_accuracy": 0.22617765367031098,
|
|
"num_tokens": 48150485.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 4.904856443405151,
|
|
"epoch": 2.052412150089339,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004588103192116267,
|
|
"loss": 4.618,
|
|
"mean_token_accuracy": 0.21662819534540176,
|
|
"num_tokens": 48164349.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 4.99266562461853,
|
|
"epoch": 2.0530077427039903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004587857399274139,
|
|
"loss": 4.6819,
|
|
"mean_token_accuracy": 0.21372479796409607,
|
|
"num_tokens": 48175436.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 4.998205661773682,
|
|
"epoch": 2.053603335318642,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004587611540511055,
|
|
"loss": 4.7073,
|
|
"mean_token_accuracy": 0.215591698884964,
|
|
"num_tokens": 48189731.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 4.998401689529419,
|
|
"epoch": 2.0541989279332937,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004587365615835832,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.21391343474388122,
|
|
"num_tokens": 48202435.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 4.9836647510528564,
|
|
"epoch": 2.0547945205479454,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004587119625257292,
|
|
"loss": 4.7294,
|
|
"mean_token_accuracy": 0.21323393136262894,
|
|
"num_tokens": 48213821.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.015242576599121,
|
|
"epoch": 2.0553901131625967,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045868735687842584,
|
|
"loss": 4.7787,
|
|
"mean_token_accuracy": 0.21061309278011323,
|
|
"num_tokens": 48227201.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 4.997808456420898,
|
|
"epoch": 2.0559857057772484,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004586627446425556,
|
|
"loss": 4.7342,
|
|
"mean_token_accuracy": 0.21606186926364898,
|
|
"num_tokens": 48241888.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.024651098251343,
|
|
"epoch": 2.0565812983919,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004586381258190013,
|
|
"loss": 4.6845,
|
|
"mean_token_accuracy": 0.2133837580680847,
|
|
"num_tokens": 48256518.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.052515935897827,
|
|
"epoch": 2.0571768910065513,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004586135004086461,
|
|
"loss": 4.7662,
|
|
"mean_token_accuracy": 0.20470735132694245,
|
|
"num_tokens": 48270570.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 4.894044303894043,
|
|
"epoch": 2.057772483621203,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004585888684123731,
|
|
"loss": 4.6472,
|
|
"mean_token_accuracy": 0.21425148993730544,
|
|
"num_tokens": 48283977.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.059590816497803,
|
|
"epoch": 2.0583680762358547,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004585642298310659,
|
|
"loss": 4.7646,
|
|
"mean_token_accuracy": 0.2038243219256401,
|
|
"num_tokens": 48298306.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 4.975022411346435,
|
|
"epoch": 2.0589636688505064,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004585395846656083,
|
|
"loss": 4.7258,
|
|
"mean_token_accuracy": 0.2110723152756691,
|
|
"num_tokens": 48312983.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 4.971974515914917,
|
|
"epoch": 2.0595592614651577,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004585149329168842,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.22564656734466554,
|
|
"num_tokens": 48325877.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 4.97450475692749,
|
|
"epoch": 2.0601548540798094,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045849027458577776,
|
|
"loss": 4.6857,
|
|
"mean_token_accuracy": 0.21402446776628495,
|
|
"num_tokens": 48340601.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 4.966651821136475,
|
|
"epoch": 2.060750446694461,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004584656096731735,
|
|
"loss": 4.7568,
|
|
"mean_token_accuracy": 0.21040738821029664,
|
|
"num_tokens": 48354315.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 4.972498512268066,
|
|
"epoch": 2.0613460393091128,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045844093817995615,
|
|
"loss": 4.7496,
|
|
"mean_token_accuracy": 0.20570498704910278,
|
|
"num_tokens": 48368107.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 4.986482191085815,
|
|
"epoch": 2.061941631923764,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045841626010701065,
|
|
"loss": 4.7254,
|
|
"mean_token_accuracy": 0.21739650815725325,
|
|
"num_tokens": 48380892.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 4.95725736618042,
|
|
"epoch": 2.0625372245384157,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004583915754552221,
|
|
"loss": 4.7066,
|
|
"mean_token_accuracy": 0.22050643265247344,
|
|
"num_tokens": 48394222.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.050916624069214,
|
|
"epoch": 2.0631328171530674,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004583668842254759,
|
|
"loss": 4.8463,
|
|
"mean_token_accuracy": 0.2000848799943924,
|
|
"num_tokens": 48408816.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.050668048858642,
|
|
"epoch": 2.0637284097677187,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004583421864186577,
|
|
"loss": 4.7448,
|
|
"mean_token_accuracy": 0.2067953020334244,
|
|
"num_tokens": 48422992.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 4.956272840499878,
|
|
"epoch": 2.0643240023823703,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045831748203565333,
|
|
"loss": 4.705,
|
|
"mean_token_accuracy": 0.21063263863325118,
|
|
"num_tokens": 48436832.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.034248638153076,
|
|
"epoch": 2.064919594997022,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045829277107734895,
|
|
"loss": 4.7339,
|
|
"mean_token_accuracy": 0.21296836584806442,
|
|
"num_tokens": 48450406.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 4.968057680130005,
|
|
"epoch": 2.0655151876116737,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004582680535446309,
|
|
"loss": 4.6574,
|
|
"mean_token_accuracy": 0.2133042961359024,
|
|
"num_tokens": 48464665.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 4.9468334197998045,
|
|
"epoch": 2.066110780226325,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004582433294383858,
|
|
"loss": 4.7326,
|
|
"mean_token_accuracy": 0.2148236393928528,
|
|
"num_tokens": 48478794.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.015590238571167,
|
|
"epoch": 2.0667063728409767,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045821859875950035,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.20900966674089433,
|
|
"num_tokens": 48494371.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 4.9544456005096436,
|
|
"epoch": 2.0673019654556284,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045819386150886167,
|
|
"loss": 4.6098,
|
|
"mean_token_accuracy": 0.2275538668036461,
|
|
"num_tokens": 48507362.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 4.9464785099029545,
|
|
"epoch": 2.06789755807028,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000458169117687357,
|
|
"loss": 4.7272,
|
|
"mean_token_accuracy": 0.21071847528219223,
|
|
"num_tokens": 48522667.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 4.999831104278565,
|
|
"epoch": 2.0684931506849313,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004581443672958739,
|
|
"loss": 4.7472,
|
|
"mean_token_accuracy": 0.20975856930017472,
|
|
"num_tokens": 48537316.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.040734577178955,
|
|
"epoch": 2.069088743299583,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045811961033530014,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.21686651408672333,
|
|
"num_tokens": 48552012.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 4.967529678344727,
|
|
"epoch": 2.0696843359142347,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045809484680652376,
|
|
"loss": 4.6965,
|
|
"mean_token_accuracy": 0.2124081000685692,
|
|
"num_tokens": 48564919.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.012693405151367,
|
|
"epoch": 2.0702799285288864,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004580700767104328,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.21300858110189438,
|
|
"num_tokens": 48580149.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.045080041885376,
|
|
"epoch": 2.0708755211435377,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045804530004791595,
|
|
"loss": 4.8108,
|
|
"mean_token_accuracy": 0.21319193989038468,
|
|
"num_tokens": 48593130.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 4.964148092269897,
|
|
"epoch": 2.0714711137581894,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004580205168198617,
|
|
"loss": 4.6792,
|
|
"mean_token_accuracy": 0.21999790668487548,
|
|
"num_tokens": 48607426.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 4.918228101730347,
|
|
"epoch": 2.072066706372841,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004579957270271592,
|
|
"loss": 4.6448,
|
|
"mean_token_accuracy": 0.22436890453100206,
|
|
"num_tokens": 48621195.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.03189263343811,
|
|
"epoch": 2.0726622989874928,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045797093067069734,
|
|
"loss": 4.7512,
|
|
"mean_token_accuracy": 0.20770135074853896,
|
|
"num_tokens": 48637311.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 4.929001951217652,
|
|
"epoch": 2.073257891602144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045794612775136584,
|
|
"loss": 4.6307,
|
|
"mean_token_accuracy": 0.2185093179345131,
|
|
"num_tokens": 48650312.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 4.964619827270508,
|
|
"epoch": 2.0738534842167957,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004579213182700541,
|
|
"loss": 4.7185,
|
|
"mean_token_accuracy": 0.21051293462514878,
|
|
"num_tokens": 48663762.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 4.998100805282593,
|
|
"epoch": 2.0744490768314474,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004578965022276521,
|
|
"loss": 4.8239,
|
|
"mean_token_accuracy": 0.2039844200015068,
|
|
"num_tokens": 48678565.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 4.978855466842651,
|
|
"epoch": 2.0750446694460987,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004578716796250501,
|
|
"loss": 4.6801,
|
|
"mean_token_accuracy": 0.21452220380306244,
|
|
"num_tokens": 48692527.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.098312520980835,
|
|
"epoch": 2.0756402620607504,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045784685046313804,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.20286500304937363,
|
|
"num_tokens": 48707023.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.037558841705322,
|
|
"epoch": 2.076235854675402,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045782201474280684,
|
|
"loss": 4.7952,
|
|
"mean_token_accuracy": 0.2077130988240242,
|
|
"num_tokens": 48719796.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 4.966028833389283,
|
|
"epoch": 2.0768314472900538,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045779717246494724,
|
|
"loss": 4.6787,
|
|
"mean_token_accuracy": 0.21936357617378235,
|
|
"num_tokens": 48732902.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.02615213394165,
|
|
"epoch": 2.077427039904705,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004577723236304503,
|
|
"loss": 4.7325,
|
|
"mean_token_accuracy": 0.21095615029335021,
|
|
"num_tokens": 48748891.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 4.98934154510498,
|
|
"epoch": 2.0780226325193567,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004577474682402072,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.207158462703228,
|
|
"num_tokens": 48763008.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.072190046310425,
|
|
"epoch": 2.0786182251340084,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004577226062951096,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.21086834073066713,
|
|
"num_tokens": 48776999.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.0209380149841305,
|
|
"epoch": 2.07921381774866,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004576977377960492,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.2049417719244957,
|
|
"num_tokens": 48790859.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 4.948944759368897,
|
|
"epoch": 2.0798094103633114,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004576728627439179,
|
|
"loss": 4.6008,
|
|
"mean_token_accuracy": 0.22398001849651336,
|
|
"num_tokens": 48803438.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 4.973986959457397,
|
|
"epoch": 2.080405002977963,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004576479811396082,
|
|
"loss": 4.7157,
|
|
"mean_token_accuracy": 0.2129591077566147,
|
|
"num_tokens": 48821044.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 4.915360355377198,
|
|
"epoch": 2.0810005955926147,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004576230929840123,
|
|
"loss": 4.6366,
|
|
"mean_token_accuracy": 0.21462171375751496,
|
|
"num_tokens": 48834968.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.00009331703186,
|
|
"epoch": 2.0815961882072664,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004575981982780229,
|
|
"loss": 4.7314,
|
|
"mean_token_accuracy": 0.21024030745029448,
|
|
"num_tokens": 48847857.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.0125689029693605,
|
|
"epoch": 2.0821917808219177,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004575732970225331,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.22297215610742568,
|
|
"num_tokens": 48863459.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 4.963811445236206,
|
|
"epoch": 2.0827873734365694,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045754838921843597,
|
|
"loss": 4.6928,
|
|
"mean_token_accuracy": 0.20736825913190843,
|
|
"num_tokens": 48877281.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 4.976984739303589,
|
|
"epoch": 2.083382966051221,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004575234748666249,
|
|
"loss": 4.6771,
|
|
"mean_token_accuracy": 0.2166152998805046,
|
|
"num_tokens": 48891269.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 4.962597751617432,
|
|
"epoch": 2.0839785586658723,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004574985539679936,
|
|
"loss": 4.6614,
|
|
"mean_token_accuracy": 0.22157773077487947,
|
|
"num_tokens": 48905319.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 4.968909883499146,
|
|
"epoch": 2.084574151280524,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045747362652343585,
|
|
"loss": 4.7419,
|
|
"mean_token_accuracy": 0.20424915701150895,
|
|
"num_tokens": 48920393.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.028786849975586,
|
|
"epoch": 2.0851697438951757,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004574486925338458,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.203680382668972,
|
|
"num_tokens": 48935249.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 4.948528575897217,
|
|
"epoch": 2.0857653365098274,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004574237520001178,
|
|
"loss": 4.6239,
|
|
"mean_token_accuracy": 0.2182837575674057,
|
|
"num_tokens": 48950039.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 4.963123750686646,
|
|
"epoch": 2.0863609291244787,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00045739880492314645,
|
|
"loss": 4.7143,
|
|
"mean_token_accuracy": 0.21391999572515488,
|
|
"num_tokens": 48963517.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.078504419326782,
|
|
"epoch": 2.0869565217391304,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004573738513038265,
|
|
"loss": 4.8045,
|
|
"mean_token_accuracy": 0.21500573605298995,
|
|
"num_tokens": 48975014.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 4.988951253890991,
|
|
"epoch": 2.087552114353782,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000457348891143053,
|
|
"loss": 4.7233,
|
|
"mean_token_accuracy": 0.21446850150823593,
|
|
"num_tokens": 48989289.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.03763861656189,
|
|
"epoch": 2.0881477069684338,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004573239244417213,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.21301895380020142,
|
|
"num_tokens": 49002157.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.037372827529907,
|
|
"epoch": 2.088743299583085,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004572989512007268,
|
|
"loss": 4.7084,
|
|
"mean_token_accuracy": 0.2135653093457222,
|
|
"num_tokens": 49015381.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 4.989010190963745,
|
|
"epoch": 2.0893388921977367,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045727397142096543,
|
|
"loss": 4.6717,
|
|
"mean_token_accuracy": 0.218785560131073,
|
|
"num_tokens": 49032492.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.040188550949097,
|
|
"epoch": 2.0899344848123884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000457248985103333,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.2115941807627678,
|
|
"num_tokens": 49045259.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 4.993995094299317,
|
|
"epoch": 2.09053007742704,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004572239922487259,
|
|
"loss": 4.6661,
|
|
"mean_token_accuracy": 0.21273283809423446,
|
|
"num_tokens": 49059493.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 4.9403623104095455,
|
|
"epoch": 2.0911256700416914,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00045719899285804027,
|
|
"loss": 4.6874,
|
|
"mean_token_accuracy": 0.21885189712047576,
|
|
"num_tokens": 49073731.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 4.980516195297241,
|
|
"epoch": 2.091721262656343,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045717398693217315,
|
|
"loss": 4.6712,
|
|
"mean_token_accuracy": 0.20902455896139144,
|
|
"num_tokens": 49088534.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 4.908794498443603,
|
|
"epoch": 2.0923168552709948,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045714897447202125,
|
|
"loss": 4.6085,
|
|
"mean_token_accuracy": 0.21532895565032958,
|
|
"num_tokens": 49102257.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 4.9744044780731205,
|
|
"epoch": 2.092912447885646,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045712395547848185,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.21167011708021163,
|
|
"num_tokens": 49117186.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 4.984029388427734,
|
|
"epoch": 2.0935080405002977,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004570989299524523,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.20218639969825744,
|
|
"num_tokens": 49132402.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.073115682601928,
|
|
"epoch": 2.0941036331149494,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045707389789483016,
|
|
"loss": 4.6731,
|
|
"mean_token_accuracy": 0.21868521720170975,
|
|
"num_tokens": 49144891.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 4.9348548412322994,
|
|
"epoch": 2.094699225729601,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004570488593065133,
|
|
"loss": 4.6552,
|
|
"mean_token_accuracy": 0.21697223484516143,
|
|
"num_tokens": 49158424.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 4.906344413757324,
|
|
"epoch": 2.0952948183442524,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004570238141883999,
|
|
"loss": 4.7038,
|
|
"mean_token_accuracy": 0.2241743192076683,
|
|
"num_tokens": 49172217.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 4.970289039611816,
|
|
"epoch": 2.095890410958904,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045699876254138823,
|
|
"loss": 4.7183,
|
|
"mean_token_accuracy": 0.21286372542381288,
|
|
"num_tokens": 49186164.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 4.907176208496094,
|
|
"epoch": 2.0964860035735557,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004569737043663768,
|
|
"loss": 4.6645,
|
|
"mean_token_accuracy": 0.21904864460229873,
|
|
"num_tokens": 49199880.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.060323810577392,
|
|
"epoch": 2.0970815961882074,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004569486396642645,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.21238988339900972,
|
|
"num_tokens": 49211813.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.081239509582519,
|
|
"epoch": 2.0976771888028587,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004569235684359504,
|
|
"loss": 4.7255,
|
|
"mean_token_accuracy": 0.21089772880077362,
|
|
"num_tokens": 49227780.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 4.903807878494263,
|
|
"epoch": 2.0982727814175104,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004568984906823337,
|
|
"loss": 4.6169,
|
|
"mean_token_accuracy": 0.22037457227706908,
|
|
"num_tokens": 49241499.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.058795356750489,
|
|
"epoch": 2.098868374032162,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045687340640431374,
|
|
"loss": 4.8152,
|
|
"mean_token_accuracy": 0.21152069866657258,
|
|
"num_tokens": 49254706.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 4.9749712467193605,
|
|
"epoch": 2.099463966646814,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004568483156027905,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.21707356721162796,
|
|
"num_tokens": 49268278.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 4.99205322265625,
|
|
"epoch": 2.100059559261465,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045682321827866383,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.21693841218948365,
|
|
"num_tokens": 49282001.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.018934679031372,
|
|
"epoch": 2.1006551518761167,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000456798114432834,
|
|
"loss": 4.6662,
|
|
"mean_token_accuracy": 0.2153848797082901,
|
|
"num_tokens": 49294152.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 4.909296560287475,
|
|
"epoch": 2.1012507444907684,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004567730040662013,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.2182688072323799,
|
|
"num_tokens": 49309501.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 4.929120922088623,
|
|
"epoch": 2.1018463371054197,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004567478871796665,
|
|
"loss": 4.6742,
|
|
"mean_token_accuracy": 0.21665476858615876,
|
|
"num_tokens": 49325663.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 4.970756244659424,
|
|
"epoch": 2.1024419297200714,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045672276377413054,
|
|
"loss": 4.6876,
|
|
"mean_token_accuracy": 0.21072292923927308,
|
|
"num_tokens": 49339976.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 4.938046026229858,
|
|
"epoch": 2.103037522334723,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004566976338504945,
|
|
"loss": 4.624,
|
|
"mean_token_accuracy": 0.22180319875478743,
|
|
"num_tokens": 49353706.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 4.975035762786865,
|
|
"epoch": 2.1036331149493748,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004566724974096597,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.2123758912086487,
|
|
"num_tokens": 49366331.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 4.934516716003418,
|
|
"epoch": 2.104228707564026,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004566473544525279,
|
|
"loss": 4.6844,
|
|
"mean_token_accuracy": 0.21726742386817932,
|
|
"num_tokens": 49379870.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 4.951099872589111,
|
|
"epoch": 2.1048243001786777,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004566222049800008,
|
|
"loss": 4.657,
|
|
"mean_token_accuracy": 0.22049307227134704,
|
|
"num_tokens": 49394294.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.026038408279419,
|
|
"epoch": 2.1054198927933294,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00045659704899298045,
|
|
"loss": 4.7163,
|
|
"mean_token_accuracy": 0.21040642112493516,
|
|
"num_tokens": 49409546.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.010000276565552,
|
|
"epoch": 2.106015485407981,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004565718864923693,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.2181204855442047,
|
|
"num_tokens": 49424712.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.001414966583252,
|
|
"epoch": 2.1066110780226324,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004565467174790697,
|
|
"loss": 4.8041,
|
|
"mean_token_accuracy": 0.21059056222438813,
|
|
"num_tokens": 49438958.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 4.964740467071533,
|
|
"epoch": 2.107206670637284,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004565215419539846,
|
|
"loss": 4.7244,
|
|
"mean_token_accuracy": 0.214161516726017,
|
|
"num_tokens": 49452643.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 4.952199792861938,
|
|
"epoch": 2.1078022632519358,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045649635991801686,
|
|
"loss": 4.6173,
|
|
"mean_token_accuracy": 0.22276891469955445,
|
|
"num_tokens": 49465133.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 4.9826233863830565,
|
|
"epoch": 2.1083978558665875,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004564711713720698,
|
|
"loss": 4.744,
|
|
"mean_token_accuracy": 0.2104612648487091,
|
|
"num_tokens": 49479230.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 4.96231689453125,
|
|
"epoch": 2.1089934484812387,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004564459763170469,
|
|
"loss": 4.6643,
|
|
"mean_token_accuracy": 0.21327825784683227,
|
|
"num_tokens": 49493461.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 4.994941997528076,
|
|
"epoch": 2.1095890410958904,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045642077475385186,
|
|
"loss": 4.749,
|
|
"mean_token_accuracy": 0.21554481536149978,
|
|
"num_tokens": 49505919.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.018100023269653,
|
|
"epoch": 2.110184633710542,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045639556668338854,
|
|
"loss": 4.7088,
|
|
"mean_token_accuracy": 0.21318003982305528,
|
|
"num_tokens": 49520411.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 4.851964235305786,
|
|
"epoch": 2.1107802263251934,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045637035210656124,
|
|
"loss": 4.5462,
|
|
"mean_token_accuracy": 0.22844339460134505,
|
|
"num_tokens": 49533689.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 4.944947004318237,
|
|
"epoch": 2.111375818939845,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045634513102427426,
|
|
"loss": 4.7265,
|
|
"mean_token_accuracy": 0.2126840189099312,
|
|
"num_tokens": 49546938.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 4.992167568206787,
|
|
"epoch": 2.1119714115544967,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004563199034374323,
|
|
"loss": 4.7063,
|
|
"mean_token_accuracy": 0.21340484768152237,
|
|
"num_tokens": 49561202.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.026288032531738,
|
|
"epoch": 2.1125670041691484,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004562946693469402,
|
|
"loss": 4.7344,
|
|
"mean_token_accuracy": 0.2155055359005928,
|
|
"num_tokens": 49574704.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 4.985771226882934,
|
|
"epoch": 2.1131625967837997,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004562694287537031,
|
|
"loss": 4.7254,
|
|
"mean_token_accuracy": 0.210019314289093,
|
|
"num_tokens": 49588764.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 4.901813936233521,
|
|
"epoch": 2.1137581893984514,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045624418165862626,
|
|
"loss": 4.6817,
|
|
"mean_token_accuracy": 0.22579230666160582,
|
|
"num_tokens": 49601830.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.04276442527771,
|
|
"epoch": 2.114353782013103,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004562189280626154,
|
|
"loss": 4.7444,
|
|
"mean_token_accuracy": 0.20827723145484925,
|
|
"num_tokens": 49616855.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.0149599552154545,
|
|
"epoch": 2.114949374627755,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004561936679665761,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.20498281717300415,
|
|
"num_tokens": 49632013.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.047214460372925,
|
|
"epoch": 2.115544967242406,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004561684013714147,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.21710124909877776,
|
|
"num_tokens": 49645420.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.022673225402832,
|
|
"epoch": 2.1161405598570577,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004561431282780372,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.20981265753507614,
|
|
"num_tokens": 49660063.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 4.986819076538086,
|
|
"epoch": 2.1167361524717094,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045611784868735024,
|
|
"loss": 4.6666,
|
|
"mean_token_accuracy": 0.2160114824771881,
|
|
"num_tokens": 49674054.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 4.944037580490113,
|
|
"epoch": 2.117331745086361,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004560925626002605,
|
|
"loss": 4.6628,
|
|
"mean_token_accuracy": 0.22098389267921448,
|
|
"num_tokens": 49687603.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 4.921845626831055,
|
|
"epoch": 2.1179273377010124,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000456067270017675,
|
|
"loss": 4.6824,
|
|
"mean_token_accuracy": 0.21976568698883056,
|
|
"num_tokens": 49702559.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.005400991439819,
|
|
"epoch": 2.118522930315664,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045604197094050087,
|
|
"loss": 4.7638,
|
|
"mean_token_accuracy": 0.21435973346233367,
|
|
"num_tokens": 49717358.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 4.919161319732666,
|
|
"epoch": 2.1191185229303158,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004560166653696457,
|
|
"loss": 4.6687,
|
|
"mean_token_accuracy": 0.21430710405111314,
|
|
"num_tokens": 49731643.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.022206544876099,
|
|
"epoch": 2.1197141155449675,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000455991353306017,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.21912163496017456,
|
|
"num_tokens": 49744535.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 4.987455272674561,
|
|
"epoch": 2.1203097081596187,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004559660347505228,
|
|
"loss": 4.7222,
|
|
"mean_token_accuracy": 0.2147303268313408,
|
|
"num_tokens": 49758287.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.049823427200318,
|
|
"epoch": 2.1209053007742704,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000455940709704071,
|
|
"loss": 4.7736,
|
|
"mean_token_accuracy": 0.2056627720594406,
|
|
"num_tokens": 49773062.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 4.959107303619385,
|
|
"epoch": 2.121500893388922,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045591537816757027,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.2140902265906334,
|
|
"num_tokens": 49786320.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 4.8956685066223145,
|
|
"epoch": 2.1220964860035734,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045589004014192903,
|
|
"loss": 4.614,
|
|
"mean_token_accuracy": 0.22170186489820481,
|
|
"num_tokens": 49799765.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 4.938561487197876,
|
|
"epoch": 2.122692078618225,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045586469562805624,
|
|
"loss": 4.687,
|
|
"mean_token_accuracy": 0.22085033655166625,
|
|
"num_tokens": 49813382.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.011349058151245,
|
|
"epoch": 2.1232876712328768,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004558393446268608,
|
|
"loss": 4.7002,
|
|
"mean_token_accuracy": 0.2094699040055275,
|
|
"num_tokens": 49826000.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 4.989745473861694,
|
|
"epoch": 2.1238832638475285,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004558139871392521,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.21352478712797165,
|
|
"num_tokens": 49840725.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 4.972358989715576,
|
|
"epoch": 2.1244788564621797,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004557886231661396,
|
|
"loss": 4.6814,
|
|
"mean_token_accuracy": 0.21310349106788634,
|
|
"num_tokens": 49854400.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.017924976348877,
|
|
"epoch": 2.1250744490768314,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00045576325270843326,
|
|
"loss": 4.7326,
|
|
"mean_token_accuracy": 0.20735680609941481,
|
|
"num_tokens": 49868724.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.022557497024536,
|
|
"epoch": 2.125670041691483,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004557378757670429,
|
|
"loss": 4.738,
|
|
"mean_token_accuracy": 0.20931271016597747,
|
|
"num_tokens": 49883103.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 4.9805006980896,
|
|
"epoch": 2.126265634306135,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004557124923428788,
|
|
"loss": 4.6754,
|
|
"mean_token_accuracy": 0.21318685114383698,
|
|
"num_tokens": 49896179.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 4.9635285377502445,
|
|
"epoch": 2.126861226920786,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004556871024368514,
|
|
"loss": 4.7097,
|
|
"mean_token_accuracy": 0.21399344503879547,
|
|
"num_tokens": 49911524.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.054542160034179,
|
|
"epoch": 2.1274568195354377,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045566170604987145,
|
|
"loss": 4.7781,
|
|
"mean_token_accuracy": 0.21078726500272751,
|
|
"num_tokens": 49925970.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.080336666107177,
|
|
"epoch": 2.1280524121500894,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004556363031828498,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.21215197294950486,
|
|
"num_tokens": 49940184.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 4.985653257369995,
|
|
"epoch": 2.1286480047647407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045561089383669776,
|
|
"loss": 4.7268,
|
|
"mean_token_accuracy": 0.21465538144111634,
|
|
"num_tokens": 49953995.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 4.952040815353394,
|
|
"epoch": 2.1292435973793924,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004555854780123265,
|
|
"loss": 4.6765,
|
|
"mean_token_accuracy": 0.2149527534842491,
|
|
"num_tokens": 49967243.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.061246013641357,
|
|
"epoch": 2.129839189994044,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004555600557106477,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.21195138096809388,
|
|
"num_tokens": 49981431.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.077571439743042,
|
|
"epoch": 2.130434782608696,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004555346269325734,
|
|
"loss": 4.7825,
|
|
"mean_token_accuracy": 0.20235372185707093,
|
|
"num_tokens": 49994984.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 4.941259336471558,
|
|
"epoch": 2.131030375223347,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045550919167901553,
|
|
"loss": 4.6374,
|
|
"mean_token_accuracy": 0.21431142538785936,
|
|
"num_tokens": 50007028.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 4.90662260055542,
|
|
"epoch": 2.1316259678379987,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004554837499508864,
|
|
"loss": 4.5942,
|
|
"mean_token_accuracy": 0.22207791954278946,
|
|
"num_tokens": 50020302.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 4.9964323997497555,
|
|
"epoch": 2.1322215604526504,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004554583017490987,
|
|
"loss": 4.6795,
|
|
"mean_token_accuracy": 0.2213491752743721,
|
|
"num_tokens": 50033923.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 4.9859250545501705,
|
|
"epoch": 2.132817153067302,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045543284707456514,
|
|
"loss": 4.7544,
|
|
"mean_token_accuracy": 0.21112529188394547,
|
|
"num_tokens": 50047118.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 4.943114805221557,
|
|
"epoch": 2.1334127456819534,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004554073859281986,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.21328506320714952,
|
|
"num_tokens": 50061020.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 4.969066190719604,
|
|
"epoch": 2.134008338296605,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004553819183109125,
|
|
"loss": 4.7025,
|
|
"mean_token_accuracy": 0.2140820175409317,
|
|
"num_tokens": 50075226.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.022880983352661,
|
|
"epoch": 2.1346039309112568,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045535644422362026,
|
|
"loss": 4.7633,
|
|
"mean_token_accuracy": 0.2079104572534561,
|
|
"num_tokens": 50091552.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 4.959588718414307,
|
|
"epoch": 2.1351995235259085,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00045533096366723563,
|
|
"loss": 4.6744,
|
|
"mean_token_accuracy": 0.2141692817211151,
|
|
"num_tokens": 50105657.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 4.921263027191162,
|
|
"epoch": 2.1357951161405597,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004553054766426725,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.21883376985788344,
|
|
"num_tokens": 50121410.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 4.949065780639648,
|
|
"epoch": 2.1363907087552114,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045527998315084513,
|
|
"loss": 4.7217,
|
|
"mean_token_accuracy": 0.21936641931533812,
|
|
"num_tokens": 50135149.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.04304518699646,
|
|
"epoch": 2.136986301369863,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004552544831926679,
|
|
"loss": 4.7109,
|
|
"mean_token_accuracy": 0.217091166973114,
|
|
"num_tokens": 50148342.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 4.9335085391998295,
|
|
"epoch": 2.137581893984515,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045522897676905535,
|
|
"loss": 4.627,
|
|
"mean_token_accuracy": 0.22350196838378905,
|
|
"num_tokens": 50164010.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 4.944278764724731,
|
|
"epoch": 2.138177486599166,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004552034638809225,
|
|
"loss": 4.671,
|
|
"mean_token_accuracy": 0.2130119174718857,
|
|
"num_tokens": 50178175.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 4.929482555389404,
|
|
"epoch": 2.1387730792138178,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004551779445291843,
|
|
"loss": 4.5419,
|
|
"mean_token_accuracy": 0.22750747948884964,
|
|
"num_tokens": 50191411.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.070211505889892,
|
|
"epoch": 2.1393686718284695,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045515241871475634,
|
|
"loss": 4.8246,
|
|
"mean_token_accuracy": 0.19816162139177323,
|
|
"num_tokens": 50204029.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 4.9502486228942875,
|
|
"epoch": 2.1399642644431207,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004551268864385539,
|
|
"loss": 4.6628,
|
|
"mean_token_accuracy": 0.2193152666091919,
|
|
"num_tokens": 50219742.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 4.960524559020996,
|
|
"epoch": 2.1405598570577724,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000455101347701493,
|
|
"loss": 4.6687,
|
|
"mean_token_accuracy": 0.2093665599822998,
|
|
"num_tokens": 50234470.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 4.993955802917481,
|
|
"epoch": 2.141155449672424,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045507580250448955,
|
|
"loss": 4.7307,
|
|
"mean_token_accuracy": 0.21507792174816132,
|
|
"num_tokens": 50247814.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 4.948988151550293,
|
|
"epoch": 2.141751042287076,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004550502508484598,
|
|
"loss": 4.6679,
|
|
"mean_token_accuracy": 0.21270288974046708,
|
|
"num_tokens": 50260656.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 4.9638909816741945,
|
|
"epoch": 2.142346634901727,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004550246927343203,
|
|
"loss": 4.7309,
|
|
"mean_token_accuracy": 0.21714805364608764,
|
|
"num_tokens": 50276685.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 4.9788319110870365,
|
|
"epoch": 2.1429422275163788,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004549991281629879,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.2191089615225792,
|
|
"num_tokens": 50289521.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 4.954628276824951,
|
|
"epoch": 2.1435378201310304,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004549735571353793,
|
|
"loss": 4.6758,
|
|
"mean_token_accuracy": 0.21536242812871934,
|
|
"num_tokens": 50303275.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 4.975089073181152,
|
|
"epoch": 2.144133412745682,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004549479796524119,
|
|
"loss": 4.7405,
|
|
"mean_token_accuracy": 0.20944585353136064,
|
|
"num_tokens": 50317613.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 2.144133412745682,
|
|
"eval_entropy": 4.749624477658526,
|
|
"eval_loss": 4.782408714294434,
|
|
"eval_mean_token_accuracy": 0.21968724697968428,
|
|
"eval_num_tokens": 50317613.0,
|
|
"eval_runtime": 24.2825,
|
|
"eval_samples_per_second": 1050.674,
|
|
"eval_steps_per_second": 131.37,
|
|
"step": 18000
|
|
}
|
|
],
|
|
"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": 8.9811987213312e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|