c3e03886d6
Model: fpadovani/nld-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.27213352685050796,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.774228096008301,
|
|
"epoch": 0.00045355587808418,
|
|
"grad_norm": 17.375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.4464,
|
|
"mean_token_accuracy": 7.704160525463521e-05,
|
|
"num_tokens": 10827.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.7717701435089115,
|
|
"epoch": 0.00090711175616836,
|
|
"grad_norm": 18.375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.3304,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 21025.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.839741182327271,
|
|
"epoch": 0.00136066763425254,
|
|
"grad_norm": 24.125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.0962,
|
|
"mean_token_accuracy": 7.401924231089651e-05,
|
|
"num_tokens": 31678.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.192698621749878,
|
|
"epoch": 0.00181422351233672,
|
|
"grad_norm": 32.0,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.3294,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 41025.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.903842544555664,
|
|
"epoch": 0.0022677793904208998,
|
|
"grad_norm": 10.8125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 11.653,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 51270.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.564220905303955,
|
|
"epoch": 0.00272133526850508,
|
|
"grad_norm": 3.453125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.7764,
|
|
"mean_token_accuracy": 0.0030453664774540814,
|
|
"num_tokens": 62142.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.698297691345214,
|
|
"epoch": 0.00317489114658926,
|
|
"grad_norm": 3.203125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.5251,
|
|
"mean_token_accuracy": 0.017070478899404405,
|
|
"num_tokens": 72709.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.688808727264405,
|
|
"epoch": 0.00362844702467344,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.1613,
|
|
"mean_token_accuracy": 0.029810004867613316,
|
|
"num_tokens": 82313.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.627019691467286,
|
|
"epoch": 0.00408200290275762,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.8529,
|
|
"mean_token_accuracy": 0.03834186047315598,
|
|
"num_tokens": 92450.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.572821617126465,
|
|
"epoch": 0.0045355587808417995,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.7295,
|
|
"mean_token_accuracy": 0.0418919712305069,
|
|
"num_tokens": 103978.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.587093353271484,
|
|
"epoch": 0.00498911465892598,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.5671,
|
|
"mean_token_accuracy": 0.04565211050212383,
|
|
"num_tokens": 114134.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.595294857025147,
|
|
"epoch": 0.00544267053701016,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.5346,
|
|
"mean_token_accuracy": 0.04470008127391338,
|
|
"num_tokens": 125037.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.570393085479736,
|
|
"epoch": 0.00589622641509434,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.3921,
|
|
"mean_token_accuracy": 0.04514850843697786,
|
|
"num_tokens": 134721.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.546493816375733,
|
|
"epoch": 0.00634978229317852,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.3112,
|
|
"mean_token_accuracy": 0.04249380584806204,
|
|
"num_tokens": 144448.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.550293254852296,
|
|
"epoch": 0.006803338171262699,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.2335,
|
|
"mean_token_accuracy": 0.04518970362842083,
|
|
"num_tokens": 154343.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.532429504394532,
|
|
"epoch": 0.00725689404934688,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.2049,
|
|
"mean_token_accuracy": 0.041810613870620725,
|
|
"num_tokens": 165650.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.50885066986084,
|
|
"epoch": 0.007710449927431059,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.2095,
|
|
"mean_token_accuracy": 0.03873651716858149,
|
|
"num_tokens": 177098.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.484589099884033,
|
|
"epoch": 0.00816400580551524,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.9579,
|
|
"mean_token_accuracy": 0.04810894541442394,
|
|
"num_tokens": 187903.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.423638439178466,
|
|
"epoch": 0.00861756168359942,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.8843,
|
|
"mean_token_accuracy": 0.04500575102865696,
|
|
"num_tokens": 198077.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.382922554016114,
|
|
"epoch": 0.009071117561683599,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.8487,
|
|
"mean_token_accuracy": 0.04283392727375031,
|
|
"num_tokens": 208641.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.327754020690918,
|
|
"epoch": 0.009524673439767779,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.6499,
|
|
"mean_token_accuracy": 0.0530441515147686,
|
|
"num_tokens": 218398.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.238056182861328,
|
|
"epoch": 0.00997822931785196,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.501,
|
|
"mean_token_accuracy": 0.05147750936448574,
|
|
"num_tokens": 229059.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.118829822540283,
|
|
"epoch": 0.01043178519593614,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.4107,
|
|
"mean_token_accuracy": 0.05338236689567566,
|
|
"num_tokens": 239775.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.956042957305907,
|
|
"epoch": 0.01088534107402032,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.2389,
|
|
"mean_token_accuracy": 0.053830433264374734,
|
|
"num_tokens": 249954.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.754269218444824,
|
|
"epoch": 0.011338896952104499,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.1364,
|
|
"mean_token_accuracy": 0.05633715465664864,
|
|
"num_tokens": 260056.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.600945854187012,
|
|
"epoch": 0.01179245283018868,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.0344,
|
|
"mean_token_accuracy": 0.05928211845457554,
|
|
"num_tokens": 269904.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.370787525177002,
|
|
"epoch": 0.01224600870827286,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.9224,
|
|
"mean_token_accuracy": 0.05375306829810143,
|
|
"num_tokens": 280900.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.10864839553833,
|
|
"epoch": 0.01269956458635704,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.8234,
|
|
"mean_token_accuracy": 0.055295905098319054,
|
|
"num_tokens": 290844.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.816210174560547,
|
|
"epoch": 0.013153120464441219,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.7326,
|
|
"mean_token_accuracy": 0.062234926223754886,
|
|
"num_tokens": 301345.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.610615539550782,
|
|
"epoch": 0.013606676342525399,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.6332,
|
|
"mean_token_accuracy": 0.06342925988137722,
|
|
"num_tokens": 312681.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.336861324310302,
|
|
"epoch": 0.01406023222060958,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.5646,
|
|
"mean_token_accuracy": 0.06853245571255684,
|
|
"num_tokens": 323492.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.240836334228515,
|
|
"epoch": 0.01451378809869376,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.564,
|
|
"mean_token_accuracy": 0.06723525486886502,
|
|
"num_tokens": 334521.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.05573558807373,
|
|
"epoch": 0.014967343976777939,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.5656,
|
|
"mean_token_accuracy": 0.07214355692267418,
|
|
"num_tokens": 345468.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.033101844787598,
|
|
"epoch": 0.015420899854862119,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.4802,
|
|
"mean_token_accuracy": 0.07146222665905952,
|
|
"num_tokens": 355911.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.941764783859253,
|
|
"epoch": 0.0158744557329463,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.505,
|
|
"mean_token_accuracy": 0.07519448474049568,
|
|
"num_tokens": 367537.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.970178508758545,
|
|
"epoch": 0.01632801161103048,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.6193,
|
|
"mean_token_accuracy": 0.07340684309601783,
|
|
"num_tokens": 377918.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.922939395904541,
|
|
"epoch": 0.01678156748911466,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.4722,
|
|
"mean_token_accuracy": 0.07753909192979336,
|
|
"num_tokens": 388461.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.8546586513519285,
|
|
"epoch": 0.01723512336719884,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.4354,
|
|
"mean_token_accuracy": 0.08010556474328041,
|
|
"num_tokens": 399771.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.820327281951904,
|
|
"epoch": 0.01768867924528302,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.3185,
|
|
"mean_token_accuracy": 0.07953049913048744,
|
|
"num_tokens": 410254.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.83513126373291,
|
|
"epoch": 0.018142235123367198,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.3297,
|
|
"mean_token_accuracy": 0.07624107114970684,
|
|
"num_tokens": 419792.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.7827085018157955,
|
|
"epoch": 0.018595791001451378,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.3324,
|
|
"mean_token_accuracy": 0.08292475119233131,
|
|
"num_tokens": 429264.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.716277408599853,
|
|
"epoch": 0.019049346879535557,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.2853,
|
|
"mean_token_accuracy": 0.08389051035046577,
|
|
"num_tokens": 439624.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.717530107498169,
|
|
"epoch": 0.01950290275761974,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.267,
|
|
"mean_token_accuracy": 0.0840241178870201,
|
|
"num_tokens": 449556.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.703034257888794,
|
|
"epoch": 0.01995645863570392,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.2846,
|
|
"mean_token_accuracy": 0.08519925326108932,
|
|
"num_tokens": 460243.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.728843021392822,
|
|
"epoch": 0.0204100145137881,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.3326,
|
|
"mean_token_accuracy": 0.0805255938321352,
|
|
"num_tokens": 469767.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.720327663421631,
|
|
"epoch": 0.02086357039187228,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.2493,
|
|
"mean_token_accuracy": 0.08286545500159263,
|
|
"num_tokens": 480329.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.666221618652344,
|
|
"epoch": 0.02131712626995646,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.214,
|
|
"mean_token_accuracy": 0.07896244674921035,
|
|
"num_tokens": 490096.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.731700372695923,
|
|
"epoch": 0.02177068214804064,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.2592,
|
|
"mean_token_accuracy": 0.07835591658949852,
|
|
"num_tokens": 501231.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.684773302078247,
|
|
"epoch": 0.022224238026124818,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.1609,
|
|
"mean_token_accuracy": 0.08823157548904419,
|
|
"num_tokens": 510722.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.513065958023072,
|
|
"epoch": 0.022677793904208998,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.2055,
|
|
"mean_token_accuracy": 0.08414689600467681,
|
|
"num_tokens": 521452.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.660957479476929,
|
|
"epoch": 0.023131349782293177,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.211,
|
|
"mean_token_accuracy": 0.08599318936467171,
|
|
"num_tokens": 532397.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.555563879013062,
|
|
"epoch": 0.02358490566037736,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1818,
|
|
"mean_token_accuracy": 0.08441983088850975,
|
|
"num_tokens": 542271.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.615720558166504,
|
|
"epoch": 0.02403846153846154,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.1579,
|
|
"mean_token_accuracy": 0.09066328033804893,
|
|
"num_tokens": 552411.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.520418405532837,
|
|
"epoch": 0.02449201741654572,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.1502,
|
|
"mean_token_accuracy": 0.08552343845367431,
|
|
"num_tokens": 561518.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.588455486297607,
|
|
"epoch": 0.0249455732946299,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.1831,
|
|
"mean_token_accuracy": 0.08754325062036514,
|
|
"num_tokens": 571361.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.492841577529907,
|
|
"epoch": 0.02539912917271408,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.0901,
|
|
"mean_token_accuracy": 0.09500023052096367,
|
|
"num_tokens": 580926.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.54066162109375,
|
|
"epoch": 0.025852685050798258,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.1773,
|
|
"mean_token_accuracy": 0.08410000652074814,
|
|
"num_tokens": 592282.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.580021572113037,
|
|
"epoch": 0.026306240928882438,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.1784,
|
|
"mean_token_accuracy": 0.08815034925937652,
|
|
"num_tokens": 602767.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.532192230224609,
|
|
"epoch": 0.026759796806966617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.0936,
|
|
"mean_token_accuracy": 0.08808856308460236,
|
|
"num_tokens": 612763.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.443887853622437,
|
|
"epoch": 0.027213352685050797,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0434,
|
|
"mean_token_accuracy": 0.09205911681056023,
|
|
"num_tokens": 622796.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.466957712173462,
|
|
"epoch": 0.027666908563134977,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.0302,
|
|
"mean_token_accuracy": 0.09625576436519623,
|
|
"num_tokens": 633136.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.39753270149231,
|
|
"epoch": 0.02812046444121916,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0236,
|
|
"mean_token_accuracy": 0.09388496801257133,
|
|
"num_tokens": 643347.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.445803928375244,
|
|
"epoch": 0.02857402031930334,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.0109,
|
|
"mean_token_accuracy": 0.09590190947055817,
|
|
"num_tokens": 653096.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.36529951095581,
|
|
"epoch": 0.02902757619738752,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.04,
|
|
"mean_token_accuracy": 0.09056715369224548,
|
|
"num_tokens": 663557.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.485755491256714,
|
|
"epoch": 0.0294811320754717,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.1043,
|
|
"mean_token_accuracy": 0.09179518148303031,
|
|
"num_tokens": 674395.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.3991217613220215,
|
|
"epoch": 0.029934687953555878,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.0039,
|
|
"mean_token_accuracy": 0.0983194276690483,
|
|
"num_tokens": 684776.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.310597705841064,
|
|
"epoch": 0.030388243831640058,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.9818,
|
|
"mean_token_accuracy": 0.09324271008372306,
|
|
"num_tokens": 694886.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.388318014144898,
|
|
"epoch": 0.030841799709724237,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.0598,
|
|
"mean_token_accuracy": 0.09387328922748565,
|
|
"num_tokens": 705426.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.296148014068604,
|
|
"epoch": 0.03129535558780842,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.0644,
|
|
"mean_token_accuracy": 0.09106143489480019,
|
|
"num_tokens": 716271.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.398095321655274,
|
|
"epoch": 0.0317489114658926,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.0437,
|
|
"mean_token_accuracy": 0.09280406758189201,
|
|
"num_tokens": 726875.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.330491304397583,
|
|
"epoch": 0.032202467343976776,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.9817,
|
|
"mean_token_accuracy": 0.09162108749151229,
|
|
"num_tokens": 737825.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.354272747039795,
|
|
"epoch": 0.03265602322206096,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.9502,
|
|
"mean_token_accuracy": 0.09616798982024193,
|
|
"num_tokens": 747424.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.289549160003662,
|
|
"epoch": 0.033109579100145135,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.9635,
|
|
"mean_token_accuracy": 0.09623874425888061,
|
|
"num_tokens": 757649.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.327360343933106,
|
|
"epoch": 0.03356313497822932,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.947,
|
|
"mean_token_accuracy": 0.09573540687561036,
|
|
"num_tokens": 768556.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.2021252632141115,
|
|
"epoch": 0.034016690856313495,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.9449,
|
|
"mean_token_accuracy": 0.0929239995777607,
|
|
"num_tokens": 778331.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.242694997787476,
|
|
"epoch": 0.03447024673439768,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.9322,
|
|
"mean_token_accuracy": 0.09555335119366645,
|
|
"num_tokens": 788065.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.3150105476379395,
|
|
"epoch": 0.03492380261248186,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.9711,
|
|
"mean_token_accuracy": 0.09826483204960823,
|
|
"num_tokens": 798912.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.2783135890960695,
|
|
"epoch": 0.03537735849056604,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.9073,
|
|
"mean_token_accuracy": 0.10042868107557297,
|
|
"num_tokens": 809580.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.212211751937867,
|
|
"epoch": 0.03583091436865022,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.996,
|
|
"mean_token_accuracy": 0.09339204281568528,
|
|
"num_tokens": 820207.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.088284826278686,
|
|
"epoch": 0.036284470246734396,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.826,
|
|
"mean_token_accuracy": 0.09160310104489326,
|
|
"num_tokens": 831038.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.272746944427491,
|
|
"epoch": 0.03673802612481858,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.9068,
|
|
"mean_token_accuracy": 0.09824135601520538,
|
|
"num_tokens": 842144.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.274405145645142,
|
|
"epoch": 0.037191582002902755,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.9044,
|
|
"mean_token_accuracy": 0.10123971402645111,
|
|
"num_tokens": 851315.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.09048376083374,
|
|
"epoch": 0.03764513788098694,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.921,
|
|
"mean_token_accuracy": 0.09870171621441841,
|
|
"num_tokens": 861233.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.206084251403809,
|
|
"epoch": 0.038098693759071114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.9004,
|
|
"mean_token_accuracy": 0.09542403146624565,
|
|
"num_tokens": 871131.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.1921416282653805,
|
|
"epoch": 0.0385522496371553,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.8717,
|
|
"mean_token_accuracy": 0.09407154396176338,
|
|
"num_tokens": 882195.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.185799217224121,
|
|
"epoch": 0.03900580551523948,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8489,
|
|
"mean_token_accuracy": 0.10136798098683357,
|
|
"num_tokens": 891806.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.238110542297363,
|
|
"epoch": 0.03945936139332366,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.9054,
|
|
"mean_token_accuracy": 0.09595799744129181,
|
|
"num_tokens": 901350.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.158117580413818,
|
|
"epoch": 0.03991291727140784,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.8187,
|
|
"mean_token_accuracy": 0.09831003770232201,
|
|
"num_tokens": 912061.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.09474549293518,
|
|
"epoch": 0.040366473149492016,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7766,
|
|
"mean_token_accuracy": 0.1011108048260212,
|
|
"num_tokens": 922220.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.1174585819244385,
|
|
"epoch": 0.0408200290275762,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8018,
|
|
"mean_token_accuracy": 0.10038985908031464,
|
|
"num_tokens": 932319.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.0610755443572994,
|
|
"epoch": 0.041273584905660375,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.8413,
|
|
"mean_token_accuracy": 0.09963766038417816,
|
|
"num_tokens": 943254.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.112555265426636,
|
|
"epoch": 0.04172714078374456,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.8619,
|
|
"mean_token_accuracy": 0.0950029470026493,
|
|
"num_tokens": 953921.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.016997766494751,
|
|
"epoch": 0.042180696661828734,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.7679,
|
|
"mean_token_accuracy": 0.10482859760522842,
|
|
"num_tokens": 963832.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.03766975402832,
|
|
"epoch": 0.04263425253991292,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.866,
|
|
"mean_token_accuracy": 0.09811323508620262,
|
|
"num_tokens": 974066.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.129855823516846,
|
|
"epoch": 0.0430878084179971,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.8551,
|
|
"mean_token_accuracy": 0.10151214599609375,
|
|
"num_tokens": 984402.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.089972972869873,
|
|
"epoch": 0.04354136429608128,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.7652,
|
|
"mean_token_accuracy": 0.09788535833358765,
|
|
"num_tokens": 993555.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.085727262496948,
|
|
"epoch": 0.04399492017416546,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7472,
|
|
"mean_token_accuracy": 0.10479735285043716,
|
|
"num_tokens": 1002920.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.040792322158813,
|
|
"epoch": 0.044448476052249636,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.8392,
|
|
"mean_token_accuracy": 0.09684377312660217,
|
|
"num_tokens": 1013611.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.981588220596313,
|
|
"epoch": 0.04490203193033382,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.7247,
|
|
"mean_token_accuracy": 0.09907414987683297,
|
|
"num_tokens": 1024121.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.122877836227417,
|
|
"epoch": 0.045355587808417995,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.9627,
|
|
"mean_token_accuracy": 0.10345524102449417,
|
|
"num_tokens": 1033845.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.049224853515625,
|
|
"epoch": 0.04580914368650218,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7454,
|
|
"mean_token_accuracy": 0.10035812482237816,
|
|
"num_tokens": 1044642.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.04058837890625,
|
|
"epoch": 0.046262699564586354,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.8115,
|
|
"mean_token_accuracy": 0.1038434311747551,
|
|
"num_tokens": 1054728.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.993410062789917,
|
|
"epoch": 0.04671625544267054,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.7643,
|
|
"mean_token_accuracy": 0.09849002212285995,
|
|
"num_tokens": 1065743.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.9517449855804445,
|
|
"epoch": 0.04716981132075472,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.686,
|
|
"mean_token_accuracy": 0.10116103440523147,
|
|
"num_tokens": 1076798.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.008026170730591,
|
|
"epoch": 0.047623367198838897,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.8212,
|
|
"mean_token_accuracy": 0.10135331153869628,
|
|
"num_tokens": 1087445.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.9268933773040775,
|
|
"epoch": 0.04807692307692308,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7326,
|
|
"mean_token_accuracy": 0.10336857363581657,
|
|
"num_tokens": 1098379.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.028698968887329,
|
|
"epoch": 0.048530478955007256,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.809,
|
|
"mean_token_accuracy": 0.10176651552319527,
|
|
"num_tokens": 1108016.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.998309707641601,
|
|
"epoch": 0.04898403483309144,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7018,
|
|
"mean_token_accuracy": 0.10114236250519752,
|
|
"num_tokens": 1117887.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.907250595092774,
|
|
"epoch": 0.049437590711175615,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6942,
|
|
"mean_token_accuracy": 0.09997687637805938,
|
|
"num_tokens": 1128497.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.936363220214844,
|
|
"epoch": 0.0498911465892598,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7284,
|
|
"mean_token_accuracy": 0.10731528326869011,
|
|
"num_tokens": 1138168.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.892492866516113,
|
|
"epoch": 0.050344702467343974,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6977,
|
|
"mean_token_accuracy": 0.10209395885467529,
|
|
"num_tokens": 1148357.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.959150648117065,
|
|
"epoch": 0.05079825834542816,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.719,
|
|
"mean_token_accuracy": 0.10157941356301307,
|
|
"num_tokens": 1159964.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.994518995285034,
|
|
"epoch": 0.05125181422351233,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.7767,
|
|
"mean_token_accuracy": 0.10542606040835381,
|
|
"num_tokens": 1170683.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.960160112380981,
|
|
"epoch": 0.051705370101596516,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7378,
|
|
"mean_token_accuracy": 0.09894839897751809,
|
|
"num_tokens": 1181680.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.797056579589844,
|
|
"epoch": 0.0521589259796807,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6327,
|
|
"mean_token_accuracy": 0.10385172069072723,
|
|
"num_tokens": 1191619.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.813391923904419,
|
|
"epoch": 0.052612481857764876,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.6332,
|
|
"mean_token_accuracy": 0.103890310972929,
|
|
"num_tokens": 1202264.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.810958385467529,
|
|
"epoch": 0.05306603773584906,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6287,
|
|
"mean_token_accuracy": 0.104695063829422,
|
|
"num_tokens": 1212119.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.923195457458496,
|
|
"epoch": 0.053519593613933235,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.764,
|
|
"mean_token_accuracy": 0.10014403387904167,
|
|
"num_tokens": 1222317.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.910294437408448,
|
|
"epoch": 0.05397314949201742,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.703,
|
|
"mean_token_accuracy": 0.10804183036088943,
|
|
"num_tokens": 1232914.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.811793613433838,
|
|
"epoch": 0.054426705370101594,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.5542,
|
|
"mean_token_accuracy": 0.11040094196796417,
|
|
"num_tokens": 1244214.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.8492508888244625,
|
|
"epoch": 0.05488026124818578,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6376,
|
|
"mean_token_accuracy": 0.10812766700983048,
|
|
"num_tokens": 1254626.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.818840599060058,
|
|
"epoch": 0.05533381712626995,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.7416,
|
|
"mean_token_accuracy": 0.10723426789045334,
|
|
"num_tokens": 1265461.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.867012405395508,
|
|
"epoch": 0.055787373004354136,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6166,
|
|
"mean_token_accuracy": 0.10740614756941795,
|
|
"num_tokens": 1275810.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.771302795410156,
|
|
"epoch": 0.05624092888243832,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.63,
|
|
"mean_token_accuracy": 0.11132507100701332,
|
|
"num_tokens": 1285170.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.833296775817871,
|
|
"epoch": 0.056694484760522496,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5804,
|
|
"mean_token_accuracy": 0.10996494144201278,
|
|
"num_tokens": 1295460.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.802701473236084,
|
|
"epoch": 0.05714804063860668,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.7121,
|
|
"mean_token_accuracy": 0.10138657614588738,
|
|
"num_tokens": 1306656.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.8321558952331545,
|
|
"epoch": 0.057601596516690855,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.6778,
|
|
"mean_token_accuracy": 0.10745546817779542,
|
|
"num_tokens": 1318019.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.660759735107422,
|
|
"epoch": 0.05805515239477504,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.6174,
|
|
"mean_token_accuracy": 0.1097694255411625,
|
|
"num_tokens": 1328120.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.918548679351806,
|
|
"epoch": 0.058508708272859214,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.6987,
|
|
"mean_token_accuracy": 0.10450451076030731,
|
|
"num_tokens": 1338354.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.80439510345459,
|
|
"epoch": 0.0589622641509434,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6586,
|
|
"mean_token_accuracy": 0.10693488866090775,
|
|
"num_tokens": 1348666.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.861764764785766,
|
|
"epoch": 0.05941582002902757,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.705,
|
|
"mean_token_accuracy": 0.10773044675588608,
|
|
"num_tokens": 1359713.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.759540653228759,
|
|
"epoch": 0.059869375907111756,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5522,
|
|
"mean_token_accuracy": 0.110796270519495,
|
|
"num_tokens": 1369507.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.832991409301758,
|
|
"epoch": 0.06032293178519594,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.715,
|
|
"mean_token_accuracy": 0.10180763974785804,
|
|
"num_tokens": 1380726.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.828793239593506,
|
|
"epoch": 0.060776487663280115,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.642,
|
|
"mean_token_accuracy": 0.11072484701871872,
|
|
"num_tokens": 1391423.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.827483797073365,
|
|
"epoch": 0.0612300435413643,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.6225,
|
|
"mean_token_accuracy": 0.1150636076927185,
|
|
"num_tokens": 1402492.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.715798854827881,
|
|
"epoch": 0.061683599419448475,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6714,
|
|
"mean_token_accuracy": 0.11112096533179283,
|
|
"num_tokens": 1412497.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.875859308242798,
|
|
"epoch": 0.06213715529753266,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.6295,
|
|
"mean_token_accuracy": 0.11218903288245201,
|
|
"num_tokens": 1423214.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.707458257675171,
|
|
"epoch": 0.06259071117561683,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6269,
|
|
"mean_token_accuracy": 0.10577443093061448,
|
|
"num_tokens": 1434044.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.722873497009277,
|
|
"epoch": 0.06304426705370102,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5825,
|
|
"mean_token_accuracy": 0.10959424301981927,
|
|
"num_tokens": 1444387.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.695552062988281,
|
|
"epoch": 0.0634978229317852,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5396,
|
|
"mean_token_accuracy": 0.10780341550707817,
|
|
"num_tokens": 1455157.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.774385118484497,
|
|
"epoch": 0.06395137880986937,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.6271,
|
|
"mean_token_accuracy": 0.11427033320069313,
|
|
"num_tokens": 1466145.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.722665452957154,
|
|
"epoch": 0.06440493468795355,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.6276,
|
|
"mean_token_accuracy": 0.111500333994627,
|
|
"num_tokens": 1476713.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.750820589065552,
|
|
"epoch": 0.06485849056603774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.6316,
|
|
"mean_token_accuracy": 0.11196371614933014,
|
|
"num_tokens": 1486908.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.727015495300293,
|
|
"epoch": 0.06531204644412192,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5495,
|
|
"mean_token_accuracy": 0.11699655205011368,
|
|
"num_tokens": 1498185.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.688741731643677,
|
|
"epoch": 0.0657656023222061,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5868,
|
|
"mean_token_accuracy": 0.11200948804616928,
|
|
"num_tokens": 1508376.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.779923057556152,
|
|
"epoch": 0.06621915820029027,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.6764,
|
|
"mean_token_accuracy": 0.10785475298762322,
|
|
"num_tokens": 1519953.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.637065696716308,
|
|
"epoch": 0.06667271407837445,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.5419,
|
|
"mean_token_accuracy": 0.11318475008010864,
|
|
"num_tokens": 1529793.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.70322322845459,
|
|
"epoch": 0.06712626995645864,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5429,
|
|
"mean_token_accuracy": 0.11152931004762649,
|
|
"num_tokens": 1540859.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.675182676315307,
|
|
"epoch": 0.06757982583454282,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.4683,
|
|
"mean_token_accuracy": 0.11367111355066299,
|
|
"num_tokens": 1549783.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.616857862472534,
|
|
"epoch": 0.06803338171262699,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5441,
|
|
"mean_token_accuracy": 0.10823952555656433,
|
|
"num_tokens": 1560522.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.6370926856994625,
|
|
"epoch": 0.06848693759071117,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5206,
|
|
"mean_token_accuracy": 0.11319050565361977,
|
|
"num_tokens": 1570668.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.6942650318145756,
|
|
"epoch": 0.06894049346879536,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.6439,
|
|
"mean_token_accuracy": 0.11470866054296494,
|
|
"num_tokens": 1581523.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.626244068145752,
|
|
"epoch": 0.06939404934687954,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5478,
|
|
"mean_token_accuracy": 0.10985084623098373,
|
|
"num_tokens": 1591356.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.59173264503479,
|
|
"epoch": 0.06984760522496372,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5349,
|
|
"mean_token_accuracy": 0.11471892967820167,
|
|
"num_tokens": 1601779.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.733083581924438,
|
|
"epoch": 0.07030116110304789,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5258,
|
|
"mean_token_accuracy": 0.11292637586593628,
|
|
"num_tokens": 1611995.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.631600999832154,
|
|
"epoch": 0.07075471698113207,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5418,
|
|
"mean_token_accuracy": 0.11008346080780029,
|
|
"num_tokens": 1621834.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.629804039001465,
|
|
"epoch": 0.07120827285921626,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.596,
|
|
"mean_token_accuracy": 0.10650180131196976,
|
|
"num_tokens": 1632881.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.621839952468872,
|
|
"epoch": 0.07166182873730044,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5746,
|
|
"mean_token_accuracy": 0.11100505664944649,
|
|
"num_tokens": 1642870.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.605715703964234,
|
|
"epoch": 0.07211538461538461,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.441,
|
|
"mean_token_accuracy": 0.12122759222984314,
|
|
"num_tokens": 1653390.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.608106994628907,
|
|
"epoch": 0.07256894049346879,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.5597,
|
|
"mean_token_accuracy": 0.11547763496637345,
|
|
"num_tokens": 1663382.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.710092163085937,
|
|
"epoch": 0.07302249637155298,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.5794,
|
|
"mean_token_accuracy": 0.11190545409917832,
|
|
"num_tokens": 1673601.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.551822805404663,
|
|
"epoch": 0.07347605224963716,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4868,
|
|
"mean_token_accuracy": 0.11824472174048424,
|
|
"num_tokens": 1683565.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.574606466293335,
|
|
"epoch": 0.07392960812772134,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.4743,
|
|
"mean_token_accuracy": 0.11708612516522407,
|
|
"num_tokens": 1693636.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.7191204071044925,
|
|
"epoch": 0.07438316400580551,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5787,
|
|
"mean_token_accuracy": 0.1106836386024952,
|
|
"num_tokens": 1703415.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.614391088485718,
|
|
"epoch": 0.0748367198838897,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.547,
|
|
"mean_token_accuracy": 0.11781998202204705,
|
|
"num_tokens": 1713579.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.650404357910157,
|
|
"epoch": 0.07529027576197388,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.5694,
|
|
"mean_token_accuracy": 0.11126149147748947,
|
|
"num_tokens": 1724583.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.56261305809021,
|
|
"epoch": 0.07574383164005806,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.4685,
|
|
"mean_token_accuracy": 0.11994619444012641,
|
|
"num_tokens": 1735293.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.594982242584228,
|
|
"epoch": 0.07619738751814223,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.5008,
|
|
"mean_token_accuracy": 0.11226540133357048,
|
|
"num_tokens": 1745623.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.603390169143677,
|
|
"epoch": 0.07665094339622641,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.52,
|
|
"mean_token_accuracy": 0.11589490175247193,
|
|
"num_tokens": 1755713.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.6110374450683596,
|
|
"epoch": 0.0771044992743106,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.5272,
|
|
"mean_token_accuracy": 0.11683018952608108,
|
|
"num_tokens": 1765264.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.545265436172485,
|
|
"epoch": 0.07755805515239478,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.5236,
|
|
"mean_token_accuracy": 0.11411887183785438,
|
|
"num_tokens": 1775769.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.497287750244141,
|
|
"epoch": 0.07801161103047896,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4583,
|
|
"mean_token_accuracy": 0.11649047806859017,
|
|
"num_tokens": 1786245.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.541773176193237,
|
|
"epoch": 0.07846516690856313,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4934,
|
|
"mean_token_accuracy": 0.1203076533973217,
|
|
"num_tokens": 1796040.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.557205772399902,
|
|
"epoch": 0.07891872278664731,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.5032,
|
|
"mean_token_accuracy": 0.11635191962122918,
|
|
"num_tokens": 1806007.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.6393091678619385,
|
|
"epoch": 0.0793722786647315,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5811,
|
|
"mean_token_accuracy": 0.10934827327728272,
|
|
"num_tokens": 1816935.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.550049209594727,
|
|
"epoch": 0.07982583454281568,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.4333,
|
|
"mean_token_accuracy": 0.1151725821197033,
|
|
"num_tokens": 1827419.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.5682214260101315,
|
|
"epoch": 0.08027939042089985,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.5467,
|
|
"mean_token_accuracy": 0.11440723314881325,
|
|
"num_tokens": 1837933.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.561804389953613,
|
|
"epoch": 0.08073294629898403,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.5946,
|
|
"mean_token_accuracy": 0.11757715567946433,
|
|
"num_tokens": 1848551.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.58006534576416,
|
|
"epoch": 0.08118650217706821,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4703,
|
|
"mean_token_accuracy": 0.11650048196315765,
|
|
"num_tokens": 1858380.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.507673358917236,
|
|
"epoch": 0.0816400580551524,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3925,
|
|
"mean_token_accuracy": 0.12206198945641518,
|
|
"num_tokens": 1868291.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.512743759155273,
|
|
"epoch": 0.08209361393323658,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4936,
|
|
"mean_token_accuracy": 0.11916299089789391,
|
|
"num_tokens": 1879219.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.576422262191772,
|
|
"epoch": 0.08254716981132075,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4837,
|
|
"mean_token_accuracy": 0.11856920123100281,
|
|
"num_tokens": 1889809.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.512048292160034,
|
|
"epoch": 0.08300072568940493,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.4555,
|
|
"mean_token_accuracy": 0.11503883451223373,
|
|
"num_tokens": 1899986.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.468104887008667,
|
|
"epoch": 0.08345428156748912,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4304,
|
|
"mean_token_accuracy": 0.1187589332461357,
|
|
"num_tokens": 1909314.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.530900621414185,
|
|
"epoch": 0.0839078374455733,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.4927,
|
|
"mean_token_accuracy": 0.11667392775416374,
|
|
"num_tokens": 1918443.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.4985747814178465,
|
|
"epoch": 0.08436139332365747,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4426,
|
|
"mean_token_accuracy": 0.12001407295465469,
|
|
"num_tokens": 1928683.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.341750717163086,
|
|
"epoch": 0.08481494920174165,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.3506,
|
|
"mean_token_accuracy": 0.11788592040538788,
|
|
"num_tokens": 1938293.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.479642105102539,
|
|
"epoch": 0.08526850507982583,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4465,
|
|
"mean_token_accuracy": 0.11793545484542847,
|
|
"num_tokens": 1948233.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.530252504348755,
|
|
"epoch": 0.08572206095791002,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3522,
|
|
"mean_token_accuracy": 0.12431273758411407,
|
|
"num_tokens": 1958611.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.493687391281128,
|
|
"epoch": 0.0861756168359942,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.5117,
|
|
"mean_token_accuracy": 0.12384502068161965,
|
|
"num_tokens": 1968957.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.461392259597778,
|
|
"epoch": 0.08662917271407837,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.3574,
|
|
"mean_token_accuracy": 0.12506917640566825,
|
|
"num_tokens": 1978503.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.35320930480957,
|
|
"epoch": 0.08708272859216255,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3587,
|
|
"mean_token_accuracy": 0.12145144119858742,
|
|
"num_tokens": 1988458.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.526880693435669,
|
|
"epoch": 0.08753628447024674,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.4944,
|
|
"mean_token_accuracy": 0.11722690165042877,
|
|
"num_tokens": 1999984.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.340011119842529,
|
|
"epoch": 0.08798984034833092,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3565,
|
|
"mean_token_accuracy": 0.12677358314394951,
|
|
"num_tokens": 2010645.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.513621473312378,
|
|
"epoch": 0.08844339622641509,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.4595,
|
|
"mean_token_accuracy": 0.1156634084880352,
|
|
"num_tokens": 2020196.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.416438961029053,
|
|
"epoch": 0.08889695210449927,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3612,
|
|
"mean_token_accuracy": 0.11996159106492996,
|
|
"num_tokens": 2030101.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.428423595428467,
|
|
"epoch": 0.08935050798258345,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.4427,
|
|
"mean_token_accuracy": 0.12014320492744446,
|
|
"num_tokens": 2040454.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.405238437652588,
|
|
"epoch": 0.08980406386066764,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.3829,
|
|
"mean_token_accuracy": 0.1194852776825428,
|
|
"num_tokens": 2050378.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.48555850982666,
|
|
"epoch": 0.09025761973875182,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.4375,
|
|
"mean_token_accuracy": 0.1193937435746193,
|
|
"num_tokens": 2060282.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.425385618209839,
|
|
"epoch": 0.09071117561683599,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.4225,
|
|
"mean_token_accuracy": 0.1208973728120327,
|
|
"num_tokens": 2070563.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.519330835342407,
|
|
"epoch": 0.09116473149492017,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999999985110217,
|
|
"loss": 6.4932,
|
|
"mean_token_accuracy": 0.1223867803812027,
|
|
"num_tokens": 2080153.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.329967784881592,
|
|
"epoch": 0.09161828737300436,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999999924620471,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.12452480345964431,
|
|
"num_tokens": 2090590.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.515519332885742,
|
|
"epoch": 0.09207184325108854,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999999817600155,
|
|
"loss": 6.417,
|
|
"mean_token_accuracy": 0.11619279980659485,
|
|
"num_tokens": 2101945.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.467217254638672,
|
|
"epoch": 0.09252539912917271,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999999664049268,
|
|
"loss": 6.4102,
|
|
"mean_token_accuracy": 0.12234249636530876,
|
|
"num_tokens": 2112514.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.314993619918823,
|
|
"epoch": 0.09297895500725689,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999999463967816,
|
|
"loss": 6.3675,
|
|
"mean_token_accuracy": 0.12220757827162743,
|
|
"num_tokens": 2122296.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.554604530334473,
|
|
"epoch": 0.09343251088534107,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049999992173558,
|
|
"loss": 6.5145,
|
|
"mean_token_accuracy": 0.10880634039640427,
|
|
"num_tokens": 2134512.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.392258501052856,
|
|
"epoch": 0.09388606676342526,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999998924213228,
|
|
"loss": 6.4275,
|
|
"mean_token_accuracy": 0.12143760100007057,
|
|
"num_tokens": 2143934.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.342760133743286,
|
|
"epoch": 0.09433962264150944,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999998584540105,
|
|
"loss": 6.3158,
|
|
"mean_token_accuracy": 0.11730768010020257,
|
|
"num_tokens": 2155730.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.444509124755859,
|
|
"epoch": 0.09479317851959361,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999998198336437,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.11236922815442085,
|
|
"num_tokens": 2166422.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.4285173416137695,
|
|
"epoch": 0.09524673439767779,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999997765602233,
|
|
"loss": 6.4565,
|
|
"mean_token_accuracy": 0.11630769446492195,
|
|
"num_tokens": 2177842.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.47231822013855,
|
|
"epoch": 0.09570029027576198,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999997286337502,
|
|
"loss": 6.5277,
|
|
"mean_token_accuracy": 0.11602402850985527,
|
|
"num_tokens": 2188614.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.416055536270141,
|
|
"epoch": 0.09615384615384616,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999996760542254,
|
|
"loss": 6.3069,
|
|
"mean_token_accuracy": 0.12384679168462753,
|
|
"num_tokens": 2197886.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.2871458530426025,
|
|
"epoch": 0.09660740203193033,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049999961882165,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.12341554090380669,
|
|
"num_tokens": 2209930.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.457307767868042,
|
|
"epoch": 0.09706095791001451,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999995569360251,
|
|
"loss": 6.39,
|
|
"mean_token_accuracy": 0.11931687965989113,
|
|
"num_tokens": 2219767.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.368694543838501,
|
|
"epoch": 0.0975145137880987,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499999490397352,
|
|
"loss": 6.3183,
|
|
"mean_token_accuracy": 0.12491154968738556,
|
|
"num_tokens": 2230082.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.255974912643433,
|
|
"epoch": 0.09796806966618288,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999994192056321,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.1294071279466152,
|
|
"num_tokens": 2240066.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.41351056098938,
|
|
"epoch": 0.09842162554426705,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993433608669,
|
|
"loss": 6.3732,
|
|
"mean_token_accuracy": 0.121247049421072,
|
|
"num_tokens": 2250732.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.363176012039185,
|
|
"epoch": 0.09887518142235123,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999992628630579,
|
|
"loss": 6.2529,
|
|
"mean_token_accuracy": 0.12264698669314385,
|
|
"num_tokens": 2261452.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.3054649353027346,
|
|
"epoch": 0.09932873730043541,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999991777122069,
|
|
"loss": 6.3573,
|
|
"mean_token_accuracy": 0.12316267415881157,
|
|
"num_tokens": 2271929.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.356408214569091,
|
|
"epoch": 0.0997822931785196,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999990879083156,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.12437993809580802,
|
|
"num_tokens": 2282987.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.351103973388672,
|
|
"epoch": 0.10023584905660378,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999989934513857,
|
|
"loss": 6.3068,
|
|
"mean_token_accuracy": 0.13111748546361923,
|
|
"num_tokens": 2292796.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.383915185928345,
|
|
"epoch": 0.10068940493468795,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999988943414193,
|
|
"loss": 6.3617,
|
|
"mean_token_accuracy": 0.12342413067817688,
|
|
"num_tokens": 2303057.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.292774343490601,
|
|
"epoch": 0.10114296081277213,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999987905784184,
|
|
"loss": 6.3395,
|
|
"mean_token_accuracy": 0.12345447167754173,
|
|
"num_tokens": 2314168.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.347012901306153,
|
|
"epoch": 0.10159651669085631,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999986821623853,
|
|
"loss": 6.3135,
|
|
"mean_token_accuracy": 0.12161569744348526,
|
|
"num_tokens": 2325241.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.389744472503662,
|
|
"epoch": 0.1020500725689405,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999985690933219,
|
|
"loss": 6.3344,
|
|
"mean_token_accuracy": 0.12111192867159844,
|
|
"num_tokens": 2334866.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.2507038593292235,
|
|
"epoch": 0.10250362844702467,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999984513712311,
|
|
"loss": 6.3401,
|
|
"mean_token_accuracy": 0.11989274248480797,
|
|
"num_tokens": 2345422.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.4327864170074465,
|
|
"epoch": 0.10295718432510885,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999983289961146,
|
|
"loss": 6.3632,
|
|
"mean_token_accuracy": 0.12089978456497193,
|
|
"num_tokens": 2356285.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.264034223556519,
|
|
"epoch": 0.10341074020319303,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999982019679755,
|
|
"loss": 6.2759,
|
|
"mean_token_accuracy": 0.12783560231328012,
|
|
"num_tokens": 2366861.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.348967456817627,
|
|
"epoch": 0.10386429608127722,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999980702868164,
|
|
"loss": 6.3095,
|
|
"mean_token_accuracy": 0.13093309253454208,
|
|
"num_tokens": 2376851.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.375752353668213,
|
|
"epoch": 0.1043178519593614,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999979339526396,
|
|
"loss": 6.3741,
|
|
"mean_token_accuracy": 0.12913595587015153,
|
|
"num_tokens": 2386857.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.366842555999756,
|
|
"epoch": 0.10477140783744557,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999977929654484,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.12512771040201187,
|
|
"num_tokens": 2397035.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.386923742294312,
|
|
"epoch": 0.10522496371552975,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999976473252453,
|
|
"loss": 6.3748,
|
|
"mean_token_accuracy": 0.12434866130352021,
|
|
"num_tokens": 2408177.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.419609022140503,
|
|
"epoch": 0.10567851959361393,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999974970320338,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.12743960320949554,
|
|
"num_tokens": 2418445.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.237172079086304,
|
|
"epoch": 0.10613207547169812,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999973420858165,
|
|
"loss": 6.3161,
|
|
"mean_token_accuracy": 0.1236274503171444,
|
|
"num_tokens": 2428990.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.369281435012818,
|
|
"epoch": 0.10658563134978229,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999971824865968,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.12022999972105027,
|
|
"num_tokens": 2439643.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.437968683242798,
|
|
"epoch": 0.10703918722786647,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999970182343782,
|
|
"loss": 6.3961,
|
|
"mean_token_accuracy": 0.12295096069574356,
|
|
"num_tokens": 2450691.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.316388273239136,
|
|
"epoch": 0.10749274310595065,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999968493291638,
|
|
"loss": 6.3304,
|
|
"mean_token_accuracy": 0.12266101613640785,
|
|
"num_tokens": 2460706.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.174196100234985,
|
|
"epoch": 0.10794629898403484,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999966757709573,
|
|
"loss": 6.2314,
|
|
"mean_token_accuracy": 0.12887799739837646,
|
|
"num_tokens": 2470947.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.283685493469238,
|
|
"epoch": 0.10839985486211902,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999964975597622,
|
|
"loss": 6.1927,
|
|
"mean_token_accuracy": 0.13100447580218316,
|
|
"num_tokens": 2481132.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.299878740310669,
|
|
"epoch": 0.10885341074020319,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999963146955821,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.12988563030958175,
|
|
"num_tokens": 2491701.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.244841003417969,
|
|
"epoch": 0.10930696661828737,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499996127178421,
|
|
"loss": 6.313,
|
|
"mean_token_accuracy": 0.12518261447548867,
|
|
"num_tokens": 2502360.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.283074140548706,
|
|
"epoch": 0.10976052249637155,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999959350082825,
|
|
"loss": 6.1874,
|
|
"mean_token_accuracy": 0.12541429623961448,
|
|
"num_tokens": 2512140.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.323525142669678,
|
|
"epoch": 0.11021407837445574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999957381851709,
|
|
"loss": 6.3119,
|
|
"mean_token_accuracy": 0.12578000873327255,
|
|
"num_tokens": 2522721.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.276627159118652,
|
|
"epoch": 0.1106676342525399,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999955367090901,
|
|
"loss": 6.177,
|
|
"mean_token_accuracy": 0.13011879548430444,
|
|
"num_tokens": 2531786.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.302189302444458,
|
|
"epoch": 0.11112119013062409,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999953305800441,
|
|
"loss": 6.2937,
|
|
"mean_token_accuracy": 0.12109724506735801,
|
|
"num_tokens": 2542895.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.235093212127685,
|
|
"epoch": 0.11157474600870827,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999951197980374,
|
|
"loss": 6.2842,
|
|
"mean_token_accuracy": 0.12432139739394188,
|
|
"num_tokens": 2554120.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.333096551895141,
|
|
"epoch": 0.11202830188679246,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999949043630744,
|
|
"loss": 6.3243,
|
|
"mean_token_accuracy": 0.12348744869232178,
|
|
"num_tokens": 2563935.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.225638771057129,
|
|
"epoch": 0.11248185776487664,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999946842751593,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.12366029843688012,
|
|
"num_tokens": 2574465.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.264844942092895,
|
|
"epoch": 0.11293541364296081,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999944595342968,
|
|
"loss": 6.1886,
|
|
"mean_token_accuracy": 0.13071749806404115,
|
|
"num_tokens": 2584694.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.227580261230469,
|
|
"epoch": 0.11338896952104499,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999942301404916,
|
|
"loss": 6.1615,
|
|
"mean_token_accuracy": 0.1314219854772091,
|
|
"num_tokens": 2594540.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.110536909103393,
|
|
"epoch": 0.11384252539912917,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999939960937484,
|
|
"loss": 6.103,
|
|
"mean_token_accuracy": 0.13548171445727347,
|
|
"num_tokens": 2604896.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.294047069549561,
|
|
"epoch": 0.11429608127721336,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999937573940721,
|
|
"loss": 6.2735,
|
|
"mean_token_accuracy": 0.1363769695162773,
|
|
"num_tokens": 2614143.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.137121486663818,
|
|
"epoch": 0.11474963715529753,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999935140414674,
|
|
"loss": 6.18,
|
|
"mean_token_accuracy": 0.12688928544521333,
|
|
"num_tokens": 2623999.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.380985927581787,
|
|
"epoch": 0.11520319303338171,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999932660359395,
|
|
"loss": 6.3721,
|
|
"mean_token_accuracy": 0.12538434714078903,
|
|
"num_tokens": 2636208.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.249299001693726,
|
|
"epoch": 0.11565674891146589,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999930133774936,
|
|
"loss": 6.2537,
|
|
"mean_token_accuracy": 0.13482384383678436,
|
|
"num_tokens": 2645854.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.322882556915284,
|
|
"epoch": 0.11611030478955008,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999927560661348,
|
|
"loss": 6.2406,
|
|
"mean_token_accuracy": 0.1355570986866951,
|
|
"num_tokens": 2655877.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.303021097183228,
|
|
"epoch": 0.11656386066763426,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999924941018685,
|
|
"loss": 6.257,
|
|
"mean_token_accuracy": 0.12821097895503045,
|
|
"num_tokens": 2666157.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.149188089370727,
|
|
"epoch": 0.11701741654571843,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999922274847,
|
|
"loss": 6.1708,
|
|
"mean_token_accuracy": 0.13158801943063736,
|
|
"num_tokens": 2676647.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.261129522323609,
|
|
"epoch": 0.11747097242380261,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499991956214635,
|
|
"loss": 6.2095,
|
|
"mean_token_accuracy": 0.14001647382974625,
|
|
"num_tokens": 2686417.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.232670593261719,
|
|
"epoch": 0.1179245283018868,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499991680291679,
|
|
"loss": 6.2224,
|
|
"mean_token_accuracy": 0.1243120551109314,
|
|
"num_tokens": 2697540.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.192728900909424,
|
|
"epoch": 0.11837808417997098,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999913997158378,
|
|
"loss": 6.2607,
|
|
"mean_token_accuracy": 0.12081601396203041,
|
|
"num_tokens": 2709397.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.286089134216309,
|
|
"epoch": 0.11883164005805515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999911144871169,
|
|
"loss": 6.2128,
|
|
"mean_token_accuracy": 0.12598777934908867,
|
|
"num_tokens": 2720430.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.178103065490722,
|
|
"epoch": 0.11928519593613933,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999908246055226,
|
|
"loss": 6.1701,
|
|
"mean_token_accuracy": 0.12547316178679466,
|
|
"num_tokens": 2730648.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.184869623184204,
|
|
"epoch": 0.11973875181422351,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999905300710607,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.1283143639564514,
|
|
"num_tokens": 2739979.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.296625852584839,
|
|
"epoch": 0.1201923076923077,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999902308837373,
|
|
"loss": 6.2786,
|
|
"mean_token_accuracy": 0.12489124983549119,
|
|
"num_tokens": 2750329.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.146040248870849,
|
|
"epoch": 0.12064586357039188,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999899270435584,
|
|
"loss": 6.1522,
|
|
"mean_token_accuracy": 0.13480892404913902,
|
|
"num_tokens": 2760535.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.269543600082398,
|
|
"epoch": 0.12109941944847605,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999896185505307,
|
|
"loss": 6.1902,
|
|
"mean_token_accuracy": 0.12844027504324912,
|
|
"num_tokens": 2770470.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.204631614685058,
|
|
"epoch": 0.12155297532656023,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999893054046603,
|
|
"loss": 6.2205,
|
|
"mean_token_accuracy": 0.12515390738844873,
|
|
"num_tokens": 2781506.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.161186933517456,
|
|
"epoch": 0.12200653120464441,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999889876059537,
|
|
"loss": 6.0858,
|
|
"mean_token_accuracy": 0.13881843388080597,
|
|
"num_tokens": 2791245.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.227107095718384,
|
|
"epoch": 0.1224600870827286,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999886651544176,
|
|
"loss": 6.1082,
|
|
"mean_token_accuracy": 0.13308778330683707,
|
|
"num_tokens": 2801680.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.124445152282715,
|
|
"epoch": 0.12291364296081277,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999883380500584,
|
|
"loss": 6.1789,
|
|
"mean_token_accuracy": 0.1382739506661892,
|
|
"num_tokens": 2812805.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.302854251861572,
|
|
"epoch": 0.12336719883889695,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999880062928831,
|
|
"loss": 6.2143,
|
|
"mean_token_accuracy": 0.1299120791256428,
|
|
"num_tokens": 2822834.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.152606868743897,
|
|
"epoch": 0.12382075471698113,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999876698828985,
|
|
"loss": 6.1596,
|
|
"mean_token_accuracy": 0.13407627418637275,
|
|
"num_tokens": 2832312.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.221649599075318,
|
|
"epoch": 0.12427431059506532,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999873288201116,
|
|
"loss": 6.1793,
|
|
"mean_token_accuracy": 0.1410585030913353,
|
|
"num_tokens": 2842998.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.259373044967651,
|
|
"epoch": 0.1247278664731495,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004999869831045294,
|
|
"loss": 6.1999,
|
|
"mean_token_accuracy": 0.13460145518183708,
|
|
"num_tokens": 2854218.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.121993970870972,
|
|
"epoch": 0.12518142235123367,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999866327361589,
|
|
"loss": 6.096,
|
|
"mean_token_accuracy": 0.13676728904247284,
|
|
"num_tokens": 2864484.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.224773120880127,
|
|
"epoch": 0.12563497822931785,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999862777150077,
|
|
"loss": 6.2064,
|
|
"mean_token_accuracy": 0.1293405920267105,
|
|
"num_tokens": 2873800.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.2337018013000485,
|
|
"epoch": 0.12608853410740203,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999859180410829,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.12882139533758163,
|
|
"num_tokens": 2884247.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.138038253784179,
|
|
"epoch": 0.12654208998548622,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999855537143919,
|
|
"loss": 6.1086,
|
|
"mean_token_accuracy": 0.13381363451480865,
|
|
"num_tokens": 2894739.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.129825210571289,
|
|
"epoch": 0.1269956458635704,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999851847349425,
|
|
"loss": 6.1729,
|
|
"mean_token_accuracy": 0.1333797574043274,
|
|
"num_tokens": 2904376.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.258524942398071,
|
|
"epoch": 0.12744920174165458,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999848111027419,
|
|
"loss": 6.2175,
|
|
"mean_token_accuracy": 0.1292863242328167,
|
|
"num_tokens": 2914304.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.214796018600464,
|
|
"epoch": 0.12790275761973874,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999844328177983,
|
|
"loss": 6.1028,
|
|
"mean_token_accuracy": 0.13051475137472152,
|
|
"num_tokens": 2924400.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.328621816635132,
|
|
"epoch": 0.12835631349782292,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999840498801191,
|
|
"loss": 6.3489,
|
|
"mean_token_accuracy": 0.1303907461464405,
|
|
"num_tokens": 2935040.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.081346130371093,
|
|
"epoch": 0.1288098693759071,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999836622897126,
|
|
"loss": 6.1337,
|
|
"mean_token_accuracy": 0.13372014090418816,
|
|
"num_tokens": 2945536.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.166437578201294,
|
|
"epoch": 0.1292634252539913,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999832700465865,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.13463784158229827,
|
|
"num_tokens": 2954969.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.1763997077941895,
|
|
"epoch": 0.12971698113207547,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999828731507491,
|
|
"loss": 6.1646,
|
|
"mean_token_accuracy": 0.12978584319353104,
|
|
"num_tokens": 2966218.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.1608034610748295,
|
|
"epoch": 0.13017053701015965,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999824716022085,
|
|
"loss": 6.2042,
|
|
"mean_token_accuracy": 0.12838013991713523,
|
|
"num_tokens": 2976640.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.1678853034973145,
|
|
"epoch": 0.13062409288824384,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999820654009731,
|
|
"loss": 6.1584,
|
|
"mean_token_accuracy": 0.13406179323792458,
|
|
"num_tokens": 2985883.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.187309789657593,
|
|
"epoch": 0.13107764876632802,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999816545470513,
|
|
"loss": 6.1702,
|
|
"mean_token_accuracy": 0.1267956852912903,
|
|
"num_tokens": 2996695.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.194827270507813,
|
|
"epoch": 0.1315312046444122,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999812390404514,
|
|
"loss": 6.1609,
|
|
"mean_token_accuracy": 0.13191465437412261,
|
|
"num_tokens": 3007500.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.0264750003814695,
|
|
"epoch": 0.13198476052249636,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999808188811823,
|
|
"loss": 6.0252,
|
|
"mean_token_accuracy": 0.13417760878801346,
|
|
"num_tokens": 3017299.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.300446462631226,
|
|
"epoch": 0.13243831640058054,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999803940692524,
|
|
"loss": 6.3135,
|
|
"mean_token_accuracy": 0.12158919349312783,
|
|
"num_tokens": 3028389.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.197498369216919,
|
|
"epoch": 0.13289187227866472,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999799646046707,
|
|
"loss": 6.1173,
|
|
"mean_token_accuracy": 0.13784717693924903,
|
|
"num_tokens": 3038883.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.177143383026123,
|
|
"epoch": 0.1333454281567489,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999795304874461,
|
|
"loss": 6.2414,
|
|
"mean_token_accuracy": 0.13582047894597055,
|
|
"num_tokens": 3049904.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.133323240280151,
|
|
"epoch": 0.1337989840348331,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999790917175873,
|
|
"loss": 6.078,
|
|
"mean_token_accuracy": 0.13267199248075484,
|
|
"num_tokens": 3059788.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.19330358505249,
|
|
"epoch": 0.13425253991291727,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999786482951036,
|
|
"loss": 6.0752,
|
|
"mean_token_accuracy": 0.1339847445487976,
|
|
"num_tokens": 3070413.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.126073980331421,
|
|
"epoch": 0.13470609579100146,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999782002200041,
|
|
"loss": 6.1987,
|
|
"mean_token_accuracy": 0.1323849603533745,
|
|
"num_tokens": 3081093.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.15864782333374,
|
|
"epoch": 0.13515965166908564,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999777474922982,
|
|
"loss": 6.124,
|
|
"mean_token_accuracy": 0.12964514642953873,
|
|
"num_tokens": 3090594.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.221482515335083,
|
|
"epoch": 0.13561320754716982,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999772901119951,
|
|
"loss": 6.2361,
|
|
"mean_token_accuracy": 0.1309862792491913,
|
|
"num_tokens": 3101061.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.122462558746338,
|
|
"epoch": 0.13606676342525398,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999768280791043,
|
|
"loss": 6.1558,
|
|
"mean_token_accuracy": 0.13689188212156295,
|
|
"num_tokens": 3111715.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.163290500640869,
|
|
"epoch": 0.13652031930333816,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999763613936352,
|
|
"loss": 6.0644,
|
|
"mean_token_accuracy": 0.13736301958560942,
|
|
"num_tokens": 3121378.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.096087884902954,
|
|
"epoch": 0.13697387518142234,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999758900555979,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.1399257391691208,
|
|
"num_tokens": 3131229.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.0675342082977295,
|
|
"epoch": 0.13742743105950653,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999754140650017,
|
|
"loss": 6.1017,
|
|
"mean_token_accuracy": 0.13268654868006707,
|
|
"num_tokens": 3140859.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.186848449707031,
|
|
"epoch": 0.1378809869375907,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999749334218567,
|
|
"loss": 6.1,
|
|
"mean_token_accuracy": 0.13572516441345214,
|
|
"num_tokens": 3151692.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.060773086547852,
|
|
"epoch": 0.1383345428156749,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999744481261726,
|
|
"loss": 6.1658,
|
|
"mean_token_accuracy": 0.1306878425180912,
|
|
"num_tokens": 3161879.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.109863138198852,
|
|
"epoch": 0.13878809869375908,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999739581779597,
|
|
"loss": 6.0243,
|
|
"mean_token_accuracy": 0.1430966079235077,
|
|
"num_tokens": 3171282.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.160919523239135,
|
|
"epoch": 0.13924165457184326,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499973463577228,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.13672013431787491,
|
|
"num_tokens": 3181398.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.1300629615783695,
|
|
"epoch": 0.13969521044992744,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999729643239877,
|
|
"loss": 6.2069,
|
|
"mean_token_accuracy": 0.1347118280827999,
|
|
"num_tokens": 3191431.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.1940147399902346,
|
|
"epoch": 0.1401487663280116,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999724604182492,
|
|
"loss": 6.2112,
|
|
"mean_token_accuracy": 0.12552011385560036,
|
|
"num_tokens": 3202147.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.215757179260254,
|
|
"epoch": 0.14060232220609578,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999719518600229,
|
|
"loss": 6.069,
|
|
"mean_token_accuracy": 0.13700326383113862,
|
|
"num_tokens": 3212428.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.07675952911377,
|
|
"epoch": 0.14105587808417996,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999714386493192,
|
|
"loss": 6.1366,
|
|
"mean_token_accuracy": 0.1377066530287266,
|
|
"num_tokens": 3222099.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.184482622146606,
|
|
"epoch": 0.14150943396226415,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999709207861489,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.13630361706018448,
|
|
"num_tokens": 3232079.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.0271689891815186,
|
|
"epoch": 0.14196298984034833,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999703982705227,
|
|
"loss": 6.0002,
|
|
"mean_token_accuracy": 0.14721214026212692,
|
|
"num_tokens": 3241762.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.100229215621948,
|
|
"epoch": 0.1424165457184325,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999698711024513,
|
|
"loss": 6.0699,
|
|
"mean_token_accuracy": 0.13954419642686844,
|
|
"num_tokens": 3252571.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.0743285655975345,
|
|
"epoch": 0.1428701015965167,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999693392819456,
|
|
"loss": 6.1225,
|
|
"mean_token_accuracy": 0.13330407217144966,
|
|
"num_tokens": 3263542.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.2108501434326175,
|
|
"epoch": 0.14332365747460088,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999688028090166,
|
|
"loss": 6.1965,
|
|
"mean_token_accuracy": 0.13395313844084739,
|
|
"num_tokens": 3273295.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.2388311386108395,
|
|
"epoch": 0.14377721335268506,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999682616836755,
|
|
"loss": 6.2142,
|
|
"mean_token_accuracy": 0.13328842967748641,
|
|
"num_tokens": 3283605.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.087570333480835,
|
|
"epoch": 0.14423076923076922,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999677159059334,
|
|
"loss": 6.0438,
|
|
"mean_token_accuracy": 0.14040226265788078,
|
|
"num_tokens": 3293837.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.992144441604614,
|
|
"epoch": 0.1446843251088534,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999671654758016,
|
|
"loss": 6.0574,
|
|
"mean_token_accuracy": 0.14208618625998498,
|
|
"num_tokens": 3304131.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.161336088180542,
|
|
"epoch": 0.14513788098693758,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004999666103932915,
|
|
"loss": 6.0925,
|
|
"mean_token_accuracy": 0.13309103175997733,
|
|
"num_tokens": 3313543.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.0388938903808596,
|
|
"epoch": 0.14559143686502177,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999660506584145,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.13285203129053116,
|
|
"num_tokens": 3324487.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.177606534957886,
|
|
"epoch": 0.14604499274310595,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999654862711823,
|
|
"loss": 6.085,
|
|
"mean_token_accuracy": 0.13585741370916365,
|
|
"num_tokens": 3335094.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.041245794296264,
|
|
"epoch": 0.14649854862119013,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999649172316065,
|
|
"loss": 6.0213,
|
|
"mean_token_accuracy": 0.13612035140395165,
|
|
"num_tokens": 3344252.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.07570447921753,
|
|
"epoch": 0.14695210449927432,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499964343539699,
|
|
"loss": 6.1063,
|
|
"mean_token_accuracy": 0.1323385626077652,
|
|
"num_tokens": 3354265.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.204560565948486,
|
|
"epoch": 0.1474056603773585,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999637651954714,
|
|
"loss": 6.2092,
|
|
"mean_token_accuracy": 0.13653515949845313,
|
|
"num_tokens": 3364616.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.1248493671417235,
|
|
"epoch": 0.14785921625544268,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999631821989358,
|
|
"loss": 6.1551,
|
|
"mean_token_accuracy": 0.13333765044808388,
|
|
"num_tokens": 3373650.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.091972589492798,
|
|
"epoch": 0.14831277213352684,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999625945501043,
|
|
"loss": 6.0473,
|
|
"mean_token_accuracy": 0.13804969042539597,
|
|
"num_tokens": 3384590.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.157991361618042,
|
|
"epoch": 0.14876632801161102,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499962002248989,
|
|
"loss": 6.0816,
|
|
"mean_token_accuracy": 0.13664070069789885,
|
|
"num_tokens": 3395616.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.1123932838439945,
|
|
"epoch": 0.1492198838896952,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999614052956024,
|
|
"loss": 6.0892,
|
|
"mean_token_accuracy": 0.13248431012034417,
|
|
"num_tokens": 3405810.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.143494653701782,
|
|
"epoch": 0.1496734397677794,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999608036899563,
|
|
"loss": 6.1237,
|
|
"mean_token_accuracy": 0.13100728020071983,
|
|
"num_tokens": 3415932.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.0603516578674315,
|
|
"epoch": 0.15012699564586357,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999601974320636,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.13310141935944558,
|
|
"num_tokens": 3425626.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.097725772857666,
|
|
"epoch": 0.15058055152394775,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999595865219367,
|
|
"loss": 6.0662,
|
|
"mean_token_accuracy": 0.1289604127407074,
|
|
"num_tokens": 3434837.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.11887493133545,
|
|
"epoch": 0.15103410740203194,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999589709595881,
|
|
"loss": 6.0818,
|
|
"mean_token_accuracy": 0.14125847369432448,
|
|
"num_tokens": 3445238.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.03086633682251,
|
|
"epoch": 0.15148766328011612,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999583507450308,
|
|
"loss": 6.0619,
|
|
"mean_token_accuracy": 0.1350873090326786,
|
|
"num_tokens": 3456738.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.022101402282715,
|
|
"epoch": 0.1519412191582003,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999577258782774,
|
|
"loss": 5.9519,
|
|
"mean_token_accuracy": 0.13770247548818587,
|
|
"num_tokens": 3466296.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.160738801956176,
|
|
"epoch": 0.15239477503628446,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499957096359341,
|
|
"loss": 6.1438,
|
|
"mean_token_accuracy": 0.13199611157178878,
|
|
"num_tokens": 3476989.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.0629199028015135,
|
|
"epoch": 0.15284833091436864,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999564621882343,
|
|
"loss": 5.9823,
|
|
"mean_token_accuracy": 0.14023435190320016,
|
|
"num_tokens": 3487050.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.138583707809448,
|
|
"epoch": 0.15330188679245282,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999558233649708,
|
|
"loss": 6.1963,
|
|
"mean_token_accuracy": 0.1306483641266823,
|
|
"num_tokens": 3497777.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.148853921890259,
|
|
"epoch": 0.153755442670537,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999551798895636,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.133428006619215,
|
|
"num_tokens": 3509066.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.038267374038696,
|
|
"epoch": 0.1542089985486212,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999545317620258,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.13769044652581214,
|
|
"num_tokens": 3519567.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.028669166564941,
|
|
"epoch": 0.15466255442670537,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999538789823711,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.14178896844387054,
|
|
"num_tokens": 3529402.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.16622405052185,
|
|
"epoch": 0.15511611030478956,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999532215506127,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.14612792134284974,
|
|
"num_tokens": 3539805.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.986016368865966,
|
|
"epoch": 0.15556966618287374,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999525594667645,
|
|
"loss": 5.9352,
|
|
"mean_token_accuracy": 0.14136730134487152,
|
|
"num_tokens": 3550477.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.952186918258667,
|
|
"epoch": 0.15602322206095792,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049995189273084,
|
|
"loss": 6.0427,
|
|
"mean_token_accuracy": 0.1397734761238098,
|
|
"num_tokens": 3560729.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.097905158996582,
|
|
"epoch": 0.15647677793904208,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499951221342853,
|
|
"loss": 6.1137,
|
|
"mean_token_accuracy": 0.12626646235585212,
|
|
"num_tokens": 3571538.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.125197029113769,
|
|
"epoch": 0.15693033381712626,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999505453028174,
|
|
"loss": 6.1197,
|
|
"mean_token_accuracy": 0.1374218739569187,
|
|
"num_tokens": 3583128.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.121435117721558,
|
|
"epoch": 0.15738388969521044,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999498646107472,
|
|
"loss": 6.0475,
|
|
"mean_token_accuracy": 0.1424655109643936,
|
|
"num_tokens": 3594358.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.065750217437744,
|
|
"epoch": 0.15783744557329463,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999491792666566,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.14380643963813783,
|
|
"num_tokens": 3604345.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.030856895446777,
|
|
"epoch": 0.1582910014513788,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999484892705597,
|
|
"loss": 6.0287,
|
|
"mean_token_accuracy": 0.13884891346096992,
|
|
"num_tokens": 3616129.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.111476278305053,
|
|
"epoch": 0.158744557329463,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999477946224705,
|
|
"loss": 6.0824,
|
|
"mean_token_accuracy": 0.13742278516292572,
|
|
"num_tokens": 3627458.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.081455039978027,
|
|
"epoch": 0.15919811320754718,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999470953224037,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.13912637010216714,
|
|
"num_tokens": 3636047.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.941955947875977,
|
|
"epoch": 0.15965166908563136,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999463913703735,
|
|
"loss": 5.956,
|
|
"mean_token_accuracy": 0.14151325970888137,
|
|
"num_tokens": 3646930.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.053501844406128,
|
|
"epoch": 0.16010522496371554,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999456827663948,
|
|
"loss": 6.0337,
|
|
"mean_token_accuracy": 0.14219933450222016,
|
|
"num_tokens": 3657279.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.029218292236328,
|
|
"epoch": 0.1605587808417997,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499944969510482,
|
|
"loss": 5.948,
|
|
"mean_token_accuracy": 0.14011043757200242,
|
|
"num_tokens": 3667070.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.026233434677124,
|
|
"epoch": 0.16101233671988388,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999442516026498,
|
|
"loss": 5.9741,
|
|
"mean_token_accuracy": 0.13762375786900521,
|
|
"num_tokens": 3677560.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.963876390457154,
|
|
"epoch": 0.16146589259796806,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999435290429133,
|
|
"loss": 5.934,
|
|
"mean_token_accuracy": 0.14428269788622855,
|
|
"num_tokens": 3686701.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.075827646255493,
|
|
"epoch": 0.16191944847605225,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999428018312872,
|
|
"loss": 6.035,
|
|
"mean_token_accuracy": 0.14326198846101762,
|
|
"num_tokens": 3696338.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.04256386756897,
|
|
"epoch": 0.16237300435413643,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999420699677867,
|
|
"loss": 6.0059,
|
|
"mean_token_accuracy": 0.141026820987463,
|
|
"num_tokens": 3705752.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.1249024868011475,
|
|
"epoch": 0.1628265602322206,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999413334524269,
|
|
"loss": 6.0907,
|
|
"mean_token_accuracy": 0.13355766385793685,
|
|
"num_tokens": 3716225.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.983501863479614,
|
|
"epoch": 0.1632801161103048,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999405922852229,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.13743126392364502,
|
|
"num_tokens": 3726593.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.018549251556396,
|
|
"epoch": 0.16373367198838898,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999398464661901,
|
|
"loss": 6.0353,
|
|
"mean_token_accuracy": 0.13529310375452042,
|
|
"num_tokens": 3737563.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.175122833251953,
|
|
"epoch": 0.16418722786647316,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999390959953441,
|
|
"loss": 6.0825,
|
|
"mean_token_accuracy": 0.1384120099246502,
|
|
"num_tokens": 3747752.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.976292610168457,
|
|
"epoch": 0.16464078374455732,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999383408727002,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.13851915821433067,
|
|
"num_tokens": 3758795.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.05274600982666,
|
|
"epoch": 0.1650943396226415,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999375810982741,
|
|
"loss": 6.0132,
|
|
"mean_token_accuracy": 0.1393853485584259,
|
|
"num_tokens": 3768690.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.971596431732178,
|
|
"epoch": 0.16554789550072568,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999368166720815,
|
|
"loss": 6.0593,
|
|
"mean_token_accuracy": 0.13606920316815377,
|
|
"num_tokens": 3779018.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.16007022857666,
|
|
"epoch": 0.16600145137880987,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999360475941382,
|
|
"loss": 5.9574,
|
|
"mean_token_accuracy": 0.14323117956519127,
|
|
"num_tokens": 3788985.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.033173227310181,
|
|
"epoch": 0.16645500725689405,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049993527386446,
|
|
"loss": 6.1029,
|
|
"mean_token_accuracy": 0.1309938281774521,
|
|
"num_tokens": 3800787.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.060845899581909,
|
|
"epoch": 0.16690856313497823,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999344954830633,
|
|
"loss": 5.9746,
|
|
"mean_token_accuracy": 0.13664656654000282,
|
|
"num_tokens": 3811381.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.05128288269043,
|
|
"epoch": 0.16736211901306242,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999337124499638,
|
|
"loss": 6.0943,
|
|
"mean_token_accuracy": 0.14225277155637742,
|
|
"num_tokens": 3822055.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.048533248901367,
|
|
"epoch": 0.1678156748911466,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999329247651777,
|
|
"loss": 6.0429,
|
|
"mean_token_accuracy": 0.13500285595655442,
|
|
"num_tokens": 3831900.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.054124593734741,
|
|
"epoch": 0.16826923076923078,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999321324287213,
|
|
"loss": 6.0071,
|
|
"mean_token_accuracy": 0.1393166773021221,
|
|
"num_tokens": 3842702.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.126334619522095,
|
|
"epoch": 0.16872278664731494,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999313354406114,
|
|
"loss": 5.9721,
|
|
"mean_token_accuracy": 0.13867918774485588,
|
|
"num_tokens": 3852690.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.936737442016602,
|
|
"epoch": 0.16917634252539912,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499930533800864,
|
|
"loss": 5.9698,
|
|
"mean_token_accuracy": 0.14831455647945405,
|
|
"num_tokens": 3863040.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.028145837783813,
|
|
"epoch": 0.1696298984034833,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999297275094958,
|
|
"loss": 6.0554,
|
|
"mean_token_accuracy": 0.13361043334007264,
|
|
"num_tokens": 3873613.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.9600602149963375,
|
|
"epoch": 0.1700834542815675,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999289165665235,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.14620799273252488,
|
|
"num_tokens": 3883936.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.9179552555084225,
|
|
"epoch": 0.17053701015965167,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999281009719639,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.14930711612105368,
|
|
"num_tokens": 3893788.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.955077457427978,
|
|
"epoch": 0.17099056603773585,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999272807258339,
|
|
"loss": 5.9045,
|
|
"mean_token_accuracy": 0.14696305319666864,
|
|
"num_tokens": 3903434.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.98124589920044,
|
|
"epoch": 0.17144412191582004,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999264558281504,
|
|
"loss": 5.9164,
|
|
"mean_token_accuracy": 0.14665744602680206,
|
|
"num_tokens": 3913476.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.882257986068725,
|
|
"epoch": 0.17189767779390422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999256262789305,
|
|
"loss": 5.8757,
|
|
"mean_token_accuracy": 0.14397282898426056,
|
|
"num_tokens": 3923301.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.017929792404175,
|
|
"epoch": 0.1723512336719884,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999247920781913,
|
|
"loss": 6.0171,
|
|
"mean_token_accuracy": 0.1397230200469494,
|
|
"num_tokens": 3933335.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.048897361755371,
|
|
"epoch": 0.17280478955007256,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999239532259502,
|
|
"loss": 6.0409,
|
|
"mean_token_accuracy": 0.13537009730935096,
|
|
"num_tokens": 3944171.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.089568996429444,
|
|
"epoch": 0.17325834542815674,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999231097222244,
|
|
"loss": 6.1116,
|
|
"mean_token_accuracy": 0.13979827240109444,
|
|
"num_tokens": 3954160.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.0698545455932615,
|
|
"epoch": 0.17371190130624092,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999222615670312,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.14813649281859398,
|
|
"num_tokens": 3964110.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.989406299591065,
|
|
"epoch": 0.1741654571843251,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999214087603885,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.13940656036138535,
|
|
"num_tokens": 3974293.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.934039068222046,
|
|
"epoch": 0.1746190130624093,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999205513023135,
|
|
"loss": 5.9553,
|
|
"mean_token_accuracy": 0.14510801061987877,
|
|
"num_tokens": 3984346.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.9414143562316895,
|
|
"epoch": 0.17507256894049347,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999196891928245,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.1501953735947609,
|
|
"num_tokens": 3992897.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.9804035186767575,
|
|
"epoch": 0.17552612481857766,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999188224319388,
|
|
"loss": 5.9295,
|
|
"mean_token_accuracy": 0.1484602600336075,
|
|
"num_tokens": 4002575.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.99068865776062,
|
|
"epoch": 0.17597968069666184,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999179510196746,
|
|
"loss": 5.9908,
|
|
"mean_token_accuracy": 0.1398739770054817,
|
|
"num_tokens": 4013752.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.032836437225342,
|
|
"epoch": 0.17643323657474602,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999170749560498,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.14885374158620834,
|
|
"num_tokens": 4023718.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.925063753128052,
|
|
"epoch": 0.17688679245283018,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999161942410827,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.1374013051390648,
|
|
"num_tokens": 4034210.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.060517311096191,
|
|
"epoch": 0.17734034833091436,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999153088747913,
|
|
"loss": 5.9787,
|
|
"mean_token_accuracy": 0.139659071713686,
|
|
"num_tokens": 4044868.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.909337139129638,
|
|
"epoch": 0.17779390420899854,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499914418857194,
|
|
"loss": 5.9873,
|
|
"mean_token_accuracy": 0.1421900287270546,
|
|
"num_tokens": 4055049.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.143319940567016,
|
|
"epoch": 0.17824746008708273,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999135241883092,
|
|
"loss": 6.0254,
|
|
"mean_token_accuracy": 0.14073289632797242,
|
|
"num_tokens": 4065889.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.994856882095337,
|
|
"epoch": 0.1787010159651669,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999126248681555,
|
|
"loss": 6.0474,
|
|
"mean_token_accuracy": 0.13780821710824967,
|
|
"num_tokens": 4077288.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.0060615062713625,
|
|
"epoch": 0.1791545718432511,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999117208967513,
|
|
"loss": 5.9939,
|
|
"mean_token_accuracy": 0.14116482213139533,
|
|
"num_tokens": 4087402.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.124054670333862,
|
|
"epoch": 0.17960812772133528,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999108122741154,
|
|
"loss": 6.0457,
|
|
"mean_token_accuracy": 0.13824116289615632,
|
|
"num_tokens": 4098150.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.931825828552246,
|
|
"epoch": 0.18006168359941946,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999098990002666,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.14494443386793138,
|
|
"num_tokens": 4108134.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.072109079360962,
|
|
"epoch": 0.18051523947750364,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999089810752237,
|
|
"loss": 6.0357,
|
|
"mean_token_accuracy": 0.13650458827614784,
|
|
"num_tokens": 4118251.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.921803188323975,
|
|
"epoch": 0.1809687953555878,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499908058499006,
|
|
"loss": 5.8887,
|
|
"mean_token_accuracy": 0.1494055435061455,
|
|
"num_tokens": 4129228.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.943948698043823,
|
|
"epoch": 0.18142235123367198,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999071312716321,
|
|
"loss": 5.9474,
|
|
"mean_token_accuracy": 0.14696409404277802,
|
|
"num_tokens": 4139391.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.006927824020385,
|
|
"epoch": 0.18187590711175616,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999061993931215,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.14896611645817756,
|
|
"num_tokens": 4148891.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.163501930236817,
|
|
"epoch": 0.18232946298984035,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999052628634934,
|
|
"loss": 6.2293,
|
|
"mean_token_accuracy": 0.13529689162969588,
|
|
"num_tokens": 4159551.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.137354469299316,
|
|
"epoch": 0.18278301886792453,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999043216827671,
|
|
"loss": 6.0245,
|
|
"mean_token_accuracy": 0.13915295749902726,
|
|
"num_tokens": 4170055.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.894563341140747,
|
|
"epoch": 0.1832365747460087,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999033758509621,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.1426935002207756,
|
|
"num_tokens": 4180767.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.976743268966675,
|
|
"epoch": 0.1836901306240929,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499902425368098,
|
|
"loss": 6.0046,
|
|
"mean_token_accuracy": 0.14720579907298087,
|
|
"num_tokens": 4190654.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.0072839736938475,
|
|
"epoch": 0.18414368650217708,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999014702341944,
|
|
"loss": 5.9162,
|
|
"mean_token_accuracy": 0.14252835661172866,
|
|
"num_tokens": 4200753.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.982507371902466,
|
|
"epoch": 0.18459724238026126,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999005104492712,
|
|
"loss": 6.0081,
|
|
"mean_token_accuracy": 0.14058929979801177,
|
|
"num_tokens": 4210994.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.036164665222168,
|
|
"epoch": 0.18505079825834542,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998995460133481,
|
|
"loss": 5.9517,
|
|
"mean_token_accuracy": 0.14202935472130776,
|
|
"num_tokens": 4220883.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.995604372024536,
|
|
"epoch": 0.1855043541364296,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004998985769264451,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.1352172464132309,
|
|
"num_tokens": 4231269.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.994415187835694,
|
|
"epoch": 0.18595791001451378,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998976031885821,
|
|
"loss": 5.9821,
|
|
"mean_token_accuracy": 0.13850782588124275,
|
|
"num_tokens": 4241559.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.946982669830322,
|
|
"epoch": 0.18641146589259797,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998966247997794,
|
|
"loss": 5.8821,
|
|
"mean_token_accuracy": 0.14087381660938264,
|
|
"num_tokens": 4250870.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.9092240810394285,
|
|
"epoch": 0.18686502177068215,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998956417600572,
|
|
"loss": 5.8321,
|
|
"mean_token_accuracy": 0.14701732099056244,
|
|
"num_tokens": 4260848.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.90106840133667,
|
|
"epoch": 0.18731857764876633,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998946540694358,
|
|
"loss": 5.9497,
|
|
"mean_token_accuracy": 0.14662184566259384,
|
|
"num_tokens": 4270973.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.0752662181854244,
|
|
"epoch": 0.18777213352685052,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998936617279357,
|
|
"loss": 6.0441,
|
|
"mean_token_accuracy": 0.13860629945993425,
|
|
"num_tokens": 4281211.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.913724660873413,
|
|
"epoch": 0.1882256894049347,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998926647355773,
|
|
"loss": 5.903,
|
|
"mean_token_accuracy": 0.14046634137630462,
|
|
"num_tokens": 4291425.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.071384477615356,
|
|
"epoch": 0.18867924528301888,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998916630923813,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.14140329733490944,
|
|
"num_tokens": 4301079.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.993822479248047,
|
|
"epoch": 0.18913280116110304,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998906567983685,
|
|
"loss": 5.9682,
|
|
"mean_token_accuracy": 0.14236864894628526,
|
|
"num_tokens": 4312374.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.950992774963379,
|
|
"epoch": 0.18958635703918722,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998896458535595,
|
|
"loss": 5.8985,
|
|
"mean_token_accuracy": 0.14630423933267594,
|
|
"num_tokens": 4322810.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.95527663230896,
|
|
"epoch": 0.1900399129172714,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998886302579752,
|
|
"loss": 5.8899,
|
|
"mean_token_accuracy": 0.14624738991260527,
|
|
"num_tokens": 4332082.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.014179372787476,
|
|
"epoch": 0.19049346879535559,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499887610011637,
|
|
"loss": 5.976,
|
|
"mean_token_accuracy": 0.1419885538518429,
|
|
"num_tokens": 4342632.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.916087007522583,
|
|
"epoch": 0.19094702467343977,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998865851145656,
|
|
"loss": 5.9117,
|
|
"mean_token_accuracy": 0.14088311344385146,
|
|
"num_tokens": 4353544.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.980039072036743,
|
|
"epoch": 0.19140058055152395,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998855555667822,
|
|
"loss": 6.0379,
|
|
"mean_token_accuracy": 0.1379381775856018,
|
|
"num_tokens": 4363636.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.0455575466156,
|
|
"epoch": 0.19185413642960814,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998845213683084,
|
|
"loss": 5.9077,
|
|
"mean_token_accuracy": 0.14140428155660628,
|
|
"num_tokens": 4373672.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.835667896270752,
|
|
"epoch": 0.19230769230769232,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998834825191652,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.14386406689882278,
|
|
"num_tokens": 4383199.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.009014415740967,
|
|
"epoch": 0.1927612481857765,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998824390193743,
|
|
"loss": 5.9413,
|
|
"mean_token_accuracy": 0.14438435882329942,
|
|
"num_tokens": 4394446.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.04556131362915,
|
|
"epoch": 0.19321480406386066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998813908689573,
|
|
"loss": 5.9947,
|
|
"mean_token_accuracy": 0.14130873903632163,
|
|
"num_tokens": 4405882.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.920941781997681,
|
|
"epoch": 0.19366835994194484,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998803380679359,
|
|
"loss": 5.8482,
|
|
"mean_token_accuracy": 0.14850495457649232,
|
|
"num_tokens": 4415280.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.956070137023926,
|
|
"epoch": 0.19412191582002902,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998792806163317,
|
|
"loss": 6.0573,
|
|
"mean_token_accuracy": 0.13813181966543198,
|
|
"num_tokens": 4425755.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.9665940284729,
|
|
"epoch": 0.1945754716981132,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998782185141667,
|
|
"loss": 5.9163,
|
|
"mean_token_accuracy": 0.13927923887968063,
|
|
"num_tokens": 4436259.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.970826911926269,
|
|
"epoch": 0.1950290275761974,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998771517614629,
|
|
"loss": 5.9388,
|
|
"mean_token_accuracy": 0.13907137587666513,
|
|
"num_tokens": 4446423.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.963461065292359,
|
|
"epoch": 0.19548258345428157,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998760803582422,
|
|
"loss": 5.8887,
|
|
"mean_token_accuracy": 0.1487796500325203,
|
|
"num_tokens": 4456678.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.92654185295105,
|
|
"epoch": 0.19593613933236576,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998750043045269,
|
|
"loss": 5.8878,
|
|
"mean_token_accuracy": 0.14657580107450485,
|
|
"num_tokens": 4467031.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.977866840362549,
|
|
"epoch": 0.19638969521044994,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998739236003392,
|
|
"loss": 5.9626,
|
|
"mean_token_accuracy": 0.1362947404384613,
|
|
"num_tokens": 4477771.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.975367212295533,
|
|
"epoch": 0.1968432510885341,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998728382457014,
|
|
"loss": 5.9837,
|
|
"mean_token_accuracy": 0.1417712986469269,
|
|
"num_tokens": 4488426.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.073901844024658,
|
|
"epoch": 0.19729680696661828,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998717482406362,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.1399609178304672,
|
|
"num_tokens": 4499735.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.915829515457153,
|
|
"epoch": 0.19775036284470246,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998706535851657,
|
|
"loss": 5.9059,
|
|
"mean_token_accuracy": 0.14285302758216858,
|
|
"num_tokens": 4509500.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.927563905715942,
|
|
"epoch": 0.19820391872278664,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998695542793129,
|
|
"loss": 5.9101,
|
|
"mean_token_accuracy": 0.14308948516845704,
|
|
"num_tokens": 4520431.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.991705322265625,
|
|
"epoch": 0.19865747460087083,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998684503231003,
|
|
"loss": 6.0086,
|
|
"mean_token_accuracy": 0.14144350960850716,
|
|
"num_tokens": 4532294.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.943409013748169,
|
|
"epoch": 0.199111030478955,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499867341716551,
|
|
"loss": 5.9129,
|
|
"mean_token_accuracy": 0.14232037886977195,
|
|
"num_tokens": 4542488.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.885735511779785,
|
|
"epoch": 0.1995645863570392,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998662284596878,
|
|
"loss": 5.8553,
|
|
"mean_token_accuracy": 0.14037457183003427,
|
|
"num_tokens": 4552933.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.944642543792725,
|
|
"epoch": 0.20001814223512338,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998651105525335,
|
|
"loss": 5.846,
|
|
"mean_token_accuracy": 0.14879003316164016,
|
|
"num_tokens": 4562373.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.890647745132446,
|
|
"epoch": 0.20047169811320756,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998639879951115,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.14374665394425393,
|
|
"num_tokens": 4572715.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.039751386642456,
|
|
"epoch": 0.2009252539912917,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499862860787445,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.14138285890221597,
|
|
"num_tokens": 4582782.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.931440114974976,
|
|
"epoch": 0.2013788098693759,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998617289295571,
|
|
"loss": 5.9624,
|
|
"mean_token_accuracy": 0.1358715571463108,
|
|
"num_tokens": 4594108.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.978836011886597,
|
|
"epoch": 0.20183236574746008,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998605924214714,
|
|
"loss": 5.9241,
|
|
"mean_token_accuracy": 0.14495790153741836,
|
|
"num_tokens": 4604732.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.946112108230591,
|
|
"epoch": 0.20228592162554426,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998594512632114,
|
|
"loss": 6.0523,
|
|
"mean_token_accuracy": 0.13024092167615892,
|
|
"num_tokens": 4614998.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.972310304641724,
|
|
"epoch": 0.20273947750362845,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998583054548006,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.1418835252523422,
|
|
"num_tokens": 4624665.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.947936773300171,
|
|
"epoch": 0.20319303338171263,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998571549962628,
|
|
"loss": 5.8824,
|
|
"mean_token_accuracy": 0.14991916120052337,
|
|
"num_tokens": 4633731.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.932089471817017,
|
|
"epoch": 0.2036465892597968,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998559998876216,
|
|
"loss": 5.8978,
|
|
"mean_token_accuracy": 0.1406530499458313,
|
|
"num_tokens": 4643421.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.991897392272949,
|
|
"epoch": 0.204100145137881,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998548401289012,
|
|
"loss": 5.9815,
|
|
"mean_token_accuracy": 0.14005577862262725,
|
|
"num_tokens": 4653795.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.006911277770996,
|
|
"epoch": 0.20455370101596518,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998536757201253,
|
|
"loss": 5.9461,
|
|
"mean_token_accuracy": 0.14425258636474608,
|
|
"num_tokens": 4664840.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.921462535858154,
|
|
"epoch": 0.20500725689404933,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998525066613181,
|
|
"loss": 5.9605,
|
|
"mean_token_accuracy": 0.14682526290416717,
|
|
"num_tokens": 4675508.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.9264942646026615,
|
|
"epoch": 0.20546081277213352,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998513329525038,
|
|
"loss": 5.8727,
|
|
"mean_token_accuracy": 0.1501593768596649,
|
|
"num_tokens": 4685995.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.995488023757934,
|
|
"epoch": 0.2059143686502177,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998501545937066,
|
|
"loss": 5.9227,
|
|
"mean_token_accuracy": 0.14225359484553338,
|
|
"num_tokens": 4696659.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.867328739166259,
|
|
"epoch": 0.20636792452830188,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499848971584951,
|
|
"loss": 5.8615,
|
|
"mean_token_accuracy": 0.15242719650268555,
|
|
"num_tokens": 4706438.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.889807510375976,
|
|
"epoch": 0.20682148040638607,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998477839262611,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.1458761513233185,
|
|
"num_tokens": 4716402.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.955387878417969,
|
|
"epoch": 0.20727503628447025,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499846591617662,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.14434442222118377,
|
|
"num_tokens": 4728488.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.912747049331665,
|
|
"epoch": 0.20772859216255443,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998453946591779,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.14680054485797883,
|
|
"num_tokens": 4738693.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.982892036437988,
|
|
"epoch": 0.20818214804063861,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998441930508339,
|
|
"loss": 5.867,
|
|
"mean_token_accuracy": 0.14620437175035478,
|
|
"num_tokens": 4748895.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.956034708023071,
|
|
"epoch": 0.2086357039187228,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998429867926547,
|
|
"loss": 5.9875,
|
|
"mean_token_accuracy": 0.14012246131896972,
|
|
"num_tokens": 4760135.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.089736557006836,
|
|
"epoch": 0.20908925979680695,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998417758846651,
|
|
"loss": 6.0374,
|
|
"mean_token_accuracy": 0.14575955420732498,
|
|
"num_tokens": 4769935.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.0489821434021,
|
|
"epoch": 0.20954281567489114,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998405603268903,
|
|
"loss": 5.9447,
|
|
"mean_token_accuracy": 0.14609623178839684,
|
|
"num_tokens": 4779520.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.840287733078003,
|
|
"epoch": 0.20999637155297532,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998393401193554,
|
|
"loss": 5.8684,
|
|
"mean_token_accuracy": 0.14978107139468194,
|
|
"num_tokens": 4791256.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.842484188079834,
|
|
"epoch": 0.2104499274310595,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998381152620857,
|
|
"loss": 5.8286,
|
|
"mean_token_accuracy": 0.1479355052113533,
|
|
"num_tokens": 4801334.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.891949033737182,
|
|
"epoch": 0.21090348330914369,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998368857551067,
|
|
"loss": 5.7918,
|
|
"mean_token_accuracy": 0.15084001272916794,
|
|
"num_tokens": 4811361.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.865246343612671,
|
|
"epoch": 0.21135703918722787,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998356515984433,
|
|
"loss": 5.8649,
|
|
"mean_token_accuracy": 0.14442769065499306,
|
|
"num_tokens": 4821190.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.967099905014038,
|
|
"epoch": 0.21181059506531205,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998344127921213,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.14606177806854248,
|
|
"num_tokens": 4830694.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.83759298324585,
|
|
"epoch": 0.21226415094339623,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998331693361666,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.14482705742120744,
|
|
"num_tokens": 4841344.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.916370058059693,
|
|
"epoch": 0.21271770682148042,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998319212306046,
|
|
"loss": 5.8601,
|
|
"mean_token_accuracy": 0.14071092009544373,
|
|
"num_tokens": 4851161.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.892922449111938,
|
|
"epoch": 0.21317126269956457,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499830668475461,
|
|
"loss": 5.8446,
|
|
"mean_token_accuracy": 0.14808950796723366,
|
|
"num_tokens": 4860740.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.941983938217163,
|
|
"epoch": 0.21362481857764876,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499829411070762,
|
|
"loss": 5.8718,
|
|
"mean_token_accuracy": 0.1465384006500244,
|
|
"num_tokens": 4871733.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.912432241439819,
|
|
"epoch": 0.21407837445573294,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998281490165335,
|
|
"loss": 5.9292,
|
|
"mean_token_accuracy": 0.14041552618145942,
|
|
"num_tokens": 4883617.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.977138614654541,
|
|
"epoch": 0.21453193033381712,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998268823128016,
|
|
"loss": 5.8841,
|
|
"mean_token_accuracy": 0.14232782125473023,
|
|
"num_tokens": 4894519.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.894336938858032,
|
|
"epoch": 0.2149854862119013,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998256109595923,
|
|
"loss": 5.8185,
|
|
"mean_token_accuracy": 0.14750942587852478,
|
|
"num_tokens": 4904965.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.793227291107177,
|
|
"epoch": 0.2154390420899855,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998243349569323,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.15446996241807937,
|
|
"num_tokens": 4914618.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.894077157974243,
|
|
"epoch": 0.21589259796806967,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998230543048477,
|
|
"loss": 5.8212,
|
|
"mean_token_accuracy": 0.15240628868341446,
|
|
"num_tokens": 4924341.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.813013172149658,
|
|
"epoch": 0.21634615384615385,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499821769003365,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.14865444898605346,
|
|
"num_tokens": 4934231.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.808397579193115,
|
|
"epoch": 0.21679970972423804,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998204790525109,
|
|
"loss": 5.7992,
|
|
"mean_token_accuracy": 0.14798300564289094,
|
|
"num_tokens": 4944303.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.8492330551147464,
|
|
"epoch": 0.2172532656023222,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998191844523119,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.14911072105169296,
|
|
"num_tokens": 4954571.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.985284900665283,
|
|
"epoch": 0.21770682148040638,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499817885202795,
|
|
"loss": 5.8453,
|
|
"mean_token_accuracy": 0.14537417143583298,
|
|
"num_tokens": 4964418.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.873136949539185,
|
|
"epoch": 0.21816037735849056,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998165813039869,
|
|
"loss": 5.8541,
|
|
"mean_token_accuracy": 0.14498028308153152,
|
|
"num_tokens": 4975036.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.87366943359375,
|
|
"epoch": 0.21861393323657474,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998152727559145,
|
|
"loss": 5.9677,
|
|
"mean_token_accuracy": 0.14030904546380044,
|
|
"num_tokens": 4985272.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.023105239868164,
|
|
"epoch": 0.21906748911465893,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499813959558605,
|
|
"loss": 5.8715,
|
|
"mean_token_accuracy": 0.14627939462661743,
|
|
"num_tokens": 4995187.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.9488426685333256,
|
|
"epoch": 0.2195210449927431,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998126417120856,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.1463703356683254,
|
|
"num_tokens": 5005013.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.997941732406616,
|
|
"epoch": 0.2199746008708273,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998113192163835,
|
|
"loss": 5.9439,
|
|
"mean_token_accuracy": 0.14230974465608598,
|
|
"num_tokens": 5016789.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.901341581344605,
|
|
"epoch": 0.22042815674891147,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499809992071526,
|
|
"loss": 5.9122,
|
|
"mean_token_accuracy": 0.14620402008295058,
|
|
"num_tokens": 5026913.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.943270683288574,
|
|
"epoch": 0.22088171262699566,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998086602775406,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.14236516878008842,
|
|
"num_tokens": 5037501.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.9212024211883545,
|
|
"epoch": 0.2213352685050798,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998073238344547,
|
|
"loss": 5.8343,
|
|
"mean_token_accuracy": 0.14206503182649613,
|
|
"num_tokens": 5048478.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.894640779495239,
|
|
"epoch": 0.221788824383164,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998059827422962,
|
|
"loss": 5.8923,
|
|
"mean_token_accuracy": 0.1398580104112625,
|
|
"num_tokens": 5059118.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.949969148635864,
|
|
"epoch": 0.22224238026124818,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998046370010926,
|
|
"loss": 5.8746,
|
|
"mean_token_accuracy": 0.15106075257062912,
|
|
"num_tokens": 5070180.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.862327241897583,
|
|
"epoch": 0.22269593613933236,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998032866108718,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.14829719066619873,
|
|
"num_tokens": 5079912.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.009226226806641,
|
|
"epoch": 0.22314949201741655,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998019315716618,
|
|
"loss": 5.9424,
|
|
"mean_token_accuracy": 0.14838250279426574,
|
|
"num_tokens": 5090549.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.816465187072754,
|
|
"epoch": 0.22360304789550073,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998005718834905,
|
|
"loss": 5.7914,
|
|
"mean_token_accuracy": 0.15030866116285324,
|
|
"num_tokens": 5100880.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.939529895782471,
|
|
"epoch": 0.2240566037735849,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997992075463862,
|
|
"loss": 5.908,
|
|
"mean_token_accuracy": 0.1464825004339218,
|
|
"num_tokens": 5111796.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.948081302642822,
|
|
"epoch": 0.2245101596516691,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997978385603769,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.14777286797761918,
|
|
"num_tokens": 5123468.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.865221118927002,
|
|
"epoch": 0.22496371552975328,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997964649254911,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.15206352174282073,
|
|
"num_tokens": 5132925.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.941302299499512,
|
|
"epoch": 0.22541727140783743,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997950866417572,
|
|
"loss": 5.9058,
|
|
"mean_token_accuracy": 0.1450276717543602,
|
|
"num_tokens": 5143445.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.9101451396942135,
|
|
"epoch": 0.22587082728592162,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997937037092034,
|
|
"loss": 5.8269,
|
|
"mean_token_accuracy": 0.14438713937997819,
|
|
"num_tokens": 5153176.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.911853361129761,
|
|
"epoch": 0.2263243831640058,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997923161278587,
|
|
"loss": 5.8592,
|
|
"mean_token_accuracy": 0.1432860165834427,
|
|
"num_tokens": 5162765.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.9264219284057615,
|
|
"epoch": 0.22677793904208998,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997909238977514,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.14676568061113357,
|
|
"num_tokens": 5173390.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.89142746925354,
|
|
"epoch": 0.22723149492017417,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997895270189108,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.14164483100175856,
|
|
"num_tokens": 5184212.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.806804370880127,
|
|
"epoch": 0.22768505079825835,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997881254913653,
|
|
"loss": 5.8189,
|
|
"mean_token_accuracy": 0.14264959916472436,
|
|
"num_tokens": 5194311.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.885697603225708,
|
|
"epoch": 0.22813860667634253,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997867193151441,
|
|
"loss": 5.8002,
|
|
"mean_token_accuracy": 0.1477848395705223,
|
|
"num_tokens": 5204708.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.83394422531128,
|
|
"epoch": 0.22859216255442671,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997853084902763,
|
|
"loss": 5.7834,
|
|
"mean_token_accuracy": 0.14696393460035323,
|
|
"num_tokens": 5214566.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.841207504272461,
|
|
"epoch": 0.2290457184325109,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997838930167911,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.15246393531560898,
|
|
"num_tokens": 5224762.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.891236639022827,
|
|
"epoch": 0.22949927431059505,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997824728947176,
|
|
"loss": 5.8883,
|
|
"mean_token_accuracy": 0.1477118618786335,
|
|
"num_tokens": 5235146.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.933800506591797,
|
|
"epoch": 0.22995283018867924,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997810481240853,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.14163196831941605,
|
|
"num_tokens": 5243867.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.862011909484863,
|
|
"epoch": 0.23040638606676342,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997796187049238,
|
|
"loss": 5.7643,
|
|
"mean_token_accuracy": 0.1487149715423584,
|
|
"num_tokens": 5254279.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.967965698242187,
|
|
"epoch": 0.2308599419448476,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997781846372623,
|
|
"loss": 5.8745,
|
|
"mean_token_accuracy": 0.1466490976512432,
|
|
"num_tokens": 5264769.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.881758451461792,
|
|
"epoch": 0.23131349782293179,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997767459211307,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.14295921698212624,
|
|
"num_tokens": 5274291.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.835591793060303,
|
|
"epoch": 0.23176705370101597,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997753025565587,
|
|
"loss": 5.7787,
|
|
"mean_token_accuracy": 0.150295127928257,
|
|
"num_tokens": 5284366.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.887094306945801,
|
|
"epoch": 0.23222060957910015,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997738545435763,
|
|
"loss": 5.8779,
|
|
"mean_token_accuracy": 0.14753376841545104,
|
|
"num_tokens": 5294494.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.842414712905883,
|
|
"epoch": 0.23267416545718433,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997724018822133,
|
|
"loss": 5.8907,
|
|
"mean_token_accuracy": 0.1439896434545517,
|
|
"num_tokens": 5305606.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.894366121292114,
|
|
"epoch": 0.23312772133526852,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997709445724996,
|
|
"loss": 5.8728,
|
|
"mean_token_accuracy": 0.14524707421660424,
|
|
"num_tokens": 5315677.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.966664171218872,
|
|
"epoch": 0.23358127721335267,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997694826144656,
|
|
"loss": 5.9577,
|
|
"mean_token_accuracy": 0.14343089759349822,
|
|
"num_tokens": 5326453.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.89670033454895,
|
|
"epoch": 0.23403483309143686,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997680160081414,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.1491502456367016,
|
|
"num_tokens": 5337591.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.8483922481536865,
|
|
"epoch": 0.23448838896952104,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997665447535573,
|
|
"loss": 5.8308,
|
|
"mean_token_accuracy": 0.15065386444330214,
|
|
"num_tokens": 5349400.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.93424882888794,
|
|
"epoch": 0.23494194484760522,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997650688507438,
|
|
"loss": 5.8278,
|
|
"mean_token_accuracy": 0.14633653834462165,
|
|
"num_tokens": 5359984.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.778865098953247,
|
|
"epoch": 0.2353955007256894,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997635882997314,
|
|
"loss": 5.8775,
|
|
"mean_token_accuracy": 0.15031310468912124,
|
|
"num_tokens": 5369254.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.970759725570678,
|
|
"epoch": 0.2358490566037736,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997621031005507,
|
|
"loss": 5.8118,
|
|
"mean_token_accuracy": 0.14642709940671922,
|
|
"num_tokens": 5379648.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.777373361587524,
|
|
"epoch": 0.23630261248185777,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997606132532325,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.15143134370446204,
|
|
"num_tokens": 5390321.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.845559740066529,
|
|
"epoch": 0.23675616835994195,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997591187578075,
|
|
"loss": 5.8326,
|
|
"mean_token_accuracy": 0.15119464695453644,
|
|
"num_tokens": 5401078.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.831754875183106,
|
|
"epoch": 0.23720972423802614,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997576196143067,
|
|
"loss": 5.791,
|
|
"mean_token_accuracy": 0.15142232924699783,
|
|
"num_tokens": 5411977.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.869622707366943,
|
|
"epoch": 0.2376632801161103,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499756115822761,
|
|
"loss": 5.7833,
|
|
"mean_token_accuracy": 0.14541143029928208,
|
|
"num_tokens": 5422967.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.9165294647216795,
|
|
"epoch": 0.23811683599419448,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997546073832015,
|
|
"loss": 5.8272,
|
|
"mean_token_accuracy": 0.15650950670242308,
|
|
"num_tokens": 5432260.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.808580589294434,
|
|
"epoch": 0.23857039187227866,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997530942956595,
|
|
"loss": 5.802,
|
|
"mean_token_accuracy": 0.1496383234858513,
|
|
"num_tokens": 5441706.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.923821020126343,
|
|
"epoch": 0.23902394775036284,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997515765601662,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.1539872854948044,
|
|
"num_tokens": 5452397.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.806406927108765,
|
|
"epoch": 0.23947750362844702,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997500541767531,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.15279131680727004,
|
|
"num_tokens": 5463762.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.8301534175872805,
|
|
"epoch": 0.2399310595065312,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997485271454516,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.14339211732149124,
|
|
"num_tokens": 5474622.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.869717407226562,
|
|
"epoch": 0.2403846153846154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997469954662933,
|
|
"loss": 5.812,
|
|
"mean_token_accuracy": 0.14975824058055878,
|
|
"num_tokens": 5484697.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.789428615570069,
|
|
"epoch": 0.24083817126269957,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997454591393097,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.14811063259840013,
|
|
"num_tokens": 5496433.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.954967594146728,
|
|
"epoch": 0.24129172714078376,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997439181645329,
|
|
"loss": 5.9288,
|
|
"mean_token_accuracy": 0.14460990205407143,
|
|
"num_tokens": 5507917.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.975463628768921,
|
|
"epoch": 0.2417452830188679,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997423725419945,
|
|
"loss": 5.9088,
|
|
"mean_token_accuracy": 0.14406671226024628,
|
|
"num_tokens": 5519159.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.845655298233032,
|
|
"epoch": 0.2421988388969521,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997408222717267,
|
|
"loss": 5.8678,
|
|
"mean_token_accuracy": 0.15028798580169678,
|
|
"num_tokens": 5529180.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.850816488265991,
|
|
"epoch": 0.24265239477503628,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997392673537612,
|
|
"loss": 5.7844,
|
|
"mean_token_accuracy": 0.1593550056219101,
|
|
"num_tokens": 5539363.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.830254602432251,
|
|
"epoch": 0.24310595065312046,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997377077881306,
|
|
"loss": 5.894,
|
|
"mean_token_accuracy": 0.14436824321746827,
|
|
"num_tokens": 5549841.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.904850482940674,
|
|
"epoch": 0.24355950653120464,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997361435748668,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.15043861716985701,
|
|
"num_tokens": 5560299.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.894953012466431,
|
|
"epoch": 0.24401306240928883,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997345747140024,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.14846533983945848,
|
|
"num_tokens": 5571081.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.8214860439300535,
|
|
"epoch": 0.244466618287373,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997330012055695,
|
|
"loss": 5.7963,
|
|
"mean_token_accuracy": 0.1535398468375206,
|
|
"num_tokens": 5581389.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.8494048595428465,
|
|
"epoch": 0.2449201741654572,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997314230496011,
|
|
"loss": 5.8218,
|
|
"mean_token_accuracy": 0.14826998114585876,
|
|
"num_tokens": 5592347.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.818295621871949,
|
|
"epoch": 0.24537373004354138,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997298402461296,
|
|
"loss": 5.7857,
|
|
"mean_token_accuracy": 0.1517721101641655,
|
|
"num_tokens": 5603411.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.848494911193848,
|
|
"epoch": 0.24582728592162553,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997282527951876,
|
|
"loss": 5.787,
|
|
"mean_token_accuracy": 0.15339138209819794,
|
|
"num_tokens": 5614615.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.791625308990478,
|
|
"epoch": 0.24628084179970972,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997266606968081,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.14949269592761993,
|
|
"num_tokens": 5624582.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.821265411376953,
|
|
"epoch": 0.2467343976777939,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997250639510241,
|
|
"loss": 5.7641,
|
|
"mean_token_accuracy": 0.14658788964152336,
|
|
"num_tokens": 5634310.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.86549563407898,
|
|
"epoch": 0.24718795355587808,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997234625578684,
|
|
"loss": 5.8658,
|
|
"mean_token_accuracy": 0.14597384184598922,
|
|
"num_tokens": 5644018.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.881694889068603,
|
|
"epoch": 0.24764150943396226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997218565173742,
|
|
"loss": 5.7995,
|
|
"mean_token_accuracy": 0.14841866344213486,
|
|
"num_tokens": 5653592.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.89327039718628,
|
|
"epoch": 0.24809506531204645,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004997202458295748,
|
|
"loss": 5.8404,
|
|
"mean_token_accuracy": 0.1519847184419632,
|
|
"num_tokens": 5662812.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.868380165100097,
|
|
"epoch": 0.24854862119013063,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997186304945034,
|
|
"loss": 5.8389,
|
|
"mean_token_accuracy": 0.1472091943025589,
|
|
"num_tokens": 5672939.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.809984922409058,
|
|
"epoch": 0.24900217706821481,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997170105121935,
|
|
"loss": 5.8024,
|
|
"mean_token_accuracy": 0.15122157633304595,
|
|
"num_tokens": 5683350.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.945703458786011,
|
|
"epoch": 0.249455732946299,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997153858826786,
|
|
"loss": 5.8884,
|
|
"mean_token_accuracy": 0.14479928761720656,
|
|
"num_tokens": 5694516.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.877769088745117,
|
|
"epoch": 0.24990928882438315,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997137566059922,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.1561413288116455,
|
|
"num_tokens": 5705443.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.7393638610839846,
|
|
"epoch": 0.25036284470246734,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997121226821681,
|
|
"loss": 5.8265,
|
|
"mean_token_accuracy": 0.1438466988503933,
|
|
"num_tokens": 5715933.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.926178312301635,
|
|
"epoch": 0.25081640058055155,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049971048411124,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.14209090322256088,
|
|
"num_tokens": 5726630.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.964452457427979,
|
|
"epoch": 0.2512699564586357,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997088408932418,
|
|
"loss": 5.8065,
|
|
"mean_token_accuracy": 0.1468511700630188,
|
|
"num_tokens": 5736890.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.693834829330444,
|
|
"epoch": 0.25172351233671986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997071930282076,
|
|
"loss": 5.7317,
|
|
"mean_token_accuracy": 0.1594724640250206,
|
|
"num_tokens": 5747042.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.852517175674438,
|
|
"epoch": 0.25217706821480407,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997055405161712,
|
|
"loss": 5.8433,
|
|
"mean_token_accuracy": 0.14911026507616043,
|
|
"num_tokens": 5757367.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.884478521347046,
|
|
"epoch": 0.2526306240928882,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997038833571671,
|
|
"loss": 5.9121,
|
|
"mean_token_accuracy": 0.14246488213539124,
|
|
"num_tokens": 5769557.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.899376440048218,
|
|
"epoch": 0.25308417997097243,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997022215512295,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.1549243524670601,
|
|
"num_tokens": 5780615.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.844459962844849,
|
|
"epoch": 0.2535377358490566,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997005550983925,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.14659300297498704,
|
|
"num_tokens": 5791271.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.723701143264771,
|
|
"epoch": 0.2539912917271408,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499698883998691,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.15313654989004136,
|
|
"num_tokens": 5801117.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.828806066513062,
|
|
"epoch": 0.25444484760522496,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996972082521591,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.14977902621030809,
|
|
"num_tokens": 5811696.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.825814199447632,
|
|
"epoch": 0.25489840348330917,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996955278588319,
|
|
"loss": 5.768,
|
|
"mean_token_accuracy": 0.15769439488649367,
|
|
"num_tokens": 5822207.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.754099035263062,
|
|
"epoch": 0.2553519593613933,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996938428187437,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.1581838384270668,
|
|
"num_tokens": 5831927.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.834832811355591,
|
|
"epoch": 0.2558055152394775,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996921531319297,
|
|
"loss": 5.7944,
|
|
"mean_token_accuracy": 0.1462201587855816,
|
|
"num_tokens": 5842093.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.81879677772522,
|
|
"epoch": 0.2562590711175617,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996904587984246,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.15955326408147813,
|
|
"num_tokens": 5850551.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.7429585456848145,
|
|
"epoch": 0.25671262699564584,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996887598182636,
|
|
"loss": 5.7179,
|
|
"mean_token_accuracy": 0.15299306213855743,
|
|
"num_tokens": 5860651.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.741921520233154,
|
|
"epoch": 0.25716618287373005,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996870561914819,
|
|
"loss": 5.7073,
|
|
"mean_token_accuracy": 0.15380395650863649,
|
|
"num_tokens": 5871500.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.753065347671509,
|
|
"epoch": 0.2576197387518142,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996853479181145,
|
|
"loss": 5.7024,
|
|
"mean_token_accuracy": 0.14877581000328063,
|
|
"num_tokens": 5881523.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.855972957611084,
|
|
"epoch": 0.2580732946298984,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996836349981969,
|
|
"loss": 5.8495,
|
|
"mean_token_accuracy": 0.14823734387755394,
|
|
"num_tokens": 5891162.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.766469144821167,
|
|
"epoch": 0.2585268505079826,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996819174317645,
|
|
"loss": 5.7406,
|
|
"mean_token_accuracy": 0.15299083068966865,
|
|
"num_tokens": 5901818.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.832020998001099,
|
|
"epoch": 0.2589804063860668,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996801952188528,
|
|
"loss": 5.841,
|
|
"mean_token_accuracy": 0.1450772315263748,
|
|
"num_tokens": 5913889.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.846477127075195,
|
|
"epoch": 0.25943396226415094,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996784683594973,
|
|
"loss": 5.7912,
|
|
"mean_token_accuracy": 0.15060947686433793,
|
|
"num_tokens": 5923429.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.9096756935119625,
|
|
"epoch": 0.2598875181422351,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996767368537338,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.1533066600561142,
|
|
"num_tokens": 5933847.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.770804500579834,
|
|
"epoch": 0.2603410740203193,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996750007015983,
|
|
"loss": 5.7053,
|
|
"mean_token_accuracy": 0.15112933814525603,
|
|
"num_tokens": 5943874.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.81883487701416,
|
|
"epoch": 0.26079462989840346,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996732599031264,
|
|
"loss": 5.7723,
|
|
"mean_token_accuracy": 0.1524694785475731,
|
|
"num_tokens": 5953653.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.84723162651062,
|
|
"epoch": 0.2612481857764877,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996715144583543,
|
|
"loss": 5.724,
|
|
"mean_token_accuracy": 0.1565740928053856,
|
|
"num_tokens": 5964039.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.858557844161988,
|
|
"epoch": 0.26170174165457183,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499669764367318,
|
|
"loss": 5.8498,
|
|
"mean_token_accuracy": 0.14639762043952942,
|
|
"num_tokens": 5974083.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.799863529205322,
|
|
"epoch": 0.26215529753265604,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996680096300537,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.14885008633136748,
|
|
"num_tokens": 5984629.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.76010479927063,
|
|
"epoch": 0.2626088534107402,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996662502465978,
|
|
"loss": 5.6993,
|
|
"mean_token_accuracy": 0.16074687242507935,
|
|
"num_tokens": 5994295.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.767422151565552,
|
|
"epoch": 0.2630624092888244,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996644862169864,
|
|
"loss": 5.7305,
|
|
"mean_token_accuracy": 0.1524806246161461,
|
|
"num_tokens": 6004156.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.783775281906128,
|
|
"epoch": 0.26351596516690856,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996627175412563,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.15107300579547883,
|
|
"num_tokens": 6014188.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.905015087127685,
|
|
"epoch": 0.2639695210449927,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499660944219444,
|
|
"loss": 5.8832,
|
|
"mean_token_accuracy": 0.1467879518866539,
|
|
"num_tokens": 6024879.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.935989856719971,
|
|
"epoch": 0.2644230769230769,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996591662515861,
|
|
"loss": 5.936,
|
|
"mean_token_accuracy": 0.14425073117017745,
|
|
"num_tokens": 6036374.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.863274049758911,
|
|
"epoch": 0.2648766328011611,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996573836377193,
|
|
"loss": 5.7858,
|
|
"mean_token_accuracy": 0.14999294206500052,
|
|
"num_tokens": 6046432.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.885637998580933,
|
|
"epoch": 0.2653301886792453,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996555963778806,
|
|
"loss": 5.8023,
|
|
"mean_token_accuracy": 0.1489254727959633,
|
|
"num_tokens": 6056864.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.9313414096832275,
|
|
"epoch": 0.26578374455732945,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499653804472107,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.15608129501342774,
|
|
"num_tokens": 6067294.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.811369609832764,
|
|
"epoch": 0.26623730043541366,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996520079204353,
|
|
"loss": 5.8308,
|
|
"mean_token_accuracy": 0.14605820178985596,
|
|
"num_tokens": 6077587.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.876870012283325,
|
|
"epoch": 0.2666908563134978,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499650206722903,
|
|
"loss": 5.7673,
|
|
"mean_token_accuracy": 0.15060035437345504,
|
|
"num_tokens": 6089306.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.725161027908325,
|
|
"epoch": 0.267144412191582,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996484008795471,
|
|
"loss": 5.7388,
|
|
"mean_token_accuracy": 0.14864355698227882,
|
|
"num_tokens": 6099651.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.796488952636719,
|
|
"epoch": 0.2675979680696662,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499646590390405,
|
|
"loss": 5.718,
|
|
"mean_token_accuracy": 0.14930034428834915,
|
|
"num_tokens": 6110063.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.782108545303345,
|
|
"epoch": 0.26805152394775034,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996447752555142,
|
|
"loss": 5.7581,
|
|
"mean_token_accuracy": 0.15502049624919892,
|
|
"num_tokens": 6120031.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.821945476531982,
|
|
"epoch": 0.26850507982583455,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996429554749122,
|
|
"loss": 5.8167,
|
|
"mean_token_accuracy": 0.15453848391771316,
|
|
"num_tokens": 6131274.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.907453536987305,
|
|
"epoch": 0.2689586357039187,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996411310486367,
|
|
"loss": 5.8431,
|
|
"mean_token_accuracy": 0.1503222480416298,
|
|
"num_tokens": 6140878.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.831985235214233,
|
|
"epoch": 0.2694121915820029,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996393019767253,
|
|
"loss": 5.8372,
|
|
"mean_token_accuracy": 0.1460697442293167,
|
|
"num_tokens": 6152229.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.816186428070068,
|
|
"epoch": 0.26986574746008707,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996374682592158,
|
|
"loss": 5.731,
|
|
"mean_token_accuracy": 0.15502249598503112,
|
|
"num_tokens": 6162311.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.855098247528076,
|
|
"epoch": 0.2703193033381713,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996356298961463,
|
|
"loss": 5.8514,
|
|
"mean_token_accuracy": 0.14927736073732376,
|
|
"num_tokens": 6172806.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.843709278106689,
|
|
"epoch": 0.27077285921625543,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996337868875549,
|
|
"loss": 5.803,
|
|
"mean_token_accuracy": 0.15235266238451003,
|
|
"num_tokens": 6183479.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.852834177017212,
|
|
"epoch": 0.27122641509433965,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996319392334792,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.14965162798762321,
|
|
"num_tokens": 6194201.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.759162425994873,
|
|
"epoch": 0.2716799709724238,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499630086933958,
|
|
"loss": 5.7323,
|
|
"mean_token_accuracy": 0.14620673805475234,
|
|
"num_tokens": 6204774.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.8088103294372555,
|
|
"epoch": 0.27213352685050796,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996282299890292,
|
|
"loss": 5.7233,
|
|
"mean_token_accuracy": 0.14723710864782333,
|
|
"num_tokens": 6215056.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.27213352685050796,
|
|
"eval_entropy": 5.67995113377118,
|
|
"eval_loss": 5.81314754486084,
|
|
"eval_mean_token_accuracy": 0.1565627772883592,
|
|
"eval_num_tokens": 6215056.0,
|
|
"eval_runtime": 26.5641,
|
|
"eval_samples_per_second": 1331.12,
|
|
"eval_steps_per_second": 166.39,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 110230,
|
|
"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": 9028611385344000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|