6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.357355568790947,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 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
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 83940,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 1.5035249774592e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|